Terrace detection method, device and equipment based on terrace sensing terminal and medium

Abstract

The invention relates to a terrace detection method, device and equipment based on a terrace sensing terminal and a medium, and belongs to the technical field of terrace detection.The method comprises the steps that to-be-detected time sequence data output by a target terrace sensing terminal deployed on a target terrace are received; inputting the time sequence data to be detected into a preset data detection model to obtain offset time sequence data; aligning the offset time sequence data with a target expected data distribution sequence to obtain aligned time sequence data; wherein the target expected data distribution sequence is an expected data distribution sequence corresponding to the detection type of the target floor sensing terminal; and determining that the target floor is abnormal on the detection type under the condition that the data feature of the aligned time sequence data meets a set abnormal condition.

Description

Technical Field

[0001] This disclosure relates to the technical field of floor testing, and more specifically, to a floor testing method, apparatus, equipment, and medium based on a floor sensing terminal. Background Technology

[0002] With the widespread application of outdoor flooring, it can be used in medium to large parking lots, aircraft aprons, or railway stations and docks. Currently, to detect the temperature, strain, and impedance of the flooring, corresponding temperature sensing terminals, strain sensing terminals, and impedance sensing terminals are typically configured to measure these parameters. However, the data output by these sensing terminals has systematic errors, resulting in low accuracy. Summary of the Invention

[0003] One objective of this disclosure is to provide a new technical solution for floor detection based on a floor sensing terminal.

[0004] According to a first aspect of this disclosure, a method for detecting floor level based on a floor level sensor terminal is provided, the method comprising: Receive the timing data to be detected from the target ground sensing terminal deployed on the target ground; The time series data to be detected is input into a preset data detection model to obtain offset time series data; The offset time series data is aligned with the target expected data distribution sequence to obtain aligned time series data; wherein, the target expected data distribution sequence is the expected data distribution sequence corresponding to the detection type of the target ground sensing terminal; If the data characteristics of the aligned time series data meet the set abnormal conditions, it is determined that the target ground surface has an anomaly in the detection type.

[0005] Optionally, the data detection model includes a feature extraction branch and a data processing branch; the data detection model is a data detection model adjusted based on model training parameters; the step of inputting the time series data to be detected into the preset data detection model to obtain offset time series data includes: The temporal features of the time series data to be detected are extracted through the feature extraction branch. The time-series features are processed through the data processing branch to obtain offset time-series data.

[0006] Optionally, the method further includes: Obtain the training sample set; The data detection model is trained using the training samples in the training sample set to obtain the trained data detection model.

[0007] Optionally, training the data detection model using training samples from the training sample set to obtain the trained data detection model includes: The training samples in the training sample set are input into a preset first clustering model to obtain the first cluster set; The training samples in the training sample set are input into a preset second clustering model to obtain a second cluster set; Determine the overlapping set and the individual set of the first cluster set and the second cluster set; Construct an association attribute matrix based on the overlapping set and the individual set; Based on the association attribute matrix, the sample identifier of the training sample is set to obtain the detection result; Determine the amount of labeling error between the detection result and the prediction result for the training sample; Based on the identified error, generate model training and adjustment parameters; The adjusted parameters are obtained by training the model to obtain the data detection model.

[0008] Optionally, the detection result represents a first training sample with a clustering label and a second training sample with an inferred label in the training sample set; before determining the labeling error between the detection result and the prediction result for the training sample, the method further includes: The probability parameters are determined using the presumed identifier of the second training sample; Determining the amount of labeling error between the detection result and the prediction result for the training samples includes: The probability parameter, the detection result, and the prediction result are input into the error determination algorithm to obtain the identification error amount.

[0009] Optionally, aligning the offset time-series data with the target desired data distribution sequence to obtain aligned time-series data includes: By using a preset piecewise least squares method, the offset time series data is fitted to the target expected data distribution sequence to obtain aligned time series data.

[0010] Optionally, the detection types include temperature detection, strain detection, and impedance detection; the abnormal conditions include a first feature value of the aligned timing data of the temperature detection type exceeding a first preset threshold, a second feature value of the aligned timing data of the strain detection type exceeding a second preset threshold, and a third feature value of the aligned timing data of the impedance detection type exceeding a third preset threshold.

[0011] According to a second aspect of this disclosure, a floor detection device based on a floor sensing terminal is also provided, the device comprising: The receiving module is used to receive the timing data to be detected output by the target ground sensing terminal deployed on the target ground. The first obtaining module is used to input the time series data to be detected into a preset data detection model to obtain offset time series data; The second obtaining module is used to align the offset time series data with the target expected data distribution sequence to obtain aligned time series data; wherein, the target expected data distribution sequence is the expected data distribution sequence corresponding to the detection type of the target ground sensing terminal; The determination module is used to determine that the target ground surface is abnormal in the detection type when the data characteristics of the aligned time series data meet the set abnormal conditions.

[0012] According to a third aspect of this disclosure, a computer system is also provided, the computer system including a processor, which, when executing program instructions or code, implements the floor detection method based on a floor sensing terminal as described in the first aspect.

[0013] According to a fourth aspect of this disclosure, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to execute the above-described floor detection method based on a floor sensing terminal when it is run.

[0014] According to a fifth aspect of this disclosure, a computer program product is also provided, comprising a computer program that, when executed, causes a computer to perform the steps of the above-described floor detection method based on a floor sensing terminal.

[0015] According to a sixth aspect of this disclosure, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-described floor detection method based on a floor sensing terminal through the computer program.

[0016] One beneficial effect of this disclosure is that the floor detection method based on a floor sensing terminal provided by the present invention can receive the time-series data to be detected output by the target floor sensing terminal, and then detect the time-series data to be detected through a data detection model to obtain offset time-series data. By combining the target expected data distribution sequence, the offset time-series data is aligned to obtain aligned time-series data. Through the aligned time-series data, it can be determined that the target floor has an anomaly in terms of detection type. While preserving the trend and peak value of the spikes presented by the aligned time-series data, the interference of systematic errors is eliminated, thereby improving the accuracy of detecting floor anomalies.

[0017] Other features and advantages of the embodiments of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments of the present disclosure and, together with their description, serve to explain the principles of the embodiments of the present disclosure.

[0019] Figure 1 A schematic flowchart of a floor detection method based on a floor sensing terminal according to some embodiments is shown; Figure 2 A schematic diagram of a floor detection device based on a floor sensing terminal according to some embodiments is shown; Figure 3 A schematic diagram of the hardware structure of an electronic device according to some embodiments is shown. Detailed Implementation

[0020] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0021] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0022] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0023] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0024] 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 discussed further in subsequent figures. Example

[0025] Figure 1 This is a flowchart illustrating a floor detection method based on a floor sensing terminal according to one embodiment. The implementing entity can be, for example, a server, personal computer, mobile phone, or tablet, and is not limited thereto.

[0026] like Figure 1 As shown, the floor detection method based on the floor sensing terminal in this embodiment may include the following steps S110 to S140: Step S110: Receive the timing data to be detected from the target ground sensing terminal deployed on the target ground.

[0027] In this embodiment, the target floor sensing terminal can be at least one of a temperature sensing terminal, a strain sensing terminal, and an impedance sensing terminal. When the target floor sensing terminal is a temperature sensing terminal, the time-series data to be detected can be a floor temperature curve changing over time. When the target floor sensing terminal is a strain sensing terminal, the time-series data to be detected can be a floor deformation curve after being subjected to stress changing over time. When the target floor sensing terminal is an impedance sensing terminal, the time-series data to be detected can be a curve showing the change in impedance to current changing over time.

[0028] Step S120: Input the time series data to be detected into the preset data detection model to obtain the offset time series data.

[0029] In some embodiments, the data detection model includes a feature extraction branch and a data processing branch; step S120 may include the following steps S210 and S220: Step S210: Extract the temporal features of the time series data to be detected through the feature extraction branch.

[0030] In this embodiment, the data detection model can be a deep learning network model. The feature extraction branch of the data detection model can extract the temporal features of the time series data to be detected. For example, the time series data to be detected can be a ground temperature curve that changes over time. The feature extraction branch can extract the temperature values ​​at each time point on the ground temperature curve to obtain a time-temperature set as the temporal features of the time series data to be detected.

[0031] Step S220: Through the data processing branch, the time series features are processed to obtain offset time series data.

[0032] In this embodiment, the data processing branch can eliminate systematic errors in the timing characteristics to obtain offset timing data that separates the true signal and retains signal characteristics (such as peaks and inflection points).

[0033] Step S130: Align the offset time series data with the target expected data distribution sequence to obtain aligned time series data; wherein, the target expected data distribution sequence is the expected data distribution sequence corresponding to the detection type of the target ground sensing terminal.

[0034] In some embodiments, step S130 may include the following step S610: Step S610: The offset time series data is fitted to the target expected data distribution sequence using a preset piecewise least squares method to obtain aligned time series data.

[0035] In this embodiment, the timing data is aligned. Offset time series data , here This represents the scaling factor set for the target desired data distribution sequence. This represents the scaling factor set for the target expected data distribution sequence. The scaling and scaling factors are different for different detection types of expected data distribution sequences.

[0036] In this embodiment, by setting a target desired data distribution sequence, multiple offset time series data with different unit times can be converted into multiple offset time series data with the same unit time, so as to realize that the data characteristics of the subsequently discarded fixed-aligned time series data meet the set abnormal conditions.

[0037] Step S140: If the data characteristics of the aligned time series data meet the set abnormal conditions, determine that the target ground surface has an abnormality in the detection type.

[0038] In some embodiments, the detection types include temperature detection type, strain detection type, and impedance detection type; abnormal conditions include the temperature value of the aligned timing data for temperature detection type exceeding a first preset threshold, the slope of the characteristic spike of the aligned timing data for strain detection type exceeding a second preset threshold, and the impedance value of the aligned timing data for impedance detection type exceeding a third preset threshold.

[0039] In this embodiment, the first, second, and third threshold values ​​can be set manually and are not limited here. By setting different anomaly conditions for different detection types, anomaly detection for different detection types of the target floor can be effectively achieved.

[0040] In some embodiments, the method further includes the following steps S310 and S320: Step S310: Obtain the training sample set.

[0041] In this embodiment, the training samples may include multiple training samples.

[0042] Step S320: Train the data detection model using the training samples from the training sample set to obtain the trained data detection model.

[0043] In this embodiment, by training the data detection model, the accuracy of the offset time series data output by the data detection model can be effectively improved.

[0044] In some embodiments, step S320 may include the following steps S410-S480: Step S410: Input the training samples in the training sample set into the preset first clustering model to obtain the first cluster set.

[0045] In this embodiment, the first clustering model can be a K-medoids model, which can determine the samples with strong correlation features and the samples with weak correlation features in the training samples.

[0046] Step S420: Input the training samples in the training sample set into the preset second clustering model to obtain the second cluster set.

[0047] In this embodiment, the second clustering model can be the DBSCAN model, and the GIA model can determine the samples with strong correlation features and the samples with weak correlation features in the training samples.

[0048] Step S430: Determine the overlapping set and individual sets of the first cluster set and the second cluster set.

[0049] In this embodiment, the overlapping set is the set of the same cluster in the first cluster set and the second cluster set, and the individual set is the set of the remaining sets in the first cluster set and the second cluster set other than the set of the same cluster.

[0050] Step S440: Construct an association attribute matrix based on the overlapping set and the individual set.

[0051] In this embodiment, the association attribute matrix The expression is as follows: in, express The straight-line distance between them express True category identifier, express .

[0052] In some examples, this association attribute matrix Symmetric normalization can be performed to obtain the processed association attribute matrix. C .

[0053] In this embodiment, the processed association attribute matrix C The expression is as follows: in, It is represented as a matrix consisting of the sum of the correlations between any training sample and all training samples.

[0054] Step S450: Based on the association attribute matrix, set the sample identifier of the training samples to obtain the detection results.

[0055] In this embodiment, the set of the same cluster reflected by the association attribute matrix can correspond to a first training sample with clustering labels, which are manually labeled. The remaining sets reflected by the association attribute matrix can correspond to second training samples with inferred labels, the label matrix of which... The sample identifier of the second training sample with the presumed identifier can be determined by... This is presumed. Here, I is the identity matrix, and u represents the set diffusion coefficient.

[0056] Step S460: Determine the amount of labeling error between the detection result and the prediction result for the training samples.

[0057] Step S470: Generate model training adjustment parameters based on the amount of identification error.

[0058] Step S480: Adjust the parameters through model training to obtain the adjusted data detection model.

[0059] In this embodiment, by identifying the amount of error, the model training adjustment parameters of the optimization model are determined. By adjusting the data detection model using these model training adjustment parameters, the accuracy of the offset time series data output by the data detection model can be effectively improved.

[0060] In some embodiments, the detection result represents a first training sample with a clustering identifier and a second training sample with an inferred identifier in the training sample set; prior to step S460, the method may further include the following step S510: Step S510: Determine the probability parameters using the inferred identifier of the second training sample.

[0061] In this embodiment, probability parameter The specific expression is as follows: in, Indicates the first x A probability parameter with a presumed identifier, Indicates the first x The probability that a sample belongs to the "normal class 0" Indicates the first x The probability that a sample belongs to "malicious class 1" represents the sum of the probabilities of all classes for the i-th sample.

[0062] Based on this, step S460 may include the following step S520: Step S520: Input the probability parameters, detection results and prediction results into the error determination algorithm to obtain the identification error amount.

[0063] In this embodiment, the expression for the error determination algorithm is as follows: in, Indicates the amount of labeling error. N This indicates that the total number of training samples has been reduced by one. This represents the XOR operation. This represents the prediction result output by the data detection model.

[0064] In this embodiment, the error determination algorithm can be used to obtain the amount of identification error, so as to adjust the data detection model and effectively improve the accuracy of the data detection model. Equipment Example 1

[0065] Figure 2 This is a schematic diagram of a floor detection device based on a floor sensing terminal, according to one embodiment. Figure 2 As shown, the floor detection device 200 based on the floor sensing terminal may include: The receiving module 210 is used to receive the timing data to be detected output by the target ground sensing terminal deployed on the target ground. The first obtaining module 220 is used to input the time series data to be detected into a preset data detection model to obtain offset time series data; The second obtaining module 230 is used to align the offset time series data with the target expected data distribution sequence to obtain aligned time series data; wherein, the target expected data distribution sequence is the expected data distribution sequence corresponding to the detection type of the target ground sensing terminal; The determination module 240 is used to determine whether the target ground surface has an anomaly in the detection type when the data characteristics of the aligned time series data meet the set anomaly conditions.

[0066] In some embodiments, the first obtaining module 220 is further configured to extract the temporal features of the time series data to be detected through the feature extraction branch; and to perform data processing on the temporal features through the data processing branch to obtain the offset time series data.

[0067] In some embodiments, the floor detection device 200 based on the floor sensing terminal further includes a training module for acquiring a training sample set; and for training the data detection model using the training samples in the training sample set to obtain the trained data detection model.

[0068] In some embodiments, the training module is further configured to input training samples from the training sample set into a preset first clustering model to obtain a first cluster set; input training samples from the training sample set into a preset second clustering model to obtain a second cluster set; determine the overlapping set and the separate set of the first cluster set and the second cluster set; construct an association attribute matrix based on the overlapping set and the separate set; set the sample identifier of the training samples based on the association attribute matrix to obtain the detection result; determine the identifier error between the detection result and the prediction result of the training samples; generate model training adjustment parameters based on the identifier error; and obtain the adjusted data detection model by training the model to adjust the parameters.

[0069] In some embodiments, the floor detection device 200 based on the floor sensing terminal further includes an acquisition module for determining probability parameters through the inferred identifier of the second training sample; The training module is also used to input probability parameters, detection results, and prediction results into the error determination algorithm to obtain the identification error amount.

[0070] In some embodiments, the second obtaining module 230 is further configured to fit the offset time series data with the target expected data distribution sequence using a preset piecewise least squares method to obtain aligned time series data. Equipment Example 2

[0071] Figure 3 This is a schematic diagram of the hardware structure of an electronic device according to another embodiment.

[0072] like Figure 3 As shown, the electronic device 300 includes a processor 310 and a memory 320, the memory 320 being used to store an executable computer program, and the processor 310 being used to execute methods as described in any of the above method embodiments under the control of the computer program.

[0073] Each module of the floor detection device 200 based on the floor sensing terminal described above can be implemented by the processor 310 in this embodiment executing the computer program stored in the memory 320, or it can be implemented by other structures, which are not limited here.

[0074] This invention can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the invention.

[0075] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0076] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0077] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0078] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0079] 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 apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0080] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be 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 perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0081] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It will be known to those skilled in the art that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are equivalent.

[0082] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, and are 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 terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims

1. A method for detecting floor surface conditions based on a floor surface sensor terminal, characterized in that, The method includes: Receive the timing data to be detected from the target ground sensing terminal deployed on the target ground; The time series data to be detected is input into a preset data detection model to obtain offset time series data; The offset time series data is aligned with the target expected data distribution sequence to obtain aligned time series data; wherein, the target expected data distribution sequence is the expected data distribution sequence corresponding to the detection type of the target ground sensing terminal; If the data characteristics of the aligned time series data meet the set abnormal conditions, it is determined that the target ground surface has an anomaly in the detection type.

2. The method according to claim 1, characterized in that, The data detection model includes a feature extraction branch and a data processing branch; the data detection model is a data detection model adjusted based on model training parameters; the step of inputting the time series data to be detected into the preset data detection model to obtain offset time series data includes: The temporal features of the time series data to be detected are extracted through the feature extraction branch. The time-series features are processed through the data processing branch to obtain offset time-series data.

3. The method according to claim 2, characterized in that, The method further includes: Obtain the training sample set; The data detection model is trained using the training samples in the training sample set to obtain the trained data detection model.

4. The method according to claim 1, characterized in that, The step of training the data detection model using training samples from the training sample set to obtain the trained data detection model includes: The training samples in the training sample set are input into a preset first clustering model to obtain the first cluster set; The training samples in the training sample set are input into a preset second clustering model to obtain a second cluster set; Determine the overlapping set and the individual set of the first cluster set and the second cluster set; Construct an association attribute matrix based on the overlapping set and the individual set; Based on the association attribute matrix, the sample identifier of the training sample is set to obtain the detection result; Determine the amount of labeling error between the detection result and the prediction result for the training sample; Based on the identified error, generate model training and adjustment parameters; The adjusted parameters are obtained by training the model to obtain the data detection model.

5. The method according to claim 1, characterized in that, The detection result represents the first training sample with clustering label and the second training sample with inference label in the training sample set; Before determining the amount of labeling error between the detection result and the prediction result for the training samples, the method further includes: The probability parameters are determined using the presumed identifier of the second training sample; Determining the amount of labeling error between the detection result and the prediction result for the training samples includes: The probability parameter, the detection result, and the prediction result are input into the error determination algorithm to obtain the identification error amount.

6. The method according to claim 1, characterized in that, The step of aligning the offset time-series data with the target desired data distribution sequence to obtain aligned time-series data includes: By using a preset piecewise least squares method, the offset time series data is fitted to the target expected data distribution sequence to obtain aligned time series data.

7. The method according to claim 1, characterized in that, The detection types include temperature detection, strain detection, and impedance detection; the abnormal conditions include the temperature value of the aligned timing data of the temperature detection type exceeding a first preset threshold, the slope of the characteristic spike of the aligned timing data of the strain detection type exceeding a second preset threshold, and the impedance value of the aligned timing data of the impedance detection type exceeding a third preset threshold.

8. A floor detection device based on a floor sensing terminal, characterized in that, The device includes: The receiving module is used to receive the timing data to be detected output by the target ground sensing terminal deployed on the target ground. The first obtaining module is used to input the time series data to be detected into a preset data detection model to obtain offset time series data; The second obtaining module is used to align the offset time series data with the target expected data distribution sequence to obtain aligned time series data; wherein, the target expected data distribution sequence is the expected data distribution sequence corresponding to the detection type of the target ground sensing terminal; The determination module is used to determine that the target ground surface is abnormal in the detection type when the data characteristics of the aligned time series data meet the set abnormal conditions.

9. An electronic device, characterized in that, The system includes a memory and a processor, the memory being used to store a computer program; the processor being used to execute the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images