Data processing method and apparatus

Abstract

The application provides a data processing method and device, wherein the data processing method comprises: obtaining to-be-processed data used for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data comprises at least one to-be-processed sub-data; determining a first step counting parameter and a second step counting parameter corresponding to each to-be-processed sub-data; determining a target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data; and determining target step counting data corresponding to the to-be-processed data based on the initial step counting data and the target state corresponding to each to-be-processed sub-data. The target state corresponding to each to-be-determined data in the to-be-processed sub-data is determined, so as to eliminate the false step counting in the to-be-processed sub-data, thereby improving the accuracy of step counting on the to-be-processed data. Compared with a traditional step counting algorithm, the calculation amount is greatly reduced, and the calculation cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a data processing method. The present application also relates to a data processing device, a computing device and a computer readable storage medium. BACKGROUND

[0002] With the development of science and technology, people's living standards gradually improve, artificial intelligence is more and more deeply into people's life, and is applied to various scenes. The existing step counting algorithm is generally based on the ACC signal data of the bracelet or the mobile phone to count, and the ACC signal data is used to count the user's steps. However, due to the difference of scenes, the traditional step counting algorithm will appear miscounting steps in multiple scenes, such as brushing teeth, swinging hands, alarm clock and the like, which will make the step counting algorithm increase the number of steps for the user, resulting in poor user experience.

[0003] Therefore, how to improve the accuracy of the step counting algorithm for different scenes has become a technical problem to be solved. SUMMARY

[0004] Therefore, the embodiments of the present application provide a data processing method. The present application also relates to a data processing device, a computing device and a computer readable storage medium to solve the above problems in the prior art.

[0005] According to a first aspect of the embodiments of the present application, a data processing method is provided, comprising:

[0006] obtaining to-be-processed data for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data comprises at least one to-be-processed sub-data;

[0007] determining a first step counting parameter and a second step counting parameter corresponding to each to-be-processed sub-data;

[0008] determining a target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data;

[0009] determining target step counting data corresponding to the to-be-processed data based on the initial step counting data and the target state corresponding to each to-be-processed sub-data.

[0010] According to a second aspect of the embodiments of the present application, a data processing device is provided, comprising:

[0011] a data obtaining module configured to obtain to-be-processed data for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data comprises at least one to-be-processed sub-data;

[0012] A parameter determination module is configured to determine a first step counting parameter and a second step counting parameter corresponding to each to-be-processed sub-data.

[0013] A state determination module is configured to determine a target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data.

[0014] A data determination module is configured to determine target step counting data corresponding to the to-be-processed data based on the initial step counting data and the target state corresponding to each to-be-processed sub-data.

[0015] According to a third aspect of an embodiment of the present application, a computing device is provided, which includes a memory, a processor, and computer instructions stored in the memory and executable on the processor, and the processor implements the steps of the data processing method when executing the computer instructions.

[0016] According to a fourth aspect of an embodiment of the present application, a computer readable storage medium is provided, which stores computer instructions, and the computer instructions implement the steps of the data processing method when executed by a processor.

[0017] The data processing method provided by the present application includes: obtaining to-be-processed data for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data includes at least one to-be-processed sub-data; determining a first step counting parameter and a second step counting parameter corresponding to each to-be-processed sub-data; determining a target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data; and determining target step counting data corresponding to the to-be-processed data based on the initial step counting data and the target state corresponding to each to-be-processed sub-data.

[0018] An embodiment of the present application eliminates the false step counting in the to-be-processed sub-data by judging the target state corresponding to each to-be-determined data in the to-be-processed sub-data, thereby improving the accuracy of step counting of the to-be-processed data, and greatly reducing the calculation amount and the calculation cost compared with the traditional step counting algorithm. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is an application scenario diagram of a data processing method provided by an embodiment of the present application;

[0020] Figure 2 is a flowchart of a data processing method provided by an embodiment of the present application;

[0021] Figure 3 is a processing flowchart of a data processing method applied to an outdoor walking scenario provided by an embodiment of the present application;

[0022] Figure 4 is a structural schematic diagram of a data processing device provided by an embodiment of the present application.

[0023] Figure 5 is a structural block diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced without the specific details, and the present application should not be construed as limited to the embodiments described herein. In other instances, well-known methods, procedures, components, and networks have not been described in detail as not to unnecessarily obscure aspects of the present application.

[0025] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments of the present application. As used in one or more embodiments of the present application and the accompanying claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in one or more embodiments of the present application and the following claims, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0026] It will be understood that, although the terms first, second, etc. can be used herein to describe various information, these terms are not intended to denote a temporal or chronological order. Rather, these terms are used only as a shorthand notation. For example, in one or more embodiments of the present application, a first can be termed a second, and, similarly, a second can be termed a first, without departing from the scope of one or more embodiments of the present application. As used herein, the term "if' can be interpreted to mean "when" or "upon" or "in response to determining" taking into account the context in which the term is used.

[0027] First, the noun terms related to one or more embodiments of the present application are explained.

[0028] ACC (Accelerometer): Accelerometer sensor signal, the signal is divided into x, y, z axes.

[0029] In the current practical application, the existing step counting algorithm is based on the ACC signal data of a bracelet or a mobile phone, and the step counting algorithm is completed by counting the number of peaks and periodicity of the ACC signal data. However, in practical application, in addition to regular walking, hand swinging, alarm, tooth brushing, etc. will generate multiple peaks in the ACC signal data, and the traditional algorithm has low distinguishability for different application scenarios, thereby causing a large number of miscounting steps.

[0030] In the present application, a data processing method is provided, and the present application also relates to a data processing device, a computing device, and a computer readable storage medium, which are described in detail in the following embodiments.

[0031] Figure 1 An application scenario schematic diagram of a data processing method according to an embodiment of the present application is shown. The data processing method provided in the embodiment of the present application is applied to a terminal, which can be a notebook computer, a desktop computer, a tablet computer, a smart device, a server, a cloud server, a distributed server, etc. In the embodiments provided in the present application, the specific form of the terminal is not limited.

[0032] As shown in Figure 1 For example, the smart bracelet worn by the user collects behavior data generated by the user in the walking process, and uploads the collected to-be-processed data and initial step counting data corresponding to the to-be-processed data to a terminal for processing. First, after obtaining the to-be-processed data, the to-be-processed data is divided into at least one to-be-processed sub-data based on a preset time length, for example, the preset time length can be 2 seconds, 2.5 seconds, etc. Second, the to-be-processed sub-data divided into data segments is input into a state classification model to determine the target state corresponding to each to-be-judgment data in the to-be-processed sub-data through the output result of the state classification model, and then determine whether the initial step counting data corresponding to each to-be-judgment data exists false counting step according to the target state corresponding to each to-be-judgment data, to determine the target step counting data corresponding to each to-be-judgment data, so as to determine the target step counting data corresponding to the to-be-processed data according to the target step counting data corresponding to each to-be-judgment data.

[0033] The data processing method provided in the present application is no longer affected by the traditional step counting algorithm, and the number of peaks generated according to the ACC signal data and the corresponding periodicity are used to determine the corresponding step counting value. Instead, the ACC signal data is segmented according to a preset time length, and the segmented to-be-processed sub-data is processed. Specifically, by judging the target state corresponding to each to-be-judgment data in the to-be-processed sub-data, false counting steps existing in the to-be-processed sub-data are eliminated, thereby improving the accuracy of step counting on the to-be-processed data.

[0034] Figure 2 A flowchart of a data processing method according to an embodiment of the present application is shown, which specifically includes the following steps:

[0035] Step 202: obtaining to-be-processed data for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data includes at least one to-be-processed sub-data.

[0036] The to-be-processed data refers to data used for counting the number of steps, and can be ACC signal data, and more specifically, can be ACC 3-axis signal data. The initial step counting data refers to a step counting value corresponding to the to-be-processed data determined based on the to-be-processed data. The to-be-processed sub-data can be understood as segmented data obtained by segmenting the to-be-processed data.

[0037] For example, the to-be-processed data is ACC signal data corresponding to a user in 1 minute, the initial step counting data is a step counting value corresponding to the user in 1 minute, and the to-be-processed sub-data is segmented data obtained by segmenting the ACC signal data in 1 minute.

[0038] In actual application, the to-be-processed data can be collected by a data collection device. In order to ensure the processing efficiency of subsequent calculation and processing of the to-be-processed data, the to-be-processed data in a certain time period can be obtained in advance before the to-be-processed data is collected by the data collection device, so as to prevent the to-be-processed data from being too much and causing problems such as delay in processing and data backlog.

[0039] Specifically, in a specific embodiment provided by the present application, the to-be-processed data used for counting the number of steps is obtained, including:

[0040] The to-be-processed data used for counting the number of steps in a preset time interval is obtained based on a data collection device.

[0041] The data collection device refers to an intelligent device used for collecting the to-be-processed data, which can be an acceleration sensor, an accelerometer or other collection devices that can collect ACC signal data. The preset time interval refers to a time interval set in advance for collecting the to-be-processed data.

[0042] Taking the acceleration sensor as the data collection device and 1 minute as the preset time interval as an example, the acceleration sensor will collect ACC 3-axis signal data in 1 minute from the time of the last collection.

[0043] Further, in the process of collecting the to-be-processed data, the sampling frequency can be set according to the actual situation to sample the to-be-processed data. For example, the sampling frequency can be 25 Hz, 30 Hz, etc. When the sampling frequency is 25 Hz, the data collection device can collect 25 times of to-be-processed data in 1 second, and correspondingly, when the sampling frequency is 30 Hz, the data collection device can collect 30 times of to-be-processed data in 1 second.

[0044] In a specific embodiment provided by the present application, after obtaining the to-be-processed data used for counting the number of steps, the method further includes:

[0045] The to-be-processed data is divided into at least one to-be-processed sub-data based on a preset time length.

[0046] The preset time length refers to a time interval that is set in advance for segmenting the to-be-processed data. Specifically, the to-be-processed data can be divided according to the preset time length to obtain at least one to-be-processed sub-data corresponding to the to-be-processed data. For example, the preset time length is 2 seconds, and the to-be-processed data collected is to-be-processed data within 1 minute. Based on the preset time length, the to-be-processed data is segmented to obtain 30 data segments with a time length of 2 seconds.

[0047] It should be noted that the preset time length can be set according to actual application conditions, which is not limited in the present application.

[0048] For obtaining the initial step data corresponding to the to-be-processed data, the wave peak and wave trough data corresponding to the to-be-processed data can be detected, and the initial step data corresponding to the to-be-processed data can be determined according to the number of wave peaks and wave troughs and the change rule of acceleration data in a gait cycle. Alternatively, the to-be-processed data can be preprocessed, such as filtering, and then the wave peak and wave trough data are counted to determine the initial step data.

[0049] The data processing method provided in the present application segments the to-be-processed data according to the preset time length and processes the segmented to-be-processed sub-data.

[0050] Step 204: determining the first step parameter and the second step parameter corresponding to each to-be-processed sub-data.

[0051] The first step parameter refers to a judgment condition for determining whether the to-be-judgment data needs to be processed based on the state classification model. The second step parameter refers to a delay step parameter corresponding to the to-be-judgment data, which is used to determine the target state corresponding to the to-be-judgment data. Specifically, the method for determining the first step parameter and the second step parameter corresponding to each to-be-processed sub-data is realized by the following method:

[0052] In a specific embodiment provided in the present application, determining the first step parameter and the second step parameter corresponding to each to-be-processed sub-data comprises:

[0053] determining a target to-be-processed sub-data in the to-be-processed data, and determining at least one to-be-judgment data based on the target to-be-processed sub-data;

[0054] determining the first step parameter corresponding to each to-be-judgment data;

[0055] determining the second step parameter corresponding to each to-be-judgment data based on the first step parameter corresponding to each to-be-judgment data.

[0056] The target sub-data to be processed refers to the sub-data to be processed in the sub-data to be processed, which needs to determine the first step parameter and the second step parameter. The data to be determined refers to the data in the sub-data to be processed, which needs to determine the target state corresponding thereto. The data to be determined can be the data corresponding to each hertz.

[0057] Specifically, in the collected sub-data to be processed, at least one data to be determined is determined in the target sub-data to be processed, and the first step parameter corresponding to each data to be determined is determined. In the specific embodiments provided in the present application, the value corresponding to the first step parameter can be set to 0, 1, 2, 3, 4, and 5. Setting the first step parameter to 0, 1, 2, 3, 4, and 5 can be understood as calculating and processing the data corresponding to 5 hertz when calculating the target sub-data to be processed, rather than calculating and processing the data corresponding to each hertz based on the sampling probability. If the data corresponding to each 1 hertz is calculated and processed, the data between adjacent hertz has a high degree of coincidence and a high degree of similarity. Calculating and processing the data corresponding to each 1 hertz can be approximately repeated calculation of the same data. As a result, the processing workload is increased and the computing resources are increased. Correspondingly, since the data between adjacent hertz has a high degree of coincidence and a high degree of similarity, calculating and processing the data corresponding to each 5 hertz will not affect the processing result of the data.

[0058] As described above, when the first step parameter is 0, that is, the data corresponding to 0 hertz, the target state corresponding to the data to be determined is determined by processing the data to be determined. When the first step parameter is 1, that is, the data corresponding to 1 hertz, the target state corresponding to the data to be determined is determined by directly determining the target state corresponding to the previous data to be determined (that is, the data to be determined corresponding to the first step parameter 0) corresponding to the data to be determined. Similarly, when the first step parameter is 2, 3, and 4, the target state corresponding to the data to be determined corresponding to the first step parameter 2, 3, and 4 is determined by directly determining the target state corresponding to the data to be determined corresponding to the first step parameter 1, 2, and 3.

[0059] After determining the first step parameter corresponding to each data to be determined, the second step parameter corresponding to each data to be determined can be determined according to the first step parameter corresponding to each data to be determined. The value corresponding to the second step parameter can also be determined according to the actual application, for example, the second step parameter is set to 150.

[0060] In a specific implementation provided in the present application, the second step counting parameter corresponding to each to-be-judged data is determined based on the first step counting parameter corresponding to each to-be-judged data, including:

[0061] In the at least one to-be-judged data, a target to-be-judged data and a target first step counting parameter corresponding to the target to-be-judged data are determined.

[0062] In the case where the target first step counting parameter is zero, a target state of the target to-be-judged data is determined based on a state classification model.

[0063] Based on the target state corresponding to the target to-be-judged data, a target second step counting parameter corresponding to the target to-be-judged data is determined.

[0064] Wherein, the target to-be-judged data refers to the to-be-judged data in the at least one to-be-judged data that needs to determine the target state. The target first step counting parameter refers to the first step counting parameter corresponding to the target to-be-judged data. The target second step counting parameter refers to the second step counting parameter corresponding to the target to-be-judged data.

[0065] The target state refers to the behavior state corresponding to each to-be-judged data, and the target state is used to determine whether the initial step data corresponding to each to-be-judged data needs to be counted. Specifically, the target state includes a counting state and a non-counting state. If the target state is the counting state, it means that the initial step data corresponding to the to-be-judged data in the target state needs to be counted. If the target state is the non-counting state, it means that the initial step data corresponding to the to-be-judged data in the target state does not need to be counted.

[0066] The state classification model refers to a model used for classifying the target state corresponding to the to-be-judged data. For example, the to-be-judged data is input into the state classification model, and the target state corresponding to the to-be-judged data output by the state classification model can be obtained.

[0067] Further, in the at least one to-be-judged data, the target to-be-judged data is determined, and the target first step counting parameter corresponding to the target to-be-judged data is determined. The value of the target first step counting parameter is determined. If the target first step counting parameter is zero, the target to-be-judged data can be input into the state classification model for state classification processing, and the target state corresponding to the target to-be-judged data can be obtained. Then, the target second step counting parameter corresponding to the target to-be-judged data can be determined according to the target state corresponding to the target to-be-judged data.

[0068] Specifically, the state classification model can be obtained by training the following method:

[0069] The sample signal data and the sample state corresponding to the sample signal data are received.

[0070] inputting the sample signal data into the state classification model to obtain a predicted state of the sample signal data;

[0071] calculating a loss value of the state classification model according to the sample state and the predicted state;

[0072] adjusting a model parameter of the state classification model according to the loss value, and continuing to train the state classification model until a training stop condition is reached.

[0073] The sample signal data refers to signal data obtained in a sample signal data set and divided based on a preset time length, and is a training sample of the state classification model. The sample signal data set refers to a set composed of signal data obtained by collecting ACC signal data in different preset time intervals. The sample state refers to an actual state corresponding to the sample signal data. The predicted state refers to a state output by the state classification model when the sample signal data is input into the state classification model. The loss value refers to a difference value between the sample state and the predicted state, and is used to measure the difference between the sample state and the predicted state.

[0074] Specifically, the sample signal data can be obtained by the above-mentioned obtaining method of obtaining to-be-processed sub-data. The sample signal data is input into the state classification model, and the state classification model is used to identify the state corresponding to the sample signal data. At this time, the state classification model is a model that has not been trained, and there will be a deviation between the predicted state identified and classified and the actual sample state. Therefore, the model parameter of the state classification model needs to be adjusted accordingly. Specifically, the loss value of the state classification model is calculated according to the output predicted state and the sample state. The loss function for calculating the loss value can be a 0-1 loss function, an absolute value loss function, a square loss function, a cross-entropy loss function, and the like in actual application. In this application, preferably, the cross-entropy function is selected as the loss function for calculating the loss value, and the model parameter of the state classification model is adjusted according to the loss value. The adjusted model parameter is used to continue to train the state classification model based on the next batch of sample signal data, until the stop condition of model training is reached.

[0075] Specifically, the model training stop condition includes that the model loss value is less than a preset threshold and / or the training round reaches a preset round.

[0076] In a specific embodiment provided in the present application, taking the model loss value being less than the preset threshold as the training stop condition as an example, the preset threshold is 0.3. When the model loss value is less than 0.3, it is considered that the training of the state classification model is completed.

[0077] In another specific implementation provided in the present application, the preset training round is taken as the training stop condition, and the preset training round is 30. When the training round of the sample signal data reaches 30, it is considered that the state classification model training is completed.

[0078] In still another specific implementation provided in the present application, two training stop conditions of the preset threshold and the preset training round are set, and the loss value and the training round are monitored simultaneously. When any one of the model loss value or the training round meets the training stop condition, it is considered that the state classification model training is completed.

[0079] It should be noted that before the training of the state classification model, the sample signal data in the state scene needs to be classified, so that the number of sample signal data corresponding to each state scene is balanced. Specifically, the number of sample signal data corresponding to each state scene is balanced, that is, the number of sample signal data corresponding to the non-counting state is balanced with the number of sample signal data corresponding to the counting state, and at the same time, the sample signal data corresponding to different state scenes (such as alarm clock scene, tooth brushing scene, office scene, etc.) in the non-counting state also needs to be balanced.

[0080] The way to achieve sample signal data balance can be realized by manual classification or by training a classification weight model. The implementation of the sample signal data balance is not limited in the present application.

[0081] Further, in a specific implementation provided in the present application, the target second step counting parameter corresponding to the target to-be-judged data is determined based on the target state corresponding to the target to-be-judged data, comprising:

[0082] In the case that the target state corresponding to the target to-be-judged data is a non-counting state, the target second step counting parameter corresponding to the target to-be-judged data is set as a second step counting parameter threshold;

[0083] In the case that the target state corresponding to the target to-be-judged data is a counting state, the target second step counting parameter corresponding to the target to-be-judged data is determined according to the second step counting parameter corresponding to the previous to-be-judged data corresponding to the target to-be-judged data.

[0084] The second step parameter threshold refers to a delay step parameter set for the target to-be-judgment data when it is determined that the target state corresponding to the target to-be-judgment data is a non-counting state. Specifically, the second step parameter can be set to 150. The setting of the second step parameter threshold is not unique and can be set according to actual application. Taking the second step parameter threshold set to 150 as an example, in the case where the target state of the target to-be-judgment data is a non-counting state, the corresponding second step parameter set for the target to-be-judgment data is the second step parameter threshold. Specifically, the interruption interval time length can be 6 seconds, and if the sampling frequency corresponding to the data collection equipment for collecting the to-be-processed data is 25 Hz, then the second step parameter threshold is 25*6=150.

[0085] Specifically, the value of the second step parameter is determined according to the target state corresponding to the target to-be-judgment data. In the case where the target state corresponding to the target to-be-judgment data is a non-counting state, the second step parameter corresponding to the target to-be-judgment data is set to the second step parameter threshold. In the case where the target state corresponding to the target to-be-judgment data is a counting state, the second step parameter corresponding to the target to-be-judgment data is determined according to the second step parameter corresponding to the previous to-be-judgment data corresponding to the target to-be-judgment data. Specifically, the second step parameter corresponding to the target to-be-judgment data can be determined as the value of the second step parameter corresponding to the previous to-be-judgment data corresponding to the target to-be-judgment data minus one.

[0086] Correspondingly, in the case where the target first step parameter corresponding to the target to-be-judgment data is not zero (i.e., the target first step parameter is 1 or 2 or 3 or 4), the method for determining the second step parameter corresponding to the target to-be-judgment data can also be determined based on the method for determining the target state corresponding to the target to-be-judgment data as a counting state.

[0087] The data processing method provided in the present application can be used to determine the target state corresponding to the to-be-judgment data in the to-be-processed sub-data in the subsequent process by determining the first step parameter and the second step parameter corresponding to each to-be-processed sub-data.

[0088] Step 206: Determine the target state corresponding to each to-be-processed sub-data according to the first step parameter and the second step parameter corresponding to each to-be-processed sub-data.

[0089] After determining the first step parameter and the second step parameter corresponding to each to-be-processed sub-data, the target state corresponding to each to-be-processed sub-data can be further determined according to the first step parameter and the second step parameter corresponding to each to-be-processed sub-data.

[0090] In a specific implementation provided in the present application, the target state corresponding to each to-be-processed sub-data is determined according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data, and the target state corresponding to each to-be-processed sub-data is determined according to the target state corresponding to each to-be-judged data corresponding to the to-be-processed sub-data.

[0091] In the case where the target first step counting parameter is zero, the target to-be-judged data is input into the state classification model to obtain the target state corresponding to the target to-be-judged data output by the state classification model.

[0092] In the case where the target first step counting parameter is not zero, the target state corresponding to the previous to-be-judged data corresponding to the target to-be-judged data is determined as the target state corresponding to the target to-be-judged data.

[0093] The target state corresponding to the target to-be-processed sub-data is determined according to the target state corresponding to each to-be-judged data corresponding to the target to-be-processed sub-data.

[0094] Specifically, after the target first step counting parameter and the target second step counting parameter corresponding to the target to-be-judged data are determined, the value of the target first step counting parameter is determined. If the target first step counting parameter is zero, the target to-be-judged data is input into the state classification model, and the target state corresponding to the target to-be-judged data is determined according to the output result of the state classification model. If the target first step counting parameter is not zero, the target state corresponding to the previous to-be-judged data corresponding to the target to-be-judged data is determined as the target state corresponding to the target to-be-judged data.

[0095] That is, in the case where the target first step counting parameter is not zero, the state classification model does not classify the target state corresponding to the target to-be-judged data. Since the coincidence degree of the data corresponding to adjacent Herz is high and the similarity is also high, the state classification model only identifies and classifies the target state corresponding to the target to-be-judged data in the case where the target first step counting parameter is zero, thereby reducing the computing resources.

[0096] For example, in the case where the target first step counting parameter is zero, the target state corresponding to the target to-be-judged data determined based on the state classification model is a counting state, and in the case where the target first step counting parameter is 1, 2, 3, and 4, the counting state is directly determined as the target state corresponding to the target to-be-judged data in the case where the target first step counting parameter is 1, 2, 3, and 4.

[0097] Further, after the target state corresponding to each to-be-judged data is determined, the target state corresponding to each to-be-processed sub-data can be determined according to the target state corresponding to each to-be-judged data corresponding to the to-be-processed sub-data.

[0098] Further, the specific implementation method for determining the first step counting parameter and the second step counting parameter corresponding to each to-be-judged data can be implemented by the following method:

[0099] In the case where the target state corresponding to the target to-be-judged data is determined, the target first step counting parameter is increased by 1, and in the case where the target state is a counting state, the target second step counting parameter is decreased by 1.

[0100] In the case where the target first step counting parameter reaches a first step counting parameter threshold, the target first step counting parameter is set to zero.

[0101] In the case where the target second step counting parameter is zero or the target state corresponding to the target to-be-judged data is a non-counting state, the target second step counting parameter is set to a second step counting parameter threshold.

[0102] Specifically, after the target state corresponding to the target to-be-judged data is determined, the target first step counting parameter is increased by 1, and the first step counting parameter after the increase is taken as the first step counting parameter corresponding to the next to-be-judged data. If the target state corresponding to the target to-be-judged data is a counting state, the target first step counting parameter is increased by 1 while the target second step counting parameter is decreased by 1.

[0103] If the target first step counting parameter accumulates to the first step counting parameter threshold, the target first step counting parameter is reset to zero. Further, if the target second step counting parameter is decreased to zero or the target state corresponding to the target to-be-judged data is a non-counting state, the target second step counting parameter is reset to the second step counting parameter threshold.

[0104] Further, in a specific implementation provided in the present application, after the target state corresponding to each to-be-judged data is determined, the method further comprises:

[0105] adding the target state corresponding to each to-be-judged data output by the state classification model to a state queue.

[0106] The state queue refers to a queue for storing the target state corresponding to each to-be-judged data output by the state classification model.

[0107] Specifically, after the target state corresponding to each to-be-judged data is determined, the target state output by the state classification model is added to the state queue for subsequent determination of the target step counting data corresponding thereto based on the target state.

[0108] The data processing method provided in the present application can determine the target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter after the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data are determined.

[0109] Step 208: determining the target step data corresponding to the to-be-processed data based on the initial step data and the target state corresponding to each to-be-processed sub-data.

[0110] The target step data refers to the step data after the initial step data corresponding to the to-be-processed data is corrected.

[0111] Specifically, after the target state corresponding to each to-be-processed sub-data is determined, whether the initial step data corresponding to each to-be-processed sub-data needs to be counted can be determined according to the target state corresponding to each to-be-processed sub-data, so that the initial step data corresponding to each to-be-processed sub-data can be corrected to reduce the error between the actual step data corresponding to each to-be-processed sub-data.

[0112] Further, in a specific embodiment provided in the present application, the target step data corresponding to the to-be-processed data is determined based on the initial step data and the target state corresponding to each to-be-processed sub-data, including:

[0113] counting the number of elements and the element values in the state queue;

[0114] determining the target state corresponding to the to-be-judged data based on the number of elements and the element values;

[0115] in the case that the target state is a non-counting state, determining that the target step data corresponding to the to-be-judged data is zero;

[0116] in the case that the target state is a counting state, determining that the initial step data corresponding to the to-be-judged data is the target step data corresponding to the to-be-judged data;

[0117] determining the target step data corresponding to the to-be-processed data according to the target step data corresponding to the to-be-judged data.

[0118] The number of elements refers to the number of target states stored in the state queue; the element value refers to the value corresponding to each element (i.e. target state) stored in the state queue. Specifically, the element value can include 0 or 1, and the element value of 0 indicates that the target state is a non-counting state, and the element value of 1 indicates that the target state is a counting state.

[0119] Specifically, the number of elements stored in the state queue and the element value corresponding to each element are counted, and the target state corresponding to the to-be-judged data is determined based on the counted number of elements and element values. If it is determined that the target state corresponding to the to-be-judged data is a non-counting state, it means that the initial step data corresponding to the to-be-judged data does not need to be counted, and then the target step data corresponding to the to-be-judged data is determined to be zero. If it is determined that the target state corresponding to the to-be-judged data is a counting state, it means that the initial step data corresponding to the to-be-judged data needs to be counted, and then the initial step data corresponding to the to-be-judged data is determined as the target step data corresponding to the to-be-judged data. Based on the above method, after determining the target step data corresponding to each to-be-judged data, the target step data corresponding to the to-be-processed data can be determined according to the target step data corresponding to each to-be-judged data.

[0120] Further, in a specific embodiment provided in the present application, determining the target state corresponding to the to-be-judged data based on the number of elements and the element value comprises:

[0121] obtaining a first preset threshold and a second preset threshold;

[0122] In the case where the number of elements is less than the first preset threshold, the target state corresponding to each to-be-judged data is determined according to each element value;

[0123] In the case where the number of elements is equal to the first preset threshold, the number of elements with a value of zero in the state queue is determined, and in the case where the number of elements with a value of zero in the state queue is less than the second preset threshold, the target state corresponding to the to-be-judged data is determined to be a counting state, and in the case where the number of elements with a value of zero in the state queue is equal to or greater than the second preset threshold, the target state corresponding to the to-be-judged data is determined to be a non-counting state.

[0124] The first preset threshold refers to the storage capacity of the state queue, and the second preset threshold refers to the basis for judging the actual state of the current target state according to the number of elements in the state queue corresponding to the non-counting state.

[0125] Specifically, the first preset threshold and the second preset threshold are acquired, it is determined whether the number of elements in the state queue is equal to the first preset threshold, if it is determined that the number of elements is less than the first preset threshold, the target state corresponding to the to-be-judged data corresponding to each element value is determined according to the element value, that is, if the element value is 1, it is determined that the target state of the to-be-judged data corresponding to the element value is the counting state, and if the element value is 0, it is determined that the target state of the to-be-judged data corresponding to the element value is the non-counting state; if the number of elements is equal to the first preset threshold, the number of elements with the element value of 0 in the state queue is counted, and in the case that the number of elements with the element value of 0 is less than the second preset threshold, it can be determined that the target state corresponding to the current to-be-judged data is the counting state, and in the case that the number of elements with the element value of 0 is equal to or greater than the second preset threshold, it can be determined that the target state corresponding to the current to-be-judged data is the non-counting state.

[0126] Since the storage capacity of the state queue is the value corresponding to the first preset threshold, the number of elements in the state queue will not be greater than the first preset threshold. However, it does not mean that after the number of elements stored in the state queue reaches the first preset threshold, the storage of new elements is stopped. Further, the state queue stores the target state corresponding to each to-be-judged data based on the output order of the state classification model, so in the case that the number of elements in the state queue reaches the first preset threshold, the first element stored in the current state queue needs to be removed first before storing new elements.

[0127] For example, if the first preset threshold is 20, it means that the storage capacity of the state queue is 20, that is, more than 20 elements cannot be stored in the state queue. When the state classification model outputs the target state corresponding to the 21st to-be-judged data, the state queue will remove the first element in the current queue, so that the output of the 21st target state by the state classification model can be stored in the state queue, so the number of elements in the state queue is still 20.

[0128] Taking the first preset threshold value as 20 and the second preset threshold value as 17 as an example, if the number of elements stored in the state queue is 15, it can be determined that the number of elements is less than the first preset threshold value, and the 15 elements (target states) are stored in the state queue at the same time, and the target states corresponding to the 15 elements are determined as the actual target states corresponding thereto. If the number of elements stored in the state queue is 20, it can be determined that the number of elements is equal to the first preset threshold value, and then it is needed to judge the number of element values that are 0 corresponding to the 20 elements, if the number of element values that are 0 is 13, it can be determined that the number of element values that are 0 is less than the second preset threshold value, and the actual target state corresponding to the 20th element (target state) is determined as the counting state; if the number of element values that are 0 is 18, it can be determined that the number of element values that are 0 is greater than the second preset threshold value, and the actual target state corresponding to the 20th element (target state) is determined as the non-counting state.

[0129] The data processing method provided in the application can store each target state in the state queue after obtaining the target states output by the state classification model, and then can further determine the target state corresponding to each to-be-judged data according to the number and element values of the elements in the state queue, thereby improving the accuracy of statistical step counting.

[0130] The data processing method provided in the application comprises: obtaining to-be-processed data for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data comprises at least one to-be-processed sub-data; determining a first step counting parameter and a second step counting parameter corresponding to each to-be-processed sub-data; determining a target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data; and determining target step counting data corresponding to the to-be-processed data based on the initial step counting data and the target state corresponding to each to-be-processed sub-data.

[0131] An embodiment of the application achieves the elimination of false step counting in to-be-processed sub-data by judging the target state corresponding to each to-be-judged data in the to-be-processed sub-data, thereby improving the accuracy of step counting of to-be-processed data, and greatly reducing the amount of calculation and the cost of calculation compared with traditional step counting algorithms.

[0132] The following describes the data processing method provided in the application in combination with the accompanying drawings Figure 3 The data processing method provided in the application is further described below by taking the application of the data processing method provided in the application in an outdoor walking scene as an example. Wherein, Figure 3 FIG. 1 shows a processing flowchart of a data processing method applied in an outdoor walking scene according to an embodiment of the application, and specifically comprises the following steps:

[0133] Step 302: based on the acquisition device, acquiring acceleration signal data for counting steps within 1 minute, and dividing the acceleration signal data into 30 acceleration segment signal data according to a preset time length of 2 seconds.

[0134] Step 304: determining target acceleration segment signal data in the 30 acceleration segment signal data, and determining 50 to-be-judged data based on the target acceleration segment signal data.

[0135] Step 306: determining target to-be-judged data and a target first step counting parameter corresponding to the target to-be-judged data as 0 in the 50 to-be-judged data.

[0136] Step 308: inputting the target to-be-judged data into a state classification model to acquire a target state corresponding to the target to-be-judged data output by the state classification model as a non-counting state.

[0137] Step 310: increasing the target first step counting parameter by 1 to obtain a target first step counting parameter of 1, and setting a target second step counting parameter threshold corresponding to the target to-be-judged data as 150.

[0138] Step 312: outputting a non-counting state corresponding to the target to-be-judged data and storing the non-counting state into a state queue.

[0139] Step 314: determining target step counting data corresponding to the target to-be-judged data as zero based on the non-counting state corresponding to the target to-be-judged data.

[0140] Step 316: determining a target state corresponding to next to-be-judged data corresponding to the target to-be-judged data as a non-counting state according to the target first step counting parameter being 1 and the non-counting state corresponding to the target to-be-judged data.

[0141] Step 318: increasing the target first step counting parameter by 1 to obtain a target first step counting parameter of 2, and setting a target second step counting parameter threshold corresponding to the next to-be-judged data as 150.

[0142] Step 320: determining a target state corresponding to next to-be-judged data corresponding to the next to-be-judged data as a non-counting state according to the target first step counting parameter being 2 and the non-counting state corresponding to the next to-be-judged data.

[0143] Step 322: repeating the above steps 316 to 320 until the target first step counting parameter is 5, and setting the target first step counting parameter as 0.

[0144] Step 324: repeat the above steps 308 to 322 until the target state judgment corresponding to the to-be-judged data in the 30 acceleration segment signal data is completed, and the target step counting data corresponding to each to-be-judged data is determined according to the target state corresponding to each to-be-judged data.

[0145] Step 326: determining the target step counting data corresponding to the acceleration signal data according to the target step counting data corresponding to each to-be-judged data.

[0146] An embodiment of the present application realizes that the false step counting in the to-be-processed sub-data is eliminated by judging the target state corresponding to each to-be-judged data in the to-be-processed sub-data, so as to improve the accuracy of step counting of the to-be-processed data. Compared with the traditional step counting algorithm, the calculation amount is greatly reduced, and the calculation cost is also reduced.

[0147] Corresponding to the method embodiments, the present application also provides data processing device embodiments, Figure 4 The structure schematic diagram of a data processing device provided by an embodiment of the present application is shown. As shown in the figure, Figure 4 The device comprises:

[0148] The data acquisition module 402 is configured to acquire to-be-processed data for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data comprises at least one to-be-processed sub-data;

[0149] The parameter determination module 404 is configured to determine the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data;

[0150] The state determination module 406 is configured to determine the target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data;

[0151] The data determination module 408 is configured to determine the target step counting data corresponding to the to-be-processed data based on the initial step counting data and the target state corresponding to each to-be-processed sub-data.

[0152] Optionally, the data acquisition module 402 is further configured to:

[0153] Acquire the to-be-processed data for counting steps in a preset time interval based on a data acquisition device.

[0154] Optionally, the data acquisition module 402 is further configured to:

[0155] Divide the to-be-processed data into at least one to-be-processed sub-data based on a preset time length.

[0156] Optionally, the parameter determination module 404 is further configured to:

[0157] determine target to-be-processed sub-data in the to-be-processed data, and determine at least one to-be-judgment data based on the target to-be-processed sub-data;

[0158] determine a first step counting parameter corresponding to each to-be-judgment data;

[0159] determine a second step counting parameter corresponding to each to-be-judgment data based on the first step counting parameter corresponding to each to-be-judgment data.

[0160] Optionally, the parameter determination module 404 is further configured to:

[0161] determine target to-be-judgment data and a target first step counting parameter corresponding to the target to-be-judgment data in the at least one to-be-judgment data;

[0162] in a case where the target first step counting parameter is zero, determine a target state of the target to-be-judgment data based on a state classification model;

[0163] determine a target second step counting parameter corresponding to the target to-be-judgment data based on the target state corresponding to the target to-be-judgment data.

[0164] Optionally, the parameter determination module 404 is further configured to:

[0165] in a case where the target state corresponding to the target to-be-judgment data is a non-counting state, set the target second step counting parameter corresponding to the target to-be-judgment data as a second step counting parameter threshold;

[0166] in a case where the target state corresponding to the target to-be-judgment data is a counting state, determine the target second step counting parameter corresponding to the target to-be-judgment data according to a second step counting parameter corresponding to a previous to-be-judgment data corresponding to the target to-be-judgment data.

[0167] Optionally, the state determination module 406 is further configured to:

[0168] in a case where the target first step counting parameter is zero, input the target to-be-judgment data into the state classification model to obtain a target state corresponding to the target to-be-judgment data output by the state classification model;

[0169] in a case where the target first step counting parameter is not zero, determine a target state corresponding to the target to-be-judgment data as a target state corresponding to a previous to-be-judgment data corresponding to the target to-be-judgment data;

[0170] According to a target state corresponding to each to-be-judged data corresponding to the target to-be-processed sub-data, a target state corresponding to the target to-be-processed sub-data is determined.

[0171] Optionally, the state determining module 406 is further configured to:

[0172] In a case where the target state corresponding to the target to-be-judged data is determined, the target first step counting parameter is increased by 1, and in a case where the target state is a counting state, the target second step counting parameter is decreased by 1.

[0173] In a case where the target first step counting parameter reaches a first step counting parameter threshold, the target first step counting parameter is set to zero.

[0174] In a case where the target second step counting parameter is zero or the target state corresponding to the target to-be-judged data is a non-counting state, the target second step counting parameter is set to a second step counting parameter threshold.

[0175] Optionally, the state determining module 406 is further configured to:

[0176] The target state corresponding to each to-be-judged data output by the state classification model is added to a state queue.

[0177] Optionally, the data determining module 408 is further configured to:

[0178] The number of elements and the element values in the state queue are counted.

[0179] Based on the number of elements and the element values, a target state corresponding to the to-be-judged data is determined.

[0180] In a case where the target state is a non-counting state, it is determined that a target step counting data corresponding to the to-be-judged data is zero.

[0181] In a case where the target state is a counting state, it is determined that an initial step counting data corresponding to the to-be-judged data is a target step counting data corresponding to the to-be-judged data.

[0182] According to the target step counting data corresponding to the to-be-judged data, a target step counting data corresponding to the to-be-processed data is determined.

[0183] Optionally, the data determining module 408 is further configured to:

[0184] A first preset threshold and a second preset threshold are obtained.

[0185] In a case where the number of elements is less than the first preset threshold, a target state corresponding to each to-be-judged data is determined according to each element value.

[0186] In a case where the number of elements is equal to the first preset threshold, a number of elements with a value of zero in the state queue is determined, in a case where the number of elements with a value of zero in the state queue is less than a second preset threshold, a target state corresponding to the to-be-judged data is determined as a counting state, and in a case where the number of elements with a value of zero in the state queue is equal to or greater than the second preset threshold, the target state corresponding to the to-be-judged data is determined as a non-counting state.

[0187] The data processing apparatus provided in the application comprises a data acquisition module configured to acquire to-be-processed data for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data comprises at least one to-be-processed sub-data; a parameter determination module configured to determine a first step counting parameter and a second step counting parameter corresponding to each to-be-processed sub-data; a state determination module configured to determine a target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data; and a data determination module configured to determine target step counting data corresponding to the to-be-processed data based on the initial step counting data and the target state corresponding to each to-be-processed sub-data.

[0188] An embodiment of the application achieves the elimination of false step counting in to-be-processed sub-data by judging the target state corresponding to each to-be-judged data in the to-be-processed sub-data, thereby improving the accuracy of step counting of to-be-processed data, and greatly reducing the amount of calculation and the cost of calculation relative to a traditional step counting algorithm.

[0189] The above is a schematic scheme of the data processing apparatus of the embodiment. It should be noted that the technical scheme of the data processing apparatus and the technical scheme of the data processing method described above belong to the same concept, and the details of the technical scheme of the data processing apparatus that are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0190] Figure 5 A structural block diagram of a computing device 500 according to an embodiment of the application is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 through a bus 530, and a database 550 is used to save data.

[0191] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or combinations of such networks, such as the Internet. The access device 540 can include one or more of any type of network interface (for example, a network interface card (NIC)), such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, or the like.

[0192] In one embodiment of the present application, the above-mentioned components of the computing device 500, as well as other components not shown in FIG. 5, can be connected to each other by a bus. It should be understood that Figure 5 the components of the computing device 500 can be connected to each other by a bus. Figure 5 The computing device structure diagram shown is merely for the purpose of example, and is not a limitation on the scope of the present application. Those skilled in the art can add or replace other components as needed.

[0193] The computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (for example, a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, and the like), a mobile phone (for example, a smartphone), a wearable computing device (for example, a smart watch, smart glasses, and the like), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 500 can also be a mobile or stationary server.

[0194] wherein the processor 520 implements the steps of the data processing method when executing the computer instructions.

[0195] The above is a schematic scheme of the computing device of the embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the data processing method described above belong to the same concept, and the details of the technical scheme of the computing device that are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0196] An embodiment of the present application further provides a computer readable storage medium, which stores computer instructions, and the computer instructions are executed by a processor to implement the steps of the data processing method.

[0197] The above is a schematic scheme of the computer readable storage medium of the embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the data processing method described above belong to the same concept, and the details of the technical scheme of the storage medium that are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0198] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0199] The computer instructions include computer program code, which can be in the form of source code, object code, executable code, or some intermediate form. The computer readable medium can include any entity or apparatus capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0200] It should be noted that, for the aforementioned method embodiments, the sequences of the described actions are not the only ones that can be performed to implement the present application. In some embodiments, the sequences of actions can be performed in different order or simultaneously. In some embodiments, other sequences of actions can be performed, which should be apparent to a person of ordinary skill in the art in light of the teachings of the present application.

[0201] In the above embodiments, the description of each embodiment focuses on different aspects, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0202] The preferred embodiments of the present application disclosed above are only used to explain the present application. The alternative embodiments do not describe all the details and limit the present application to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of the present application. The present application selects and describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and use the present application. The present application is limited by the claims and their full scope and equivalents.

Claims

1. A data processing method, characterized by, The method comprises: obtaining to-be-processed data for counting steps, and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data comprises at least one to-be-processed sub-data; determining a first step counting parameter and a second step counting parameter corresponding to each to-be-processed sub-data, wherein the second step counting parameter is determined based on the first step counting parameter and a state classification model; determining a target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data; determining target step counting data corresponding to the to-be-processed data based on the initial step counting data and the target state corresponding to each to-be-processed sub-data.

2. The method of claim 1, wherein, The method comprises: obtaining to-be-processed data for counting steps based on a data collection device within a preset time interval.

3. The method of claim 2, wherein, After obtaining the to-be-processed data for counting steps, the method further comprises: dividing the to-be-processed data into at least one to-be-processed sub-data based on a preset time length.

4. The method of claim 1, wherein, The method comprises: determining a target to-be-processed sub-data in the to-be-processed data, and determining at least one to-be-judged data based on the target to-be-processed sub-data; determining a first step counting parameter corresponding to each to-be-judged data; determining a second step counting parameter corresponding to each to-be-judged data based on the first step counting parameter corresponding to each to-be-judged data.

5. The method of claim 4, wherein, The method comprises: determining a target to-be-judged data and a target first step counting parameter corresponding to the target to-be-judged data in the at least one to-be-judged data; in a case where the target first step counting parameter is zero, determining a target state of the target to-be-judged data based on a state classification model; determining a target second step counting parameter corresponding to the target to-be-judged data based on the target state corresponding to the target to-be-judged data.

6. The method of claim 5, wherein, The method comprises: in a case where the target state corresponding to the target to-be-judged data is a non-counting state, setting the target second step counting parameter corresponding to the target to-be-judged data as a second step counting parameter threshold; in a case where the target state corresponding to the target to-be-judged data is a counting state, determining the target second step counting parameter corresponding to the target to-be-judged data according to a second step counting parameter corresponding to a previous to-be-judged data corresponding to the target to-be-judged data.

7. The method of claim 5, wherein, The method comprises: in a case where the target first step counting parameter is zero, inputting the target to-be-judged data into the state classification model to obtain a target state of the target to-be-judged data output by the state classification model; in a case where the target first step counting parameter is not zero, determining a target state corresponding to the target to-be-judged data as a target state corresponding to a previous to-be-judged data corresponding to the target to-be-judged data; According to a target state corresponding to each to-be-judged data, a target state corresponding to the target to-be-processed sub-data is determined.

8. The method of claim 7, wherein, The method further comprises: In a case where the target state corresponding to the target to-be-judged data is determined, the target first step counting parameter is increased by 1, and in a case where the target state is a counting state, the target second step counting parameter is decreased by 1; In a case where the target first step counting parameter reaches a first step counting parameter threshold, the target first step counting parameter is set to zero; In a case where the target second step counting parameter is zero or the target state corresponding to the target to-be-judged data is a non-counting state, the target second step counting parameter is set to a second step counting parameter threshold.

9. The method of claim 7, wherein, After determining the target state corresponding to each to-be-judged data, the method further comprises: Adding the target state corresponding to each to-be-judged data output by the state classification model to a state queue.

10. The method of claim 9, wherein, Based on the initial step counting data and the target state corresponding to each to-be-processed sub-data, a target step counting data corresponding to the to-be-processed data is determined, comprising: Counting the number of elements and element values in the state queue; Based on the number of elements and the element values, determining the target state corresponding to the to-be-judged data; In a case where the target state is a non-counting state, determining that the target step counting data corresponding to the to-be-judged data is zero; In a case where the target state is a counting state, determining that the initial step counting data corresponding to the to-be-judged data is the target step counting data corresponding to the to-be-judged data; According to the target step counting data corresponding to the to-be-judged data, determining the target step counting data corresponding to the to-be-processed data.

11. The method of claim 10, wherein, Based on the number of elements and the element values, determining the target state corresponding to the to-be-judged data, comprising: Obtaining a first preset threshold and a second preset threshold; In a case where the number of elements is less than the first preset threshold, determining the target state corresponding to each to-be-judged data according to each element value; In a case where the number of elements is equal to the first preset threshold, determining the number of elements with zero element values in the state queue, in a case where the number of elements with zero element values in the state queue is less than a second preset threshold, determining that the target state corresponding to the to-be-judged data is a counting state, and in a case where the number of elements with zero element values in the state queue is equal to or greater than the second preset threshold, determining that the target state corresponding to the to-be-judged data is a non-counting state.

12. A data processing apparatus, characterized by Comprising: A data acquisition module configured to acquire to-be-processed data for counting steps and initial step counting data corresponding to the to-be-processed data, wherein the to-be-processed data comprises at least one to-be-processed sub-data; A parameter determination module configured to determine a first step counting parameter and a second step counting parameter corresponding to each to-be-processed sub-data, wherein the second step counting parameter is determined based on the first step counting parameter and a state classification model; A state determination module configured to determine a target state corresponding to each to-be-processed sub-data according to the first step counting parameter and the second step counting parameter corresponding to each to-be-processed sub-data; A data determining module is configured to determine target step counting data corresponding to the to-be-processed data based on the initial step counting data and a target state corresponding to each to-be-processed sub-data.

13. A computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, wherein, The processor executes the computer instructions to implement the steps of the method in any one of claims 1-11.

14. A computer-readable storage medium storing computer instructions, wherein, The computer instructions are executed by the processor to implement the steps of the method in any one of claims 1-11.

Images