Vehicle determination method and device, electronic equipment and storage medium

Abstract

The invention provides a vehicle determination method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a current first air pressure sequence, detecting the current motion state of an object according to the first air pressure sequence, and responding to the motion state of taking a vehicle, determining a first confidence coefficient and a prediction confidence coefficient of at least one candidate vehicle according to the first air pressure sequence, determining a target confidence coefficient of each candidate vehicle according to the first confidence coefficient and the prediction confidence coefficient of each candidate vehicle, and determining a target confidence coefficient of each candidate vehicle according to the target confidence coefficient of the at least one candidate vehicle. According to the method, the target vehicle currently taken by the object is determined, the first confidence coefficient and the prediction confidence coefficient of the candidate vehicle are determined through the air pressure characteristics, and the target confidence coefficient of the candidate vehicle is determined based on the prediction confidence coefficient and the first confidence coefficient, so that the accuracy of the target confidence coefficient of the candidate vehicle is improved; therefore, the accuracy of determining the target vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for determining a means of transportation. Background Art

[0002] As the configuration of the terminal devices carried by users becomes higher and higher, more and more functions can be realized.

[0003] In the related art, the vehicle taken is usually determined based on GPS speed information, inertial measurement unit (IMU) sensor data or data from a terminal's signal base station. However, the above technology has the problem of misjudgment and cannot accurately determine the vehicle taken. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the present application proposes a method, device, electronic device and storage medium for determining a vehicle to improve the accuracy of determining a vehicle.

[0006] In one aspect, an embodiment of the present application provides a method for determining a means of transport, including:

[0007] Get the current first air pressure sequence;

[0008] detecting a current motion state of the object according to the first air pressure sequence;

[0009] In response to the motion state being riding a vehicle, determining a first confidence and a predicted confidence of at least one candidate vehicle according to the first air pressure sequence;

[0010] Determining a target confidence of each of the candidate transportation tools according to the first confidence and the predicted confidence of each of the candidate transportation tools;

[0011] The target vehicle currently taken by the subject is determined according to the target confidence level of the at least one candidate vehicle.

[0012] In another aspect, an embodiment of the present application provides a vehicle determination device, comprising:

[0013] An acquisition module, used for acquiring the current first air pressure sequence;

[0014] a detection module, configured to detect a current motion state of the object according to the first air pressure sequence;

[0015] A first determination module, configured to determine, in response to the motion state being riding a vehicle, a first confidence level and a prediction confidence level of at least one candidate vehicle according to the first air pressure sequence;

[0016] A second determination module, configured to determine a target confidence of each of the candidate transportation tools according to the first confidence and the predicted confidence of each of the candidate transportation tools;

[0017] The third determination module is used to determine the target transportation tool that the subject is currently riding according to the target confidence level of the at least one candidate transportation tool.

[0018] Another aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the above aspect is implemented.

[0019] Another aspect of the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method described in the aforementioned aspect is implemented.

[0020] Another aspect of the present application provides a computer program product on which a computer program is stored. When the program is executed by a processor, the method described in the above aspect is implemented.

[0021] The method, device, electronic device and storage medium for determining a vehicle proposed in the present application obtain a current first air pressure sequence, detect a current motion state of an object based on the first air pressure sequence, determine a first confidence and a predicted confidence of at least one candidate vehicle based on the first air pressure sequence in response to the motion state being riding a vehicle, determine a target confidence of each candidate vehicle based on the first confidence and the predicted confidence of each candidate vehicle, determine a target vehicle that the object is currently riding based on the target confidence of at least one candidate vehicle, determine the first confidence and the predicted confidence of possible candidate vehicles through air pressure characteristics, determine the target confidence of the candidate vehicle based on the predicted confidence and the first confidence, thereby improving the accuracy of the target confidence of the candidate vehicles and thus improving the accuracy of determining the target vehicle.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flow chart of a method for determining a means of transport provided in an embodiment of the present application;

[0025] Figure 2 A flowchart of another method for determining a means of transport provided in an embodiment of the present application;

[0026] Figure 3 A flowchart of another method for determining a means of transport provided in an embodiment of the present application;

[0027] Figure 4 A flowchart of another method for determining a means of transport provided in an embodiment of the present application;

[0028] Figure 5 A flowchart of another method for determining a means of transport provided in an embodiment of the present application;

[0029] Figure 6 A flowchart of another method for determining a means of transport provided in an embodiment of the present application;

[0030] Figure 7 A flowchart of another method for determining a means of transport provided in an embodiment of the present application;

[0031] Figure 8 A schematic diagram of the structure of a vehicle determination device provided in an embodiment of the present application;

[0032] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0034] The following describes the transportation determination method, device, electronic device and storage medium of the embodiments of the present application with reference to the accompanying drawings.

[0035] In the related art, IMU sensor related algorithms are usually used, and the signal base station of the terminal directly sends a signal with a mark, as well as GPS speed information, etc. to determine the vehicle the user is currently riding. However, the above method has the possibility of misjudgment and low accuracy. To this end, the present application provides a vehicle determination method, which determines the first confidence and predicted confidence of possible candidate vehicles through air pressure characteristics, determines the target confidence of the candidate vehicle based on the predicted confidence and the first confidence, improves the accuracy of the target confidence of the candidate vehicle, and thus improves the accuracy of the target vehicle determination.

[0036] Figure 1 A flowchart of a method for determining a means of transportation provided in an embodiment of the present application.

[0037] The executor of the transportation determination method in the embodiment of the present application is a transportation determination device, which can be set in an electronic device. The electronic device is, for example, a terminal device equipped with a pedometer sensor and a pressure sensor, such as a smart phone, a smart wearable device, a handheld computer, etc., which is not limited in this embodiment.

[0038] like Figure 1 As shown, the method may include the following steps:

[0039] Step 101, obtaining the current first air pressure sequence.

[0040] In the embodiment of the present application, the first air pressure sequence is the step counting state data of the set time collected by the pressure sensor. The pressure sensor is always on to collect air pressure data. The sampling rate is, for example, 10 Hz, that is, 10 data are collected in 1 second. Each air pressure data represents the atmospheric pressure at the current location of the mobile terminal. Among them, the set time is the time set according to the demand, for example, 5 minutes. The set time is the current corresponding set time, for example, the current time is the starting point or end point.

[0041] Step 102: Detect the current motion state of the object according to the first air pressure sequence.

[0042] The movement status includes riding a transportation vehicle and not riding a transportation vehicle. Transportation vehicles include airplanes, high-speed trains, ordinary railways, buses, subways, and cars (small cars, long-distance buses), etc.

[0043] In one implementation of the embodiment of the present application, the first air pressure sequence is divided into a plurality of subsequences of equal duration according to the air pressure data at each moment contained in the first air pressure sequence, and the air pressure change value in each subsequence is calculated according to the air pressure data contained in each subsequence. For each subsequence, if the air pressure change value in the subsequence is greater than the first set value, it is considered that the air pressure corresponding to the subsequence has risen; if the air pressure change value in the subsequence is less than the first set value, it is considered that the air pressure corresponding to the subsequence is stable; if the air pressure change value in the subsequence is less than the second set value, it is considered that the air pressure corresponding to the subsequence has dropped. If there is a continuous stable air pressure duration greater than the first duration in multiple subsequences, or the sum of the air pressure change values ​​in multiple subsequences is less than the set air pressure value, it is determined that the current motion state of the object is not riding a means of transportation, otherwise, it is considered to be riding a means of transportation. Among them, the first duration is, for example, 4 minutes, and the set air pressure value is, for example, 200 Pa.

[0044] As an example, the set duration of the first air pressure sequence is 5 minutes, and the duration of the subsequence is 5 seconds, that is, there are 60 subsequences, 10 air pressure data are collected per second, and a total of 50 air pressure data are collected in 50 seconds. The air pressure change value within 5 seconds is calculated, and Bari (i = 1, 2 ... 50) is recorded as the i-th data. The air pressure change value BarDiff satisfies the following formula:

[0045]

[0046] When the absolute value of BarDiff is less than the first set value, i.e. 0.05 hPa, it is considered that the air pressure changes steadily within 5 seconds. When BarDiff is greater than 0.05 hPa, it is considered that the air pressure rises within 5 seconds. When BarDiff is less than the second set value, i.e. -0.05 hPa, it is considered that the air pressure drops within 5 seconds.

[0047] Step 103 , in response to the motion state being riding a vehicle, determining a first confidence level and a predicted confidence level of at least one candidate vehicle according to the first air pressure sequence.

[0048] The first confidence and the predicted confidence are both used to indicate the possibility that the candidate means of transportation is the means of transportation currently taken by the user, and the confidence is proportional to the possibility of the candidate means of transportation.

[0049] In the embodiment of the present application, based on the characteristics that changes in air pressure are strongly correlated with changes in altitude and speed, and because different means of transportation have different operating speeds and altitudes, the means of transportation taken can be divided using characteristics such as the periodicity and stability of changes in air pressure, thereby determining the first confidence level of various candidate means of transportation that the object may take based on the changes in air pressure in the first air pressure sequence.

[0050] As an implementation method, the first air pressure sequence may be predicted based on the trained machine learning model to obtain prediction confidences corresponding to various candidate transportation vehicles that may be taken.

[0051] Step 104 : determining a target confidence level of each candidate transportation tool according to the first confidence level and the predicted confidence level of each candidate transportation tool.

[0052] In one implementation of an embodiment of the present application, for each candidate means of transportation, the first confidence and the predicted confidence of the candidate means of transportation are fused to obtain the target confidence of the candidate means of transportation. Optionally, the fusion is weighted addition, that is, the vector corresponding to the first confidence and the vector corresponding to the predicted confidence are added in aligning order, thereby obtaining the first confidence and the predicted confidence, and correcting the first confidence by the predicted confidence through fusion, thereby improving the accuracy and reliability of the target confidence of each candidate means of transportation.

[0053] Step 105 : determining the target transportation tool that the subject is currently riding according to the target confidence level of at least one candidate transportation tool.

[0054] In the embodiment of the present application, based on the target confidence of at least one candidate vehicle, the vehicle with the largest target confidence is screened out, and the candidate vehicle corresponding to the largest target confidence is used as the target vehicle.

[0055] In the method for determining a vehicle of an embodiment of the present application, a current first air pressure sequence is obtained, and a current motion state of an object is detected based on the first air pressure sequence. In response to the motion state being riding a vehicle, a first confidence and a predicted confidence of at least one candidate vehicle of the object are determined based on the first air pressure sequence. A target confidence of each candidate vehicle is determined based on the first confidence and the predicted confidence of each candidate vehicle. A target vehicle that the object is currently riding is determined based on the target confidence of at least one candidate vehicle. The first confidence and the predicted confidence of possible candidate vehicles are determined through air pressure characteristics. The target confidence of the candidate vehicle is determined based on the predicted confidence and the first confidence, thereby improving the accuracy of the target confidence of the candidate vehicles and thus improving the accuracy of determining the target vehicle.

[0056] Based on the above embodiments, Figure 2 A flow chart of another method for determining a means of transport provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the method comprises the following steps:

[0057] Step 201, obtaining the current first air pressure sequence.

[0058] In the embodiment of the present application, since the original air pressure data contains random background noise, it will have a negative effect on subsequent calculations. Therefore, before determining the current first air pressure sequence, it is filtered. A 50-order filter is used for the 10Hz original data. Let each moment be the current moment t, the real-time reported original data be Bar[t], and the filtered data of the previous moment t-1 be BarF[t-1]. Then the calculation formula of the filtered data BarF[t] at the current moment t is: BarF[t]←(BarF[t-1]×49+Bar[t])÷50.

[0059] Step 202: Detect the current motion state of the object according to the first air pressure sequence.

[0060] Among them, the relevant explanations in the aforementioned embodiments are also applicable to steps 201-202 of the embodiments of the present application. The principles are the same and will not be repeated here.

[0061] For determining the current running state of the object, in one implementation method of the embodiment of the present application, the pedometer status data of a set time length collected by the pedometer sensor can be obtained. The pedometer sensor adopts an event trigger mode for reporting, that is, when there is a walking state, data is collected to obtain the pedometer value. The data frequency is not fixed, and the time of reporting the pedometer value is recorded, and the pedometer value is filtered. Specifically, for the data collected by the pedometer, for each moment as the current moment t, the non-repetitive reporting count CountT between the previous moment t-1 and the current moment t of the reporting time StepT is counted, and a first pedometer sequence is generated according to the pedometer value after filtering. Then, according to the first pedometer sequence and / or the first air pressure sequence, the current motion state of the object is detected.

[0062] As an implementation method, the first pedometer sequence is divided into multiple subsequences of equal duration according to each pedometer value included in the first pedometer sequence, and the total step value in each subsequence is calculated according to the pedometer value included in each subsequence. For each subsequence, if the total step value in the subsequence is greater than the first set pedometer value, it is considered that the user is walking during the duration of the subsequence, and if the total step value in the subsequence is less than or equal to the first set pedometer value, it is considered that the user is not walking during the duration of the subsequence. Therefore, if there is a continuous walking time greater than the second duration in multiple subsequences, or the cumulative pedometer value is greater than the second set pedometer value, it is considered that the user is not currently on a vehicle, otherwise, it is considered that the user is currently on a vehicle.

[0063] The second duration is, for example, three minutes (36 subsequences), and the second set step value is 200 steps.

[0064] As another implementation method, the current motion state of the object is detected according to the first pedometer sequence and the first air pressure sequence, that is, if the first pedometer sequence satisfies the situation that the continuous walking time is greater than the second duration, or the accumulated pedometer value is greater than the second set pedometer value, and the first air pressure sequence satisfies the situation that the air pressure is continuously stable for a duration greater than the first duration, or the sum of the air pressure change values ​​in multiple sub-series is less than the set air pressure value, it is considered that the object is not currently on a vehicle; otherwise, it is considered that the object is currently on a vehicle.

[0065] As one implementation method, the current motion state of the object is detected according to the first air pressure sequence. For details, please refer to the explanation in the aforementioned embodiment. The principle is the same and will not be repeated here.

[0066] Step 203 , in response to the motion state being riding a vehicle, dividing the first air pressure sequence into a plurality of sub-air pressure sequences based on a preset time interval.

[0067] Step 204: Generate a mean air pressure sequence according to the air pressure means and time sequence of the plurality of sub-air pressure sequences.

[0068] In the embodiment of the present application, the first air pressure sequence is divided into a plurality of sub-air pressure sequences based on a preset time interval, and a mean air pressure sequence is generated according to the air pressure means and time sequence of the plurality of sub-air pressure sequences.

[0069] As an example, the preset time interval is 5 seconds, and the duration of the first air pressure sequence is 5 minutes. The first air pressure sequence can be divided into 60 sub-air pressure sequences, each of which is 5 seconds long. The average air pressure of the multiple air pressure values ​​contained in each air pressure sequence is calculated, and an average air pressure sequence containing 60 average air pressure values ​​is generated according to the order of time corresponding to each sub-air pressure sequence.

[0070] Step 205 , calculating the similarity between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate transportation tool, and obtaining the similarity between the mean air pressure sequence and each set air pressure sequence.

[0071] The candidate transportation means refer to various transportation means that users can usually take, including airplanes, high-speed railways, ordinary railways, buses, subways and cars (cars, long-distance buses), etc.

[0072] In an embodiment of the present application, for each candidate vehicle, the air pressure data collected when the candidate vehicle is actually operating on the road can generate a set air pressure sequence as a reference standard, and the similarity is calculated with the currently collected mean air pressure sequence to obtain the similarity between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate vehicle, wherein the similarity can be indicated by a distance, for example, the Euclidean distance, and the distance between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate vehicle can be determined, wherein if the windows of the candidate vehicle can be opened and closed, then the set air pressure sequence of the candidate vehicle under the open window operation state and the set air pressure sequence under the closed window operation state are obtained, thereby obtaining a first distance between the mean air pressure sequence and the set air pressure sequence of the candidate vehicle when the window is open, and a second distance between the mean air pressure sequence and the set air pressure sequence of the candidate vehicle when the window is closed, and selecting the smaller value between the first distance and the second distance as the distance between the mean air pressure sequence and the candidate vehicle. Furthermore, the distance between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate transportation tool is used as the similarity between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate transportation tool.

[0073] Step 206: Determine the initial confidence level of each candidate transportation tool based on each similarity level.

[0074] In an embodiment of the present application, the similarity between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate means of transportation is reciprocally normalized to obtain the initial confidence between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate means of transportation, that is, the initial confidence of each candidate means of transportation, thereby realizing the initial confidence of each candidate means of transportation that may be taken based on the air pressure sequence data and prior experience.

[0075] Step 207 : determining a first confidence level of each candidate transportation tool according to the initial confidence level of each candidate transportation tool.

[0076] In one implementation of the embodiment of the present application, the initial confidence of each candidate means of transport is used as the first confidence of each candidate means of transport, that is, the first confidence of each candidate means of transport is the same as the initial confidence.

[0077] It should be noted that, in response to determining that the motion state is not taking a vehicle according to the first air pressure sequence, the output category is "other" and the confidence level is 1, which determines that the person is not taking a vehicle.

[0078] Step 208: Input the mean air pressure sequence into the trained prediction model to determine the prediction confidence of at least one candidate vehicle according to the output of the prediction model.

[0079] In the embodiment of the present application, the mean pressure sequence is input into the time-frequency domain feature extraction network of the trained prediction model to obtain time domain features and frequency domain features, wherein the time domain features include the maximum value, minimum value, range, mean, standard deviation, cumulative sum, quartile, zero crossing number, minimum tenth value ratio, mode, median, etc. of the pressure in the mean pressure sequence. The frequency domain features include the spectral DC component, spectral maximum value, maximum frequency, second largest frequency, spectral energy, spectral entropy, maximum value and DC component ratio, spectral shape mean, spectral shape standard deviation, spectral shape slope, spectral shape kurtosis, etc.

[0080] The mean pressure sequence is input into the time series feature extraction network of the trained prediction model to obtain the time series feature. As an implementation method, the mean pressure sequence is input into the projection layer of the time series feature extraction network for high-dimensional space feature mapping to obtain high-dimensional space features, so as to realize mapping the first pressure sequence of time to the high-dimensional feature space, and then the high-dimensional space features are input into the time mask layer of the time series feature extraction network for masking to obtain masked high-dimensional space features, and then the masked high-dimensional space features and the high-dimensional space features are multiplied to obtain the target high-dimensional space features, and the target high-dimensional space features are input into the convolution layer of the time series feature extraction network, for example, the hole convolution layer, to obtain the time series features. As an example, the mean pressure sequence is 1*60 sequence data, which is input into the projection layer to generate 120*60 high-dimensional space information. The projection layer is essentially a fully connected layer, which maps the one-dimensional time series data into the 120-dimensional latent space to obtain high-dimensional space features, because the latent space contains more information. Then, the 120*60 high-dimensional spatial features are input into the time mask layer for random masking, and the 120*60 masked data is output. In essence, a 1*60 01 binary mask is generated, which is multiplied by the unmasked original data, i.e., the high-dimensional spatial features, to set some of the 60 time data to zero, thereby enhancing the contextual sequence connection of the time series. Finally, the 120*60 masked data is passed through the dilated convolution module to generate a 36*60 time series matrix, and then the mean of the time dimension is calculated to generate a 36*1 time series feature. In essence, it is 36 residual convolution modules, which are used to extract time series features with contextual connections.

[0081] Furthermore, the time domain features, frequency domain features and time series features are fused and input into the fusion module of the prediction model for feature fusion. Classification is performed based on the fused features to obtain the prediction confidence of each candidate means of transportation. The prediction model obtained by training is used to predict at least one candidate means of transportation corresponding to the mean air pressure data, and the prediction confidence of each candidate means of transportation is obtained, thereby improving the prediction efficiency.

[0082] Step 209 : determining the target confidence of each candidate transportation tool according to the first confidence and the predicted confidence of each candidate transportation tool.

[0083] Step 210 , determining the target transportation tool that the subject is currently riding based on the target confidence level of at least one candidate transportation tool.

[0084] Among them, step 209 and step 210 can refer to the explanation in the above-mentioned embodiment, and the principles are the same, which will not be repeated here.

[0085] In the vehicle determination method of the embodiment of the present application, the first confidence of possible candidate vehicles is determined by prior knowledge of air pressure characteristics, and the prediction confidence of each candidate vehicle corresponding to the first air pressure sequence is predicted based on the trained prediction model. The fusion result of the prediction confidence and the first confidence is used as the target confidence of the candidate vehicle, which improves the accuracy of the target confidence of the candidate vehicle and thus improves the accuracy of the target vehicle determination.

[0086] In the above-mentioned embodiments, it is explained that the first confidence of each candidate vehicle can be determined based on the similarity between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate vehicle. In actual scenarios, it is possible to further determine which candidate vehicle it is based on the different change characteristics of the mean air pressure data, and adjust the confidence of the more likely candidate vehicle based on the set confidence adjustment coefficient to achieve confidence correction, thereby improving the accuracy of target vehicle determination. The following uses different embodiments to illustrate how to determine the first confidence of each candidate vehicle based on the initial confidence of each candidate vehicle.

[0087] Based on the above embodiments, the embodiments of the present application provide another method for determining a means of transportation. In the embodiments of the present application, the candidate means of transportation corresponding to the mean air pressure sequence can be further determined based on whether the mean air pressure sequence is periodic. That is, if the mean air pressure sequence is periodic, then the corresponding candidate means of transportation is determined to be most likely the first candidate means of transportation. The first candidate means of transportation is a means of transportation that has periodicity in air pressure changes or speed changes, such as a bus or a subway. In this case, it is necessary to use a first confidence adjustment coefficient to increase the confidence of the first candidate means of transportation, that is, to increase the possibility that the candidate means of transportation is the first candidate means of transportation. Figure 3 A flow chart of another method for determining a means of transport provided in an embodiment of the present application is shown as follows: Figure 3 As shown, step 207 includes the following steps:

[0088] Step 301: convert the mean air pressure sequence from the time domain to the frequency domain, and determine the spectrum energy of the mean air pressure sequence in the frequency domain and the first energy of the main frequency.

[0089] In an embodiment of the present application, the mean air pressure sequence is Fourier transformed to convert from the time domain to the frequency domain, the energy corresponding to each of the multiple frequencies is determined for the mean air pressure sequence in the frequency domain, the first energy of the main frequency is determined from the energies corresponding to the multiple frequencies, and the sum of the multiple spectra is determined as the spectrum energy.

[0090] Step 302, in response to a ratio between the first energy and the spectrum energy being greater than a set threshold, determining a first confidence adjustment coefficient of a first candidate vehicle included in at least one candidate vehicle according to a ratio between the ratio and the set threshold.

[0091] Step 303: adjusting the initial confidence of the first candidate transportation means according to the first confidence adjustment coefficient of the first candidate transportation means to obtain the first confidence of the first candidate transportation means.

[0092] In an embodiment of the present application, the ratio between the first energy and the spectrum energy is compared with a set threshold. If the ratio is greater than the set threshold, it means that there is periodicity in the air pressure change in the mean air pressure sequence, and the candidate transportation vehicle whose collected air pressure has periodic changes may be the first candidate transportation vehicle, such as a bus and a subway. The ratio is used as the first confidence adjustment coefficient, and the first confidence adjustment coefficient is used to adjust the initial confidence of the first candidate transportation vehicle to obtain the first confidence of the first candidate transportation vehicle, thereby improving the first confidence of the first candidate transportation vehicle with a periodic air pressure change law through the periodic characteristics of the air pressure change, and improving the accuracy of the first confidence of the first candidate transportation vehicle.

[0093] Step 304 : determining first confidences of other candidate transportation vehicles other than the first candidate transportation vehicle according to the initial confidences of other candidate transportation vehicles other than the first candidate transportation vehicle.

[0094] The initial confidences of other candidate transportation means other than the first candidate transportation means remain unchanged, that is, the initial confidences of other candidate transportation means other than the first candidate transportation means are used as the first confidences of other candidate transportation means other than the first candidate transportation means.

[0095] In the method for determining a vehicle of an embodiment of the present application, if it is determined that the mean air pressure sequence has periodicity based on the distribution of energy in the frequency domain, then the candidate vehicle corresponding to the mean air pressure sequence is most likely to be the first candidate vehicle. The first candidate vehicle is a vehicle that has periodic changes in air pressure or speed, such as a bus or a subway. In this case, it is necessary to use a first confidence adjustment coefficient to improve the confidence of the first candidate vehicle, and maintain the initial confidence of other candidate vehicles other than the first candidate vehicle unchanged. By using the periodic characteristics of air pressure changes, the confidence of the first candidate vehicle that conforms to the periodic changes is increased, thereby improving the accuracy of the confidence of the first candidate vehicle, thereby increasing the accuracy of the subsequent target vehicle determination.

[0096] Based on the above embodiments, the embodiments of the present application provide another method for determining a means of transportation. In the embodiments of the present application, the candidate means of transportation corresponding to the mean air pressure sequence can be further determined based on whether the mean air pressure sequence is stable. That is, if the mean air pressure sequence is stable, it is determined that the corresponding candidate means of transportation is very likely to be the second candidate means of transportation. The second candidate means of transportation, such as an airplane or a high-speed rail, needs to use a second confidence adjustment coefficient to increase the confidence of the second candidate means of transportation, that is, to increase the possibility that the candidate means of transportation is the second candidate means of transportation. Figure 4 A flow chart of another method for determining a means of transport provided in an embodiment of the present application is shown as follows: Figure 4 As shown, step 207 includes the following steps:

[0097] Step 401, determining multiple differences between moments according to the mean air pressure at each moment in the mean air pressure sequence.

[0098] As an implementation method, the difference can be a first-order difference, that is, the difference between adjacent moments, that is, the average air pressure at moment t is Bar[t], and the average air pressure at moment t-1 before moment t is Bar[t-1], then the first-order difference between moment t and moment t-1 is Bar[t]-Bar[t-1].

[0099] As another implementation, the difference may also be a multi-order difference, that is, a difference between intervals of time, for example, a second-order difference, that is, the second-order difference between time t and time t-2 is Bar[t]-Bar[t-2].

[0100] Step 402, determining the standard deviation of multiple air pressure means according to multiple differences between time points.

[0101] Among them, the mean and standard deviation corresponding to the multiple air pressure mean values ​​can be determined according to the multiple differences between the moments, and the method for determining the mean and standard deviation in the relevant technology can be adopted, which is not limited in this embodiment.

[0102] Step 403 : in response to the standard deviation being less than or equal to the standard deviation threshold, obtaining a set second confidence adjustment coefficient of a second candidate transportation tool included in the at least one candidate transportation tool.

[0103] Step 404: adjust the initial confidence of the second candidate transportation tool according to the second confidence adjustment coefficient to obtain the first confidence of the second candidate transportation tool.

[0104] In the embodiment of the present application, the standard deviation is compared with the standard deviation threshold. If the standard deviation is less than or equal to the standard deviation threshold, it indicates that the air pressure can be determined to have a long-term stable change according to the mean air pressure sequence, and the air pressure change is strongly correlated with the speed or altitude change. Therefore, it can be considered that the speed or altitude has a stable change. Therefore, it is determined that at least one candidate transportation tool is likely to include the second candidate transportation tool, and the second candidate transportation tool is a high-speed rail or an airplane. Then, the set second confidence adjustment coefficient corresponding to the second candidate transportation tool in this scenario is obtained, and the initial confidence of the second candidate transportation tool is adjusted to increase the confidence of the second candidate transportation tool, thereby realizing the stability characteristics of the air pressure change, improving the first confidence of the second candidate transportation tool with a stable air pressure change law, and improving the accuracy of the first confidence of the second candidate transportation tool.

[0105] Optionally, in the embodiment of the present application, when the standard deviation is less than or equal to the standard deviation threshold, the candidate transportation tool can be determined to be the second candidate transportation tool, that is, an airplane or a subway. Further, as an implementation method, the mean corresponding to multiple air pressure means can also be determined. If the mean is greater than the first mean threshold, it is considered that the height or speed changes very quickly, and the second candidate transportation tool may be an airplane; if the mean is greater than the second mean threshold and less than the first mean threshold, it is considered that the height or speed changes very quickly, and the second candidate transportation tool may be a subway, wherein the second mean threshold is less than the first mean threshold. If the mean is less than or equal to the second mean threshold, it is considered that it is impossible to determine whether it is the second candidate transportation tool in this scenario, and the confidence of the second candidate transportation tool is not adjusted.

[0106] Step 405 : determining first confidences of other candidate transportation vehicles other than the second candidate transportation vehicle according to the initial confidences of other candidate transportation vehicles other than the second candidate transportation vehicle.

[0107] The initial confidences of the other candidate transportation means other than the second candidate transportation means remain unchanged, that is, the initial confidences of the other candidate transportation means other than the second candidate transportation means are used as the first confidences of the other candidate transportation means other than the second candidate transportation means.

[0108] In the method for determining a vehicle in an embodiment of the present application, if the standard deviation is less than or equal to the standard deviation threshold, it is determined that the mean air pressure sequence is stable, and the candidate vehicle corresponding to the mean air pressure sequence is determined to be very likely the second candidate vehicle. The second candidate vehicle has the characteristic of long-term stable changes in air pressure, that is, stable changes in speed or height. If the second candidate vehicle is, for example, a bus or a subway, it is necessary to use a second confidence adjustment coefficient to increase the confidence of the second candidate vehicle, and maintain the initial confidence of other candidate vehicles other than the second candidate vehicle unchanged. By using the stability characteristics of the air pressure change, the confidence of the second candidate vehicle that meets the stability change is increased, and the accuracy of the confidence of the second candidate vehicle is improved, thereby increasing the accuracy of the subsequent target vehicle determination.

[0109] Based on the above embodiment, that is, if there is instability in the mean air pressure sequence, it is determined that the corresponding candidate means of transportation is very likely to be the third candidate means of transportation. The third candidate means of transportation, such as a car or an ordinary railway, needs to adopt a third confidence adjustment coefficient to increase the confidence of the third candidate means of transportation, that is, to increase the possibility that the candidate means of transportation is the third candidate means of transportation. Figure 5 A flow chart of another method for determining a means of transport provided in an embodiment of the present application is shown as follows: Figure 5 As shown, step 207 includes the following steps:

[0110] Step 501, determining multiple differences between moments according to the mean air pressure at each moment in the mean air pressure sequence.

[0111] Step 502, determining the standard deviation of multiple air pressure means according to multiple differences between time points.

[0112] For details, please refer to the explanations in the aforementioned embodiments. The principles are the same and will not be repeated here.

[0113] Step 503: in response to the standard deviation being greater than the standard deviation threshold, obtaining a third confidence adjustment coefficient set for a third candidate transportation tool included in the at least one candidate transportation tool.

[0114] Step 504: adjust the initial confidence of the third candidate transportation tool according to the third confidence adjustment coefficient to obtain the first confidence of the third candidate transportation tool.

[0115] In the embodiment of the present application, the standard deviation is compared with the standard deviation threshold. If the standard deviation is greater than the standard deviation threshold, it indicates that the air pressure change can be determined to be unstable according to the mean air pressure sequence, and the air pressure change is strongly correlated with the speed or height change. Therefore, it can be considered that the speed or height change is unstable. Therefore, it is determined that at least one candidate vehicle is very likely to be the third candidate vehicle, and the third candidate vehicle is a car or an ordinary railway. Then, the set third confidence adjustment coefficient corresponding to the third candidate vehicle in this scenario is obtained, and the initial confidence of the third candidate vehicle is adjusted to increase the confidence of the third candidate vehicle, thereby realizing the instability characteristics of the air pressure change, increasing the first confidence of the third candidate vehicle with the unstable air pressure change law, and improving the accuracy of the first confidence of the third candidate vehicle.

[0116] Step 505 : determining first confidences of other candidate transportation means other than the third candidate transportation means according to the initial confidences of other candidate transportation means other than the third candidate transportation means.

[0117] The initial confidences of the other candidate transportation means except the third candidate transportation means remain unchanged, that is, the initial confidences of the other candidate transportation means except the third candidate transportation means are used as the first confidences of the other candidate transportation means except the third candidate transportation means.

[0118] In the method for determining a vehicle in an embodiment of the present application, if the standard deviation is greater than the standard deviation threshold, it is determined that the mean air pressure sequence is unstable, and the candidate vehicle corresponding to the mean air pressure sequence is determined to be most likely the third candidate vehicle. The third candidate vehicle has the characteristic of long-term stable changes in air pressure, that is, stable changes in speed or height. If the third candidate vehicle is, for example, a bus or a subway, it is necessary to use a third confidence adjustment coefficient to improve the confidence of the third candidate vehicle, and maintain the initial confidence of other candidate vehicles other than the third candidate vehicle unchanged. By using the stability characteristics of the air pressure change, the confidence of the third candidate vehicle that meets the stability change is increased, and the accuracy of the confidence of the third candidate vehicle is improved, thereby increasing the accuracy of the subsequent target vehicle determination.

[0119] Based on the above embodiment, in actual scenarios, some candidate vehicles have windows that can be opened and closed, that is, the windows can be opened and closed, then it is determined that the corresponding candidate vehicles are very likely to be candidate vehicles with opening and closing windows, such as cars or buses, then it is necessary to use the set fourth confidence adjustment coefficient to increase the confidence of the candidate vehicles with opening and closing windows, that is, to increase the possibility that the candidate vehicles are candidate vehicles with opening and closing windows. Figure 6 A flow chart of another method for determining a means of transport provided in an embodiment of the present application is shown as follows: Figure 6As shown, step 207 includes the following steps:

[0120] Step 601, determining multiple differences between moments according to the mean air pressure at each moment in the mean air pressure sequence.

[0121] For details, please refer to the explanations in the aforementioned embodiments. The principles are the same and will not be repeated here.

[0122] Step 602: In response to the absolute value of at least one difference being greater than an air pressure threshold, a fourth confidence adjustment coefficient of a candidate vehicle setting for an opening / closing type window included in at least one candidate vehicle is obtained.

[0123] Step 603: Adjust the initial confidence of the candidate transportation vehicle with opening and closing windows according to the fourth confidence adjustment coefficient to obtain the first confidence of the candidate transportation vehicle with opening and closing windows.

[0124] In an embodiment of the present application, if there is at least one difference whose absolute value is greater than the air pressure threshold, it means that there is a sudden change in air pressure, and opening or closing the window will cause the air pressure to change greatly first and then stabilize. Therefore, it can be determined that at least one candidate vehicle may be a candidate vehicle with opening and closing windows, and cars and buses among the vehicles can open or close windows. Therefore, to determine that at least one candidate vehicle is a car or a bus, it is necessary to obtain the set fourth confidence adjustment coefficient to increase the initial confidence of the car or bus, so as to improve the accuracy of the first confidence of the candidate vehicle with opening and closing windows.

[0125] Step 604, determining first confidences of other candidate vehicles other than the candidate vehicle with opening and closing windows according to the initial confidences of other candidate vehicles other than the candidate vehicle with opening and closing windows.

[0126] Among them, the initial confidences of other candidate vehicles except the candidate vehicles with opening and closing windows remain unchanged, that is, the initial confidences of other candidate vehicles except the candidate vehicles with opening and closing windows are used as the first confidences of other candidate vehicles except the candidate vehicles with opening and closing windows.

[0127] It should be noted that in Figure 3 In the corresponding embodiment, it is determined that the candidate transportation means may be the first candidate transportation means, that is, a bus or a subway. When the first candidate transportation means is determined to be a candidate transportation means with opening and closing windows, that is, a bus, according to the method of the embodiment of the present application, the fourth confidence adjustment coefficient can be further used to adjust the confidence coefficient of the bus that has been adjusted based on the first confidence adjustment coefficient, so as to improve the accuracy of the bus confidence coefficient in this scenario. Figure 5In the corresponding embodiment, when it is determined that the candidate means of transportation may be the third candidate means of transportation, that is, a car or an ordinary railway, the fourth confidence adjustment coefficient can be further used to adjust the confidence coefficient of the car that has been adjusted based on the third confidence adjustment coefficient, so as to improve the accuracy of the confidence coefficient of the car in this scenario.

[0128] In the vehicle determination method of the embodiment of the present application, it is determined that at least one candidate vehicle may be a candidate vehicle with openable and closable windows, and among the vehicles, cars and buses can open or close windows. Therefore, to determine that at least one candidate vehicle is a car or a bus, it is necessary to obtain the set fourth confidence adjustment coefficient to increase the initial confidence of the car or bus, thereby improving the accuracy of the first confidence of the candidate vehicle with openable and closable windows, thereby increasing the accuracy of the subsequent target vehicle determination.

[0129] Based on the above embodiment, in order to improve the accuracy of the target transportation currently taken by the determined object, the target confidence of at least one candidate transportation can be continuously determined, so as to improve the target transportation currently taken by the determined object based on multiple target confidences of at least one candidate transportation continuously determined. Figure 7 A flow chart of another method for determining a means of transport provided in an embodiment of the present application is shown as follows: Figure 7 As shown,

[0130] Step 701, obtaining the current first air pressure sequence.

[0131] Step 702: Detect the current motion state of the object according to the first air pressure sequence.

[0132] Step 703 , in response to the motion state being riding a vehicle, determining a first confidence level and a predicted confidence level of at least one candidate vehicle according to the first air pressure sequence.

[0133] Step 704 : determining a target confidence level of each candidate transportation tool according to the first confidence level and the predicted confidence level of each candidate transportation tool.

[0134] Among them, steps 701 to 704 can refer to the explanations in the aforementioned embodiments, and the principles are the same, so they will not be repeated here.

[0135] Step 705 , selecting a candidate vehicle with the greatest target confidence from the target confidence of at least one candidate vehicle as a target candidate vehicle.

[0136] In the embodiment of the present application, each candidate vehicle has a corresponding target confidence, and the candidate vehicle with the largest target confidence is screened out from the candidate vehicles with corresponding target confidence as the currently determined target candidate vehicle.

[0137] Step 706, obtaining a plurality of air pressure data collected before the first step counting sequence, and generating a plurality of second air pressure sequences according to the plurality of air pressure data and the plurality of air pressure data included in the first air pressure sequence.

[0138] In the embodiment of the present application, in order to improve the accuracy of the currently determined target vehicle, multiple air pressure data collected before the first pedometer sequence can be obtained, and a new air pressure sequence is formed according to the multiple air pressure data and the multiple air pressure data contained in the first air pressure sequence. A sliding window is used to move in the new air pressure sequence, and a second air pressure sequence is obtained each time it moves according to the set step length, thereby obtaining multiple second air pressure sequences. As an implementation method, the number of second air pressure sequences can be a set number, for example, 24, and the set step length is 5 seconds. Each second air pressure sequence has the same length as the first air pressure sequence, for example, also 5 minutes.

[0139] It should be noted that the second air pressure sequence may include the first air pressure sequence. In order to reduce the amount of calculation, when the second air pressure sequence that is the same as the first air pressure sequence is obtained based on sliding the sliding window, since the target candidate vehicle corresponding to the first air pressure sequence has been obtained, the second air pressure sequence that is the same as the first air pressure sequence is discarded, and only other second air pressure sequences are processed.

[0140] Step 707: Determine the target confidence of the target candidate vehicles corresponding to each second air pressure sequence.

[0141] Among them, the method for determining the target confidence of the target candidate transportation vehicle corresponding to each second air pressure sequence can refer to the method for determining the target confidence of the target candidate transportation vehicle corresponding to the first air pressure sequence in the aforementioned embodiment. The principle is the same and will not be repeated here.

[0142] Step 708 : In response to the multiple target candidate transportation vehicles being of the same type and the sum of the target confidences of the multiple target candidate transportation vehicles being greater than a confidence threshold, the target candidate transportation vehicle is used as the target transportation vehicle that the subject is currently riding.

[0143] In one implementation of the embodiment of the present application, after determining the target confidence of the target candidate transportation corresponding to the first air pressure sequence, it is stored in the cache queue. Then, after determining the target confidence of each target candidate transportation corresponding to the second air pressure sequence, it is also stored in the cache queue. When the cache queue contains the confidence of a set number of target candidate transportation, it is determined whether the types of the set number of target candidate transportation are of the same type. If they are of the same type, and the sum of the target confidences of the set number of target candidate transportation is greater than the confidence threshold, the target candidate transportation is used as the target transportation currently taken by the object. As an example, the set number is 24. If the types of the 24 target candidate transportations stored in the cache queue are all airplanes, and the sum of the target confidences of the 24 target candidate transportations is greater than the confidence threshold, it is determined that the current target transportation is an airplane. By calculating the continuous confidence, the accuracy of the target transportation determination is improved.

[0144] Step 709 : In response to the fact that the multiple target candidate vehicles are not of the same type, the sum of the target confidences of the target candidate vehicles of each type is calculated.

[0145] The multiple target candidate vehicles include target candidate vehicles determined according to the first air pressure sequence and target candidate vehicles determined according to each second air pressure sequence.

[0146] Step 710 , in response to the maximum value of the sum being greater than a confidence threshold, determining that the candidate transportation vehicle indicated by the type corresponding to the maximum value of the sum is the target transportation vehicle currently taken by the subject.

[0147] In an embodiment of the present application, in response to the fact that multiple target candidate transportation vehicles are not of the same type, the sum of the target confidences of each type of target candidate transportation vehicle is statistically calculated to obtain the sum of the confidences of multiple types of target candidate transportation vehicles. If the largest sum is greater than the confidence threshold, the target candidate transportation vehicle corresponding to the largest sum is used as the target transportation vehicle.

[0148] As an example, 24 target candidate vehicles and corresponding target confidences are stored in the cache queue. If the 24 target candidate vehicles are of three types, including target confidences of 9 airplanes and 15 high-speed trains, and the sum of the target confidences of the 9 airplanes is A, and the sum of the target confidences of the 15 high-speed trains is B, if B is greater than the confidence threshold, the high-speed train is determined to be the target vehicle.

[0149] It should be noted that, in response to the maximum value of the sum being less than or equal to the confidence threshold, it is determined that the currently riding vehicle cannot be identified.

[0150] In the vehicle determination method of the embodiment of the present application, the target confidence values ​​of multiple target candidate vehicles corresponding to multiple air pressure sequences are continuously determined, and the target vehicle is determined based on the target confidence values ​​and categories of the multiple target candidate vehicles, thereby increasing the accuracy of target vehicle determination.

[0151] Based on the above embodiment, when the target transportation vehicle currently taken by the user is determined, personalized services may be provided to the user, specifically including one or more of the following:

[0152] Commute Planning and Navigation: By identifying the mode of transportation, the app can provide tailored route suggestions, estimated arrival times, and real-time navigation instructions specific to the chosen mode. For example, if the user is taking the bus, the app can provide bus stop notifications and suggest the best transfers or alternate routes.

[0153] Travel companion: When traveling in an unfamiliar city or country, the app can use transportation mode recognition to provide information about public transportation options, including schedules, fares, and nearby stations. It can also provide users with suggestions for popular tourist destinations based on different modes of transportation.

[0154] Health and Fitness Tracking: Understanding transportation modes can enable apps to provide more accurate activity tracking and analysis. For example, it can differentiate between walking or running on the ground and taking public transportation, providing users with accurate step count, distance, and calories burned data.

[0155] Environmental impact analysis: By collecting data on users’ transportation modes, the app can estimate and provide insights into the impact of various modes of transportation on the environment. This information can encourage users to make more environmentally friendly choices and contribute to sustainable development.

[0156] Personalized recommendations: Using transportation mode recognition, the application can provide personalized recommendations for nearby attractions, restaurants, or entertainment venues based on the user's current location and selected transportation mode.

[0157] Safety and emergency services: In the event of an emergency, such as an accident or sudden weather change, apps can use traffic pattern data to alert authorities or provide safety information relevant to the user’s situation.

[0158] In order to implement the above embodiment, the embodiment of the present application also proposes a vehicle determination device.

[0159] Figure 8 A schematic diagram of the structure of a vehicle determination device provided in an embodiment of the present application.

[0160] like Figure 8 As shown, the device may include:

[0161] The acquisition module 81 is used to acquire the current first air pressure sequence.

[0162] A detection module 82, configured to detect a current motion state of the object according to the first air pressure sequence;

[0163] The first determination module 83 is used to determine a first confidence and a predicted confidence of at least one candidate vehicle according to the first air pressure sequence in response to the motion state being riding a vehicle.

[0164] The second determination module 84 is used to determine the target confidence of each of the candidate transportation tools according to the first confidence and the predicted confidence of each of the candidate transportation tools.

[0165] The third determination module 85 is configured to determine the target transportation tool that the subject is currently riding on according to the target confidence level of the at least one candidate transportation tool.

[0166] Further, in an implementation of the embodiment of the present application, the first determining module 83 is specifically configured to:

[0167] Dividing the first air pressure sequence into a plurality of sub-air pressure sequences based on a preset time interval;

[0168] Generate the mean air pressure sequence according to the air pressure mean values ​​and time sequence of the multiple sub-air pressure sequences;

[0169] A first confidence and a predicted confidence of the at least one candidate vehicle are determined based on the mean air pressure sequence.

[0170] In an implementation of the embodiment of the present application, the first determining module 83 is specifically configured to:

[0171] Calculating the similarity between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate transportation tool to obtain the similarity between the mean air pressure sequence and each set air pressure sequence;

[0172] Determining the initial confidence of each of the candidate transportation tools according to each of the similarities;

[0173] According to the initial confidence of each candidate transportation tool, a first confidence of each candidate transportation tool is determined.

[0174] In an implementation of the embodiment of the present application, the first determining module 83 is specifically configured to:

[0175] Converting the mean air pressure sequence from the time domain to the frequency domain, and determining the spectrum energy and the first energy of the main frequency of the mean air pressure sequence in the frequency domain;

[0176] In response to a ratio between the first energy and the spectrum energy being greater than a set threshold, determining a first confidence adjustment coefficient of a first candidate vehicle included in the at least one candidate vehicle according to a ratio between the ratio and the set threshold;

[0177] According to the first confidence adjustment coefficient of the first candidate transportation means, adjusting the initial confidence of the first candidate transportation means to obtain the first confidence of the first candidate transportation means;

[0178] According to the initial confidences of the other candidate vehicles except the first candidate vehicle, first confidences of the other candidate vehicles except the first candidate vehicle are determined.

[0179] In an implementation of the embodiment of the present application, the first determining module 83 is specifically configured to:

[0180] Determine multiple differences between the moments according to the mean air pressure at each moment in the mean air pressure sequence;

[0181] Determining standard deviations of a plurality of air pressure means according to a plurality of differences between the moments;

[0182] In response to the standard deviation being less than or equal to a standard deviation threshold, obtaining a set second confidence adjustment coefficient of a second candidate transportation tool included in the at least one candidate transportation tool;

[0183] According to the second confidence adjustment coefficient, adjusting the initial confidence of the second candidate transportation means to obtain a first confidence of the second candidate transportation means;

[0184] According to the initial confidences of the other candidate vehicles except the second candidate vehicle, first confidences of the other candidate vehicles except the second candidate vehicle are determined.

[0185] In an implementation of the embodiment of the present application, the first determining module 83 is specifically configured to:

[0186] In response to the standard deviation being greater than the standard deviation threshold, obtaining a third confidence adjustment coefficient set for a third candidate transportation tool included in the at least one candidate transportation tool;

[0187] According to the third confidence adjustment coefficient, adjusting the initial confidence of the third candidate transportation means to obtain a first confidence of the third candidate transportation means;

[0188] According to the initial confidences of the other candidate vehicles except the third candidate vehicle, first confidences of the other candidate vehicles except the third candidate vehicle are determined.

[0189] In an implementation of the embodiment of the present application, the first determining module 83 is specifically configured to:

[0190] Determine multiple differences between the moments according to the mean air pressure at each moment in the mean air pressure sequence;

[0191] In response to the absolute value of at least one difference being greater than an air pressure threshold, obtaining a fourth confidence adjustment coefficient of a candidate vehicle setting of an opening / closing type window included in the at least one candidate vehicle;

[0192] According to the fourth confidence adjustment coefficient, the initial confidence of the candidate transportation means of the opening and closing type window is adjusted to obtain the first confidence of the candidate transportation means of the opening and closing type window;

[0193] According to the initial confidences of other candidate vehicles other than the candidate vehicle for the opening and closing type window, the first confidences of other candidate vehicles other than the candidate vehicle for the opening and closing type window are determined.

[0194] In an implementation of the embodiment of the present application, the first determining module 83 is specifically configured to:

[0195] The mean air pressure sequence is input into the trained prediction model to determine the prediction confidence of the at least one candidate vehicle according to the output of the prediction model.

[0196] In an implementation of the embodiment of the present application, the first determining module 83 is specifically configured to:

[0197] Input the mean air pressure sequence into the trained time-frequency domain feature extraction network of the prediction model to obtain time-domain features and frequency-domain features;

[0198] Inputting the mean air pressure sequence into the trained time series feature extraction network of the prediction model to obtain time series features for characterizing contextual connections;

[0199] The time domain features, frequency domain features and time series features are fused and input into the fusion module of the prediction model to perform feature fusion, and classification is performed based on the fused features to obtain the prediction confidence of each of the candidate transportation tools.

[0200] In an implementation of the embodiment of the present application, the third determining module 85 is specifically configured to:

[0201] Selecting a candidate vehicle with the greatest target confidence from the target confidence of the at least one candidate vehicle as the target candidate vehicle;

[0202] Acquire a plurality of air pressure data collected before the first step counting sequence;

[0203] Generate multiple second air pressure sequences according to the multiple air pressure data and the multiple air pressure data included in the first air pressure sequence; wherein the second air pressure sequence has the same length as the first air pressure sequence;

[0204] Determining target confidences of target candidate vehicles corresponding to each of the second air pressure sequences;

[0205] In response to the multiple target candidate vehicles being of the same type and the sum of the target confidences of the multiple target candidate vehicles being greater than a confidence threshold, the target candidate vehicle is used as the target vehicle currently taken by the subject.

[0206] In an implementation of the embodiment of the present application, the third determining module 85 is specifically configured to:

[0207] In response to the plurality of target candidate vehicles not being of the same type, summing up the target confidences of the target candidate vehicles of different types;

[0208] In response to the maximum value of the sum being greater than a confidence threshold, it is determined that the target candidate vehicle indicated by the type corresponding to the maximum value of the sum is the target vehicle currently being ridden by the subject.

[0209] It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment, and will not be repeated here.

[0210] In the vehicle determination device of the embodiment of the present application, the current first pedometer sequence and the first air pressure sequence are obtained, and the current motion state of the object is detected according to the first pedometer sequence and / or the first air pressure sequence. In response to the motion state being riding a vehicle, the first confidence of at least one candidate vehicle of the object is determined according to the first air pressure sequence, and the predicted confidence of at least one candidate vehicle is determined. The target confidence of each candidate vehicle is determined according to the first confidence and the predicted confidence of each candidate vehicle. The target vehicle currently ridden by the object is determined according to the target confidence of at least one candidate vehicle. The first confidence of the possible candidate vehicles is determined by the air pressure characteristics, thereby improving the accuracy. The target confidence of each candidate vehicle is determined according to the predicted confidence and the first confidence of each candidate vehicle corresponding to the first air pressure sequence, thereby improving the accuracy of the target confidence of each candidate vehicle, thereby improving the accuracy of the target vehicle determination.

[0211] In order to implement the above embodiments, the present application also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the above method embodiments is implemented.

[0212] In order to implement the above embodiments, the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in the above method embodiments is implemented.

[0213] In order to implement the above embodiments, the present application also proposes a computer program product on which a computer program is stored. When the computer program is executed by a processor, the method described in the above method embodiments is implemented.

[0214] Fig. 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a message transceiver device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0215] Reference Fig. 9 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0216] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0217] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0218] The power component 806 provides power to the various components of the electronic device 800. The power component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

[0219] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0220] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0221] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0222] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of the components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0223] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 4G or 5G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0224] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0225] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of an electronic device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0226] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0227] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0228] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0229] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0230] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0231] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0232] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0233] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for determining a means of transport, characterized in that: include: Get the current first air pressure sequence; detecting a current motion state of the object according to the first air pressure sequence; In response to the motion state being riding a vehicle, determining a first confidence and a predicted confidence of at least one candidate vehicle according to the first air pressure sequence; Determining a target confidence of each of the candidate transportation tools according to the first confidence and the predicted confidence of each of the candidate transportation tools; The target vehicle currently taken by the subject is determined according to the target confidence level of the at least one candidate vehicle.

2. The method according to claim 1, characterized in that Determining a first confidence level and a predicted confidence level of at least one candidate transportation tool of the object according to the first air pressure sequence includes: Dividing the first air pressure sequence into a plurality of sub-air pressure sequences based on a preset time interval; Generate the mean air pressure sequence according to the air pressure mean values ​​and time sequence of the multiple sub-air pressure sequences; A first confidence and a predicted confidence of the at least one candidate vehicle are determined based on the mean air pressure sequence.

3. The method according to claim 2, characterized in that Determining a first confidence level of at least one candidate vehicle according to the mean air pressure sequence includes: Calculating the similarity between the mean air pressure sequence and the set air pressure sequence corresponding to each candidate transportation tool to obtain the similarity between the mean air pressure sequence and each set air pressure sequence; Determining the initial confidence of each of the candidate transportation tools according to each of the similarities; According to the initial confidence of each candidate transportation tool, a first confidence of each candidate transportation tool is determined.

4. The method according to claim 3, characterized in that Determining the first confidence level of each candidate transportation tool according to the initial confidence level of each candidate transportation tool comprises: Converting the mean air pressure sequence from the time domain to the frequency domain, and determining the spectrum energy and the first energy of the main frequency of the mean air pressure sequence in the frequency domain; In response to a ratio between the first energy and the spectrum energy being greater than a set threshold, determining a first confidence adjustment coefficient of a first candidate vehicle included in the at least one candidate vehicle according to a ratio between the ratio and the set threshold; According to the first confidence adjustment coefficient of the first candidate transportation means, adjusting the initial confidence of the first candidate transportation means to obtain the first confidence of the first candidate transportation means; According to the initial confidences of the other candidate vehicles except the first candidate vehicle, first confidences of the other candidate vehicles except the first candidate vehicle are determined.

5. The method according to claim 3, characterized in that Determining the first confidence level of each candidate transportation tool according to the initial confidence level of each candidate transportation tool comprises: Determine multiple differences between the moments according to the mean air pressure at each moment in the mean air pressure sequence; Determining standard deviations of a plurality of air pressure means according to a plurality of differences between the moments; In response to the standard deviation being less than or equal to a standard deviation threshold, obtaining a set second confidence adjustment coefficient of a second candidate transportation tool included in the at least one candidate transportation tool; According to the second confidence adjustment coefficient, adjusting the initial confidence of the second candidate transportation means to obtain a first confidence of the second candidate transportation means; According to the initial confidences of the other candidate vehicles except the second candidate vehicle, first confidences of the other candidate vehicles except the second candidate vehicle are determined.

6. The method according to claim 5, characterized in that The method further comprises: In response to the standard deviation being greater than the standard deviation threshold, obtaining a third confidence adjustment coefficient set for a third candidate transportation tool included in the at least one candidate transportation tool; According to the third confidence adjustment coefficient, adjusting the initial confidence of the third candidate transportation means to obtain a first confidence of the third candidate transportation means; According to the initial confidences of the other candidate vehicles except the third candidate vehicle, first confidences of the other candidate vehicles except the third candidate vehicle are determined.

7. The method according to claim 3, characterized in that Determining the first confidence level of each candidate transportation tool according to the initial confidence level of each candidate transportation tool comprises: Determine multiple differences between the moments according to the mean air pressure at each moment in the mean air pressure sequence; In response to the absolute value of at least one difference being greater than an air pressure threshold, obtaining a fourth confidence adjustment coefficient of a candidate vehicle setting of an opening / closing type window included in the at least one candidate vehicle; According to the fourth confidence adjustment coefficient, the initial confidence of the candidate transportation means of the opening and closing type window is adjusted to obtain the first confidence of the candidate transportation means of the opening and closing type window; According to the initial confidences of other candidate vehicles other than the candidate vehicle for the opening and closing type window, the first confidences of other candidate vehicles other than the candidate vehicle for the opening and closing type window are determined.

8. The method according to claim 1, characterized in that Determining the prediction confidence of the at least one candidate transportation tool according to the mean air pressure sequence includes: The mean air pressure sequence is input into the trained prediction model to determine the prediction confidence of the at least one candidate vehicle according to the output of the prediction model.

9. The method according to claim 8, characterized in that The step of inputting the mean air pressure sequence into a trained prediction model to determine the prediction confidence of the at least one candidate transportation tool according to an output of the prediction model comprises: Input the mean air pressure sequence into the trained time-frequency domain feature extraction network of the prediction model to obtain time-domain features and frequency-domain features; Inputting the mean air pressure sequence into the trained time series feature extraction network of the prediction model to obtain time series features for characterizing contextual connections; The time domain features, frequency domain features and time series features are fused and input into the fusion module of the prediction model to perform feature fusion, and classification is performed based on the fused features to obtain the prediction confidence of each of the candidate transportation tools.

10. The method according to claim 1, characterized in that The step of determining the target transportation tool currently taken by the subject according to the target confidence level of the at least one candidate transportation tool comprises: Selecting a candidate vehicle with the largest target confidence from the target confidence of the at least one candidate vehicle as the target candidate vehicle; Acquire a plurality of air pressure data collected before the first step counting sequence; Generate multiple second air pressure sequences according to the multiple air pressure data and the multiple air pressure data included in the first air pressure sequence; wherein the second air pressure sequence has the same length as the first air pressure sequence; Determining target confidences of target candidate vehicles corresponding to each of the second air pressure sequences; In response to the multiple target candidate vehicles being of the same type and the sum of the target confidences of the multiple target candidate vehicles being greater than a confidence threshold, the target candidate vehicle is used as the target vehicle currently taken by the subject.

11. The method according to claim 10, characterized in that The method further comprises: In response to the plurality of target candidate vehicles not being of the same type, summing up the target confidences of the target candidate vehicles of different types; In response to the maximum value of the sum being greater than a confidence threshold, it is determined that the target candidate vehicle indicated by the type corresponding to the maximum value of the sum is the target vehicle currently being ridden by the subject.

12. A means of transport determination device, characterized in that: include: An acquisition module, used for acquiring the current first air pressure sequence; a detection module, configured to detect a current motion state of the object according to the first air pressure sequence; A first determination module, configured to determine, in response to the motion state being riding a vehicle, a first confidence level and a prediction confidence level of at least one candidate vehicle according to the first air pressure sequence; A second determination module, configured to determine a target confidence of each of the candidate transportation tools according to the first confidence and the predicted confidence of each of the candidate transportation tools; The third determination module is used to determine the target transportation tool that the subject is currently riding according to the target confidence level of the at least one candidate transportation tool.

13. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 11 is implemented.

14. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images