A method, device, equipment and storage medium for vehicle fuel anti-theft alarm

Abstract

The present invention discloses a vehicle fuel anti-theft alarm method, device, equipment and storage medium. The method includes: detecting the number of times the fuel tank cap is touched through a touch sensing module on the fuel tank cap; collecting sound data through a sound collection module inside the fuel tank cap and comparing the similarity with preset target damage sound data to obtain a target sound comparison result; obtaining the fuel reduction amount in the fuel tank within a preset time; determining the current theft risk level according to the number of times of being touched, the target sound comparison result, the fuel reduction amount and the current vehicle key sensing situation; and determining and executing the target alarm action corresponding to the current theft risk level based on the corresponding relationship between each theft risk level and each alarm action. The present invention can detect abnormal conditions of the fuel tank from multiple aspects, thereby accurately determining the current theft risk level of vehicle fuel, and further being able to execute corresponding alarm actions according to the current theft risk level, significantly improving the anti-theft effect for vehicle fuel.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle anti-theft, and in particular to a vehicle fuel anti-theft alarm method, device, terminal device and computer-readable storage medium. Background Art

[0002] With the continuous increase in the vehicle ownership, the incidents of vehicle fuel theft are not uncommon. The theft of vehicle fuel will not only cause economic losses to users, but also reduce the driving range of the vehicle, thus delaying the travel plans of users. The existing fuel anti-theft methods usually rely on the lock of the vehicle fuel tank cap itself. However, when the vehicle fuel is stolen, the user is usually far away from the vehicle and it is difficult to detect the theft of vehicle fuel. And when the lock of the vehicle fuel tank cap itself is damaged, the prior art cannot send out an alarm, resulting in poor anti-theft effect. Summary of the Invention

[0003] The present invention provides a vehicle fuel anti-theft alarm method, device, equipment and storage medium. By detecting the number of touches on the fuel tank cap, the similarity between the sound around the fuel tank and a preset damage sound, the fuel reduction amount in the fuel tank within a preset time, and the current vehicle key sensing situation, the current theft risk level can be accurately determined. Furthermore, corresponding alarm actions can be executed according to the current theft risk level, significantly improving the anti-theft effect of vehicle fuel.

[0004] To solve the above technical problems, the first aspect of the embodiments of the present invention provides a vehicle fuel anti-theft alarm method, including the following steps:

[0005] Detect the number of touches on the fuel tank cap through a touch sensing module preset on the fuel tank cap;

[0006] Based on a sound collection module preset in the fuel tank cap, obtain the sound data collected by the sound collection module, compare the sound data with preset target damage sound data, and obtain a target sound comparison result;

[0007] Obtain the fuel reduction amount in the fuel tank within a preset time;

[0008] Determine the current theft risk level according to the number of touches, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation;

[0009] Based on the corresponding relationship between each preset theft risk level and each alarm action, determine the target alarm action corresponding to the current theft risk level and execute it.

[0010] As a preferred solution, the step of detecting the number of touches on the fuel tank cap through a touch sensing module preset on the fuel tank cap specifically includes the following steps:

[0011] Receive the signals sent by the touch sensing module within a preset detection time, and statistically obtain the number of signal transmissions;

[0012] Determine the number of times the fuel tank cap is touched within the preset detection time according to the number of signal transmissions.

[0013] As a preferred solution, comparing the voice data with preset target destruction voice data to obtain a target voice comparison result specifically includes the following steps:

[0014] Preprocess the voice data and the target destruction voice data respectively to obtain preprocessed voice data to be recognized and preprocessed reference voice data;

[0015] Perform auditory conversion processing on the preprocessed voice data to be recognized and the preprocessed reference voice data respectively to obtain the voice data to be recognized after auditory conversion and the reference voice data after auditory conversion;

[0016] Perform perceptual subtraction on the preprocessed voice data to be recognized and the voice data to be recognized after auditory conversion to obtain the voice data to be recognized after perceptual subtraction;

[0017] Perform perceptual subtraction on the preprocessed reference voice data and the reference voice data after auditory conversion to obtain the reference voice data after perceptual subtraction;

[0018] Perform symmetric processing, L1 - norm and L3 - norm to obtain the Bark domain mean value processing, bad interval realignment processing, and time - domain averaging processing on the voice data to be recognized after perceptual subtraction and the reference voice data after perceptual subtraction in sequence to obtain the voice data to be recognized after time - domain averaging and the reference voice data after time - domain averaging;

[0019] Calculate the similarity score between the voice data to be recognized after time - domain averaging and the reference voice data after time - domain averaging;

[0020] When the similarity score is greater than a preset similarity score threshold, determine that the voice data is abnormal voice data;

[0021] When the similarity score is less than or equal to the preset similarity score threshold, determine that the voice data is normal voice data.

[0022] As a preferred solution, the current vehicle key sensing situation is that the vehicle key is sensed or not sensed.

[0023] As a preferred solution, determining the current theft risk degree according to the number of touches, the target voice comparison result, the fuel reduction amount, and the current vehicle key sensing situation specifically includes the following steps:

[0024] When the number of touches meets a preset abnormal touch number, based on the risk scores corresponding to each abnormal touch number range in a preset risk score table, determine a first risk score corresponding to the number of touches;

[0025] Based on the risk scores corresponding to each voice comparison result in the preset risk score table, determine a second risk score corresponding to the target voice comparison result;

[0026] When the fuel reduction amount meets a preset abnormal fuel reduction amount, based on the risk scores corresponding to each fuel reduction amount range in the preset risk score table, determine a third risk score corresponding to the fuel reduction amount;

[0027] Based on the risk scores corresponding to each vehicle key sensing situation in the preset risk score table, determine a fourth risk score corresponding to the current vehicle key sensing situation;

[0028] According to the first risk score, the second risk score, the third risk score, and the fourth risk score, calculate and obtain a current total risk score and use it as a quantization value of the current theft risk level.[[ID=!!15]]

[0029] As a preferred solution, based on the corresponding relationship between each preset theft risk level and each alarm action, determine a target alarm action corresponding to the current theft risk level and execute it, which specifically includes the following steps:

[0030] Based on the current total risk score corresponding to the current theft risk level and the corresponding relationship between each preset risk score and each alarm action, determine a target alarm action corresponding to the current total risk score and execute it.

[0031] As a preferred solution, the alarm action includes one or more of controlling the vehicle lights to flash, controlling the vehicle to emit an alarm, controlling a camera preset on the vehicle to collect images around the vehicle, sending an alarm message to a user terminal, and controlling the vehicle to sound the horn.

[0032] A second aspect of an embodiment of the present invention provides a vehicle fuel anti-theft alarm device, including:

[0033] A touch detection module, configured to detect the number of touches of the fuel tank cap through a touch sensing module preset on the fuel tank cap;

[0034] A voice comparison module, configured to obtain voice data collected by a voice collection module based on a voice collection module preset in the fuel tank cap, compare the voice data with preset target damage voice data for similarity, and obtain a target voice comparison result;

[0035] A fuel quantity detection module for obtaining the fuel reduction in the fuel tank within a preset time;

[0036] A theft risk level determination module for determining the current theft risk level according to the number of touches, the target sound comparison result, the fuel reduction, and the current vehicle key sensing situation;

[0037] An alarm module for determining and executing the target alarm action corresponding to the current theft risk level based on the corresponding relationship between each preset theft risk level and each alarm action.

[0038] A third aspect of the embodiments of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the vehicle fuel anti-theft alarm method described in any item of the first aspect is implemented.

[0039] A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the vehicle fuel anti-theft alarm method described in any item of the first aspect.

[0040] Compared with the prior art, the beneficial effect of the embodiments of the present invention is that by detecting the number of touches on the fuel tank cap, the similarity between the sound around the fuel tank and the preset destruction sound, the fuel reduction in the fuel tank within a preset time, and the current vehicle key sensing situation, the current theft risk level can be accurately determined, and then the corresponding alarm action can be executed according to the current theft risk level, significantly improving the anti-theft effect of vehicle fuel. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a schematic flowchart of the vehicle fuel anti-theft alarm method in the embodiments of the present invention;

[0042] Figure 2 is a schematic structural diagram of the vehicle fuel anti-theft alarm device in the embodiments of the present invention. DETAILED DESCRIPTION

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0044] See Figure 1, in the first aspect of the embodiment of the present invention, a vehicle fuel anti-theft alarm method is provided, including the following steps S1 to S5:

[0045] Step S1, detecting the number of times the fuel tank cap is touched through a touch sensing module preset on the fuel tank cap;

[0046] Step S2, based on a sound collection module preset in the fuel tank cap, obtaining the sound data collected by the sound collection module, comparing the similarity of the sound data with preset target damage sound data, and obtaining a target sound comparison result;

[0047] Step S3, obtaining the fuel reduction amount of the fuel tank within a preset time;

[0048] Step S4, determining the current theft risk degree according to the number of times of touching, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation;

[0049] Step S5, based on the corresponding relationship between each preset theft risk degree and each alarm action, determining the target alarm action corresponding to the current theft risk degree and executing it.

[0050] Specifically, in this embodiment, a touch sensing module such as a touch button is preset on the fuel tank cap. It can be understood that the fuel tank cap is a cover plate provided on one side of the vehicle body, rather than a knob cover provided at the fuel tank opening. Generally, when a user needs to refuel the vehicle, the fuel tank cap is first popped out from one side of the vehicle body by operating the fuel tank cap opening button, and when refueling is completed, the fuel tank cap is manually pressed back to the initial position. Therefore, the fuel tank cap will be touched 1 to 2 times during this process. If a thief tries to forcefully open the fuel tank cap to steal fuel, the fuel tank cap will surely be touched multiple times. Therefore, by detecting the number of times the fuel tank cap is touched, it is possible to assist in judging whether there is a risk of vehicle fuel theft.

[0051] Furthermore, since a thief usually pries open the fuel tank cap forcefully to damage the lock of the fuel tank cap when trying to open it, in this embodiment, a sound collection module preset in the fuel tank cap is used to collect the sound data around the fuel tank, and the similarity of the sound data is compared with the preset target damage sound data, so that it is possible to judge whether the collected sound data is abnormal according to the target sound comparison result. It can be understood that the target damage sound data can be collected and pre-stored specifically during the fuel tank cap tilting test before the vehicle leaves the factory.

[0052] Furthermore, when a thief steals fuel, the fuel reduction amount in the fuel tank per unit time is necessarily more than that during normal use. Therefore, in this embodiment, the fuel reduction amount of the fuel tank within a preset time is obtained to assist in judging whether there is a risk of vehicle fuel theft.

[0053] Further, based on the number of touches, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation, determine the current theft risk level. It should be noted that in this embodiment, in addition to considering the number of touches, the target sound comparison result, and the fuel reduction amount, the current vehicle key sensing situation is also considered. If only the number of touches, the target sound comparison result, and the fuel reduction amount are considered, the probability of false alarm may be relatively high. By using the current vehicle key sensing situation to determine whether the user is near the vehicle, the probability of false alarm can be effectively reduced, and the current theft risk level can be determined more accurately.

[0054] Further, based on the correspondence between each preset theft risk level and each alarm action, determine the target alarm action corresponding to the current theft risk level and execute it. It can be understood that in this embodiment, different alarm actions are preset according to different theft risk levels, so that appropriate alarm schemes can be determined according to different risk scenarios, ensuring the anti-theft effect while being able to more reasonably implement the vehicle fuel anti-theft alarm measures.

[0055] As a preferred solution, the step of detecting the number of touches of the fuel tank cap by using a touch sensing module preset on the fuel tank cap specifically includes the following steps:

[0056] Receive the signals sent by the touch sensing module within a preset detection time, and statistically obtain the number of signal transmissions;

[0057] Determine the number of touches of the fuel tank cap within the preset detection time according to the number of signal transmissions.

[0058] Specifically, when the touch sensing module senses being touched, it will send out a signal once. Therefore, in this embodiment, by receiving the signals sent by the touch sensing module within a preset detection time to statistically obtain the number of signal transmissions, the number of touches of the fuel tank cap within the preset detection time can be determined accordingly.

[0059] As a preferred solution, the step of comparing the similarity between the sound data and the preset target damage sound data to obtain the target sound comparison result specifically includes the following steps:

[0060] Preprocess the sound data and the target damage sound data respectively to obtain preprocessed sound data to be recognized and preprocessed reference sound data;

[0061] Perform auditory conversion processing on the preprocessed sound data to be recognized and the preprocessed reference sound data respectively to obtain the sound data to be recognized after auditory conversion and the reference sound data after auditory conversion;

[0062] Perform perceptual subtraction on the preprocessed sound data to be recognized and the sound data to be recognized after auditory conversion to obtain the sound data to be recognized after perceptual subtraction;

[0063] Perform perceptual subtraction on the preprocessed reference sound data and the reference sound data after auditory conversion to obtain the reference sound data after perceptual subtraction;

[0064] Perform symmetric processing, L1 norm and L3 norm to calculate the Bark domain mean, bad interval realignment processing, and time domain averaging processing on the sound data to be recognized after perceptual subtraction and the reference sound data after perceptual subtraction in sequence to obtain the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging;

[0065] Calculate the similarity score between the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging;

[0066] When the similarity score is greater than the preset similarity score threshold, determine that the sound data is abnormal sound data;

[0067] When the similarity score is less than or equal to the preset similarity score threshold, determine that the sound data is normal sound data.

[0068] It should be noted that the preprocessing performed on the sound data and the target damage sound data in this embodiment includes level adjustment, IRS filtering, delay compensation, and linear frequency compensation. Since the collected sound data and the target damage sound data may come from different speech systems, resulting in differences in signal levels, in order to facilitate comparison, it is necessary to adjust both to a unified and constant level; IRS filtering can simulate the transmission frequency characteristics and fully consider the characteristics of the sound data and the target damage sound data.

[0069] Furthermore, perform auditory conversion processing on the preprocessed sound data to be recognized and the preprocessed reference sound data respectively to obtain the sound data to be recognized after auditory conversion and the reference sound data after auditory conversion. Specifically, the process of auditory conversion includes: adding a Hanning window to the preprocessed sound data to be recognized and the preprocessed reference sound data respectively; performing Fourier transform on the preprocessed sound data to be recognized and the preprocessed reference sound data after adding the Hanning window; mapping the spectrum after Fourier transform to a Bark spectrum; mapping the Bark spectrum to loudness.

[0070] Furthermore, in this embodiment, considering the interference difference generated during the auditory conversion of the sound data to be recognized and the reference sound data during preprocessing, through perceptual subtraction processing, symmetry processing, calculating the Bark domain mean using the L1 norm and L3 norm, bad interval realignment processing, and time domain averaging processing to remove perturbations and distortions during the auditory conversion, and finally calculating the similarity score between the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging.

[0071] When the similarity score is greater than the preset similarity score threshold, the sound data is determined to be abnormal sound data; when the similarity score is less than or equal to the preset similarity score threshold, the sound data is determined to be normal sound data.

[0072] As a preferred solution, the current vehicle key sensing situation is either sensing the vehicle key or not sensing the vehicle key.

[0073] It should be noted that existing vehicles usually have the function of sensing the vehicle key, that is, when the vehicle key is within the sensing range of the vehicle, the vehicle can respond to the signal sent by the vehicle key to perform related actions, such as unlocking the vehicle. Therefore, in this embodiment, through the current vehicle key sensing situation, it can be determined whether the user is near the vehicle. When the current vehicle key sensing situation is sensing the vehicle key, it is determined that the user is near the vehicle, and the risk of the fuel tank being stolen is relatively low; when the current vehicle key sensing situation is not sensing the vehicle key, it is determined that the user is not near the vehicle, and the risk of the fuel tank being stolen is relatively high.

[0074] As a preferred solution, determining the current theft risk degree according to the number of touches, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation specifically includes the following steps:

[0075] When the number of touches meets the preset abnormal touch number, based on the risk scores corresponding to each abnormal touch number interval in the preset risk score table, determine the first risk score corresponding to the number of touches;

[0076] Based on the risk scores corresponding to each sound comparison result in the preset risk score table, determine the second risk score corresponding to the target sound comparison result;

[0077] When the fuel reduction amount meets the preset abnormal fuel reduction amount, based on the risk scores corresponding to each fuel reduction amount interval in the preset risk score table, determine the third risk score corresponding to the fuel reduction amount;

[0078] Based on the risk scores corresponding to each vehicle key sensing situation in the preset risk score table, determine the fourth risk score corresponding to the current vehicle key sensing situation;

[0079] Based on the first risk score, the second risk score, the third risk score, and the fourth risk score, calculate to obtain the current total risk score and use it as the quantization value of the current risk of theft.

[0080] Specifically, in order to be able to quantify the current risk of theft in this embodiment, a risk score table is pre-constructed to clarify the risk scores corresponding to various situations. When the number of touches meets the preset abnormal touch times, for example, when the number of touches exceeds 4 times within 10s, it is determined as abnormal touch. Based on the risk scores corresponding to each abnormal touch times interval in the risk score table, determine the first risk score corresponding to the number of touches. It can be understood that the more the number of touches within the preset detection time, the greater the current risk of the fuel tank being stolen. Therefore, in this embodiment, different abnormal touch times intervals are preset to correspond to different risk scores. Exemplarily, the risk score corresponding to the number of touches being 5 - 10 times within 10s is 1 point; the risk score corresponding to the number of touches being more than 10 times within 10s is 2 points.

[0081] Based on the risk scores corresponding to each sound comparison result in the risk score table, determine the second risk score corresponding to the target sound comparison result. Exemplarily, when the target sound comparison result determines that the collected sound data is normal sound data, that is, it does not match the characteristics of the target damaged sound data, the corresponding risk score is 1 point; when the target sound comparison result determines that the collected sound data is abnormal sound data, that is, it matches the characteristics of the target damaged sound data, the corresponding risk score is 2 points.

[0082] When the fuel reduction amount meets the preset abnormal fuel reduction amount, for example, when the fuel reduction amount exceeds 4L within 1min, based on the risk scores corresponding to each fuel reduction amount interval in the risk score table, determine the third risk score corresponding to the fuel reduction amount. Exemplarily, when the fuel reduction amount within 1min is 5 - 10L, the corresponding risk score is 1 point; when the fuel reduction amount within 1min is more than 10L, the corresponding risk score is 2 points.

[0083] Based on the risk scores corresponding to each vehicle key sensing situation in the risk score table, determine the fourth risk score corresponding to the current vehicle key sensing situation. Exemplarily, the risk score corresponding to sensing the vehicle key is -2 points, indicating that the current risk of the fuel tank being stolen is relatively low; the risk score corresponding to not sensing the vehicle key is 2 points.

[0084] Add the first risk score, the second risk score, the third risk score, and the fourth risk score to obtain the current total risk score, thereby completing the quantification of the current risk of theft.

[0085] As one of the optional embodiments, the risk score table is shown in Table 1 below:

[0086] Table 1 Risk Score Table

[0087]

[0088] As a preferred solution, based on the corresponding relationship between each preset stolen risk level and each alarm action, determining the target alarm action corresponding to the current stolen risk level and executing it specifically includes the following steps:

[0089] Based on the current total risk score corresponding to the current stolen risk level and the corresponding relationship between each preset risk score and each alarm action, determining the target alarm action corresponding to the current total risk score and executing it.

[0090] Specifically, in this embodiment, the corresponding relationship between each risk score and each alarm action is pre-constructed. After determining the current total risk score corresponding to the current stolen risk level, based on this corresponding relationship, determining the target alarm action corresponding to the current total risk score and executing it, so as to realize the differentiation of alarm measures corresponding to different risk scenarios.

[0091] It should be noted that in order to avoid the mis-triggering of alarm measures, based on considering the risk scores corresponding to various risk situations, the initial risk score for triggering alarm measures in this embodiment is set to a relatively large score. Exemplarily, based on the above risk score table, the initial risk score for triggering alarm measures is set to 4 points.

[0092] As a preferred solution, the alarm actions include one or more of controlling the vehicle lights to flash, controlling the vehicle to emit an alarm, controlling the camera preset on the vehicle to collect images around the vehicle, sending an alarm message to the user terminal, and controlling the vehicle to honk.

[0093] As one of the optional embodiments, the corresponding relationship table between each risk score and each alarm action is shown in Table 2 below:

[0094] Table 2 Corresponding Relationship Table between Each Risk Score and Each Alarm Action

[0095]

[0096] A vehicle fuel anti-theft alarm method provided by an embodiment of the present invention can accurately determine the current stolen risk level by detecting the number of touches on the fuel tank cap, the similarity between the sound around the fuel tank and the preset damage sound, the fuel reduction amount in the fuel tank within a preset time, and the current vehicle key sensing situation. Furthermore, corresponding alarm actions can be executed according to the current stolen risk level, significantly improving the anti-theft effect of vehicle fuel.

[0097] See Figure 2 , the second aspect of the embodiment of the present invention provides a vehicle fuel anti-theft alarm device, including:

[0098] A touch detection module 201, configured to detect the number of times the fuel tank cap is touched through a touch sensing module preset on the fuel tank cap;

[0099] A sound comparison module 202, configured to obtain sound data collected by the sound collection module based on the sound collection module preset in the fuel tank cap, compare the sound data with preset target damage sound data for similarity, and obtain a target sound comparison result;

[0100] A fuel quantity detection module 203, configured to obtain the fuel reduction amount in the fuel tank within a preset time;

[0101] A theft risk degree determination module 204, configured to determine the current theft risk degree according to the number of times of being touched, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation;

[0102] An alarm module 205, configured to determine a target alarm action corresponding to the current theft risk degree based on the corresponding relationship between preset theft risk degrees and respective alarm actions, and execute the target alarm action.

[0103] As a preferred solution, the touch detection module 201 is configured to detect the number of times the fuel tank cap is touched through a touch sensing module preset on the fuel tank cap, and specifically includes:

[0104] Receiving signals sent by the touch sensing module within a preset detection time, and statistically obtaining the number of signal transmissions;

[0105] Determining the number of times the fuel tank cap is touched within the preset detection time according to the number of signal transmissions.

[0106] As a preferred solution, the sound comparison module 202 is configured to compare the sound data with preset target damage sound data for similarity to obtain a target sound comparison result, and specifically includes:

[0107] Preprocessing the sound data and the target damage sound data respectively to obtain preprocessed sound data to be recognized and preprocessed reference sound data;

[0108] Performing auditory conversion processing on the preprocessed sound data to be recognized and the preprocessed reference sound data respectively to obtain the sound data to be recognized after auditory conversion and the reference sound data after auditory conversion;

[0109] Perform perceptual subtraction on the preprocessed sound data to be recognized and the audibly transformed sound data to be recognized, to obtain the sound data to be recognized after perceptual subtraction;

[0110] Perform perceptual subtraction on the preprocessed reference sound data and the audibly transformed reference sound data, to obtain the reference sound data after perceptual subtraction;

[0111] Perform symmetric processing, L1 norm and L3 norm to calculate the Bark domain mean, bad interval realignment processing, and time domain averaging processing on the sound data to be recognized after perceptual subtraction and the reference sound data after perceptual subtraction in sequence, to obtain the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging;

[0112] Calculate the similarity score between the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging;

[0113] When the similarity score is greater than the preset similarity score threshold, determine that the sound data is abnormal sound data;

[0114] When the similarity score is less than or equal to the preset similarity score threshold, determine that the sound data is normal sound data.

[0115] As a preferred solution, the current vehicle key sensing situation is that the vehicle key is sensed or not sensed.

[0116] As a preferred solution, the stolen risk degree determination module 204 is used to determine the current stolen risk degree according to the number of touches, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation, specifically including:

[0117] When the number of touches meets the preset abnormal number of touches, based on the risk scores corresponding to each abnormal number of touches interval in the preset risk score table, determine the first risk score corresponding to the number of touches;

[0118] Based on the risk scores corresponding to each sound comparison result in the preset risk score table, determine the second risk score corresponding to the target sound comparison result;

[0119] When the fuel reduction amount meets the preset abnormal fuel reduction amount, based on the risk scores corresponding to each fuel reduction amount interval in the preset risk score table, determine the third risk score corresponding to the fuel reduction amount;

[0120] Based on the risk scores corresponding to each vehicle key sensing situation in the preset risk score table, determine the fourth risk score corresponding to the current vehicle key sensing situation;

[0121] Based on the first risk score, the second risk score, the third risk score, and the fourth risk score, calculate to obtain a current total risk score and use it as a quantization value of the current risk of theft.

[0122] As a preferred solution, the alarm module 205 is configured to determine and execute a target alarm action corresponding to the current risk of theft based on a preset correspondence between each risk of theft and each alarm action, specifically including:

[0123] Based on the current total risk score corresponding to the current risk of theft and a preset correspondence between each risk score and each alarm action, determine and execute the target alarm action corresponding to the current total risk score.

[0124] As a preferred solution, the alarm action includes one or more of controlling the vehicle lights to flash, controlling the vehicle to emit an alarm, controlling a camera preset on the vehicle to collect images around the vehicle, sending an alarm message to a user terminal, and controlling the vehicle to sound a horn.

[0125] It should be noted that a vehicle fuel anti-theft alarm device provided in an embodiment of the present invention can implement all processes of the vehicle fuel anti-theft alarm method described in any of the above embodiments. The functions of each module in the device and the achieved technical effects are respectively the same as the functions and the achieved technical effects of the vehicle fuel anti-theft alarm method described in the above embodiments, and will not be elaborated here.

[0126] A third aspect of an embodiment of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the vehicle fuel anti-theft alarm method described in any of the embodiments of the first aspect.

[0127] The terminal device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. The terminal device may further include input / output devices, network access devices, a bus, etc.

[0128] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal device, and connects all parts of the entire terminal device through various interfaces and lines.

[0129] The memory can be used to store the computer program and / or module. The processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and by calling the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0130] A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the vehicle fuel anti-theft alarm method described in any embodiment of the first aspect.

[0131] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary hardware platform. Of course, it can also be implemented entirely through hardware. Based on such an understanding, all or part of the technical solution of the present invention that contributes to the background art can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0132] The above is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A vehicle fuel anti-theft alarm method, characterized in that, Including the following steps: Detect the number of times the fuel tank cap is touched through a touch sensing module preset on the fuel tank cap; Based on a sound acquisition module preset inside the fuel tank cap, obtain the sound data collected by the sound acquisition module, compare the similarity between the sound data and preset target damage sound data, and obtain a target sound comparison result; Obtain the fuel reduction amount of the fuel tank within a preset time; Determine the current theft risk level according to the number of touches, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation; Based on the corresponding relationship between each preset theft risk level and each alarm action, determine the target alarm action corresponding to the current theft risk level and execute it; Among them, the step of comparing the similarity between the sound data and the preset target damage sound data to obtain a target sound comparison result specifically includes the following steps: Perform preprocessing on the sound data and the target damage sound data respectively to obtain preprocessed sound data to be recognized and preprocessed reference sound data; Perform auditory conversion processing on the preprocessed sound data to be recognized and the preprocessed reference sound data respectively to obtain the sound data to be recognized after auditory conversion and the reference sound data after auditory conversion; Perform perceptual subtraction on the preprocessed sound data to be recognized and the sound data to be recognized after auditory conversion to obtain the sound data to be recognized after perceptual subtraction; Perform perceptual subtraction on the preprocessed reference sound data and the reference sound data after auditory conversion to obtain the reference sound data after perceptual subtraction; Perform symmetric processing, L1 norm and L3 norm to calculate the Bark domain mean processing, bad interval realignment processing, and time domain averaging processing on the sound data to be recognized after perceptual subtraction and the reference sound data after perceptual subtraction in sequence to obtain the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging; Calculate the similarity score between the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging; When the similarity score is greater than a preset similarity score threshold, determine that the sound data is abnormal sound data; When the similarity score is less than or equal to the preset similarity score threshold, determine that the sound data is normal sound data.

2. The vehicle fuel anti-theft alarm method according to claim 1, characterized in that, The step of detecting the number of times the fuel tank cap is touched through a touch sensing module preset on the fuel tank cap specifically includes the following steps: Receive the signals sent by the touch sensing module within a preset detection time, and statistically obtain the number of signal transmissions; Determine the number of times the fuel tank cap is touched within the preset detection time according to the number of signal transmissions.

3. The vehicle fuel anti-theft alarm method according to claim 1, characterized in that, The current vehicle key sensing situation is that the vehicle key is sensed or not sensed.

4. The vehicle fuel theft prevention and alarm method according to claim 1, characterized in that, The step of determining the current theft risk level according to the number of touches, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation specifically includes the following steps: When the number of touches meets the preset abnormal touch number, determine a first risk score corresponding to the number of touches based on the risk scores corresponding to each abnormal touch number interval in a preset risk score table; Determine a second risk score corresponding to the target sound comparison result based on the risk scores corresponding to each sound comparison result in the preset risk score table; When the fuel reduction amount meets the preset abnormal fuel reduction amount, determine a third risk score corresponding to the fuel reduction amount based on the risk scores corresponding to each fuel reduction amount interval in the preset risk score table; Determine a fourth risk score corresponding to the current vehicle key sensing situation based on the risk scores corresponding to each vehicle key sensing situation in the preset risk score table; Calculate and obtain a current total risk score based on the first risk score, the second risk score, the third risk score, and the fourth risk score, and use it as a quantization value of the current theft risk level.

5. The vehicle fuel anti-theft alarm method according to claim 4, characterized in that Based on the corresponding relationship between each preset theft risk level and each alarm action, determine and execute the target alarm action corresponding to the current theft risk level, which specifically includes the following steps: Based on the current total risk score corresponding to the current theft risk level and the corresponding relationship between each preset risk score and each alarm action, determine and execute the target alarm action corresponding to the current total risk score.

6. The vehicle fuel anti-theft alarm method according to claim 5, characterized in that, The alarm actions include one or more of controlling the vehicle lights to flash, controlling the vehicle to emit an alarm, controlling a camera preset on the vehicle to collect images around the vehicle, sending an alarm message to a user terminal, and controlling the vehicle to sound the horn.

7. A vehicle fuel anti-theft alarm device, characterized in that, Include: A touch detection module for detecting the number of touches on the fuel tank cap through a touch sensing module preset on the fuel tank cap; A sound comparison module for obtaining sound data collected by the sound collection module based on a sound collection module preset in the fuel tank cap, comparing the similarity of the sound data with preset target damage sound data, and obtaining a target sound comparison result; A fuel quantity detection module for obtaining the fuel reduction amount in the fuel tank within a preset time; A theft risk level determination module for determining the current theft risk level according to the number of touches, the target sound comparison result, the fuel reduction amount, and the current vehicle key sensing situation; An alarm module for determining and executing the target alarm action corresponding to the current theft risk level based on the corresponding relationship between each preset theft risk level and each alarm action; Among them, the sound comparison module is used to compare the similarity of the sound data with preset target damage sound data to obtain a target sound comparison result, which specifically includes: Perform preprocessing on the sound data and the target damage sound data respectively to obtain preprocessed sound data to be recognized and preprocessed reference sound data; Perform auditory conversion processing on the preprocessed sound data to be recognized and the preprocessed reference sound data respectively to obtain the sound data to be recognized after auditory conversion and the reference sound data after auditory conversion; Perform perceptual subtraction on the preprocessed sound data to be recognized and the sound data to be recognized after auditory conversion to obtain the sound data to be recognized after perceptual subtraction; Perform perceptual subtraction on the preprocessed reference sound data and the reference sound data after auditory conversion to obtain the reference sound data after perceptual subtraction; Perform symmetric processing, L1 norm and L3 norm to calculate the Bark domain mean, bad interval realignment processing, and time domain averaging processing on the sound data to be recognized after perceptual subtraction and the reference sound data after perceptual subtraction in sequence to obtain the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging; Calculate the similarity score between the sound data to be recognized after time domain averaging and the reference sound data after time domain averaging; When the similarity score is greater than the preset similarity score threshold, determine that the sound data is abnormal sound data; When the similarity score is less than or equal to the preset similarity score threshold, determine that the sound data is normal sound data.

8. A terminal device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the vehicle fuel anti-theft alarm method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the vehicle fuel anti-theft alarm method according to any one of claims 1 to 6.

Images