CN107738622B - Vehicle intelligent response method and device, storage medium and electronic equipment - Google Patents
Vehicle intelligent response method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN107738622B CN107738622B CN201710758059.0A CN201710758059A CN107738622B CN 107738622 B CN107738622 B CN 107738622B CN 201710758059 A CN201710758059 A CN 201710758059A CN 107738622 B CN107738622 B CN 107738622B
- Authority
- CN
- China
- Prior art keywords
- energy
- audio data
- sound
- trend
- interval
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
Abstract
The disclosure provides a vehicle intelligent response method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring sound signals of a vehicle in real time, and acquiring energy distribution of the sound signals according to energy values corresponding to each audio data frame in the sound signals; judging whether the sound signal is the sound of closing the vehicle door or not according to the energy distribution of the sound signal; and if the sound signal is the sound of closing the vehicle door, controlling the vehicle to perform intelligent response. According to the scheme, the timeliness of intelligent response is improved.
Description
Technical Field
The present disclosure relates to the field of intelligent control, and in particular, to a vehicle intelligent response method and apparatus, a storage medium, and an electronic device.
Background
At present, an automobile becomes an important vehicle in daily life, and with the continuous progress of science and technology, various intelligent technologies are applied to the automobile to provide convenience for users to use. For example, Bluetooth hardware equipment can be externally connected in the vehicle, so that high-quality man-machine voice interaction is realized; according to the change of driving environment, the change of user's use demand and the like, the self-adaptive adjustment of the vehicle is realized, for example, the brightness of a seat, a rearview mirror, a car lamp and the like is automatically adjusted.
Generally, the intelligent functions of the vehicle are mostly activated after determining that the user starts using the vehicle. For example, if an external bluetooth hardware device is used, it is necessary to determine that a user starts to use a vehicle, and connect the bluetooth hardware device with a terminal device; if the temperature in the vehicle is adjusted, it is also required to determine that the user can perform intelligent adjustment after starting to use the vehicle.
At present, vehicles are mainly based on ignition information to perform intelligent response. That is, if the ignition information of the vehicle is collected, it can be determined that the user starts using the vehicle, and further, the vehicle can be controlled to start the smart function for smart response. For some intelligent functions which are immediately embodied when people need to get on the vehicle, the timeliness of the scheme is poor.
Disclosure of Invention
The main purpose of the present disclosure is to provide a vehicle intelligent response method and apparatus, a storage medium, and an electronic device, which are helpful to improve timeliness of intelligent response.
In order to achieve the above object, the present disclosure provides a vehicle smart response method, the method including:
acquiring sound signals of a vehicle in real time, and acquiring energy distribution of the sound signals according to energy values corresponding to each audio data frame in the sound signals;
judging whether the sound signal is the sound of closing the vehicle door or not according to the energy distribution of the sound signal;
and if the sound signal is the sound of closing the vehicle door, controlling the vehicle to perform intelligent response.
Optionally, the determining whether the sound signal is a sound of closing a vehicle door according to the energy distribution of the sound signal includes:
judging whether the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to the time sequence, wherein the energy in the first energy interval is in an ascending trend, the energy in the second energy interval is in an attenuation trend, and the number N of audio data frames corresponding to the first energy interval1The number N of audio data frames corresponding to the second energy interval is less than2；
And if the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to the time sequence, judging that the sound signal is the sound of closing the vehicle door.
Optionally, the method further comprises:
after determining that the energy distribution of the sound signal is chronologically divided into a first energy interval and a second energy interval, the method further includes:
when N is present1The duration corresponding to each audio data frame is not greater than the first duration, and/or, N2And judging that the sound signal is the sound of closing the vehicle door when the duration corresponding to each audio data frame is not less than the second duration.
Optionally, the manner of dividing the first energy interval from the energy distribution of the sound signal is as follows:
sequentially comparing energy values corresponding to two adjacent audio data frames, and judging whether the energy is in an ascending trend, wherein the ascending trend gradually becomes slow along with the time sequence;
and if the energy is in an ascending trend and the ascending trend gradually becomes slow along with the time sequence, determining the audio data frame with the energy starting to ascend as a starting frame, and determining the audio data frame with the energy stopping to ascend as an ending frame to obtain the first energy interval.
Optionally, the manner of dividing the second energy interval from the energy distribution of the sound signal is as follows:
judging whether the energy of the audio data frames subsequent to the end frame is in an attenuation trend or not, wherein the number of the audio data frames in the attenuation trend is more than N1；
If the energy of the audio data frames subsequent to the end frame shows an attenuation trend, and the number of the audio data frames showing the attenuation trend is more than the N1And dividing the audio data frame with the attenuation trend into the second energy interval.
Optionally, the determining whether the energy of the audio data frame subsequent to the end frame is in a decay trend includes:
grouping the audio data frames subsequent to the end frame, and calculating the energy value of each group;
and sequentially comparing the energy values of the two adjacent groups to judge whether the energy is in a decay trend.
The present disclosure provides a vehicle intelligent response device, the device comprising:
the energy distribution acquisition module is used for acquiring sound signals of a vehicle in real time and acquiring energy distribution of the sound signals according to the energy value corresponding to each audio data frame in the sound signals;
the vehicle door closing judging module is used for judging whether the sound signal is the sound of closing the vehicle door according to the energy distribution of the sound signal;
and the intelligent response control module is used for controlling the vehicle to carry out intelligent response when the sound signal is the sound for closing the vehicle door.
Optionally, the door closing determination module includes:
the interval division judging module is used for judging whether the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to the time sequence, the energy in the first energy interval is in an ascending trend, the energy in the second energy interval is in an attenuation trend, and the number N of the audio data frames corresponding to the first energy interval1The number N of audio data frames corresponding to the second energy interval is less than2；
And the vehicle door closing determination module is used for determining that the sound signal is the sound for closing the vehicle door when the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to a time sequence.
Optionally, after the section division determining module determines that the energy distribution of the sound signal is divided into a first energy section and a second energy section in time sequence,
the vehicle door closing judgment module is used for judging whether the vehicle door is closed at N1The duration corresponding to each audio data frame is not greater than the first duration, and/or, N2And judging that the sound signal is the sound of closing the vehicle door when the duration corresponding to each audio data frame is not less than the second duration.
Optionally, the vehicle door closing determination module further includes:
the ascending trend judging module is used for sequentially comparing energy values corresponding to two adjacent audio data frames and judging whether the energy is in an ascending trend, and the ascending trend gradually becomes slow along with the time sequence;
and the first energy interval obtaining module is used for determining the audio data frame with the energy starting to rise as a starting frame and determining the audio data frame with the energy stopping rising as an ending frame when the energy is in a rising trend and the rising trend gradually changes gradually along with the time sequence, so as to obtain the first energy interval.
Optionally, the vehicle door closing determination module further includes:
an attenuation trend judging module for judging whether the energy of the audio data frame following the ending frame is in an attenuation trend, and the number of the audio data frames in the attenuation trend is more than N1；
A second energy interval obtaining module, configured to obtain an attenuation trend for the energy of the audio data frame subsequent to the end frame, where the number of audio data frames with the attenuation trend is greater than N1And dividing the audio data frame with the attenuation trend into the second energy interval.
Optionally, the attenuation trend determining module is configured to group audio data frames subsequent to the end frame, and calculate an energy value of each group; and sequentially comparing the energy values of the two adjacent groups to judge whether the energy is in a decay trend.
The present disclosure provides a storage medium having stored therein a plurality of instructions, which are loaded by a processor, for performing the steps of the above-described vehicle intelligent response method.
The present disclosure provides an electronic device, comprising;
the storage medium described above; and
a processor to execute the instructions in the storage medium.
In the scheme, the sound signals of the vehicle can be collected in real time, the vehicle door closing recognition is carried out according to the energy distribution of the sound signals, if the energy distribution of the sound signals indicates that the sound signals are vehicle door closing sounds, a user can be judged that the vehicle is on the vehicle, and the vehicle can be controlled to start an intelligent function to carry out intelligent response. So, compare and just carry out intelligent response after gathering the information of igniting in prior art, this disclosed scheme helps improving intelligent response's timeliness.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
FIG. 1 is a schematic flow chart diagram of a vehicle intelligent response method according to an aspect of the present disclosure;
FIG. 2 is a schematic diagram illustrating the energy distribution of the closing sound of the door according to the present disclosure;
FIG. 3 is a schematic diagram of the configuration of the vehicle intelligent response device according to the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device for vehicle intelligent response according to the present disclosure.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
Referring to fig. 1, a flow diagram of the disclosed vehicle intelligent response method is shown. May include the steps of:
s101, collecting sound signals of a vehicle in real time, and obtaining energy distribution of the sound signals according to energy values corresponding to each audio data frame in the sound signals.
And S102, judging whether the sound signal is the sound of closing the vehicle door or not according to the energy distribution of the sound signal.
S103, if the sound signal is the sound of closing the vehicle door, controlling the vehicle to perform intelligent response.
In order to improve the timeliness of intelligent response of the vehicle, the sound signal of the vehicle can be collected, if the door of the vehicle is identified according to the energy distribution of the sound signal, the user can be judged to get on the vehicle and begin to use the vehicle, and the vehicle can be controlled to start an intelligent function to perform intelligent response. So, compare and just carry out intelligent response after gathering the information of igniting in prior art, this disclosed scheme helps improving intelligent response's timeliness.
As an example, the sound collection may be performed by a microphone in a rear-mounted device of the vehicle, or a microphone in a front-mounted device of the vehicle, which may not be particularly limited in the present disclosure. In addition, the microphone may be in a sound collection state at all times; or after the user stops using a certain intelligent function or finishes using the vehicle to get off, the microphone can be started to collect sound, and the sound collection can be flexibly set according to actual application requirements.
Generally, different sounds have different energy distributions in time sequence, so after a sound signal is collected, the sound signal may be windowed and framed to determine a plurality of continuous audio data frames, and an energy value corresponding to each audio data frame is calculated to obtain the energy distribution of the sound signal. Then, whether the sound signal is the sound of closing the vehicle door or not can be judged according to the energy distribution of the sound signal, and then intelligent response is carried out according to the judgment result. In practical applications, the frame length of the audio data frame may be set according to requirements, for example, the frame length may be 10 ms. As an example, the smart response may be embodied as an automatic connection of a bluetooth device, vehicle preheating, sound field adjustment, light adjustment, air conditioning adjustment, seat adjustment, and the like, which may not be particularly limited in the present disclosure.
The following explains a process of recognizing the door closing sound based on the energy distribution of the sound signal in the present disclosure.
Generally, the sound of closing the door may be represented in time sequence as a higher rise of energy in a short time, and the energy will continue to decay until the normal state is recovered in a subsequent period of time, which may be specifically seen in the energy distribution diagram shown in fig. 2. When the door closing voice recognition is carried out by combining the characteristics, whether the energy distribution of the voice signal can be divided into the following energy intervals according to the time sequence can be judged: a first energy interval for fast increasing in a short time, a second energy interval for continuously attenuating in a long time, and the number N of audio data frames corresponding to the first energy interval1Is less than the number N of audio data frames corresponding to the second energy interval2. In the scheme of the disclosure, if the two energy intervals can be divided according to the time sequence, the collected sound signal can be judged to be the sound of closing the vehicle door.
As an example, after two energy intervals are divided according to time sequence, N can also be judged1Whether the corresponding time length of each audio data frame is greater than a first duration or not, when N is1The duration corresponding to each audio data frame is not greater than the first duration, and it can be determined that the energy of the first energy interval is embodied as a short-time fast boost. Combining practicesIn application, the first duration may be 20 to 40ms, which is not particularly limited in the present disclosure.
As an example, after two energy intervals are divided according to time sequence, N can also be judged2Whether the corresponding time length of each audio data frame is less than the second duration, when N is2The duration corresponding to each audio data frame is not less than the second duration, and it can be determined that the energy of the second energy interval is embodied as long-time continuous attenuation. The second duration may be 150ms in combination with practical applications, which may not be specifically limited by the present disclosure.
In summary, the long-time sustained decay in the present disclosure is relative to the time of energy boost, for example, the time of short-time fast boost can be 30ms, and the time of long-time sustained decay can be 210 ms.
It will be appreciated that the energy peaks corresponding to the door closing sounds may vary, depending on the actual door closing intensity, the volume of the microphone, etc. In addition, considering that the door closing sound returns to normal after a period of time, the energy attenuation time is usually not longer than 250-310 ms, as can be seen from the energy distribution shown in fig. 2. The disclosed solution may not be particularly limited to energy peaks, maximum duration of decay, etc.
As an example, the first energy interval may be divided from the energy distribution of the sound signal in the following manner: sequentially comparing energy values corresponding to two adjacent audio data frames, and judging whether the energy is in an ascending trend, wherein the ascending trend gradually becomes slow along with the time sequence; and if the energy is in an ascending trend and the ascending trend gradually becomes slow along with the time sequence, determining the audio data frame with the energy starting to ascend as a starting frame, and determining the audio data frame with the energy stopping to ascend as an ending frame to obtain the first energy interval.
As an example, for consecutive 3 frames of audio data, if the energy corresponding to each frame is A in sequence1、A2、A3. The decision process may be embodied as follows:
judging whether the energy is in an ascending trend can be represented as:judging whether the energy value of the current frame is larger than the energy value of the adjacent previous frame; or judging whether the ratio of the energy values of two adjacent frames is greater than 1. For example, A2>A1The energy can be judged to be in an ascending trend; or (A)2/A1)>1 can also be judged as the energy is in the ascending trend. At this time, A may be1The corresponding audio data frame is determined as the onset frame.
Whether the ascending trend gradually becomes slow along with the time sequence is judged, and the judgment can be embodied as follows: for audio data frames with rising energy, whether the energy difference value of two adjacent frames gradually becomes smaller along with the time sequence can be judged; or judging whether the energy ratio of two adjacent frames gradually becomes smaller along with the sequence. For example, (A)2-A1)>(A3-A2) The ascending trend can be judged to gradually become slow along with the time sequence; or (A)2/A1)>(A3/A2) It can also be determined that the ascending trend gradually becomes slower with time.
For example, to divide the first energy interval of short-time fast boosting, the following threshold values may be set: t is1＝2，T2＝1，T31.2, and is in (A)2/A1)>T1，T2<(A3/A2)<T3In time, the interval corresponding to the 3 audio data frames in the energy distribution of the sound signal is divided into a first energy interval. Understandably, if (A)4/A3)<1, it means that the energy stops rising, so A can be changed3The corresponding audio data frame is determined as the end frame, wherein A4The energy corresponding to the 4 th audio data frame immediately after the continuous 3 audio data frames.
As an example, the second energy interval may be divided from the energy distribution of the sound signal in the following manner: judging whether the energy of the audio data frames subsequent to the end frame is in an attenuation trend or not, wherein the number of the audio data frames in the attenuation trend is more than N1(ii) a If the energy of the audio data frames subsequent to the end frame shows an attenuation trend, and the number of the audio data frames showing the attenuation trend is more than the N1Then will beAnd dividing the audio data frames with the attenuation trend into the second energy interval.
As an example, it can be determined whether the energy of the audio data frame subsequent to the ending frame shows an attenuation trend with reference to the above manner of determining that the energy shows an ascending trend, and the description is not repeated here. It is understood that the energy value of each audio data frame may be utilized for attenuation trend determination; or, considering that the attenuation speed is slower than the rising speed and the duration time is longer, the audio data frames subsequent to the end frame may be grouped, and the energy value of each group is calculated; then, whether the energy is in the attenuation trend is judged by sequentially comparing the energy values of the two adjacent groups. For example, the energy value of each group may be embodied as the sum of the energy values of all audio data frames comprised by the group, or as the average of the energy values of all audio data frames comprised by the group. The number of audio data frames divided into one group, the calculation mode of the energy value of each group, and the like in the scheme of the disclosure are not particularly limited, and it is sufficient to ensure that the number of audio data frames contained in each group and the calculation mode of the energy value are the same.
For example, in order to divide the second energy interval which is continuously attenuated for a long time, the following threshold value can be set: t is4＝0.8，T5Dividing every 3 frames into one group, calculating the energy average value B of 3 frames of audio data, if T4<B(n+1)/B(n)<T5Then, the intervals corresponding to the grouped audio data frames in the energy distribution of the sound signal may be divided into second energy intervals.
Referring to fig. 3, a schematic diagram of the vehicle smart response device of the present disclosure is shown. The apparatus may include:
the energy distribution obtaining module 201 is configured to collect a sound signal of a vehicle in real time, and obtain energy distribution of the sound signal according to an energy value corresponding to each audio data frame in the sound signal;
the vehicle door closing judgment module 202 is configured to judge whether the sound signal is a sound of closing a vehicle door according to the energy distribution of the sound signal;
and the intelligent response control module 203 is used for controlling the vehicle to perform intelligent response when the sound signal is the sound of closing the vehicle door.
Optionally, the door closing determination module includes:
the interval division judging module is used for judging whether the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to the time sequence, the energy in the first energy interval is in an ascending trend, the energy in the second energy interval is in an attenuation trend, and the number N of the audio data frames corresponding to the first energy interval1The number N of audio data frames corresponding to the second energy interval is less than2；
And the vehicle door closing determination module is used for determining that the sound signal is the sound for closing the vehicle door when the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to a time sequence.
Optionally, after the section division determining module determines that the energy distribution of the sound signal is divided into a first energy section and a second energy section in time sequence,
the vehicle door closing judgment module is used for judging whether the vehicle door is closed at N1The duration corresponding to each audio data frame is not greater than the first duration, and/or, N2And judging that the sound signal is the sound of closing the vehicle door when the duration corresponding to each audio data frame is not less than the second duration.
Optionally, the vehicle door closing determination module further includes:
the ascending trend judging module is used for sequentially comparing energy values corresponding to two adjacent audio data frames and judging whether the energy is in an ascending trend, and the ascending trend gradually becomes slow along with the time sequence;
and the first energy interval obtaining module is used for determining the audio data frame with the energy starting to rise as a starting frame and determining the audio data frame with the energy stopping rising as an ending frame when the energy is in a rising trend and the rising trend gradually changes gradually along with the time sequence, so as to obtain the first energy interval.
Optionally, the vehicle door closing determination module further includes:
attenuation trendA potential judging module for judging whether the energy of the audio data frame following the ending frame is in an attenuation trend, and the number of the audio data frames in the attenuation trend is more than the N1；
A second energy interval obtaining module, configured to obtain an attenuation trend for the energy of the audio data frame subsequent to the end frame, where the number of audio data frames with the attenuation trend is greater than N1And dividing the audio data frame with the attenuation trend into the second energy interval.
Optionally, the attenuation trend determining module is configured to group audio data frames subsequent to the end frame, and calculate an energy value of each group; and sequentially comparing the energy values of the two adjacent groups to judge whether the energy is in a decay trend.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Referring to fig. 4, a schematic structural diagram of an electronic device 300 for vehicle intelligent response according to the present disclosure is shown. Referring to fig. 4, the electronic device 300 includes a processing component 301 that further includes one or more processors, and storage device resources, represented by storage medium 302, for storing instructions, such as application programs, that are executable by the processing component 301. The application programs stored in the storage medium 302 may include one or more modules that each correspond to a set of instructions. Further, the processing component 301 is configured to execute instructions to perform the vehicle intelligent response method described above.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (14)
1. A vehicle smart response method, the method comprising:
acquiring sound signals of a vehicle in real time, and acquiring energy distribution of the sound signals according to energy values corresponding to each audio data frame in the sound signals;
judging whether the sound signal is the sound of closing the vehicle door or not according to the energy distribution of the sound signal;
and if the sound signal is the sound of closing the vehicle door, controlling the vehicle to perform intelligent response.
2. The method of claim 1, wherein the determining whether the sound signal is a sound of a closed door according to the energy distribution of the sound signal comprises:
judging whether the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to the time sequence, wherein the energy in the first energy interval is in an ascending trend, the energy in the second energy interval is in an attenuation trend, and the number N of audio data frames corresponding to the first energy interval1The number N of audio data frames corresponding to the second energy interval is less than2；
And if the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to the time sequence, judging that the sound signal is the sound of closing the vehicle door.
3. The method of claim 2, wherein after determining that the energy distribution of the sound signal is time-sequentially divided into a first energy interval and a second energy interval, the method further comprises:
when N is present1The duration corresponding to each audio data frame is not greater than the first duration, and/or, N2And judging that the sound signal is the sound of closing the vehicle door when the duration corresponding to each audio data frame is not less than the second duration.
4. A method according to claim 2 or 3, characterized in that the first energy interval is divided from the energy distribution of the sound signal in such a way that:
sequentially comparing energy values corresponding to two adjacent audio data frames, and judging whether the energy is in an ascending trend, wherein the ascending trend gradually becomes slow along with the time sequence;
and if the energy is in an ascending trend and the ascending trend gradually becomes slow along with the time sequence, determining the audio data frame with the energy starting to ascend as a starting frame, and determining the audio data frame with the energy stopping to ascend as an ending frame to obtain the first energy interval.
5. The method according to claim 4, wherein the second energy interval is divided from the energy distribution of the sound signal by:
judging whether the energy of the audio data frames subsequent to the end frame is in an attenuation trend or not, wherein the number of the audio data frames in the attenuation trend is more than N1；
If the energy of the audio data frames subsequent to the end frame shows an attenuation trend, and the number of the audio data frames showing the attenuation trend is more than the N1And dividing the audio data frame with the attenuation trend into the second energy interval.
6. The method of claim 5, wherein the determining whether the energy of the audio data frame subsequent to the end frame is in a decay trend comprises:
grouping the audio data frames subsequent to the end frame, and calculating the energy value of each group;
and sequentially comparing the energy values of the two adjacent groups to judge whether the energy is in a decay trend.
7. A vehicle smart response apparatus, characterized in that the apparatus comprises:
the energy distribution acquisition module is used for acquiring sound signals of a vehicle in real time and acquiring energy distribution of the sound signals according to the energy value corresponding to each audio data frame in the sound signals;
the vehicle door closing judging module is used for judging whether the sound signal is the sound of closing the vehicle door according to the energy distribution of the sound signal;
and the intelligent response control module is used for controlling the vehicle to carry out intelligent response when the sound signal is the sound for closing the vehicle door.
8. The apparatus of claim 7, wherein the door closure determination module comprises:
the interval division judging module is used for judging whether the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to the time sequence, the energy in the first energy interval is in an ascending trend, the energy in the second energy interval is in an attenuation trend, and the number N of the audio data frames corresponding to the first energy interval1The number N of audio data frames corresponding to the second energy interval is less than2；
And the vehicle door closing determination module is used for determining that the sound signal is the sound for closing the vehicle door when the energy distribution of the sound signal is divided into a first energy interval and a second energy interval according to a time sequence.
9. The apparatus of claim 8, wherein after the section division determining module determines that the energy distribution of the audio signal is time-sequentially divided into a first energy section and a second energy section,
the vehicle door closing judgment module is used for judging whether the vehicle door is closed at N1The duration corresponding to each audio data frame is not greater than the first duration, and/or, N2And judging that the sound signal is the sound of closing the vehicle door when the duration corresponding to each audio data frame is not less than the second duration.
10. The apparatus according to claim 8 or 9, wherein the door closing determination module further comprises:
the ascending trend judging module is used for sequentially comparing energy values corresponding to two adjacent audio data frames and judging whether the energy is in an ascending trend, and the ascending trend gradually becomes slow along with the time sequence;
and the first energy interval obtaining module is used for determining the audio data frame with the energy starting to rise as a starting frame and determining the audio data frame with the energy stopping rising as an ending frame when the energy is in a rising trend and the rising trend gradually changes gradually along with the time sequence, so as to obtain the first energy interval.
11. The apparatus of claim 10, wherein the door closure determination module further comprises:
an attenuation trend judging module for judging whether the energy of the audio data frame following the ending frame is in an attenuation trend, and the number of the audio data frames in the attenuation trend is more than N1；
A second energy interval obtaining module, configured to obtain an attenuation trend for the energy of the audio data frame subsequent to the end frame, where the number of audio data frames with the attenuation trend is greater than N1And dividing the audio data frame with the attenuation trend into the second energy interval.
12. The apparatus of claim 11,
the attenuation trend judging module is used for grouping the audio data frames subsequent to the end frame and calculating the energy value of each group; and sequentially comparing the energy values of the two adjacent groups to judge whether the energy is in a decay trend.
13. A storage medium having stored thereon a plurality of instructions, wherein the instructions are loadable by a processor and adapted to cause execution of the steps of the method according to any of claims 1 to 6.
14. An electronic device, characterized in that the electronic device comprises;
the storage medium of claim 13; and
a processor to execute the instructions in the storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710758059.0A CN107738622B (en) | 2017-08-29 | 2017-08-29 | Vehicle intelligent response method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710758059.0A CN107738622B (en) | 2017-08-29 | 2017-08-29 | Vehicle intelligent response method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107738622A CN107738622A (en) | 2018-02-27 |
| CN107738622B true CN107738622B (en) | 2020-09-11 |
Family
ID=61235765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710758059.0A Active CN107738622B (en) | 2017-08-29 | 2017-08-29 | Vehicle intelligent response method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107738622B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110010158B (en) * | 2019-03-29 | 2021-05-18 | 联想(北京)有限公司 | Detection method, detection device, electronic device, and computer-readable medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201130430Y (en) * | 2007-12-24 | 2008-10-08 | 合肥讯飞数码科技有限公司 | Wireless voice interactive vehicular equipment |
| CN104361887A (en) * | 2014-11-20 | 2015-02-18 | 哈尔滨工业大学 | Quick acoustic event detection system under traveling noise environment |
| CN110895930B (en) * | 2015-05-25 | 2022-01-28 | 展讯通信（上海）有限公司 | Voice recognition method and device |
| CN105741838B (en) * | 2016-01-20 | 2019-10-15 | 百度在线网络技术（北京）有限公司 | Voice awakening method and device |
-
2017
- 2017-08-29 CN CN201710758059.0A patent/CN107738622B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107738622A (en) | 2018-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110047487B (en) | Wake-up method and device for vehicle-mounted voice equipment, vehicle and machine-readable medium | |
| US8285545B2 (en) | Voice command acquisition system and method | |
| CN110060685B (en) | Voice wake-up method and device | |
| US7729911B2 (en) | Speech recognition method and system | |
| CN110475170A (en) | Control method, device, mobile terminal and the storage medium of earphone broadcast state | |
| CN108831461B (en) | Skylight voice control method and system | |
| CN109087660A (en) | Method, apparatus, equipment and computer readable storage medium for echo cancellor | |
| CN105933819A (en) | Method and device for adjusting volume of car stereo | |
| CN110460921A (en) | A kind of pick-up control method, device, vehicle and storage medium | |
| CN104986101B (en) | Vehicle room lamp control system and its control method | |
| CN107738622B (en) | Vehicle intelligent response method and device, storage medium and electronic equipment | |
| CN114750686A (en) | Method and device for controlling atmosphere lamp | |
| CN105208186A (en) | Prompt mode adjusting device, method and mobile terminal | |
| CN104270858B (en) | Method and device for intelligently controlling lighting system through voice | |
| CN114215451B (en) | Control method and system for wind vibration of vehicle window | |
| CN109410929A (en) | Vehicle part control method and device, computer readable storage medium, terminal | |
| CN116052723A (en) | Music rhythm detection method and device and electronic equipment | |
| KR100607010B1 (en) | Methods and apparatus for reducing noise associated with an electrical speech signal | |
| CN113665561B (en) | Charging control method and system of hybrid electric vehicle and hybrid electric vehicle | |
| CN106024004A (en) | Dual-microphone noise reduction processing method and system for mobile terminal and mobile terminal | |
| CN108035646B (en) | Power windows control method, device, equipment, system and readable storage medium storing program for executing | |
| CN107472254A (en) | A kind of method and system of wagon control | |
| CN113362845B (en) | Method, apparatus, device, storage medium and program product for noise reduction of sound data | |
| CN114255779A (en) | Audio noise reduction method for VR device, electronic device and storage medium | |
| CN113555017A (en) | AI-based intelligent voice vehicle-mounted atmosphere lamp control system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |