CN112053678A

CN112053678A - Lock opening and closing method and system based on voice recognition, lock opening and closing body and shared vehicle

Info

Publication number: CN112053678A
Application number: CN201910491198.0A
Authority: CN
Inventors: 刘增义; 马爱国
Original assignee: Beijing Kuaisongguo Technology Co ltd
Current assignee: Beijing Kuaisongguo Technology Co ltd
Priority date: 2019-06-06
Filing date: 2019-06-06
Publication date: 2020-12-08
Anticipated expiration: 2039-06-06
Also published as: CN112053678B

Abstract

The invention provides a locking and unlocking method based on voice recognition, which can convert voice information input by a user into specific voice characteristics and can generate a voice characteristic database in a vehicle; after the corresponding user registration is completed, the voice recognition device can be further awakened based on a preset signal, the voice information can be converted into voice characteristics, the real-time generated voice characteristics can be compared, and a corresponding control signal is output based on a comparison judgment result. Based on the steps, the calculation amount and time for processing the voice information after the voice input of the user can be simplified, and the voice feature database is generated in the vehicle, so that the dependence on the network can be reduced when related data is called and matched, and the smoothness of locking and unlocking operation can be ensured. The invention further provides a shared vehicle, a switch lock main body and a system based on the shared vehicle and the cloud server.

Description

Lock opening and closing method and system based on voice recognition, lock opening and closing body and shared vehicle

[ technical field ] A method for producing a semiconductor device

The invention relates to the field of voice control, in particular to a locking and unlocking method and system based on voice recognition, a locking and unlocking body and a shared vehicle.

[ background of the invention ]

In shared (electric) bicycle, shared automobile, smart home equipment and application, a user usually controls the equipment (such as locking and unlocking operation) by means of electronic equipment such as a mobile phone and the like through code scanning, network password downloading and the like, although the scheme is widely and mature in application, the shared (electric) bicycle is unlocked due to the loss of two-dimensional codes on the shared (electric) bicycle or network delay of unlocking equipment, and great inconvenience is brought to unlocking of the shared (electric) bicycle. In some specific situations, for example, the electronic device such as a mobile phone is not carried, the electronic device is not usable (for example, the battery is used up, no wireless network is available, etc.), and operations such as locking and unlocking cannot be performed, which causes great inconvenience to the user and also affects the commercial benefit of the operation subject of the device.

Further, the conventional unlocking method cannot realize the identification of the user and the restriction of the use of the vehicle by the non-compliant user, for example, the requirement of prohibiting minors from using other people's account numbers to use the shared vehicle.

Therefore, it is desirable to provide a novel unlocking method to solve the above technical problems.

[ summary of the invention ]

In order to solve the problems of the existing locking and unlocking method, the invention provides a locking and unlocking method based on voice recognition and a system thereof, a locking and unlocking main body and a shared vehicle.

In order to solve the technical problems, the invention provides a technical scheme as follows: a method for switching on and off a lock based on voice recognition comprises the following steps: step S1, establishing and updating a voice characteristic database; acquiring voice input information of a user, converting the voice input information into corresponding voice characteristics, and updating and storing the voice characteristics so as to generate a voice characteristic database in the vehicle; step S2, based on the preset signal to wake up, collecting the user real-time voice input information and processing to obtain the real-time voice characteristics, and comparing and judging with the voice characteristics stored in the voice characteristics database; and step S3, outputting a control signal corresponding to the switch lock based on the comparison and judgment result.

Preferably, step S2 further includes the steps of: step S21, the user wakes up, collects the user voice input and preprocesses the voice input; and step S22, generating user voice characteristics and identifying and comparing.

Preferably, in step S21, the user wake-up pattern includes one or more of a specific voice combination wake-up, a sensor wake-up, a key wake-up or a gesture wake-up.

Preferably, when the user awakening mode is voice combination awakening, the signal-to-noise ratio of the voice information input by the user is used as an awakening judgment reference, and if the zero crossing rate of the signal and/or the signal energy is greater than a preset value, the voice information can be awakened to be collected.

Preferably, the speech features extracted in the above step S1 include speech features based on mel-frequency cepstral coefficients.

In order to solve the above technical problems, the present invention provides another technical solution as follows: a shared vehicle comprises a vehicle main body, a lock structure and a control module, wherein the lock structure and the control module are arranged on the vehicle main body, the control module comprises a storage unit and a control unit, and a computer program stored in the storage unit executes the steps in the method for opening and closing the lock based on voice recognition to control the opening or closing of the lock structure.

Preferably, the sharing vehicle further comprises a voice collector, and the voice collector acquires real-time voice information of the user and transmits the real-time voice information to the control unit.

Preferably, after the control unit processes the acquired real-time voice information, the control unit may retrieve a plurality of stored voice features satisfying a preset proximity threshold range from the storage unit, compare corresponding data in the control unit, and send a corresponding control instruction to the lock structure based on a comparison determination result to control the opening or closing of the lock structure.

In order to solve the above technical problems, the present invention provides another technical solution as follows: a lock opening and closing body comprises a lock structure and a control module, wherein the control module comprises a storage unit and a control unit, and a computer program stored in the storage unit executes the steps in the method for opening and closing the lock based on voice recognition so as to control the opening or closing of the lock structure.

In order to solve the above technical problems, the present invention provides another technical solution as follows: a system for unlocking and locking based on voice recognition comprises a cloud server and a plurality of sharing vehicles which are mutually communicated with the cloud server, wherein the cloud server acquires and judges an active area of the sharing vehicles used by a user, and further sends a control instruction to the sharing vehicles based on the active area of the user, so that user characteristic data stored in the sharing vehicles are transmitted to the cloud server and are shared to storage units of all the sharing vehicles in the active area by the cloud server.

Compared with the prior art, the locking and unlocking method and system based on voice recognition, the shared vehicle and the locking and unlocking main body have the following beneficial effects:

(1) the invention provides a method for opening and closing a lock based on voice recognition, which comprises three steps, wherein based on the method, voice information input by a user can be converted into specific voice characteristics, and a voice characteristic database can be generated in a vehicle; after the corresponding user registration is completed, the voice recognition device can be further awakened based on a preset signal, the voice information can be converted into voice characteristics, the real-time generated voice characteristics can be compared, and a corresponding control signal is output based on a comparison judgment result. Based on the steps, the computation amount and time for processing the voice information after the voice input of the user can be simplified, and the voice feature database is generated in the vehicle, so that the dependence on the network can be reduced when related data is called and matched, and the fluency of locking and unlocking operations can be ensured under the condition of no network or poor network. And because the voice recognition switch lock is used, the corresponding switch lock equipment can be used even if the terminal equipment is powered off or has no signal. Furthermore, the lock opening and closing method based on voice recognition can also be used for discriminating the user identity based on the acquired voice characteristics, so that the problem that other people, especially minors, use shared vehicles by utilizing non-self-registration terminal equipment to open and close locks is avoided.

(2) The method provided by the invention also comprises the steps of awakening the user, collecting the voice input of the user and preprocessing the voice input; and user voice feature generation and identification comparison are carried out, in the actual use process, the convenience of use of a user can be improved by a specific awakening mode, and the corresponding identification module can be started in the awakening state without keeping the running state for a long time, so that the equipment loss of the corresponding switch lock main body can be reduced, and the corresponding electric energy consumption can be saved.

(3) In the method provided by the invention, the user awakening mode comprises one or more combinations of specific voice combination awakening, sensor awakening, key awakening or gesture awakening, and various awakening modes can be matched with different application scenes, so that the universality of the method for switching on and off the lock based on voice recognition can be improved.

(4) When the user awakening mode is voice combination awakening, the signal-to-noise ratio of voice information input by a user is used as an awakening judgment reference, and if the signal zero crossing rate and/or the signal energy are/is greater than a preset value, the voice information can be awakened to be collected, so that the awakening accuracy is improved.

(5) In the method provided by the invention, the extracted voice features comprise voice features based on the Mel frequency cepstrum coefficient, and the voice features of the corresponding voice information can be quickly and accurately obtained by utilizing the voice feature mode of the Mel frequency cepstrum coefficient, so that the speed and the accuracy of voice recognition can be improved.

(6) The invention also provides a shared vehicle which comprises a vehicle main body, a lock structure arranged on the vehicle main body and a control module, wherein the control module comprises a storage unit and a control unit, and a computer program stored in the storage unit executes the steps in the method for opening and closing the lock based on the voice recognition so as to control the opening or closing of the lock structure. The control component is arranged in the shared vehicle, so that the voice recognition process through voice input of a user can be simplified, and the voice information input can be conveniently carried out on the shared vehicle by the user under the condition of no terminal device app assistance, so that the opening or closing of the switch lock main body is controlled.

(7) The sharing vehicle further comprises a voice collector, and the voice collector acquires real-time voice information of a user and transmits the real-time voice information to the control unit. By arranging the voice collector above the shared vehicle, the locking and unlocking operation based on voice recognition can be independent of the app control of the terminal device, and can be treated as emergency locking and unlocking in some use scenes with poor wireless networks.

(8) In the shared vehicle provided by the invention, after the control unit processes the acquired real-time voice information, the control unit can call a plurality of stored voice characteristics meeting a preset proximity threshold range from the storage unit, compare corresponding data in the control unit, and send a corresponding control instruction to the lock structure based on a comparison judgment result to control the opening or closing of the lock structure. By setting the threshold range of the approximation degree, the rapid comparison and matching between the real-time voice features and the stored voice features can be realized, the accuracy is ensured, the matching speed of data can be further reduced, and the corresponding features do not need to be searched in a traversal mode in the corresponding voice feature database.

(9) The invention also provides a switch lock body, which comprises a lock structure and a control module, wherein the control module comprises a storage unit and a control unit, and a computer program stored in the storage unit executes the steps in the method for switching the lock based on the voice recognition so as to control the opening or closing of the lock structure.

(10) The invention also provides a system for locking and unlocking based on voice recognition, wherein the cloud server acquires and judges an active area of a shared vehicle used by a user, and further sends a control instruction to the shared vehicle based on the active area of the user, so that user characteristic data stored in the shared vehicle is transmitted to the cloud server and is shared to storage units of all shared vehicles in the active area by the cloud server. The system for opening and closing the lock based on the voice recognition can be based on the active area of a certain user, and the corresponding user information is transmitted to the voice feature database of the shared vehicle positioned in the active area in advance, so that the corresponding shared vehicle can find the storage semantic features matched with the real-time voice features input by the user in the voice feature database when the user directly performs the voice recognition unlocking through the shared vehicle under the condition of no network or poor network.

[ description of the drawings ]

Fig. 1 is a schematic diagram of a structure and functional modules of a shared vehicle according to a first embodiment of the present invention.

FIG. 2 is a functional block diagram of a control module in the shared vehicle.

Fig. 3 is a schematic diagram of signal transmission between the sharing vehicle and the terminal device and the cloud server.

Fig. 4 is a flowchart illustrating a method for switching a lock based on voice recognition according to a third embodiment of the present invention.

Fig. 5 is a flowchart illustrating the detailed step of step S2 shown in fig. 4.

Fig. 6 is a flowchart illustrating a detailed step of step S22 shown in fig. 5.

Fig. 7 is a block diagram of a locking and unlocking system based on voice recognition according to a fourth embodiment of the present invention.

Fig. 8 is a functional block diagram of another embodiment of the voice recognition based locking and unlocking system shown in fig. 7.

The attached drawings indicate the following:

90. a shared vehicle; 91. a vehicle main body; 92. a switch lock body; 921. a lock structure; 922. a control module; 901. a voice collector; 902. a control unit; 903. a storage unit; 100. a terminal device; 109, a voice collector; 800. a cloud server;

10. a lock opening and closing system; 101. a cloud server; 102. a shared vehicle; 11. A voice input module; 12. a voice feature storage module; 13. a voice feature comparison module; 14. a vehicle control module.

[ detailed description ] embodiments

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Referring to fig. 1, a shared vehicle 90 according to a first embodiment of the present invention includes a vehicle body 91 and a switch lock body 92 disposed on the vehicle body 91 for controlling the operation of the vehicle body 91. The vehicle body 91 includes, but is not limited to, a shared electric vehicle, a shared automobile, a shared bicycle, and a shared scooter or other operating vehicle.

As shown in fig. 1, the switch lock body 92 further includes a lock structure 921 and a control module 922 for controlling the lock structure 921. Further, referring to fig. 2, the control module 922 specifically includes a voice collector 901, a control unit 902 and a storage unit 903. The voice information collected by the voice collector 901 can be transmitted to the control unit 902, and the control unit 902 processes the voice information and transmits the processed voice information to the storage unit 903 for storage.

Further, the storage unit 903 stores a computer program, and the computer program can be used to execute specific method steps corresponding to locking and unlocking based on voice recognition, so that the locking and unlocking of the lock structure 921 can be controlled.

In particular, the storage unit 903 includes a storage portion such as a Read Only Memory (ROM), a Random Access Memory (RAM), and a hard disk, and the control unit 902 can execute various appropriate operations and processes according to a program stored in the Read Only Memory (ROM) or a program loaded in the Random Access Memory (RAM). In a Random Access Memory (RAM), various programs and data required for the operation of the control module 922 are also stored.

When the user wakes up the voice collector 901 again, the voice collector 901 obtains real-time voice information of the user and transmits the real-time voice information to the control unit 902, after the control unit 902 processes the obtained real-time voice information, the control unit 902 can call the voice information with higher correlation with the real-time voice information from the storage unit 903, compare corresponding data in the control unit 902, and send a corresponding control instruction to the lock structure 921 based on a comparison judgment result to control the lock structure 921 to be opened or closed.

The control unit 902 may retrieve a stored speech feature with a high correlation with the stored speech feature from the storage unit 903, and may set an approximation threshold, and after processing the obtained real-time speech information, the control unit 902 may obtain a feature range of the actual speech information input by the user after the processing, where the feature range may include a speech feature based on mel-frequency cepstrum coefficient (MFCC), or may include one or a combination of a voiceprint feature and a speech rate tone feature that are matched with the user information after the processing. The control unit 902 can retrieve a plurality of stored voice features within the threshold range of the degree of approximation from the storage unit 903 and compare the voice features, so that the speed and accuracy of voice recognition of a user can be improved, and the data processing amount and the calculation amount can be reduced.

In other embodiments, as shown in fig. 3, the sharing vehicle 90 and at least one terminal device 100 may implement signal transmission, the terminal device 100 may also include a voice collector 109, and both the voice collector 901 and the voice collector 901 in the sharing vehicle 90 may be used to collect voice information of a user. In a specific use scenario, a user may perform corresponding voice input by using the voice collector 109 in the terminal device 100 based on a requirement, or may perform corresponding voice input based on the voice collector 901 in the shared vehicle 90.

Referring to fig. 3, a plurality of the sharing vehicles 90 and the cloud server 800 may communicate with each other, and a small area network may be formed between the sharing vehicles 90. In the invention, the collection and processing of the voice information are all performed on the switch lock main body 92, therefore, in the process of controlling the switch lock based on the voice recognition provided by the invention, uploading or downloading of a large amount of voice information is not involved, so that the rapidity of unlocking data processing can be improved, and in the process of switching the lock, the operation of the switch lock main body 92 does not depend on the speed of network transmission because the switch lock main body is not required to be interconnected with the cloud server 800 at any time, so that the switch lock main body can normally work under the condition of poor network signals or no network.

Further, in the present invention, only the voice features obtained by the corresponding processing may be correspondingly stored in the storage unit 903 in the switch lock body 92, and when performing the judgment comparison, only the voice features obtained by the processing are compared, so that the whole judgment comparison and retrieval of the voice features is convenient and the data processing amount is small, and therefore, the requirement of the actual operation can be satisfied, and even on the basis of no wireless network or poor wireless network signals, the normal use of the shared vehicle 90 can be ensured, thereby improving the commercial benefit of the operator.

With continuing reference to fig. 1 and fig. 3, a second embodiment of the present invention provides a switch lock body 92, where the switch lock body 92 also includes a lock structure 921 and a control module 922, the control module 922 includes a storage unit 903 and a control unit 902, and a computer program stored in the storage unit 903 executes steps in a method for switching a lock based on voice recognition to control opening or closing of the lock structure 921. The details of the switch lock body 92 are related to the shared vehicle described in the first embodiment, and will not be described herein.

It should be noted that the switch lock body 92 may also be used in operating vehicles, smart home products, and the like.

Referring to fig. 4, a third embodiment of the present invention provides a method for unlocking and locking based on voice recognition S10, which is specifically executed by the control unit 902 of the shared vehicle 90 provided in the first embodiment of the present invention and the control unit 902 of the unlocking and locking body 92 provided in the second embodiment of the present invention, wherein the method for unlocking and locking based on voice recognition S10 specifically includes the following steps:

step S1, establishing and updating a voice characteristic database; acquiring voice input information of a user, converting the voice input information into corresponding voice characteristics, and updating and storing the voice characteristics so as to generate a voice characteristic database in the vehicle;

step S2, based on the preset signal to wake up, collecting the user real-time voice input information and processing to obtain the real-time voice characteristics, and comparing and judging with the voice characteristics stored in the voice characteristics database; and

in step S3, a corresponding control signal is output based on the comparison determination result.

In the above steps, the data processing and comparing and judging subjects of the method S10 for unlocking and locking based on voice recognition are performed in the control module 922 in the shared vehicle 90, which can further improve the accuracy of the recognition, so as to avoid the influence on the unlocking experience of the user due to network delay or poor network, and further improve the sensitivity of the user for unlocking by voice recognition. It is to be understood that, in the method for unlocking and locking based on voice recognition S10, the data processing and the comparison determination operations can be performed in the cloud server 800 at the same time, so as to improve the accuracy of the data operation.

The registered user can also collect the user identity voice information by means of a client (APP) in the terminal device 100, and the user identity voice information is transmitted to the database through the network after being preprocessed; and after receiving the preprocessed voice information file of the registered user, the database performs data processing to generate and store the voice characteristic file of the registered user to form a voice characteristic data file library.

Specifically, in some embodiments, the speech feature extracted in step S1 may be performed based on Mel-Frequency Cepstral coefficients (MFCCs), which may specifically include the following steps:

(1) pre-emphasis, framing and windowing are carried out on the acquired voice information;

(2) for each short time analysis window, obtaining a corresponding frequency spectrum through FFT (fast Fourier transform);

(3) passing the frequency spectrum through a Mel filter bank to obtain a Mel frequency spectrum;

(4) performing cepstrum analysis on the Mel frequency spectrum to obtain a Mel frequency cepstrum coefficient MFCC, wherein the Mel frequency cepstrum coefficient MFCC is the voice feature corresponding to the current frame;

further, in the step (4), performing the cepstrum analysis further specifically includes: taking logarithm, and performing inverse transformation, wherein the actual inverse transformation is generally realized by DCT (discrete cosine transform) discrete cosine transform, and the 2 nd to 13 th coefficients after DCT discrete cosine transform are taken as MFCC coefficients.

Based on the above steps, the complicated voice information input by the user can be simplified and processed into corresponding voice characteristics, thereby simplifying the data processing amount of subsequent storage and comparison analysis and improving the processing speed.

In the above-described step S1, the update is saved to the storage unit 903 to generate the voice feature database, and the corresponding voice feature may be associated with the user personal information and stored in the voice feature database based on the registration information of the user. Because the voice information initially input by the user is processed into voice features with small capacity, the storage capacity of the generated voice feature database is small, and the data processing and transmission speed is higher.

Further, in order to ensure that the data in the storage unit 903 of the sharing vehicle 90 can be updated, the cloud server 800 may issue a control instruction to the sharing vehicle 90 based on the active area of the sharing vehicle 90 used by the user, so that the user feature data stored in the sharing vehicle 90 is transmitted to the cloud server 800 and shared by the cloud server 800 to the voice feature database of all sharing vehicles 90 in the active area.

Referring to fig. 5, in step S2, the voice waking up based on the preset signal, collecting and processing the user voice real-time input information, and comparing the user voice real-time input information with the voice feature in the voice feature database in the vehicle control device for judgment may specifically include the following steps:

step S21, the user wakes up, collects the user voice input and preprocesses the voice input; when a user needs to control the shared vehicle 90, the control module 922 is awakened through a specific voice combination and/or a sensor, the voice collecting unit collects voice information of the user and preprocesses the voice information, and a voice file is generated and uploaded to the voice feature database for further data processing;

it can be understood that the control module 922 further includes a vibration sensor and a voice wake-up unit to implement voice wake-up judgment. In step S21, taking one specific operation as an example, when the user uses voice to unlock the lock, the user needs to input his/her name and password with voice. Specifically, the name and the password must be consistent with the voice uploaded during registration, and in order to meet the diversified use scenes of the user, the voice information input by the user may be other voice information, provided that the name and the password must be consistent with the voice information during registration.

Further, in step S21, a voice wake-up determination is performed by means of the vibration sensor and the voice wake-up unit. Since the lock usage scenario based on speech recognition of the shared vehicle 90 is generally a near-field speech scenario, the SIGNAL-to-NOISE RATIO (SNR) of the input speech SIGNAL is relatively high, and whether to wake up the speech information collection unit can be determined based on the power strength of the speech SIGNAL and the Zero Crossing Rate (ZCR). Specifically, when the user awakening mode is voice combination awakening, the signal-to-noise ratio of the voice information input by the user is used as an awakening judgment reference, and if the signal zero crossing rate and/or the signal energy are/is greater than a preset value, the voice information can be awakened to be collected. The preset value described herein can be set based on actual needs, and is not limited herein.

In other embodiments, voice wake-up may also be implemented by setting a special wake-up word.

In the invention, in order to eliminate the interference of the background noise, the background noise can be eliminated by adopting methods such as a noise cancellation method, an enhancement algorithm based on wavelet analysis, a harmonic enhancement algorithm based on voice spectrum characteristics or an enhancement algorithm based on short-time spectrum estimation, and the like.

After the voice wakeup decision passes, the voice collector 901 may start voice collection.

In the present invention, the collected speech waveform is subjected to speech preprocessing (speech coding) for further processing.

In some embodiments, the data after the voice preprocessing may be sent to the cloud server, and the cloud server may further process the voice file.

The step S22 of generating user speech features and comparing the user speech features with the recognition may be further subdivided into the following steps, as shown in fig. 6:

step S221, converting the acquired voice information into real-time voice characteristics;

the preprocessed voice information is generated into voice feature parameters by using mel-frequency cepstrum coefficients (MFCCs), and the parameters are stored in a user voice feature database as user information and are stored, specifically, the mel-frequency cepstrum coefficients are already described in the above contents in the MFCC processing process, and are not described herein again.

Step S222, extracting voice features in a corresponding voice feature database based on the real-time voice features, finding out stored voice features pre-stored in the voice feature database by a user, and comparing and judging; specifically, the real-time speech feature may be subjected to state recognition and phoneme conversion, and then a threshold value may be set, and the real-time speech feature may be compared with the threshold value of the real-time speech feature, so as to determine whether the real-time speech feature is consistent with the stored speech feature in the speech feature database.

Further, the setting of the threshold may be adjusted by combining the signal-to-noise ratio (SNR) of the voice information, that is, different thresholds may be set for the SNR voice signals with different sizes, so as to reduce the probability of misjudgment.

In the above step S3, a correspondence control signal is output based on the comparison determination result. Specifically, if the real-time voice feature is matched with the voice feature stored in the voice feature database and the error range is smaller than the preset threshold, the voice information input by the user can be considered to meet the requirement for controlling the switch lock, so that a corresponding instruction can be obtained based on voice recognition to control the switch of the vehicle lock.

In some embodiments of the present invention, the specific steps are as follows:

assuming that the user a uses the shared vehicle 90 for the first time, the user a performs the first voice input through the voice collector 901, thereby establishing a voice feature database matching the user information. A corresponding voice feature database may be stored in the storage unit 903 of the shared vehicle 90, and the voice feature database may also be synchronously stored in the cloud server 800.

When the user a uses the shared vehicle 90 of the same carrier again, the user a may wake up the switch lock body 92 of the shared vehicle 90 based on a specific voice command or a key signal. If the user a presses a wake-up button (not shown) provided on the switch lock body 92, the switch lock body 92 is woken up. After the lock switch body 92 is awakened, the voice input information of the user a can be collected, the collected real-time voice input information of the user a is processed to obtain real-time voice characteristics, and the real-time voice characteristics are compared with the stored voice characteristics in the voice characteristic database for judgment. If the stored voice characteristics matched with the voice characteristics can be found in the voice characteristic database, corresponding user information in the voice characteristic database is matched with the real-time voice characteristics, and therefore a corresponding unlocking signal can be generated. Similarly, the user a may also issue a lock-off signal to the same shared vehicle 90 by voice based on the above steps.

In other specific embodiments, after the user a uses the shared vehicle 90 of the same operation subject for multiple times, the active area range of the user a may be estimated, and the cloud server 800 may transmit the voice feature corresponding to the user a to the shared vehicle 90 parked in the active area range of the user a, and update the voice feature to the voice feature database in the storage unit 903 of the corresponding shared vehicle 90, so that when the user a uses the shared vehicle 90 in the frequently active area range, the shared vehicle 90 may directly call the stored voice feature database in the on-off lock main body 92 of the shared vehicle and perform comparison and determination, that is, based on the user information matching result, if the determination is consistent, a corresponding on-off lock signal is given.

Referring to fig. 7, a locking and unlocking system 10 based on voice recognition is further provided in a fourth embodiment of the present invention, and includes a cloud server 101 and a plurality of sharing vehicles 102 in the first embodiment, where the sharing vehicles 102 are in signal communication with the cloud server 101, and the cloud server 101 obtains and determines an active area of a sharing vehicle 102 used by a user, and further sends a control instruction to the sharing vehicle 102 based on the active area of the user, so that user characteristic data stored in the sharing vehicle 102 is transmitted to the cloud server 101, and is shared by the cloud server 101 to storage units of all sharing vehicles 102 in the active area of the corresponding user.

It will be appreciated that in some embodiments, the following steps are included: the user a often uses a shared vehicle 102 of a certain operator in the area a, and the corresponding area a is defined as an active area, and the setting of the active area can be obtained by performing overall planning based on a common place and a common path where the user a uses the shared vehicle 102. The cloud server 101 may broadcast, based on the active area of the user a, voice features related to the user a to all sharing vehicles 102 in the active area of the user a, and correspondingly store the voice features in the storage unit of the sharing vehicle 102. Specifically, the user a and the shared vehicle 102 may be located by a gps (global Positioning system) or a base station of a mobile network.

Since the active area for a certain user is changeable, the cloud server 101 may share the voice feature of the corresponding user to all the sharing vehicles 102 in the corresponding active area periodically or after the active area change rate exceeds a certain set value.

The above-described speech recognition-based locking and unlocking system 10 may improve the convenience of the user in using the shared vehicle 102 in the active area, and thus may improve the user experience. If the user uses the shared vehicle 102 outside the defined active area, the corresponding cloud server may modify the active area based on the number of times the user uses the shared vehicle, so as to ensure the timeliness and accuracy of information sharing.

Further, as shown in fig. 8, the lock/unlock system 10 based on voice recognition may further include a voice input module 11, a voice feature storage module 12, a voice feature comparison module 13, and a vehicle control module 14, and the specific functions thereof are as follows:

the voice input module 11 is configured to obtain voice information of a user, and after obtaining corresponding voice information, perform corresponding extraction and primary processing (such as voice coding) to generate a voice file adapted to voice processing, that is, it can be considered that the voice input module 11 can correspondingly convert the voice information obtained from the voice collector (not shown) into voice features.

A voice feature storage module 12 configured to transmit the voice features obtained through the processing of the voice input module 11 to the storage unit (not shown) for storage, so as to form a voice feature database.

And the voice feature comparison module 13 is configured to compare the voice features generated in real time with the stored voice features in the voice feature database, and discriminate the corresponding user voice, so as to make a judgment and a corresponding instruction for the next lock-on/lock-off control. And

and the vehicle control module 14 is configured to control a corresponding lock switch based on the judgment instruction output by the voice feature comparison module 13.

In particular, according to the above disclosed embodiments of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the disclosed embodiments of the invention may include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flowchart.

When the computer program is executed, the above-mentioned functions defined in the method for training a neural network model with an anti-counterfeiting function of the present application are executed. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

In the present application, a computer readable storage medium may also be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures of the present application illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present invention may be implemented by software or hardware. The described units may also be located in the processor.

the invention provides a method for opening and closing a lock based on voice recognition, which comprises three steps, wherein based on the method, voice information input by a user can be converted into specific voice characteristics, and a voice characteristic database can be generated in a vehicle; after the corresponding user registration is completed, the voice recognition device can be further awakened based on a preset signal, the voice information can be converted into voice characteristics, the real-time generated voice characteristics can be compared, and a corresponding control signal is output based on a comparison judgment result. Based on the steps, the computation amount and time for processing the voice information after the voice input of the user can be simplified, and the voice feature database is generated in the vehicle, so that the dependence on the network can be reduced when related data is called and matched, and the fluency of locking and unlocking operations can be ensured under the condition of no network or poor network. And because the voice recognition switch lock is used, the corresponding switch lock equipment can be used even if the terminal equipment is powered off or has no signal. Furthermore, the lock opening and closing method based on voice recognition can also be used for discriminating the user identity based on the acquired voice characteristics, so that the problem that other people, especially minors, use shared vehicles by utilizing non-self-registration terminal equipment to open and close locks is avoided.

The invention also provides a switch lock body, which comprises a lock structure and a control module, wherein the control module comprises a storage unit and a control unit, and a computer program stored in the storage unit executes the steps in the method for switching the lock based on the voice recognition so as to control the opening or closing of the lock structure.

The invention also provides a system for locking and unlocking based on voice recognition, wherein the cloud server acquires and judges an active area of a shared vehicle used by a user, and further sends a control instruction to the shared vehicle based on the active area of the user, so that user characteristic data stored in the shared vehicle is transmitted to the cloud server and is shared to storage units of all shared vehicles in the active area by the cloud server. The system for opening and closing the lock based on the voice recognition can be based on the active area of a certain user, and the corresponding user information is transmitted to the voice feature database of the shared vehicle positioned in the active area in advance, so that the corresponding shared vehicle can find the storage semantic features matched with the real-time voice features input by the user in the voice feature database when the user directly performs the voice recognition unlocking through the shared vehicle under the condition of no network or poor network.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit of the present invention are intended to be included within the scope of the present invention.

Claims

1. A method for opening and closing a lock based on voice recognition is characterized in that: which comprises the following steps:

and step S3, outputting a corresponding switch lock control signal based on the comparison judgment result.

2. The method for switching a lock based on speech recognition of claim 1, wherein: step S2 further includes the steps of:

step S21, the user wakes up, collects the user voice input and preprocesses the voice input; and

step S22, user speech feature generation and recognition comparison.

3. The method for switching a lock based on speech recognition of claim 2, wherein: in step S21, the user wake-up pattern includes one or more combinations of specific voice combination wake-up, sensor wake-up, button wake-up, or gesture wake-up.

4. A method for switching a lock based on speech recognition as claimed in claim 3, characterized in that: when the user awakening mode is voice combination awakening, the signal-to-noise ratio of voice information input by a user is used as an awakening judgment reference, and if the zero crossing rate of the signal and/or the signal energy is larger than a preset value, the voice information can be awakened to be collected.

5. The method for switching a lock based on speech recognition of claim 1, wherein: the speech features extracted in the above step S1 include speech features based on mel-frequency cepstral coefficients.

6. A shared vehicle, characterized by: the shared vehicle comprises a vehicle main body, a lock structure arranged on the vehicle main body and a control module, wherein the control module comprises a storage unit and a control unit, and a computer program stored in the storage unit executes the steps of the method for switching the lock based on the voice recognition in any one of the claims 1-5 so as to control the opening or closing of the lock structure.

7. The shared vehicle as claimed in claim 6, wherein: the sharing vehicle further comprises a voice collector, and the voice collector acquires real-time voice information of a user and transmits the real-time voice information to the control unit.

8. The shared vehicle as claimed in claim 6, wherein: after the control unit processes the acquired real-time voice information, the control unit can call a plurality of stored voice features meeting a preset proximity threshold range from the storage unit, compare corresponding data in the control unit, and send a corresponding control instruction to the lock structure based on a comparison judgment result to control the opening or closing of the lock structure.

9. A switch lock body, its characterized in that: the switch lock body comprises a lock structure and a control module, wherein the control module comprises a storage unit and a control unit, and a computer program stored in the storage unit executes the steps in the voice recognition based lock switching method according to any one of claims 1 to 5 to control the opening or closing of the lock structure.

10. A system for opening and closing a lock based on voice recognition is characterized in that: the system comprises a cloud server and a plurality of sharing vehicles which are mutually transmitted with the cloud server, wherein the cloud server acquires and judges an active area of the sharing vehicle used by a user, and further sends a control instruction to the sharing vehicle based on the active area of the user, so that user characteristic data stored in the sharing vehicle is transmitted to the cloud server and is shared to storage units of all sharing vehicles in the active area of the corresponding user by the cloud server.