WO2021042548A1

WO2021042548A1 - Code-scanning vehicle moving method, electronic apparatus and storage medium

Info

Publication number: WO2021042548A1
Application number: PCT/CN2019/117806
Authority: WO
Inventors: 董毅
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-09-04
Filing date: 2019-11-13
Publication date: 2021-03-11
Also published as: CN110719370A

Abstract

The present application relates to the technical field of artificial intelligence. Provided are a code-scanning vehicle moving method, an electronic apparatus and a computer-readable storage medium. The method comprises: scanning, by means of an application, a QR code of a vehicle to be moved, acquiring setting information of the vehicle to be moved, and sending the setting information to a called end of the vehicle to be moved; acquiring a virtual phone number of the called end, and calling the called end by means of the virtual phone number; when two parties are in a call mode, acquiring emotion information of the two parties by means of emotion recognition technology; when it is recognized that one of the two call parties is angry, switching the call of the two parties to an intelligent speech mode; and when it is recognized that the two call parties are calm, switching the call of the two parties from the intelligent speech mode to the call mode. In the present application, a called end is called by means of scanning a QR code to move a vehicle, and emotions of two parties are recognized by means of emotion recognition technology, such that the problems in existing vehicle moving manners of a process being tedious and time-consuming, intensification of a conflict between the two parties due to communication not being timely, and information leakage are solved.

Description

Code scanning and car shifting method, electronic device and storage medium

This application requires the application number 201910832160.5, the filing date of September 04, 2019, and the priority of the patent application entitled "Code Scanning Method, Electronic Device and Storage Medium".

Technical field

This application relates to the field of artificial intelligence technology, and in particular to a method for scanning code and moving a car, an electronic device and a computer-readable storage medium.

Background technique

With the development of two-dimensional code technology, two-dimensional code technology is widely used in various fields. For the current situation where the car owner needs to contact the other party's car owner, such as car occupying or moving the car, it is generally through the traffic police to check the phone to contact the car owner. The process of this method is cumbersome, cumbersome and time-consuming, and because the communication is not timely, it is easy to intensify the contradiction between the two parties and cause relatively big problems; in addition, directly calling the mobile phone number also has the risk of information leakage.

Based on the various problems of the above-mentioned manoeuvring, the inventor realized that the traditional method of manoeuvring could not meet the needs of customers, so a new method of manoeuvring was urgently needed to solve the above-mentioned problems.

Summary of the invention

This application provides a code scanning method, electronic device, and computer-readable storage medium for moving a car, the main purpose of which is to call the called end to move the car by scanning a QR code, and to recognize the emotions of both parties through emotion recognition technology during the call. , So as to solve the problem of cumbersome and time-consuming processes in the existing car-moving method, intensified conflicts between the two parties due to lack of communication in time, and information leakage problems in direct calls to mobile phone numbers.

In addition, in order to achieve the above-mentioned object, the present application provides a method for scanning a car and moving a car, which is applied to an electronic device, on which an APP corresponding to the two-dimensional code is installed, and the method includes:

S110: The caller scans the QR code of the car to be moved through the APP, obtains the setting information of the car to be moved, and sends the setting information in the form of notification information to the called of the car to be moved end;

S120: Obtain a virtual phone of the called end, and call the called end through the virtual phone;

S130: When the calling terminal and the called terminal are in the call mode, obtain the emotional information of the calling terminal and the called terminal through the emotion recognition technology, and determine the calling terminal and the called terminal according to the acquired emotional information. State whether the communication mode of the called terminal is to maintain the call mode or switch to the intelligent voice mode;

S140: When the two parties are in the call mode, when it is recognized that one of the calling end and the called end is angry, switch the two parties from the call mode to the intelligent voice mode;

S150: When the two parties are in the smart voice mode, when it is recognized that both parties are emotionally calm, switch the two parties from the smart voice mode to the call mode;

S160: After the calling terminal successfully communicates with the called terminal, the called terminal removes the car to be moved according to the setting information.

In addition, in order to achieve the above objective, the present application provides a code scanning and car shifting system, which includes:

The setting information acquisition module is used to scan the QR code of the car to be moved through the APP to obtain the setting information of the car to be moved, and the setting information is sent to the car to be moved in the form of a notification message. Caller

The called terminal module is used to obtain the virtual phone of the called terminal, and call the called terminal through the virtual phone;

The emotional information acquiring module is used to acquire the emotional information of the calling terminal and the called terminal through the emotional recognition technology when the calling terminal and the called terminal are in the call mode, and determine the emotional information according to the acquired emotional information. Whether the communication mode between the calling terminal and the called terminal is to maintain the call mode or switch to the intelligent voice mode;

When the two parties are in the call mode, when it is recognized that one of the calling end and the called end is angry, switching the two parties from the call mode to the intelligent voice mode;

When both parties are in the smart voice mode, when it is recognized that both parties are emotionally calm, switch the two parties from the smart voice mode to the call mode;

The car to be moved module is used to move the car to be moved by the called terminal according to the setting information after the calling terminal successfully communicates with the called terminal.

In order to achieve the above objective, the present application also provides an electronic device, which includes a memory and a processor, the memory includes a code scanning and carousing program, and the code scanning and carousing program is implemented as follows when the code scanning and carousing are executed by the processor step:

The caller scans the QR code of the car to be moved through the APP, obtains the setting information of the car to be moved, and sends the setting information to the called end of the car to be moved in the form of notification information;

Acquiring the virtual phone number of the called terminal, and calling the called terminal through the virtual phone number;

When the calling terminal and the called terminal are in the call mode, the emotional information of the calling terminal and the called terminal is acquired through the emotion recognition technology, and the emotional information obtained is used to determine the calling terminal and the called terminal. Whether the communication mode of the caller is to maintain the call mode or switch to the intelligent voice mode;

After the calling terminal and the called terminal successfully communicate, the called terminal removes the car to be moved according to the setting information.

In addition, in order to achieve the above object, the present application also provides a computer-readable storage medium, the computer-readable storage medium includes a code scanning and carousel program, when the code scanning and carousel program is executed by a processor, the implementation is as described above. Any step in the scanning method described above.

The code scanning method, electronic device and computer-readable storage medium of the present application proposes to obtain the virtual phone of the called end by scanning the two-dimensional code, and call the called end through the virtual phone to move the vehicle. In this way, the called is called It can avoid calling the mobile phone number directly, thereby solving the problem of leaking phone information; in addition, the emotion recognition technology is used to identify the emotions of both parties during the conversation between the caller and the called end, so as to avoid intensifying conflicts between the two parties due to untimely communication; The method of moving the vehicle provided by the application is not only simple and time-saving, but also can avoid conflicts between the calling end and the called end in the communication process.

Description of the drawings

FIG. 1 is a schematic diagram of an application environment of a preferred embodiment of a method for scanning a code and moving a car according to this application;

2 is a schematic diagram of modules of a preferred embodiment of the code scanning and car shifting system according to the application;

Fig. 3 is a flowchart of a preferred embodiment of a method for scanning a code and moving a car according to this application.

The realization, functional characteristics, and advantages of the purpose of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

detailed description

It should be understood that the specific embodiments described here are only used to explain the application, and not used to limit the application.

The present application provides a method for scanning a code and moving a car, which is applied to an electronic device 1. Referring to FIG. 1, this is a schematic diagram of the application environment of the preferred embodiment of the code scanning and car shifting method of the present application.

In this embodiment, the electronic device 1 may be a terminal device with arithmetic function, such as a server, a smart phone, a tablet computer, a portable computer, a desktop computer, and the like.

The electronic device 1 includes a processor 12, a memory 11, a network interface 14 and a communication bus 15.

The memory 11 includes at least one type of readable storage medium. The at least one type of readable storage medium may be a non-volatile storage medium such as flash memory, hard disk, multimedia card, card-type memory 11, and the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1. In other embodiments, the readable storage medium may also be the external memory 11 of the electronic device 1, such as a plug-in hard disk or a smart memory card (Smart Media Card, SMC) equipped on the electronic device 1. , Secure Digital (SD) card, Flash Card, etc.

In this embodiment, the readable storage medium of the memory 11 is usually used to store the code scanning program 10 installed in the electronic device 1 and the APP (Application, Chinese for the mobile phone's first) corresponding to the two-dimensional code. Three-party application) and so on. The memory 11 can also be used to temporarily store data that has been output or will be output.

In some embodiments, the processor 12 may be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run program codes or process data stored in the memory 11, such as scanning codes and moving cars. Procedure 10 and so on.

The network interface 14 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface), and is usually used to establish a communication connection between the electronic device 1 and other electronic devices.

The communication bus 15 is used to realize the connection and communication between these components.

FIG. 1 only shows the electronic device 1 with the components 11-15, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead.

Optionally, the electronic device 1 may also include a calling terminal interface, which may include an input unit such as a keyboard (Keyboard), a voice input device such as a microphone (microphone) and other devices with voice recognition functions, and a voice output device such as audio, Headphones, etc., optionally, the calling terminal interface may also include a standard wired interface and a wireless interface.

Optionally, the electronic device 1 may also include a display, and the display may also be referred to as a display screen or a display unit. In some embodiments, it may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an organic light-emitting diode (Organic Light-Emitting Diode, OLED) touch device, etc. The display is used to display information processed in the electronic device 1 and used to display a visualized call terminal interface.

Optionally, the electronic device 1 further includes a touch sensor. The area provided by the touch sensor for the caller to perform a touch operation is called a touch area. In addition, the touch sensor described here may be a resistive touch sensor, a capacitive touch sensor, or the like. Moreover, the touch sensor includes not only a contact-type touch sensor, but also a proximity-type touch sensor and the like. In addition, the touch sensor may be a single sensor, or may be, for example, a plurality of sensors arranged in an array.

In addition, the area of the display of the electronic device 1 may be the same as or different from the area of the touch sensor. Optionally, the display and the touch sensor are stacked to form a touch display screen. The device detects the touch operation triggered by the caller based on the touch screen.

Optionally, the electronic device 1 may also include a radio frequency (RF) circuit, a sensor, an audio circuit, etc., which will not be repeated here.

In the device embodiment shown in FIG. 1, the memory 11, which is a computer storage medium, may include an operating system and a code scanning and carousing program 10; when the processor 12 executes the code scanning and carousing program 10 stored in the memory 11 To achieve the following steps:

The caller scans the QR code of the car to be moved through the APP to obtain the setting information of the car to be moved, and the setting information is sent to the called end of the car to be moved in the form of notification information;

Preferably, the setting information includes: location information of the vehicle to be moved, photo information of the vehicle to be moved, and license plate information of the vehicle to be moved.

Preferably, the obtaining the emotion information of the calling terminal and the called terminal through the emotion recognition technology in the APP includes the following steps:

Obtain the voice data to be tested;

Perform feature extraction on the voice data to be tested to obtain voice features;

The emotion recognition model is used to recognize the voice feature, and the emotion recognition result is obtained.

Preferably, the use of an emotion recognition model to recognize the voice feature, and obtaining an emotion recognition result includes the following steps:

Adopt a neural network-based emotion recognition model to recognize the voice features, and judge whether an accurate recognition result can be output;

If the accurate recognition result can be output, use the accurate recognition result as the emotion recognition result;

If the accurate recognition result cannot be output, the emotion recognition model based on the support vector machine is used to recognize the voice feature, and the emotion recognition result is obtained.

Preferably, when the communication between the calling terminal and the called terminal fails, the calling terminal activates the smart voice mode of the APP to notify the called terminal to move the car.

The electronic device 1 proposed in the above embodiment obtains the virtual phone of the called end by scanning the two-dimensional code, and calls the called end through the virtual phone to move the car. In this way, the called end is called, which can avoid directly calling the mobile phone number. Solve the problem of leaking phone information; in addition, the emotion recognition technology is used to identify the emotions of both parties during the conversation between the calling end and the called end, so as to avoid intensifying conflicts between the two parties due to delay in communication; adopting the method of manoeuvring provided by this application is not only simple in the process , It saves time, and can also avoid conflicts between the calling end and the called end in the communication process.

In other embodiments, this application also provides a code scanning and car shifting system. As shown in FIG. 2, the code scanning and moving car system includes: a setting information acquisition module 110, a called terminal module 120, an emotion information acquisition module 130, and a waiting car moving module 140, in which:

The setting information acquisition module 110 is used to scan the QR code of the car to be moved through the APP to obtain the setting information of the car to be moved, and the setting information is sent to the car’s to be moved in the form of a notification message. Called end

The called terminal module 120 is used to obtain the virtual phone of the called terminal, and call the called terminal through the virtual phone;

The emotional information acquiring module 130 is used to acquire the emotional information of the calling terminal and the called terminal through the emotional recognition technology when the calling terminal and the called terminal are in a conversation mode, and judge according to the acquired emotional information Whether the communication mode between the calling terminal and the called terminal is a call-on-hold mode or a switch to an intelligent voice mode;

The car to be moved module 140 is used to move the car to be moved by the called terminal according to the setting information after the calling terminal successfully communicates with the called terminal.

The setting information in the setting information acquisition module 110 includes: location information of the vehicle to be moved, photo information of the vehicle to be moved, and license plate information of the vehicle to be moved.

The emotion information obtaining module 130 includes: a voice data obtaining unit 131 to be tested, a voice feature obtaining unit 132, and an emotion recognition result obtaining unit 133.

Wherein, the voice data acquisition unit 131 to be tested is used to acquire the voice data to be tested;

The voice feature obtaining unit 132 is configured to perform feature extraction on the voice data to be tested to obtain voice features;

The emotion recognition result obtaining unit 133 is configured to recognize the voice feature using an emotion recognition model, and obtain an emotion recognition result.

Among them, the emotion recognition result acquisition unit 133 includes: a judgment accurate recognition result output unit, an accurate recognition result output unit, and an accurate recognition result non-output unit.

Wherein, the judgment accurate recognition result output unit is used for recognizing the voice feature using a neural network-based emotion recognition model, and judging whether an accurate recognition result can be output;

An accurate recognition result output unit, configured to use the accurate recognition result as the emotion recognition result if the accurate recognition result can be output;

The accurate recognition result non-output unit is configured to, if the accurate recognition result cannot be output, use an emotion recognition model based on a support vector machine to recognize the voice feature to obtain the emotion recognition result.

In addition, this application also provides a method for scanning a code and moving a car. Referring to FIG. 3, it is a flowchart of a preferred embodiment of a method for scanning a code and moving a car according to this application. The method can be executed by a device, and the device can be implemented by software and/or hardware.

In this embodiment, the method of scanning code and carousing includes: step S110-step S160.

S110: The caller scans the QR code on the car to be moved through the APP to obtain the setting information of the car to be moved, and the setting information is sent to the called of the car to be moved in the form of notification information end;

S120: Obtain the virtual phone number of the called terminal, and call the called terminal through the virtual phone number;

In this application, first install an APP corresponding to the QR code on an electronic device such as a mobile terminal such as a mobile phone, a tablet computer, etc. This APP requires the caller to register. This APP can not only be used to scan the code, but also to move the car. Vehicle management, and connect insurance companies and vehicle management offices, and can perform policy inquiries and violations inquiries. In the embodiment of the present application, the calling end refers to the user, and the called end refers to the owner of the vehicle, and the user and the owner of the vehicle remove the car that needs to be moved through the above-mentioned method.

In step S110 and step S120, the phone of the called end of the car to be moved generates a QR code and places it on the car to be moved; the calling end first downloads an APP that matches the QR code, and when the car needs to be moved, The caller scans the QR code on the car to be moved through the APP to obtain the setting information of the car to be moved and the virtual number of the called end of the car to be moved. The setting information of the car to be moved will be directly sent to the called party of the car to be moved. After receiving the setting information, the called end will then receive a call from the calling end through the virtual number.

Among them, it should be noted that the first thing the called end receives is the setting information of the car to be moved. The setting information includes: the location of the car to be moved, the photo of the parking space and the license plate number, and the purpose of the call, etc. The called end After seeing the setting information, you can know which location the car needs to be moved, and the call received below is not a harassing call, but a call that needs to be moved; and the caller's phone number received by the called end is also a virtual phone number, also That is, the phone numbers of both parties are virtual numbers, and the real number of the other party cannot be seen by each other, which can well protect the phone privacy of both parties.

In step S130, when the called party and the calling party are in a conversation mode after connecting to the phone, the emotion recognition technology in the APP is used to identify the emotions of the two parties (the called party and the calling party) of the conversation, wherein the emotion recognition method Including the following steps:

S131: Obtain the voice data to be tested;

S132: Perform feature extraction on the voice data to be tested to obtain voice features;

S133: Use an emotion recognition model to recognize the voice feature, and obtain an emotion recognition result.

In the above method, in step S131, the voice data to be tested carries the data source ID; the emotion recognition model is used to recognize the voice features to obtain the emotion recognition result, including: based on the data source ID of the voice data to be tested, obtaining and A target emotion recognition model associated with the data source ID; the target emotion recognition model is used to recognize the voice feature, and the emotion recognition result is obtained.

In step S132, the voice features include, but are not limited to, prosodic features, voice quality features, frequency spectrum features, vocabulary features, and voiceprint features. Among them, the prosodic feature, also called the super-sound quality feature or the super-segment feature, refers to the changes in the pitch, length and intensity of the speech in addition to the tone quality features. The prosodic features include, but are not limited to, the pitch frequency, pronunciation duration, pronunciation amplitude, and pronunciation speed in this embodiment. The sound quality features include, but are not limited to, the formants F1-F3, frequency band energy distribution, harmonic signal-to-noise ratio, and short-term energy jitter in this embodiment. Spectrum characteristics, also known as vibration spectrum characteristics, refer to the decomposition of complex oscillations into resonant oscillations with different amplitudes and frequencies. The amplitudes of these resonant oscillations are arranged in a pattern formed by frequency. The frequency spectrum feature is integrated with the rhythm feature and the sound quality feature to improve the anti-noise effect of the feature parameter.

In this embodiment, the frequency spectrum feature adopts Mel-Frequency Cepstral Coefficients (MFCC), which can reflect the auditory characteristics of human ears. Vocabulary features are used to reflect the part-of-speech features of words used in the voice data to be tested, including but not limited to the positive words and negative words in this embodiment. The part-of-speech feature is combined with other voice features to help identify the emotion of the speaker corresponding to the voice data to be tested. The voiceprint feature (i-vector feature) is a feature related to the speaker, and combined with other voice features, it can more effectively improve the accuracy of the recognition during the speech recognition process.

In step S133, the emotion recognition model is a model pre-trained in the institution for identity verification. Emotion recognition results include, but are not limited to, recognizing the emotions such as happiness, anger, sadness, annoyance, and peace of the speaker corresponding to the voice feature.

Specifically, the terminal device uses a pre-trained emotion recognition model to recognize voice features, so as to obtain the emotion recognition results of happiness, anger, sadness, annoyance, and calm carried by the speaker when speaking. In this embodiment, the emotion recognition model is used to intelligently recognize speech features to obtain emotion recognition results. The recognition process has high processing efficiency, and can realize timely and comprehensive sampling of the voice data to be tested corresponding to the speaker without manual intervention. Conducive to saving labor costs.

Using the emotion recognition model to recognize voice features and obtain the emotion recognition results includes the following steps:

S1331: Use a neural network-based emotion recognition model to recognize voice features, and judge whether an accurate recognition result can be output;

S1332: If the accurate recognition result can be output, use the accurate recognition result as the emotion recognition result;

S1333: If the accurate recognition result cannot be output, the emotion recognition model based on the support vector machine is used to recognize the voice feature, and the emotion recognition result is obtained.

In step S1331, the emotion recognition model based on the neural network is a model for recognizing emotions in the speech data obtained by training the training speech data using the neural network model. A neural network-based emotion recognition model includes an input layer, a hidden layer, and an output layer. The acquired voice features are input into the input layer of the neural network-based emotion recognition model, and the voice features are recognized through the hidden layer, and then the output recognition is output through the output layer. As a result, the recognition results include accurate recognition results and fuzzy recognition results. The accurate recognition result is used to indicate that the voice feature corresponds to a specific emotion; the fuzzy recognition result is used to indicate that the voice feature cannot correspond to a specific emotion.

In step S1332, if the accurate recognition result can be output, the accurate recognition result is used as the emotion recognition result. In this embodiment, if the emotion recognition model based on the neural network can output accurate recognition results, it indicates that the speaker's emotion corresponding to the voice data to be tested is happy, angry, sad, annoying, and calm. The highest probability is much greater than the second highest probability. If the difference between the two is greater than the preset probability difference, the recognition result output by the emotion recognition model based on the neural network is more accurate, and the accurate recognition result can be directly output as the emotion recognition result.

In step S1333, if the accurate recognition result cannot be output, the emotion recognition model based on the support vector machine is used to recognize the voice feature, and the emotion recognition result is obtained.

In this embodiment, if the neural network-based emotion recognition model cannot output accurate recognition results, that is, the neural network-based emotion recognition model outputs fuzzy recognition results, indicating that the speaker's emotions corresponding to the voice data to be tested are happy, angry, sad, The difference between the highest probability of annoyance and calmness and the second highest probability is not greater than the preset probability difference, that is, it is impossible to accurately identify the speaker corresponding to a specific emotion. Therefore, the emotion recognition model based on the support vector machine needs to be used to further recognize the voice features to obtain the emotion recognition result, so as to further improve the accuracy of emotion recognition.

Among them, the emotion recognition model based on the support vector machine is a model for recognizing emotions in the speech data obtained by training the training speech data using the support vector machine model. The training process of the emotion recognition model of the support vector machine is as follows: the support vector machine model training is to separate different types of emotion attributes, which include five emotions: happiness, anger, sadness, irritability and calmness. Specifically, by inputting the voice features of the training voice data (that is, the prosody feature, the sound quality feature, the frequency spectrum feature, the vocabulary feature, and the voiceprint feature), the audio feature of the test data is extracted, and the optimal solution space corresponding to the feature is obtained. This space is For the corresponding emotion expression space, complete the emotion classification and judgment of the input training speech data.

In the above steps S1332 and S1333, it can be recognized that in the call mode, the two parties on the call recognize whether the emotion is angry or calm. If it is recognized that the emotion of one of the two parties is angry, switch the phones of both parties to the intelligent voice mode to avoid both parties. The intensification of the contradiction; when it is recognized that the emotions of both parties return to calm, the normal conversation between the two parties is resumed, that is, the smart voice mode is switched to the call mode, so as to smoothly communicate the situation of moving the car.

In this application, if the two parties successfully communicate, the called end will remove the car based on the telephone communication and the received setting information. In addition, when the communication between the calling terminal and the called terminal fails, the calling terminal activates the smart voice mode of the APP to notify the called terminal to move the car.

In the embodiment of the present application, the calling terminal and the called terminal communicate through the call mode or the combined communication mode and the intelligent voice mode, and the called terminal and the calling terminal reach an agreement on when the car that needs to be removed will be removed, etc. Wait, this means that the calling end and the called end have successfully communicated. It is also possible that due to communication problems or time issues, the two parties did not reach an agreement, and the caller cannot know when the callee can remove the car. In this case, the communication fails, and the caller uses the intelligent voice mode Notify the called party to move the car. In this case, the two parties do not need to communicate directly to avoid intensification of the conflict between the two parties.

The code scanning method for carousing proposed in the above embodiment obtains the virtual phone of the called terminal by scanning the QR code, and calls the called terminal through the virtual phone to move the car. Calling the called terminal in this way can avoid directly calling the mobile phone number. , So as to solve the problem of leaking phone information; in addition, the emotion recognition technology is used to identify the emotions of both parties during the conversation between the calling end and the called end, so as to avoid intensifying the conflicts between the two parties due to delay in communication; using the method of manoeuvring provided in this application not only The process is simple and time-saving, and it can also avoid conflicts between the calling end and the called end in the communication process.

In addition, an embodiment of the present application also proposes a computer-readable storage medium, the computer-readable storage medium includes a code scan and carousel program, and when the code scan and carousel program is executed by a processor, the following operations are implemented:

The calling terminal scans the QR code of the car to be moved through the APP to obtain the setting information of the car to be moved, and the setting information is sent to the called terminal of the car to be moved in the form of notification information;

Obtain the voice data to be tested;

The specific implementation of the computer-readable storage medium of the present application is substantially the same as the specific implementation of the above-mentioned code scanning method and electronic device, and will not be repeated here.

It should be noted that, in this article, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements, It also includes other elements not explicitly listed, or elements inherent to the process, device, article, or method. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, device, article, or method that includes the element.

The serial numbers of the foregoing embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. Through the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disk, optical disk), including a number of instructions to make a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present application.

The above are only the preferred embodiments of the application, and do not limit the scope of the patent for this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of the application, or directly or indirectly applied to other related technical fields , The same reason is included in the scope of patent protection of this application.

Claims

A method for scanning a car and moving a car is applied to an electronic device, and an APP corresponding to a two-dimensional code is installed on the electronic device, wherein the method includes:

S110: The caller scans the QR code on the car to be moved through the APP, obtains the setting information of the car to be moved, and sends the setting information to the car to be moved in the form of notification information. Caller

S120: Obtain the virtual phone number of the called terminal, and call the called terminal through the virtual phone number;

S130: When the calling terminal and the called terminal are in the call mode, obtain the emotional information of the calling terminal and the called terminal through the emotion recognition technology, and determine the calling terminal and the called terminal according to the acquired emotional information. State whether the communication mode of the called terminal is to maintain the call mode or switch to the intelligent voice mode;

S140: When the two parties are in the call mode, when it is recognized that one of the calling end and the called end is angry, switch the two parties from the call mode to the intelligent voice mode;

S150: When the two parties are in the smart voice mode, when it is recognized that both parties are emotionally calm, switch the two parties from the smart voice mode to the call mode;

S160: After the calling terminal successfully communicates with the called terminal, the called terminal removes the car to be moved according to the setting information.
The method for scanning a car and moving a car according to claim 1, wherein the setting information includes: position information of the car to be moved, photo information of the parking space of the car to be moved, and license plate information of the car to be moved.
The method for scanning a car and moving a car according to claim 1, wherein said obtaining the emotion information of the calling end and the called end through the emotion recognition technology in the APP comprises the following steps:

Obtain the voice data to be tested;

Perform feature extraction on the voice data to be tested to obtain voice features;

The emotion recognition model is used to recognize the voice feature, and the emotion recognition result is obtained.
The method of scanning code and carousing according to claim 3, characterized in that,

The voice features include prosodic features, sound quality features, frequency spectrum features, vocabulary features, and voiceprint features.
The method of scanning code and carousing according to claim 3, characterized in that,

The voice data to be tested carries the data source ID; where,

Based on the data source ID of the voice data to be tested, obtain the target emotion recognition model associated with the data source ID;

The target emotion recognition model is used to recognize the voice feature, and the emotion recognition result is obtained.
The method of scanning a car and moving a car according to claim 5, wherein said adopting an emotion recognition model to recognize said voice feature, and obtaining an emotion recognition result comprises the following steps:

Adopt a neural network-based emotion recognition model to recognize the voice features, and judge whether an accurate recognition result can be output;

If the accurate recognition result can be output, use the accurate recognition result as the emotion recognition result;

If the accurate recognition result cannot be output, the emotion recognition model based on the support vector machine is used to recognize the voice feature, and the emotion recognition result is obtained.
The scan code and carousel method according to claim 6, characterized in that,

The neural network-based emotion recognition model includes an input layer, a hidden layer and an output layer.
The code scanning and car shifting method according to claim 7, characterized in that,

The step of using a neural network-based emotion recognition model to recognize the voice feature and judging whether an accurate recognition result can be output includes:

Input the acquired voice features into the input layer;

Performing recognition processing on voice features through the hidden layer;

Outputting a recognition result through the output layer, where the recognition result includes an accurate recognition result and a fuzzy recognition result;

The accurate recognition result is a recognition result used to indicate that the voice feature corresponds to a specific emotion; the fuzzy recognition result is a recognition result used to indicate that the voice feature cannot correspond to a specific emotion.
The scan code and carousel method according to claim 6, characterized in that,

The support vector machine-based emotion recognition model adopts a support vector machine model to train training speech data to obtain a model for recognizing emotions in the speech data.
The scan code and carousel method according to claim 9, characterized in that,

Wherein, the step of training the training speech data by the support vector machine model includes:

By inputting the voice features of the training voice data, extract the audio features of the data to be tested, obtain the optimal solution space corresponding to the audio features, and complete the emotion classification and judgment of the input training voice data, wherein the solution space is corresponding Emotional expression space.
The code scanning and car shifting method according to any one of claims 1-10, characterized in that,

When the communication between the calling terminal and the called terminal fails, the calling terminal notifies the called terminal to move the car through an intelligent voice mode.
A code scanning and moving car system includes:

The setting information acquisition module is used to scan the QR code of the car to be moved through the APP to obtain the setting information of the car to be moved, and the setting information is sent to the car to be moved in the form of a notification message. Caller

The called terminal module is used to obtain the virtual phone of the called terminal, and call the called terminal through the virtual phone;

The emotional information acquiring module is used to acquire the emotional information of the calling terminal and the called terminal through the emotional recognition technology when the calling terminal and the called terminal are in the call mode, and determine the emotional information according to the acquired emotional information. Whether the communication mode between the calling terminal and the called terminal is to maintain the call mode or switch to the intelligent voice mode;

When the two parties are in the call mode, when it is recognized that one of the calling end and the called end is angry, switching the two parties from the call mode to the intelligent voice mode;

When both parties are in the smart voice mode, when it is recognized that both parties are emotionally calm, switch the two parties from the smart voice mode to the call mode;

The car to be moved module is used to move the car to be moved by the called terminal according to the setting information after the calling terminal successfully communicates with the called terminal.
The code scanning and car shifting system according to claim 12, characterized in that,

The emotion information acquisition module includes: a voice data acquisition unit to be tested, a voice feature acquisition unit, and an emotion recognition result acquisition unit; wherein,

The voice data acquisition unit to be tested is used to acquire voice data to be tested;

A voice feature acquisition unit, configured to perform feature extraction on the voice data to be tested to obtain voice features;

The emotion recognition result obtaining unit is used for recognizing the voice feature using the emotion recognition model to obtain the emotion recognition result.
The code scanning and car shifting system according to claim 13, characterized in that,

The emotion recognition result acquisition unit includes: a judgment accurate recognition result output unit, an accurate recognition result output unit, and an accurate recognition result non-output unit;

Wherein, the judgment and accurate recognition result output unit is used for recognizing the voice feature by using an emotion recognition model based on a neural network, and judging whether an accurate recognition result can be output;

The accurate recognition result output unit is configured to use the accurate recognition result as the emotion recognition result if the accurate recognition result can be output;

The accurate recognition result non-output unit is configured to, if the accurate recognition result cannot be output, use an emotion recognition model based on a support vector machine to recognize the voice feature to obtain the emotion recognition result.
An electronic device, characterized in that the electronic device includes a memory and a processor, the memory includes a code scanning and carousel program, and the following steps are implemented when the code scanning and carousel are executed by the processor:

The calling terminal scans the QR code of the car to be moved through the APP to obtain the setting information of the car to be moved, and the setting information is sent to the called terminal of the car to be moved in the form of notification information;

Acquiring the virtual phone number of the called terminal, and calling the called terminal through the virtual phone number;

When the calling terminal and the called terminal are in the call mode, the emotional information of the calling terminal and the called terminal is acquired through the emotion recognition technology, and the emotional information obtained is used to determine the calling terminal and the called terminal. Whether the communication mode of the caller is to maintain the call mode or switch to the intelligent voice mode;

When the two parties are in the call mode, when it is recognized that one of the calling end and the called end is angry, switching the two parties from the call mode to the intelligent voice mode;

When both parties are in the smart voice mode, when it is recognized that both parties are emotionally calm, switch the two parties from the smart voice mode to the call mode;

After the calling terminal and the called terminal successfully communicate, the called terminal removes the car to be moved according to the setting information.
The electronic device according to claim 15, wherein the setting information comprises: position information of the car to be moved, photo information of the parking space of the car to be moved, and license plate information of the car to be moved.
The electronic device according to claim 15, wherein the obtaining the emotion information of the calling end and the called end through the emotion recognition technology in the APP comprises the following steps:

Obtain the voice data to be tested;

Perform feature extraction on the voice data to be tested to obtain voice features;

The emotion recognition model is used to recognize the voice feature, and the emotion recognition result is obtained.
15. The electronic device according to claim 15, wherein said adopting an emotion recognition model to recognize said voice feature, and obtaining an emotion recognition result comprises the following steps:

Adopt a neural network-based emotion recognition model to recognize the voice features, and judge whether an accurate recognition result can be output;

If the accurate recognition result can be output, use the accurate recognition result as the emotion recognition result;

If the accurate recognition result cannot be output, the emotion recognition model based on the support vector machine is used to recognize the voice feature, and the emotion recognition result is obtained.
The electronic device of claim 17, wherein:

The voice data to be tested carries the data source ID; where,

Based on the data source ID of the voice data to be tested, obtain the target emotion recognition model associated with the data source ID;

The target emotion recognition model is used to recognize the voice feature, and the emotion recognition result is obtained.
A computer-readable storage medium, characterized in that, the computer-readable storage medium includes a code scanning and carousel program, and when the code scanning and carousel program is executed by a processor, it realizes any one of The steps of the scan code and car shift method described in the item.