Authentication method and device, storage medium, electronic device and product

Abstract

Embodiments of the present specification provide an authentication method, an authentication device, a computer readable storage medium, an electronic device and a computer program product. The authentication method comprises: obtaining an identification model for identifying a preset keyword from a server to a local, the identification model being trained based on an audio training set, the audio training set comprising a plurality of audios containing the preset keyword; after detecting a preset trigger operation, starting to play some locally pre-stored authentication questions, and receiving voice information when a user answers the authentication questions; then, identifying the voice information by the identification model to determine the answer of the user to the authentication question; and then, determining whether the authentication is passed in combination with the answer of the user to the authentication question and a standard answer of the authentication question.

Description

Technical Field

[0001] This specification relates to the field of data processing technology, and in particular to an authentication method, authentication device, computer-readable storage medium, electronic device, and computer program product. Background Technology

[0002] Currently, regulatory authorities have clearly stipulated that data generated by third-party platforms during securities account opening and trading processes belongs solely to the corresponding securities institution. Third-party platforms are not permitted to allow any data from these processes to be accessed by any institution other than the securities institution. In related technologies, when voice recognition is required during account opening authentication, online voice recognition solutions are used. However, these solutions rely heavily on network stability. In scenarios with poor network conditions or unstable services, the authentication process is difficult to complete smoothly. Furthermore, data may be intercepted by third parties during network transmission, posing privacy and compliance risks. Additionally, online voice recognition is time-consuming, impacting user experience. Therefore, there is an urgent need for a rapid authentication method that avoids data interception by third parties during the authentication process and reduces the authentication process's dependence on the network.

[0003] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this specification, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this specification is to provide an authentication method, authentication device, computer-readable storage medium, electronic device, and computer program product that provides a scheme for local authentication to at least partially prevent data interception during the authentication process by third parties, reduce the reliance of the authentication process on the network, and accelerate the authentication speed.

[0005] Other features and advantages of this specification will become apparent from the following detailed description, or may be learned in part by practice of this specification.

[0006] According to one aspect of this specification, an authentication method is provided, the method comprising: obtaining a recognition model for recognizing preset keywords from a server and storing it locally; wherein the recognition model is trained based on an audio training set, the audio training set including a plurality of audio recordings containing the preset keywords; after detecting a preset trigger operation, playing the locally pre-stored authentication question and receiving voice information of a user answering the authentication question; recognizing the voice information through the recognition model to determine the user's answer to the authentication question; and determining whether authentication is successful based on the user's answer to the authentication question and a pre-stored standard answer to the authentication question; wherein the standard answer to the authentication question is the preset keyword.

[0007] According to another aspect of this specification, an authentication device is provided, the device comprising: an acquisition module, a playback and reception module, a determination module, and an authentication module;

[0008] The system includes the following modules: an acquisition module for acquiring a recognition model for identifying preset keywords from a server and storing it locally; wherein the recognition model is trained on an audio training set, which includes several audio recordings containing the preset keywords; a playback and reception module for playing the locally stored authentication question and receiving the user's voice information when answering the authentication question after detecting a preset trigger operation; a first determination module for identifying the voice information using the recognition model and determining the user's answer to the authentication question; and a second determination module for determining whether authentication is successful based on the user's answer to the authentication question and the pre-stored standard answer to the authentication question, wherein the standard answer to the authentication question is the preset keyword.

[0009] According to another aspect of this specification, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the authentication method as described above.

[0010] According to one aspect of this specification, a computer-readable storage medium is provided that stores instructions which, when executed on a computer or processor, cause the computer or processor to perform the authentication method as described above.

[0011] According to another aspect of this specification, a computer program product containing instructions is provided that, when the computer program product is run on a computer or processor, causes the computer or processor to perform the authentication method as described above.

[0012] The authentication methods, authentication devices, computer-readable storage media, electronic devices, and computer program products provided in the embodiments of this specification have the following technical effects:

[0013] In the exemplary embodiments provided in this specification, a recognition model for identifying preset keywords is obtained from the server and stored locally. This recognition model is trained based on an audio training set, which includes several audio recordings containing the preset keywords. Since this recognition model is used to identify the preset keywords without requiring other complex recognition methods, it is relatively small in size, occupies less memory locally, and has lower computational requirements, making it suitable for local operation. Upon detecting a preset trigger operation, a pre-stored authentication question is played, and the user's voice information when answering the authentication question is received. Then, the recognition model identifies the voice information to determine the user's answer to the authentication question. Next, based on the user's answer to the authentication question and the pre-stored standard answer to the authentication question, it is determined whether authentication is successful; wherein the standard answer to the authentication question is the preset keyword. In other words, the solutions provided by the exemplary embodiments in this specification can directly recognize the user's voice information locally based on a local recognition model, without first sending the voice information to the securities firm, which then sends it to its purchased voice recognition service. This reduces the time required for voice recognition, allowing for rapid local completion of voice recognition, thereby accelerating authentication and improving user experience. Furthermore, local voice recognition does not involve data transmission over the network, thus preventing data interception during the authentication process by third parties and reducing the authentication process's dependence on the network.

[0014] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification. It is obvious that the drawings described below are merely some embodiments of this specification, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0016] Figure 1 This is a schematic flowchart illustrating an embodiment of the authentication method provided in this specification.

[0017] Figure 2 This is a schematic flowchart illustrating an embodiment of S130 provided in this specification.

[0018] Figure 3 This is a schematic diagram of an authentication device provided in one embodiment of this specification.

[0019] Figure 4A schematic diagram of an authentication device provided for another embodiment of this specification.

[0020] Figure 5 The schematic diagram illustrates the structure of an electronic device according to an exemplary embodiment of this specification. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this specification clearer, the embodiments of this specification will be described in further detail below with reference to the accompanying drawings.

[0022] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.

[0023] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this specification more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of the embodiments described herein. However, those skilled in the art will recognize that the technical solutions described herein may be practiced with one or more of the specific details mentioned above omitted, or other methods, components, apparatus, steps, etc., may be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this specification.

[0024] Furthermore, the accompanying drawings are merely illustrative diagrams of this specification and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0025] During the securities account opening process, brokerage firms need to confirm that the user applying for the account is indeed the user and that the user is aware of the risks of the stock market and voluntarily chooses to open a stock account with the brokerage firm. Therefore, throughout the account opening process, with the user's permission, a video of the user must be recorded using the front-facing camera of their mobile phone. During the video recording, the user's name, whether they are the one making the operation, and whether they voluntarily choose to open a securities account with the firm will be verified. Regulatory authorities have clearly stipulated that the ownership of data generated by third-party platforms during securities account opening and trading belongs solely to the corresponding securities institution. Third-party platforms are not permitted to allow any data from institutions other than securities institutions to be obtained during securities trading and account opening.

[0026] In related technologies, during account opening authentication: after each question is played, the user's voice is recorded and sent to the brokerage firm through the server-side Automatic Speech Recognition (ASR) interface provided by the brokerage firm. After receiving the user's voice, the brokerage firm forwards it to its purchased speech recognition service for speech recognition. The speech recognition service returns the recognized text to a third-party platform. The third-party platform determines whether the account opening authentication is successful based on the standard answer provided by the brokerage firm.

[0027] However, the above solution uses online speech recognition, which relies on the stability of the network and brokerage services. In scenarios with poor network conditions or unstable services, the authentication process is difficult to carry out smoothly. Furthermore, data may be intercepted by third parties during network transmission, posing privacy and compliance risks. In addition, the online speech recognition process is relatively long and time-consuming, affecting the user experience.

[0028] This specification provides an authentication method, an authentication device, and a computer-readable storage medium, electronic device, and computer program product for implementing the above method, which can solve the aforementioned problems existing in related technologies. The authentication method embodiments provided in this specification will be described in detail below:

[0029] in, Figure 1 This is a schematic flowchart illustrating an authentication method provided in one embodiment of this specification. For example, the entity executing the authentication method provided in this embodiment is an electronic device, such as a mobile phone, computer, laptop, or tablet. (See reference) Figure 1 The embodiment shown in the figure includes: S110-S140.

[0030] S110: Obtain the recognition model used to identify preset keywords from the server to the local machine.

[0031] S120: After detecting the preset trigger operation, play the above-mentioned locally stored authentication questions and receive the voice information of the user when answering the above-mentioned authentication questions.

[0032] S130: The above-mentioned voice information is identified through the above-mentioned recognition model to determine the above-mentioned user's answer to the above-mentioned authentication question.

[0033] S140: Based on the user's answer to the authentication question and the pre-stored standard answer to the authentication question, determine whether the authentication is successful; wherein, the standard answer to the authentication question is the preset keyword.

[0034] exist Figure 1 In the authentication method provided by the illustrated embodiment, since the recognition model is used to recognize preset keywords without performing other complex recognition, the recognition model is small in size, occupies less local memory, and has lower computational requirements, thus making it suitable for local operation. After detecting a preset trigger operation, a locally stored authentication question is played, and the user's voice information when answering the authentication question is received. Then, the aforementioned voice information is recognized by the recognition model to determine the user's answer to the authentication question. Next, based on the user's answer to the authentication question and the pre-stored standard answer to the authentication question, it is determined whether authentication is successful; wherein, the standard answer to the authentication question is the preset keyword. In other words, the solution provided by the exemplary embodiment of this specification can directly recognize the user's voice information locally based on a local recognition model, without first sending the voice information to a securities firm, which then sends it to its purchased voice recognition service. This reduces the time consumed by voice recognition, allowing for rapid local completion of voice recognition, thereby accelerating authentication and improving user experience. Furthermore, performing speech recognition locally does not involve data transmission over the network, thus avoiding data interception by third parties during the authentication process to some extent, and reducing the authentication process's dependence on the network.

[0035] The following are Figure 1 The specific implementation methods of each step in the illustrated embodiments are described in detail below:

[0036] In step S110, the electronic device retrieves a recognition model from the server for recognizing preset keywords to its local storage. This recognition model is trained on an audio training set, which includes several audio recordings containing the preset keywords; therefore, the recognition model is essentially a speech recognition model.

[0037] In an exemplary embodiment, several audio files in the audio training set can all be short audio files. Short audio files can be audio files with fewer than a preset number of characters. The preset number of characters can be set according to actual needs. For example, the preset number of characters can be set between 3 and 10. It can be understood that within a certain range, the fewer the preset number of characters, the smaller the size of the audio training set and the smaller the size of the trained recognition model.

[0038] In an exemplary embodiment, the server can train a model based on the ResNet residual network and the aforementioned audio training set to obtain the recognition model, which can be approximately 100kb in size. This means the recognition model is a simplified version; even if it is acquired by the electronic device and stored locally, it will not consume excessive local storage space or computing resources, thus enabling it to run locally on the electronic device without affecting its normal functions.

[0039] In an exemplary embodiment, the preset keywords include keywords representing affirmation and keywords representing negation. For example, keywords representing affirmation may include any one of the following or any combination thereof: "yes", "agree", "support", etc. Keywords representing negation may include any one of the following or any combination thereof: "no", "disagree", "disagree", "oppose", etc. The aforementioned keywords representing affirmation and negation are usually relatively short in length. Therefore, the audio training set includes several audio recordings containing the above keywords, resulting in a smaller audio training set size and a smaller recognition model size. Furthermore, the recognition model is relatively easy to use to identify the above keywords, thereby improving recognition efficiency.

[0040] In an exemplary embodiment, the audio samples in the audio training set can cover languages ​​from different regions. These languages ​​can include languages ​​from all over the world and / or dialects from across the country, enabling the trained recognition model to recognize speech information in a wide variety of languages, thereby improving the applicability of the authentication method in this embodiment.

[0041] In an exemplary embodiment, the electronic device obtains the recognition model from the server in two ways: either the electronic device downloads the recognition model from the server, or the server actively sends the recognition model to the electronic device, thereby enabling the electronic device to obtain the recognition model. For example, after training the recognition model, the server can send the recognition model to an electronic device with a preset application installed. This preset application can be an application with authentication requirements, such as Alipay. However, this embodiment does not specifically limit this.

[0042] In an exemplary embodiment, the electronic device can, upon detecting entry into a preset authentication page, retrieve a recognition model from the server for identifying preset keywords and store it locally. The preset authentication page indicates that the user is likely to enter the authentication process through this page, meaning the user has a need for authentication. For example, detecting entry into a preset authentication page could be: detecting that the user clicked to enter a securities account opening page. It is understandable that since entering the securities account opening page indicates the user is likely to open a securities account, and the securities account opening process requires user authentication, the securities account opening page can be understood as a preset authentication page.

[0043] In this exemplary embodiment, after detecting that the user has entered the preset authentication page, it is highly likely that the user is about to enter the authentication process. At this time, obtaining the recognition model from the server is beneficial to obtain the recognition model in a timely and effective manner, avoiding unnecessary acquisition steps, and thus avoiding wasting user traffic to a certain extent.

[0044] In S120, after detecting a preset trigger operation, the electronic device begins playing locally stored authentication questions and turns on the microphone to receive the user's voice information when answering the authentication questions. The locally stored authentication questions can be questions provided by securities firms, and the sentence structure of the authentication questions can be a judgment sentence. Therefore, the standard answer to the authentication questions is usually a keyword indicating affirmation or a keyword indicating negation.

[0045] In an exemplary embodiment, authentication questions may include: Please confirm if the user's name is Zhang San, please confirm if this operation is being performed by the user themselves, and please confirm whether you voluntarily wish to open a securities account with this institution. It is understood that different securities firms may provide different authentication questions, and this embodiment does not specifically limit the form of the authentication questions. The standard answer to the authentication question can be the aforementioned preset keywords, for example: the standard answer to "Please confirm if the user's name is Zhang San" is "Yes," the standard answer to "Please confirm if this operation is being performed by the user themselves" is "Yes," and the standard answer to "Please confirm whether you voluntarily wish to open a securities account with this institution" is "Yes."

[0046] In an exemplary embodiment, a preset trigger operation can be used to indicate that the authentication question can be started. For example, a preset virtual button can be displayed on the electronic device, and when the user clicks the virtual button, it can be determined that a preset trigger operation has been detected. Optionally, the preset trigger operation can also be a voice trigger operation; for example, if the electronic device receives a preset voice command, it can be determined that a preset trigger operation has been detected.

[0047] In an exemplary embodiment, both the locally stored authentication questions and the standard answers to those questions can be in text format. When it is necessary to play the authentication question, the electronic device can play the authentication question in speech form via Text-to-Speech (TTS) and prompt the user to answer it. Thus, the electronic device can receive the user's voice information while the user is answering the authentication question. Optionally, the authentication question can be played using the default language set by the electronic device, which can be either Chinese or a foreign language.

[0048] In step S130, the electronic device identifies the voice information using the aforementioned recognition model and determines the user's answer to the authentication question. The recognition model identifies preset keywords in the voice information, allowing the electronic device to determine the user's answer to the authentication question based on these preset keywords. For example, the preset keywords identified from the voice information can be used as the user's answer to the authentication question.

[0049] In an exemplary embodiment, the electronic device can extract speech features from the received speech information and then input these speech features into a recognition model. The recognition model can then output a recognition result, which can be the aforementioned preset keywords. The speech features may include Mel-Frequency Cepstral Coefficients (MFCC) features and / or Filter Banks (FBank) features. In a specific implementation, if the speech information contains preset keywords, the recognition model can output a recognition result; if the speech information does not contain preset keywords, the recognition model may not output a recognition result.

[0050] In an exemplary embodiment, the implementation of S130 may include, as follows: Figure 2 S1302-S1306 shown:

[0051] S1302: Extract the above-mentioned speech information by a preset speech segment duration, and extract the speech features of the extracted speech segment information.

[0052] S1304: Input the above speech features into the above recognition model to obtain the recognition result of the above speech segment information.

[0053] S1305: Based on the above identification results, determine the above user's answer to the above authentication question.

[0054] The following are Figure 2 The specific implementation methods of each step in the illustrated embodiments are described in detail below:

[0055] In step S1302, the preset duration of a speech segment can be set according to actual needs. The unit of the speech segment duration can be at the millisecond level, for example, it can be between 200 milliseconds and 500 milliseconds. That is, the speech information can be segmented according to the preset speech segment duration to obtain several speech segment information, and the duration of these speech segment information can be the aforementioned preset speech segment duration. Then, the speech features of these segmented speech information are extracted, and the speech features can include the aforementioned MFCC features and / or FBank features.

[0056] In S1304, the electronic device can input the aforementioned speech features into the aforementioned recognition model to obtain the recognition result of the aforementioned speech segment information. That is, the input of the recognition model is the speech features of the aforementioned speech segment information, and the output is the recognition result of the aforementioned speech segment information. This recognition result can be the aforementioned preset keywords, that is, keywords representing affirmation or keywords representing negation.

[0057] In step S1306, the electronic device determines the user's answer to the authentication question based on the recognition result. For example, the recognition result of any speech segment can be used as the user's answer to the authentication question. Optionally, a target speech segment can be selected from several segmented speech segments, and the recognition result of that target speech segment can be used as the user's answer to the authentication question. This target speech segment can be a speech segment in the middle position among the several speech segments. It is understood that speech segments in the middle position are relatively stable; therefore, using the recognition result of that target speech segment as the user's answer to the authentication question helps improve the accuracy of the determined answer.

[0058] In an exemplary embodiment, in S1302, the electronic device can extract the voice information by a preset voice segment duration and extract the voice features of the extracted voice segment information until it is determined that at least two consecutive voice segment information have the same recognition result, at which point the extraction of the voice information by the preset voice segment duration stops. Correspondingly, in S1306, the electronic device can determine the recognition result of the at least two identical voice segment information as the user's answer to the authentication question. That is, the electronic device does not need to extract the entire voice information or extract the voice features of all voice segment information. When it is determined that at least two consecutive voice segment information have the same recognition result, the extraction of voice segment information in the voice information can be stopped. For example, if the recognition results of the first two voice segment information in the voice information are the same, there is no need to continue extracting the voice segment information after the first two voice segment information. After the corresponding recognition model recognizes the first two voice segment information, the electronic device can obtain the answer to the authentication question without having to perform voice recognition on the voice segment information after the first two voice segment information, thereby improving recognition efficiency. Meanwhile, the fact that at least two consecutive speech segments have the same recognition result indicates that the recognition result is relatively stable and accurate. Therefore, this embodiment can improve recognition efficiency while improving recognition accuracy.

[0059] In an exemplary embodiment, the duration of the voice segment in S1302 includes a first voice segment duration and a second voice segment duration, wherein the first voice segment duration is longer than the second voice segment duration. In S1302, the electronic device can extract the first voice segment information from the voice information using the first voice segment duration, and extract several voice segments information following the first voice segment information using the second voice segment duration. The first and second voice segment durations can be set according to actual needs.

[0060] For example, the duration of the first speech segment can be set to 500 milliseconds, and the duration of the second speech segment can be set to 300 milliseconds. The electronic device can then perform recognition from a continuous stream of speech information locally in real time. Initially, a 500-millisecond segment of speech information is extracted for recognition calculation, and subsequently, 300-millisecond segments are extracted every 300 milliseconds for recognition calculation. The recognition and calculation process can include: sequentially extracting speech features from the extracted speech segments using the speech waveform; inputting the speech features into the classification network of the recognition model for classification calculation; and obtaining the classification result, which is the recognition result of the recognition model. Optionally, if two consecutive recognition results are both keywords representing affirmation, such as "YES," then the user's current answer is determined to be "YES," meaning the user's answer to the authentication question is "YES." Conversely, if two consecutive recognition results are both keywords representing negation, such as "NO," then the user's current answer is determined to be "NO," meaning the user's answer to the authentication question is "NO."

[0061] In this embodiment, the voice information is first extracted with a relatively long first voice segment duration, and then extracted with a relatively short second voice segment duration. Considering that the user may need a certain reaction time after the electronic device has just finished playing the authentication question, and the voice information of the user collected at the beginning may be unstable, the first extraction of the voice information with a relatively long first voice segment duration can ensure that the extracted voice segment information contains effective information, thereby improving the recognition efficiency to a certain extent.

[0062] In an exemplary embodiment, the electronic device can start timing from the moment the aforementioned voice features are input into the aforementioned recognition model. If the recognition model has not output a recognition result after the preset timing period, the locally stored authentication question is replayed, prompting the user to answer again. The preset timing period can be set according to actual needs, and the unit of the preset timing period can be seconds, for example, between 2 and 4 seconds. If the recognition model has not output a recognition result after the preset timing period, it indicates that the user's voice information may not contain the preset keywords, so the recognition model cannot recognize the preset keywords and therefore fails to output a recognition result. Alternatively, it may indicate that the user's voice information has not consistently matched the classification network in the recognition model. In this case, the electronic device can replay the authentication question and prompt the user to answer again, thereby guiding the user to continue the authentication question answering process and increasing the likelihood of successful authentication.

[0063] In S140, the electronic device can determine whether authentication is successful based on the user's answer to the authentication question and the pre-stored standard answers to the authentication questions; wherein, the standard answers to the authentication questions are the preset keywords. In this embodiment, both the authentication question and the standard answer to the authentication question can be provided by the securities firm and stored locally in text form. When the user's answer to the authentication question is the same as the pre-stored standard answer to the authentication question, it can be determined that the user's answer to the authentication question is correct, and thus authentication is successful. When multiple authentication questions are pre-stored locally, if the user's answers to all of the authentication questions are correct, authentication is successful.

[0064] In an exemplary embodiment, multiple different authentication questions are pre-stored locally. The implementation of playing the pre-stored authentication questions in S120 may include: playing the multiple authentication questions sequentially according to their playback order, and receiving voice information from the user when answering the multiple authentication questions, until it is determined that all of the authentication questions have been played or that the user's answer to the currently played authentication question is not the standard answer; wherein, when the user's answer to the currently played authentication question is the standard answer, the next authentication question is played. Correspondingly, the implementation of S140 may include: determining that authentication is successful when the user's answers to multiple authentication questions are all the standard answers; determining that authentication is unsuccessful when the user's answer to any one of the authentication questions is not the standard answer.

[0065] For example, the playback order of the above authentication questions can be set according to actual needs, and the playback order can be preset by the securities firm. For example, according to the playback order from front to back, the multiple authentication questions are: "Please confirm if the user's name is ××", "Please confirm if this operation is performed by the user", and "Please confirm whether you voluntarily open a securities account with this institution". Here, "××" is the user's name. Specifically, the electronic device can first play the first authentication question, "Please confirm if the user's name is ××", and then receive the user's voice information answering the first authentication question. If the recognition model recognizes that the voice information contains a keyword indicating affirmation, such as "yes", and the recognized "yes" is the standard answer to the first authentication question, then the second authentication question, "Please confirm if this operation is performed by the user", is played. Then, the voice information of the user's answer to the second authentication question is received. If the recognition model recognizes that the voice information contains a keyword indicating affirmation, such as "yes", and the recognized "yes" is the standard answer to the second authentication question, then the third authentication question, "Please confirm whether you voluntarily open a securities account with this institution", is played. Then, the system receives the user's voice response to the third authentication question. If the recognition model identifies a keyword indicating affirmation, such as "yes," in the voice response, and this identified "yes" is the standard answer to the third authentication question, then the authentication is successful. If the user's answer to any authentication question is not the standard answer for that question, then the authentication fails, and the next authentication question will not be played.

[0066] In an exemplary embodiment, the implementation method described above, which sequentially plays multiple authentication questions according to their playback order and receives voice information from the user when answering the authentication questions, includes: after receiving voice information from the user when answering the first authentication question, determining the user's language characteristics based on the voice information; and when it is determined that the remaining authentication questions after the first authentication question need to be played, playing the remaining authentication questions corresponding to the language characteristics. The language characteristics describe the language used in the user's voice information. For example, the language characteristics may be Chinese or a foreign language. Chinese may further include Mandarin and local dialects, and foreign languages ​​may further include English, Korean, Japanese, French, etc. In this embodiment, the language used when playing the first authentication question can be the default language set by the electronic device. Common default languages ​​include Chinese (Mandarin) or English.

[0067] For example, the first authentication question, "Please confirm whether the user's name is ××," can be played in Mandarin first. If the user's language characteristics are determined to be Shanghainese based on the voice information of the user's answer to the first authentication question, then if it is determined that the remaining authentication questions after the first authentication question need to be played, the remaining authentication questions can be played in Shanghainese.

[0068] In this embodiment, the authentication questions are played in conjunction with the user's language characteristics, so that the authentication questions heard by the user can match their own language habits, thereby improving the user's authentication experience and, to a certain extent, increasing the success rate of authentication.

[0069] In an exemplary embodiment, the implementation of S140 may include: performing voice emotion analysis on the voice information of the user when answering the authentication question, and obtaining the analysis result; determining whether the authentication is successful based on the analysis result, the user's answer to the authentication question, and the pre-stored standard answer to the authentication question.

[0070] For example, an electronic device can determine, based on the analysis results, whether the user's answer to the authentication question was voluntary. If it is determined that the user's answer was voluntary and the user's answer to the authentication question is the same as the pre-stored standard answer to the authentication question, then the authentication is successful. In other words, the conditions for successful authentication include: the user's voluntary participation and the user's answer to the authentication question being a standard answer. If the user's participation is involuntary or the user's answer to the authentication question is not a standard answer, then the authentication is unsuccessful.

[0071] For example, the analysis results of the aforementioned voice emotion analysis can include three types: positive, negative, and normal. When the analysis result is positive or normal, the electronic device determines that the user's answer to the authentication question was voluntary. When the analysis result is negative, the electronic device determines that the user's answer to the authentication question was accompanied by negative emotions such as fear, and therefore determines that the user's answer to the authentication question was not voluntary.

[0072] In this embodiment, the analysis results of the user's voice emotion are further combined to determine whether the authentication is successful, which helps to improve the accuracy of the authentication results.

[0073] For example, the electronic device can first perform voice sentiment analysis on the voice information of the user answering the authentication question, and obtain the analysis results. If the analysis results determine that the user voluntarily answered the authentication question, then the recognition model is used to recognize the voice information to determine the user's answer to the authentication question. In this embodiment, the user's answer to the authentication question is determined only when it is determined that the user voluntarily answered the authentication question. This avoids determining the user's answer when the user is not voluntarily answering the authentication question, which helps to improve the accuracy of the authentication results while avoiding unnecessary operations, thereby improving authentication efficiency.

[0074] For example, an electronic device can detect a user's emotions based on their voice information when answering authentication questions. When the electronic device determines that the user's emotions are negative based on the analysis results, it can require the user to immediately adjust their emotions until the electronic device detects that the voice emotion analysis results of the user's voice information meet the requirements. This ensures that the user is in a stable emotional state during authentication, avoiding the need for reviewers to require the user to re-authenticate after discovering abnormal emotions during the authentication process. This embodiment can detect the user's emotions in real time during the authentication process and promptly remind the user to adjust their emotions when abnormal emotions are detected, thereby effectively reducing the user's operation process and providing a smooth user experience.

[0075] It should be noted that the above figures are merely illustrative of the processes included in the methods according to exemplary embodiments of this specification, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may, for example, be executed synchronously or asynchronously in multiple modules.

[0076] The following are embodiments of the apparatus described in this specification, which can be used to execute the embodiments of the methods described in this specification. For details not disclosed in the apparatus embodiments of this specification, please refer to the embodiments of the methods described in this specification.

[0077] in, Figure 3 A schematic diagram of an authentication device that can be applied to one embodiment of this specification is shown. Please refer to... Figure 3 The authentication device shown in the figure can be implemented as all or part of an electronic device through software, hardware, or a combination of both, or it can be integrated into an electronic device as an independent module.

[0078] The authentication device 300 described in the embodiments of this specification includes: an acquisition module 310, a playback and reception module 320, a first determination module 330, and a second determination module 340.

[0079] The acquisition module 310 is used to acquire a recognition model for recognizing preset keywords from the server and store it locally; wherein the recognition model is trained based on an audio training set, which includes several audio recordings containing the preset keywords; the playback and reception module 320 is used to play the locally stored authentication question after detecting a preset trigger operation, and receive the user's voice information when answering the authentication question; the first determination module 330 is used to recognize the voice information through the recognition model and determine the user's answer to the authentication question; the second determination module 340 is used to determine whether the authentication is successful based on the user's answer to the authentication question and the pre-stored standard answer to the authentication question; wherein the standard answer to the authentication question is the preset keyword.

[0080] In an exemplary embodiment, based on the foregoing scheme, refer to... Figure 4 The first determining module 330 includes: a feature extraction module 3301, a recognition result determining module 3302, and an answer determining module 3303. Specifically, the feature extraction module 3301 is used to extract the aforementioned speech information by truncating it to a preset speech segment duration and extracting the speech features from the truncated speech segment information; the recognition result determining module 3302 is used to input the aforementioned speech features into the aforementioned recognition model to obtain the recognition result for the aforementioned speech segment information; and the answer determining module 3303 is used to determine the user's answer to the aforementioned authentication question based on the aforementioned recognition result.

[0081] In an exemplary embodiment, based on the foregoing scheme, the feature extraction module 3301 is specifically used to extract the aforementioned speech information by a preset speech segment duration, and extract the speech features of the extracted speech segment information until it is determined that at least two consecutive speech segment information have the same recognition result, at which point the extraction of the aforementioned speech information by the preset speech segment duration is stopped. The answer determination module 3303 is specifically used to determine the recognition results of the at least two identical speech segment information as the user's answer to the aforementioned authentication question.

[0082] In an exemplary embodiment, based on the aforementioned scheme, the duration of the aforementioned speech segment includes: a first speech segment duration and a second speech segment duration. The feature extraction module 3301 is specifically used to: extract the first speech segment information from the aforementioned speech information using the first speech segment duration, and extract several speech segment information after the first speech segment information using the second speech segment duration.

[0083] In an exemplary embodiment, based on the foregoing scheme, the authentication device 300 further includes a prompting module, which is used to: start timing from when the above-mentioned voice features are input into the above-mentioned recognition model; if the recognition model has not output a recognition result when the timing reaches a preset duration, then replay the above-mentioned locally stored authentication question and prompt the above-mentioned user to answer again.

[0084] In an exemplary embodiment, based on the aforementioned scheme, the acquisition module 310 is specifically used to: after detecting that a preset authentication page has been entered, acquire a recognition model for recognizing preset keywords from the server and transfer it to the local machine.

[0085] In an exemplary embodiment, based on the foregoing scheme, the preset keywords include keywords that represent affirmation and keywords that represent negation.

[0086] In an exemplary embodiment, based on the foregoing scheme, multiple different authentication questions are pre-stored locally. The playback and reception module 320 is specifically used to: play the multiple authentication questions sequentially according to their playback order, and receive the user's voice information when answering the multiple authentication questions, until it is determined that all of the multiple authentication questions have been played or that the user's answer to the currently played authentication question is not the standard answer; wherein, when the user's answer to the currently played authentication question is the standard answer, the next authentication question is played. The second determining module 340 is specifically used to: determine that authentication is successful when the user's answers to multiple authentication questions are all the standard answers; and determine that authentication is unsuccessful when the user's answer to any of the authentication questions is not the standard answer.

[0087] In an exemplary embodiment, based on the foregoing scheme, the playback and reception module 320 is specifically configured to: after receiving the voice information of the user answering the first authentication question, determine the user's language characteristics based on the voice information; when it is determined that it is necessary to continue playing the remaining authentication questions after the first authentication question, play the remaining authentication questions corresponding to the language characteristics.

[0088] In an exemplary embodiment, based on the foregoing scheme, the second determining module 340 is specifically used to: perform voice emotion analysis on the voice information of the user when answering the authentication question, and obtain the analysis result; and determine whether the authentication is successful based on the analysis result, the user's answer to the authentication question, and the pre-stored standard answer to the authentication question.

[0089] It should be noted that the authentication device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the authentication method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0090] Furthermore, the authentication device and authentication method embodiments provided in the above embodiments belong to the same concept. Therefore, for details not disclosed in the device embodiments of this specification, please refer to the above-described embodiments of the authentication method, which will not be repeated here.

[0091] This specification also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the methods described above.

[0092] Figure 5 This schematic diagram illustrates the structure of an electronic device according to an exemplary embodiment of this specification. Please refer to... Figure 5 As shown, the electronic device 500 includes a processor 501 and a memory 502.

[0093] In this embodiment, processor 901 is the control center of the computer system and can be a processor of a physical machine or a processor of a virtual machine. Processor 501 may include one or more processing cores, such as a 4-core processor or a 9-core processor. Processor 501 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 501 may also include a main processor and a coprocessor; the main processor is used to process data in the wake-up state, and the coprocessor is a low-power processor used to process data in the standby state.

[0094] In the embodiments described in this specification, the processor 501 is specifically used for:

[0095] The system retrieves a recognition model from the server to its local machine for identifying preset keywords. This recognition model is trained on an audio training set, which includes several audio recordings containing the preset keywords. Upon detecting a preset trigger operation, the system plays a locally stored authentication question and receives the user's voice information when answering the authentication question. The system then identifies the voice information using the recognition model to determine the user's answer to the authentication question. Based on the user's answer to the authentication question and the pre-stored standard answer to the authentication question, the system determines whether authentication is successful. The standard answer to the authentication question is the preset keyword.

[0096] Furthermore, the process of identifying the voice information using the aforementioned recognition model and determining the user's answer to the authentication question includes: extracting the voice information by a preset voice segment duration and extracting the voice features of the extracted voice segment information; inputting the voice features into the aforementioned recognition model to obtain the recognition result of the voice segment information; and determining the user's answer to the authentication question based on the recognition result.

[0097] Furthermore, the above-mentioned process of extracting the speech information by truncating the speech information for a preset speech segment duration and extracting the speech features of the truncated speech segment information includes: extracting the speech information by truncating the speech information for a preset speech segment duration and extracting the speech features of the truncated speech segment information until it is determined that at least two consecutive speech segments have the same recognition result, at which point the extraction of the speech information by truncating the speech information for the preset speech segment duration is stopped; the above-mentioned process of determining the user's answer to the authentication question based on the recognition result includes: determining the recognition results of the at least two identical speech segments as the user's answer to the authentication question.

[0098] Furthermore, the duration of the aforementioned audio segment includes: the duration of a first audio segment and the duration of a second audio segment, wherein the duration of the first audio segment is longer than the duration of the second audio segment, and the aforementioned audio information is extracted with a preset duration, which includes: extracting the first audio segment information from the aforementioned audio information with the duration of the first audio segment, and extracting several audio segments information after the first audio segment information with the duration of the second audio segment.

[0099] Furthermore, the processor 501 is also used to start timing from the time the above-mentioned voice features are input into the above-mentioned recognition model. If the above-mentioned recognition model has not output the recognition result when the timing reaches the preset time, the above-mentioned locally stored authentication question is replayed and the above-mentioned user is prompted to answer again.

[0100] Furthermore, the above-mentioned method of obtaining the recognition model for identifying preset keywords from the server to the local machine includes: after detecting that the preset authentication page has been entered, obtaining the recognition model for identifying preset keywords from the server to the local machine.

[0101] Furthermore, the aforementioned preset keywords include keywords that represent affirmation and keywords that represent negation.

[0102] Furthermore, the aforementioned local storage contains multiple different authentication questions. Playing the locally stored authentication questions includes: sequentially playing the multiple authentication questions according to their playback order, and receiving voice information from the user when answering the multiple authentication questions, until it is determined that all of the authentication questions have been played or that the user's answer to the currently played authentication question is not the standard answer; wherein, when the user's answer to the currently played authentication question is the standard answer, the next authentication question is played; determining authentication success based on the user's answer to the authentication question and the pre-stored standard answers to the authentication questions includes: determining authentication success when the user's answers to multiple authentication questions are all the standard answers; and determining authentication failure when the user's answer to any of the authentication questions is not the standard answer.

[0103] Furthermore, the above-mentioned authentication questions are played sequentially according to their playback order, and voice information of the user answering the authentication questions is received, including: after receiving the voice information of the user answering the first authentication question, determining the user's language characteristics based on the voice information; when it is determined that the remaining authentication questions after the first authentication question need to be played, playing the remaining authentication questions corresponding to the language characteristics.

[0104] Furthermore, the process of determining whether authentication is successful based on the user's answers to the authentication questions and the pre-stored standard answers to the authentication questions includes: performing voice emotion analysis on the user's voice information when answering the authentication questions to obtain analysis results; and determining whether authentication is successful based on the analysis results, the user's answers to the authentication questions, and the pre-stored standard answers to the authentication questions.

[0105] Memory 502 may include one or more computer-readable storage media, which may be non-transitory. Memory 502 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments of this specification, the non-transitory computer-readable storage media in memory 502 is used to store at least one instruction for execution by processor 501 to implement the methods in the embodiments of this specification.

[0106] In some embodiments, the electronic device 500 further includes a peripheral device interface 503 and at least one peripheral device. The processor 501, memory 502, and peripheral device interface 503 are connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 503 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of a display screen 504, a camera 505, and an audio circuit 506.

[0107] Peripheral interface 503 can be used to connect at least one input / output (I / O) related peripheral device to processor 501 and memory 502. In some embodiments of this specification, processor 501, memory 502, and peripheral interface 503 are integrated on the same chip or circuit board; in other embodiments of this specification, any one or two of processor 501, memory 502, and peripheral interface 503 can be implemented on separate chips or circuit boards. This specification does not specifically limit the embodiments in this regard.

[0108] Display screen 504 is used to display a user interface (UI). The UI may include graphics, text, icons, videos, and any combination thereof. When display screen 504 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 501 for processing. In this case, display screen 504 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments of this specification, there may be one display screen 504, which serves as the front panel of the electronic device 500; in other embodiments, there may be at least two display screens 504, respectively disposed on different surfaces of the electronic device 500 or in a folded design; in still other embodiments, display screen 504 may be a flexible display screen, disposed on a curved or folded surface of the electronic device 500. Furthermore, display screen 504 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 904 may be made of materials such as Liquid Crystal Display (LCD) or Organic Light-Emitting Diode (OLED).

[0109] Camera 505 is used to capture images or videos. Optionally, camera 505 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the electronic device, and the rear-facing camera is located on the back of the electronic device. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, virtual reality (VR) shooting, or other fusion shooting functions. In some embodiments of this specification, camera 505 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cool light flash, which can be used for light compensation at different color temperatures.

[0110] The audio circuit 506 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals that are input to the processor 501 for processing. For stereo sound acquisition or noise reduction purposes, there may be multiple microphones, each located in a different part of the electronic device 500. The microphone may also be an array microphone or an omnidirectional microphone.

[0111] Power supply 507 is used to supply power to the various components in electronic device 500. Power supply 507 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 507 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0112] The block diagrams of electronic devices shown in the embodiments of this specification do not constitute a limitation on the electronic device 500. The electronic device 500 may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0113] In the description of this specification, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of these terms in this specification based on the specific circumstances. Furthermore, in the description of this specification, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0114] This specification also provides a computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform one or more steps in the above embodiments. If the constituent modules of the above-described authentication device are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium.

[0115] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The aforementioned available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)).

[0116] It should be noted that the above description describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims may be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0117] The above description is merely a specific embodiment of this specification, but the scope of protection of this specification is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this specification should be included within the scope of protection of this specification. Therefore, equivalent variations made in accordance with the claims of this specification are still within the scope of this specification.

Claims

1. An authentication method, wherein, The method includes: Obtain the recognition model for identifying preset keywords from the server to the local machine; wherein, the recognition model is trained based on an audio training set, and the audio training set includes several audio recordings containing the preset keywords; After detecting a preset trigger operation, the locally stored authentication question is played, and the voice information of the user answering the authentication question is received; The speech information is extracted by a preset speech segment duration, and the speech features of the extracted speech segment information are extracted. The speech features are input into the recognition model to obtain the recognition result of the speech segment information. The extraction of the speech information by the preset speech segment duration is stopped when it is determined that there are at least two consecutive speech segments with the same recognition result. The identification results of the at least two identical speech segments are determined as the user's answer to the authentication question; The authentication is determined based on the user's answer to the authentication question and the pre-stored standard answer to the authentication question; wherein, the standard answer to the authentication question is the preset keyword.

2. The method according to claim 1, wherein, The duration of the audio segment includes: a first audio segment duration and a second audio segment duration, wherein the first audio segment duration is longer than the second audio segment duration, and the step of extracting the audio information with a preset audio segment duration includes: The first audio segment is extracted from the audio information based on the duration of the first audio segment, and several audio segments following the first audio segment are extracted based on the duration of the second audio segment.

3. The method according to claim 1, wherein, The method further includes: The timing starts when the voice features are input into the recognition model. If the recognition model has not output a recognition result when the preset time has elapsed, the locally stored authentication question is replayed, and the user is prompted to answer again.

4. The method according to claim 1, wherein, The step of obtaining the recognition model for identifying preset keywords from the server to the local machine includes: After detecting that the user has entered the preset authentication page, the system retrieves the recognition model used to identify preset keywords from the server and stores it locally.

5. The method according to claim 1, wherein, The preset keywords include keywords that represent affirmation and keywords that represent negation.

6. The method according to claim 1, wherein, The local storage contains multiple different authentication questions, and playing the locally stored authentication questions includes: According to the playback order of the multiple authentication questions, the multiple authentication questions are played sequentially, and the voice information of the user answering the multiple authentication questions is received until it is determined that all the multiple authentication questions have been played or it is determined that the user's answer to the currently played authentication question is not the standard answer; wherein, when the user's answer to the currently played authentication question is the standard answer, the next authentication question is played; The step of determining authentication success based on the user's answer to the authentication question and the pre-stored standard answers to the authentication question includes: When the user answers all of the authentication questions to the standard answers, the authentication is deemed successful. If the user's answer to any of the authentication questions is not the standard answer, the authentication is deemed to have failed.

7. The method according to claim 6, wherein, The step of playing multiple authentication questions sequentially according to their playback order, and receiving voice information from the user when answering the multiple authentication questions, includes: After receiving the user's voice information when answering the first authentication question, the user's language characteristics are determined based on the voice information; When it is determined that it is necessary to continue playing the remaining authentication questions after the first authentication question, the remaining authentication questions corresponding to the language features are played.

8. The method according to any one of claims 1 to 7, wherein, The step of determining whether authentication is successful based on the user's answer to the authentication question and the pre-stored standard answers to the authentication question includes: Voice sentiment analysis is performed on the user's voice information when answering the authentication question to obtain the analysis results; Based on the analysis results, the user's answer to the authentication question, and the pre-stored standard answer to the authentication question, it is determined whether the authentication is successful.

9. An authentication device, wherein, The device includes: The acquisition module is used to acquire a recognition model for recognizing preset keywords from the server to the local machine; wherein, the recognition model is trained based on an audio training set, and the audio training set includes several audio files containing the preset keywords; The playback and reception module is used to play the locally stored authentication questions after detecting a preset trigger operation, and to receive the voice information of the user when answering the authentication questions; The first determining module is used to extract the voice information by a preset voice segment duration, extract the voice features of the extracted voice segment information, input the voice features into the recognition model, and obtain the recognition result of the voice segment information until it is determined that there are at least two consecutive voice segment information with the same recognition result, and then stop extracting the voice information by the preset voice segment duration; the recognition results of the at least two identical voice segment information are determined as the user's answer to the authentication question; The second determining module is used to determine whether the authentication is successful based on the user's answer to the authentication question and the pre-stored standard answer to the authentication question; wherein the standard answer to the authentication question is the preset keyword.

10. A computer-readable storage medium storing a computer program that, when executed, implements the method as claimed in any one of claims 1 to 8.

11. An electronic device, wherein, The electronic device includes: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the electronic device to perform the method as described in any one of claims 1 to 8.

12. A computer program product comprising instructions that, when run on a computer or processor, cause the computer or processor to perform the method as described in any one of claims 1 to 8.

Images