Model correction method and device, electronic equipment and storage medium

By using the code scanning model and the code detection network in electronic devices, identifying the user's tapping operation and adjusting parameters, the problem of cumbersome payment operations and insufficient adaptability of electronic devices is solved, and personalized adaptability is achieved Package and convenient payment.

CN119067649APending Publication Date: 2024-12-03GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310642696.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-31
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

When scanning code payment, existing electronic devices have cumbersome operation process and poor convenience. The general model does not have enough adaptability to individuals, making it difficult to achieve personalized customization.

Method used

By using the tap-scan code model in electronic devices, using the tap-scan network to identify the user's tap operation, determine the interface relationship, and adjust the network parameters based on the sample data to obtain the corrected model to achieve implicit personalized adaptation Package and convenient payment.

Benefits of technology

With no user's sense, the personalized adaptation of the model and the convenience of scanning the code to pay is improved, the missed identification and misidentification are reduced, and the smoothness of the payment process is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067649A_ABST
    Figure CN119067649A_ABST
Patent Text Reader

Abstract

The invention discloses a model correction method and device, electronic equipment and a storage medium. If knock operation acting on the electronic equipment is recognized through a knock detection network included in the knock code scanning model, knock data corresponding to the knock operation is determined, an interface displayed by the electronic equipment in response to the knock operation is determined, an interface relation between the displayed interface and a target interface is determined, and the interface relation comprises matching or mismatching; the target interface is used for indicating the electronic equipment to execute code scanning payment, determining the tapping data as sample data based on the interface relationship, the sample data including positive sample data or negative sample data, and performing parameter adjustment on the tapping detection network based on the sample data to obtain a corrected tapping code scanning model. The positive sample data or the negative sample data are obtained in the payment and use process of the electronic equipment to carry out parameter adjustment on the knock detection network, implicit correction can be realized, and the personalized adaptation of the model and the convenience of code scanning payment are improved under the condition that a user is non-inductive.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of electronic devices, and more specifically, to a model correction method, device, electronic device and storage medium. Background Art

[0002] With the development of science and technology, electronic devices are used more and more widely and have more and more functions. They have become one of the necessities in people's daily life. At present, electronic devices can be used for scanning code payment. However, when scanning code payment is needed through electronic devices, it is necessary to first enter the desktop of the electronic device, click the icon of the payment application to enter the payment application, and then scan the code to pay through the payment application. The operation process is cumbersome and inconvenient. Summary of the invention

[0003] In view of the above problems, the present application proposes a model correction method, device, electronic device and storage medium to solve the above problems.

[0004] In a first aspect, an embodiment of the present application provides a model correction method, which is applied to an electronic device, and the method includes: if a tapping operation acting on the electronic device is identified by a tapping detection network included in the tapping and scanning code model, then determining the tapping data corresponding to the tapping operation, and determining the interface displayed by the electronic device in response to the tapping operation; determining an interface relationship between the displayed interface and a target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform a scan code payment; based on the interface relationship, determining the tapping data as sample data, wherein the sample data includes positive sample data or negative sample data; and adjusting the parameters of the tapping detection network based on the sample data to obtain a corrected tapping and scanning code model.

[0005] In a second aspect, an embodiment of the present application provides a model correction device, which is applied to an electronic device, and the device includes: an interface determination module, which is used to determine the tapping data corresponding to the tapping operation and determine the interface displayed by the electronic device in response to the tapping operation if a tapping operation acting on the electronic device is identified through a tapping detection network included in the tapping and scanning model; an interface relationship determination module, which is used to determine the interface relationship between the displayed interface and the target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform a scan code payment; a sample data determination module, which is used to determine the tapping data as sample data based on the interface relationship, wherein the sample data includes positive sample data or negative sample data; a model correction module, which is used to adjust the parameters of the tapping detection network based on the sample data to obtain a corrected tapping and scanning model.

[0006] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory is coupled to the processor, the memory stores instructions, and when the instructions are executed by the processor, the processor executes the above method.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a program code is stored, and the program code can be called by a processor to execute the above method.

[0008] The model correction method, device, electronic device and storage medium provided in the embodiments of the present application, if a tapping operation acting on an electronic device is identified by the tapping detection network included in the tapping scanning model, then the tapping data corresponding to the tapping operation is determined, and the interface displayed by the electronic device in response to the tapping operation is determined, and the interface relationship between the displayed interface and the target interface is determined, and the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform a scan code payment. Based on the interface relationship, the tapping data is determined as sample data, and the sample data includes positive sample data or negative sample data. Based on the sample data, the parameters of the tapping detection network are adjusted to obtain a corrected tapping scanning model, so that implicit correction can be achieved by obtaining positive sample data or negative sample data during the payment use of the electronic device and adjusting the parameters of the tapping detection network, thereby improving the personalized adaptation of the model and the convenience of scan code payment without the user noticing. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a flow chart of a method for calibrating a model provided in an embodiment of the present application is shown;

[0011] Figure 2 A schematic diagram of a flow chart of a method for calibrating a model provided in an embodiment of the present application is shown;

[0012] Figure 3 A schematic diagram of a flow chart of a method for calibrating a model provided in an embodiment of the present application is shown;

[0013] Figure 4 This application shows Figure 3 A schematic flow chart of step S330 of the model correction method shown;

[0014] Figure 5A schematic diagram of a flow chart of a method for calibrating a model provided in an embodiment of the present application is shown;

[0015] Figure 6 This application shows Figure 5 A schematic flow chart of step S430 of the model correction method shown;

[0016] Figure 7 A schematic diagram of a flow chart of a method for calibrating a model provided in an embodiment of the present application is shown;

[0017] Figure 8 A module block diagram of a model correction device provided by an embodiment of the present application is shown;

[0018] Fig. 9 A block diagram of an electronic device according to an embodiment of the present application for executing a correction method of a model according to an embodiment of the present application is shown;

[0019] Fig.10 A storage unit for storing or carrying program codes for implementing a correction method for a model according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0021] Among them, when it is necessary to scan the code to pay through an electronic device, it is necessary to first enter the desktop of the electronic device, click the icon of the payment application to enter the payment application, and then scan the code to pay through the payment application. The operation process is cumbersome and inconvenient. After research, the inventor found that the operation process can be simplified by tapping to scan the code and the convenience of payment can be improved.

[0022] Among them, tapping code scanning refers to the user scanning a QR code through an electronic device or the user displaying a QR code through an electronic device and being scanned by a code scanning device. The user can tap (such as quickly double-clicking) the back or side of the electronic device to achieve the function of tapping code scanning. Among them, tapping code scanning can be achieved through a tapping code scanning model. The tapping code scanning model can include two sub-networks (algorithms), namely a tapping detection network and a QR code detection network. The tapping code scanning model is obtained based on a deep learning neural network algorithm. It is inevitable that there will be missed recognition (originally there was a tapping operation, but it was not recognized as a tapping operation by the tapping code scanning model) and misrecognition (originally there was no tapping operation, but it was recognized as a tapping operation by the tapping code scanning model). How to reduce missed recognition and misrecognition is an important issue.

[0023] In addition, in the field of artificial intelligence algorithms, the adaptability of general models to individuals is also a meaningful topic. Current artificial intelligence models are basically general models. Taking the tapping detection network in the tapping code scanning model as an example, the tapping detection network is obtained by collecting a large amount of tapping data from objects of different ages and genders for training. However, despite this, each person has different hand habits. For example, Zhang San likes to tap the middle of the back shell of the electronic device with his fingertips, and Li Si likes to tap the upper left corner of the electronic device with his fingernails. Therefore, if the tapping detection network and the tapping code scanning model can be customized according to the personal habits of each user, better results will be achieved.

[0024] It is understandable that it is difficult to customize the model for each user. However, for each user, the parameters of the tap detection network in the tap scanning model can be fine-tuned to adapt to different users. For example, the tap detection network is a neural network composed of 5 convolutional layers and 3 fully connected layers. When fine-tuning the tap detection network, all convolutional layers and the first two fully connected layers can be fixed, and then the parameters of the last fully connected layer can be changed to achieve fine-tuning of the tap detection network. Among them, fine-tuning requires sample data. One method is to spend a few minutes to collect their own tapping data before each user turns on this function for the first time, for example, 10 times, and then send these 10 data to the tap detection network in the tap scanning model for fine-tuning. However, this method will be executed when the user is aware of it, which requires the user to spend extra time.

[0025] In response to the above problems, the inventors have discovered after long-term research and proposed the correction method, device, electronic device and storage medium of the model provided in the embodiments of this application. By obtaining positive sample data or negative sample data during the payment process of the electronic device to adjust the parameters of the tap detection network, implicit correction can be achieved, and the personalized adaptation of the model and the convenience of scanning code payment can be improved without the user noticing. Among them, the specific model correction method is described in detail in the subsequent embodiments.

[0026] See also Figure 1 , Figure 1 The flowchart of the correction method of the model provided by an embodiment of the present application is shown. The method is used to adjust the parameters of the tap detection network by obtaining positive sample data or negative sample data during the payment process of the electronic device, which can achieve implicit correction and improve the personalized adaptation of the model and the convenience of scanning code payment without the user noticing. In a specific embodiment, the correction method of the model is applied to Figure 8 The calibration device 200 of the model shown and the electronic device 100 ( Fig. 9). The following will take an electronic device as an example to illustrate the specific process of this embodiment. Of course, it can be understood that the electronic device used in this embodiment may include a smart phone, a tablet computer, etc., which is not limited here. Figure 1 The process shown is described in detail, and the correction method of the model can specifically include the following steps:

[0027] Step S110: If a tapping operation acting on the electronic device is identified by the tapping detection network included in the tapping code scanning model, the tapping data corresponding to the tapping operation is determined, and the interface displayed by the electronic device in response to the tapping operation is determined.

[0028] Optionally, a tapping code scanning model can be pre-trained, and the tapping code scanning model can be used to trigger the electronic device to scan the code for payment according to the tapping operation on the electronic device. The tapping code scanning model may include a tapping detection network, and the tapping detection network can be used to detect the tapping operation on the electronic device. As one way, the tapping code scanning model can be pre-trained and stored locally in the electronic device. Accordingly, the tapping code scanning can be detected and identified directly locally in the electronic device through the tapping code scanning model. As another way, the tapping code scanning model can be pre-trained and stored in a server that is communicatively connected to the electronic device. Accordingly, the tapping code scanning can be detected and identified based on the connection between the electronic device and the server through the tapping code scanning model.

[0029] In this embodiment, the tapping detection network included in the tapping code scanning model can be used to identify whether there is a tapping operation on the electronic device (such as a double-click operation on the back shell or side of the electronic device). If the tapping detection network included in the tapping code scanning model identifies a tapping operation on the electronic device, the tapping data corresponding to the tapping operation can be determined, and the interface displayed by the electronic device in response to the tapping operation can be determined. If the tapping detection network included in the tapping code scanning model does not identify a tapping operation on the electronic device, no response may be made or other operations may be performed.

[0030] In some embodiments, a touch operation acting on an electronic device can be detected, and when a touch operation acting on an electronic device is detected, touch data corresponding to the touch operation is obtained, and the touch data is input into a tap detection network included in the tapping code scanning model to instruct the tap detection network to determine whether the touch operation is a tap operation (such as a double-click operation) acting on the electronic device based on the touch data. If the tap detection network determines that the touch operation is a tap operation acting on the electronic device based on the touch data, the tap data corresponding to the tap operation can be determined, and the interface displayed by the electronic device in response to the tap operation can be determined.

[0031] It is understandable that if a tapping operation on an electronic device is identified by the tapping detection network included in the tapping code scanning model, it can be considered that the tapping detection network may accurately identify the tapping operation on the electronic device, or may misidentify the tapping operation on the electronic device. Based on this, it can be determined that the tapping data corresponding to the identified tapping operation participates in the subsequent parameter adjustment of the tapping detection network, and that the page displayed by the electronic device in response to the tapping operation makes an accuracy judgment on the recognition result of the tapping detection network.

[0032] As an implementable manner, the tapping data corresponding to the tapping operation may include: the tapping position corresponding to the tapping operation, the number of tapping times corresponding to the tapping operation, the tapping sound corresponding to the tapping operation, the tapping interval corresponding to the tapping operation, and the tapping force corresponding to the tapping operation, or a combination of the above.

[0033] As an implementable method, determining the interface displayed by the electronic device in response to a tapping operation may include: determining the current interface displayed by the electronic device in response to a tapping operation, or determining the current interface displayed by the electronic device in response to a tapping operation and N interfaces after the current interface, where N is an integer greater than or equal to 1.

[0034] Step S120: Determine an interface relationship between the displayed interface and a target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform a scan code payment.

[0035] In some embodiments, the electronic device may be pre-set and store a target interface, and the target interface is used as a basis for determining the interface displayed by the electronic device in response to the tapping operation. Therefore, in this embodiment, when determining the interface displayed by the electronic device in response to the tapping operation, the displayed interface may be compared with the target interface to determine the interface relationship between the displayed interface and the target interface.

[0036] Optionally, the interface relationship between the displayed interface and the target interface may include: the interface relationship between the displayed interface and the target interface matches. The interface relationship between the displayed interface and the target interface matches, including: the content of the displayed interface matches, the layout of the displayed interface matches, etc., which are not limited here.

[0037] Optionally, the interface relationship between the displayed interface and the target interface may include: the interface relationship between the displayed interface and the target interface does not match. Wherein, the interface relationship between the displayed interface and the target interface does not match: the content of the displayed interface and the target interface does not match, the layout does not match, etc., which is not limited here.

[0038] In some embodiments, the target interface is used to instruct the electronic device to perform scan code payment. For example, the target interface may include a payment interface for instructing the electronic device to perform scan code payment; the target interface may include a payment password input interface for instructing the electronic device to perform scan code payment; the target interface may include a payment success interface for instructing the electronic device to perform scan code payment; the target interface may include a payment failure interface for instructing the electronic device to perform scan code payment, etc., which are not limited here.

[0039] Step S130: Based on the interface relationship, determine the tapping data as sample data, wherein the sample data includes positive sample data or negative sample data.

[0040] In this embodiment, when the interface relationship between the displayed interface and the target interface is determined, the tapping data can be determined as sample data based on the interface relationship. The sample data includes positive sample data or negative sample data. That is, when the interface relationship between the displayed interface and the target interface is determined, the tapping data can be determined as positive sample data based on the interface relationship, or the tapping data can be determined as negative sample data.

[0041] In some embodiments, if it is determined based on the interface relationship that the displayed interface does not match the target interface, the tapping data can be determined as negative sample data, or, if it is determined based on the interface relationship that the displayed interface matches the target interface, the tapping data can be determined as positive sample data. It can be understood that if it is determined based on the interface relationship that the displayed interface does not match the target interface, it can be determined that the interface displayed by the electronic device in response to the tapping operation has nothing to do with the execution of the scan code payment, and it can be considered that the tapping detection network has mistakenly detected the tapping operation for indicating the scan code payment, and the tapping data corresponding to the mistakenly detected tapping operation can be determined as negative sample data; if it is determined based on the interface relationship that the displayed interface matches the target interface, it can be determined that the interface displayed by the electronic device in response to the tapping operation is related to the execution of the scan code payment, and it can be considered that the tapping detection network has accurately detected the tapping operation for indicating the scan code payment, and the tapping data corresponding to the accurately detected tapping operation can be determined as positive sample data.

[0042] Step S140: adjusting the parameters of the tap detection network based on the sample data to obtain a calibrated tap scanning model.

[0043] In this embodiment, when the tap data is determined as sample data, the tap detection network can be adjusted based on the sample data to obtain a calibrated tap detection network and a calibrated tap scanning model to adapt to the user's usage habits and realize the user's implicit personalized customization.

[0044] As an implementable method, the tap detection network can be composed of 5 convolutional layers and 3 fully connected layers. Then, when the tap data is determined as sample data, the 5 convolutional layers and the first 2 fully connected layers can be fixed, and the parameters of the last fully connected layer can be changed based on the sample data to obtain the corrected tap detection network and the corrected tap scanning model.

[0045] A correction method for a model provided in an embodiment of the present application, if a tapping operation acting on an electronic device is identified through a tapping detection network included in a tapping code scanning model, then the tapping data corresponding to the tapping operation is determined, and the interface displayed by the electronic device in response to the tapping operation is determined, and the interface relationship between the displayed interface and the target interface is determined, the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform a code scanning payment. Based on the interface relationship, the tapping data is determined as sample data, and the sample data includes positive sample data or negative sample data. Based on the sample data, the parameters of the tapping detection network are adjusted to obtain a corrected tapping code scanning model, so that implicit correction can be achieved by obtaining positive sample data or negative sample data during the payment use of the electronic device and adjusting the parameters of the tapping detection network, thereby improving the personalized adaptation of the model and the convenience of code scanning payment without the user noticing.

[0046] See also Figure 2 , Figure 2 The flow chart of the calibration method of the model provided by an embodiment of the present application is shown. The method is applied to electronic equipment. Figure 2 The process shown is described in detail, and the correction method of the model can specifically include the following steps:

[0047] Step S210: If a tapping operation acting on the electronic device is identified by the tapping detection network included in the tapping code scanning model, the tapping data corresponding to the tapping operation is determined, and the interface displayed by the electronic device in response to the tapping operation is determined.

[0048] Step S220: Determine the interface relationship between the displayed interface and the target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform scan code payment.

[0049] Step S230: Based on the interface relationship, determine the tapping data as sample data, wherein the sample data includes positive sample data or negative sample data.

[0050] For the detailed description of step S210 to step S230 , please refer to step S110 to step S130 , which will not be repeated here.

[0051] Step S240: storing the sample data in the electronic device.

[0052] In this embodiment, when the tapping data is determined as sample data, the sample data may be stored locally in the electronic device.

[0053] As a method, the storage space of the electronic device can be divided into a storage area, and the storage area is used to store the sample data. Therefore, when the tapping data is determined as the sample data, the sample data can be stored in the storage area.

[0054] Step S250: If the positive sample data and the negative sample data stored in the electronic device meet the preset conditions, the parameters of the tap detection network are adjusted based on the stored positive sample data and the negative sample data to obtain a calibrated tap scanning model.

[0055] In some embodiments, the electronic device may be pre-set and store preset conditions, which are used as a basis for judging the sample data (positive sample data and negative sample data) stored in the electronic device. Therefore, in this embodiment, each time the tapping data is determined as sample data and stored in the electronic device, the sample data (positive sample data and negative sample data) stored in the electronic device may be detected (i.e., the sample data stored by the electronic device before this time and the sample data stored this time are detected) to determine whether the positive sample data and negative sample data stored in the electronic device meet the preset conditions.

[0056] Among them, if it is determined that the stored positive sample data and negative sample data meet the preset conditions, the parameters of the tap detection network can be adjusted based on the stored positive sample data and negative sample data to obtain a corrected tap detection network and a corrected tap scanning model.

[0057] Among them, if it is determined that the stored positive sample data and negative sample data do not meet the preset conditions, the storage of the positive sample data and the negative sample data can be maintained, and the acquisition of sample data can continue, and the acquired sample data can be stored in the electronic device until the stored positive sample data and the negative sample data meet the preset conditions. The parameters of the tap detection network can be adjusted based on the stored positive sample data and the negative sample data to obtain a corrected tap detection network and a corrected tap scanning model.

[0058] In some embodiments, the number of positive sample data stored in the electronic device can be determined, and the number of negative sample data stored in the electronic device can be determined. If the number of positive sample data stored in the electronic device reaches a quantity threshold, and the number of negative sample data stored in the electronic device reaches a quantity threshold, it can be determined that the positive sample data and the negative sample data stored in the electronic device meet the preset conditions. As an implementable method, if the number of positive sample data stored in the electronic device reaches 5, and the number of negative sample data stored in the electronic device reaches 5, the parameters of the tap detection network can be adjusted based on the 5 positive sample data and the 5 negative sample data to obtain a corrected tap detection network and a corrected tap scanning model.

[0059] The calibration method of the model provided in one embodiment of the present application is compared with Figure 1 The correction method of the model shown in the embodiment also stores the determined sample data in the electronic device, and when the positive sample data and the negative sample data stored in the electronic device meet the preset conditions, the parameters of the tap detection network are adjusted based on the positive sample data and the negative sample data stored in the electronic device to realize the correction of the tap scanning model, so that the accuracy of the parameter adjustment can be improved by fine-tuning by involving multiple positive and negative sample data.

[0060] See also Figure 3 , Figure 3 The flow chart of the calibration method of the model provided in one embodiment of the present application is shown. The method is applied to the above electronic device. Figure 3 The process shown is described in detail, and the correction method of the model can specifically include the following steps:

[0061] Step S310: If a tapping operation acting on the electronic device is identified by the tapping detection network included in the tapping code scanning model, the tapping data corresponding to the tapping operation is determined.

[0062] The specific description of step S310 can be found in step S110 , which will not be repeated here.

[0063] Step S320: Turn on the camera of the electronic device and collect images through the camera.

[0064] Optionally, the scan code payment can be that the electronic device scans the QR code through the camera to make payment. For example, the electronic device can scan the first QR code of the merchant through the camera to make payment.

[0065] Optionally, the tapping code scanning model may include a tapping detection network and a QR code detection network, wherein the tapping detection network can be used to detect a tapping operation acting on the electronic device, and the QR code detection network can be used to detect whether an image of a QR code is captured.

[0066] In this embodiment, if the tapping operation acting on the electronic device is recognized by the tapping detection network in the tapping and scanning model, it can be considered that the electronic device expects to pay by scanning the QR code through the camera. Therefore, the camera of the electronic device can be turned on and image acquisition can be performed through the camera of the electronic device.

[0067] Step S330: If an image including a first QR code is captured by the camera, it is determined that the displayed interface is a first interface, wherein the first interface matches the target interface.

[0068] It is understandable that after users form behavioral habits, generally speaking, they will only tap the electronic device when they need to scan the code to pay (such as double-clicking the back cover or side of the electronic device in the figure). Therefore, if the tap detection network detects the tapping operation on the electronic device, and the QR code detection network recognizes that the camera has captured an image including the QR code, it can be determined that the tapping operation on the electronic device identified by the tap detection network is accurate, that is, the user really tapped the electronic device, and the tap detection network came up with it, rather than the user did not tap the electronic device, but the tap detection network recognized that the electronic device was tapped. Therefore, the tapping data corresponding to the tapping operation can be determined as positive sample data.

[0069] In this embodiment, in the process of collecting images through the camera, it is possible to identify whether the image collected by the camera includes an image of the first QR code. If it is determined that the image including the first QR code is collected by the camera, it can be determined that the tapping operation acting on the electronic device identified by the tapping detection network is accurate, and it can be determined that the interface displayed by the electronic device is the first interface matching the target interface. Optionally, the first interface may include a payment password input interface, a payment success interface, a payment failure interface, etc., which are not limited here.

[0070] See also Figure 4 , Figure 4 This application shows Figure 3 The following is a flow chart of step S330 of the calibration method of the model shown in FIG. Figure 4 The process shown is described in detail, and the method may specifically include the following steps:

[0071] Step S331: if the image including the first two-dimensional code is captured by the camera, the first two-dimensional code is identified.

[0072] It is understandable that the first QR code captured by the camera may be a QR code related to payment, such as a merchant's payment QR code, but it may also be a QR code unrelated to payment, such as a QR code of a personal business card. Therefore, when the electronic device captures an image including the first QR code through the camera, it may be a QR code related to payment, in which case it indicates that the user wants to perform scan code payment, or it may be a QR code unrelated to payment, in which case it indicates that the user does not want to perform scan code payment, such as adding a friend.

[0073] In this embodiment, if the image including the first two-dimensional code is captured by the camera, the first two-dimensional code can be identified, that is, whether the first two-dimensional code is related to payment can be identified. As a way, when the image including the first two-dimensional code is captured by the camera, the attribute information of the first two-dimensional code can be identified to determine whether the first two-dimensional code is related to payment.

[0074] Step S332: If it is recognized that the first QR code is related to payment, the displayed interface is determined to be the first interface.

[0075] In some embodiments, if the first QR code is identified as being related to payment, it can be determined that the tapping operation on the electronic device identified by the tapping detection network is accurate, and the user indeed expects to trigger the scan code payment by tapping the electronic device, then it can be determined that the interface displayed by the electronic device is the first interface that matches the target interface.

[0076] Step S333: If it is identified that the first QR code is not related to payment, it is determined that the displayed interface is a third interface, wherein the third interface does not match the target interface.

[0077] In some embodiments, if the first QR code is not related to payment, it can be determined that the tapping operation on the electronic device identified by the tapping detection network is wrong, and the user does not expect to trigger the scan code payment by tapping the electronic device, and it can be determined that the interface displayed by the electronic device is a third interface that does not match the target interface. The third interface may include a friend adding interface.

[0078] Step S340: If the image including the first QR code is not captured by the camera, it is determined that the displayed interface is a second interface, wherein the second interface does not match the target interface.

[0079] If the tap detection network detects a tapping operation on the electronic device, but the QR code detection network recognizes that the camera has not captured an image including the QR code, it can be determined that the tapping operation on the electronic device identified by the tap detection network is inaccurate, that is, the user did not actually tap the electronic device, but only because of the limitations of the tap detection network did the operation that was not a tapping of the electronic device be mistakenly identified as a tapping of the electronic device. Therefore, the tapping data corresponding to the tapping operation can be determined as negative sample data.

[0080] In this embodiment, in the process of capturing images through the camera, it is possible to identify whether the image captured by the camera includes an image of the first QR code. If it is determined that the image including the first QR code is not captured by the camera, it can be determined that the tapping operation acting on the electronic device identified by the tapping detection network is wrong, and it can be determined that the interface displayed by the electronic device is a second interface that does not match the target interface. Optionally, the second interface may include a preview interface captured by the camera.

[0081] Optionally, the first QR code may be a payment code.

[0082] Step S350: Determine the interface relationship between the displayed interface and the target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform scan code payment.

[0083] Step S360: Based on the interface relationship, determine the tapping data as sample data, wherein the sample data includes positive sample data or negative sample data.

[0084] Step S370: Adjust the parameters of the tap detection network based on the sample data to obtain a calibrated tap scanning model.

[0085] For the detailed description of step S350 to step S370, please refer to step S120 to step S140, which will not be repeated here.

[0086] The calibration method of the model provided in one embodiment of the present application is compared with Figure 1 The correction method of the model shown in the embodiment also turns on the camera of the electronic device and collects images through the camera. If the image including the first QR code is collected through the camera and it is determined that the tapping operation is not a misrecognition, it is determined that the interface displayed by the electronic device matches the target interface. If the image including the first QR code is not collected through the camera and it is determined that the tapping operation is a misrecognition, it is determined that the interface displayed by the electronic device does not match the target interface, thereby improving the convenience of determining the sample data and improving the efficiency of model correction.

[0087] See also Figure 5 , Figure 5 The flow chart of the calibration method of the model provided in one embodiment of the present application is shown. The method is applied to the above electronic device. Figure 5 The process shown is described in detail, and the correction method of the model can specifically include the following steps:

[0088] Step S410: If a tapping operation acting on the electronic device is identified by the tapping detection network included in the tapping code scanning model, the tapping data corresponding to the tapping operation is determined.

[0089] For the detailed description of step S410, please refer to step S110, which will not be repeated here.

[0090] Step S420: Display the second QR code.

[0091] Optionally, the scan code payment may be a payment by displaying a payment QR code on the electronic device. For example, the electronic device may pay by displaying a payment QR code and being scanned by a code scanning device.

[0092] In this embodiment, if the tapping detection network in the tapping and scanning model recognizes a tapping operation on the electronic device, it can be considered that the electronic device expects to make a payment by displaying a QR code, and therefore, a second QR code can be displayed.

[0093] Step S430: If it is determined that the second QR code is scanned by a code scanning device, then it is determined that the displayed interface is a fourth interface, wherein the fourth interface matches the target interface.

[0094] It is understandable that after users form behavioral habits, generally speaking, they will only tap the electronic device when they need to scan the code to pay (such as double-clicking the back cover or side of the electronic device in the figure). Therefore, if the tapping detection network detects the tapping operation acting on the electronic device and determines that the QR code is scanned by the code scanning device, it can be determined that the tapping operation on the electronic device identified by the tapping detection network is accurate, that is, the user really tapped the electronic device and the tapping detection network came up with it, rather than the user did not tap the electronic device, but the tapping detection network identified the tapping of the electronic device. Therefore, the tapping data corresponding to the tapping operation can be determined as positive sample data.

[0095] In this embodiment, the electronic device can detect whether the second QR code is scanned by the scanning device during the process of displaying the second QR code. If it is determined that the second QR code is scanned by the scanning device, it can be determined that the tapping operation on the electronic device identified by the tapping detection network is accurate, and it can be determined that the interface displayed by the electronic device is a fourth interface that matches the target interface. Optionally, the fourth interface may include a payment success interface, a payment failure interface, etc., which are not limited here. Optionally, the scanning device may include a device that can scan and identify QR codes.

[0096] See also Figure 6 , Figure 6 This application shows Figure 5 The following is a flow chart of step S430 of the calibration method of the model shown in FIG. Figure 6 The process shown is described in detail, and the method may specifically include the following steps:

[0097] Step S431: If it is determined that the second two-dimensional code is scanned by a code scanning device, the second two-dimensional code is identified.

[0098] It is understandable that the second QR code may be a QR code related to payment, such as a user's payment QR code, but it may also be a QR code unrelated to payment, such as a QR code of a user's personal business card. Therefore, when the electronic device displays the second QR code, it may be a QR code related to payment, in which case it indicates that the user wants to perform a scan code payment, or it may be a QR code unrelated to payment, in which case it indicates that the user does not want to perform a scan code payment, such as performing a friend addition.

[0099] In this embodiment, if the second QR code is displayed, the second QR code can be identified, that is, whether the second QR code is related to payment. As a way, when the second QR code is displayed, the attribute information of the second QR code can be identified to determine whether the second QR code is related to payment.

[0100] Step S432: If it is recognized that the second QR code is related to payment, the displayed interface is determined to be the fourth interface.

[0101] In some embodiments, if the second QR code is identified as being related to payment, it can be determined that the tapping operation on the electronic device identified by the tapping detection network is accurate, and the user indeed expects to trigger the scan code payment by tapping the electronic device, then it can be determined that the interface displayed by the electronic device is a fourth interface that matches the target interface.

[0102] Step S433: If it is recognized that the second QR code is not related to payment, it is determined that the interface displayed by the operation is the sixth interface, wherein the sixth interface does not match the target interface.

[0103] In some embodiments, if the second QR code is not related to payment, it can be determined that the tapping operation on the electronic device identified by the tapping detection network is wrong, and the user does not expect to trigger the scan code payment by tapping the electronic device, and it can be determined that the interface displayed by the electronic device is a sixth interface that does not match the target interface. The sixth interface may include a friend adding success interface, a friend adding failure interface, etc.

[0104] Step S440: If it is determined that the second QR code has not been scanned by the code scanning device, it is determined that the displayed interface is the fifth interface, wherein the fifth interface does not match the target interface.

[0105] If the tap detection network detects a tapping operation on the electronic device, but the second QR code is not scanned by the code scanning device, it can be determined that the tapping operation on the electronic device identified by the tap detection network is inaccurate, that is, the user did not actually tap the electronic device, but only because of the limitations of the tap detection network, the operation was mistakenly identified as tapping the electronic device. Therefore, the tapping data corresponding to the tapping operation can be determined as negative sample data.

[0106] In this embodiment, the electronic device can detect whether the second QR code is scanned by the scanning device during the process of displaying the second QR code. If it is determined that the second QR code is not scanned, it can be determined that the tapping operation on the electronic device identified by the tapping detection network is wrong, and it can be determined that the interface displayed by the electronic device is a fifth interface that does not match the target interface. Optionally, the fifth interface can include the second QR code display interface.

[0107] Optionally, the second QR code may be a payment code.

[0108] Step S450: Determine the interface relationship between the displayed interface and the target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform scan code payment.

[0109] Step S460: Based on the interface relationship, determine the tapping data as sample data, wherein the sample data includes positive sample data or negative sample data.

[0110] Step S470: Adjust the parameters of the tap detection network based on the sample data to obtain a calibrated tap scanning model.

[0111] For the detailed description of step S450 to step S470, please refer to step S120 to step S140, which will not be repeated here.

[0112] The calibration method of the model provided in one embodiment of the present application is compared with Figure 1 The correction method of the model shown in the present embodiment also displays a second QR code. If it is determined that the second QR code has been scanned by the code scanning device and the tapping operation is not a misrecognition, then it is determined that the displayed interface matches the target interface. If it is determined that the second QR code has not been scanned by the code scanning device and the tapping operation is a misrecognition, then it is determined that the displayed interface does not match the target interface, thereby improving the convenience of sample data determination and improving the efficiency of model correction.

[0113] See also Figure 7 , Figure 7 The flow chart of the calibration method of the model provided by an embodiment of the present application is shown. The method is applied to electronic equipment. Figure 7 The process shown is described in detail, and the correction method of the model can specifically include the following steps:

[0114] Step S510: Detecting sensor data of the acceleration sensor of the electronic device within a preset time period at a preset time interval.

[0115] Optionally, the tap-to-scan function of the electronic device may be in a normally open state. In this embodiment, the sensor data of the acceleration sensor of the electronic device within a preset time period may be detected at a preset time interval. For example, the sensor data of the acceleration sensor of the electronic device within the last 1 second may be detected every 100 milliseconds.

[0116] Step S520: Input the sensor data into the tap detection network.

[0117] In this embodiment, when sensor data is obtained, the sensor data may be input into a tap detection network so as to determine whether a tap operation is performed on the electronic device based on the sensor data through the tap detection network.

[0118] It is understandable that every time a user taps the back of an electronic device once, an obvious acceleration will be generated on the z-axis of the electronic device. If it is tapped twice, two obvious accelerations will appear. Therefore, the sensor data collected by the acceleration sensor can be used to determine whether there is a tapping operation on the back of the electronic device. Every time a user taps the side of an electronic device once, an obvious acceleration will be generated on the x-axis of the electronic device. If it is tapped twice, two obvious accelerations will appear. Therefore, the sensor data collected by the acceleration sensor can be used to determine whether there is a tapping operation on the side of the electronic device.

[0119] Step S530: If a tapping operation acting on the electronic device is identified by the tapping detection network included in the tapping code scanning model, the tapping data corresponding to the tapping operation is determined, and the interface displayed by the electronic device in response to the tapping operation is determined.

[0120] Step S540: Determine the interface relationship between the displayed interface and the target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform scan code payment.

[0121] Step S550: Based on the interface relationship, determine the tapping data as sample data, wherein the sample data includes positive sample data or negative sample data.

[0122] Step S560: Adjust the parameters of the tap detection network based on the sample data to obtain a calibrated tap scanning model.

[0123] For the detailed description of step S530 to step S560, please refer to step S110 to step S140, which will not be repeated here.

[0124] The calibration method of the model provided in one embodiment of the present application is compared with Figure 1 The correction method of the model shown in the figure, this embodiment also detects the sensor data of the acceleration sensor of the electronic device within a preset time period at a preset time interval, and inputs the sensor data into the tapping detection network, so as to keep the tapping and scanning model updated in sequence and improve the detection and recognition effect of the tapping and scanning model.

[0125] See also Figure 8 , Figure 8 The module block diagram of the model correction device provided by an embodiment of the present application is shown. The model correction device 200 is applied to the above electronic device. Figure 8 The block diagram shown in the figure is used to illustrate that the model correction device 200 includes: an interface determination module 210, an interface relationship determination module 220, a sample data determination module 230 and a model correction module 240, wherein:

[0126] The interface determination module 210 is used to determine the tapping data corresponding to the tapping operation and the interface displayed by the electronic device in response to the tapping operation if a tapping operation acting on the electronic device is identified through the tapping detection network included in the tapping code scanning model.

[0127] Furthermore, the interface determination module 210 includes: an image acquisition submodule, a first interface determination submodule and a second interface determination submodule, wherein:

[0128] The image acquisition submodule is used to turn on the camera of the electronic device and acquire images through the camera.

[0129] The first interface determination submodule is used to determine that the displayed interface is the first interface if an image including a first QR code is captured by the camera, wherein the first interface matches the target interface.

[0130] Furthermore, the first interface determination submodule includes: a first QR code recognition unit, a first interface determination unit and a second interface determination unit, wherein:

[0131] The first two-dimensional code recognition unit is used to recognize the first two-dimensional code if an image including the first two-dimensional code is captured by the camera.

[0132] The first interface determination unit is used to determine that the displayed interface is the first interface if it is recognized that the first QR code is related to payment.

[0133] The second interface determination unit is used to determine that the displayed interface is a third interface if it is recognized that the first QR code is not related to payment, wherein the third interface does not match the target interface.

[0134] The second interface determination submodule is used to determine that the displayed interface is a second interface if the image including the first QR code is not captured by the camera, wherein the second interface does not match the target interface.

[0135] Furthermore, the interface determination module 210 includes: a QR code display submodule, a fourth interface determination submodule and a fifth interface determination submodule, wherein:

[0136] The two-dimensional code display submodule is used to display the second two-dimensional code.

[0137] The fourth interface determination submodule is used to determine that the displayed interface is a fourth interface if it is determined that the second QR code is scanned by a code scanning device, wherein the fourth interface matches the target interface.

[0138] Furthermore, the fourth interface determination submodule includes:

[0139] The second two-dimensional code recognition unit is used to recognize the second two-dimensional code if it is determined that the second two-dimensional code is scanned by a code scanning device.

[0140] The fourth interface determination unit is used to determine that the displayed interface is the fourth interface if it is recognized that the second QR code is related to payment.

[0141] The sixth interface determination unit is used to determine that the interface displayed by the operation is the sixth interface if it is recognized that the second QR code is not related to payment, wherein the sixth interface does not match the target interface.

[0142] The fifth interface determination submodule is used to determine that the displayed interface is the fifth interface if it is determined that the second QR code has not been scanned by the code scanning device, wherein the fifth interface does not match the target interface.

[0143] The interface relationship determination module 220 is used to determine the interface relationship between the displayed interface and the target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform scan code payment.

[0144] The sample data determination module 230 is used to determine the tapping data as sample data based on the interface relationship, wherein the sample data includes positive sample data or negative sample data.

[0145] Furthermore, the sample data determination module 230 includes: a negative sample data determination submodule and a positive sample data determination submodule, wherein:

[0146] The negative sample data determination submodule is used to determine the tap data as negative sample data if it is determined based on the interface relationship that the displayed interface does not match the target interface.

[0147] The positive sample data determination submodule is used to determine the tapping data as positive sample data if it is determined based on the interface relationship that the displayed interface matches the target interface.

[0148] The model correction module 240 is used to adjust the parameters of the tap detection network based on the sample data to obtain a corrected tap scanning model.

[0149] Furthermore, the model correction module 240 includes: a sample data storage submodule and a model correction submodule, wherein:

[0150] The sample data storage submodule is used to store the sample data in the electronic device.

[0151] The model correction submodule is used to adjust the parameters of the tap detection network based on the stored positive sample data and negative sample data to obtain a corrected tap scanning model if the positive sample data and negative sample data stored in the electronic device meet preset conditions.

[0152] Furthermore, the model correction module 240 further includes: a quantity determination submodule and a preset condition determination submodule, wherein:

[0153] The quantity determination submodule is used to determine the quantity of positive sample data stored in the electronic device and determine the quantity of negative sample data stored in the electronic device.

[0154] The preset condition determination submodule is used to determine whether the positive sample data and negative sample data stored in the electronic device meet the preset condition if the number of positive sample data stored in the electronic device reaches a number threshold and the number of negative sample data stored in the electronic device reaches a data threshold.

[0155] Furthermore, the model correction device 200 further includes: a sensor data detection module and a sensor data input module, wherein:

[0156] The sensor data detection module is used to detect sensor data of the acceleration sensor of the electronic device within a preset time period at a preset time interval.

[0157] A sensor data input module is used to input the sensor data into the knock detection network.

[0158] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0159] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0160] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0161] See also Fig. 9 , which shows a structural block diagram of an electronic device 100 provided in an embodiment of the present application. The electronic device 100 may be an electronic device capable of running applications, such as a smart phone, a tablet computer, an e-book, etc. The electronic device 100 in the present application may include one or more of the following components: a processor 110, a memory 120, and one or more applications, wherein the one or more applications may be stored in the memory 120 and configured to be executed by one or more processors 110, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.

[0162] Among them, the processor 110 may include one or more processing cores. The processor 110 uses various interfaces and lines to connect various parts of the entire electronic device 100, and executes various functions and processes data of the electronic device 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 120, and calling data stored in the memory 120. Optionally, the processor 110 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 110 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 110, but may be implemented separately through a communication chip.

[0163] The memory 120 may include a random access memory (RAM) or a read-only memory (ROM). The memory 120 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing functions (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data (such as a phone book, audio and video data, chat record data) created by the electronic device 100 during use.

[0164] See also Fig.10 , which shows a structural block diagram of a computer-readable storage medium provided in an embodiment of the present application. The computer-readable medium 300 stores program codes, which can be called by a processor to execute the method described in the above method embodiment.

[0165] The computer readable storage medium 300 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium 300 includes a non-transitory computer-readable storage medium. The computer readable storage medium 300 has storage space for program code 310 that performs any method steps in the above method. These program codes can be read from or written to one or more computer program products. The program code 310 can be compressed, for example, in an appropriate form.

[0166] In summary, the model correction method, device, electronic device and storage medium provided in the embodiments of the present application, if the tapping operation acting on the electronic device is identified by the tapping detection network included in the tapping scanning model, then the tapping data corresponding to the tapping operation is determined, and the interface displayed by the electronic device in response to the tapping operation is determined, and the interface relationship between the displayed interface and the target interface is determined, and the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to perform a scan code payment. Based on the interface relationship, the tapping data is determined as sample data, and the sample data includes positive sample data or negative sample data. Based on the sample data, the parameters of the tapping detection network are adjusted to obtain a corrected tapping scanning model, so that implicit correction can be achieved by obtaining positive sample data or negative sample data during the payment process of the electronic device and adjusting the parameters of the tapping detection network, thereby improving the personalized adaptation of the model and the convenience of scan code payment without the user noticing.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for calibrating a model, characterized in that: Applied to electronic equipment, the method comprises: If a tapping operation acting on the electronic device is identified by the tapping detection network included in the tapping code scanning model, the tapping data corresponding to the tapping operation is determined, and the interface displayed by the electronic device in response to the tapping operation is determined; Determining an interface relationship between the displayed interface and a target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to execute a scan code payment; Based on the interface relationship, determining the knocking data as sample data, wherein the sample data includes positive sample data or negative sample data; The parameters of the tapping detection network are adjusted based on the sample data to obtain a calibrated tapping code scanning model.

2. The method according to claim 1, characterized in that The step of adjusting parameters of the tapping detection network based on the sample data to obtain a calibrated tapping code scanning model includes: storing the sample data in the electronic device; If the positive sample data and the negative sample data stored in the electronic device meet the preset conditions, the parameters of the tap detection network are adjusted based on the stored positive sample data and the negative sample data to obtain a calibrated tap scanning model.

3. The method according to claim 2, characterized in that The method further comprises: Determining the amount of positive sample data stored in the electronic device, and determining the amount of negative sample data stored in the electronic device; If the number of positive sample data stored in the electronic device reaches a number threshold, and the number of negative sample data stored in the electronic device reaches a data threshold, it is determined that the positive sample data and the negative sample data stored in the electronic device meet a preset condition.

4. The method according to claim 1, characterized in that: The determining an interface displayed by the electronic device in response to the tapping operation includes: Turning on a camera of the electronic device and acquiring images through the camera; If an image including a first QR code is captured by the camera, determining that the displayed interface is a first interface, wherein the first interface matches the target interface; or If the image including the first QR code is not captured by the camera, it is determined that the displayed interface is a second interface, wherein the second interface does not match the target interface.

5. The method according to claim 4, characterized in that If an image including a first QR code is captured by the camera, determining that the displayed interface is a first interface includes: If the image including the first two-dimensional code is captured by the camera, the first two-dimensional code is recognized; If it is recognized that the first QR code is related to payment, determining that the displayed interface is the first interface; or If it is recognized that the first QR code is not related to payment, it is determined that the displayed interface is a third interface, wherein the third interface does not match the target interface.

6. The method according to claim 1, characterized in that The determining an interface displayed by the electronic device in response to the tapping operation includes: Display the second QR code; If it is determined that the second QR code is scanned by a code scanning device, then determining that the displayed interface is a fourth interface, wherein the fourth interface matches the target interface; or If it is determined that the second QR code has not been scanned by the code scanning device, it is determined that the displayed interface is the fifth interface, wherein the fifth interface does not match the target interface.

7. The method according to claim 6, characterized in that If it is determined that the second two-dimensional code is scanned by a code scanning device, determining that the displayed interface is a fourth interface includes: If it is determined that the second two-dimensional code is scanned by a code scanning device, identifying the second two-dimensional code; If it is recognized that the second QR code is related to payment, determining that the displayed interface is the fourth interface; or If it is recognized that the second QR code is not related to payment, it is determined that the interface displayed by the operation is the sixth interface, wherein the sixth interface does not match the target interface.

8. The method according to any one of claims 1 to 7, characterized in that: The step of determining the knocking data as sample data based on the interface relationship includes: If it is determined based on the interface relationship that the displayed interface does not match the target interface, the tapping data is determined as negative sample data; or If it is determined based on the interface relationship that the displayed interface matches the target interface, the tap data is determined as positive sample data.

9. The method according to any one of claims 1 to 7, characterized in that: Before the step of identifying a tapping operation on the electronic device through the tapping detection network included in the tapping code scanning model, determining tapping data corresponding to the tapping operation, and determining an interface displayed by the electronic device in response to the tapping operation, the method further includes: At preset time intervals, detecting sensor data of an acceleration sensor of the electronic device within a preset time period; The sensor data is input into the tap detection network.

10. A model calibration device, characterized in that: Applied to electronic equipment, the device comprises: An interface determination module, configured to determine, if a tapping operation acting on the electronic device is identified through a tapping detection network included in the tapping code scanning model, tapping data corresponding to the tapping operation, and determine an interface displayed by the electronic device in response to the tapping operation; An interface relationship determination module, used to determine an interface relationship between the displayed interface and a target interface, wherein the interface relationship includes a match or a mismatch, and the target interface is used to instruct the electronic device to execute a scan code payment; A sample data determination module, used to determine the knocking data as sample data based on the interface relationship, wherein the sample data includes positive sample data or negative sample data; The model correction module is used to adjust the parameters of the tap detection network based on the sample data to obtain a corrected tap scanning model.

11. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory is coupled to the processor, the memory stores instructions, and when the instructions are executed by the processor, the processor executes the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 9.