Deep learning-based interface processing method, electronic equipment and storage medium

Abstract

The invention discloses an interface processing method based on deep learning, electronic equipment and a storage medium. The method comprises the following steps: acquiring user information of a current user; the user information and the environment information are input into a first deep learning model, interface adjustment parameters are obtained, and the first deep learning model is used for determining the interface adjustment parameters matched with the user information and the environment information according to the user information and the environment information; and adjusting an initial interface of the super cabinet according to the interface adjustment parameter to obtain an adjusted interface, and outputting the adjusted interface. According to user information and environment information of a current user, an interface adjustment parameter matched with the current user can be obtained through a first deep learning model. After the initial interface is adjusted according to the interface adjustment parameter, the adjustment interface can adapt to the personalized requirements of the current user, the adaptation degree of the super cabinet interface and user personalization is improved, and the service efficiency of the super cabinet is improved.

Description

Technical Field

[0001] The present invention relates to the field of financial equipment testing and application, and in particular to an interface processing method, electronic device, and storage medium based on deep learning. Background Art

[0002] The Super Counter System (STS) is an advanced self-service device designed by banks to optimize customer service processes and improve service efficiency. Currently, the STS interface is pre-configured, providing banking services to all users using the same pre-set interface, regardless of individual user preferences.

[0003] However, due to individual differences, different users may have different responses to the same preset interface, resulting in deviations in the service performance of super lockers and a negative impact on user experience. How to enable super lockers to provide users with a more adaptive interface has become an urgent problem to be solved. Summary of the Invention

[0004] The present invention provides an interface processing method, electronic device and storage medium based on deep learning to solve the problem that the user interface provided by super cabinets lacks individual user adaptation.

[0005] According to one aspect of the present invention, a deep learning-based interface processing method is provided, which is applied to a super cabinet. The method includes:

[0006] Get the user information of the current user;

[0007] Inputting the user information and the environmental information into a first deep learning model to obtain interface adjustment parameters, wherein the first deep learning model is used to determine the interface adjustment parameters adapted to the user information and the environmental information based on the user information and the environmental information;

[0008] The initial interface of the super cabinet is adjusted according to the interface adjustment parameters to obtain an adjustment interface, and the adjustment interface is output.

[0009] According to another aspect of the present invention, there is provided an interface processing device based on deep learning, which is applied to a super cabinet. The device includes:

[0010] User information acquisition module, used to obtain user information of the current user;

[0011] a first model processing module, configured to input the user information and the environmental information into a first deep learning model to obtain interface adjustment parameters, wherein the first deep learning model is configured to determine, based on the user information and the environmental information, interface adjustment parameters adapted to the user information and the environmental information;

[0012] An adjustment module, configured to adjust the initial interface of the super cabinet according to the interface adjustment parameters to obtain an adjustment interface;

[0013] An output module is used to output the adjustment interface.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the deep learning-based interface processing method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the deep learning-based interface processing method described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention obtains the user information of the current user; inputs the user information and environmental information into the first deep learning model to obtain interface adjustment parameters, and the first deep learning model is used to determine the interface adjustment parameters adapted to the user information and the environmental information according to the user information and the environmental information; adjusts the initial interface of the super cabinet according to the interface adjustment parameters to obtain an adjustment interface, and outputs the adjustment interface. Compared with the current situation where a set of preset interfaces is used to provide services to all users and the interface cannot be adjusted according to the user's personal characteristics, the technical solution provided by the present invention can obtain interface adjustment parameters adapted to the current user through the first deep learning model according to the user information and environmental information of the current user. After adjusting the initial interface according to the interface adjustment parameters, the adjustment interface can adapt to the personalized needs of the current user, improve the adaptability of the super cabinet interface to the user's personalization, and improve the service efficiency of the super cabinet.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flowchart of a method for processing an interface based on deep learning provided in the first embodiment of the present invention;

[0023] Figure 2 2 is a schematic structural diagram of an interface processing device based on deep learning provided in the second embodiment of the present invention;

[0024] Figure 3 2 is a schematic structural diagram of another interface processing device based on deep learning provided in the second embodiment of the present invention;

[0025] Figure 4 It is a structural diagram of an electronic device that implements the deep learning-based interface processing method of an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0029] The relevant technologies involved in this application include user experience testing, deep learning technology, and super cabinets.

[0030] User Experience Testing (UXT) is a testing method specifically designed to evaluate whether a product or service meets actual user needs. By systematically observing and analyzing user behaviors, feelings, and issues encountered during product usage, this method aims to reveal a product's usability, efficiency, satisfaction, and potential barriers to use. Through this testing, designers and developers can gain valuable insights into how to improve a product's interface and functionality, ultimately increasing overall user satisfaction and enhancing the product's market competitiveness.

[0031] Deep learning technology, a category of artificial intelligence, uses multi-layered (or deep) neural networks to learn complex patterns in data. The network consists of three main layers: an input layer receives raw data, multiple hidden layers progressively extract high-level features from the data through multi-layered nonlinear transformations, and an output layer produces the final decision or prediction. The core advantage of deep learning lies in its ability to process extremely complex data structures by increasing the depth and width of the network, enabling breakthroughs in fields such as image and sound recognition, natural language processing, and medical diagnosis.

[0032] Super Counter: Super Counter systems are advanced self-service devices designed by banks to optimize customer service processes and improve service efficiency. Designed to mimic the services provided by traditional tellers, Super Counter systems allow customers to complete a wide range of banking tasks independently, including but not limited to account management, fund transfers, cash deposits and withdrawals, and bill payments. Unlike traditional automated teller machines (ATMs), Super Counter systems are equipped with more advanced authentication technologies, such as biometric systems, and user interfaces capable of handling more complex transactions. These devices not only meet the high standards of convenience and efficiency demanded by modern bank users, but also enhance the overall customer experience through optimized user interaction design while ensuring transaction security.

[0033] A test report documents the testing process and results, analyzing discovered issues and defects to provide a basis for correcting software quality issues. In the banking system project testing cycle, the test report is the final documented output of the testing phase. A detailed test report includes an evaluation of product quality and the testing process. Based on data collected during testing and analysis of the final test results, the test manager must possess advanced documentation skills.

[0034] Currently, the interface of the Super Kiosk system is pre-configured, providing banking-related financial services to users using the same pre-set interface regardless of individual user experience. However, due to individual differences, different users may experience varying results with the same pre-set interface, leading to discrepancies in the effectiveness of the Super Kiosk service and negatively impacting the user experience. How to provide a more user-friendly interface for Super Kiosk systems has become an urgent issue.

[0035] Example 1

[0036] Figure 1 This is a flow chart of a method for interface processing based on deep learning provided by the first embodiment of the present invention. This embodiment is applicable to situations where super-cabinets provide banking financial services to users. This embodiment is also applicable to situations where user experience testing is conducted during the user experience testing phase based on the improved solution provided by the present invention. This method can be executed by an interface processing device based on deep learning. The interface processing device based on deep learning can be implemented in the form of hardware and / or software. The interface processing device based on deep learning can be configured in an electronic device. Figure 1 As shown, the method is applied to a super cabinet, and the method includes:

[0037] S110: Obtain user information of the current user.

[0038] User information includes hardware interaction data and biometric data.

[0039] For hardware interaction data, cameras can be used to record user interactions with various external hardware, including soft keyboard tapping speed, click response, and pen usage. The frequency and duration of these data can be calculated, and parameters such as user comfort and efficiency during hardware use can also be recorded.

[0040] Biometric data can be systematically collected through biometric technologies such as facial recognition, fingerprint recognition, and camera technology, including facial and fingerprint recognition, as well as other physiological parameters such as height, weight, and physical condition. This data is particularly important for evaluating the personalized adaptability and security of the system, and is used to ensure that the system can effectively recognize and respond to the unique physiological characteristics of different users.

[0041] Optionally, obtain the current user's user information, which can be implemented as follows:

[0042] Obtain user information of the current user during the user experience testing phase;

[0043] The user information includes physical characteristics and identification characteristics; the physical characteristics include: user height, age, and wheelchair riding status; the identification characteristics include: facial recognition characteristics and fingerprint recognition characteristics.

[0044] Optionally, the user interaction data may be as shown in Table 1.

[0045] Table 1

[0046]

[0047] Age and gender can be obtained from basic information such as the user's ID number. Wheelchair status and height can be captured via a camera. Wheelchair status indicates whether a user is in a wheelchair. Facial recognition and fingerprint recognition pass rates can be determined based on hardware interaction data. This hardware interaction data can be a historical average of multiple users or the current user's own historical pass rate.

[0048] The above implementation method can be implemented during the user experience testing phase. Through user testing experience, the accuracy of the first deep learning model and the second deep learning model described below can be evaluated and optimized, thereby achieving iterative optimization of the deep learning model and the initial interface of the super cabinet. The deep learning model used by the first deep learning model and the second deep learning model in this application can be a BERT model or other type of deep learning model.

[0049] Furthermore, we can track and record user behavior patterns during the Super Counter system operation, including their preferences for selected services, the order in which they click on service options, and their habitual paths throughout the entire operation process. This data can provide insights into user habits and potential operational obstacles, thereby optimizing interface design and user interaction experience.

[0050] S120. Input the user information and environmental information into a first deep learning model to obtain interface adjustment parameters, wherein the first deep learning model is used to determine interface adjustment parameters adapted to the user information and the environmental information based on the user information and the environmental information.

[0051] The environmental information may be light intensity.

[0052] Optionally, before inputting the user information and environment information into the first deep learning model, the method further includes:

[0053] Preprocessing is performed based on the user information and the environment information, and the preprocessing includes data cleaning and integration.

[0054] It can remove errors and incomplete parts from the collected data. This includes correcting data format issues, filling missing values, and excluding irrelevant or abnormal data to ensure the accuracy and reliability of subsequent analysis. Data from multiple different data sources (different users, different super lockers) are merged and standardized for unified analysis. The above process involves processing the unified data format and structure, and annotating the training data and input data of the first deep learning model according to behavioral labels (height, age, physical condition, face, fingerprint, lighting, operation information).

[0055] The input data of the first deep learning model is user information and environmental information. The first deep learning model can be established by training the pre-processed training data through the deep learning BERT algorithm. The first deep learning model is used to discover and identify common behavior patterns and trends, and reveal the user's operating habits and potential preferences. The output data of the first deep learning model is the interface adjustment parameter. It is used to adjust the interface layout of the super cabinet so that the interface layout of the super cabinet matches the input user information and environmental information. In addition, you can also choose

[0056] The above implementation method can clean and integrate user information from multiple sources through preprocessing, improve data quality, and thus improve the processing efficiency of the first deep learning model.

[0057] Exemplarily, after the first deep learning model analyzes the user information and the environmental information, the following description can be obtained.

[0058] 1. User feature-related behavior

[0059] Age and technology acceptance factors include the fact that younger users may more frequently use high-tech features such as biometrics, while older users may rely more on traditional authentication methods or require auxiliary features (such as voice commands or larger fonts).

[0060] Physical status impact includes physical status such as whether or not a wheelchair is used, which may affect the user's accessibility and operation of self-service equipment, suggesting the need for more physical assistive facilities or interface adjustments.

[0061] 2. Analysis of the effectiveness of biometric technology

[0062] The efficiency of facial and fingerprint recognition includes the pass rate and time of facial recognition and the degree of wear of fingerprint recognition, which can reveal the impact of different environmental conditions (such as light intensity) or individual differences (such as changes in hand features caused by age and occupation) on the efficiency of biometric technology.

[0063] 3. Operational behavior pattern

[0064] Operation type and frequency include analyzing the frequency of users' selection of different business options and the type of operation, revealing the user's main needs and preferences. For example, the frequency of query business operations is higher than that of transaction business operations, which may reflect the user's urgent need to obtain information.

[0065] Operation time: The length and distribution of operation time can assess the complexity of the operation and the user's familiarity with the operation process. Long operation times may indicate that the operation interface or process is not intuitive.

[0066] 4. Impact of environmental factors on operations

[0067] Light intensity includes analyzing the effect of light on operational behavior, particularly when using biometrics in outdoor devices or in environments with unstable lighting.

[0068] 5. System responsiveness and user satisfaction

[0069] System response time, including long loading times or command execution delays, can lead to user dissatisfaction and operation abandonment. Monitoring these indicators helps the technical team to make necessary system optimizations.

[0070] User feedback: By monitoring and recording users' immediate feedback (such as expressions through buttons or touch screens), users' satisfaction with the system's responses can be directly collected.

[0071] S130: Adjust the initial interface of the super cabinet according to the interface adjustment parameters to obtain an adjustment interface.

[0072] Optionally, adjusting the initial interface of the super cabinet according to the interface adjustment parameters to obtain an adjusted interface can be implemented in the following manner:

[0073] The user interaction features in the initial interface of the super cabinet are adjusted according to the interface adjustment parameters to obtain an adjustment interface, and the user interaction features include: button position, button size, menu size, touch response time, voice assistance startup status or screen brightness.

[0074] The above implementation method can adjust the initial interface in real time according to the interface adjustment parameters obtained by the first deep learning model, so that the adjustment interface output by the super cabinet can match the user information and environmental information of the current user.

[0075] Furthermore, before adjusting the initial interface of the super cabinet according to the interface adjustment parameters, the method further includes:

[0076] Get historical operation information of multiple users;

[0077] An initial interface of the super cabinet is determined based on the historical operation information and the second deep learning model.

[0078] The historical operation information includes historical operation type, historical operation frequency and historical operation time.

[0079] The above implementation method can optimize and determine the initial interface of the super cabinet through the second deep learning model based on the user's historical operation information, realize dynamic optimization of the initial interface, and improve the processing efficiency of the super cabinet.

[0080] Optionally, determining the initial interface of the super locker based on the historical operation information and the second deep learning model can be implemented in the following manner:

[0081] Determining interface optimization parameters based on the historical operation information and the second deep learning model;

[0082] The interface features of the original interface are optimized according to the interface optimization parameters to obtain an initial interface, wherein the interface features include task-oriented layout, navigation level, number of user operations, and smart filling or merging steps.

[0083] Historical operation information includes operation type, operation frequency, and operation time. Operation type includes screen tap, facial recognition, and fingerprint recognition. Operation frequency refers to the number and frequency of operations corresponding to the operation type. Operation time refers to the system response time during the operation.

[0084] The above implementation method can optimize the operation path of the business in the super cabinet through the second deep learning model according to the user's historical operation information, reduce the number of business operation steps or optimize the business operation method, and improve business processing efficiency.

[0085] For example, the second deep learning model can optimize the operational steps for completing business functions, including: adjusting the super counter design and improving super counter user interaction.

[0086] Super Counter design adjustments include adjustments to the interface layout and navigation structure based on interaction data and user behavior analysis. This includes rearranging interface elements to improve logic and optimizing in the following areas:

[0087] (1) Task-oriented layout involves arranging elements according to the user’s frequency of use and task flow. Frequently used functions (such as quick payment) should be placed in a prominent and easy-to-click location, while less frequently used functions can be placed in a secondary location.

[0088] (2) Simplify navigation, including reducing levels and avoiding deep navigation structures. Ensure that users can complete common operations within two to three steps, so that users always know where they are in the system and can easily return.

[0089] (3) Simplify the user path to reduce the number of operation steps, including designing one-click operation buttons: for example, one-click payment, one-click balance query, etc., to reduce the number of user clicks.

[0090] (4) Intelligent prompts and pre-filling include intelligently pre-filling information or providing recommended options based on user historical behavior and data: for example, priority display of commonly used payment methods and automatic suggestions for frequently used contacts.

[0091] (5) The merging step includes combining multiple operation steps into one. For example, during the payment process, selecting the payment method and confirming the payment are combined into one interface.

[0092] Super-cabinet user interaction improvements include refining and optimizing interactive elements on the interface, such as button and menu size, touch response time, based on the usage habits of different age groups and groups, and auxiliary functions for users with special needs, such as voice commands and high-contrast color modes.

[0093] In addition, the functions of the super cabinet can be adjusted and special needs analyzed.

[0094] Functional adjustments include feedback test design and functional optimization based on interaction data and super-cabinet user behavior analysis, by enhancing or modifying existing functions to better meet user needs, by adding new functions to supplement the core function set, or adjusting the working method of existing functions to improve efficiency and user satisfaction.

[0095] Special needs analysis includes accessibility assessment, customized function updates, and environmental adaptability improvements.

[0096] Accessibility assessment involves systematically evaluating and ensuring that the interface and functionality of the Super Counter system are accessible to all users, including those with disabilities. This includes checking compatibility with assistive technologies for visual, auditory, and physical operations, such as screen reader support, subtitle options, and easy-to-use interface design.

[0097] Customized features include those designed and implemented specifically for groups with special needs, such as voice feedback systems for users with limited vision or simplified operating interfaces for users with physical disabilities, ensuring that every user can effectively utilize all the system's features.

[0098] Environmental adaptability improvements include developing intelligent system features that automatically detect and adapt to varying environmental conditions, such as changing lighting and network quality. By automatically adjusting display brightness, volume, and data transmission settings, the system optimizes the user experience in various environments, thereby improving overall system reliability and user satisfaction.

[0099] S140: Output the adjustment interface.

[0100] Alternatively, an iterative approach can be used to update the system, with continuous testing and feedback loops to ensure that each update addresses identified issues and optimizes the system, gradually improving system stability and user experience.

[0101] The interface processing method based on deep learning of the embodiment of the present invention obtains the user information of the current user; inputs the user information and environmental information into the first deep learning model to obtain interface adjustment parameters, and the first deep learning model is used to determine the interface adjustment parameters adapted to the user information and the environmental information according to the user information and the environmental information; adjusts the initial interface of the super cabinet according to the interface adjustment parameters to obtain an adjustment interface, and outputs the adjustment interface. Compared with the current situation where a set of preset interfaces is used to provide services to all users and the interface cannot be adjusted according to the user's personal characteristics, the interface processing method based on deep learning provided by the present invention can obtain interface adjustment parameters adapted to the current user through the first deep learning model according to the user information and environmental information of the current user. After the initial interface is adjusted according to the interface adjustment parameters, the adjustment interface can adapt to the personalized needs of the current user, improve the adaptability of the super cabinet interface to the user's personalization, and improve the service efficiency of the super cabinet.

[0102] Existing super-counter testing technology primarily focuses on evaluating the completeness of software functionality, such as program stability and speed, while neglecting to consider the actual user experience. In particular, it lacks consideration for special needs groups and environmental factors. This makes the test unable to fully reflect the actual user experience needs of all user groups. This limits the application potential of super-counter systems in the broader market, affecting their widespread acceptance and satisfaction. Introducing deep learning models to analyze user behavior through artificial intelligence technology can provide a deeper understanding of users' specific needs and behavior patterns, thereby providing more precise user experience optimization recommendations. In-depth data-driven analysis can not only enhance the user experience of special needs groups, but also adapt to complex environmental variables, significantly improving the overall usability and market competitiveness of the system.

[0103] By incorporating deep learning technology into user experience testing at super counters, this invention enables the system to deeply understand and adapt to diverse user behaviors from the user's perspective, thereby providing a precise optimization basis for improving the system's service capabilities. This not only improves the comprehensiveness and accuracy of the test, but also achieves the following benefits:

[0104] (1) Accurately simulate and predict user behavior: Through deep learning, the system can identify and predict user behavior patterns in different situations, thereby adapting to and responding to user needs in advance.

[0105] (2) Dynamically adapt to user needs: The system can dynamically adjust its functions and interface based on data learned from user behavior, ensuring that every user has the best interactive experience, no matter how their needs change.

[0106] (3) Continuous optimization and iterative development: Deep learning enables the system to have the ability to continuously learn and continuously optimize itself based on user feedback and behavioral changes, ensuring that the system can always provide efficient, accurate and personalized services over time.

[0107] Example 2

[0108] Figure 2 This is a structural diagram of an interface processing device based on deep learning provided by the second embodiment of the present invention. This embodiment can be applied to situations where a super-cabinet machine provides banking financial services to users. This embodiment can also be applied to situations where user experience testing is conducted based on the improved solution provided by the present invention during the user experience testing phase. The interface processing device based on deep learning can be implemented in the form of hardware and / or software, and the interface processing device based on deep learning can be configured in an electronic device. Figure 2 As shown, the device includes: a user information acquisition module 21, a first model processing module 22, an adjustment module 23 and an output module 24.

[0109] User information acquisition module 21, used to obtain user information of the current user;

[0110] A first model processing module 22 is configured to input the user information and environment information into a first deep learning model to obtain interface adjustment parameters, wherein the first deep learning model is configured to determine interface adjustment parameters adapted to the user information and environment information based on the user information and environment information;

[0111] An adjustment module 23 is configured to adjust the initial interface of the super cabinet according to the interface adjustment parameters to obtain an adjusted interface;

[0112] The output module 24 is configured to output the adjustment interface.

[0113] On the basis of the above implementation, optionally, Figure 3 As shown, a preprocessing module 25 is also included for performing preprocessing based on the user information and environmental information before inputting the user information and environmental information into the first deep learning model, wherein the preprocessing includes data cleaning and integration.

[0114] Based on the above implementation, optionally, the adjustment module 23 is used to:

[0115] The user interaction features in the initial interface of the super cabinet are adjusted according to the interface adjustment parameters to obtain an adjustment interface, and the user interaction features include: button position, button size, menu size, touch response time, voice assistance startup status or screen brightness.

[0116] Based on the above embodiment, optionally, a second model processing module 26 is further included, which is used to obtain historical operation information of multiple users before adjusting the initial interface of the super cabinet according to the interface adjustment parameters;

[0117] An initial interface of the super cabinet is determined based on the historical operation information and the second deep learning model.

[0118] Based on the above implementation, optionally, the historical operation information includes historical operation type, historical operation frequency and historical operation time.

[0119] Based on the above embodiment, optionally, the second model processing module 26 is configured to determine the initial interface of the super locker according to the historical operation information and the second deep learning model, including:

[0120] Determining interface optimization parameters based on the historical operation information and the second deep learning model;

[0121] The interface features of the original interface are optimized according to the interface optimization parameters to obtain an initial interface, wherein the interface features include task-oriented layout, navigation level, number of user operations, and smart filling or merging steps.

[0122] Based on the above implementation, optionally, the user information acquisition module 21 is used to:

[0123] Obtain user information of the current user during the user experience testing phase;

[0124] The user information includes physical characteristics and identification characteristics; the physical characteristics include: user height, age, and wheelchair riding status; the identification characteristics include: facial recognition characteristics and fingerprint recognition characteristics.

[0125] The interface processing device based on deep learning in the embodiment of the present invention comprises a user information acquisition module 21 for acquiring the user information of the current user; a first model processing module 22 for inputting the user information and environmental information into the first deep learning model to obtain interface adjustment parameters, wherein the first deep learning model is used to determine interface adjustment parameters adapted to the user information and environmental information based on the user information and environmental information; an adjustment module 23 for adjusting the initial interface of the super cabinet according to the interface adjustment parameters to obtain an adjustment interface; and an output module 24 for outputting the adjustment interface. Compared with the current situation in which a set of preset interfaces is used to provide services to all users and the interface cannot be adjusted according to the user's personal characteristics, the interface processing device based on deep learning provided by the present invention can obtain interface adjustment parameters adapted to the current user through the first deep learning model based on the user information and environmental information of the current user. After the initial interface is adjusted according to the interface adjustment parameters, the adjustment interface can adapt to the personalized needs of the current user, thereby improving the adaptability of the super cabinet interface to the user's personalization and improving the service efficiency of the super cabinet.

[0126] The deep learning-based interface processing device provided in an embodiment of the present invention can execute the deep learning-based interface processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0127] Example 3

[0128] Figure 4 1 is a structural diagram of an electronic device provided in Example 3 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0129] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0130] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0131] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the deep learning-based interface processing method.

[0132] In some embodiments, the deep learning-based interface processing method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the deep learning-based interface processing method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the deep learning-based interface processing method in any other appropriate manner (e.g., by means of firmware).

[0133] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] Computer programs for implementing the deep learning-based interface processing methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0135] Example 4

[0136] A fourth embodiment of the present invention further provides a computer-readable storage medium storing computer instructions, the computer instructions being used to cause a processor to execute a deep learning-based interface processing method applied to a super cabinet, the method comprising:

[0137] Get the user information of the current user;

[0138] Inputting the user information and the environmental information into a first deep learning model to obtain interface adjustment parameters, wherein the first deep learning model is used to determine the interface adjustment parameters adapted to the user information and the environmental information based on the user information and the environmental information;

[0139] The initial interface of the super cabinet is adjusted according to the interface adjustment parameters to obtain an adjustment interface, and the adjustment interface is output.

[0140] Based on the above implementation, optionally, before inputting the user information and environment information into the first deep learning model, the method further includes:

[0141] Preprocessing is performed based on the user information and the environment information, and the preprocessing includes data cleaning and integration.

[0142] On the basis of the above embodiment, optionally, adjusting the initial interface of the super cabinet according to the interface adjustment parameter to obtain an adjustment interface includes:

[0143] The user interaction features in the initial interface of the super cabinet are adjusted according to the interface adjustment parameters to obtain an adjustment interface, and the user interaction features include: button position, button size, menu size, touch response time, voice assistance startup status or screen brightness.

[0144] Based on the above implementation, optionally, before adjusting the initial interface of the super cabinet according to the interface adjustment parameter, the method further includes:

[0145] Get historical operation information of multiple users;

[0146] An initial interface of the super cabinet is determined based on the historical operation information and the second deep learning model.

[0147] Based on the above implementation, optionally, the historical operation information includes historical operation type, historical operation frequency and historical operation time.

[0148] Based on the above embodiment, optionally, determining the initial interface of the super locker according to the historical operation information and the second deep learning model includes:

[0149] Determining interface optimization parameters based on the historical operation information and the second deep learning model;

[0150] The interface features of the original interface are optimized according to the interface optimization parameters to obtain an initial interface, wherein the interface features include task-oriented layout, navigation level, number of user operations, and smart filling or merging steps.

[0151] Based on the above implementation, optionally, obtaining the user information of the current user includes:

[0152] Obtain user information of the current user during the user experience testing phase;

[0153] The user information includes physical characteristics and identification characteristics; the physical characteristics include: user height, age, and wheelchair riding status; the identification characteristics include: facial recognition characteristics and fingerprint recognition characteristics.

[0154] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0155] To provide interaction with developers, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the developer; and a keyboard and pointing device (e.g., a mouse or trackball) through which the developer can provide input to the electronic device. Other types of devices can also be used to provide interaction with the developer; for example, the feedback provided to the developer can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the developer can be received in any form (including acoustic input, voice input, or tactile input).

[0156] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a developer computer with a graphical developer interface or a web browser through which a developer can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0157] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0158] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0159] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for interface processing based on deep learning, characterized in that: Applied to a super cabinet, the method includes: Get the user information of the current user; Inputting the user information and the environmental information into a first deep learning model to obtain interface adjustment parameters, wherein the first deep learning model is used to determine the interface adjustment parameters adapted to the user information and the environmental information based on the user information and the environmental information; The initial interface of the super cabinet is adjusted according to the interface adjustment parameters to obtain an adjustment interface, and the adjustment interface is output.

2. The method according to claim 1, characterized in that Before inputting the user information and environment information into the first deep learning model, the method further includes: Preprocessing is performed based on the user information and the environment information, and the preprocessing includes data cleaning and integration.

3. The method according to claim 1, characterized in that The initial interface of the super cabinet is adjusted according to the interface adjustment parameters to obtain an adjustment interface, including: The user interaction features in the initial interface of the super cabinet are adjusted according to the interface adjustment parameters to obtain an adjustment interface, and the user interaction features include: button position, button size, menu size, touch response time, voice assistance startup status or screen brightness.

4. The method according to claim 1, wherein Before adjusting the initial interface of the super cabinet according to the interface adjustment parameters, the method further includes: Get historical operation information of multiple users; An initial interface of the super cabinet is determined based on the historical operation information and the second deep learning model.

5. The method according to claim 4, characterized in that The historical operation information includes historical operation type, historical operation frequency and historical operation time.

6. The method according to claim 4, characterized in that Determining an initial interface of the super locker based on the historical operation information and the second deep learning model includes: Determining interface optimization parameters based on the historical operation information and the second deep learning model; The interface features of the original interface are optimized according to the interface optimization parameters to obtain an initial interface, wherein the interface features include task-oriented layout, navigation level, number of user operations, and smart filling or merging steps.

7. The method according to claim 1, characterized in that Get the user information of the current user, including: Obtain user information of the current user during the user experience testing phase; The user information includes physical characteristics and identification characteristics; the physical characteristics include: user height, age, and wheelchair riding status; the identification characteristics include: facial recognition characteristics and fingerprint recognition characteristics.

8. An interface processing device based on deep learning, characterized in that: Applied to super cabinet, the device includes: User information acquisition module, used to obtain user information of the current user; a first model processing module, configured to input the user information and the environmental information into a first deep learning model to obtain interface adjustment parameters, wherein the first deep learning model is configured to determine, based on the user information and the environmental information, interface adjustment parameters adapted to the user information and the environmental information; An adjustment module, configured to adjust the initial interface of the super cabinet according to the interface adjustment parameters to obtain an adjustment interface; An output module is used to output the adjustment interface.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the deep learning-based interface processing method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the deep learning-based interface processing method according to any one of claims 1 to 7 when executed.

Images