Method and apparatus for debugging driving waveforms of e-paper display device, device and medium

Through multiple iterative debugging and reinforcement of learning and debugging network architecture, the driving waveform of electronic paper equipment is automatically adjusted, which solves the problems of low debugging efficiency and poor stability in the existing technology, and realizes efficient and process-based driving waveform debugging.

WO2024239864A1PCT designated stage expired Publication Date: 2024-11-28BOE TECHNOLOGY GROUP CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/088669
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-24
Filing Date
2024-04-18
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

The prior art is difficult to realize the automated debugging of electronic paper equipment drive waveforms, resulting in low debugging efficiency and poor stability. The violent exhaustive method is too expensive to trial and error, making it difficult to summarize into process logic.

Method used

The multi-iteration debugging method is adopted to obtain and update the second driver waveform information based on the last iteration debugging and the debugging network, and adjust the parameters through optical detection and feedback, and use the reinforcement learning debugging network architecture to automatically adjust the driver waveform.

Benefits of technology

The process-based debugging of electronic paper equipment driver waveforms is realized, which reduces trial and error costs, improves debugging efficiency and stability, and avoids the high costs caused by violent exhaustion.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024088669_28112024_PF_FP_ABST
    Figure CN2024088669_28112024_PF_FP_ABST
Patent Text Reader

Abstract

The present disclosure relates to the technical field of display, and provides a method and apparatus for debugging driving waveforms of an e-paper display device, a device and a medium. The method comprises: for an e-paper display device to be debugged, carrying out multiple times of iterative debugging on driving waveforms of the e-paper display device; when the multiple times of iterative debugging meet a target condition, acquiring a target driving waveform corresponding to the final iterative debugging; and taking the target driving waveform as the driving waveform of the e-paper display device in actual driving, wherein during each time of iterative debugging, second driving waveform information corresponding to the iterative debugging is acquired on the basis of first driving waveform information corresponding to the previous iterative debugging and a debugging network, the e-paper display device is debugged on the basis of the second driving waveform information, and the debugging network is updated on the basis of a debugging result.
Need to check novelty before this filing date? Find Prior Art

Description

Method, device, equipment and medium for debugging electronic paper device driving waveform

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on May 24, 2023, with application number 202310596669.0 and invention name “Method, device, equipment and medium for debugging driving waveform of electronic paper device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present disclosure relate to the field of display technology, and in particular to a method, apparatus, device, and medium for debugging a driving waveform of an electronic paper device. Background Art

[0003] Electrophoretic display (EPD) is a low-energy, paper-like display technology. By continuously applying a driving voltage to the display area, the colored particles within the EPD undergo electrophoresis, thereby displaying a desired image. This continuously applied driving voltage is known as the EPD drive waveform (WF), and its quality directly determines the EPD's display quality.

[0004] To save labor costs, automated E-paper device drive waveform debugging methods have become a research focus. However, a complete drive waveform has hundreds of adjustable parameters, making brute-force trial and error prohibitively expensive. Debugging experience varies widely, making it difficult to summarize and streamline debugging logic, making automated E-paper device drive waveform debugging a challenge.

[0005] Summary of the Invention

[0006] The embodiments of the present disclosure provide a method, apparatus, device, and medium for debugging an electronic paper device driving waveform, aiming to solve the problem of how to debug the electronic paper device driving waveform in a streamlined manner.

[0007] A first aspect of the present disclosure provides a method for debugging a driving waveform of an electronic paper device, comprising:

[0008] For the electronic paper device to be debugged, performing multiple iterations of debugging on the driving waveform of the electronic paper device;

[0009] When the multiple iterations of debugging satisfy the target condition, obtaining the target driving waveform corresponding to the last iteration of debugging;

[0010] Using the target driving waveform as the driving waveform of the electronic paper device in actual driving;

[0011] During each iterative debugging, based on the first driving waveform information and debugging network corresponding to the previous iterative debugging, second driving waveform information corresponding to the current iterative debugging is obtained, the electronic paper device is debugged based on the second driving waveform information, and the debugging network is updated based on the debugging result;

[0012] The debugging network is at least used to obtain adjustment information for adjusting the first driving waveform information based on the input first driving waveform information, and the second driving waveform information is obtained based on the adjustment information and the first driving waveform information.

[0013] In an optional implementation, debugging the electronic paper device based on the second driving waveform information includes:

[0014] performing image refresh processing on the electronic paper device based on the second driving waveform information to obtain a first display image;

[0015] performing optical detection on the first display image to obtain an optical measurement value corresponding to the first display image;

[0016] The debugging result is obtained based on the optical measurement value and a reference optical value of the electronic paper device.

[0017] In an optional implementation, obtaining the debugging result based on the optical measurement value and the reference optical value includes:

[0018] acquiring a first reward parameter value based on the optical measurement value and the reference optical value, wherein the first reward parameter value is used to represent environmental feedback when the first driving waveform information is adjusted according to the adjustment information;

[0019] The debugging result is determined based on the first reward parameter value.

[0020] In an optional embodiment, the reference optical value includes a maximum reference optical value and a minimum reference optical value, and obtaining a first reward parameter value based on the optical measurement value and the reference optical value includes:

[0021] If the optical measurement value is less than or equal to the maximum reference optical value and greater than or equal to the minimum reference optical value, setting 0 as the first reward parameter value;

[0022] If the optical measurement value is greater than the maximum reference optical value, taking the difference between the optical measurement value and the maximum reference optical value as the first reward parameter value;

[0023] If the optical measurement value is less than the minimum reference optical value, the difference between the optical measurement value and the minimum reference optical value is used as the first reward parameter value.

[0024] In an optional implementation, the electronic paper device includes multiple colors, and debugging the electronic paper device based on the second driving waveform information includes:

[0025] performing image refresh processing on the electronic paper device based on the second driving waveform information to obtain a second display image, where the second display image includes a plurality of color areas;

[0026] Performing optical detection on each color region to obtain an optical measurement value corresponding to each color region;

[0027] Obtaining an optical difference value corresponding to each color region based on the optical measurement value corresponding to each color region and the reference optical value of each color region;

[0028] The debugging result is determined based on the optical difference values ​​corresponding to all color regions.

[0029] In an optional implementation, determining the debugging result based on the optical difference values ​​corresponding to all color regions includes:

[0030] The sum of the optical difference values ​​corresponding to all color areas is used as the second reward parameter value;

[0031] The debugging result is determined based on the second reward parameter value.

[0032] In an optional embodiment, the debugging network includes a first subnetwork and a second subnetwork, wherein the first subnetwork is used to output adjustment information for adjusting the first driving waveform information, and updating the debugging network based on the debugging result includes:

[0033] If the debugging result indicates that the debugging fails, inputting the second driving waveform information into the second sub-network to obtain a first expected benefit, where the first expected benefit is used to represent a benefit of the debugging network adjusting the first driving waveform information based on the adjustment information;

[0034] Based on the first expected benefit, parameters of the first sub-network are updated.

[0035] In an optional implementation, the debugging network further includes a third subnetwork and a fourth subnetwork, and updating the debugging network based on the debugging result includes:

[0036] If the debugging result indicates that the debugging fails, inputting the second driving waveform information into the third sub-network to obtain adjustment information for adjusting the second driving waveform information;

[0037] inputting the second driving waveform information and the adjustment information for adjusting the second driving waveform information into the fourth sub-network to obtain a second expected benefit, where the second expected benefit is used to represent a benefit of the debugging network adjusting the second driving waveform information based on the adjustment information;

[0038] Based on the second expected return and the first reward parameter value, the parameters of the second sub-network are updated.

[0039] In an optional implementation, updating the debugging network based on the debugging result includes:

[0040] Updating parameters of the third sub-network based on the updated parameters of the first sub-network;

[0041] Based on the updated parameters of the second sub-network, the parameters of the fourth sub-network are updated.

[0042] In an optional implementation, before acquiring the first driving waveform information, the method further includes:

[0043] Displaying the parameter setting interface of the debugging network;

[0044] In response to the update coefficient input by the user through the parameter setting interface, the update coefficient is set for the debugging network, and the update coefficient is used to adjust the parameter update process of the debugging network.

[0045] In an optional implementation, after using the target driving waveform as the driving waveform of the electronic paper device in actual driving, the method further includes:

[0046] Based on the target driving waveform, acquiring a driving waveform framework and driving waveform pulse information, wherein the driving waveform framework is used to characterize the voltage sequence of the target driving waveform, and the driving waveform pulse information is used to characterize the number of pulses and the number of cycles under the driving waveform framework;

[0047] Compiling the driving waveform framework and the driving waveform pulse information to obtain an electronic paper device driver;

[0048] The electronic paper device driver is executed to perform image refresh processing on the electronic paper device according to the target driving waveform to form a first target display image.

[0049] In an optional embodiment, the electronic paper device is an electronic paper device of a first model, and after using the target driving waveform as the driving waveform of the electronic paper device in actual driving, the method further includes:

[0050] Based on the target driving waveform, a second type of electronic paper device is driven, where the second type of electronic paper device includes the same color type as the first type of electronic paper device.

[0051] A second aspect of the present disclosure provides a device for debugging a driving waveform of an electronic paper device, comprising:

[0052] An iterative debugging module, configured to perform multiple iterative debugging on a driving waveform of an electronic paper device to be debugged;

[0053] A judgment module, configured to obtain a target driving waveform corresponding to the last iteration debugging when the multiple iteration debuggings meet the target condition;

[0054] a driving waveform acquisition module, configured to use the target driving waveform as the driving waveform of the electronic paper device in actual driving;

[0055] A single iteration module is configured to, during each iterative debugging, obtain second driving waveform information corresponding to the current iterative debugging based on the first driving waveform information and debugging network corresponding to the previous iterative debugging, debug the electronic paper device based on the second driving waveform information, and update the debugging network based on the debugging result; wherein the debugging network is configured to obtain adjustment information for adjusting the first driving waveform information based on the input first driving waveform information, and the second driving waveform information is obtained based on the adjustment information and the first driving waveform information.

[0056] In an optional implementation, the single iteration module includes:

[0057] A first display submodule, configured to perform image refresh processing on the electronic paper device based on the second driving waveform information to obtain a first display image;

[0058] a first detection submodule, configured to perform optical detection on the first display image and obtain an optical measurement value corresponding to the first display image;

[0059] The first result acquisition submodule is configured to acquire the debugging result based on the optical measurement value and a reference optical value of the electronic paper device.

[0060] In an optional implementation, the single iteration module includes:

[0061] a first reward submodule, configured to obtain a first reward parameter value based on the optical measurement value and the reference optical value, wherein the first reward parameter value is used to represent environmental feedback when the first driving waveform information is adjusted according to the adjustment information;

[0062] The second result acquisition submodule is configured to determine the debugging result based on the first reward parameter value.

[0063] In an optional embodiment, the first reward submodule includes:

[0064] a first reward obtaining unit, configured to set 0 as the first reward parameter value if the optical measurement value is less than or equal to the maximum reference optical value and greater than or equal to the minimum reference optical value;

[0065] a second reward obtaining unit, configured to use a difference between the optical measurement value and the maximum reference optical value as the first reward parameter value if the optical measurement value is greater than the maximum reference optical value;

[0066] The third reward obtaining unit is configured to use a difference between the optical measurement value and the minimum reference optical value as the first reward parameter value if the optical measurement value is less than the minimum reference optical value.

[0067] In an optional implementation, the single iteration module includes:

[0068] a second display submodule, configured to perform image refresh processing on the electronic paper device based on the second driving waveform information to obtain a second display image, where the second display image includes a plurality of color areas;

[0069] A second detection submodule is configured to perform optical detection on each color region to obtain an optical measurement value corresponding to each color region;

[0070] a difference acquisition submodule, configured to acquire an optical difference value corresponding to each color region based on the optical measurement value corresponding to each color region and a reference optical value of each color region;

[0071] The third result acquisition submodule is configured to determine the debugging result based on the optical difference values ​​corresponding to all color regions.

[0072] In an optional implementation, the third result acquisition submodule includes:

[0073] A second reward unit is configured to use the sum of the optical difference values ​​corresponding to all color areas as a second reward parameter value;

[0074] The third result obtaining unit is configured to determine the debugging result based on the second reward parameter value.

[0075] In an optional implementation, the single iteration module includes:

[0076] a first benefit submodule configured to, when the debugging result indicates that the debugging fails, input the second driving waveform information into the second subnetwork to obtain a first expected benefit, wherein the first expected benefit is used to represent a benefit of the debugging network adjusting the first driving waveform information based on the adjustment information;

[0077] A first updating submodule is configured to update parameters of the first subnetwork based on the first expected benefit.

[0078] In an optional implementation, the single iteration module includes:

[0079] an adjustment submodule, configured to input the second driving waveform information into the third subnetwork to obtain adjustment information for adjusting the second driving waveform information if the debugging result indicates that the debugging fails;

[0080] a second benefit submodule, configured to input the second driving waveform information and the adjustment information for adjusting the second driving waveform information into the fourth subnetwork to obtain a second expected benefit, wherein the second expected benefit is used to represent a benefit of the debugging network adjusting the second driving waveform information based on the adjustment information;

[0081] The second updating submodule is configured to update the parameters of the second sub-network based on the second expected return and the first reward parameter value.

[0082] In an optional implementation, the single iteration module includes:

[0083] a third updating submodule, configured to update parameters of the third subnetwork based on the updated parameters of the first subnetwork;

[0084] The fourth updating submodule is configured to update the parameters of the fourth subnetwork based on the updated parameters of the second subnetwork.

[0085] In an optional implementation, the single iteration module includes:

[0086] An interface display submodule, used to display the parameter setting interface of the debugging network;

[0087] The coefficient setting submodule is used to set the update coefficient of the debugging network in response to the update coefficient input by the user through the parameter setting interface, and the update coefficient is used to adjust the parameter update process of the debugging network.

[0088] In an optional embodiment, the device further includes:

[0089] a parsing module, configured to obtain a driving waveform framework and driving waveform pulse information based on the target driving waveform, wherein the driving waveform framework is used to characterize the voltage sequence of the target driving waveform, and the driving waveform pulse information is used to characterize the number of pulses and the number of cycles under the driving waveform framework;

[0090] A compiling module, configured to compile the driving waveform framework and the driving waveform pulse information to obtain an electronic paper device driver;

[0091] The second target display module is used to execute the electronic paper device driver to perform image refresh processing on the electronic paper device according to the target driving waveform to form a first target display image.

[0092] In an optional embodiment, the device further includes:

[0093] A driving module is configured to drive an electronic paper device of a second model based on the target driving waveform, where the electronic paper device of the second model includes the same color type as the electronic paper device of the first model.

[0094] A third aspect of the present disclosure provides a computing and processing device, including:

[0095] a memory having computer readable code stored therein; and

[0096] One or more processors, when the computer-readable code is executed by the one or more processors, the computing processing device performs the debugging method of the electronic paper device driving waveform as described in any one of the first aspects.

[0097] A fourth aspect of the embodiments of the present disclosure provides a computer-readable medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the method for debugging the driving waveform of an electronic paper device as described in any one of the first aspects. Beneficial effects:

[0098] The present disclosure provides a method, apparatus, device and medium for debugging a driving waveform of an electronic paper device, the method comprising: performing multiple iterative debugging on the driving waveform of an electronic paper device to be debugged; when the multiple iterative debuggings meet target conditions, obtaining a target driving waveform corresponding to the last iterative debugging; and using the target driving waveform as the driving waveform of the electronic paper device in actual driving; wherein, during each iterative debugging, based on first driving waveform information and a debugging network corresponding to the previous iterative debugging, second driving waveform information corresponding to the current iterative debugging is obtained, the electronic paper device is debugged based on the second driving waveform information, and the debugging network is updated based on the debugging result; wherein, the debugging network is used at least to obtain adjustment information for adjusting the first driving waveform information based on the input first driving waveform information, and the second driving waveform information is obtained based on the adjustment information and the first driving waveform information.

[0099] The present invention discloses a debugging network architecture based on reinforcement learning, which automatically adjusts the driving waveform and obtains feedback on the debugging of the driving waveform of the electronic paper device after the adjusted driving waveform, so as to iteratively update the debugging network, avoid the high trial and error cost caused by debugging through brute force, and enable the debugging of the driving waveform of the electronic paper device to be carried out in a process-oriented manner.

[0100] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0102] FIG1 schematically shows a flow chart of a method for debugging an electronic paper device driving waveform according to the method of the present disclosure;

[0103] FIG2 schematically shows a flowchart of each iteration debugging of an electronic paper device driving waveform for executing the method according to the present disclosure;

[0104] FIG3 schematically shows a flowchart of debugging an electronic paper device driving waveform for executing the method according to the present disclosure;

[0105] FIG4 schematically shows a schematic diagram of debugging multiple temperature ranges of an electronic paper device driving waveform for executing the method according to the present disclosure;

[0106] FIG5 schematically shows a debugging apparatus for executing an electronic paper device driving waveform according to the method of the present disclosure;

[0107] FIG6 schematically shows a computing processing device for executing the method according to the present disclosure. Specific embodiments

[0108] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0109] An electrophoretic display (EPD) is a low-energy, paper-like display technology that continuously applies a driving voltage to the display area, causing the colored particles within the EPD to undergo electrophoresis, thereby displaying a specified image. This continuously applied driving voltage is known as the EPD drive waveform (WF), and its quality directly determines the display quality of the EPD. Because EPD modules are affected by a variety of factors, including ambient temperature, moisture, substrate electrical properties, capacitance, and impedance, it is difficult to adjust a drive waveform that meets quality inspection standards.

[0110] In existing technology, the drive waveforms of electronic paper devices are manually debugged. Due to the varying skill levels of debuggers, this process is inefficient and unstable. In recent years, some manufacturers have attempted to build automated drive waveform debugging systems to save labor costs. However, a complete drive waveform has hundreds of adjustable parameters, making brute-force trial-and-error methods prohibitively expensive. Debugging experience varies widely, making it difficult to streamline and streamline the debugging process, making automated drive waveform debugging a challenge.

[0111] In view of this, an embodiment of the present disclosure provides a method for debugging an electronic paper device driving waveform. FIG1 schematically shows a flow chart of the method for debugging an electronic paper device driving waveform according to the present disclosure. As shown in FIG1 , the method includes the following steps:

[0112] S101 : For an electronic paper device to be debugged, perform multiple iterations of debugging on a driving waveform of the electronic paper device.

[0113] During each iterative debugging, based on the first driving waveform information and debugging network corresponding to the previous iterative debugging, second driving waveform information corresponding to the current iterative debugging is obtained, the electronic paper device is debugged based on the second driving waveform information, and the debugging network is updated based on the debugging result;

[0114] The debugging network is at least used to obtain adjustment information for adjusting the first driving waveform information based on the input first driving waveform information, and the second driving waveform information is obtained based on the adjustment information and the first driving waveform information.

[0115] S102 : When the multiple iterations of debugging satisfy a target condition, obtain a target driving waveform corresponding to the last iteration of debugging.

[0116] S103: Using the target driving waveform as the driving waveform of the electronic paper device in actual driving.

[0117] In the embodiment of the present disclosure, the electronic paper device to be debugged can be a common electronic paper device, including but not limited to two-color electronic paper devices (two-color electronic paper devices not only include black and white electronic paper devices, but also include two-color electronic paper devices of white and red, black and red, etc.), three-color electronic paper devices (such as three-color electronic paper devices including black, white and red, etc.), four-color electronic paper devices (such as four-color electronic paper devices including black, white, red and yellow, etc.), and the like.

[0118] In the embodiment of the present disclosure, the driving waveform information in the first driving waveform information and the second driving waveform information is the waveform of the source signal and the common electrode signal applied sequentially by the electronic paper device during the refresh process, and the driving waveform information includes at least one of the following: the driving voltage and reference voltage of various colored particles, the driving frequency, the driving waveform frame and the driving waveform pulse information.

[0119] Among them, the driving voltage and reference voltage of the colored particles are only affected by the material of the electronic paper device. Therefore, the driving voltage and reference voltage of the colored particles in the driving waveform information can be measured before debugging the driving waveform of the electronic paper device; the driving frequency affects the refresh time of the electronic paper device. Since the refresh time in the quality inspection specifications often has an upper limit, the driving frequency in the driving waveform information needs to be set within a reasonable range and is rarely adjusted during the debugging process; the driving waveform framework refers to the voltage sequence used by the driving waveform, which usually includes a balance stage, a shaking stage, and an imaging stage. Each stage consists of at least one stage (balance, shaking, etc.). The imaging stage generally consists of 1-3 stages, and the imaging stage generally consists of 2-4 stages. Each stage includes multiple time-series voltage segments. Each segment can select one of the colored particle drive voltage and the reference voltage. The drive waveform framework can be adjusted during the drive waveform debugging process. When the drive waveform framework needs to be adjusted, the input drive waveform information contains relevant information about the drive waveform framework. The drive waveform pulse information refers to the multiple time-series pulses and cycle numbers of the drive waveform in each stage under the selected drive waveform framework and drive frequency. The drive waveform pulse information can be represented in a matrix form (i.e., a drive waveform pulse matrix) or other forms. Corresponding to the drive waveform framework, it includes the number of pulses and cycles of multiple time sequences. Each value ranges from [0x00, 0xff] (hexadecimal). This drive waveform pulse information is the primary debugging target during the drive waveform debugging process.

[0120] For example, for a three-color electronic paper device of black, white, and red, including a driving voltage for driving black particles (referred to as black voltage), a driving voltage for driving white particles (referred to as white voltage), a driving voltage for driving red particles (referred to as red voltage), and a reference voltage, the black voltage and the white voltage are generally around +15V or -15V, the red voltage is generally between 0V and the black voltage, and the reference voltage is generally around 0V. Before debugging the driving waveform of the three-color electronic paper device, the driving voltage and the reference voltage of the colored particles are determined in advance and are not adjusted during the iterative debugging of the driving waveform; the driving frequency is set before the iterative debugging of the driving waveform and is not adjusted during the iterative debugging of the driving waveform; the red area and the black / white area in the driving waveform framework are usually performed in different stages, each stage includes four time-sequential voltage segments, and each segment can select one of black / white / red / reference voltages. When the driving waveform framework needs to be debugged, the driving waveform framework and driving waveform pulse information of the electronic paper device to be debugged are input into the debugging network as driving waveform information for debugging.

[0121] The debugging network is at least used to generate adjustment information corresponding to the driving waveform information based on the input driving waveform information. The adjustment information is adjustment information for the driving waveform pulse information. The structure of the adjustment information is the same as that of the driving waveform pulse information. For example, when the driving waveform pulse information is a driving waveform pulse matrix, the adjustment information is a driving waveform pulse adjustment matrix. Each value in the driving waveform pulse adjustment matrix represents the adjustment amplitude of the corresponding position in the driving waveform pulse matrix, and the adjustment direction is represented by positive and negative (a positive value represents an upward adjustment, and a negative value represents a downward adjustment).

[0122] The debugging network debugs the driving waveform information based on a reinforcement learning algorithm. In the disclosed embodiment, during the debugging process of the driving waveform of an electronic paper device, the environment is a debugging device used for debugging the driving waveform, the agent is the electronic paper device driver, the first driving waveform information is the status information of the current state, and the adjustment information generated by the debugging network in response to the first driving waveform information is the action to be performed in the current state. The corresponding adjustment information is executed on the first driving waveform information to obtain second driving waveform information, which serves as the status information for the next state. During each iterative debugging process, the debugging network is updated based on the feedback obtained from the interaction with the environment based on the status information of the next state, so that the debugging network is continuously optimized during the iterative process until the target conditions are met.

[0123] In order to enable those skilled in the art to better understand the solution of the present disclosure, the debugging method of the driving waveform of the electronic paper device provided by the embodiment of the present disclosure is described in detail below.

[0124] When specifically implementing step S101, since the imaging of the electronic paper device is greatly affected by the ambient temperature, when performing multiple iterative debugging on the electronic paper device, it is necessary to perform iterative debugging in multiple different temperature ranges, and output a corresponding target driving waveform in each temperature range. Specifically, first, the ambient temperature of the electronic paper device is adjusted so that the ambient temperature is within a plurality of different temperature ranges. Each temperature range is used as a target temperature range, and the driving waveform of the electronic paper device under the target temperature range is iteratively debugged multiple times. The target temperature range is any temperature range among all the temperature ranges. For example, the temperature range of the imaging environment of the electronic paper device is 0-40°C, and the temperature range is divided into multiple different temperature ranges, such as 0°C-10°C, 10°C-20°C, 20°C-30°C, and 30°C-40°C. The ambient temperature of the electronic paper device is adjusted according to each temperature range in turn, and the driving waveform of the electronic paper device is debugged in the ambient temperature of each temperature range.

[0125] In addition, before performing iterative debugging, the debugging device is initialized, and a parameter setting interface of the debugging network is displayed on the display interface of the debugging device. The user sets the update coefficient in the debugging network in advance through the parameter setting interface. The update coefficient is the weight factor required to calculate the loss when the debugging network is updated, and is used to adjust the parameter update process of the debugging network; subsequently, in response to the update coefficient input by the user through the parameter setting interface, the update coefficient of the debugging network is set.

[0126] FIG2 schematically shows a flowchart of each iteration debugging of an electronic paper device driving waveform for executing the method according to the present disclosure. As shown in FIG2 , during each iteration debugging process, the method for debugging the electronic paper device driving waveform has the following steps:

[0127] S1011 , based on the first driving waveform information and the debugging network corresponding to the previous iterative debugging, obtaining the second driving waveform information corresponding to the current iterative debugging.

[0128] FIG3 schematically shows a schematic diagram of the debugging process of the driving waveform of the electronic paper device for executing the method according to the present disclosure. As shown in FIG3 , first, the first driving waveform information in the current state is obtained. The first driving waveform information at least includes the driving waveform pulse information in the current state. The first driving waveform information may also include the driving waveform frame in the current state. The first driving waveform information is the driving waveform information of the previous state obtained after adjusting the adjustment information generated by the debugging network. For example, the driving waveform information in the previous state is s0, and the adjustment information for the driving waveform information s0 is a0. After the pulse waveform is adjusted according to the adjustment information a0 for the driving waveform information s0 in the previous state, the first driving waveform information s in the current state is obtained. Among them, the previous state and the current state can be the driving waveform information of the electronic paper device at two consecutive moments, or can be two different consecutive driving waveform information for the same electronic paper device to be iteratively debugged.

[0129] The first drive waveform information is input into a debugging network. In the embodiment of the present disclosure, the debugging network includes a first sub-network, a second sub-network, a third sub-network, and a fourth sub-network. The first drive waveform information is input into the first sub-network of the debugging network. The first sub-network selects adjustment information for the first drive waveform information (the first adjustment information in FIG. 3 ) based on the first drive waveform information in a current state. The adjustment information has the same structure as the first drive waveform information, and each value thereof corresponds to an adjustment amplitude and adjustment direction for a corresponding position in the first drive waveform information.

[0130] After obtaining adjustment information corresponding to the first drive waveform information, the first subnetwork adjusts the first drive waveform information according to the adjustment information to obtain drive waveform information for the next state as the second drive waveform information. For example, the drive waveform information in the current state is s. The first subnetwork generates adjustment information a corresponding to the input drive waveform information s. After adjusting the pulse waveform of the current drive waveform information s according to the adjustment information a, the first subnetwork obtains the second drive waveform information s′ for the next state.

[0131] S1012: Debug the electronic paper device based on the second driving waveform information.

[0132] After obtaining the second driving waveform information, which is a new state obtained by adjusting the first driving waveform information in the current state according to the adjustment information generated by the debugging network, the embodiment of the present disclosure updates the debugging network by determining whether the second driving waveform information has a positive impact on the environment, so that the debugging network can enhance its ability to obtain the optimal driving waveform during the iterative debugging process.

[0133] Figure 4 schematically shows a debugging diagram of multiple temperature ranges of an electronic paper device driving waveform for executing the method according to the present disclosure. First, the electronic paper device is refreshed based on the second driving waveform information to obtain a first display image. Specifically, the corresponding adjusted driving waveform pulse information is obtained based on the second driving waveform information. When the driving waveform information also includes a driving waveform frame, the adjusted driving waveform frame in the second driving waveform information needs to be obtained. As shown in Figure 4, after the second driving waveform information is obtained through iterative debugging, the driving waveform pulse information, the driving waveform frame, and the pre-adjusted driving voltage, reference voltage, and driving frequency of the colored particles are compiled to obtain an electronic paper device driver corresponding to the second driving waveform information. The electronic paper device driver is burned into a driving device (such as a driving board, etc.) of a debugging device, and the electronic paper device driver is executed to refresh the electronic paper device. The colored particles on the electronic paper device undergo electrophoresis under the action of the driving waveform corresponding to the second driving waveform information to obtain the first display image.

[0134] After acquiring the first display image, the disclosed embodiment uses a first reward parameter value to represent environmental feedback regarding debugging the electronic paper device based on the second drive waveform information, thereby measuring whether the second drive waveform information is capable of positively debugging the electronic paper device. Specifically, optical detection is performed on the first display image to obtain optical measurement values ​​of the first display image under a preset color model. The color of the electronic paper device has a reference optical value under the preset color model. The reference optical value can be a range of optical values ​​of the electronic paper device in the preset color model, and the reference optical value includes a maximum reference optical value and a minimum reference optical value. If the optical measurement value is less than or equal to the maximum reference optical value and greater than or equal to the minimum reference optical value, the optical measurement value is within the range of reference optical values. In this case, it is considered that the electronic paper device can correctly display colors after debugging based on the second driving waveform information, 0 is used as the first reward parameter value, and the corresponding debugging result indicates that the debugging is successful. If the optical measurement value is greater than the maximum reference optical value, the optical measurement value is outside the range of reference optical values. In this case, it is considered that the electronic paper device cannot correctly display colors after debugging based on the second driving waveform information. The difference between the optical measurement value and the maximum reference optical value is used as the first reward parameter value, and the corresponding debugging result indicates that the debugging is unsuccessful. If the optical measurement value is less than the minimum reference optical value, the optical measurement value is outside the range of reference optical values. In this case, it is considered that the electronic paper device cannot correctly display colors after debugging based on the second driving waveform information. The difference between the optical measurement value and the minimum reference optical value is used as the first reward parameter value, and the corresponding debugging result indicates that the debugging is unsuccessful.

[0135] If the debugging result indicates that the debugging is passed, the second driving waveform information is used as the target driving waveform output in the current temperature range, and the debugging process of the current temperature range is ended; if the debugging result indicates that the debugging is not passed, step S1013 is executed to update the debugging network.

[0136] In an optional embodiment, the electronic paper device may be an electronic paper device including multiple colors. At this time, the electronic paper device is refreshed based on the electronic paper device driver corresponding to the second driving waveform information. The multiple different colored particles on the electronic paper device undergo electrophoresis under the action of the driving waveform corresponding to the second driving waveform information, thereby obtaining a second display image, which includes multiple different color areas.

[0137] After acquiring the second display image, a second reward parameter value is used to represent environmental feedback regarding debugging the electronic paper device based on the second drive waveform information, thereby measuring whether the second drive waveform information is capable of positively debugging the electronic paper device. Specifically, optical detection is performed on each color region in the second display image to obtain an optical measurement value corresponding to each color region of the second display image under a preset color model. Each color region of the electronic paper device has a different baseline optical value under the preset color model. Based on the optical measurement value of each color region and the baseline optical value of each color region of the electronic paper device, an optical difference value corresponding to each color region is obtained, and the sum of the optical difference values ​​corresponding to all color regions is used as the second reward parameter value.

[0138] If the second reward parameter value is 0, it is believed that debugging the electronic paper device based on the second driving waveform information can enable each color area of ​​the electronic paper device to display the color correctly, and the debugging result corresponding to the second reward parameter value indicates that the debugging is passed; if the second reward parameter value is not 0, it is believed that debugging the electronic paper device based on the second driving waveform information cannot enable each color area of ​​the electronic paper device to display the color correctly, and the debugging result corresponding to the second reward parameter value indicates that the debugging is unsuccessful, and the parameters of the debugging network need to be updated.

[0139] For example, for a three-color electronic paper device of black, white, and red, the electronic paper device is refreshed based on the electronic paper device driver corresponding to the second driving waveform information, and the electronic paper device is refreshed into a second display image containing three color areas of black, white, and red. Since the red area is mainly determined by the a value, and the black area and the white area are mainly determined by the L value, it is only necessary to obtain the optical measurement value a and the optical measurement value L of each color area. The optical measurement values ​​of the Lab color space are detected for the black area, the white area, and the red area respectively, and the optical measurement value L of the black area is obtained. b 、a b , optical measurement value L of the white area w 、a w , optical measurement value L in the red area r 、a r The range of the reference optical value L of the black area in the three-color electronic paper device is [L b_min ,L b_max ], the range of the reference optical value a is [a b_min ,a b_max ]; the range of the reference optical value L of the white area is [L w_min ,L w_max ], the range of the reference optical value a is [a w_min ,a w_max ]; The range of the reference optical value L in the red area is [Lr_min ,L r_max ], the range of the reference optical value a is [a r_min ,a r_max ].

[0140] The optical difference value is obtained according to the following formula: L b_error =max(max(L b -L b_max ,L b_min -L b ),0) a b_error =max(max(a b -a b_max ,a b_min -a b ),0) L w_error =max(max(L w -L w_max ,L w_min -L w ),0) a w_error =max(max(a w -a w_max ,a w_min -a w ),0) L r_error =max(max(L r -L r_max ,L r_min -L r ),0) a r_error =max(max(a r -a r_max ,a r_min -a r ),0)

[0141] Among them, L b_error is the optical difference value L in the black area, L b is the optical measurement value L of the black area, L b_max is the maximum reference optical value L in the black area, L b_min is the minimum reference optical value L of the black area; a b_error is the optical difference value a in the black area, a b is the optical measurement value a of the black area, a b_max is the maximum reference optical value a in the black area, a b_min is the minimum reference optical value a of the black area; L w_error is the optical difference value L of the white area, L w is the optical measurement value L of the white area, L w_max is the maximum reference optical value L in the white area, L w_min is the minimum reference optical value L of the white area; aw_error is the optical difference value a in the white area, a w is the optical measurement value a of the white area, a w_max is the maximum reference optical value a in the white area, a w_min is the minimum reference optical value a of the white area; L r_error is the optical difference value L in the red area, L r is the optical measurement value L in the red area, L r_max is the maximum reference optical value L in the red area, L r_min is the minimum reference optical value L in the red area; a r_error is the optical difference value a in the red area, a r is the optical measurement value a in the red area, a r_max is the maximum reference optical value a in the red area, a r_min is the minimum reference optical value a in the red area.

[0142] After obtaining the optical difference value of each color area, the second reward parameter value is obtained according to the following formula: reward = -(L b_error +a b_error +L w_error +a w_error +L e_error +a r_error )

[0143] Among them, reward is the second reward parameter value.

[0144] The second reward parameter value calculated according to the above formula is: during the calculation of each optical difference value, when the optical measurement value is between the maximum reference optical value and the minimum reference optical value, the optical difference value is 0; when the optical measurement value is not between the maximum reference optical value and the minimum reference optical value, the optical difference value is greater than 0. When all optical difference values ​​are 0, the second reward parameter value is 0, indicating that the debugging result is passed; when at least one optical difference value is greater than 0, the second reward parameter value is less than 0, indicating that the debugging result is failed.

[0145] It should be noted that the above example is only a specific method provided to enable those skilled in the art to better understand the solution of the present disclosure. The method for obtaining the second reward parameter value can be determined according to actual conditions, and the present disclosure does not limit it here.

[0146] In the embodiment of the present disclosure, during each iterative debugging process, optical detection is performed on the generated second driving waveform information, and environmental feedback of the debugging result of the electronic paper device driving waveform when the first driving waveform information is adjusted according to the adjustment information is obtained as a reward parameter value. Based on the reward parameter value, whether the debugging is passed is measured, and the environmental feedback of the debugging electronic paper device is incorporated into the consideration criteria of the debugging result in the form of a reward parameter value, thereby improving the accuracy of the debugging result.

[0147] S1013: Update the debugging network based on the debugging result.

[0148] When the debugging result indicates that the debugging fails, after obtaining the first reward parameter value, the first driving waveform information, the second driving waveform information, the adjustment information corresponding to the first driving waveform information, and the first reward parameter value are combined into a four-tuple corresponding to the current state and placed into an experience pool. The experience pool includes the four-tuple corresponding to each state, and the experience pool is used to update the debugging network.

[0149] The second driving waveform information is input into the second sub-network. The second sub-network obtains a first expected benefit based on the second driving waveform information and the first driving waveform information. The first expected benefit is used to represent the benefit of the debugging network adjusting the first driving waveform information based on the adjustment information. A preset number of quads are randomly selected from the experience pool to construct a training data set. Since each quad is given a first expected benefit corresponding to the first driving waveform information in each quad when debugging fails, the training data set also corresponds to the same preset number of first expected benefits. Based on these first expected benefits corresponding to the training data set, a first loss is obtained, and the parameters of the first sub-network are updated based on the first loss.

[0150] In an optional implementation, the first loss is obtained according to the following formula:

[0151] Among them, Loss1 is the first loss; m is the preset number of the quadruple; Q(s,a) is the first expected benefit; s is the first driving waveform information; a is the adjustment information corresponding to the first driving waveform information.

[0152] In an optional embodiment, when the debugging result indicates that the debugging fails, the second driving waveform information is input into the third sub-network. The third sub-network generates adjustment information corresponding to the second driving waveform information based on the second driving waveform information and adjusts the second driving waveform information according to the adjustment information. The second driving waveform information and the adjustment information for adjusting the second driving waveform information are input into the fourth sub-network. The fourth sub-network obtains a second expected benefit based on the second driving waveform information, the second driving waveform information, and the corresponding adjustment information (the second driving waveform information and the corresponding adjustment information can be combined to form the driving waveform information for the next state). The second expected benefit is used to represent the benefit of the debugging network adjusting the second driving waveform information based on the adjustment information.

[0153] After constructing the training data set, since each quadruple obtains a second expected return corresponding to the second driving waveform information in each quadruple when debugging fails, the training data set also corresponds to the same preset number of second expected returns. Based on these second expected returns corresponding to the training data set and the first reward parameter value, the overall expected return is obtained. The overall expected return integrates the return of environmental feedback (the first reward parameter value) and the expected return of the debugging network itself (the second expected return). The overall expected return is obtained according to the following formula: y = r + γQ(s′, a′)

[0154] Wherein, y is the overall expected return; Q(s′,a′) is the second expected return; s′ is the second driving waveform information; a′ is the adjustment information corresponding to the second driving waveform information; r is the first reward parameter value; γ is the discount factor.

[0155] Finally, a second loss is obtained based on the overall expected return and the first expected return, and the parameters of the second sub-network are updated based on the second loss.

[0156] In an optional implementation, the second loss is obtained according to the following formula:

[0157] Among them, Loss2 is the second loss; m is the preset number of the quadruple; Q(s,a) is the first expected benefit; s is the first driving waveform information; a is the adjustment information corresponding to the first driving waveform information.

[0158] In an optional embodiment, in order to avoid the non-convergence problem caused by loss oscillation during the debugging process, after the parameters of the first sub-network and the parameters of the second sub-network are updated, the debugging network is updated during each iterative debugging process; and after each preset number of iterative debugging rounds, the parameters of the third sub-network and the fourth sub-network are updated, effectively reducing the problem of non-convergence caused by loss oscillation. After a preset round of iterative debugging, the parameters of the third sub-network are updated based on the updated parameters of the first sub-network; and the parameters of the fourth sub-network are updated based on the updated parameters of the second sub-network. Wherein, the parameters of the third sub-network and the fourth sub-network are updated according to the following formula: w′←σw+(1-σ)w′ θ′←σθ+(1-σ)θ′

[0159] Wherein, w′ is the parameter of the fourth sub-network; w is the parameter of the second sub-network; θ′ is the parameter of the third sub-network; θ is the parameter of the first sub-network; σ is the soft update coefficient.

[0160] Specifically, during each iterative debugging process, a reward parameter value (the first reward parameter value or the second reward parameter value described above) is obtained based on the first driving waveform information of the current state, and a debugging result is obtained based on the reward parameter value. If the debugging result indicates that the debugging fails, the parameters in the debugging network are updated; the updated debugging network is applied to the driving waveform information of the next state, and iterative debugging is repeated until the target condition is met and debugging is terminated.

[0161] The target condition may be that the debugging result indicates that the debugging has passed, and / or the number of iterative debugging reaches a preset threshold. When the debugging result obtained based on the reward parameter value during the iterative debugging process indicates that the debugging has passed, it indicates that the driving waveform information obtained during the debugging process can make the color display of the electronic paper device normal, and the iterative debugging process is stopped, and the driving waveform information obtained this time is used as the target driving waveform for the temperature range; when the debugging result obtained based on the reward parameter value during the iterative debugging process indicates that the debugging has failed, but the number of continuous iterative debugging reaches a preset threshold, and the target driving waveform corresponding to the last iterative debugging is the most accurate driving waveform information within the preset range, the iterative debugging process is stopped, and the driving waveform information obtained this time is used as the target driving waveform for the temperature range.

[0162] In an optional embodiment, when multiple iterative debugging is performed under the target temperature range until the target conditions are met, the target driving waveform corresponding to the last iterative debugging is obtained as the target driving waveform corresponding to the target temperature range, and the target driving waveform obtained by the iterative debugging under the target temperature range is placed in the target driving waveform set.

[0163] As shown in FIG4 , whenever a target driving waveform corresponding to a temperature range is added to the target driving waveform set, it is determined whether the target driving waveform set includes target driving waveforms corresponding to all preset temperature ranges. If the target driving waveform set includes target driving waveforms corresponding to all temperature ranges, the target driving waveform set is used as the driving waveform for each temperature range in actual driving of the electronic paper device, and the target driving waveform set is stored for actual driving of the electronic paper device. If the target driving waveform set does not include target driving waveforms corresponding to all temperature ranges, a temperature range that is not included is selected as the target temperature range, the driving waveform corresponding to the target temperature range is iteratively debugged, and the target driving waveform corresponding to the temperature range is output to the target driving waveform set. The above determination process is repeated until the target driving waveform set includes target driving waveforms corresponding to all temperature ranges.

[0164] When step S103 is specifically implemented, the target driving waveform is used as the driving waveform of the electronic paper device in actual driving, and the electronic paper device is driven according to the target driving waveform. Specifically, based on the target driving waveform, a driving waveform framework and driving waveform pulse information are obtained, wherein the driving waveform framework is used to represent the voltage sequence of the target driving waveform, and the driving waveform pulse information is used to represent the number of pulses and the number of cycles under the driving waveform framework; the driving waveform framework and the driving waveform pulse information are compiled to obtain an electronic paper device driver; and the electronic paper device driver is executed to perform image refresh processing on the electronic paper device according to the target driving waveform to form a first target display image.

[0165] In an optional embodiment, after obtaining the target driving waveform set, since the driving of the electronic paper device is greatly affected by the ambient temperature, in the actual driving process, it is necessary to first obtain the current ambient temperature of the electronic paper device; based on the ambient temperature, determine the debugging temperature segment, and the debugging temperature segment is the temperature segment to which the ambient temperature belongs; based on the debugging temperature segment, determine the target driving waveform set and the target driving waveform for the debugging temperature segment; and perform image refresh processing on the electronic paper device according to the target driving waveform for the debugging temperature segment to form a second target display image.

[0166] In an optional embodiment, the electronic paper device is a first model electronic paper device. After the target driving waveform is used as the driving waveform of the electronic paper device in actual driving, since the target driving waveform can normally display the colors contained in the first model electronic paper device within all preset temperature ranges, when a second model electronic paper device containing the same color type as the first model electronic paper device is used, there is no need to iteratively debug the second model electronic paper device again, and the target driving waveform (or target driving waveform set) corresponding to the first model electronic paper device can be directly reused to drive the second model electronic paper device.

[0167] In order to enable those skilled in the art to more clearly understand the solution of the present disclosure, the debugging method of the driving waveform of the electronic paper device described in the present disclosure is now described in detail through the following embodiments.

[0168] The drive waveform debugging equipment includes a PC, a driver board, an optical measuring instrument, and a constant temperature chamber. During iterative debugging, the e-paper device is connected to the driver board via an FPC cable. The driver board and optical measuring instrument are connected to the PC via a USB cable, forming the main body of the debugging equipment. The main body of the debugging equipment is placed in the constant temperature chamber to complete the debugging equipment. The optical measuring instrument is mounted directly above the e-paper device and can be controlled by the PC to move within a specified space to align the e-paper device for measurement.

[0169] As shown in Figure 4, after the debugging device is connected, a debugging project for the electronic paper device driving waveform is created and initialized on the PC, and a parameter setting interface of the debugging network is displayed on the display interface of the PC. The user can pre-set the update coefficient in the debugging network through this parameter setting interface.

[0170] Driving waveform information for a current state in a current temperature range is obtained as first driving waveform information. When the current state is not the initial state, the driving waveform information for the current state is the driving waveform information for the previous state adjusted based on adjustment information generated by the debugging network. When the current state is the initial state, the driving waveform information for the initial state is used as the first driving waveform information. After obtaining adjustment information corresponding to the first driving waveform information, the first sub-network adjusts the first driving waveform information according to the adjustment information to obtain driving waveform information for the next state as the second driving waveform information.

[0171] Based on the second driving waveform information, the corresponding adjusted driving waveform pulse information is obtained. When the driving waveform information also includes a driving waveform frame, the adjusted driving waveform frame in the second driving waveform information needs to be obtained; the driving waveform pulse information (decimal), the driving waveform frame, and the pre-adjusted driving voltage, reference voltage, and driving frequency of the colored particles are compiled to obtain an electronic paper device driver (hexadecimal) in an AXF file corresponding to the second driving waveform information; the electronic paper device driver is burned into a driver board, and the electronic paper device driver is executed to perform image processing on the electronic paper device. The colored particles on the electronic paper device undergo electrophoresis under the action of the driving waveform corresponding to the second driving waveform information, thereby obtaining a first display image.

[0172] Using a mobile optical measuring instrument on a PC, measure the designated color area of ​​the e-paper device. Display and record the corresponding optical measurement values ​​under the Lab color model. Calculate the first reward parameter value based on the optical reference value, and obtain a debugging result based on the first reward parameter value. If the debugging result indicates that the debugging is successful, the resulting driving waveform information is used as the target driving waveform for the temperature range.

[0173] If the debugging result indicates that the debugging fails, after obtaining the first reward parameter value, the first driving waveform information, the second driving waveform information, the adjustment information corresponding to the first driving waveform information, and the first reward parameter value are combined into a quadruple corresponding to the current state and placed into an experience pool. A preset number of quadruples are randomly selected from the experience pool to construct a training data set. Since each quadruple obtains a first expected return corresponding to the first driving waveform information in each quadruple when debugging fails, the training data set also corresponds to the same preset number of first expected returns. Based on these first expected returns corresponding to the training data set, a first loss is obtained, and the parameters of the first sub-network are updated based on the first loss.

[0174] The second driving waveform information is input into the third sub-network. The third sub-network generates adjustment information corresponding to the second driving waveform information based on the second driving waveform information, and adjusts the second driving waveform information according to the adjustment information. The second driving waveform information and the adjustment information for adjusting the second driving waveform information are input into the fourth sub-network to obtain a second expected return. An overall expected return is obtained based on the second expected returns corresponding to the training data set and the first reward parameter value. Finally, a second loss is obtained based on the overall expected return and the first expected return, and the parameters of the second sub-network are updated based on the second loss.

[0175] After a preset number of iterative debugging rounds, the parameters of the third sub-network are updated based on the updated parameters of the first sub-network; and the parameters of the fourth sub-network are updated based on the updated parameters of the second sub-network.

[0176] The driving waveform information for the next state is input into the updated debugging network, and the above iterative debugging process is repeated until the debugging result indicates that the debugging has passed and / or the number of iterative debugging reaches a preset threshold. The target driving waveform corresponding to the last iterative debugging is used as the target driving waveform for the temperature range. The target driving waveform obtained by iterative debugging for the temperature range (target temperature range) is placed in the target driving waveform set.

[0177] and determining whether the target driving waveform set includes target driving waveforms corresponding to all preset temperature ranges: if the target driving waveform set includes target driving waveforms corresponding to all temperature ranges, using the target driving waveform set as the driving waveform for each temperature range in actual driving of the electronic paper device, and storing the target driving waveform set for actual driving of the electronic paper device; and if the target driving waveform set does not include target driving waveforms corresponding to all temperature ranges, selecting a temperature range that is not included as the target temperature range, iteratively debugging the driving waveform corresponding to the target temperature range, and outputting the target driving waveform corresponding to the temperature range to the target driving waveform set. The above determination process is repeated until the target driving waveform set includes target driving waveforms corresponding to all temperature ranges.

[0178] The present disclosure provides a method for debugging a driving waveform of an electronic paper device, the method comprising: performing multiple iterative debugging on the driving waveform of an electronic paper device to be debugged; when the multiple iterative debuggings meet target conditions, obtaining a target driving waveform corresponding to the last iterative debugging; and using the target driving waveform as the driving waveform of the electronic paper device in actual driving; wherein, during each iterative debugging, based on first driving waveform information and a debugging network corresponding to the previous iterative debugging, second driving waveform information corresponding to the current iterative debugging is obtained, the electronic paper device is debugged based on the second driving waveform information, and the debugging network is updated based on the debugging result; wherein the debugging network is at least used to obtain adjustment information for adjusting the first driving waveform information based on the input first driving waveform information, and the second driving waveform information is obtained based on the adjustment information and the first driving waveform information.

[0179] The present invention discloses a debugging network architecture based on reinforcement learning, which automatically adjusts the driving waveform and obtains feedback on the debugging of the driving waveform of the electronic paper device after the adjusted driving waveform, so as to iteratively update the debugging network, avoid the high trial and error cost caused by debugging through brute force, and enable the debugging of the driving waveform of the electronic paper device to be carried out in a process-oriented manner.

[0180] Based on the same inventive concept, an embodiment of the present disclosure provides a device for debugging an electronic paper device driving waveform. FIG5 schematically shows a device for debugging an electronic paper device driving waveform for executing the method of the present disclosure. As shown in FIG5 , the device includes:

[0181] An iterative debugging module, configured to perform multiple iterative debugging on a driving waveform of an electronic paper device to be debugged;

[0182] A judgment module, configured to obtain a target driving waveform corresponding to the last iteration debugging when the multiple iteration debuggings meet the target condition;

[0183] a driving waveform acquisition module, configured to use the target driving waveform as the driving waveform of the electronic paper device in actual driving;

[0184] A single iteration module is configured to, during each iterative debugging, obtain second driving waveform information corresponding to the current iterative debugging based on the first driving waveform information and debugging network corresponding to the previous iterative debugging, debug the electronic paper device based on the second driving waveform information, and update the debugging network based on the debugging result; wherein the debugging network is configured to obtain adjustment information for adjusting the first driving waveform information based on the input first driving waveform information, and the second driving waveform information is obtained based on the adjustment information and the first driving waveform information.

[0185] In an optional implementation, the single iteration module includes:

[0186] A first display submodule, configured to perform image refresh processing on the electronic paper device based on the second driving waveform information to obtain a first display image;

[0187] a first detection submodule, configured to perform optical detection on the first display image and obtain an optical measurement value corresponding to the first display image;

[0188] The first result acquisition submodule is configured to acquire the debugging result based on the optical measurement value and a reference optical value of the electronic paper device.

[0189] In an optional implementation, the single iteration module includes:

[0190] a first reward submodule, configured to obtain a first reward parameter value based on the optical measurement value and the reference optical value, wherein the first reward parameter value is used to represent environmental feedback when the first driving waveform information is adjusted according to the adjustment information;

[0191] The second result acquisition submodule is configured to determine the debugging result based on the first reward parameter value.

[0192] In an optional embodiment, the first reward submodule includes:

[0193] a first reward obtaining unit, configured to set 0 as the first reward parameter value if the optical measurement value is less than or equal to the maximum reference optical value and greater than or equal to the minimum reference optical value;

[0194] a second reward obtaining unit, configured to use a difference between the optical measurement value and the maximum reference optical value as the first reward parameter value if the optical measurement value is greater than the maximum reference optical value;

[0195] The third reward obtaining unit is configured to use a difference between the optical measurement value and the minimum reference optical value as the first reward parameter value if the optical measurement value is less than the minimum reference optical value.

[0196] In an optional implementation, the single iteration module includes:

[0197] a second display submodule, configured to perform image refresh processing on the electronic paper device based on the second driving waveform information to obtain a second display image, where the second display image includes a plurality of color areas;

[0198] A second detection submodule is configured to perform optical detection on each color region to obtain an optical measurement value corresponding to each color region;

[0199] a difference acquisition submodule, configured to acquire an optical difference value corresponding to each color region based on the optical measurement value corresponding to each color region and a reference optical value of each color region;

[0200] The third result acquisition submodule is configured to determine the debugging result based on the optical difference values ​​corresponding to all color regions.

[0201] In an optional implementation, the third result acquisition submodule includes:

[0202] A second reward unit is configured to use the sum of the optical difference values ​​corresponding to all color areas as a second reward parameter value;

[0203] The third result obtaining unit is configured to determine the debugging result based on the second reward parameter value.

[0204] In an optional implementation, the single iteration module includes:

[0205] a first benefit submodule configured to, when the debugging result indicates that the debugging fails, input the second driving waveform information into the second subnetwork to obtain a first expected benefit, wherein the first expected benefit is used to represent a benefit of the debugging network adjusting the first driving waveform information based on the adjustment information;

[0206] A first updating submodule is configured to update parameters of the first subnetwork based on the first expected benefit.

[0207] In an optional implementation, the single iteration module includes:

[0208] an adjustment submodule, configured to input the second driving waveform information into the third subnetwork to obtain adjustment information for adjusting the second driving waveform information if the debugging result indicates that the debugging fails;

[0209] a second benefit submodule, configured to input the second driving waveform information and the adjustment information for adjusting the second driving waveform information into the fourth subnetwork to obtain a second expected benefit, wherein the second expected benefit is used to represent a benefit of the debugging network adjusting the second driving waveform information based on the adjustment information;

[0210] The second updating submodule is configured to update the parameters of the second sub-network based on the second expected return and the first reward parameter value.

[0211] In an optional implementation, the single iteration module includes:

[0212] a third updating submodule, configured to update parameters of the third subnetwork based on the updated parameters of the first subnetwork;

[0213] The fourth updating submodule is configured to update the parameters of the fourth subnetwork based on the updated parameters of the second subnetwork.

[0214] In an optional implementation, the single iteration module includes:

[0215] An interface display submodule, used to display the parameter setting interface of the debugging network;

[0216] The coefficient setting submodule is used to set the update coefficient of the debugging network in response to the update coefficient input by the user through the parameter setting interface, and the update coefficient is used to adjust the parameter update process of the debugging network.

[0217] In an optional embodiment, the device further includes:

[0218] a parsing module, configured to obtain a driving waveform framework and driving waveform pulse information based on the target driving waveform, wherein the driving waveform framework is used to characterize the voltage sequence of the target driving waveform, and the driving waveform pulse information is used to characterize the number of pulses and the number of cycles under the driving waveform framework;

[0219] A compiling module, configured to compile the driving waveform framework and the driving waveform pulse information to obtain an electronic paper device driver;

[0220] The second target display module is used to execute the electronic paper device driver to perform image refresh processing on the electronic paper device according to the target driving waveform to form a first target display image.

[0221] In an optional embodiment, the device further includes:

[0222] A driving module is configured to drive an electronic paper device of a second model based on the target driving waveform, where the electronic paper device of the second model includes the same color type as the electronic paper device of the first model.

[0223] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0224] The various component embodiments of the present disclosure can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the computing processing equipment according to the embodiments of the present disclosure. The present disclosure can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present disclosure can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0225] For example, FIG6 illustrates a computing and processing device that can implement the methods of the present disclosure. The computing and processing device 100 conventionally includes a processor 120 and a computer program product or computer-readable medium in the form of a memory 110. The memory 110 can be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, a hard disk, or ROM. The memory 110 has storage space for program code for executing any of the method steps described above. For example, the storage space for program code can include individual program codes for implementing various steps in the above method. These program codes can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. Such computer program products are typically portable or fixed storage units. The storage unit can have storage segments, storage space, etc. arranged similarly to the memory 110 in the computing and processing device of FIG6 . The program code can, for example, be compressed in a suitable form. Typically, the storage unit includes computer-readable codes, ie, codes that can be read by a processor such as 120 , which, when executed by a computing processing device, cause the computing processing device to perform the steps of the method described above.

[0226] References herein to "one embodiment," "an embodiment," or "one or more embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Furthermore, please note that instances of the phrase "in one embodiment" do not necessarily all refer to the same embodiment.

[0227] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present disclosure may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0228] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present disclosure may be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0229] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure 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 deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present disclosure.

Claims

1. A method for debugging an electronic paper device driving waveform, It is characterized in that include: For the electronic paper device to be debugged, performing multiple iterations of debugging on the driving waveform of the electronic paper device; When the multiple iterations of debugging meet the target condition, obtaining the target driving waveform corresponding to the last iteration of debugging; Using the target driving waveform as the driving waveform of the electronic paper device in actual driving; Wherein, in each iterative debugging, based on the first driving waveform information and debugging network corresponding to the previous iterative debugging, the second driving waveform information corresponding to the iterative debugging is obtained, the electronic paper device is debugged based on the second driving waveform information, and the debugging network is updated based on the debugging result; The debugging network is at least used to obtain adjustment information for adjusting the first driving waveform information based on the input first driving waveform information, and the second driving waveform information is obtained based on the adjustment information and the first driving waveform information.

2. The method for debugging the driving waveform of the electronic paper device according to claim 1, It is characterized in that Debugging the electronic paper device based on the second driving waveform information includes: Performing image refresh processing on the electronic paper device based on the second driving waveform information to obtain a first display image; performing optical detection on the first display image to obtain an optical measurement value corresponding to the first display image; The debugging result is obtained based on the optical measurement value and a reference optical value of the electronic paper device.

3. The method for debugging the driving waveform of the electronic paper device according to claim 2, It is characterized in that The step of obtaining the debugging result based on the optical measurement value and the reference optical value includes: Based on the optical measurement value and the reference optical value, obtaining a first reward parameter value, wherein the first reward parameter value is used to characterize environmental feedback when the first driving waveform information is adjusted according to the adjustment information; The debugging result is determined based on the first reward parameter value.

4. The method for debugging the driving waveform of the electronic paper device according to claim 3, It is characterized in that The reference optical value includes a maximum reference optical value and a minimum reference optical value. Based on the optical measurement value and the reference optical value, obtaining a first reward parameter value includes: If the optical measurement value is less than or equal to the maximum reference optical value and greater than or equal to the minimum reference optical value, taking 0 as the first reward parameter value; If the optical measurement value is greater than the maximum reference optical value, taking the difference between the optical measurement value and the maximum reference optical value as the first reward parameter value; If the optical measurement value is less than the minimum reference optical value, the difference between the optical measurement value and the minimum reference optical value is used as the first reward parameter value.

5. The method for debugging the driving waveform of the electronic paper device according to claim 1, It is characterized in that The electronic paper device includes multiple colors, and debugging the electronic paper device based on the second driving waveform information includes: Performing image brushing processing on the electronic paper device based on the second driving waveform information to obtain a second display image, wherein the second display image includes a plurality of color areas; Performing optical detection on each color region to obtain an optical measurement value corresponding to each color region; Based on the optical measurement value corresponding to each color area and the reference optical value of each color area, obtaining the optical difference value corresponding to each color area; The debugging result is determined based on the optical difference values ​​corresponding to all color regions.

6. The method for debugging the driving waveform of the electronic paper device according to claim 5, It is characterized in that Determining the debugging result based on the optical difference values ​​corresponding to all color regions includes: The sum of the optical difference values ​​corresponding to all color regions is used as the second reward parameter value; The debugging result is determined based on the second reward parameter value.

7. The method for debugging the driving waveform of the electronic paper device according to claim 3, It is characterized in that The debugging network includes a first sub-network and a second sub-network, wherein the first sub-network is used to output adjustment information for adjusting the first driving waveform information, and the updating of the debugging network based on the debugging result includes: When the debugging result indicates that the debugging fails, the second driving waveform information is input into the second sub-network to obtain a first expected benefit, where the first expected benefit is used to indicate a benefit of the debugging network adjusting the first driving waveform information based on the adjustment information; Based on the first expected benefit, parameters of the first sub-network are updated.

8. The method for debugging the driving waveform of the electronic paper device according to claim 7, It is characterized in that The debugging network further includes a third sub-network and a fourth sub-network, and updating the debugging network based on the debugging result includes: When the debugging result indicates that the debugging fails, inputting the second driving waveform information into the third sub-network to obtain adjustment information for adjusting the second driving waveform information; Inputting the second driving waveform information and the adjustment information for adjusting the second driving waveform information into the fourth sub-network to obtain a second expected benefit, wherein the second expected benefit is used to represent the benefit of the debugging network adjusting the second driving waveform information based on the adjustment information; Based on the second expected return and the first reward parameter value, the parameters of the second sub-network are updated.

9. The method for debugging the driving waveform of the electronic paper device according to claim 8, It is characterized in that The updating of the debugging network based on the debugging result includes: Based on the updated parameters of the first sub-network, updating the parameters of the third sub-network; Based on the updated parameters of the second sub-network, the parameters of the fourth sub-network are updated.

10. The method for debugging the driving waveform of an electronic paper device according to claim 1, It is characterized in that Before acquiring the first driving waveform information, the method further includes: Displaying the parameter setting interface of the debugging network; In response to the update coefficient input by the user through the parameter setting interface, the update coefficient is set for the debugging network, and the update coefficient is used to adjust the parameter update process of the debugging network.

11. The method for debugging the driving waveform of an electronic paper device according to claim 1, It is characterized in that After using the target driving waveform as the driving waveform of the electronic paper device in actual driving, the method further includes: Based on the target driving waveform, acquiring a driving waveform framework and driving waveform pulse information, wherein the driving waveform framework is used to characterize a voltage sequence of the target driving waveform, and the driving waveform pulse information is used to characterize the number of pulses and the number of cycles under the driving waveform framework; Compiling the driving waveform framework and the driving waveform pulse information to obtain an electronic paper device driver; The electronic paper device driver is executed to perform image refresh processing on the electronic paper device according to the target driving waveform to form a first target display image.

12. The method for debugging the driving waveform of an electronic paper device according to claim 1, It is characterized in that The electronic paper device is an electronic paper device of a first model. After the target driving waveform is used as the driving waveform of the electronic paper device in actual driving, the method further includes: Based on the target driving waveform, a second type of electronic paper device is driven, where the second type of electronic paper device and the first type of electronic paper device have the same color type.

13. A debugging device for driving waveform of an electronic paper device, It is characterized in that include: An iterative debugging module, used for iteratively debugging a driving waveform of an electronic paper device to be debugged for multiple times; A judgment module, used for obtaining a target driving waveform corresponding to the last iteration debugging when the multiple iteration debuggings meet the target condition; A driving waveform acquisition module, used to use the target driving waveform as the driving waveform of the electronic paper device in actual driving; A single iteration module is used to obtain, during each iteration debugging, the second driving waveform information corresponding to the iteration debugging based on the first driving waveform information and the debugging network corresponding to the previous iteration debugging, debug the electronic paper device based on the second driving waveform information, and update the debugging network based on the debugging result; wherein the debugging network is at least used to obtain adjustment information for adjusting the first driving waveform information based on the input first driving waveform information, and the second driving waveform information is obtained based on the adjustment information and the first driving waveform information.

14. A computing device, It is characterized in that include: a memory having computer readable code stored therein; as well as One or more processors, when the computer readable code is executed by the one or more processors, the computing processing device executes the debugging method of the driving waveform of the electronic paper device according to any one of claims 1-12.

15. A computer readable medium having a computer program / instructions stored thereon, It is characterized in that When the computer program / instruction is executed by a processor, the method for debugging the driving waveform of an electronic paper device according to any one of claims 1 to 12 is implemented.

Citation Information

Patent Citations

  • Self generation method of driving waveform for electrophoresis display equipment

    CN105575336A

  • Electronic paper drive debugging method, device and computer device based on machine learning

    CN109272948A

  • Electronic paper display device, debugging method and driving method

    CN111599317A

  • Display method and device of electrophoretic particle driving data, equipment and medium

    CN114373430A

  • Debugging method and device for driving waveform of electronic paper equipment, equipment and medium

    CN116682382A