Information entry auxiliary method, device, electronic device and storage medium

By collecting and processing the brainwave signals of the entrant and translating them into text information to correct entry errors, the problem of hand errors in information entry is solved and the accuracy of entry is improved.

CN113204980BInactive Publication Date: 2024-12-06BANK OF CHINA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110643745.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-09
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Long-term input of information is prone to manual errors and lead to errors, which will cause huge losses to the organization or enterprise.

Method used

The brain wave signal of the inscriber is collected, preprocessed and translated into text information, and the text information is used to correct the entered information, so that the information assisted by the deep neural network and text translation model can be used to realize the information auxiliary input.

Benefits of technology

Reduce or even avoid the probability of information entry errors and improve entry accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113204980B_ABST
    Figure CN113204980B_ABST
Patent Text Reader

Abstract

The present invention provides an information entry auxiliary method, device, electronic device and storage medium, which can collect the brain wave signal of the person entering the data, and translate it into corresponding text information after preprocessing, and then make corrections to the text information actually entered by the person entering the data based on the text information. Based on the present invention, the auxiliary entry of text can be realized, the probability of error in information entry can be reduced or even avoided, and the accuracy of entry can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of software technology, and more specifically, to an information entry auxiliary method, device, electronic equipment and storage medium. Background Art

[0002] With the popularization of computer technology, a large amount of information needs to be entered into computers. However, long-term information entry will inevitably lead to manual errors, which will cause huge losses to organizations or enterprises. Summary of the invention

[0003] In view of this, in order to solve the above problems, the present invention provides an information entry auxiliary method, device, electronic device and storage medium, and the technical solution is as follows:

[0004] One aspect of the present invention provides an information entry auxiliary method, the method comprising:

[0005] Collecting brain wave signals of the input person and preprocessing the brain wave signals;

[0006] translating the preprocessed brain wave signal into first text information;

[0007] The second text information entered by the inputter is corrected using the first text information.

[0008] Preferably, the preprocessing of the brain wave signal includes:

[0009] Performing filtering processing on the brain wave signal;

[0010] Downsampling the filtered EEG signal;

[0011] Normalize the downsampled EEG signal.

[0012] Preferably, the translating the preprocessed brain wave signal into the first text information includes:

[0013] Retrieving a text translation model, wherein the text translation model is obtained by training a deep neural network using a preset brain wave signal as a sample and aiming to make a text prediction result of the sample close to a text annotation result of the sample;

[0014] The preprocessed brain wave signal is input into the text translation model, and the first text information output by the text translation model is obtained.

[0015] Preferably, the deep neural network comprises:

[0016] Continuous wavelet transform layer, CNN autoencoder, inverse continuous wavelet transform layer, RNN encoder and RNN decoder.

[0017] Preferably, the using the first text information to modify the second text information entered by the inputter includes:

[0018] Converting the first text information into a first time series according to the acquisition time of the brain wave signal;

[0019] Converting the second text information into a second time series according to the input time of the second text information;

[0020] Calculating the similarity between the first time series and the second time series;

[0021] If the similarity satisfies the corresponding correction condition, the first text information is outputted so that the inputter can correct the second text information based on the first text information.

[0022] Preferably, calculating the similarity between the first time series and the second time series includes:

[0023] Divide the first time series and the second time series into multiple time periods, where each time period corresponds to a first sub-time series and a second sub-time series, the first sub-time series is a partial sequence of the first time series, and the second sub-time series is a partial sequence of the second time series;

[0024] For each of the multiple time periods, calculating the similarity between the first sub-time series and the second sub-time series in the time period;

[0025] Correspondingly, if the similarity meets the corresponding correction condition, outputting the first text information includes:

[0026] If the similarity corresponding to the time period satisfies the correction condition, the text information corresponding to the first sub-time series in the time period is output.

[0027] Another aspect of the present invention provides an information entry auxiliary device, the device comprising:

[0028] The acquisition module is used to acquire the brain wave signals of the input person and pre-process the brain wave signals;

[0029] A translation module, used for translating the preprocessed brain wave signal into first text information;

[0030] The correction module is used to correct the second text information entered by the inputter by using the first text information.

[0031] Preferably, the translation module is specifically used for:

[0032] A text translation model is retrieved, wherein the text translation model is obtained by training a deep neural network with a preset brain wave signal as a sample and a goal of making a text prediction result of the sample close to a text annotation result of the sample; the preprocessed brain wave signal is input into the text translation model, and the first text information output by the text translation model is obtained.

[0033] Another aspect of the present invention provides an electronic device, comprising: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used to implement any one of the information entry assistance methods.

[0034] Another aspect of the present invention provides a storage medium, wherein the storage medium stores computer executable instructions, and the computer executable instructions are used to execute any one of the information entry auxiliary methods.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention provides an information entry auxiliary method, device, electronic device and storage medium, which can collect the brain wave signal of the person entering the data, and translate it into corresponding text information after preprocessing, and then make corrections to the text information actually entered by the person entering the data based on the text information. Based on the present invention, the auxiliary entry of text can be realized, the probability of error in information entry can be reduced or even avoided, and the accuracy of entry can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0038] Figure 1 A method flow chart of an information entry auxiliary method provided by an embodiment of the present invention;

[0039] Figure 2 A partial method flow chart of the information entry auxiliary method provided by an embodiment of the present invention;

[0040] Figure 3 A flowchart of another part of the information entry auxiliary method provided by an embodiment of the present invention;

[0041] Figure 4A flowchart of another part of the information entry auxiliary method provided by an embodiment of the present invention;

[0042] Figure 5 A schematic diagram of the structure of an information entry auxiliary device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0045] See also Figure 1 As shown in the method flow chart, an embodiment of the present invention provides an information entry auxiliary method, which includes the following steps:

[0046] S10, collecting the brain wave signals of the input person and preprocessing the brain wave signals.

[0047] In the embodiment of the present invention, brain waves, namely EEG, are a method of recording brain activity using electrophysiological indicators. When the brain is active, the postsynaptic potentials of a large number of neurons are summed up. It records the changes in electric waves during brain activity and is the overall response of the electrophysiological activity of brain nerve cells on the cerebral cortex or scalp surface.

[0048] When entering text information, the user can collect brain wave signals by wearing an electrode cap. Generally speaking, the electrode cap contains multiple electrodes, which are arranged at different positions of the user's brain to collect brain wave signals at corresponding positions.

[0049] Furthermore, to ensure the validity of the brain wave signal, in the embodiment of the present invention, the brain wave signal may be amplified first and then filtered to filter out clutter and interference waves of the amplified brain wave signal.

[0050] In order to improve the usability of brain wave signals, in the specific implementation process, the "pre-processing of brain wave signals" in step S10 can be performed by the following steps, and the method flow chart is as follows: Figure 2 As shown:

[0051] S101, filtering the brain wave signal.

[0052] In the embodiment of the present invention, filtering is an operation to filter out a specific frequency band in a signal, which is an important measure to suppress and prevent interference. The inventors have found through verification that the frequency of the brain wave signal related to the present invention is mainly within 70Hz-150Hz, so a 70Hz-150Hz Hann window bandpass filter can be used to filter out irrelevant frequency bands.

[0053] S102, downsampling the filtered brain wave signal.

[0054] In the embodiment of the present invention, downsampling refers to a process of reducing the sampling rate of a signal in the field of digital signal processing, and the sampling rate refers to the number of samples extracted from a continuous signal per second to form a discrete signal.

[0055] In order to improve the calculation efficiency and ensure the real-time performance of the calculation, the present invention performs downsampling processing on the EEG signal. Excessive downsampling will cause frequency band aliasing. The inventor has found through verification that the downsampling rate in the present invention is more suitable when it is reduced to 200Hz.

[0056] It should be noted that in the embodiment of the present invention, the order of filtering and downsampling cannot be changed. Once downsampling is performed first and then filtering, the frequency cannot be reduced to 200 Hz or frequency band aliasing may occur.

[0057] S103, normalizing the down-sampled brain wave signal.

[0058] In the embodiment of the present invention, normalization refers to mapping the amplitude of the brain wave signal to between (-1, +1). In order to prevent accidental factors from interfering with the brain wave, a normalization operation is adopted. It should be noted that if the normalization and downsampling steps are reversed, a lot of computing power will be wasted and computing efficiency will be reduced.

[0059] S20, translating the preprocessed brain wave signal into first text information.

[0060] In the embodiment of the present invention, a text translation model may be used to process the brain wave signal to obtain text information translated from the brain wave signal, namely, the first text information.

[0061] In the specific implementation process, step S20 "translating the preprocessed brain wave signal into the first text information" can adopt the following steps, and the method flow chart is as follows Figure 3 As shown:

[0062] S201, calling up a text translation model, wherein the text translation model is obtained by training a deep neural network using a preset brain wave signal as a sample and aiming to make the text prediction result of the sample close to the text annotation result of the sample.

[0063] S202: Input the preprocessed brain wave signal into a text translation model, and obtain first text information output by the text translation model.

[0064] In an embodiment of the present invention, when training a text translation model, a deep learning network (DNN) as its basic model can be formed by a combination of three main algorithms: a continuous wavelet transform algorithm, a convolutional neural network (CNN), and a recurrent neural network (RNN). Therefore, the text translation model is a DNN model, and the DNN model is used to encode and decode the brain wave signal to obtain the first text information. It should be noted that the training process of the text translation model belongs to the traditional machine learning training process, which will not be repeated here.

[0065] Furthermore, in order to adapt to the application scenarios of the present invention, the embodiment of the present invention further constructs a deep neural network. Specifically, the deep neural network includes: a continuous wavelet transform layer, a CNN autoencoder, an inverse continuous wavelet transform layer, an RNN encoder and an RNN decoder.

[0066] In the embodiment of the present invention, the electrode cap has multiple electrodes, so the collected brain wave signals are multi-channel. Therefore, the present invention can select the brain wave signal of one channel from multiple channels through a genetic algorithm as a sample for this iterative training of the deep neural network.

[0067] Specifically, according to the acquisition time, the EEG signal can exist in the form of a time series. Therefore, the continuous wavelet transform layer can convert the time series signal into a time-frequency signal through continuous wavelet transform. Then, the CNN autoencoder can remove the noise in the time-frequency signal output by the continuous wavelet transform layer. Furthermore, the inverse continuous wavelet transform layer converts the time-frequency signal output by the CNN autoencoder into a time series signal through inverse continuous wavelet transform. Furthermore, the RNN encoder converts the time series signal output by the inverse continuous wavelet transform layer into a time series language feature. Finally, the RNN decoder translates the language feature output by the RNN encoder into language.

[0068] It should be noted that: 1) Encoding and decoding are relative concepts, and are essentially the conversion from one form of information representation to another.

[0069] 2) For the use of genetic algorithms to screen input channels. In the process of multi-channel EEG analysis, not all channels are relevant to the target task. It is unreliable and impossible to use manual screening methods for a large number of channels. Therefore, genetic algorithms are used for feature screening.

[0070] 3) Use CNN autoencoder to filter out time-frequency spectrum noise. Since the language factor is limited, it should correspond to the limited time-frequency spectrum state of EEG. CNN is a good image recognition model, so it has good processing performance for two-dimensional spectrum. Therefore, the time-frequency spectrum is recognized as syllable features through CNN encoder, and then the syllable features are converted into time-frequency spectrum with lower noise through CNN decoder.

[0071] 4) RNN has better time series signal processing capabilities than CNN, so the RNN encoder is further used to translate the time series signal into time series language features, and then the RNN decoder is used to convert the language time series features into language text.

[0072] S30: using the first text information to modify the second text information entered by the inputter.

[0073] In the embodiment of the present invention, the text information entered by the inputter through an input medium such as a keyboard, a touch screen, etc., i.e., the second text information, can be compared with the first text information to determine whether there is a difference between the inputter's idea and the actual input. If there is a difference between the two, the inputter can be reminded to ensure that the inputter can modify the input content in time, thereby reducing the workload of modification after the input is completed. In practical applications, the second text information can be displayed on one side of the input box of the inputter, thereby prompting the inputter to modify.

[0074] Of course, if there is no difference between the inputter's idea and the actual input, it means that no auxiliary input is required and no operation is performed at this time.

[0075] In the specific implementation process, step S30 "using the first text information to modify the second text information entered by the inputter" can adopt the following steps, and the method flow chart is as follows: Figure 4 As shown:

[0076] S301, converting first text information into a first time series according to the acquisition time of the brain wave signal.

[0077] In an embodiment of the present invention, for the brain wave signals collected by the electrode cap, text translation can be performed on them according to the order of their collection time to obtain the first text information at different collection times. Thus, the first text information can be converted into a corresponding time series, i.e., a first time series, according to the collection time. The horizontal axis of the first time series is time, and the vertical axis is the first text information.

[0078] S302: Convert the second text information into a second time series according to the input time of the second text information.

[0079] In the embodiment of the present invention, the second text information actually input by the inputter can be converted into a corresponding time series, namely a second time series, according to the input time. The abscissa of the second time series is time and the ordinate is the second text information.

[0080] S303: Calculate the similarity between the first time series and the second time series.

[0081] In the embodiment of the present invention, the current time can be used as a reference to calculate the similarity between the first time series and the second time series within a certain time window. That is, the subsequences of the first time series and the second time series whose acquisition time is within the time window are respectively intercepted, and the similarity between the time series intercepted from the first time series and the time series intercepted from the second time series is further calculated, which can effectively reduce the amount of data processing.

[0082] Furthermore, when calculating the degree of similarity, DWT (dynamic time warping), that is, a dynamic time warping algorithm, can be used to calculate the degree of similarity between two time series.

[0083] It should be noted that the time series in the embodiment of the present invention refers to a series of values ​​of the same statistical indicator arranged in the order of their occurrence time.

[0084] S304: If the similarity level satisfies the corresponding correction condition, the first text information is outputted, so that the inputter can correct the second text information based on the first text information.

[0085] In an embodiment of the present invention, if the degree of similarity is less than the corresponding threshold, it is determined that there is a difference between the first text information and the second text information within the time window. At this time, the part of the first text information located in the time window can be output on one side of the input box of the entrant, thereby prompting the entrant to make modifications.

[0086] In the specific implementation process, step S303 "calculating the similarity between the first time series and the second time series" can adopt the following steps:

[0087] The first time series and the second time series are divided into multiple time periods, where one time period corresponds to a first sub-time series and a second sub-time series, the first sub-time series is a partial sequence of the first time series, and the second sub-time series is a partial sequence of the second time series; for each of the multiple time periods, the similarity between the first sub-time series and the second sub-time series in the time period is calculated.

[0088] In the embodiment of the present invention, whether it is the first time series or the second time series, the intercepted time series within the time window can be further divided into different time periods, such as according to a specified time interval, or according to punctuation marks, which is not limited by the present invention. The first time series corresponds to a first sub-time series in multiple time periods, and the second time series corresponds to a second sub-time series in multiple time periods.

[0089] For a first sub-time series and a second sub-time series that belong to the same time period, the embodiment of the present invention may use a dynamic time warping algorithm to calculate the similarity between the two.

[0090] If the similarity between the first sub-time series and the second sub-time series in a certain period is less than the corresponding threshold, the first text information corresponding to the first sub-time series in the period can be output on one side of the input box of the inputter, thereby prompting the inputter to make modifications.

[0091] The information entry auxiliary method provided by the embodiment of the present invention can collect the brain wave signals of the inputter, and translate them into corresponding text information after preprocessing, and then make corrections to the text information actually input by the inputter based on the text information. Based on the present invention, the auxiliary input of text can be realized, the probability of error in information input can be reduced or even avoided, and the input accuracy can be improved.

[0092] Based on the information entry auxiliary method provided in the above embodiment, an embodiment of the present invention provides a device for executing the above information entry auxiliary method. The structural diagram of the device is shown in FIG. Figure 5 As shown, including:

[0093] The acquisition module 10 is used to acquire the brain wave signals of the input person and pre-process the brain wave signals;

[0094] A translation module 20, used for translating the preprocessed brain wave signal into first text information;

[0095] The correction module 30 is used to correct the second text information entered by the inputter using the first text information.

[0096] Optionally, the acquisition module 10 for preprocessing the brain wave signal is specifically used for:

[0097] The brain wave signal is filtered; the filtered brain wave signal is downsampled; and the downsampled brain wave signal is normalized.

[0098] Optionally, the translation module 20 is specifically used for:

[0099] A text translation model is retrieved, where the text translation model is obtained by training a deep neural network using a preset brain wave signal as a sample and taking a text prediction result of the sample close to a text annotation result of the sample as a goal; the preprocessed brain wave signal is input into the text translation model, and the first text information output by the text translation model is obtained.

[0100] Optionally, a deep neural network includes:

[0101] Continuous wavelet transform layer, CNN autoencoder, inverse continuous wavelet transform layer, RNN encoder and RNN decoder.

[0102] Optionally, the correction module 30 is specifically used for:

[0103] According to the acquisition time of the brain wave signal, the first text information is converted into a first time series; according to the input time of the second text information, the second text information is converted into a second time series; the similarity between the first time series and the second time series is calculated; if the similarity meets the corresponding correction condition, the first text information is output so that the inputter can correct the second text information based on the first text information.

[0104] Optionally, the correction module 30 for calculating the similarity between the first time series and the second time series is specifically used to:

[0105] The first time series and the second time series are divided into a plurality of time periods, wherein one time period corresponds to a first sub-time series and a second sub-time series, the first sub-time series is a partial sequence of the first time series, and the second sub-time series is a partial sequence of the second time series; for each of the plurality of time periods, the similarity between the first sub-time series and the second sub-time series in the time period is calculated;

[0106] Accordingly, if the similarity meets the corresponding correction condition, the correction module 30 for outputting the first text information is specifically configured to:

[0107] If the similarity corresponding to the time period meets the correction condition, the text information corresponding to the first sub-time series under the time period is output.

[0108] It should be noted that the detailed functions of each module of the information entry auxiliary device in the embodiment of the present invention can be found in the corresponding disclosed part of the information entry auxiliary method embodiment, and will not be repeated here.

[0109] The information entry auxiliary device provided by the embodiment of the present invention can collect the brain wave signals of the inputter and translate them into corresponding text information after preprocessing, and then make corrections to the text information actually input by the inputter based on the text information. Based on the present invention, the auxiliary input of text can be realized, the probability of error in information input can be reduced or even avoided, and the input accuracy can be improved.

[0110] Based on the information entry assistance method provided in the above embodiment, an embodiment of the present invention also provides an electronic device, which includes: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used to implement the information entry assistance method.

[0111] Based on the information entry assistance method provided in the above embodiment, an embodiment of the present invention further provides a storage medium, in which computer executable instructions are stored, and the computer executable instructions are used to execute the information entry assistance method.

[0112] The above is a detailed introduction to an information entry auxiliary method, device, electronic device and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for a person skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0113] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0114] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device that includes a series of elements is inherent to the elements, or also includes elements inherent to these processes, methods, articles or devices. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.

[0115] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information entry auxiliary method, characterized in that: The method comprises: Collecting brain wave signals of the input person and preprocessing the brain wave signals; translating the preprocessed brain wave signal into first text information; Using the first text information to modify the second text information entered by the inputter; The translating the preprocessed brain wave signal into the first text information includes: Retrieving a text translation model, wherein the text translation model is obtained by training a deep neural network using a preset brain wave signal as a sample and aiming to make a text prediction result of the sample close to a text annotation result of the sample; Inputting the preprocessed brain wave signal into the text translation model, and acquiring the first text information output by the text translation model; The using the first text information to modify the second text information entered by the inputter includes: Converting the first text information into a first time series according to the acquisition time of the brain wave signal; Converting the second text information into a second time series according to the input time of the second text information; Calculating the similarity between the first time series and the second time series; If the similarity satisfies the corresponding correction condition, the first text information is outputted so that the inputter can correct the second text information based on the first text information.

2. The method according to claim 1, characterized in that The preprocessing of the brain wave signal comprises: Performing filtering processing on the brain wave signal; Downsampling the filtered brain wave signal; Normalize the downsampled EEG signal.

3. The method according to claim 1, characterized in that The deep neural network comprises: Continuous wavelet transform layer, CNN autoencoder, inverse continuous wavelet transform layer, RNN encoder and RNN decoder.

4. The method according to claim 1, characterized in that: The calculating the similarity between the first time series and the second time series includes: Divide the first time series and the second time series into multiple time periods, where each time period corresponds to a first sub-time series and a second sub-time series, the first sub-time series is a partial sequence of the first time series, and the second sub-time series is a partial sequence of the second time series; For each time period of the multiple time periods, calculating the similarity between the first sub-time series and the second sub-time series in the time period; Correspondingly, if the similarity meets the corresponding correction condition, outputting the first text information includes: If the similarity corresponding to the time period satisfies the correction condition, the text information corresponding to the first sub-time series in the time period is output.

5. An information entry auxiliary device, characterized in that: The device comprises: The acquisition module is used to acquire the brain wave signals of the input person and pre-process the brain wave signals; A translation module, used for translating the preprocessed brain wave signal into first text information; A correction module, used for correcting the second text information entered by the inputter using the first text information; The translation module is specifically used for: Retrieving a text translation model, wherein the text translation model is obtained by training a deep neural network with a preset brain wave signal as a sample and a goal of making a text prediction result of the sample close to a text annotation result of the sample; inputting the preprocessed brain wave signal into the text translation model, and obtaining the first text information output by the text translation model; The correction module is specifically used for: Converting the first text information into a first time series according to the acquisition time of the brain wave signal; Converting the second text information into a second time series according to the input time of the second text information; Calculating the similarity between the first time series and the second time series; If the similarity satisfies the corresponding correction condition, the first text information is outputted so that the inputter can correct the second text information based on the first text information.

6. An electronic device, characterized in that: The electronic device comprises: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used to implement the information entry auxiliary method described in any one of claims 1-4.

7. A storage medium, characterized in that: The storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the information entry auxiliary method described in any one of claims 1-4.