An information determination method, apparatus and electronic device

Abstract

The embodiment of the present application discloses a kind of information determination method, the method comprises: to be identified picture is handled, obtains first test paper text;The first test paper text is analyzed, obtains the subject information of the first test paper text and the question type in the first test paper text;The first test paper text is analyzed based on the subject information and the question type, determine the keyword matched with the subject information and the question type.This embodiment of the present application also discloses a kind of information determination device and electronic equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the information determination technology in the field of smart education, and in particular to an information determination method and device and electronic equipment. BACKGROUND

[0002] With the maturity of optical character recognition (OCR) technology, the OCR technology has become an important means for electronic test questions and test question input into a question bank. At present, the OCR technology generally uses the confidence of words and phrases to prompt which words and phrases may not be accurately recognized. However, in the current recognition mode, the words and phrases with low OCR prompt confidence are not necessarily the information that users want to focus on, and the words and phrases that users are more interested in are not prompted when errors occur. For this situation, if the person performing the review does not understand and is not sensitive to the professional field corresponding to the test question, errors may be missed, resulting in errors in the electronic test question. SUMMARY

[0003] Embodiments of the present application provide an information determination method, device and electronic equipment, which solve the problem of inaccurate error prompt for information that users focus on when performing electronic test questions in related technologies, resulting in errors in the electronic test question.

[0004] The technical solution of the present application is implemented as follows:

[0005] An information determination method, the method comprising:

[0006] processing a to-be-recognized picture to obtain a first test question text;

[0007] analyzing the first test question text to obtain subject information to which the first test question text belongs and a type of a question in the first test question text;

[0008] analyzing the first test question text based on the subject information and the type of the question to determine a keyword matching the subject information and the type of the question.

[0009] In the above solution, the analyzing the first test question text to obtain the subject information to which the first test question text belongs and the type of the question in the first test question text comprises:

[0010] performing word segmentation processing on the first test question text by using a natural language processing technology to obtain words in the first test question text;

[0011] analyzing the first test question text based on the words in the first test question text to obtain the subject information to which the first test question text belongs and the type of the question in the first test question text.

[0012] In the scheme, the first test text is analyzed based on the words in the first test text to obtain subject information to which the first test text belongs and a question type of a question in the first test text, and the method comprises:

[0013] A target corpus corresponding to the test question is obtained.

[0014] The first test text is analyzed based on the words in the first test text and the target corpus to determine the subject information and the question type.

[0015] In the scheme, the first test text is analyzed based on the subject information and the question type to determine a keyword matching the subject information and the question type, and the method comprises:

[0016] The type of the word in the first test text is determined, wherein different types of words show different forms.

[0017] The keyword is determined from the words in the first test text based on the type of the word, the subject information to which the first test text belongs, and the question type.

[0018] In the scheme, the keyword is determined from the words in the first test text based on the type of the word, the subject information to which the first test text belongs, and the question type, and the method comprises:

[0019] The type of the word in the first test text is determined, wherein different types of words show different forms.

[0020] In the scheme, the first test text is analyzed based on the subject information and the question type to determine a keyword matching the subject information and the question type, and the method comprises:

[0021] The first test text is analyzed by using a natural language processing technology to obtain sentence meaning information of the first test text.

[0022] Based on the subject information and the question type of the first test text, a target sentence corresponding to incorrect sentence meaning information in the sentence meaning information of the first test text is determined.

[0023] The second keyword is obtained by extracting a word matching a word in the target sentence from the words in the first test text, wherein the keyword further comprises the second keyword.

[0024] In the scheme, the method further comprises:

[0025] The keyword is displayed in the first question text and the second question text included in the image to be identified in a target display manner to remind the user to pay attention to the keyword; wherein the first question text and the second question text correspond to the same question information.

[0026] In the above scheme, the process of processing the image to be recognized to obtain the first test question text includes:

[0027] If it is determined that the second test question text included in the image to be identified has been edited and needs to be reviewed, the image to be identified is processed to obtain the first test question text; wherein, the review process can again determine whether there is erroneous text information in the second test question text.

[0028] An information determining device, the device comprising:

[0029] The processing unit is used to process the image to be recognized to obtain the text of the first test question;

[0030] The first analysis unit is used to analyze the first test question text to obtain the subject information to which the first test question text belongs and the question type in the first test question text;

[0031] The second analysis unit is used to analyze the first test question text based on the subject information and the question type, and to determine keywords that match the subject information and the question type.

[0032] An electronic device, comprising: a processor, a memory, and a communication bus;

[0033] The communication bus is used to realize the communication connection between the processor and the memory;

[0034] The processor is used to execute an information determination program in memory to perform the following steps:

[0035] The image to be identified is processed to obtain the text of the first test question;

[0036] The first test question text is analyzed to obtain the subject information to which the first test question text belongs and the question type in the first test question text;

[0037] Based on the subject information and the question type, the text of the first test question is analyzed to determine keywords that match the subject information and the question type.

[0038] The information determination method, apparatus, and electronic device provided in the embodiments of this application process an image to be recognized to obtain a first test question text. The first test question text is then analyzed to obtain the subject information and question type. Based on the subject information and question type, the first test question text is analyzed to determine keywords matching the subject information and question type. Thus, keywords matching the subject information and question type in the test question text can be determined directly, rather than solely relying on OCR technology. This solves the problem in related technologies where inaccurate error prompts are not provided for information of interest to users during test question digitization, leading to errors in test question digitization and improving the accuracy of test question digitization. Attached Figure Description

[0039] Figure 1 A flowchart illustrating an information determination method provided for an embodiment of this application;

[0040] Figure 2 A flowchart illustrating another information determination method provided for an embodiment of this application;

[0041] Figure 3 A flowchart illustrating yet another information determination method provided for an embodiment of this application;

[0042] Figure 4 A schematic diagram illustrating the display of keywords in an information determination method provided in an embodiment of this application;

[0043] Figure 5 A schematic diagram of the structure of an information determination device provided for an embodiment of this application;

[0044] Figure 6 This is a schematic diagram of the structure of an electronic device provided as an embodiment of this application. Detailed Implementation

[0045] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0046] It should be understood that the phrases "embodiments of this application" or "foreign embodiments" throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, "embodiments of this application" or "in the foreign embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0047] Unless otherwise specified, any step in the embodiments of this application performed by the electronic device may be executed by the processor of the electronic device. It is also worth noting that the embodiments of this application do not limit the order in which the electronic device performs the following steps. Furthermore, the methods used to process data in different embodiments may be the same or different methods. It should also be noted that any step in the embodiments of this application can be executed independently by the electronic device; that is, when the electronic device performs any step in the following embodiments, it may not depend on the execution of other steps.

[0048] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0049] Embodiments of this application provide an information determination method, which can be applied to electronic devices, with reference to... Figure 1 As shown, the method includes the following steps:

[0050] Step 101: Process the image to be recognized to obtain the text of the first test question.

[0051] The image to be recognized can be an image from which information needs to be recognized and processed, and the image includes the text of the second test question that needs to be recognized. Before processing the image to be recognized, it can be acquired first. This image can be stored locally on the electronic device or obtained from another electronic device. In one feasible implementation, the image to be recognized can be obtained by acquiring the text of the second test question to be processed. It should be noted that this acquisition can be performed using the image acquisition device of the electronic device itself or using the image acquisition device of another electronic device.

[0052] In this embodiment of the application, the first test question text can be obtained by recognizing the image to be recognized; wherein, the recognition processing of the image to be recognized can be achieved by using OCR recognition technology.

[0053] Step 102: Analyze the first test question text to obtain the subject information to which the first test question text belongs and the question types in the first test question text.

[0054] In this embodiment of the application, the first test question text can be analyzed based on the words in the first test question text to obtain the subject information to which the first test question text belongs and the question type in the first test question text.

[0055] The subject information of the first test question text can refer to the test subject corresponding to the first test question text. In one feasible implementation, the subject information can include subjects such as mathematics, English, Chinese, physics, chemistry, history, and geography. The question types in the first test question text can refer to the question types that can be included in test questions of different subjects. In one feasible implementation, the question types can include fill-in-the-blank questions, multiple choice questions, application questions, true / false questions, and essay questions.

[0056] Step 103: Analyze the text of the first test question based on the subject information and question type to determine the keywords that match the subject information and question type.

[0057] In this embodiment, keywords can be selected from the words in the first test question text after analyzing the subject information and question type. Specifically, keywords can be determined from the words in the first test question text based on the relationship between the words and the subject information of the first test question text, as well as the relationship between the words and the question type they belong to; alternatively, keywords can also be determined by first obtaining the semantic information of sentences in the first test question text based on the subject information and question type, and then determining the keywords from the words in the first test question text based on the semantic information of those sentences.

[0058] The information determination method provided in the embodiments of this application processes the image to be recognized to obtain a first test question text, analyzes the first test question text to obtain the subject information to which the first test question text belongs and the question type in the first test question text, and analyzes the first test question text based on the subject information and question type to determine keywords that match the subject information and question type. In this way, keywords that match the subject information and question type in the test question text can be determined according to the subject information and question type in the test question text, rather than simply using OCR technology to determine keywords in the test question text. This solves the problem in related technologies that it is impossible to accurately provide error prompts for information of interest to users when digitizing test questions, resulting in errors in the digitization of test questions, and improves the accuracy of digitized test questions.

[0059] Based on the foregoing embodiments, embodiments of this application provide an information determination method, referring to... Figure 2 As shown, the method includes the following steps:

[0060] Step 201: If the electronic device determines that the second test question text included in the image to be recognized has been edited and needs to be reviewed, it processes the image to be recognized to obtain the first test question text.

[0061] The review process can further determine whether there are any erroneous text messages in the second question text.

[0062] In this embodiment, the second test question text included in the image to be recognized has been edited. After the editing is completed, and the second test question text needs to be reviewed, OCR recognition can be performed on the image to be recognized to obtain the first test question text. Editing can refer to a student answering the second test question text, and review can refer to a teacher grading the student's answer; alternatively, editing can refer to the first electronic input of the second test question text, and review can refer to confirming whether there are any errors in the first electronically entered test question text. Of course, editing and review can also refer to other processes that conform to the limitations of this application.

[0063] Step 202: The electronic device uses natural language processing technology to segment the first test question text to obtain the words in the first test question text.

[0064] Natural language processing technology can include Natural Language Processing (NPL); words can refer to the words included in the first test question text; it should be noted that the words included in the first test question text can be obtained by directly using NPL technology to perform word segmentation.

[0065] Step 203: The electronic device analyzes the first test question text based on the words in the first test question text to obtain the subject information to which the first test question text belongs and the question type in the first test question text.

[0066] The subject information of the first test question text and the question type in the first test question text can be obtained based on the relationship between the words in the first test question text and the target corpus corresponding to the test questions.

[0067] Step 203 can be implemented in the following way:

[0068] Step 203a: The electronic device acquires the target corpus corresponding to the test questions.

[0069] The target corpus can be the test questions for all subjects; that is, the test questions for all subjects correspond to one target corpus, meaning the target corpus can be the corpus of test questions for all subjects.

[0070] In this embodiment, the target corpus can be obtained by analyzing test questions from various subjects; alternatively, the target corpus can be obtained by training with a large number of test questions for each subject. The target corpus may include words corresponding to various subjects and question types.

[0071] Step 203b: The electronic device analyzes the first test question text based on the words in the first test question text and the target corpus to determine the subject information to which the first test question text belongs and the question type in the first test question text.

[0072] In this embodiment, words in the first test question text can be matched and analyzed with words included in the target corpus to obtain the subject information and question types of the first test question text. Specifically, the subject to which the first test question text belongs can be determined based on the subject corresponding to the words in the target corpus that match the words in the first test question text; simultaneously, the question types included in the first test question text can be determined based on the question types corresponding to the words in the target corpus that match the words in the first test question text. Correspondingly, based on the questions to which the words corresponding to all determined question types belong, the question type of each question in the first test question text can be determined.

[0073] It should be noted that if the subject corresponding to the word matching the first test question text in the target corpus is mathematics, then the subject of the first test question text is mathematics; if the question type corresponding to the word matching the first test question text in the target corpus is multiple choice, then the question type for determining the word is multiple choice.

[0074] Step 204: The electronic device determines the type of words in the first test question text.

[0075] Different types of words are displayed in different forms.

[0076] The word type can refer to what kind of word it is; in the embodiments of this application, the word type can include the word types corresponding to various subjects such as numbers, Chinese characters, English characters, and chemical characters.

[0077] Step 205: The electronic device identifies keywords from the words in the first test question text based on the word type, the subject information to which the first test question text belongs, and the question type.

[0078] In this embodiment of the application, keywords can be obtained by extracting words that match the subject information and question type of the first test question text from the words included in the first test question text; wherein, keywords can be obtained by extracting words that match the subject information and words that match the question type of the first test question text from the words included in the first test question text respectively.

[0079] It should be noted that the keyword method used in this application, which uses the word type in the test question text, the subject information of the first test question text, and the question type of the first test question text to obtain keywords that match the subject information and question type, determines keywords that are related to the information in the test question text. This makes the determined keywords more representative of the information that users are interested in, and further ensures the accuracy of the digitized test questions.

[0080] It should be noted that the descriptions of the same or corresponding steps in this embodiment and other embodiments can be found in the descriptions of other embodiments, and will not be repeated here.

[0081] The information determination method provided in the embodiments of this application can determine the keywords in the test question text that match the subject information and question type based on the subject information and question type of the test question text, rather than simply using OCR technology to determine the keywords in the test question text. This solves the problem in related technologies that it is impossible to accurately provide error prompts for information of interest to users when digitizing test questions, which leads to errors in the digitization of test questions, and improves the accuracy of digitization of test questions.

[0082] Based on the foregoing embodiments, embodiments of this application provide an information determination method, referring to... Figure 3 As shown, the method includes the following steps:

[0083] Step 301: If the electronic device determines that the second test question text included in the image to be recognized has been edited and needs to be reviewed, it processes the image to be recognized to obtain the first test question text.

[0084] The review process can further determine whether there are any erroneous text messages in the second question text.

[0085] Step 302: The electronic device uses natural language processing technology to segment the first test question text to obtain the words in the first test question text.

[0086] Step 303: The electronic device acquires the target corpus corresponding to the test questions.

[0087] Step 304: The electronic device analyzes the first test question text based on the words in the first test question text and the target corpus to determine the subject information to which the first test question text belongs and the question type in the first test question text.

[0088] Step 305: The electronic device determines the type of words in the first test question text.

[0089] Different types of words are displayed in different forms.

[0090] Step 306: The electronic device extracts words from the first test question text whose word type matches the subject information of the first test question text, and words whose word type matches the question type of the question in which the word is located, to obtain the first keyword.

[0091] The keywords include the primary keyword.

[0092] In this embodiment, a first sub-keyword can be obtained by filtering words from the first test question text whose word type matches the subject information of the first test question text. Simultaneously, a second sub-keyword can be obtained by filtering words from the first test question text whose word type matches the question type of the question in the first test question text. The first keyword includes both the first and second sub-keywords. That is, if the subject information of the first test question text is physics, then the first sub-keyword obtained from the first test question text can include words matching the physics subject. In one feasible implementation, the first sub-keyword can include formulas, physical symbols, etc., from physics formulas. If the question type of the word in the first test question text is a true / false question, then the second sub-keyword can include words matching true / false questions. In one feasible implementation, the second sub-keyword can include words such as "yes / no," "correct / incorrect," and "definite."

[0093] Step 307: The electronic device uses natural language processing technology to analyze the text of the first test question and obtain the semantic information of the first test question text.

[0094] The semantic information of the first test question text can be obtained by first using NPL technology to segment the first test question text into sentences, obtaining the sentences included in the first test question text, and then analyzing each sentence to obtain the semantic information of the first test question text.

[0095] Step 308: Based on the subject information and question type of the first test question text, the electronic device determines the target sentence corresponding to the sentence with an error in the sentence meaning information of the first test question text.

[0096] In this embodiment, the accuracy of the semantic information of the first test text can be determined by combining the subject information and question type of the first test text, and then the target sentence of the first test text can be obtained based on the accuracy of the semantic information. Specifically, the accuracy of the sentence information can be determined based on the matching degree between the semantic information and the subject information and question type of the first test text; if the semantic information does not match the subject information and question type of the first test text, the semantic information is considered to be incorrect; if the semantic information matches the subject information and question type of the first test text, the semantic information is considered accurate. In one feasible implementation, if the subject information of the first test text is English, the question type is a true / false question, and the determined semantic information is about which of the following categories a chemical formula belongs to, then the semantic information can be considered to be incorrect, and this sentence is the target sentence.

[0097] It should be noted that the accuracy of the semantic information in the first test question text can also be determined based on the subject information and question type of the first test question text, as well as the confidence level of the words in the identified sentences. Thus, because the accuracy of the semantic information in the first test question text is determined by incorporating word confidence levels, the second keywords identified based on the accuracy of the semantic information are more aligned with user interests, thereby ensuring the accuracy of the digitized test questions.

[0098] Step 309: The electronic device extracts words from the first test text that match the words in the target sentence to obtain the second keyword.

[0099] The keywords also include secondary keywords.

[0100] In this embodiment, the second keyword can be obtained by filtering words from the first test question text that match words in the target sentence. Furthermore, this embodiment can also determine the second keyword in the first test question text based on the semantic information of the first test question text, thus broadening the range of determined keywords and further reducing errors in the digitization of test questions.

[0101] It should be noted that steps 307-309 can be executed after steps 305-306, or simultaneously with steps 305-306. Of course, steps 307-309 and steps 305-306 can also be executed in an OR relationship; that is, only steps 307-309 can be executed without steps 305-306, or only steps 305-306 can be executed without steps 307-309. In other words, the first approach of determining the first keyword from the words in the first test question text based on word type, subject information, and question type, and the second approach of determining the second keyword from the words in the first test question text based on sentence meaning information, subject information, and question type, can be executed simultaneously, or only one of the first and second approaches can be executed; or the second approach can be executed after the first approach.

[0102] Based on the foregoing embodiments, in other embodiments of this application, the method further includes the following steps:

[0103] Step 310: The electronic device displays keywords in the first test question text and the second test question text included in the image to be recognized in a target display mode to remind the user to pay attention to the keywords.

[0104] The first and second test question texts correspond to the same test question information.

[0105] In this embodiment of the application, the first test question text and the second test question text refer to the same test question information. The first test question text can be obtained by recognizing the image to which the second test question text belongs.

[0106] In other embodiments of this application, identified keywords can be displayed in a targeted display manner within the first and second test question texts, thereby more clearly drawing the user's attention to these keywords. The targeted display manner can include highlighting, bolding, or different color markings, etc., making the keywords prominently displayed in both the first and second test question texts, allowing users to spot them at a glance. Furthermore, this ensures that users can easily focus on these keywords when reviewing the first and second test question texts, improving review efficiency and thus enhancing the accuracy and efficiency of electronic processing.

[0107] It should be noted that the descriptions of the same or corresponding steps in this embodiment and other embodiments can be found in the descriptions of other embodiments, and will not be repeated here.

[0108] The information determination method provided in the embodiments of this application can determine the keywords in the test question text that match the subject information and question type based on the subject information and question type of the test question text, rather than simply using OCR technology to determine the keywords in the test question text. This solves the problem in related technologies that it is impossible to accurately provide error prompts for information of interest to users when digitizing test questions, resulting in errors in the digitization of test questions.

[0109] Based on the foregoing embodiments, in other embodiments of this application, the first and second test question texts are the same test question information about chemistry. In this case, after segmenting the first test question text, the resulting words can include chemical formulas and chemical symbols. Based on these words (chemical formulas and formula symbols) and the target corpus, the subject information of the first test question text is determined to be chemistry. Simultaneously, based on words such as "calculation," "option," and "judgment," the question type can be determined to include calculation questions, fill-in-the-blank questions, multiple-choice questions, and judgment questions. Furthermore, the word type is determined to be chemical symbols. Then, based on the word type, subject information, and question type, words related to chemical formulas and chemical symbols can be determined from the words in the first test question text as the first keyword. Simultaneously, based on the sentence meaning information, subject information (chemistry), and question type (multiple-choice question) of the first test question text, the second keyword can be determined. In one feasible implementation, such as... Figure 4 As shown, the first keyword can include "CaC2+2H2O-C2H2↑+Ca(OH)2", "CH2=CH2+Br2→CH2BrCH2", and "baking soda", while the second keyword can include the word "physics"; and, as Figure 4 As shown, the first keyword and the second keyword can be displayed in bold in both the first and second question texts.

[0110] Based on the foregoing embodiments, embodiments of this application provide an information determining device, which can be applied to... Figures 1 to 3 In the information determination method provided in the corresponding embodiment, refer to Figure 5 As shown, the device 4 may include: a processing unit 41, a first analysis unit 42, and a second analysis unit 43, wherein:

[0111] Processing unit 41 is used to process the image to be recognized to obtain the first test question text;

[0112] The first analysis unit 42 is used to analyze the first test text to obtain the subject information to which the first test text belongs and the question type in the first test text;

[0113] The second analysis unit 43 is used to analyze the text of the first test question based on subject information and question type, and to determine keywords that match the subject information and question type.

[0114] In other embodiments of this application, the first analysis unit 42 is further configured to perform the following steps:

[0115] Natural language processing technology was used to segment the text of the first test question to obtain the words in the text of the first test question.

[0116] By analyzing the words in the first test question text, we can obtain the subject information to which the first test question text belongs and the question type in the first test question text.

[0117] In other embodiments of this application, the first analysis unit 42 is further configured to perform the following steps:

[0118] Obtain the target corpus corresponding to the test questions;

[0119] Based on the words in the first test question text and the target corpus, the subject information of the first test question text and the question type in the first test question text are determined.

[0120] In other embodiments of this application, the second analysis unit 43 is further configured to perform the following steps:

[0121] Determine the word types in the text of the first test question;

[0122] Different types of words are displayed in different forms;

[0123] Based on the word type, the subject information of the first test question text, and the question type of the questions in the first test question text, keywords are identified from the words in the first test question text.

[0124] In other embodiments of this application, the second analysis unit 43 is further configured to extract words from the first test question text whose word type matches the subject information to which the first test question text belongs, and words whose word type matches the question type of the question in which the word is located, to obtain the first keyword;

[0125] The keywords include the primary keyword.

[0126] In other embodiments of this application, the second analysis unit 43 is further configured to perform the following steps:

[0127] Natural language processing technology was used to analyze the text of the first test question to obtain the sentence meaning information of the first test question text;

[0128] Based on the subject information and question types in the first test text, the target sentences corresponding to the erroneous semantic information in the first test text are identified.

[0129] From the words in the first test question text, extract words that match the words in the target sentence to obtain the second keyword; among them, the keyword also includes the second keyword.

[0130] In other embodiments of this application, the information determining device 4 further includes a display unit 44, wherein:

[0131] Display unit 44 is used to display keywords in a target display manner in the first test question text and the second test question text included in the image to be recognized, so as to remind the user to pay attention to the keywords;

[0132] The first and second test question texts correspond to the same test question information.

[0133] In other embodiments of this application, the processing unit 41 is further configured to process the image to be identified to obtain the first test text when it is determined that the second test text included in the image to be identified has been edited and needs to be reviewed.

[0134] The review process can further determine whether there are any erroneous text messages in the second question text.

[0135] It should be noted that the interaction process between the modules in this embodiment can be referred to Figures 1 to 3 The implementation process of the information determination method provided in the corresponding embodiments will not be described in detail here.

[0136] The information determination device provided in the embodiments of this application can determine the keywords in the test question text that match the subject information and question type based on the subject information and question type of the test question text, rather than simply using OCR technology to determine the keywords in the test question text. This solves the problem in related technologies that it is impossible to accurately provide error prompts for information of interest to users when digitizing test questions, resulting in errors in the digitization of test questions.

[0137] Based on the foregoing embodiments, embodiments of this application provide an electronic device 5, which can be applied to... Figures 1 to 3 In the information determination method provided in the corresponding embodiment, refer to Figure 6 As shown, the electronic device 5 may include: a processor 51, a memory 52, and a communication bus 53, wherein:

[0138] Communication bus 53 is used to realize the communication connection between processor 51 and memory 52;

[0139] The processor 51 is used to execute the information determination program stored in the memory 52 to perform the following steps:

[0140] The image to be identified is processed to obtain the text of the first test question;

[0141] The first test text was analyzed to obtain the subject information to which the first test text belonged and the question types in the first test text;

[0142] The text of the first test question was analyzed based on subject information and question type to identify keywords that match the subject information and question type.

[0143] In other embodiments of this application, the processor 51 is used to execute the analysis of the first test question text stored in the memory 52 to obtain the subject information to which the first test question text belongs and the question type in the first test question text, so as to implement the following steps:

[0144] Natural language processing technology was used to segment the text of the first test question to obtain the words in the text of the first test question.

[0145] By analyzing the words in the first test question text, we can obtain the subject information to which the first test question text belongs and the question type in the first test question text.

[0146] In other embodiments of this application, the processor 51 is used to execute the analysis of the first test question text based on the words in the first test question text stored in the memory 52, to obtain the subject information to which the first test question text belongs and the question type in the first test question text, so as to implement the following steps:

[0147] Obtain the target corpus corresponding to the test questions;

[0148] Based on the words in the first test question text and the target corpus, the subject information of the first test question text and the question type in the first test question text are determined.

[0149] In other embodiments of this application, the processor 51 is used to analyze the first test question text stored in the memory 52 based on subject information and question type, and determine keywords that match the subject information and question type to achieve the following steps:

[0150] From the words in the first test question text, extract words whose type matches the subject information of the first test question text, and words whose type matches the question type of the question in which the word is located, to obtain the first keyword;

[0151] The keywords include the primary keyword.

[0152] In other embodiments of this application, the processor 51 is used to analyze the first test question text stored in the memory 52 based on subject information and question type, and determine keywords that match the subject information and question type to achieve the following steps:

[0153] Natural language processing technology was used to analyze the text of the first test question to obtain the sentence meaning information of the first test question text;

[0154] Based on the subject information and question types in the first test text, the target sentences corresponding to the erroneous semantic information in the first test text are identified.

[0155] The second keyword is obtained by extracting words from the text of the first test question that match the words in the target sentence;

[0156] The keywords also include secondary keywords.

[0157] In other embodiments of this application, the processor 71 may execute the information determination program stored in the memory 72 to further implement the following steps:

[0158] Keywords are displayed in a target-oriented manner within the first question text and the second question text included in the image to be identified, to draw the user's attention to the keywords;

[0159] The first and second test question texts correspond to the same test question information.

[0160] In other embodiments of this application, the processor 51 is used to process the image to be recognized stored in the memory 52 to obtain the first test question text, in order to implement the following steps:

[0161] If it is determined that the second test question text included in the image to be recognized has been edited and needs to be reviewed, the image to be recognized is processed to obtain the first test question text;

[0162] The review process can further determine whether there are any erroneous text messages in the second question text.

[0163] It should be noted that the specific implementation process of the steps executed by the processor in this embodiment can be referred to Figures 1 to 3 The implementation process of the information determination method provided in the corresponding embodiments will not be described in detail here.

[0164] The electronic device provided in the embodiments of this application can determine the keywords in the test question text that match the subject information and question type based on the subject information and question type of the test question text, rather than simply using OCR technology to determine the keywords in the test question text. This solves the problem in related technologies that it is impossible to accurately provide error prompts for information of interest to users when digitizing test questions, resulting in errors in the digitization of test questions.

[0165] Based on the foregoing embodiments, embodiments of this application provide a computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement... Figures 1 to 3 The steps in the information determination method provided in the corresponding embodiment.

[0166] It should be noted that the specific implementation process of the steps executed by the processor in this embodiment can be referred to Figures 1 to 3 The implementation process of the information determination method provided in the corresponding embodiments will not be described in detail here.

[0167] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0168] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0169] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0170] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0171] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. An information determination method, the method comprising: The image to be recognized is processed to obtain the text of the first test question; The first test question text is analyzed to obtain the subject information to which the first test question text belongs and the question type in the first test question text; Based on the subject information and the question type, the text of the first test question is analyzed to determine keywords that match the subject information and the question type; The step of analyzing the first test question text based on the subject information and the question type to determine keywords matching the subject information and the question type includes: Natural language processing technology is used to analyze the first test question text to obtain the sentence meaning information of the first test question text; Based on the subject information and question type of the first test question text, determine the target statement corresponding to the erroneous semantic information in the semantic information of the first test question text; From the words in the first test question text, words that match the words in the target sentence are extracted to obtain the second keyword; wherein, the keyword also includes the second keyword.

2. The method according to claim 1, characterized in that, The analysis of the first test question text to obtain the subject information to which the first test question text belongs and the question types in the first test question text includes: Natural language processing technology is used to segment the first test question text to obtain the words in the first test question text; Based on the words in the first test question text, the subject information to which the first test question text belongs and the question type in the first test question text are obtained.

3. The method according to claim 2, characterized in that, The step of analyzing the first test question text based on the words in the first test question text to obtain the subject information to which the first test question text belongs and the question type in the first test question text includes: Obtain the target corpus corresponding to the test questions; The first test question text is analyzed based on the words in the first test question text and the target corpus to determine the subject information and the question type.

4. The method according to claim 2, characterized in that, The step of analyzing the first test question text based on the subject information and the question type to determine keywords matching the subject information and the question type includes: Determine the word types in the first test question text; different word types will be displayed in different forms. Based on the type of the word, the subject information to which the first test question text belongs, and the question type, the keywords are determined from the words in the first test question text.

5. The method according to claim 4, characterized in that, The process of determining the keywords from the words in the first test question text based on the word type, the subject information of the first test question text, and the question type includes: From the words in the first test question text, words whose type matches the subject information to which the first test question text belongs, and words whose type matches the question type of the question in which the word is located, are extracted to obtain the first keyword; wherein, the keyword includes the first keyword.

6. The method according to claim 1, characterized in that, The method further includes: The keyword is displayed in the first question text and the second question text included in the image to be identified in a target display manner to remind the user to pay attention to the keyword; wherein the first question text and the second question text correspond to the same question information.

7. The method according to claim 1, characterized in that, The process of processing the image to be recognized to obtain the first test question text includes: If it is determined that the second test question text included in the image to be identified has been edited and needs to be reviewed, the image to be identified is processed to obtain the first test question text; wherein, the review process can again determine whether there is erroneous text information in the second test question text.

8. An information determining device, characterized in that, The device includes: The processing unit is used to process the image to be recognized to obtain the text of the first test question; The first analysis unit is used to analyze the first test question text to obtain the subject information to which the first test question text belongs and the question type in the first test question text; The second analysis unit is used to analyze the first test question text based on the subject information and the question type, and determine keywords that match the subject information and the question type; The second analysis unit is specifically used to analyze the first test question text using natural language processing technology to obtain the sentence meaning information of the first test question text; Based on the subject information and question type of the first test question text, determine the target statement corresponding to the erroneous semantic information in the semantic information of the first test question text; From the words in the first test question text, words that match the words in the target sentence are extracted to obtain the second keyword; wherein, the keyword also includes the second keyword.

9. An electronic device, characterized in that, The electronic device includes: a processor, a memory, and a communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute an information determination program in memory to perform the following steps: The image to be recognized is processed to obtain the text of the first test question; The first test question text is analyzed to obtain the subject information to which the first test question text belongs and the question type in the first test question text; Based on the subject information and the question type, the text of the first test question is analyzed to determine keywords that match the subject information and the question type; The step of analyzing the first test question text based on the subject information and the question type to determine keywords matching the subject information and the question type includes: The first test text is analyzed using natural language processing technology to obtain the semantic information of the first test text; based on the subject information and question type of the first test text, the target sentence corresponding to the semantic information of the first test text containing errors is determined; from the words of the first test text, words that match the words in the target sentence are extracted to obtain the second keyword; wherein, the keyword also includes the second keyword.

Images