Text review method and system based on multi-display collaboration

Abstract

The present invention relates to the field of text processing technology, specifically to a text review method and system based on multi-display collaboration. First, extract the text content and digitize it, build a terminology word library to store key information words, including qualification, project, technology and price words; use a comparison algorithm to compare the text data with the words in the terminology word library, determine the key information sentences in the text, and color-mark them according to the keyword type; check the format, text and calculation errors in the text, and mark the wrong statements; build a multi-display interface display strategy to display the original text, key information and error information respectively, and review the text; use the RSA asymmetric encryption algorithm to encrypt the reviewed text data, public key encryption, and private key decryption. The present invention can greatly improve the review efficiency and quality.

Description

Technical Field

[0001] The present invention relates to the technical field of text processing, and in particular to a text review method and system based on multi-display collaboration. Background Art

[0002] With the rapid development of information technology, the amount and types of text information are increasing. For all kinds of text information, it is necessary to review and audit to ensure the correctness, compliance and completeness of the text content. Traditional text review methods mainly rely on manual reading and review, which is inefficient and prone to omissions and errors. Therefore, there is an urgent need for an efficient and accurate text review method.

[0003] The rules for text review are complex and changeable, which places high demands on the professional quality of text review experts. Affected by human factors, the review process is prone to arbitrariness and uncontrollability, making it difficult to keep records and trace the entire process. At the same time, there is a lack of effective connection between multiple review links, and data is difficult to share, which seriously affects the timeliness of the review. Reliance on manual operations makes the review process prone to errors, especially when reviewing large amounts of text. The understanding and analysis of text content is completely dependent on manpower. When faced with complex text content, the pressure on human resources is high, and the review results may be subjective.

[0004] At present, emerging technologies such as artificial intelligence, big data analysis, and natural language processing are becoming increasingly mature, providing new ideas and methods for text review. By integrating and applying a variety of intelligent algorithms and models, key information in the text can be extracted and analyzed more efficiently and accurately, and format, text and calculation errors can be automatically identified, greatly improving the efficiency and quality of review.

[0005] In view of this, the present invention proposes a text review method and system based on multi-display collaboration. Summary of the invention

[0006] To achieve the above object, the present invention provides the following technical solution: a text review method based on multi-display collaboration, comprising:

[0007] Extract the language and characters in the text, digitize the language and characters, and convert the language and characters into text data;

[0008] Constructing a text terminology word library, wherein the text terminology word library is used to store key information words in the text; the key information words include qualification type words, project type words, technology type words and price type words;

[0009] Construct a text term comparison algorithm to compare text data with the key information words in the text term database, determine whether the sentences in the text are key information, and mark the key information in the text with different colors according to the type of key words contained in the sentence;

[0010] Check the text for formatting, wording and calculation errors, and mark the text with errors;

[0011] Construct a text review display strategy with multiple display interfaces, use multiple display interfaces to display text information, including displaying the original text, key text information, and text error information, and review the text;

[0012] The reviewed text data is encrypted using the asymmetric encryption algorithm RSA, the text data is encrypted using the public key, and the text data is decrypted using the private key.

[0013] Preferably, the text includes paper text and electronic text; for paper text, the paper text is scanned to generate a PDF format file of the paper text; through optical character recognition (OCR) technology, text information in the PDF format text is extracted, and the extracted text is stored in an electronic document; for electronic text, the electronic file is directly parsed to extract the text content in the electronic text; and both the paper text and the electronic text are converted into text data.

[0014] Preferably, the construction of the text terminology database specifically includes manually presetting key words of qualification type words, project type words, technology type words and price type words in the text; constructing a key word set S, in which there are sub-sets S of different types of words. i ∈S, i represents the word type, S i represents the i-th word type subset in the keyword set; the subset S of each type of word i There is a word S ij ,S ij ∈S i , j represents the specific word number, S ij represents the jth word in the i-th word type subset; the subset word S of all words ij Mapped to the corresponding word vector V ij , V ij Represents the word vector of the jth word in the i-th word type subset of the mapping;

[0015]

[0016] Among them, V is the word vector matrix, representing the text term vocabulary; i∈[1,i0], j∈[1,j0].

[0017] Preferably, the text data is marked as W, and the text data W is split into m0 natural sentences using natural language processing technology. The natural sentence is a complete sentence, and each natural sentence is divided into a natural word sequence, and the natural word sequence data is mapped to natural word vector data:

[0018]

[0019] Among them, n1 to For natural sentences The number of natural words contained; m∈[1,m0]; is the nth natural sentence in the mth natural sentence in the text data W m natural word vectors; compare each natural word vector data with the word vector in the text term vocabulary, if there is That is, if the natural words divided are the same words in the text terminology library, then the mark The natural sentence is the key information of the text;

[0020] Using the cosine similarity comparison algorithm, compare and V ij and set the similarity threshold θ. If:

[0021]

[0022] in, Representation vector The modulus of ||V ij || represents vector V ij Model;

[0023] Then judge V ij The similarity vector of the two vectors means that the words represented by the two vectors are similar words; when V ij When the similarity vector of The natural sentence is the key information of the text;

[0024] Extract key information from the text and annotate it with color, setting different annotation colors for the same and similar words in the text terminology dictionary.

[0025] Preferably, the acquired text is converted into text data, and the text content is divided into different paragraphs and parts, including titles, texts and tables, according to the structure and format of the text;

[0026] Check text for format errors, predefine format requirements, including font, font size, line spacing, and paragraph indentation, use regular expressions to match text content, and check whether the text content meets the defined format requirements;

[0027] Check the text for textual errors using the Aspell spelling check library and the LanguageTool grammar check library;

[0028] Check the text for calculation errors. Use regular expressions to extract numbers, amounts, and calculation formulas from the text. Use the MathPix formula parsing library to parse the extracted formulas. Calculate the extracted numbers and formulas. Compare the calculation results with the calculation data in the text to verify whether the text calculation results are correct.

[0029] When formatting, text, and calculation errors are found in the text, the errors are marked.

[0030] Preferably, a text review display strategy of multiple display interfaces is constructed, and a first display interface, a second display interface, a third display interface, and a fourth display interface are constructed; the annotation results of the original text, the key information of the text, and the error information of the text are displayed in different display interfaces, and the text is reviewed through the display interfaces;

[0031] Displaying the original text in the first display interface, the displayed original text is in PDF format for paper text and in electronic format for electronic text;

[0032] Displaying the text key information in the second display interface and setting the display priority of the text key information, setting the text key information containing the same words in the text terminology dictionary as the first display priority, and setting the text key information containing similar words in the text terminology dictionary as the second display priority; the first display priority is higher than the second display priority, and under the same priority, the text key information is displayed in descending order according to the number of the same words and similar words in the text terminology dictionary contained in the text key information in the second display interface;

[0033] Displaying error messages in the text in the third display interface, arranging and displaying the error messages in the order in which they appear in the text data, and confirming the displayed error messages during review;

[0034] In the fourth display interface, the text is reviewed and the score and review result of the text are input.

[0035] Preferably, the reviewed text is encrypted using an asymmetric encryption algorithm RSA, and a public key (e, b) and a private key (d, b) are generated using the RSA algorithm, the public key is used for encryption, and the private key is used for decryption;

[0036] Select prime numbers p and q, calculate b=pq, b is the modulus of the RSA key, used for encryption and decryption process calculation;

[0037] Calculate Euler function in represents the number of positive integers less than or equal to b and coprime with b;

[0038] Calculate the integer e, let and Where e is part of the RSA public key data, coprime, gcd(·) represents the greatest common divisor, which is used to ensure that e and There are no common factors;

[0039] Calculate d so that d is the RSA private key, which is the The multiplicative inverse of The remainder is 1;

[0040] Encrypt the reviewed text using the public key (e, b): Serialize the reviewed text into a byte string r, converting the structured data into encrypted binary form;

[0041] Encrypt r in blocks to get the ciphertext block R u :

[0042]

[0043] in, represents the modular exponentiation operation in the encryption process; k is the number of blocks, R u is the uth ciphertext block; the ciphertext block R u Splice into a complete ciphertext R, so as to merge the encrypted block data into a complete encrypted text; store the encrypted text and review results in a secure database.

[0044] A text review system based on multi-display collaboration, which is implemented based on the text review method based on multi-display collaboration, and includes a text preprocessing module, a text terminology vocabulary module, a key information comparison module, an error checking and marking module, a multi-interface display module, and an encryption module;

[0045] The text preprocessing module is used to extract the language text in the text, digitize the text, and convert the text into text data;

[0046] The text term word library module is used to construct a text term word library, and the text term word library is used to store key information words in the text; the key information words include qualification type words, project type words, technology type words and price type words;

[0047] The key information comparison module is used to construct a text term comparison algorithm, compare text data with the key information words in the text term library, determine whether the sentence in the text is the text key information, and mark the text key information with different colors according to the type of key words contained in the sentence;

[0048] The error checking and marking module is used to check whether there are formatting, text and calculation errors in the text, and mark the text with errors;

[0049] The multi-interface display module is used to construct a text review display strategy for multiple display interfaces, use multiple display interfaces to display text information, display the original text, key text information and text error information, and review the text;

[0050] The encryption module uses an asymmetric encryption algorithm RSA to encrypt the reviewed text data, uses a public key to encrypt the text data, and uses a private key to decrypt the text data.

[0051] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the text review method based on multi-display collaboration by calling the computer program stored in the memory.

[0052] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the text review method based on multi-display collaboration.

[0053] Beneficial effects of the present invention: The present invention can greatly improve the efficiency of text review. By automatically extracting and identifying key information of the text and adopting a multi-display interface collaborative display method, review experts can quickly locate the review points and focus on key content, eliminating a lot of tedious manual browsing and comparison work, and the text review efficiency can be improved by more than 50%.

[0054] The present invention can significantly reduce the risk of errors in text review. Based on intelligent algorithms and rule engines, the system can automatically detect formatting, text and calculation errors in the text to avoid omissions and misjudgments by review experts. At the same time, the system will give intelligent prompts for suspected errors or key information to further ensure the accuracy and fairness of the review results.

[0055] The present invention strengthens the security protection of text data, constructs the RSA asymmetric encryption algorithm, encrypts the review data throughout the process, and combines strict identity authentication and access control to prevent data leakage and tampering risks to the greatest extent, providing a solid security guarantee for government procurement reviews.

[0056] The present invention displays the original text, key information extraction results, error detection results, etc. in a targeted manner on different display interfaces, so that review experts can obtain the key information required for review more quickly and accurately without having to search page by page in lengthy text files, thereby greatly improving the efficiency of information acquisition and recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flowchart of a text review method based on multi-display collaboration of the present invention;

[0058] Figure 2 It is a structural schematic diagram of a text review system based on multi-display collaboration of the present invention;

[0059] Figure 3 It is a schematic diagram of the structure of an electronic device provided by the present invention;

[0060] Figure 4 It is a schematic diagram of the structure of the computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0061] In order to better understand the present application, a more detailed description will be made of various aspects of the present application with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application, and are not intended to limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0062] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0063] It should also be understood that expressions such as "include", "including", "have", "contain" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0064] Unless otherwise specified, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that, unless clearly stated in this application, words defined in common dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0065] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0066] Example 1

[0067] Reference Figure 1 The first embodiment of the present invention provides a text review method based on multi-display collaboration.

[0068] Step 1: Extract the language and characters in the text, digitize the language and characters, and convert the language and characters into text data.

[0069] Specifically, the text includes paper text and electronic text; for paper text, the paper text is scanned to generate a PDF format file of the paper text; through optical character recognition (OCR) technology, text information in the PDF format text is extracted, and the extracted text is stored in an electronic document; for electronic text, the electronic file is directly parsed to extract the text content in the electronic text; both the paper text and the electronic text are converted into text data.

[0070] This step realizes the digitization of text, converting paper and electronic texts into text data, laying the foundation for subsequent text processing; using OCR and other technologies to automatically extract unstructured paper document content improves data preparation efficiency.

[0071] Step 2: Build a text terminology database to store key information words in the text, including qualification type words, project type words, technology type words, and price type words.

[0072] Specifically, the construction of the text terminology database specifically includes manually presetting the key words of the qualification type words, project type words, technology type words and price type words in the text; constructing a key word set S, in which there are sub-sets S of different types of words i ∈S, i represents the word type, S i represents the i-th word type subset in the keyword set; the subset S of each type of word i There is a word S ij ,S ij ∈S i , j represents the specific word number, S ij represents the jth word in the i-th word type subset; the subset word S of all words ij Mapped to the corresponding word vector V ij , V ij Represents the word vector of the jth word in the i-th word type subset of the mapping;

[0073]

[0074] Among them, V is the word vector matrix, representing the text term vocabulary; i∈[1,i0], j∈[1,j0].

[0075] This step predefines the key words of the text and divides them into sets by type to make the vocabulary structure clear; the introduction of word vector representation provides quantitative mathematical model support for the recognition and comparison of key information in the text.

[0076] Step 3: Build a text term comparison algorithm and annotate the key information of the text.

[0077] Specifically, the text data is marked as W, and natural language processing technology is used to split the text data W into m0 natural sentences The natural sentence is a complete sentence, and each natural sentence is divided into a natural word sequence, and the natural word sequence data is mapped to natural word vector data:

[0078]

[0079] Among them, n1 to For natural sentences The number of natural words contained; m∈[1,m0]; is the nth natural sentence in the mth natural sentence in the text data W mnatural word vectors; compare each natural word vector data with the word vector in the text term vocabulary, if there is That is, if the natural words divided are the same words in the text terminology library, then the mark The natural sentence in which it is located is the key information of the text.

[0080] Using the cosine similarity comparison algorithm, compare and V ij and set the similarity threshold θ. If:

[0081]

[0082] in, Representation vector The modulus of ||V ij || represents vector V ij Model.

[0083] Then judge V ij The similarity vector of the two vectors means that the words represented by the two vectors are similar words; when V ij When the similarity vector of The natural sentence in which it is located is the key information of the text.

[0084] Extract key information from the text and annotate it with color, setting different annotation colors for the same and similar words in the text terminology dictionary.

[0085] This step first performs natural language segmentation and then semantic comparison, reflecting an in-depth analysis from grammar to semantics; it combines identical word matching and similar word matching, enhancing the generalization of recognition on the basis of precise matching; it also colors key information to highlight review points, making it easier for experts to quickly obtain core information.

[0086] Step 4: Check the text for formatting, text, and calculation errors, and mark any erroneous statements.

[0087] Specifically, the acquired text is converted into text data, and the text content is divided into different paragraphs and parts, including titles, texts, and tables, according to the structure and format of the text.

[0088] Check text for format errors and predefine format requirements, including font, font size, line spacing, and paragraph indentation. Use regular expressions to match text content to check whether the text content meets the defined format requirements.

[0089] To check text for errors, use the Aspell spelling check library to check text, and the LanguageTool grammar check library to check text grammar.

[0090] Check the text for calculation errors, use regular expressions to extract numbers, amounts, and calculation formulas from the text, use the MathPix formula parsing library to parse the extracted formulas, calculate the extracted numbers and formulas, compare the calculation results with the calculation data in the text, and verify whether the text calculation results are correct.

[0091] When formatting, text, and calculation errors are found in the text, the errors are marked.

[0092] This step comprehensively checks the formatting, text and calculation errors in the text, improving the standardization and accuracy of the review; marking the erroneous content prominently helps reviewers to identify problems in a timely manner and improve the quality of the review.

[0093] Step 5: Construct a text review display strategy for multiple display interfaces.

[0094] Specifically, a text review display strategy for multiple display interfaces is constructed, and a first display interface, a second display interface, a third display interface, and a fourth display interface are constructed; the annotation results of the original text, key text information, and error information of the text are displayed in different display interfaces, and the text is reviewed through the display interfaces.

[0095] The text original is displayed in the first display interface, and the displayed text original is in PDF format for paper text and in electronic format for electronic text.

[0096] The text key information is displayed in the second display interface, and the display priority of the text key information is set. The text key information containing the same words in the text terminology dictionary is set as the first display priority, and the text key information containing similar words in the text terminology dictionary is set as the second display priority. The first display priority is higher than the second display priority. Under the same priority level, the text key information is displayed in descending order in the second display interface according to the number of the same words and similar words in the text terminology dictionary contained in the text key information.

[0097] The error messages appearing in the text are displayed in the third display interface, and are displayed in the order in which the error messages appear in the text data. The displayed error messages are confirmed during the review.

[0098] In the fourth display interface, the text is reviewed and the score and review result of the text are input.

[0099] The design of the multi-display interface set up in this step takes into account both comprehensiveness and pertinence of information, providing an information-based handle for review; by setting priority for the display of key information, it helps the reviewer focus on key points and improves review efficiency; and by separating error information from the scoring interface, the objectivity and fairness of the review is ensured.

[0100] Step 6: Use the RSA asymmetric encryption algorithm to encrypt the reviewed text data.

[0101] 1. Use the RSA algorithm to generate a public key (e, b) and a private key (d, b). The public key is used for encryption and the private key is used for decryption.

[0102] Specifically, prime numbers p and q are selected, and b=pq is calculated, where b is the modulus of the RSA key, which is used for encryption and decryption process calculations.

[0103] Calculate Euler function in Represents the number of positive integers less than or equal to b and coprime with b.

[0104] Calculate the integer e, let and Where e is part of the RSA public key data, coprime, gcd(·) represents the greatest common divisor, which is used to ensure that e and There are no common factors.

[0105] Calculate d so that d is the RSA private key, which is the The multiplicative inverse of The remainder is 1.

[0106] Encrypt the reviewed text using the public key (e, b): Serialize the reviewed text into a byte string r, and convert the structured data into an encrypted binary form.

[0107] Encrypt r in blocks to get the ciphertext block R u :

[0108]

[0109] in, represents the modular exponentiation operation in the encryption process; k is the number of blocks, R u is the uth ciphertext block; the ciphertext block R u Splice into a complete ciphertext R, so as to merge the encrypted block data into a complete encrypted text; store the encrypted text and review results in a secure database.

[0110] In this step, the public and private keys are asymmetrically encrypted to prevent data leakage during transmission and storage. Through block encryption processing, encryption efficiency review is taken into account while ensuring security, and the review results are stored together with the encrypted text to ensure the integrity and non-tamperability of the data.

[0111] Example 2

[0112] Reference Figure 2 ,The second embodiment of the present invention provides a text review system based on multi-display collaboration.

[0113] The system includes a text preprocessing module, a text terminology word library module, a key information comparison module, an error checking and marking module, a multi-interface display module and an encryption module.

[0114] The text preprocessing module is used to extract the language text in the text, digitize the text, and convert the text into text data.

[0115] The text terminology word library module is used to construct a text terminology word library, and the text terminology word library is used to store key information words in the text; the key information words include qualification type words, project type words, technology type words and price type words.

[0116] The key information comparison module is used to construct a text term comparison algorithm, compare text data with key information words in a text term library, determine whether a sentence in the text is text key information, and mark the text key information with different colors according to the type of key words contained in the sentence.

[0117] The error checking and marking module is used to check whether there are formatting, text and calculation errors in the text, and to mark the text where errors occur.

[0118] The multi-interface display module is used to construct a text review display strategy for multiple display interfaces, and uses multiple display interfaces to display text information, display the original text, key text information and text error information, and review the text.

[0119] The encryption module uses an asymmetric encryption algorithm RSA to encrypt the reviewed text data, uses a public key to encrypt the text data, and uses a private key to decrypt the text data.

[0120] Example 3

[0121] Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3As shown, according to another aspect of the present invention, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the text review method based on multi-display collaboration as described above can be executed.

[0122] The method or system according to the embodiment of the present invention can also be used by Figure 3 The architecture of the electronic device shown is implemented.

[0123] like Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, and the like.

[0124] The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, can store the text review method based on multi-display collaboration provided by the present invention.

[0125] The method for reviewing text based on multi-display collaboration includes: extracting language and text in a text, digitizing the language and text, and converting the language and text into text data; constructing a text terminology word library, wherein the text terminology word library is used to store key information words in the text; the key information words include qualification type words, project type words, technology type words, and price type words; constructing a text terminology comparison algorithm, comparing text data with key information words in the text terminology library, judging whether a sentence in the text is text key information, and marking the text key information with different colors according to the type of key words contained in the sentence; checking whether there are format, word and calculation errors in the text, and marking the expression text with errors; constructing a text review display strategy for multiple display interfaces, using multiple display interfaces to display text information, displaying the original text, text key information and text error information, and reviewing the text; using an asymmetric encryption algorithm RSA to encrypt the reviewed text data, encrypting the text data with a public key, and decrypting the text data with a private key.

[0126] Furthermore, the electronic device 500 may also include a user interface 508. Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0127] Example 4

[0128] Figure 4It is a schematic diagram of the structure of a computer-readable storage medium provided by an embodiment of the present invention.

[0129] like Figure 4 As shown, a computer readable storage medium 600 according to one embodiment of the present invention.

[0130] Computer readable storage medium 600 has computer readable instructions stored thereon.

[0131] When the computer-readable instructions are executed by a processor, the text review method based on multi-display collaboration according to the embodiments of the present invention described with reference to the above drawings may be executed.

[0132] The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. In addition, according to an embodiment of the present invention, the process described above with reference to the flowchart may be implemented as a computer software program.

[0133] For example, the present invention provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided by the present invention, such as: extracting language and text in a text, digitizing the language and text, and converting the language and text into text data; constructing a text terminology vocabulary, which is used to store key information words in the text; the key information words include qualification type words, project type words, technology type words and price type words; constructing a text term comparison algorithm to compare text data with the text terminology vocabulary Compare the words of key information to determine whether the sentences in the text are key information of the text, and mark the key information of the text with different colors according to the type of key words contained in the sentences; check whether there are formatting, text and calculation errors in the text, and mark the text with errors; build a text review display strategy with multiple display interfaces, use multiple display interfaces to display text information, display the original text, text key information and text error information, and review the text; use the asymmetric encryption algorithm RSA to encrypt the reviewed text data, encrypt the text data with the public key, and decrypt the text data with the private key.

[0134] When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present invention are performed. The method, apparatus, and device of the present invention may be implemented in many ways. For example, the method, apparatus, and device of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.

[0135] The above sequence for the steps of the method is for illustration only, and the steps of the method of the present invention are not limited to the sequence specifically described above unless otherwise specifically stated.

[0136] In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0137] In addition, the parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0138] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A text review method based on multi-display collaboration, characterized in that: include: Step 1: Extract the language and characters in the text, digitize the language and characters, and convert the language and characters into text data; Step 2: construct a text terminology word library, which is used to store key information words in the text; the key information words include qualification type words, project type words, technology type words and price type words; Step 3: Build a text term comparison algorithm to compare the text data with the key information words in the text term database to determine whether the sentences in the text are key information, and mark the key information in different colors according to the type of key words contained in the sentences; Step 4: Check the text for formatting, text, and calculation errors, and mark the text with errors, including: The acquired text is converted into text data, and the text content is divided into different paragraphs and parts, including titles, texts and tables, according to the structure and format of the text; Check text for format errors, predefine format requirements, including font, font size, line spacing, and paragraph indentation, use regular expressions to match text content, and check whether the text content meets the defined format requirements; Check the text for textual errors using the Aspel l spelling check library and the LanguageTool grammar check library; Check the text for calculation errors. Use regular expressions to extract numbers, amounts, and calculation formulas from the text. Use the MathPix formula parsing library to parse the extracted formulas. Calculate the extracted numbers and formulas. Compare the calculation results with the calculation data in the text to verify whether the text calculation results are correct. When formatting, text, and calculation errors are found in the text, the errors are marked; Step 5: Construct a text review display strategy for multiple display interfaces, use multiple display interfaces to display text information, including displaying the original text, key text information, and text error information, and review the text, including: Constructing a text review display strategy for multiple display interfaces, constructing a first display interface, a second display interface, a third display interface, and a fourth display interface; displaying the annotation results of the original text, key text information, and text error information in different display interfaces, and reviewing the text through the display interfaces; Displaying the original text in the first display interface, the displayed original text is in PDF format for paper text and in electronic format for electronic text; Displaying the text key information in the second display interface and setting the display priority of the text key information, setting the text key information containing the same words in the text terminology dictionary as the first display priority, and setting the text key information containing similar words in the text terminology dictionary as the second display priority; the first display priority is higher than the second display priority, and under the same priority, the text key information is displayed in descending order according to the number of the same words and similar words in the text terminology dictionary contained in the text key information in the second display interface; Displaying error messages in the text in the third display interface, arranging and displaying the error messages in the order in which they appear in the text data, and confirming the displayed error messages during review; Review the text in the fourth display interface, input the score of the text and the review result; Step 6: Use the asymmetric encryption algorithm RSA to encrypt the reviewed text data, use the public key to encrypt the text data, and use the private key to decrypt the text data, specifically including: The reviewed text is encrypted using the asymmetric encryption algorithm RSA. The RSA algorithm is used to generate the public key (e, b) and private key (d, b). The public key is used for encryption and the private key is used for decryption. Select prime numbers p and q, calculate b=pq, b is the modulus of the RSA key, used for encryption and decryption process calculation; Calculate Euler function in represents the number of positive integers less than or equal to b and coprime with b; Calculate the integer e, let and Where e is part of the RSA public key data, coprime, the gcd(·) function represents the greatest common divisor, which is used to ensure that e and There are no common factors; Calculate d so that d is the RSA private key, which is The multiplicative inverse of The remainder is 1; Encrypt the reviewed text using the public key (e, b): Serialize the reviewed text into a byte string r, converting the structured data into encrypted binary form; Encrypt r in blocks to get the ciphertext block R u : in, represents the modular exponentiation operation in the encryption process; k is the number of blocks, R u is the uth ciphertext block; the ciphertext block R u Splice into a complete ciphertext R, so as to merge the encrypted block data into a complete encrypted text; store the encrypted text and review results in a secure database.

2. The text review method based on multi-display collaboration according to claim 1 is characterized in that: The text includes paper text and electronic text; for paper text, the paper text is scanned to generate a PDF format file of the paper text; through optical character recognition (OCR) technology, text information in the PDF format text is extracted, and the extracted text is stored in an electronic document; for electronic text, the electronic file is directly parsed to extract the text content in the electronic text; both the paper text and the electronic text are converted into text data.

3. The text review method based on multi-display collaboration according to claim 2 is characterized in that: The construction of the text terminology database specifically includes manually presetting the key words of the qualification type words, project type words, technology type words and price type words in the text; constructing a key word set S, in which there are sub-sets S of different types of words. i ∈S, i represents the word type, S i represents the i-th word type subset in the keyword set; the subset S of each type of word i There is a word S ij ,S ij ∈S i , j represents the specific word number, S ij represents the jth word in the i-th word type subset; the subset word S of all words ij Mapped to the corresponding word vector V ij , V ij Represents the word vector of the jth word in the i-th word type subset of the mapping; Where V is the word vector matrix, representing the text term vocabulary; i∈[1,i0], j∈[1,j0].

4. The text review method based on multi-display collaboration according to claim 3 is characterized in that: Construct a text term comparison algorithm, mark the text data as W, and use natural language processing technology to split the text data W into m0 natural sentences The natural sentence is a complete sentence, and each natural sentence is divided into a natural word sequence, and the natural word sequence data is mapped to natural word vector data: Among them, n1 to For natural sentences The number of natural words contained; m∈[1,m0]; is the nth natural sentence in the mth natural sentence in the text data W m natural word vectors; compare each natural word vector data with the word vector in the text term vocabulary, if there is That is, if the natural words divided are the same words in the text terminology library, then the mark The natural sentence is the key information of the text; Using the cosine similarity comparison algorithm, compare and V ij and set the similarity threshold θ. If: in, Representation vector The modulus of ||V ij || represents vector V ij Model; Then judge V ij The similarity vector of the two vectors means that the words represented by the two vectors are similar words; when V ij When the similarity vector of The natural sentence is the key information of the text; Extract key information from the text and annotate it with color, setting different annotation colors for the same and similar words in the text terminology dictionary.

5. A text review system based on multi-display collaboration, which is used to implement the text review method based on multi-display collaboration according to any one of claims 1 to 4, characterized in that: It includes a text preprocessing module, a text terminology database module, a key information comparison module, an error checking and marking module, a multi-interface display module and an encryption module; The text preprocessing module is used to extract the language text in the text, digitize the text, and convert the text into text data; The text term word library module is used to construct a text term word library, and the text term word library is used to store key information words in the text; the key information words include qualification type words, project type words, technology type words and price type words; The key information comparison module is used to construct a text term comparison algorithm, compare text data with the key information words in the text term library, determine whether the sentence in the text is the text key information, and mark the text key information with different colors according to the type of key words contained in the sentence; The error checking and marking module is used to check whether there are formatting, text and calculation errors in the text, and mark the text with errors; The multi-interface display module is used to construct a text review display strategy for multiple display interfaces, use multiple display interfaces to display text information, display the original text, key text information and text error information, and review the text; The encryption module uses an asymmetric encryption algorithm RSA to encrypt the reviewed text data, uses a public key to encrypt the text data, and uses a private key to decrypt the text data.

6. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the text review method based on multi-display collaboration as described in any one of claims 1 to 4 by calling the computer program stored in the memory.

7. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the text review method based on multi-display collaboration as described in any one of claims 1 to 4.

Images