A method, device and system for generating strong passwords based on natural language analysis

Abstract

The present invention relates to a method, device and system for generating strong passwords based on natural language analysis. The method includes: obtaining a text to be parsed; extracting the text to be parsed to determine a keyword sequence; generating password metadata according to the keyword sequence and a custom sequence set by a user; and generating a final password sequence through voice transformation and morphological transformation of the password metadata. The present invention solves the problem of difficult memorization caused by random strong passwords or sequential strong passwords, extracts keywords through natural language analysis, supports user configuration of custom sequences, and uses various transformation processes to increase the complexity of the password and meet the characteristics of a strong password that is easy to remember.

Description

Technical Field

[0001] The present invention relates to the field of computer security technology, and particularly to a method, device and system for generating strong passwords based on natural language analysis. Background Art

[0002] With the development of networks and mobile communications, the usage rates of network communication, mobile payment, and online banking are getting higher and higher. The importance of these systems is also increasing. Communicating, shopping, and paying through networks and mobile devices have become important ways of people's lives. While network communication, shopping, and mobile payment bring convenience to people's lives, the protection of people's network identities, social accounts, and bank accounts has become an important matter in daily life. Currently, identity authentication is achieved by setting static passwords of a certain length. For the security of the system, strong passwords of a relatively long length are often set, including uppercase and lowercase characters, numbers, and symbols. Such strong passwords are very difficult to remember, and there is a risk of forgetting the password or leakage due to plain text recording. If weak passwords are used, it is very likely that the attacker will crack or guess the password to obtain system permissions, which is very insecure.

[0003] Most of the existing authentication processes are implemented through static passwords of a certain complexity. If this static password is too simple, such as 123456, 12345678, password, etc., it is very easy for the attacker to guess or brute-force crack it to obtain system permissions. If the static password is set too complex, such as randomly generating 16-bit strong passwords like "oBSy!JyzSmD&%96V", "rzGhuU@Yn#CgNH$8", there will be a problem of being unable to remember, and it will be recorded in plain text in a certain place, which is very easy to cause leakage. Therefore, there is an urgent need for an efficient, accurate and memory-friendly strong password generation method to solve the above problems. Summary of the Invention

[0004] In view of this, it is necessary to provide a method, device and system for generating strong passwords based on natural language analysis to overcome the problems in the prior art that the password setting is complex, there is a possibility of leakage, and it is not conducive to memory.

[0005] To solve the above technical problems, the present invention provides a method for generating strong passwords based on natural language analysis, including:

[0006] Obtaining the text to be parsed;

[0007] Extracting the text to be parsed to determine the keyword sequence;

[0008] Generating password metadata according to the keyword sequence and the custom sequence set by the user;

[0009] Generating the final password sequence according to the password metadata through voice transformation and morphological transformation.

[0010] Further, the extraction of the text to be parsed to determine the keyword sequence includes:

[0011] Decompose the text to be parsed into several token units, and perform standardization processing on each token unit to obtain the corresponding labeled part of speech;

[0012] Based on the labeled part of speech, perform semantic analysis and frequency analysis to determine the high-frequency keywords, and form the keyword sequence.

[0013] Further, the generation of password metadata and connectors according to the keyword sequence and the custom sequence set by the user includes:

[0014] Concatenate the keyword sequence and the custom sequence to form metadata, and perform a cryptographic hash function calculation to determine the corresponding hash string;

[0015] Randomly select several characters from the hash string as ASCII codes, and determine whether they meet the preset conditions. If they meet, use the selected ASCII codes as the connectors;

[0016] Concatenate the keyword sequence, the custom sequence, and the connectors to form the password metadata.

[0017] Further, the preset conditions include that the ASCII code is a printable character and at the same time a special symbol.

[0018] Further, the generation of the final password sequence by performing voice transformation and morphological transformation on the password metadata includes:

[0019] Perform voice transformation on the password metadata to convert it into a voice-transformed password;

[0020] Perform morphological transformation on the voice-transformed password to convert it into a morphologically-transformed password;

[0021] Determine whether the morphologically-transformed password meets the specified password conditions. If it meets, output it as the final password sequence;

[0022] If it does not meet, return to the step of extracting the text to be parsed to determine the keyword sequence.

[0023] Further, the performing voice transformation on the password metadata to convert it into a voice-transformed password includes:

[0024] Convert the password metadata into pinyin data;

[0025] According to the configured English dictionary library, determine the first mapping relationship between phonetic symbols and pinyin;

[0026] Based on the first mapping relationship, match the phonetic symbols and pinyin of the pinyin data;

[0027] Extract the English of the password metadata that meets the preset matching condition, and convert it into a voice-transformed password.

[0028] Further, the step of morphologically transforming the voice-transformed password into a morphologically transformed password further includes:

[0029] Convert the voice-transformed password into the morphologically transformed password according to the configured character shape mapping table.

[0030] Further, the specified password condition includes: the morphologically transformed password meets the preset length.

[0031] The present invention also provides an apparatus for generating a strong password based on natural language analysis, including:

[0032] An acquisition unit, configured to acquire a text to be parsed;

[0033] A processing unit, configured to extract the text to be parsed to determine a keyword sequence; and further configured to generate password metadata according to the keyword sequence and a custom sequence set by a user;

[0034] A generation unit, configured to perform voice transformation and morphological transformation according to the password metadata to generate a final password sequence.

[0035] The present invention also provides a system for generating a strong password based on natural language analysis, including a processor, and the processor is configured to execute the method for generating a strong password based on natural language analysis as described above.

[0036] Compared with the prior art, the beneficial effects of the present invention include: First, effectively acquire the text to be parsed; then, extract keywords through natural language analysis to generate a keyword sequence, and support a custom sequence configured by the user to facilitate the diversity of password generation; furthermore, combine the keyword sequence and the custom sequence to generate password metadata to increase complexity; finally, combine voice transformation, and through a certain algorithm, change it into voice-transformed data with the same or similar pronunciation but different characters, and combine morphological transformation, and through a certain algorithm, change it into morphologically similar data with different characters to generate a final password sequence, ensuring its security and reliability and being easy to remember. In summary, the present invention solves the problem of difficult memorization brought by random strong passwords or sequential strong passwords, extracts keywords through natural language analysis, supports user-configured custom sequences, and uses various transformation processes to increase the complexity of the password and meet the characteristics of a strong password that is easy to remember. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1Schematic flowchart of an embodiment of the method for generating a strong password based on natural language analysis provided by the present invention;

[0038] Figure 2 Provided by the present invention Figure 1 Schematic flowchart of an embodiment of step S102 in

[0039] Figure 3 Provided by the present invention Figure 2 Schematic flowchart of an embodiment of step S203 in

[0040] Figure 4 Provided by the present invention Figure 2 Schematic flowchart of an embodiment of step S204 in

[0041] Figure 5 Provided by the present invention Figure 4 Schematic flowchart of an embodiment of step S401 in

[0042] Figure 6 Schematic structural diagram of an embodiment of the device for generating a strong password based on natural language analysis provided by the present invention;

[0043] Figure 7 Schematic structural diagram of an embodiment of the electronic device provided by the present invention. Detailed implementation manners

[0044] The following describes the preferred embodiments of the present invention in conjunction with the accompanying drawings. The accompanying drawings form a part of this application and are used together with the embodiments of the present invention to explain the principles of the present invention, rather than to limit the scope of the present invention.

[0045] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of these features. In addition, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0046] In the description of the present invention, referring to "embodiment" means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The phrase appears at various positions in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the described embodiments may be combined with other embodiments.

[0047] The present invention provides a method, apparatus and system for generating strong passwords based on natural language analysis. By using keyword sequences and user-defined sequences, and combining various transformation means, strong passwords with sufficient password strength and easy to remember are generated, providing a new idea for further improving the reliability and memorability of generated passwords.

[0048] Before describing the embodiments, the relevant terms involved are defined:

[0049] Strong password: The English name is Strong password, which refers to a password that is not easily guessed or cracked. It has the following characteristics: It is at least 8 characters long, does not contain all or part of the user account name, and contains at least three of the following four types of characters: uppercase letters, lowercase letters, numbers, and symbols on the keyboard (such as!, @, #). There is no regular combination of uppercase and lowercase letters, numbers, and symbols. Some login systems support the input of full-width symbols, as well as special symbols such as Chinese and other languages. It is not a password that is easily guessed (for example: abc1qaz@WSX, qazwsxedc, iloveyou, etc.).

[0050] Based on the description of the above technical terms, in the prior art, most authentication processes are often implemented through static passwords with a certain degree of complexity. Their settings are simple and easy to be cracked by brute force, and if the settings are complex, they are redundant and difficult to remember, which easily causes information leakage accidents. Therefore, the present invention aims to propose an efficient and accurate method, apparatus and system for generating strong passwords based on natural language analysis.

[0051] The following will separately describe the specific embodiments in detail:

[0052] An embodiment of the present invention provides a method for generating strong passwords based on natural language analysis. Combining Figure 1 Looking at Figure 1 FIG. is a schematic flowchart of an embodiment of the method for generating strong passwords based on natural language analysis provided by the present invention. The above method includes steps S101 to S104, where:

[0053] In step S101, the text to be parsed is obtained;

[0054] In step S102, the text to be parsed is extracted to determine the keyword sequence;

[0055] In step S103, password metadata is generated according to the keyword sequence and the user-defined sequence set by the user;

[0056] In step S104, phonetic transformation and morphological transformation are performed on the password metadata to generate the final password sequence.

[0057] In the embodiment of the present invention, first, the text to be parsed is effectively obtained; then, keywords are extracted through natural language analysis to generate a keyword sequence, and a custom sequence configured by the user is supported to facilitate the diversity of password generation; furthermore, the keyword sequence and the custom sequence are combined to generate password metadata to increase complexity; finally, combined with voice transformation, it is changed into voice transformation data with the same or similar pronunciation but different characters through a certain algorithm, and combined with morphological transformation, it is changed into morphological transformation data with similar morphology but different characters through a certain algorithm to generate the final password sequence, ensuring its security and reliability and being easy to remember.

[0058] It should be noted that the main steps of the present invention are as follows: through the keyword extraction module, keywords can be extracted from the target system or enterprise-related information. These keywords are generally related to the target enterprise or target system and are conducive to memory. After extracting the keyword sequence, the user-defined sequence is combined, and then it enters the password metadata generation module to generate metadata, and a hash operation is performed. The connection symbol is calculated through a certain algorithm from the result of the hash operation; after the metadata and the connection symbol are spliced, the voice transformation module and the morphological transformation module are executed; after multiple cycles, the final password sequence is obtained.

[0059] As a preferred embodiment, combined with Figure 2 to see, Figure 2 provided by the present invention Figure 1 is a schematic flowchart of an embodiment of step S102 in the present invention. The above step S102 includes steps S201 to S202, where:

[0060] In step S201, the text to be parsed is decomposed into several token units, and each token unit is standardized to obtain the corresponding part-of-speech annotation.

[0061] In step S202, meaning analysis and frequency analysis are performed according to the part-of-speech annotation to determine high-frequency keywords and form the keyword sequence.

[0062] In the embodiment of the present invention, through the method of natural language analysis, keywords in a piece of text are extracted. The input can be enterprise introductions, official website content, product introductions, etc. This module uses NLP natural language analysis technology, and mainly has the following steps: First, prepare the input text. Through the tokenization method, the text is decomposed into useful units (tokens). After generating the tokens, the part of speech of each unit is analyzed and standardized. Through the standardization process, the word stem of the word is identified and the part of speech is annotated. The nouns among them are analyzed for meaning and occurrence frequency. High-frequency keywords with similar meanings are obtained. The keywords obtained by this module are generally concepts or phrases that the user is more familiar with, forming a keyword sequence.

[0063] It should be noted that various publicly available NLP natural language analysis models can be used to extract keywords, or an algorithm can be designed independently to extract keywords. The core purpose is to obtain highly relevant and memorable keywords from a piece of text.

[0064] As a preferred embodiment, in combination with Figure 3 let's look at Figure 3 provided by the present invention Figure 2 is a schematic flowchart of an embodiment of step S203 in. The above step S203 includes steps S301 to S303, where:

[0065] In step S301, the keyword sequence and the custom sequence are concatenated to form metadata, and a cryptographic hash function is calculated to determine the corresponding hash string;

[0066] In step S302, several characters of the hash string are randomly selected as ASCII codes, and it is determined whether the preset conditions are met. If so, the selected ASCII codes are used as the connection symbols;

[0067] In step S303, the keyword sequence, the custom sequence, and the connection symbol are concatenated to form the password metadata.

[0068] In an embodiment of the present invention, the metadata generation module is responsible for calculating metadata and connection symbols from the input keyword sequence and user-defined sequence.

[0069] It should be noted that the generated keyword sequences, for example, according to the introduction of a certain company, obtain keyword sequences such as "visualization", "R & D center", "core technology", "national high-tech", etc., and are combined with user-defined sequences such as "19870606", "abt", "Test123", etc., which can form basic data and be input into the metadata generation module to generate metadata and connection symbols.

[0070] It should be noted that other mathematical methods can be used to calculate the connection symbol and the password metadata, as long as the input can be calculated into characters that can be used as passwords. For example, extracting decimal characters for conversion calculation instead of hexadecimal. For example, generating a 3-bit connection symbol, etc., all belong to the same alternative solutions.

[0071] As a preferred embodiment, the preset conditions include that the ASCII code is a printable character and at the same time a special symbol.

[0072] In an embodiment of the present invention, preset conditions are set to effectively identify the ASCII code.

[0073] In a specific embodiment of the present invention, the password metadata is generated as follows:

[0074] In the first step, the keyword + custom sequence is operated by MD5 to obtain a hash string. For example, after concatenating the keyword sequence "visualization" and the custom character "abt" and calculating md5("visualizationabt"), the result is: "19A1047D227D1BD9D05D21093804ACA1".

[0075] In the second step, randomly select 2 digits from the md5 result as 16 - bit ASCII codes, and determine whether they are printable characters. If they are printable characters and special symbols, they can be used as connection symbols. Taking 19A1047D227D1BD9D05D21093804ACA1 as an example:

[0076] 0x49 - 73 - I is a printable character but not a special symbol;

[0077] 0x93 - 147 - non - printable character;

[0078] 0x30 - 48 - 0 is a printable character but not a special symbol; ...

[0080] 0x5d - 93 - ] is a printable character and also a special symbol, and can be used as a connection symbol; ...

[0082] 0x40 - 64 - @ is a printable character and also a special symbol, and can be used as a connection symbol;

[0083] The range of special symbols is within the following ASCII code (decimal) range:

[0084] 32 - 47 symbols;

[0085] 58 - 64 symbols;

[0086] 91 - 96 symbols;

[0087] 123 - 126 symbols;

[0088] In the third step: The keyword + user sequence + connection symbol are combined to form password metadata, such as: "visualizationabt]@".

[0089] Illustrated by a specific example as follows: When the metadata is: "visualizationabt"; the connection symbol is: "]@"; then the formed password metadata is: "visualizationabt]@".

[0090] As a preferred embodiment, combined with Figure 4 look at Figure 4 provided by the present invention Figure 2Flow schematic diagram of an embodiment of step S204. The above step S204 includes steps S401 to S404, where:

[0091] In step S401, the password metadata is subjected to voice transformation to be transformed into a voice-transformed password;

[0092] In step S402, the voice-transformed password is subjected to morphological transformation to be transformed into a morphologically-transformed password;

[0093] In step S403, it is determined whether the morphologically-transformed password meets the specified password conditions. If it meets, it is output as the final password sequence;

[0094] In step S404, if it does not meet, it returns to the step of extracting the text to be parsed and determining the keyword sequence.

[0095] In the embodiment of the present invention, the password metadata supports voice transformation and is changed into password metadata with the same or similar pronunciation and different characters through a certain algorithm; the password metadata supports morphological transformation and is changed into password metadata with similar morphology and different characters through a certain algorithm; after cycling, a final password sequence is generated, meeting the characteristics of a strong password that is easy to remember.

[0096] As a preferred embodiment, combined with Figure 5 to see Figure 5 provided by the present invention Figure 4 Flow schematic diagram of an embodiment of step S401. The above step S401 includes steps S501 to S504, where:

[0097] In step S501, the password metadata is converted into pinyin data;

[0098] In step S502, according to the configured English dictionary library, the first mapping relationship between phonetic symbols and pinyin is determined;

[0099] In step S503, based on the first mapping relationship, the pinyin data is matched with phonetic symbols and pinyin;

[0100] In step S504, the English of the password metadata with a matching degree reaching the preset matching condition is extracted and transformed into a voice-transformed password.

[0101] In the embodiment of the present invention, effective voice transformation is performed through the configured English dictionary library.

[0102] As a preferred embodiment, the above step S402 includes:

[0103] According to the configured character shape mapping table, the voice-transformed password is transformed into the morphologically-transformed password.

[0104] In the embodiment of the present invention, effective morphological transformation is performed through the configured character shape mapping table.

[0105] As a preferred embodiment, the above-specified password conditions include: the morphological transformation password meets a preset length.

[0106] In the embodiment of the present invention, by setting specified password conditions, the loop can be effectively exited, and a final password sequence is generated after the loop, meeting the characteristics of a strong password that is easy to remember.

[0107] In a specific embodiment of the present invention, the final password sequence is generated as follows:

[0108] Step 1, the password metadata voice transformation module realizes the ability to convert Chinese characters to ASCII codes by converting Chinese characters into pinyin. For example, "visualization" is converted to "keshihua". Further, this module needs to configure an English dictionary to record common English words + phonetic notations for future reference.

[0109] Step 2, a correspondence table is formed between the phonetic notations and Chinese pinyin. For example:

[0110] ″a″: ″a″,

[0111] ″e″: ″ai″,

[0112] ″i″: ″yi″,

[0113] ″I″: ″yi″,

[0114] ″eI″: ″ei″,

[0115] ″aI″: ″ai″,

[0116] : ″wei″,

[0117] : ″ou″,

[0118] ″au″: ″ao″,

[0119] : ″yi″,

[0120] : ″aei″,

[0121] : ′wei′, ...

[0123] Step 3: Map the pinyin converted in the first step through the mapping relationship in the third step, and match the pinyin and phonetic symbols in the English dictionary in the second step. For those with a relatively high matching degree, extract their English to form the conversion from Chinese pronunciation to English. For example:

[0124] "Coming prepared" can be converted to "Coming bear".

[0125] "Hiding one's light" can be converted to "Hiding blue".

[0126] "Visualization" can be converted to "Kiss-ization".

[0127] Finally, for those without approximate pronunciations, take the first letter. After conversion, "Visualization" gets the final result: "KissH"; combine the custom sequence and the separator to get the result "KissHabt]@";

[0128] Step 4: Pass through the password metadata morphological transformation module, mainly through a mapping table with relatively similar character shapes, such as:

[0129] ″i″ -> ″1″,

[0130] ″a″ -> ″4″,

[0131] ″0″ -> ″@″,

[0132] ″8″ -> ″&″,

[0133] ″o″ -> ″0″,

[0134] ″1″ -> ″!″,

[0135] ″b″ -> ″6″, ......

[0137] After the above process, convert "KissHabt]@" to "k1ssH46t]@";

[0138] Step 5: After splicing the above process multiple times, a strong password with a specified length can be generated and is easy to remember. For example: "k1ssH46t]@k1ssH46t]@", and the final password sequence will output the generated password: "k1ssH46t]@k1ssH46t]@".

[0139] An embodiment of the present invention also provides a device for generating a strong password based on natural language analysis. Combining Figure 6 to see, Figure 6 is a schematic structural diagram of an embodiment of the device for generating a strong password based on natural language analysis provided by the present invention. The device 600 for generating a strong password based on natural language analysis includes:

[0140] An acquisition unit 601, configured to acquire the text to be parsed;

[0141] A processing unit 602, configured to extract the text to be parsed to determine a keyword sequence; and further configured to generate password metadata according to the keyword sequence and a custom sequence set by a user;

[0142] A judgment unit 603, configured to perform voice transformation and morphological transformation according to the password metadata to generate a final password sequence.

[0143] For a more specific implementation manner of each unit of the apparatus for generating a strong password based on natural language analysis, reference may be made to the description of the above method for generating a strong password based on natural language analysis, and it has a similar beneficial effect, which will not be elaborated herein.

[0144] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method for generating a strong password based on natural language analysis as described above is implemented.

[0145] Generally speaking, computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. A non-transitory computer-readable storage medium can include any computer-readable medium except for a signal propagating temporarily itself.

[0146] A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0147] Computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. In particular, the Python language suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., connected through the Internet using an Internet service provider).

[0148] An embodiment of the present invention also provides an electronic device. Considering Figure 7 in combination Figure 7 FIG. is a schematic structural diagram of an embodiment of the electronic device provided by the present invention. The electronic device 700 includes a processor 701, a memory 702, and a computer program stored in the memory 702 and executable on the processor 701. When the processor 701 executes the program, the method for generating a strong password based on natural language analysis as described above is implemented.

[0149] As a preferred embodiment, the above-mentioned electronic device 700 further includes a display 703 for displaying the data processing result after the processor 701 executes the method for generating a strong password based on natural language analysis.

[0150] Exemplarily, the computer program can be divided into one or more modules / units. One or more modules / units are stored in the memory 702 and executed by the processor 701 to complete the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device 700. For example, the computer program can be divided into multiple units, and the specific functions of each unit are as described in the above respective sub-steps, and will not be elaborated here one by one.

[0151] The electronic device 700 can be a desktop computer with an adjustable camera module, a notebook, a palm computer, a smart phone, or other devices.

[0152] Among them, the processor 701 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 701 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0153] Among them, the memory 702 may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. Among them, the memory 702 is used to store programs. After receiving the execution instruction, the processor 701 executes the program. The methods defined by the processes disclosed in any of the embodiments of the present invention can be applied to or implemented by the processor 701.

[0154] Among them, the display 703 may be an LCD display screen or an LED display screen. For example, the display screen on a mobile phone.

[0155] It can be understood that Figure 7 The structure shown is only a schematic structural diagram of the electronic device 700, and the electronic device 700 may also include more or fewer components than Figure 7 shown. Figure 7 The components shown in can be implemented using hardware, software, or a combination thereof.

[0156] The computer-readable storage medium and electronic device provided according to the above embodiments of the present invention can be implemented with reference to the content specifically described in the method for generating a strong password based on natural language analysis according to the present invention, and have beneficial effects similar to those of the method for generating a strong password based on natural language analysis as described above, which will not be elaborated here.

[0157] The present invention discloses a method, device and system for generating a strong password based on natural language analysis. First, an effective acquisition of the text to be parsed is performed; then, keywords are extracted through natural language analysis to generate a keyword sequence, and a user-configured custom sequence is supported to facilitate the diversity of password generation; furthermore, password metadata is generated by combining the keyword sequence and the custom sequence to increase complexity; finally, combined with voice transformation, it is changed into voice transformation data with the same or similar pronunciation but different characters through a certain algorithm, and combined with morphological transformation, it is changed into morphological transformation data with similar morphology but different characters through a certain algorithm to generate the final password sequence, ensuring its security and reliability and being easy to remember.

[0158] The technical solution of the present invention solves the problem of difficult memorization brought by random strong passwords or sequential strong passwords. Keywords are extracted through natural language analysis, a user-configured custom sequence is supported, and various transformation processes are used to increase the complexity of the password and meet the characteristics of a strong password that is easy to remember.

[0159] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for generating a strong password based on natural language analysis, characterized in that, it includes: Obtain the text to be parsed; Extract the text to be parsed to determine the keyword sequence; Generate password metadata according to the keyword sequence and the custom sequence set by the user; Perform voice transformation and morphological transformation according to the password metadata to generate the final password sequence; The generating password metadata according to the keyword sequence and the custom sequence set by the user includes: Concatenate the keyword sequence and the custom sequence to form metadata, and perform password hash function calculation to determine the corresponding hash string; Randomly select several characters from the hash string as ASCII codes, and determine whether they meet the preset conditions. If they meet, use the selected ASCII codes as connectors; Concatenate the keyword sequence, the custom sequence and the connector to form the password metadata; The preset conditions include that the ASCII code is a printable character and at the same time is a special symbol; The performing voice transformation and morphological transformation according to the password metadata to generate the final password sequence includes: Perform voice transformation on the password metadata to convert it into a voice-transformed password; Perform morphological transformation on the voice-transformed password to convert it into a morphologically-transformed password; Determine whether the morphologically-transformed password meets the specified password conditions. If it meets, output it as the final password sequence; If it does not meet, return to the step of extracting the text to be parsed to determine the keyword sequence.

2. The method for generating a strong password based on natural language analysis according to claim 1, characterized in that, the extracting the text to be parsed to determine the keyword sequence includes: Decompose the text to be parsed into several token units, and perform standardization processing on each token unit to obtain the corresponding part-of-speech annotation; Perform meaning analysis and frequency analysis according to the part-of-speech annotation to determine the high-frequency keywords and form the keyword sequence.

3. The method for generating a strong password based on natural language analysis according to claim 1, characterized in that, the performing voice transformation on the password metadata to convert it into a voice-transformed password includes: Convert the password metadata into pinyin data; Determine the first mapping relationship between phonetic symbols and pinyin according to the configured English dictionary library; Based on the first mapping relationship, perform matching of phonetic symbols and pinyin on the pinyin data; Extract the English of the password metadata with a matching degree reaching the preset matching condition and convert it into a voice-transformed password.

4. The method for generating a strong password based on natural language analysis according to claim 1, characterized in that, the performing morphological transformation on the voice-transformed password to convert it into a morphologically-transformed password further includes: Convert the voice-transformed password into the morphologically-transformed password according to the configured character shape mapping table.

5. The method for generating a strong password based on natural language analysis according to claim 1, characterized in that, the specified password conditions include: the morphologically-transformed password meets the preset length.

6. An apparatus for generating a strong password based on natural language analysis, characterized in that, it includes: An acquisition unit for acquiring the text to be parsed; A processing unit for extracting the text to be parsed to determine a keyword sequence; It is also used to generate password metadata according to the keyword sequence and the custom sequence set by the user; A generation unit for performing voice transformation and morphological transformation on the password metadata to generate a final password sequence; The generating password metadata according to the keyword sequence and the custom sequence set by the user includes: Concatenate the keyword sequence and the custom sequence to form metadata, and perform a password hash function calculation to determine the corresponding hash string; Randomly select several characters from the hash string as ASCII codes, and determine whether the preset conditions are met. If so, use the selected ASCII codes as separators; Concatenate the keyword sequence, the custom sequence and the separator to form the password metadata; The preset conditions include that the ASCII code is a printable character and at the same time a special symbol; The performing voice transformation and morphological transformation on the password metadata to generate a final password sequence includes: Perform voice transformation on the password metadata to convert it into a voice-transformed password; Perform morphological transformation on the voice-transformed password to convert it into a morphologically transformed password; Determine whether the morphologically transformed password meets the specified password conditions. If so, output it as the final password sequence; If not, return to the step of extracting the text to be parsed to determine the keyword sequence.

7. A system for generating strong passwords based on natural language analysis, characterized in that, It includes a processor, and the processor is used to execute the method for generating strong passwords based on natural language analysis according to any one of claims 1 to 5.

Images