CN115033880A - Computer software management system based on internet - Google Patents
Computer software management system based on internet Download PDFInfo
- Publication number
- CN115033880A CN115033880A CN202210692532.0A CN202210692532A CN115033880A CN 115033880 A CN115033880 A CN 115033880A CN 202210692532 A CN202210692532 A CN 202210692532A CN 115033880 A CN115033880 A CN 115033880A
- Authority
- CN
- China
- Prior art keywords
- information
- software
- result
- obtaining unit
- target user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
- G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements
- G06F21/562—Static detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Bioethics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- Virology (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a computer software management system based on the Internet, which is used for executing a computer software management method, and the method comprises the following steps: acquiring first preprocessing data information of first software; constructing a main feature word set and obtaining a main feature word extraction result; connecting a multi-party data source according to the main feature word extraction result, and performing data processing to obtain a first classification result; performing text analysis to obtain a first high-frequency vocabulary set; performing sensitivity analysis based on the first high-frequency vocabulary set, and performing horizontal inter-class sensitivity sequencing according to a sensitivity analysis result; and generating a first early warning instruction based on the sequencing result, and managing the first software. The technical problems that in the prior art, the identification efficiency of sensitive information of computer software is low, the identification accuracy is low, and therefore a user experiences poor software using experience and is easy to suffer from fraud risk are solved.
Description
Technical Field
The invention relates to the field of data processing, in particular to an internet-based computer software management system.
Background
With the continuous development of computer software development technology, the number of computer software is greatly increased. However, there are no few computer software with certain risks, such as low-quality software and phishing software. Some software such as friend making software, recruitment software, investment software, video software and the like realizes fraud for users through ways of recommending commodities, providing friend making opportunities, providing employment opportunities and the like for the users, so that the body and mind of the users are damaged. Meanwhile, the supervision of computer software is far from enough, and some potential risks cannot be effectively identified. There is a great deal of interest in exploring systems for managing computer software.
However, the prior art has at least the following problems:
the method has the technical problems that the identification efficiency of the sensitive information of the computer software is low, and the identification accuracy is low, so that the experience of a user using the software is poor, and the user is easy to suffer from fraud risks.
Disclosure of Invention
The embodiment of the application provides a computer software management system based on the Internet, and solves the technical problems that in the prior art, the identification efficiency and the identification accuracy of sensitive information of computer software are low, so that a user has poor experience of using the software and is easy to suffer from fraud risk, and achieves the technical effects that the sensitive information is identified for the software by constructing a sensitivity analysis method, the identification efficiency and the identification accuracy of the sensitive information are improved by a text analysis technology, so that the experience of using the software by the user is improved, and the fraud risk of the user is reduced.
In view of the above problems, the embodiments of the present application provide an internet-based computer software management system.
In a first aspect, an embodiment of the present application provides an internet-based computer software management system, where the system includes: the first obtaining unit is used for butting open data information of first software, screening the open data information of the first software and obtaining first preprocessing data information of the first software; the second obtaining unit is used for constructing a main feature word set, and extracting the main feature words of the first preprocessed data information to obtain a main feature word extraction result; the third obtaining unit is used for butting a multi-party data source according to the main characteristic word extraction result, and obtaining a first classification result after data integration, pretreatment and classification are carried out; a fourth obtaining unit, configured to perform text analysis on the first classification result to obtain a first high-frequency vocabulary set; the first execution unit is used for carrying out sensitivity analysis based on the first high-frequency vocabulary set and carrying out horizontal inter-class sensitivity sequencing according to a sensitivity analysis result; a fifth obtaining unit, configured to obtain, based on the inter-horizontal-class sensitivity ranking result, main feature word subsets corresponding to the first K inter-horizontal-class sensitivities; and the second execution unit is used for generating a first early warning instruction based on the main characteristic word subset and sending the first early warning instruction to a first target user.
In another aspect, the present application further provides an internet-based computer software management method, including: the method comprises the steps of butting open data information of first software, screening the open data information of the first software, and obtaining first preprocessing data information of the first software; constructing a main feature word set, and performing main feature word extraction on the first preprocessed data information to obtain a main feature word extraction result; connecting a multi-party data source according to the main feature word extraction result, and performing data integration, preprocessing and classification to obtain a first classification result; performing text analysis on the first classification result to obtain a first high-frequency vocabulary set; performing sensitivity analysis based on the first high-frequency vocabulary set, and performing horizontal inter-class sensitivity sequencing according to a sensitivity analysis result; obtaining main feature word subsets corresponding to the first K lateral inter-class sensitivities on the basis of the ranking result of the lateral inter-class sensitivities; and generating a first early warning instruction based on the main characteristic word subset, and sending the first early warning instruction to a first target user.
In a third aspect, the present invention provides an internet-based computer software management system, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the system of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the method comprises the steps of obtaining first preprocessing data information of first software; constructing a main feature word set, and performing feature extraction on the first preprocessed data information to obtain a main feature word extraction result; butting a multi-party data source according to the main feature word extraction result, and obtaining a first classification result after data processing; performing text analysis to obtain a first high-frequency vocabulary set; performing sensitivity analysis based on the first high-frequency vocabulary set, and performing horizontal inter-class sensitivity sequencing according to the sensitivity analysis result; and generating a first early warning instruction based on the sequencing result, and managing the first software. The method achieves the technical effects that the sensitive information is identified for the software by constructing the sensitivity analysis method, and the identification efficiency and the identification accuracy of the sensitive information are improved by the text analysis technology, so that the experience of the user using the software is improved, and the fraud risk of the user is reduced.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flow chart of an Internet-based computer software management system according to an embodiment of the present application;
FIG. 2 is a schematic view illustrating a process of obtaining the sensitivity analysis result of an Internet-based computer software management system according to an embodiment of the present invention;
FIG. 3 is a schematic view illustrating a process of adding the mark information in the Internet-based computer software management system according to an embodiment of the present invention;
FIG. 4 is a schematic flowchart illustrating a second warning instruction generated by the Internet-based computer software management system according to an embodiment of the present disclosure;
FIG. 5 is a schematic structural diagram of an Internet-based computer software management system according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of the reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a first executing unit 15, a fifth obtaining unit 16, a second executing unit 17, a computing device 90, a memory 91, a processor 92, and an input-output interface 93.
Detailed Description
The embodiment of the application provides a computer software management system based on the Internet, and solves the technical problems that in the prior art, the identification efficiency of sensitive information of computer software is low, the identification accuracy is low, and therefore a user experiences poor software using experience and is easy to suffer from fraud risks. The method achieves the technical effects that the sensitive information is identified for the software by constructing the sensitivity analysis method, and the identification efficiency and the identification accuracy of the sensitive information are improved by the text analysis technology, so that the experience of the user using the software is improved, and the fraud risk of the user is reduced.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
At present, computer software with certain risks, such as low-quality software and phishing software, still exists. In some friend making software, recruitment software, investment software and video software, fraud is realized on a user through ways of recommending commodities for the user, providing friend making opportunities, providing employment opportunities and the like, so that the mind and body of the user are damaged, and even more serious consequences can be caused. Meanwhile, the supervision of computer software is not strong enough, and some potential risks cannot be effectively identified. Therefore, the technical problems that the efficiency of identifying sensitive information of computer software is low, the identification accuracy is low, the experience of a user using the software is poor, and the user is easy to suffer from fraud risks exist in the prior art.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides an internet-based computer software management system, wherein the system comprises: the first obtaining unit is used for butting open data information of first software, screening the open data information of the first software and obtaining first preprocessing data information of the first software; the second obtaining unit is used for constructing a main feature word set, and extracting the main feature words of the first preprocessed data information to obtain a main feature word extraction result; the third obtaining unit is used for butting a multi-party data source according to the main feature word extraction result, and obtaining a first classification result after data integration, pretreatment and classification are carried out; a fourth obtaining unit, configured to perform text analysis on the first classification result to obtain a first high-frequency vocabulary set; the first execution unit is used for carrying out sensitivity analysis based on the first high-frequency vocabulary set and carrying out horizontal inter-class sensitivity sequencing according to a sensitivity analysis result; a fifth obtaining unit, configured to obtain, based on the inter-horizontal-class sensitivity ranking result, main feature word subsets corresponding to the first K inter-horizontal-class sensitivities; and the second execution unit is used for generating a first early warning instruction based on the main characteristic word subset and sending the first early warning instruction to a first target user.
Having thus described the general principles of the present application, embodiments thereof will now be described with reference to the accompanying drawings. As can be known to those skilled in the art, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
Example one
As shown in fig. 1, an embodiment of the present application provides an internet-based computer software management method, which is applied to an internet-based computer software management system, where the method includes:
step S100: the method comprises the steps of butting open data information of first software, screening the open data information of the first software, and obtaining first preprocessing data information of the first software;
in particular, network investment fraud, network friend-making fraud and network job hunting fraud, which are frequently appeared in the field of people, are often prohibited because of the hiding property, the imperceptibility and the continuous updating of fraud means with the development of scientific technology. These network fraud events are often tied to computer software implemented fraud. Therefore, a computer software management method aiming at phishing needs to be searched, potential sensitive information in computer software is sharply identified, so that the computer software is managed, and a foundation is laid for creating a safe and harmonious internet computer software use environment and experience space.
The first software is any type of computer software which needs software management. The open data information is data information that all users exposed to the first software can touch. For example: taking the first software as job hunting software as an example, the open data information includes, but is not limited to, the contents of discussion forums in the software, announcements and notifications issued in the software, detailed pages of various position information in the software, and the like. And performing internet big data docking, acquiring open data information of the first software, removing invalid data in the open data information, and finishing screening to obtain first preprocessing data information of the first software. The invalid data comprises but is not limited to a privacy policy text and a user avatar, the privacy policy is removed because the first software cannot be used if the user does not agree with the privacy policy, the privacy policy text is a default selection for all users using the first software, few users read the first software, the influence on the first user is not great, the reason for removing the user avatar is that the user avatar is generally any picture information and sometimes may be a default image, and the data analysis value is not high. And removing some data information with no analysis value or low analysis value can lay a foundation for improving the data analysis efficiency of the first software.
Step S200: constructing a main feature word set, and extracting main feature words from the first preprocessed data information to obtain a main feature word extraction result;
further, step S200 in the embodiment of the present application further includes:
step S210: obtaining a first target user and a second target user of the first software;
step S220: acquiring a second target user safety management element based on the association mode information of the second target user and the first target user;
step S230: collecting attention intention information of the first target user to the first software;
step S240: and constructing the main characteristic word set based on the attention intention information and the second target user safety management element.
Specifically, due to the semantic complex property, the property of being easily misread and the strong relevance of the text data, the text data can be used as a good material for analyzing the safety evaluation of computer software. In order to carry out deep analysis on the first software, text data analysis is carried out on the first preprocessing information.
Firstly, a main characteristic word set is constructed, and the main characteristic word set is an important characteristic word set containing various management elements. The target users of the first software include a first target user and a second target user, which are two different participants of the first software, often in an opposite perspective, for example: the first target user is set as an information receiving subject such as a viewer, a job seeker, a reader, a consumer and the like in a narrow sense of understanding, and the second target user is set as an information publishing subject such as a video presenter, a recruitment unit, a content publisher and a merchant; the first target user and the second target user are two roles of conversation in the first software, which includes that the first target user and the second target user are two people of online chat, but the information of the first target user and the second target user is often asymmetric, and certain information is hidden.
According to a specific application scenario of the first software, obtaining real identities of the first target user and the second target user, so as to obtain association mode information of the first target user and the second target user, where the association mode information is a social contact and connection relationship between the first target user and the second target user, to name an example without limitation: if the first software is recruitment software, the association mode between the first target user and the second target user is specifically that the first target user is connected to the second target user through a method of searching keywords and the like, and initiates a conversation with the second target user after reading information of a recruitment brief chapter, an enterprise introduction and the like of the second target user, so as to perform deep chat.
The first target user is a user with a weak situation in the first software, so that security management needs to be performed on a second target user, and the security management elements of the second target user are elements needing to be verified, and the elements often have a certain strangeness on the first target user. Still taking the recruitment software as an example, since the association information of the two in the recruitment software includes the recruitment letter, the enterprise introduction and the post introduction of the second target user, the authenticity of the information needs to be ensured, and the enterprise introduction (enterprise name, enterprise position, etc.), the post, the recruitment salary, etc. need to be verified.
The attention intention information of the first target user to the first software refers to the attention important content of the first target user to the first software, such as: the first target user king likes to pay attention to job hunting experience and comments of other job seekers on the enterprise very much when the job hunting software is used for finding work. It is therefore necessary to add information of the first target user that is of great interest to the part that needs to be reviewed. Combining the attention intention with the second target user safety management element, extracting key words based on a semantic understanding technology, and constructing the main feature word set by taking high-frequency words as main feature words.
After the main feature word set is constructed, main feature word extraction is carried out on first preprocessing data information in first software, and key words for identifying safety risks can be extracted. And the main characteristic word extraction result is obtained by extracting the main characteristic of the first preprocessed data information through the main characteristic word set. The following are exemplary: and the main feature word extraction result of the recruitment software comprises all enterprise names, all post names and the like. Through the deep analysis of the first target user and the second target user of the first software, a scientific and reliable main feature word set is constructed, the main feature word extraction is further carried out on the first preprocessed data information, the potential information with certain risk in the first preprocessed information can be extracted, and data support is provided for the safety management of the first software.
Step S300: connecting a multi-party data source according to the main feature word extraction result, and performing data integration, preprocessing and classification to obtain a first classification result;
step S400: performing text analysis on the first classification result to obtain a first high-frequency vocabulary set;
specifically, the open data of the first software is often limited and monolithic, so that other data sources in the internet big data are needed to be relied on during analysis and checking, and the safety inspection of the first software is comprehensively and scientifically performed. Therefore, a multi-party data source is connected according to the main feature word extraction result, data resources related to the main feature word extraction result are integrated and preprocessed (repeated information is removed), and the connected data information is classified according to the main feature word to obtain a plurality of data subsets, namely the first classification result. The following are exemplary: and carrying out data source docking through the enterprise names to obtain the data information of each enterprise, and carrying out data classification according to the enterprise names to obtain the data information of each enterprise.
And performing text analysis in the first classification result, namely completing text mining by performing word segmentation, word stop removal, word frequency statistics and the like in a semantic analysis technology. High-frequency words are obtained through word frequency statistics, and represent important and non-negligible information in a text, such as: the high-frequency occurrence of the term such as loss of credit represents that the credit investigation condition of the enterprise is not good, and the high-frequency occurrence of the term such as poverty relief, donation and the like represents that the enterprise is a good enterprise. All high-frequency words form a first high-frequency word set, and a foundation can be laid for quickly verifying safety elements of a safety management user by generating the first high-frequency word set.
Step S500: performing sensitivity analysis based on the first high-frequency vocabulary set, and performing horizontal inter-class sensitivity sequencing according to a sensitivity analysis result;
further, as shown in fig. 2, step S500 in the embodiment of the present application further includes:
step S510: constructing a sensitivity evaluation index set based on the first software;
step S520: obtaining a standard threshold range set of the sensitivity evaluation index set;
step S530: obtaining a deviation degree list of the sensitivity evaluation indexes based on the standard threshold range set;
step S540: performing weight distribution based on the standard threshold range set to obtain a weight distribution result;
step S550: and obtaining the sensitivity analysis result based on the sensitivity evaluation index set, the deviation degree list and the weight distribution result.
Specifically, on the basis of the first high-frequency vocabulary set, security check is carried out on the second target users, and the sensitive second target users are screened out through sensitivity analysis. The sensitivity evaluation index used in the sensitivity analysis is constructed according to the content published on the first software, and exemplarily: if the first software is recruitment software, the sensitivity evaluation index set comprises but is not limited to consistency of published information, timeliness of published information and comprehensiveness of published information. To ensure the right of awareness of the first target user, a set of standard threshold ranges is set based on the basis of ensuring the basic rights and interests of the first target user, which is as follows: the preset standard threshold range set is that the consistency of the issued information reaches 80%, the timeliness of the issued information reaches 80%, and the comprehensiveness of the issued information reaches 60%. The following are exemplary: firstly, defining the coincidence degree of high-frequency words, wherein the coincidence degree is 25% if the information released in the first software is overlapped with 25 words in a high-frequency word set which comprises 100 words. The timeliness is the contact ratio between the high-frequency words from the nearest data source in the high-frequency word set and the first software release information, the effectiveness of the data is set by an inspector, the high-frequency word set is divided into data source time, if the high-frequency words in the last 3 months are 10, and only 1 word appears in the first software release information in the 10 high-frequency words, the contact ratio is 10%, and the timeliness is 10%. Comprehensiveness is defined as a high degree of vocabulary overlap, i.e., 25% of vocabulary overlap, and 25% of comprehensiveness. The judgment of consistency needs to compare word senses by using semantic understanding technology, for example: the high-frequency word is the address Guangdong, and the address Guangxi appears in the public information, the high-frequency word and the address Guangxi are inconsistent, whether the high-frequency word is consistent in the first software release information or not is judged through semantic understanding and comparison, and after the inconsistency rate is obtained, a consistency evaluation result is obtained through reverse deduction, if: the number of high-frequency words is 100, 15 high-frequency words with inconsistency are recognized, the inconsistency rate is 15%, and the consistency rate is 75%.
The degree of deviation list includes the degree of deviation of the sensitivity evaluation index from the preset standard range. The calculation method of the deviation degree is as follows: if the first software is recruitment software and the evaluation dimensions are consistency, timeliness and comprehensiveness, the consistency of the information released by the company A in the first software and the captured high-frequency vocabulary is 30%, the timeliness is 40%, the comprehensiveness is 40%, the preset standard threshold range is that the consistency of the released information reaches 80%, the timeliness of the released information reaches 80%, the comprehensiveness of the released information reaches 60%, and the consistency deviation degree of the two is that
A degree of age-related deviation of
The global deviation is
From the above calculation results, a list of degrees of deviation of company a can be obtained as shown in table 1. Two columns of the deviation degree table are formed by the sensitivity evaluation index and the calculation result of the deviation degree, thereby forming a deviation degree list.
TABLE 1 deviation List of company A
And then carrying out weight distribution according to the standard threshold range set, wherein the larger the standard value from the standard threshold range set is, the less the standard value is, the higher the weight is given when the standard value is not met with the standard criterion, the smaller the standard threshold range is, the more the standard value is, the lower the weight is given, the weight distribution method can carry out distribution according to the existing expert method to obtain a weight distribution result, and the sensitivity analysis result is obtained according to the sensitivity evaluation index set, the deviation degree list and the weight distribution result.
By y ═ α X 1 +βX 2 +γX 3 +…+θX n Calculating the sensitivity analysis result, wherein y is the sensitivity analysis result, alpha, beta, gamma and theta are distributed weights, and X is 1 、X 2 、X 3 、X n Is an index for sensitivity evaluation. The obtained sensitivity analysis result is used for evaluating the sensitivity of the text information of the first software from multiple dimensions.
And performing horizontal inter-class sensitivity ranking according to the sensitivity analysis result, wherein the horizontal inter-class ranking can be understood as sensitivity ranking among different main feature words, for example: the sensitivity between different human units is ranked. The hiler sorting algorithm is essentially a packet insertion method, and is an improved method for direct insertion sorting.
Step S600: obtaining main feature word subsets corresponding to the first K lateral inter-class sensitivities on the basis of the ranking result of the lateral inter-class sensitivities;
step S700: and generating a first early warning instruction based on the main characteristic word subset, and managing the first software based on the first early warning instruction.
Specifically, according to the ranking result of the sensitivity among the horizontal classes, the main feature word subsets corresponding to the sensitivities among the first K horizontal classes are intercepted, and K can be set according to the user requirements, such as the first 3, the first 10, the first 50 and the like. The main characteristic word subset is a sensitive word set with sensitivity ranking positioned at the top K in the main characteristic words. And taking the main feature word subset as content needing early warning, sending the main feature word subset to a first target user based on a first early warning instruction for improving the alertness of the first target user, and sending the main feature word subset to a software verifying personnel for managing and controlling the potential risk of the first software. The effects of improving the identification efficiency and the identification accuracy of the sensitive information and improving the experience of the user in using the software are achieved.
Further, the embodiment S500 of the present application further includes:
step 551: obtaining category information of the first high-frequency vocabulary set, and obtaining first length information based on the category information;
step S552: performing horizontal category grouping by taking the first length information as an interval, and sequencing in a group according to the sensitivity analysis result;
step S553: obtaining second length information based on the first length information, performing transverse classification grouping according to the second length information, and sequencing in a group according to the sensitivity analysis result;
step S554: and continuously resetting intervals, grouping and sequencing until the interval length is 1, and performing in-group sequencing to obtain the sensitivity sequencing result among the transverse classes.
Specifically, the category information of the first high-frequency vocabulary set includes information on how many categories the first high-frequency vocabulary set has, that is, the number of categories. And (4) sorting the sensitivity among the classes by using a Hill sorting method. And obtaining first length information based on the category information, wherein the first length information is set by self according to the category information, and half of the number of categories can be generally selected. And grouping the first length information as intervals, and sequencing the grouped groups according to the sensitivity analysis result of each high-frequency vocabulary set from high to low. Selecting any length shorter than the first length as second length information according to the first length information, preferably selecting half of the first length information as the second length information, grouping again by taking the second length information as an interval, sequencing from high to low in the group, continuing grouping and sequencing according to the method until the interval length is 1, stopping dividing the interval, sequencing for the last time after the interval length is 1, and finally obtaining the result of sequencing the sensitivity between the transverse classes from high to low. Through the sequencing of the Hill sequencing algorithm, each type of high-frequency words in the first high-frequency word set can be sequenced quickly, so that a foundation is laid for the generation of subsequent early warning information.
Further, the embodiment of the present application further includes:
step S710: performing emotional characteristic analysis on the first classification result to obtain a second high-frequency vocabulary set;
step S720: performing emotion polarity classification on the second high-frequency vocabulary set to obtain a forward emotion word set, a reverse emotion word set and a neutral emotion word set;
step S730: performing in-class emotion word proportion analysis according to the word frequency information of each polar emotion word set to obtain a first proportion coefficient set;
step S740: and according to the first proportion coefficient set, carrying out user emotion scoring on the first classification result to obtain a user emotion scoring result.
Specifically, the first classification result is a first high-frequency vocabulary set obtained through the word frequency analysis in the text analysis, and the extraction of the vocabulary with the emotional characteristics in the first classification result can be continued through the emotion analysis, which is exemplary: words like happy, convenient, far away and the like are words with emotional characteristics. The sentiment analysis can mainly utilize some comment texts with sentiment colors so as to supplement the first high-frequency words. And taking the emotional characteristic words as second high-frequency words according to the emotional characteristic analysis to form a second high-frequency word set, wherein the second high-frequency word set corresponds to the first high-frequency word set one by one.
Because the emotion is divided into positive, neutral and negative, the second high-frequency vocabulary set is classified according to the polarity of the emotion, and three subclasses are further subdivided in each class of second high-frequency vocabulary. And classifying the words to obtain a positive emotion word set, a negative emotion word set and a neutral emotion word set, performing emotion word proportion analysis on each second high-frequency word class through word frequency statistics to obtain a proportion coefficient of each emotion word class, wherein all the proportion coefficients form the first proportion coefficient set. And the user emotion scoring result is obtained by weighted calculation of all the emotion characteristic vocabulary ratios and corresponding scores. The score value can be set by itself, for example: the forward word is divided into 50 points, the neutral word is divided into 30 points, and the backward word is divided into-50 points. The user emotion scoring result reflects the emotion experience of most users similar to the first target user of the first software on the Internet, and has a greater reference significance for the first target user.
Further, as shown in fig. 3, step S740 in the embodiment of the present application further includes:
step S741: obtaining a first emotion scoring threshold interval;
step S742: if the user emotion scoring result is lower than the first emotion scoring threshold interval, first marking information is obtained;
step S743: if the emotion scoring result of the user is higher than the first emotion scoring threshold interval, second marking information is obtained;
step S744: if the user emotion scoring result falls into the first emotion scoring threshold interval, obtaining third marking information;
step S745: adding the first tag information, the second tag information, and the third tag information to the first warning instruction.
Specifically, since a higher emotion score indicates better user experience and a lower emotion score indicates worse user experience, if the emotion score of the user can be added to the first warning instruction, public information on the first software is evaluated from another dimension, that is, the user experience dimension. A first sentiment scoring threshold interval is obtained, and the scoring threshold interval is generally set to be a median value for distinguishing good, medium and poor user experiences. Assuming that the setting is 55-65 points, the interval of 55-65 points is general for the user experience, and neither good nor bad is said.
And when the emotion scoring result of the user is lower than the first emotion scoring threshold interval, which indicates that the user experience is poor, the corresponding second high-frequency vocabulary obtains first mark information with poor user experience. When the user emotion scoring result is higher than the first emotion scoring threshold interval, which indicates that the user experience is good, the corresponding second high-frequency vocabulary obtains second mark information with good user experience. When the user emotion scoring result falls into the first emotion scoring threshold interval, the user experience is general, and the corresponding second high-frequency vocabulary obtains third mark information of the user experience. After the marking is finished, when a first early warning instruction is generated, according to the marking information matched with the corresponding second high-frequency vocabulary in the main feature word subset, the marking information is added to the first early warning instruction.
Further, as shown in fig. 4, step S700 in the embodiment of the present application further includes:
step S750: obtaining a first time period, and obtaining a first early warning instruction set received by a first target user based on the first time period;
step S760: acquiring a behavior data set of the first target user to a first early warning instruction set;
step S770: constructing a first target user representation based on the first set of early warning instructions and the set of behavioral data;
step S780: and generating a second early warning instruction for multiple target users meeting the first target user portrait.
Specifically, the first time period is a period of time intercepted from the time when the first target user uses the first software, a first early warning instruction set received by the first target user in the period of time is collected, and a behavior data set is obtained by tracking the operation behavior of the first user on the first software, wherein the behavior data set comprises the first early warning instruction adopted by the first user and refused to be adopted by the first user. The tracking of operational behavior may be understood as: and assuming that after the recruitment software receives the first early warning instruction, the user A still carries out online communication and resume delivery with the company in the first early warning instruction, the chat texts can be captured, and therefore the user behavior data is judged to be the first early warning instruction refused to be adopted. Information in the segment area concerned by the first target user can be summarized according to the first early warning instruction set, for example: farming, forestry, herding, humanity, information communication and the like, and establishing a user portrait for a first target user based on the existing user portrait method according to the first early warning instruction set and the behavior data set. The user portrait is substantially user datamation, and is a tagged image abstracted by the user through the user browsing content, basic information filled by the user and behavior data of the user. And constructing user portrait for other target users of the first software, wherein the other target users have the same role as the first target user, comparing the user portrait by comparing the similarity of the user tagged images, namely the similarity of the user tags, and calling the users with certain portrait similarity as the multi-target users meeting the first target user portrait. The following are exemplary: the first target user is a job seeker king, a plurality of persons such as job seekers, small plums and Zhao-Zhao are matched by comparing the user image of the king with the user images of other job seekers, and the matched persons are multiple target users meeting the first target user image. And sending the first early warning instruction set of the first target user as the second early warning instruction to the multiple target users, so as to add an early warning instruction, namely the second early warning instruction, for the users with certain similarity.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus necessary general-purpose hardware, and certainly can also be implemented by special-purpose hardware including special-purpose integrated circuits, special-purpose CPUs, special-purpose memories, special-purpose components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions may be various, such as analog circuits, digital circuits, or dedicated circuits. However, for the present application, the implementation of a software program is more preferable. Based on such understanding, the technical solutions of the present application may be substantially embodied in the form of a software product, which is stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk of a computer, and includes several instructions for causing a computer device to execute the method according to the embodiments of the present application.
To sum up, the internet-based computer software management system provided by the embodiment of the present application has the following technical effects:
1. the method comprises the steps of obtaining first preprocessing data information of first software; constructing a main feature word set, and performing feature extraction on the first preprocessed data information to obtain a main feature word extraction result; connecting a multi-party data source according to the main feature word extraction result, and performing data processing to obtain a first classification result; performing text analysis to obtain a first high-frequency vocabulary set; performing sensitivity analysis based on the first high-frequency vocabulary set, and performing horizontal inter-class sensitivity sequencing according to the sensitivity analysis result; and generating a first early warning instruction based on the sequencing result, and managing the first software. The method achieves the technical effects that the sensitive information is identified for the software by constructing the sensitivity analysis method, and the identification efficiency and the identification accuracy of the sensitive information are improved by the text analysis technology, so that the experience of the user using the software is improved, and the fraud risk of the user is reduced.
2. Due to the fact that the method based on the applicable emotion feature analysis is adopted, emotion polarity classification is carried out, the user emotion scoring result is obtained, correlation is carried out according to the user emotion scoring result and user experience, text content is deeply mined, and the emotion mark is added to the first early warning instruction, so that the technical effect of using experience of others for reference is achieved.
Example two
Based on the same inventive concept as the internet-based computer software management method in the foregoing embodiment, the present invention further provides an internet-based computer software management system, as shown in fig. 5, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to interface open data information of first software, screen the open data information of the first software, and obtain first preprocessed data information of the first software;
the second obtaining unit 12, where the second obtaining unit 12 is configured to construct a main feature word set, perform main feature word extraction on the first preprocessed data information, and obtain a main feature word extraction result;
a third obtaining unit 13, where the third obtaining unit 13 is configured to, according to the main feature word extraction result, perform data integration, preprocessing, and classification on a multi-party data source to obtain a first classification result;
a fourth obtaining unit 14, where the fourth obtaining unit 14 is configured to perform text analysis on the first classification result to obtain a first high-frequency vocabulary set;
the first execution unit 15 is configured to perform sensitivity analysis based on the first high-frequency vocabulary set, and perform horizontal inter-class sensitivity ranking according to a sensitivity analysis result;
a fifth obtaining unit 16, where the fifth obtaining unit 16 is configured to obtain, based on the horizontal inter-class sensitivity ranking result, main feature word subsets corresponding to the top K horizontal inter-class sensitivities;
a second execution unit 17, where the second execution unit 17 is configured to generate a first warning instruction based on the main feature word subset, and send the first warning instruction to a first target user.
Further, the system further comprises:
a first construction unit for constructing a sensitivity evaluation index set based on the first software;
a sixth obtaining unit configured to obtain a standard threshold range set of the sensitivity evaluation index set;
a seventh obtaining unit configured to obtain a list of degrees of deviation of the sensitivity evaluation index based on the set of standard threshold ranges;
an eighth obtaining unit, configured to perform weight distribution based on the standard threshold range set, and obtain a weight distribution result;
a ninth obtaining unit configured to obtain the sensitivity analysis result based on the sensitivity evaluation index set, the deviation degree list, and the weight assignment result.
Further, the system further comprises:
a tenth obtaining unit, configured to obtain category information of the first high-frequency vocabulary set, and obtain first length information based on the category information;
the third execution unit is used for performing horizontal category grouping by taking the first length information as an interval, and sorting the groups according to the sensitivity analysis result;
a fourth execution unit, configured to obtain second length information based on the first length information, perform horizontal category grouping according to the second length information, and sort groups according to the sensitivity analysis result;
and the eleventh obtaining unit is used for continuously resetting intervals, grouping and sorting until the interval length is 1, and performing intra-group sorting to obtain the horizontal inter-class sensitivity sorting result.
Further, the system further comprises:
a twelfth obtaining unit, configured to obtain a first target user and a second target user of the first software;
a thirteenth obtaining unit, configured to obtain a second target user security management element based on the association manner information of the second target user and the first target user;
a fifth execution unit, configured to collect attention intention information of the first target user to the first software;
a second constructing unit, configured to construct the main feature word set based on the attention intention information and the second target user security management element.
Further, the system further comprises:
a fourteenth obtaining unit, configured to perform emotion feature analysis on the first classification result, and obtain a second high-frequency vocabulary set;
a fifteenth obtaining unit, configured to perform emotion polarity classification on the second high-frequency vocabulary set, and obtain a forward emotion word set, a reverse emotion word set, and a neutral emotion word set;
a sixteenth obtaining unit, configured to perform intra-class emotion word proportion analysis according to the word frequency information of each polar emotion word set, to obtain a first scale coefficient set;
a seventeenth obtaining unit, configured to perform user emotion scoring on the first classification result according to the first scale coefficient set, and obtain a user emotion scoring result.
Further, the system further comprises:
an eighteenth obtaining unit, configured to obtain a first emotion score threshold interval;
a nineteenth obtaining unit, configured to obtain first label information if the user emotion scoring result is lower than the first emotion scoring threshold interval;
a twentieth obtaining unit, configured to obtain second label information if the user emotion scoring result is higher than the first emotion scoring threshold interval;
a twenty-first obtaining unit, configured to obtain third tag information if the user emotion scoring result falls into the first emotion scoring threshold interval;
a sixth execution unit, configured to add the first tag information, the second tag information, and the third tag information to the first warning instruction.
Further, the system further comprises:
a twenty-second obtaining unit, configured to obtain a first time period, and obtain, based on the first time period, a first warning instruction set received by a first target user;
a twenty-third obtaining unit, configured to obtain a behavior data set of the first target user for a first set of warning instructions;
a third construction unit to construct a first target user representation based on the first set of early warning instructions and the set of behavioral data;
a seventh execution unit to generate a second warning instruction for a plurality of target users satisfying the first target user representation.
In the embodiment of the present application, the network device and the terminal device may be divided into functional modules according to the above method example, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one receiving module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and another division manner may be available in actual implementation. Through the foregoing detailed description of the internet-based computer software management system, those skilled in the art can clearly understand the implementation method of the internet-based computer software management system in the present embodiment, so for the brevity of the description, detailed description is not provided herein.
Exemplary electronic device
FIG. 6 is a schematic diagram of a computing device of the present application. The computing device 90 shown in fig. 6 may include: memory 91, processor 92, input/output interface 93. The memory 91, the processor 92 and the input/output interface 93 are connected through an internal connection path, the memory 33 is used for storing instructions, and the processor 92 is used for executing the instructions stored in the memory 91 so as to control the input/output interface 93 to receive input data and information and output data such as operation results.
FIG. 6 is a schematic diagram of a computing device of another embodiment of the present application. The computing device 90 shown in fig. 6 may include a memory 91, a processor 92, and an input/output interface 93. The memory 91, the processor 92 and the input/output interface 93 are connected through an internal connection path, the memory 91 is used for storing instructions, and the processor 92 is used for executing the instructions stored in the memory 92 so as to control the input/output interface 93 to receive input data and information and output data such as operation results.
In implementation, the steps of the above method may be performed by instructions in the form of hardware, integrated logic circuits, or software in the processor 92. The method for recognizing the abnormal message and/or the method for training the abnormal message recognition model disclosed by the embodiment of the application can be directly implemented by a hardware processor, or implemented by combining hardware and software modules in the processor. The software module may be located in a random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, or other storage medium known in the art. The storage medium is located in the memory 91, and the processor 92 reads the information in the memory 91 and performs the steps of the above method in combination with the hardware thereof. To avoid repetition, it is not described in detail here.
It should be understood that in the embodiment of the present application, the processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be appreciated that in embodiments of the present application, the memory may comprise both read-only memory and random access memory, and may provide instructions and data to the processor. A portion of the processor may also include non-volatile random access memory. For example, the processor may also store information of the device type.
It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
In the several embodiments provided in this application, it should be understood that the disclosed system, and method may be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, indirect coupling or communication connection of systems or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable system. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be read by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., Digital Versatile Disk (DVD)), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the present application.
Claims (9)
1. An internet-based computer software management system, the system comprising:
the first obtaining unit is used for butting open data information of first software, screening the open data information of the first software and obtaining first preprocessing data information of the first software;
the second obtaining unit is used for constructing a main feature word set, and extracting the main feature words of the first preprocessed data information to obtain a main feature word extraction result;
the third obtaining unit is used for butting a multi-party data source according to the main feature word extraction result, and obtaining a first classification result after data integration, pretreatment and classification are carried out;
a fourth obtaining unit, configured to perform text analysis on the first classification result to obtain a first high-frequency vocabulary set;
the first execution unit is used for carrying out sensitivity analysis based on the first high-frequency vocabulary set and carrying out horizontal inter-class sensitivity sequencing according to a sensitivity analysis result;
a fifth obtaining unit, configured to obtain, based on the inter-horizontal-class sensitivity ranking result, main feature word subsets corresponding to the first K inter-horizontal-class sensitivities;
and the second execution unit is used for generating a first early warning instruction based on the main characteristic word subset and sending the first early warning instruction to a first target user.
2. The system of claim 1, wherein the first execution unit comprises:
a first construction unit for constructing a sensitivity evaluation index set based on the first software;
a sixth obtaining unit configured to obtain a standard threshold range set of the sensitivity evaluation index set;
a seventh obtaining unit configured to obtain a list of degrees of deviation of the sensitivity evaluation index based on the set of standard threshold ranges;
an eighth obtaining unit, configured to perform weight distribution based on the standard threshold range set, and obtain a weight distribution result;
a ninth obtaining unit configured to obtain the sensitivity analysis result based on the sensitivity evaluation index set, the deviation degree list, and the weight assignment result.
3. The system of claim 2, wherein the system comprises:
a tenth obtaining unit, configured to obtain category information of the first high-frequency vocabulary set, and obtain first length information based on the category information;
the third execution unit is used for performing horizontal category grouping by taking the first length information as an interval, and sorting the groups according to the sensitivity analysis result;
a fourth execution unit, configured to obtain second length information based on the first length information, perform horizontal category grouping according to the second length information, and sort the groups according to the sensitivity analysis result;
and the eleventh obtaining unit is used for continuously resetting intervals, grouping and sorting until the interval length is 1, and performing intra-group sorting to obtain the horizontal inter-class sensitivity sorting result.
4. The system of claim 1, wherein the second obtaining unit comprises:
a twelfth obtaining unit, configured to obtain a first target user and a second target user of the first software;
a thirteenth obtaining unit, configured to obtain a second target user security management element based on the association manner information of the second target user and the first target user;
a fifth execution unit, configured to collect attention intention information of the first target user on the first software;
a second constructing unit, configured to construct the main feature word set based on the attention intention information and the second target user security management element.
5. The system of claim 1, wherein the system comprises:
a fourteenth obtaining unit, configured to perform emotion feature analysis on the first classification result, and obtain a second high-frequency vocabulary set;
a fifteenth obtaining unit, configured to perform emotion polarity classification on the second high-frequency vocabulary set, and obtain a forward emotion word set, a reverse emotion word set, and a neutral emotion word set;
a sixteenth obtaining unit, configured to perform intra-class emotion word proportion analysis according to the word frequency information of each polar emotion word set, to obtain a first scale coefficient set;
a seventeenth obtaining unit, configured to perform user emotion scoring on the first classification result according to the first scale coefficient set, and obtain a user emotion scoring result.
6. The system of claim 5, wherein the system comprises:
an eighteenth obtaining unit, configured to obtain a first emotion score threshold interval;
a nineteenth obtaining unit, configured to obtain first tag information if the user emotion scoring result is lower than the first emotion scoring threshold interval;
a twentieth obtaining unit, configured to obtain second label information if the user emotion scoring result is higher than the first emotion scoring threshold interval;
a twenty-first obtaining unit, configured to obtain third tag information if the user emotion scoring result falls into the first emotion scoring threshold interval;
a sixth execution unit, configured to add the first tag information, the second tag information, and the third tag information to the first warning instruction.
7. The system of claim 1, wherein the system comprises:
a twenty-second obtaining unit, configured to obtain a first time period, and obtain, based on the first time period, a first warning instruction set received by a first target user;
a twenty-third obtaining unit, configured to obtain a behavior data set of the first target user for a first set of warning instructions;
a third construction unit to construct a first target user representation based on the first set of early warning instructions and the set of behavioral data;
a seventh execution unit to generate a second warning instruction for a plurality of target users satisfying the first target user representation.
8. An internet-based computer software management method applied to the internet-based computer software management system according to any one of claims 1 to 7, the method comprising:
the method comprises the steps of butting open data information of first software, screening the open data information of the first software, and obtaining first preprocessing data information of the first software;
constructing a main feature word set, and performing main feature word extraction on the first preprocessed data information to obtain a main feature word extraction result;
butting a plurality of data sources according to the main feature word extraction result, and performing data integration, preprocessing and classification to obtain a first classification result;
performing text analysis on the first classification result to obtain a first high-frequency vocabulary set;
performing sensitivity analysis based on the first high-frequency vocabulary set, and performing horizontal inter-class sensitivity sequencing according to a sensitivity analysis result;
obtaining main feature word subsets corresponding to the first K lateral inter-class sensitivities on the basis of the ranking result of the lateral inter-class sensitivities;
and generating a first early warning instruction based on the main characteristic word subset, and sending the first early warning instruction to a first target user.
9. An internet-based computer software management system comprising at least one processor and a memory, the at least one processor coupled with the memory for reading and executing instructions in the memory, to perform the system of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210692532.0A CN115033880A (en) | 2022-06-17 | 2022-06-17 | Computer software management system based on internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210692532.0A CN115033880A (en) | 2022-06-17 | 2022-06-17 | Computer software management system based on internet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115033880A true CN115033880A (en) | 2022-09-09 |
Family
ID=83125242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210692532.0A Pending CN115033880A (en) | 2022-06-17 | 2022-06-17 | Computer software management system based on internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115033880A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115526173A (en) * | 2022-10-12 | 2022-12-27 | 湖北大学 | Feature word extraction method and system based on computer information technology |
-
2022
- 2022-06-17 CN CN202210692532.0A patent/CN115033880A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115526173A (en) * | 2022-10-12 | 2022-12-27 | 湖北大学 | Feature word extraction method and system based on computer information technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163478B (en) | Risk examination method and device for contract clauses | |
| Zhang et al. | Casm: A deep-learning approach for identifying collective action events with text and image data from social media | |
| Zannettou et al. | On the origins of memes by means of fringe web communities | |
| JP6986527B2 (en) | How and equipment to process video | |
| US20160285918A1 (en) | System and method for classifying documents based on access | |
| Himdi et al. | Arabic fake news detection based on textual analysis | |
| CN111444387A (en) | Video classification method and device, computer equipment and storage medium | |
| Bonifazi et al. | A social network analysis–based approach to investigate user behaviour during a cryptocurrency speculative bubble | |
| CN111783126B (en) | Private data identification method, device, equipment and readable medium | |
| CN112132238A (en) | Method, device, equipment and readable medium for identifying private data | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN114693192A (en) | Wind control decision method and device, computer equipment and storage medium | |
| Perez et al. | I Call BS: Fraud detection in crowdfunding campaigns | |
| CN115033880A (en) | Computer software management system based on internet | |
| Amorim et al. | Novelty detection in social media by fusing text and image into a single structure | |
| Wang et al. | An explainable sentiment prediction model based on the portraits of users sharing representative opinions in social sensors | |
| Bhoj et al. | LSTM powered identification of clickbait content on entertainment and news websites | |
| CN115098794A (en) | Public opinion manufacturing group identification method, device, equipment and storage medium | |
| Motohashi et al. | Technological competitiveness of China's internet platformers: comparison of Google and Baidu by using patent text information | |
| Xu et al. | Identify user variants based on user behavior on social media | |
| CN111914542A (en) | Suspected illegal investment market subject identification method, device, terminal and storage medium | |
| Xiong | A method of mining key accounts from internet pyramid selling data | |
| US20190304040A1 (en) | System and Method for Vetting Potential Jurors | |
| Shandilya et al. | Fairness for whom? Understanding the reader’s perception of fairness in text summarization | |
| CN109409189A (en) | Dangerous person's recognition methods and device based on network trace |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |