CN114661974A - Method for public opinion analysis and early warning of government affair website by utilizing natural language semantic analysis - Google Patents

Method for public opinion analysis and early warning of government affair website by utilizing natural language semantic analysis Download PDF

Info

Publication number
CN114661974A
CN114661974A CN202210276938.0A CN202210276938A CN114661974A CN 114661974 A CN114661974 A CN 114661974A CN 202210276938 A CN202210276938 A CN 202210276938A CN 114661974 A CN114661974 A CN 114661974A
Authority
CN
China
Prior art keywords
public opinion
image
warning
public
analysis
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.)
Granted
Application number
CN202210276938.0A
Other languages
Chinese (zh)
Other versions
CN114661974B (en
Inventor
严彦
赵根
闫亮
王彦集
李翔
罗波
洪永文
侯伟
戴一明
彭丽媛
郑翔
付世娇
张运
邹敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Planning And Natural Resources Information Center
Original Assignee
Chongqing Planning And Natural Resources Information Center
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Planning And Natural Resources Information Center filed Critical Chongqing Planning And Natural Resources Information Center
Priority to CN202210276938.0A priority Critical patent/CN114661974B/en
Publication of CN114661974A publication Critical patent/CN114661974A/en
Application granted granted Critical
Publication of CN114661974B publication Critical patent/CN114661974B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
    • H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
    • H04L63/0435—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload wherein the sending and receiving network entities apply symmetric encryption, i.e. same key used for encryption and decryption
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
    • H04L63/083—Network architectures or network communication protocols for network security for authentication of entities using passwords
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Security & Cryptography (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Library & Information Science (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Hardware Design (AREA)
  • Computing Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Probability & Statistics with Applications (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a method for public opinion analysis and early warning of a government affair website by utilizing natural language semantic analysis, which comprises the following steps: s1, judging whether public opinion warning words exist in the collected text information data: if public opinion warning words exist in the collected text information data, executing the next step; if the public opinion warning words do not exist in the collected text information data, continuing to wait, and returning to the step S1; and S2, extracting the user ID corresponding to the public sentiment warning word and giving out the public sentiment warning word, collecting the speech of the user ID within a period of time, and pushing the speech to a website administrator. The invention can realize public opinion monitoring and pushing of the character information collected on the government platform.

Description

Method for public opinion analysis and early warning of government affair website by utilizing natural language semantic analysis
Technical Field
The invention relates to the technical field of government affair public sentiment, in particular to a method for public sentiment analysis and early warning of a government affair website by utilizing natural language semantic analysis.
Background
Public opinion monitoring is a complex technology which crosses social science and data science, and needs to have preliminary prejudgment on events at the initial stage of public opinion occurrence so as to fully make preparation for coping. The description of the public opinion events mainly comes from news texts on network media and social platforms similar to Sina microblogs, and people directly inform others or indirectly know the related information of the public opinion events from others through reading, forwarding, commenting and the like.
Disclosure of Invention
The invention aims to at least solve the technical problems in the prior art, and particularly creatively provides a method for public opinion analysis and early warning of a government affair website by utilizing natural language semantic analysis, which comprises the following steps:
s1, judging whether public sentiment warning words exist in the collected text information data:
if public opinion warning words exist in the collected text information data, executing the next step;
if the public opinion warning words do not exist in the collected text information data, continuing to wait, and returning to the step S1;
and S2, extracting the user ID which sends the public sentiment warning words and corresponds to the public sentiment warning words, collecting the speech of the user ID within a period of time, and pushing the speech to a website administrator.
In a preferred embodiment of the invention, the speech includes one or any combination of reading, forwarding, and commenting.
In a preferred embodiment of the present invention, the push mode includes one or any combination of a short message, an email, and a mobile phone voice message.
In a preferred embodiment of the present invention, step S1 includes the following steps:
s11, acquiring an image file, and extracting character data in the image file according to the acquired image file;
s12, acquiring a public opinion warning word database, grouping the acquired public opinion warning words, setting a public opinion central warning word as a standard public opinion word for each group of public opinion warning words, setting the distance from other similar public opinion words to the standard public opinion word to be less than a preset distance threshold value by using the standard public opinion word as an initial node, and dividing the similar public opinion words into the same group;
and S13, identifying the public opinion warning words according to the character data extracted in the step S11.
In a preferred embodiment of the present invention, the format of the image file includes one or any combination of bmp, jpg, png, tif, gif.
In conclusion, by adopting the technical scheme, the public opinion monitoring and pushing method and the public opinion monitoring and pushing device can realize public opinion monitoring and pushing on the character information collected on the government platform.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow diagram of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
The invention provides a method for public opinion analysis and early warning of a government affairs website by utilizing natural language semantic analysis, which comprises the following steps as shown in figure 1:
s1, judging whether public sentiment warning words exist in the collected text information data:
if public opinion warning words exist in the collected text information data, executing the next step;
if the public opinion warning words do not exist in the collected text information data, continuing to wait, and returning to the step S1;
and S2, extracting the user ID which sends the public sentiment warning words and corresponds to the public sentiment warning words, collecting the speech of the user ID within a period of time, and pushing the speech to a website administrator. The statement comprises one or any combination of reading, forwarding and commenting; the pushing mode comprises one or any combination of short messages, electronic mailboxes and mobile phone voice messages.
In a preferred embodiment of the present invention, step S1 includes the following steps:
s11, acquiring an image file, wherein the format of the image file comprises one or any combination of bmp, jpg, png, tif and gif, and extracting character data in the image file according to the acquired image file;
s12, acquiring a public opinion warning word database, grouping the acquired public opinion warning words, setting a public opinion central warning word as a standard public opinion word for each group of public opinion warning words, setting the distance from other similar public opinion words to the standard public opinion word to be less than a preset distance threshold value by using the standard public opinion word as an initial node, and dividing the similar public opinion words into the same group;
and S13, identifying the public opinion warning words according to the character data extracted in the step S11.
In a preferred embodiment of the present invention, the method for extracting text data in an image file from an acquired image file in step S11 includes the following steps:
s111, let λ be 1;
s112, operating on the λ -th image:
w＝N/(P×Q)，
wherein Q represents the height of the λ -th image;
p represents the width of the λ -th image;
w represents the ratio of the total number of pixels of the pixel target point to the lambda image;
n represents that the image separation threshold value H is larger than or equal to the number of extracted gray values in the lambda image;
S113，w′＝(-N+P×Q)/P×Q，
w' represents the ratio of the total number of pixels of the pixel background points to the lambda image;
Figure BDA0003556175520000041
where ζ represents a grayscale average of the target image;
Ai∈A＝{A1,A2,A3,…,AN,AN+1}，
a represents a gray value set of all pixel points in a target image;
Aiexpressing the gray value of the ith pixel point in the target image;
S114，
Figure BDA0003556175520000042
where ξ represents the grayscale average of the background image;
Bj∈B＝{B1,B2,B3,…,BP×Q-N,BP×Q-N+1}，
b represents a gray value set of all pixel points in the background image;
Bjexpressing the gray value of the jth pixel point in the background image;
S115，
Figure BDA0003556175520000043
wherein,
Figure BDA0003556175520000045
expressing the gray level average value of the extracted lambda image;
S116，
Figure BDA0003556175520000044
wherein η represents an image variance gray value;
maximizing the image variance gray value eta by using a traversal methodmaxThen, obtaining an image separation threshold value H;
s117, judging an image separation threshold H and extracting a k pixel point gray value I in a lambda imageλ,kThe magnitude of the relationship of (1):
if Iλ,kWhen the ratio is less than or equal to H, let Iλ,k＝255；
If Iλ,kIf > H, then let Iλ,k＝0；k＝1,2,3,…,P×Q；
S118, extracting characters in the target image in the lambda image;
s119, judging lambda and
Figure BDA0003556175520000052
the magnitude of the relationship between:
if it is
Figure BDA0003556175520000053
Representing the total number of images in the image file; then the process is ended;
if it is
Figure BDA0003556175520000054
λ +1, the process returns to step S112.
In a preferred embodiment of the present invention, in step S12, the method for calculating the distance from the near public sentiment word to the standard public sentiment word comprises:
Figure BDA0003556175520000051
wherein, aijRepresenting the part-of-speech values of the similar public sentiment words at the characteristic points (i, j);
i represents the total number of each line of characteristic points in the similar public sentiment words;
j represents the total number of each row of characteristic points in the similar public opinion words;
Figure BDA0003556175520000055
coefficients representing close public sentiment words;
Figure BDA0003556175520000056
bijrepresenting a part-of-speech value of the standard public sentiment word at the characteristic point (i, j);
i' represents the total number of characteristic points of each line in the standard public sentiment words;
j' represents the total number of each row of characteristic points in the standard public sentiment words;
phi represents the coefficient of the standard public sentiment word; φ ∈ (0, 1).
In a preferred embodiment of the present invention, the method further includes step S4, logging in through the mobile intelligent handheld terminal to view the identified public opinion warning words. The method for logging in the server side through the mobile intelligent handheld terminal comprises the following steps:
s41, the server side obtains an SM4 symmetric KEY SM4_ KEY, and the mobile intelligent handheld terminal obtains a communication identifier TK; the method for obtaining the SM4 symmetric KEY SM4_ KEY by the server side and obtaining the communication identification TK by the mobile intelligent handheld terminal comprises the following steps:
s411, the mobile intelligent handheld terminal sends a request for obtaining an SM2 public key to a server, and an SM2 public key SM2_ PUBKEY and SM2 private key SM2_ PRIKEY pair are stored on the server;
s412, after receiving the SM2 public key request sent by the mobile intelligent handheld terminal, the server end returns the SM2 public key SM2_ PUBKEY to the mobile intelligent handheld terminal in a plaintext form;
s413, after receiving the SM2 public KEY SM2_ PUBKEY sent by the server, the mobile intelligent handheld terminal generates an SM4 symmetric KEY SM4_ KEY;
s414, using SM2 public KEY SM2_ PUBKEY to encrypt SM4 symmetric KEY SM4_ KEY by SM2 to obtain ciphertext ENSM4K, and sending the ciphertext ENSM4K to the server;
s415, after receiving the ciphertext ENSM4K sent by the mobile intelligent handheld terminal, the server side decrypts the received ciphertext ENSM4K by using an SM2 private KEY SM2_ PRIKEY to obtain an SM4 symmetric private KEY SM4_ KEY, and generates a communication identifier TK;
s416, establishing association between the TK and the SM4 symmetric KEY SM4_ KEY to form a KV KEY value pair, and storing the KV KEY value pair in a cache server terminal redis; carrying out SM4 symmetric encryption on the communication identifier TK by using an SM4 symmetric KEY SM4_ KEY to obtain an encrypted identifier ENTK, and returning the encrypted identifier ENTK to the mobile intelligent handheld terminal;
s417, the mobile intelligent handheld terminal carries out SM4 symmetric decryption on the received encrypted identifier ENTK by using an SM4 symmetric KEY SM4_ KEY to obtain the communication identifier TK. The SM4 symmetric KEY SM4_ KEY has timeliness, which may be one hour, one day, one month, etc., and updates the SM4 symmetric KEY SM4_ KEY after expiration, and for security, the server may also update the SM2 public KEY SM2_ PUBKEY and SM2 private KEY SM2_ PRIKEY pair at the same time.
S42, the mobile intelligent handheld terminal encrypts the obtained user name and password respectively by using an SM4 symmetric KEY SM4_ KEY to obtain an encrypted user name and an encrypted password; the mobile intelligent handheld terminal sends an encrypted user name, an encrypted password and a communication identifier TK to a server side;
s43, after receiving the encrypted user name, the encrypted password and the communication identifier TK sent by the mobile intelligent handheld terminal, the server side obtains an SM4 symmetric KEY SM4_ KEY corresponding to the communication identifier TK from a cache server side redis according to the communication identifier TK;
s44, the server side decrypts the encrypted user name and the encrypted password by using the SM4 symmetric KEY SM4_ KEY obtained in the step S43 to obtain a decrypted user name and a decrypted password; and after the verification is passed, the mobile intelligent handheld terminal successfully logs in the server side.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims (6)

1. A public opinion analyzing and early warning method for government affairs websites by utilizing natural language semantic analysis is characterized by comprising the following steps:
s1, judging whether public opinion warning words exist in the collected text information data:
if public opinion warning words exist in the collected text information data, executing the next step;
if the public opinion warning words do not exist in the collected text information data, continuing to wait, and returning to the step S1;
and S2, extracting the user ID which sends the public sentiment warning words and corresponds to the public sentiment warning words, collecting the speech of the user ID within a period of time, and pushing the speech to a website administrator.
2. The method for government website public opinion analysis and early warning using natural language semantic analysis according to claim 1, wherein the speech includes one or any combination of reading, forwarding and commenting.
3. The method for public opinion analysis and warning of government affairs website using natural language semantic analysis as claimed in claim 1, wherein the pushing manner includes one or any combination of short message, email, mobile phone voice message.
4. The method for public opinion analysis and warning of government affairs website using semantic analysis according to claim 1, wherein the step S1 comprises the steps of:
s11, acquiring an image file, and extracting character data in the image file according to the acquired image file;
s12, acquiring a public opinion warning word database, grouping the acquired public opinion warning words, setting a public opinion central warning word as a standard public opinion warning word for each group of public opinion warning words, setting the distance from other close public opinion warning words to the standard public opinion warning word to be less than a preset distance threshold value by using the standard public opinion warning word as an initial node, and dividing the close public opinion warning words into the same group;
and S13, identifying the public opinion warning words according to the character data extracted in the step S11.
5. The method for government website public opinion analysis and early warning using natural language semantic analysis according to claim 4, wherein the format of the image file includes one or any combination of bmp, jpg, png, tif, gif.
6. The method for public opinion analysis and warning of government affairs website using semantic analysis of natural language as claimed in claim 4, wherein the method for extracting text data in the image file according to the acquired image file in step S11 comprises the steps of:
s111, making λ 1;
s112, operating on the λ -th image:
w＝N/(P×Q)，
wherein Q represents the height of the λ -th image;
p represents the width of the λ -th image;
w represents the ratio of the total number of pixels of the pixel target point to the lambda image;
n represents that the image separation threshold value H is larger than or equal to the number of extracted gray values in the lambda image;
S113，w′＝(-N+P×Q)/P×Q，
w' represents the ratio of the total number of pixels of the pixel background points to the lambda image;
Figure FDA0003556175510000021
where ζ represents a grayscale average of the target image;
Ai∈A＝{A1,A2,A3,...,AN,AN+1}，
a represents a gray value set of all pixel points in a target image;
Aiexpressing the gray value of the ith pixel point in the target image;
S114，
Figure FDA0003556175510000022
where ξ represents the grayscale average of the background image;
Bj∈B＝{B1,B2,B3,…,BP×Q-N,BP×Q-N+1}，
b represents a gray value set of all pixel points in the background image;
Bjexpressing the gray value of the jth pixel point in the background image;
S115，
Figure FDA0003556175510000023
wherein,
Figure FDA0003556175510000031
expressing the gray level average value of the extracted lambda image;
S116，
Figure FDA0003556175510000032
wherein η represents an image variance gray value;
maximizing the image variance gray value eta by using a traversal methodmaxThen, obtaining an image separation threshold value H;
s117, judging an image separation threshold H and extracting a k pixel point gray value I in a lambda imageλ,kThe magnitude of the relationship of (1):
if Iλ,kWhen the ratio is less than or equal to H, let Iλ,k＝255；
If Iλ,kIf > H, then let Iλ,k＝0；k＝1,2,3,…,P×Q；
S118, extracting characters in the target image in the lambda image;
s119, judging lambda and
Figure FDA0003556175510000033
magnitude of the relationship between:
if it is
Figure FDA0003556175510000034
Figure FDA0003556175510000035
Representing the total number of images in the image file; then the process is finished;
if it is
Figure FDA0003556175510000036
λ +1, the process returns to step S112.
CN202210276938.0A 2022-03-21 2022-03-21 Government website public opinion analysis and early warning method by utilizing natural language semantic analysis Active CN114661974B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210276938.0A CN114661974B (en) 2022-03-21 2022-03-21 Government website public opinion analysis and early warning method by utilizing natural language semantic analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210276938.0A CN114661974B (en) 2022-03-21 2022-03-21 Government website public opinion analysis and early warning method by utilizing natural language semantic analysis

Publications (2)

Publication Number Publication Date
CN114661974A true CN114661974A (en) 2022-06-24
CN114661974B CN114661974B (en) 2024-03-08

Family

ID=82031379

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210276938.0A Active CN114661974B (en) 2022-03-21 2022-03-21 Government website public opinion analysis and early warning method by utilizing natural language semantic analysis

Country Status (1)

Country Link
CN (1) CN114661974B (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001067362A (en) * 1999-08-25 2001-03-16 Hitachi Ltd Word importance calculation method, document retrieving interface and word dictionary preparing method
CN105183847A (en) * 2015-09-07 2015-12-23 北京京东尚科信息技术有限公司 Feature information collecting method and device for web review data
CN107315778A (en) * 2017-05-31 2017-11-03 温州市鹿城区中津先进科技研究院 A kind of natural language the analysis of public opinion method based on big data sentiment analysis
CN108595472A (en) * 2018-03-07 2018-09-28 合肥工业大学 A kind of government website public sentiment monitoring system based on semantic analysis
CN108776671A (en) * 2018-05-12 2018-11-09 苏州华必讯信息科技有限公司 A kind of network public sentiment monitoring system and method
WO2019227710A1 (en) * 2018-05-31 2019-12-05 平安科技（深圳）有限公司 Network public opinion analysis method and apparatus, and computer-readable storage medium
CN110991218A (en) * 2019-10-10 2020-04-10 北京邮电大学 Network public opinion early warning system and method based on images
CN111460814A (en) * 2020-03-10 2020-07-28 中国平安人寿保险股份有限公司 Sensitive information detection method, device, terminal and medium
CN111783456A (en) * 2020-07-14 2020-10-16 北京伯乐互联科技发展有限公司 Public opinion analysis method using semantic analysis technology
CN111931027A (en) * 2020-08-17 2020-11-13 深圳新闻网传媒股份有限公司 Intelligent news public opinion early warning system
CN112434226A (en) * 2020-12-15 2021-03-02 易研信息科技有限公司 Network public opinion monitoring and early warning method
CN113015171A (en) * 2021-04-09 2021-06-22 安徽舆鹰信息技术有限公司 System with network public opinion monitoring and analyzing functions
CN113128209A (en) * 2021-04-22 2021-07-16 百度在线网络技术（北京）有限公司 Method and device for generating word stock

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001067362A (en) * 1999-08-25 2001-03-16 Hitachi Ltd Word importance calculation method, document retrieving interface and word dictionary preparing method
CN105183847A (en) * 2015-09-07 2015-12-23 北京京东尚科信息技术有限公司 Feature information collecting method and device for web review data
CN107315778A (en) * 2017-05-31 2017-11-03 温州市鹿城区中津先进科技研究院 A kind of natural language the analysis of public opinion method based on big data sentiment analysis
CN108595472A (en) * 2018-03-07 2018-09-28 合肥工业大学 A kind of government website public sentiment monitoring system based on semantic analysis
CN108776671A (en) * 2018-05-12 2018-11-09 苏州华必讯信息科技有限公司 A kind of network public sentiment monitoring system and method
WO2019227710A1 (en) * 2018-05-31 2019-12-05 平安科技（深圳）有限公司 Network public opinion analysis method and apparatus, and computer-readable storage medium
CN110991218A (en) * 2019-10-10 2020-04-10 北京邮电大学 Network public opinion early warning system and method based on images
CN111460814A (en) * 2020-03-10 2020-07-28 中国平安人寿保险股份有限公司 Sensitive information detection method, device, terminal and medium
CN111783456A (en) * 2020-07-14 2020-10-16 北京伯乐互联科技发展有限公司 Public opinion analysis method using semantic analysis technology
CN111931027A (en) * 2020-08-17 2020-11-13 深圳新闻网传媒股份有限公司 Intelligent news public opinion early warning system
CN112434226A (en) * 2020-12-15 2021-03-02 易研信息科技有限公司 Network public opinion monitoring and early warning method
CN113015171A (en) * 2021-04-09 2021-06-22 安徽舆鹰信息技术有限公司 System with network public opinion monitoring and analyzing functions
CN113128209A (en) * 2021-04-22 2021-07-16 百度在线网络技术（北京）有限公司 Method and device for generating word stock

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
刘树春等: "《深度实践OCR 基于深度学习的文字识别》", 30 May 2020, pages: 13 - 17 *
刘润奇等: "网络多媒体数据中舆情关联主题的挖掘方法", 深圳大学学报(理工版), 27 December 2019 (2019-12-27), pages 72 - 78 *
吴良斌: "《SAR图像处理与目标识别》", 30 January 2013, pages: 151 - 158 *
李曦等: "基于属性加密的共享文件分级访问控制方案", 燕山大学学报, 30 September 2017 (2017-09-30), pages 450 - 455 *

Also Published As

Publication number Publication date
CN114661974B (en) 2024-03-08

Similar Documents

Publication Publication Date Title
Gurajala et al. Fake Twitter accounts: profile characteristics obtained using an activity-based pattern detection approach
US10181168B2 (en) Personal safety verification system and similarity search method for data encrypted for confidentiality
EP2698967A1 (en) Social network data mining method for terminal user, and relevant method, device and system
CN112614586B (en) Remote disease intelligent diagnosis system based on medical images and block chains
CN113656807B (en) Vulnerability management method, device, equipment and storage medium
CN104883671B (en) A kind of judgment method and system of refuse messages
CN109995929B (en) Operation and account information processing method and device
CN105701224B (en) Security information customized service system based on big data
US11431749B2 (en) Method and computing device for generating indication of malicious web resources
WO2016177148A1 (en) Short message interception method and device
CN107516210A (en) A kind of method of mobile payment based on Quick Response Code and bluetooth for track traffic
WO2022151639A1 (en) Method and apparatus for extracting picture to be identified, and device and storage medium
CN112818316A (en) Voiceprint-based identity recognition and application method, device and equipment
CN116108491A (en) Data leakage early warning method, device and system based on semi-supervised federal learning
US11487898B2 (en) System for providing query processing service based on personal information protection
CN108510235A (en) Management system for hunter's industry
CN114036264B (en) Email authorship attribution identification method based on small sample learning
WO2021112881A1 (en) System and method for short message service (sms) content classification
CN114661974B (en) Government website public opinion analysis and early warning method by utilizing natural language semantic analysis
CN117436047A (en) Verification code generation method, device, computer equipment and storage medium
US10200355B2 (en) Methods and systems for generating a user profile
CN114661934B (en) Method for multidimensional monitoring of government new media public opinion early warning based on data mining analysis technology
CN113420549B (en) Abnormal character string identification method and device
CN113221984B (en) User drunk driving behavior analysis and prediction method, device, equipment and storage medium
CN114997423A (en) Semi-centralized confrontation training method for federal learning

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
GR01 Patent grant
GR01 Patent grant