CN115859380A - Electronic data solid certificate correlation method - Google Patents
Electronic data solid certificate correlation method Download PDFInfo
- Publication number
- CN115859380A CN115859380A CN202310175666.XA CN202310175666A CN115859380A CN 115859380 A CN115859380 A CN 115859380A CN 202310175666 A CN202310175666 A CN 202310175666A CN 115859380 A CN115859380 A CN 115859380A
- Authority
- CN
- China
- Prior art keywords
- data
- text
- image data
- suspect
- improved
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000007787 solid Substances 0.000 title claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000012217 deletion Methods 0.000 claims abstract description 7
- 230000037430 deletion Effects 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 235000014510 cooky Nutrition 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims 1
- 230000002708 enhancing effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- 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
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Storage Device Security (AREA)
Abstract
The invention discloses an electronic data solid certificate correlation method, which comprises the following steps: s1: reading data in a machine to be subjected to evidence collection and cloud disk data accessed by the machine in a read-only mode, and classifying the data according to a file format; s2: carrying out matrix vectorization on the acquired image data, and inputting the generated matrix vector into an improved convolutional neural network for processing; s3: performing keyword matching and information extraction on the acquired operation log data and the deleted residual data; s4: and (4) extracting and storing the image data of which the calculation result of the step (S2) meets the set threshold, summarizing the image data and the available information output by the step (S3), associating the image data and the available information according to log time, and uploading the image data to a evidence-fixing platform. By adopting the improved parallel Boyer-Moore algorithm to process the operation log data and the deletion residual data, the integrity of the evidence is greatly improved, and the evidence deleted, removed or damaged by the suspect is further perfected.
Description
Technical Field
The invention relates to the technical field of electronic communication, in particular to an electronic data solid evidence correlation method.
Background
In the future, lawless persons can hide and transmit illegal data such as illegal audio and video data and destructive programs by using the cloud storage service. Regarding the current evidence obtaining technology, most of the existing evidence obtaining tools are oriented to a single machine, and the evidence obtaining analysis can not be carried out on data in cloud storage. In addition, the evidence obtaining work is also challenged by the practical difficulties of difficult evidence obtaining, cross-region, high case handling cost and the like existing in the network crime. Therefore, the efficient evidence obtaining method for cloud storage research has important practical significance.
In the prior art, some internet security certificates for electronic data appear, but the internet security certificates are for local computers, and correlation between the local computers and information stored in cloud is not relevant, so that at present, only the electronic data stored in cloud is subjected to the security certificate or relevant information of the local computers is subjected to the security certificate. For the fixation of an evidence chain with a plurality of storage modes and high evidence values, the current electronic data evidence fixation system is relatively poor and cannot meet the requirements well. At the present stage, if the cloud storage is associated with the electronic data of the local computer, no relevant algorithm is available for association; and the algorithm for separately performing evidence fixing on the cloud-stored electronic data is relatively lagged behind and has low accuracy, for example, the KMP algorithm is adopted, but the performance of the algorithm is not fully utilized, and in the process of screening local evidence, because a lot of files are locally stored and the evidence is destroyed, such as deletion and removal of related evidence, the efficiency is low in the searching process, and the operation process cannot be searched according to the residual information after deletion.
Disclosure of Invention
Aiming at the problems mentioned in the prior art, in order to solve the technical problems, the invention provides an electronic data solid evidence correlation method, which solves the correlation between cloud storage and local data, realizes quick processing through an improved neural network algorithm, specially identifies and processes log data, and can greatly enhance the determination of evidence integrity, and the electronic data solid evidence correlation method comprises the following steps:
s1: reading data in a machine to be proved and cloud disk data accessed by the machine in a read-only mode, classifying the data according to a file format, wherein the data types comprise image data, operation log data, text data and deleted residual data; the image data comprises pictures, videos and audio data;
s2: carrying out matrix vectorization on the acquired image data, and inputting the generated matrix vector into an improved convolutional neural network for processing; the improved convolutional neural network outputs a calculation result after processing, and the image data of which the calculation result meets a set threshold value is extracted and stored;
s3: performing keyword matching and information extraction on the acquired operation log data and the acquired deletion residual data, and S31 firstly converting keywords to be matched into binary data; s32, reading the next keyword to be matched; s33, reading the cloud storage, the cloud disk and the local data; matching by adopting an improved parallel Boyer-Moore algorithm; if the matching is successful, outputting available information, and turning to S32; if the matching fails, the step goes to S32; judging whether the file is completely read, finishing the step of completely reading, and otherwise, executing S32; available information includes location, results, time;
the improved parallel Boyer-Moore algorithm adopts a plurality of modes for parallel computation, including moving a mode string P from the left side of a text T to the right side, comparing the mode string P with the text T from the right side to the left side when characters are compared, moving the mode string P from the end of the text T to the left side while moving the mode string P from the left side of the text T to the right side, and moving the mode string P from the middle of the text T to the left side and moving the mode string P to the right side for comparison;
s4: and (3) extracting and storing the image data of which the calculation result in the step (S2) meets the set threshold, summarizing the image data and the available information output in the step (S3), and associating the image data and the available information according to the log time and uploading the image data to a evidence fixing platform.
Preferably, the step S1 is preceded by audio data
By the suspect sound component->
And a voice component for the person speaking into the suspect>
Composition, sound source letterInformation is>
、/>
The sound source feedback parameter is->
,
And the sound information satisfies: />
。
Preferably, step S2 further includes; performing matrix vectorization, including performing feature extraction on data in the acquired time period T of the picture, video and audio data to form a matrix vector H, and inputting the matrix vector H into a trained improved convolutional neural network; the trained improved convolutional neural network is formed by training images, videos and audio data of suspects and original persons.
Preferably, the improved convolutional neural network employs an improved loss function of Q:
wherein ,
indicates the probability of picture, video or audio data of the suspect or the original person in the ith sample, and then>
Expressing as characteristic parameters of a suspect or an original speaker, dividing a matrix vector set consisting of pictures, videos and audio data into N sections, expressing that the amplitude exceeds a value, determined by the characteristics of the suspect or the original speaker,m represents an angle excess value, is>
And a secant function value of a sample vector of picture, video and audio data representing the suspect or the original person in the ith sample and a feature vector of the suspect or the original person.
Preferably, the improved parallel Boyer-Moore algorithm, when shifting the pattern string P from the left to the right of the text T, the characters jump as follows, where ch is a mismatched text character that occurs when the text T is compared with the pattern P: the distance K of the movement pattern string is:
Preferably, the operation log data includes installation traces, database files, cookies, and operations such as adding and deleting the files on the client device by the user.
Preferably, the cloud disk data accessed by the machine includes a hundred-degree network disk, a 115 network disk, a 360 network disk, a storage path in cloud storage, a unique identifier, a file name in a hundred-degree cloud storage server, an md5 value, and a time for accessing the server.
The invention provides an electronic data solid evidence correlation method, which can realize the following beneficial technical effects:
1. improving the loss function Q by using improved convolutional neural networks, i.e. secant function in calculation
And a sample vector representing picture, video and audio data of a suspect or an original advertiser in the ith sample and a feature vector of the suspect or the original advertiser are introduced into the calculation process, so that the calculation efficiency is greatly enhanced.
2. The improved parallel Boyer-Moore algorithm adopts a plurality of modes for parallel computation, including moving the mode string P from the left side of the text T to the right side, comparing the mode string P with the text T from the right side to the left side when characters are compared, and simultaneously moving the mode string P from the left side of the text T to the right side, moving the mode string P from the tail end of the text T to the left side in parallel computation, and moving the mode string P from the middle of the text T to the left side and the right side for comparison, thereby greatly enhancing the computation efficiency.
3. The integrity of evidence is greatly improved by adopting the improved parallel Boyer-Moore algorithm to process the operation log data and the deleted residual data, so that the evidence deleted, removed or damaged by a suspect is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of the steps of an electronic data integrity association method of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the above problems in the prior art, as shown in fig. 1: the invention provides an electronic data solid evidence correlation method, which solves the correlation between cloud storage and local data, realizes quick processing through an improved neural network algorithm, specially identifies and processes log data, and can greatly enhance the determination of evidence integrity.
S1: reading data in a machine to be proved and cloud disk data accessed by the machine in a read-only mode, classifying the data according to a file format, wherein the data types comprise image data, operation log data, text data and deleted residual data; the image data comprises pictures, videos and audio data;
in some embodiments, the file type is identified by a file format, such as word, pdf, excel, jpeg, ppt, avi, and the like, and further, pictures in word, pictures in ppt, pictures in web page, and video are identified.
S2: carrying out matrix vectorization on the acquired image data, and inputting the generated matrix vector into an improved convolutional neural network for processing; the improved convolutional neural network outputs a calculation result after processing, and the image data of which the calculation result meets a set threshold value is extracted and stored;
s3: performing keyword matching and information extraction on the acquired operation log data and the acquired deletion residual data, and S31 firstly converting keywords to be matched into binary data; s32, reading the next keyword to be matched; s33, reading the cloud storage, the cloud disk and the local data; matching by adopting an improved parallel Boyer-Moore algorithm; if the matching is successful, outputting available information, and turning to S32; if the matching fails, the step goes to S32; judging whether the file is completely read, finishing the step of completely reading, and otherwise, executing S32; available information includes location, results, time;
the improved parallel Boyer-Moore algorithm adopts a plurality of modes for parallel computation, including moving a mode string P from the left side of a text T to the right side, comparing the mode string P with the text T from the right side to the left side when characters are compared, and simultaneously moving the mode string P from the left side of the text T to the right side, moving the mode string P from the tail end of the text T to the left side in parallel computation, and moving the mode string P from the middle of the text T to the left side and the right side for comparison, thereby greatly enhancing the computation efficiency;
s4: and (4) extracting and storing the image data of which the calculation result of the step (S2) meets the set threshold, summarizing the image data and the available information output by the step (S3), associating the image data and the available information according to log time, and uploading the image data to a evidence-fixing platform.
In some embodiments, audio data is also included before step S1
By the suspect sound component->
And a voice component +that is based on the suspect>
The sound source information is->
、/>
The sound source feedback parameter is->
,
And the sound information satisfies: />
。
In some embodiments, the step S2 further comprises; performing matrix vectorization, including performing feature extraction on data in the acquired time period T of the image, video and audio data to form a matrix vector H, and inputting the matrix vector H into a trained improved convolutional neural network; the trained improved convolutional neural network is formed by training images, videos and audio data of suspects and original announcers.
In some embodiments, the improved convolutional neural network employs an improved loss function of Q:
wherein ,
represents the probability of picture, video or audio data of a suspect or an originator in the ith sample, and->
The characteristic parameters of the suspect or the original advertiser are represented, a matrix vector set consisting of picture, video and audio data is divided into N sections, s represents an amplitude exceeding value and is determined by the characteristics of the suspect or the original advertiser, m represents an angle exceeding value, and the N sections are combined>
And a secant function value of a sample vector of picture, video and audio data of the suspect or the original in the ith sample and a feature vector of the suspect or the original.
In some embodiments, the improved parallel Boyer-Moore algorithm, when shifting the pattern string P from the left of the text T to the right, the characters jump as follows, where ch is the unmatched text character that occurs when the text T is compared to the pattern P: the distance K of the movement pattern string is:
Preferably, the operation log data includes installation traces, database files, cookies, and operations such as adding and deleting the files on the client device by the user.
In some embodiments, the cloud disk data accessed by the machine includes a hundred degree network disk, a 115 network disk, a 360 network disk, a storage path in cloud storage, a unique identifier, a file name in a hundred degree cloud storage server, an md5 value, and a time of accessing the server.
In some embodiments, step S4: and (4) extracting and storing the image data of which the calculation result of the step (S2) meets the set threshold, summarizing the image data and the available information output by the step (S3), associating the image data and the available information according to log time, and uploading the image data to a evidence-fixing platform. For example, the video image displays log operation text information at corresponding time, or the picture and the audio simultaneously display text information such as word, excel and the like at corresponding time, so that the association at the same time point is realized; or in some embodiments, the association of content, such as the association of certain video frames in a video with image information.
The invention provides an electronic data solid certificate correlation method which realizes the following effects:
1. improving the loss function Q by using improved convolutional neural networks, i.e. secant functions in the calculation
And a sample vector representing picture, video and audio data of a suspect or an original advertiser in the ith sample and a feature vector of the suspect or the original advertiser are introduced into the calculation process, so that the calculation efficiency is greatly enhanced.
2. The improved parallel Boyer-Moore algorithm adopts a plurality of modes for parallel computation, including moving the mode string P from the left side of the text T to the right side, comparing the mode string P with the text T from the right side to the left side when characters are compared, and simultaneously moving the mode string P from the left side of the text T to the right side, moving the mode string P from the tail end of the text T to the left side in parallel computation, and moving the mode string P from the middle of the text T to the left side and the right side for comparison, thereby greatly enhancing the computation efficiency.
3. The integrity of evidence is greatly improved by adopting the improved parallel Boyer-Moore algorithm to process the operation log data and the deleted residual data, so that the evidence deleted, removed or damaged by a suspect is further improved.
The above detailed description is provided for the electronic data certificate correlation method, and the principle and the implementation of the present invention are explained by applying a specific example, and the above description of the embodiment is only used to help understanding the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea and method of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (7)
1. An electronic data solid certificate correlation method is characterized by comprising the following steps:
s1: reading data in a machine to be proved and cloud disk data accessed by the machine in a read-only mode, classifying the data according to a file format, wherein the data types comprise image data, operation log data, text data and residual data; the image data comprises pictures, videos and audio data;
s2: carrying out matrix vectorization on the acquired image data, and inputting the generated matrix vector into an improved convolutional neural network for processing; the improved convolutional neural network outputs a calculation result after processing, and the image data of which the calculation result meets a set threshold value is extracted and stored;
s3: performing keyword matching and information extraction on the acquired operation log data and the acquired deletion residual data, and S31 firstly converting keywords to be matched into binary data; s32, reading the next keyword to be matched; s33, reading the cloud storage, the cloud disk and the local data; matching by adopting an improved parallel Boyer-Moore algorithm; if the matching is successful, outputting available information, and turning to S32; if the matching fails, the step goes to S32; judging whether the file is read completely, finishing the step of executing after the file is read completely, and otherwise executing S32; available information includes location, results, time;
the improved parallel Boyer-Moore algorithm adopts a plurality of modes for parallel computation, including moving a mode string P from the left side of a text T to the right side, comparing the mode string P with the text T from the right side to the left side when characters are compared, moving the mode string P from the end of the text T to the left side while moving the mode string P from the left side of the text T to the right side, and moving the mode string P from the middle of the text T to the left side and moving the mode string P to the right side for comparison;
s4: and (4) extracting and storing the image data of which the calculation result of the step (S2) meets the set threshold, summarizing the image data and the available information output by the step (S3), associating the image data and the available information according to log time, and uploading the image data to a evidence-fixing platform.
2. The electronic data warranty association method of claim 1, further comprising, prior to step S1, audio data
By a suspect sound component>
And a voice component for the person speaking into the suspect>
The sound source information is->
、
The sound source feedback parameter is->
,/>
And the sound information satisfies:
3. the electronic data solid certificate correlation method according to claim 2, wherein the step S2 further includes; performing matrix vectorization, including performing feature extraction on data in the acquired time period T of the image, video and audio data to form a matrix vector H, and inputting the matrix vector H into a trained improved convolutional neural network; the trained improved convolutional neural network is formed by training images, videos and audio data of suspects and original persons.
4. The electronic data solid certificate association method of claim 1,
the improved convolutional neural network uses an improved loss function of Q:
wherein ,
represents the probability of picture, video or audio data of a suspect or an originator in the ith sample, and->
The characteristic parameters of the suspect or the original advertiser are represented, a matrix vector set consisting of picture, video and audio data is divided into N sections, s represents an amplitude exceeding value and is determined by the characteristics of the suspect or the original advertiser, R represents an angle exceeding value, and then the N sections are combined>
And a secant function value of a sample vector of picture, video and audio data of the suspect or the original in the ith sample and a feature vector of the suspect or the original.
5. The electronic data solid certificate association method of claim 4,
when the improved parallel Boyer-Moore algorithm moves the pattern string P from the left to the right of the text T, the characters jump as follows, wherein ch is a unmatched text character which appears when the text T is compared with the pattern P: the distance K of the movement pattern string is:
6. The electronic data evidence correlation method of claim 1, wherein the operation log data comprises operation behaviors such as installation traces, database files, cookies, addition and deletion of the files on the client device by a user, and the like.
7. The electronic data solid certificate association method of claim 1,
the cloud disk data accessed by the machine comprise a hundred-degree network disk, a 115 network disk, a 360 network disk, a storage path in cloud storage, a unique identifier, a file name in a hundred-degree cloud storage server, an md5 value and the time for accessing the server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310175666.XA CN115859380B (en) | 2023-02-28 | 2023-02-28 | Electronic data fixed certificate association method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310175666.XA CN115859380B (en) | 2023-02-28 | 2023-02-28 | Electronic data fixed certificate association method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115859380A true CN115859380A (en) | 2023-03-28 |
| CN115859380B CN115859380B (en) | 2023-05-09 |
Family
ID=85659296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310175666.XA Active CN115859380B (en) | 2023-02-28 | 2023-02-28 | Electronic data fixed certificate association method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115859380B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040260733A1 (en) * | 2003-06-23 | 2004-12-23 | Adelstein Frank N. | Remote collection of computer forensic evidence |
| WO2018094764A1 (en) * | 2016-11-23 | 2018-05-31 | 深圳大学 | Method and device for pattern string match verification based on cloud service |
| CN109635099A (en) * | 2018-12-21 | 2019-04-16 | 山东华夏高科信息股份有限公司 | Case-involving electronic data evidence obtaining management system |
| US20210067563A1 (en) * | 2019-08-31 | 2021-03-04 | Purdue Research Foundation | Automating digital forensic evidence collection |
| WO2021120480A1 (en) * | 2019-12-19 | 2021-06-24 | 深圳壹账通智能科技有限公司 | Evidence collection method and system based on image recognition, and computer device and storage medium |
| CN114842483A (en) * | 2022-06-27 | 2022-08-02 | 齐鲁工业大学 | Standard file information extraction method and system based on neural network and template matching |
-
2023
- 2023-02-28 CN CN202310175666.XA patent/CN115859380B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040260733A1 (en) * | 2003-06-23 | 2004-12-23 | Adelstein Frank N. | Remote collection of computer forensic evidence |
| WO2018094764A1 (en) * | 2016-11-23 | 2018-05-31 | 深圳大学 | Method and device for pattern string match verification based on cloud service |
| CN109635099A (en) * | 2018-12-21 | 2019-04-16 | 山东华夏高科信息股份有限公司 | Case-involving electronic data evidence obtaining management system |
| US20210067563A1 (en) * | 2019-08-31 | 2021-03-04 | Purdue Research Foundation | Automating digital forensic evidence collection |
| WO2021120480A1 (en) * | 2019-12-19 | 2021-06-24 | 深圳壹账通智能科技有限公司 | Evidence collection method and system based on image recognition, and computer device and storage medium |
| CN114842483A (en) * | 2022-06-27 | 2022-08-02 | 齐鲁工业大学 | Standard file information extraction method and system based on neural network and template matching |
Non-Patent Citations (2)
| Title |
|---|
| XINDONG WANG ETAL: "Study on the Evidence Collection for Network Security Intrusion Detection" * |
| 张春生;张晓英;王国忠;: "字符串随机探测模式匹配算法" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115859380B (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106650799B (en) | A kind of electronic evidence classification extracting method and system | |
| WO2020244066A1 (en) | Text classification method, apparatus, device, and storage medium | |
| CN102799647B (en) | Method and device for webpage reduplication deletion | |
| CN113011889B (en) | Account anomaly identification method, system, device, equipment and medium | |
| WO2020228182A1 (en) | Big data-based data deduplication method and apparatus, device, and storage medium | |
| Harichandran et al. | Bytewise approximate matching: the good, the bad, and the unknown | |
| CN109446299B (en) | Method and system for searching e-mail content based on event recognition | |
| CN112052451A (en) | Webshell detection method and device | |
| CN111241496B (en) | Method and device for determining small program feature vector and electronic equipment | |
| CN110991246A (en) | Video detection method and system | |
| US11328095B2 (en) | Peceptual video fingerprinting | |
| CN114650176A (en) | Phishing website detection method and device, computer equipment and storage medium | |
| CN114372267B (en) | Malicious webpage identification detection method based on static domain, computer and storage medium | |
| CN113762040B (en) | Video identification method, device, storage medium and computer equipment | |
| CN111444364B (en) | Image detection method and device | |
| CN113821630A (en) | Data clustering method and device | |
| CN116996269A (en) | Intelligent fraudulent website identification method based on computing power network | |
| CN115859380B (en) | Electronic data fixed certificate association method | |
| CN114881012A (en) | Article title and content intelligent rewriting system and method based on natural language processing | |
| CN114003737A (en) | Double-record examination assisting method, device, equipment and medium based on artificial intelligence | |
| US9189488B2 (en) | Determination of landmarks | |
| CN112966126B (en) | High-reliability knowledge base construction method capable of inquiring and tracing mass unstructured data content | |
| CN114116963B (en) | Chat record matching event analysis method, terminal equipment and storage medium | |
| CN111625627B (en) | Data right determining method and device based on block chain and computer equipment | |
| Almeida et al. | File forgery detection using a weighted rule-based system |
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 |