CN115408490A - Official document proofreading method, system and equipment based on knowledge base and storage medium - Google Patents
Official document proofreading method, system and equipment based on knowledge base and storage medium Download PDFInfo
- Publication number
- CN115408490A CN115408490A CN202211356334.3A CN202211356334A CN115408490A CN 115408490 A CN115408490 A CN 115408490A CN 202211356334 A CN202211356334 A CN 202211356334A CN 115408490 A CN115408490 A CN 115408490A
- Authority
- CN
- China
- Prior art keywords
- network
- knowledge base
- expression
- keyword
- video
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000001915 proofreading effect Effects 0.000 title claims description 31
- 230000014509 gene expression Effects 0.000 claims abstract description 169
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 235000019633 pungent taste Nutrition 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7844—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 original textual content or text extracted from visual content or transcript of audio data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method, a system, equipment and a storage medium for checking official documents based on a knowledge base, wherein the checking method comprises the following steps: acquiring real-time network data, analyzing the heat condition of the real-time network data to determine network expression, and constructing or updating a network expression knowledge base; acquiring a target text, performing keyword and sentence division on the target text, traversing each divided keyword and sentence, comparing the keyword and sentence with the network phrase knowledge base, and triggering corresponding word reminding according to the comparison similarity between the keyword and the network phrases in the network phrase knowledge base. The invention can update the network term knowledge base in real time, compares the keyword sentences in the official manuscript with the network term knowledge base, identifies whether the official manuscript has the network terms, and can accurately proofread the official manuscript by a proofreader under the reminding of words in the system, thereby improving the accuracy of the official manuscript.
Description
Technical Field
The invention relates to the technical field of text proofreading, in particular to a method, a system, equipment and a storage medium for official document proofreading based on a knowledge base.
Background
The speaker often writes an official document in advance before the official document is presented, so that the speaker can give a speech according to the official document. In order to ensure that official statements are more accurate, proofreading of the manuscript is needed, and non-compliant contents in the manuscript are identified and corrected. However, the existing manuscript proofreading only identifies wrongly written characters in the manuscript, and the proofreading process is too simple; in addition, internet languages are gradually started in the present stage, and the real meanings of the network terms are greatly different from the literal meanings thereof, so that if a manuscript writer inadvertently uses the network terms in official manuscripts, the content of the manuscripts is deviated, and the situation cannot be identified through the existing text proofreading software, and the accuracy of the manuscripts cannot be ensured.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the objectives of the present invention is to provide a method for checking official documents based on a knowledge base, which can improve the accuracy of checking the manuscript.
The invention also aims to provide a official document proofreading system based on the knowledge base.
It is a further object of the present invention to provide an electronic device.
It is a further object of the present invention to provide a computer readable storage medium.
One of the purposes of the invention is realized by adopting the following technical scheme:
a official document proofreading method based on a knowledge base comprises the following steps:
acquiring real-time network data, analyzing the heat condition of the real-time network data to determine network expression, and constructing or updating a network expression knowledge base;
acquiring a target text, carrying out keyword and sentence division on the target text, traversing each divided keyword and sentence, comparing the keyword and sentence with the network expression knowledge base, and triggering corresponding word reminding according to the comparison similarity between the keyword and the network expression in the network expression knowledge base.
Further, the real-time network data comprises network videos which are obtained from the target addresses and reach the heat degree standard; the popularity is the preference degree of a user group to the network video or the network text in the statistical time period; and the target address is self-defined according to the user setting.
Further, the method for determining the network expression comprises the following steps:
acquiring flow data of the network video, and calculating an average flow value of the network video by combining video duration;
and calling out the video frame number of which the flow value is higher than the average flow value in the network video, analyzing the audio content of the video frame number to obtain the hot words contained in the video frame number, and storing the hot words as primary network words in the network word knowledge base.
Further, when acquiring the traffic data of the network video, the method further includes:
and calling out video frame numbers of which the flow values are lower than the average flow value and the flow difference value between the flow values and the average flow value is within a set range in the network videos, analyzing the audio contents of the video frame numbers to obtain the hot words contained in the video frames, and storing the hot words as secondary network expressions in the network expression knowledge base.
Further, the real-time network data also comprises network expression counted by the target website, and the network expression of the target website is directly obtained and stored in the network expression knowledge base.
Further, when acquiring the traffic data of the network video, the method further includes:
calculating the use frequency of each network expression in the network expression knowledge base, acquiring the release time of the network video, and weighting each network expression in the network expression knowledge base according to the release time to calculate the word popularity of each network expression in the network expression knowledge base;
when the word popularity of any network expression is lower than the popularity threshold, the network expression is marked as a three-level network expression.
Further, the method for comparing the keyword sentences with the network expression knowledge base comprises the following steps:
and comparing the keyword sentences with the primary network expression, the secondary network expression and the tertiary network expression in the network expression knowledge base respectively, if the comparison similarity between the keyword sentences and any network expression is higher than a preset threshold value, triggering word reminding of a corresponding level according to the level of the network expression, and pushing source information corresponding to the network expression.
The second purpose of the invention is realized by adopting the following technical scheme:
a knowledge-base-based official document proofreading system for performing the above-mentioned knowledge-base-based official document proofreading method, the system comprising:
the network server is used for acquiring real-time network data, analyzing the heat condition of the real-time network data to determine network expression, and constructing or updating a network expression knowledge base;
and the proofreading server is used for acquiring a target text, performing keyword-sentence division on the target text, traversing each divided keyword sentence, comparing the keyword sentence with the network expression knowledge base, and triggering corresponding word reminding according to a comparison result.
The third purpose of the invention is realized by adopting the following technical scheme:
an electronic device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor implementing the method of collation of official documents based on a knowledge base as described above when executing the computer program.
The fourth purpose of the invention is realized by adopting the following technical scheme:
a computer-readable storage medium having stored thereon a computer program which, when executed, implements the above-described method of collation of official documents based on a knowledge base.
Compared with the prior art, the invention has the beneficial effects that:
the invention can update the network term knowledge base in real time, compares the keyword sentences in the official manuscript with the network term knowledge base, identifies whether the network terms exist in the official manuscript, and can accurately proofread the official manuscript by a proofreader under the reminding of words in the system, thereby improving the accuracy of the official manuscript.
Drawings
FIG. 1 is a flow chart of the method for checking official documents based on the knowledge base according to the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
Example one
The embodiment provides an official document proofreading method based on a knowledge base, which mainly identifies network words used in official documents, so that proofreading personnel can proofread the official documents according to word reminding to improve the accuracy of the official documents.
As shown in fig. 1, the official document proofreading method specifically includes the following steps:
step S1: acquiring real-time network data, analyzing the heat condition of the real-time network data to determine network expressions, and constructing or updating a network expression knowledge base;
step S2: acquiring a target text, carrying out keyword and sentence division on the target text, traversing each divided keyword and sentence, comparing the keyword and sentence with the network expression knowledge base, and triggering corresponding word reminding according to the comparison similarity between the keyword and the network expression in the network expression knowledge base.
Before manuscript proofreading is carried out, a network expression knowledge base is required to be constructed in advance by using a network server, and the network expression knowledge base is used for storing network expressions with high network heat and large flow at present; the network server acquires real-time network data from a target address through the Internet, and the target address can be edited in a user-defined mode, so that the network address can be increased, decreased or modified, and the network data can be acquired from the specified network address.
The network server can acquire network data from the target address according to a preset time interval, and can also actively trigger the network server to acquire new network data from the target address when the target address updates data or generates new data, so that the real-time performance of the network data is ensured.
The data type of the network data obtained from the target address may be a network video or a network text. After the network server acquires the network video, whether the heat of the network video reaches the standard or not needs to be judged, wherein the heat is the like degree of a user group to the network video within a statistical time period, the like degree can be determined through the whole watching flow of the network video, namely whether the whole watching flow value of the network video exceeds a first threshold value or not is judged, if the like exceeds the first threshold value, the heat of the network video is relatively high, and at the moment, the network video can be used as a network phrase analysis basis; and if the watching flow value of the network video does not exceed the first threshold, filtering the network video if the network video is relatively low in heat.
Meanwhile, the network server acquires the traffic data of the network video from the target address, wherein the traffic data refers to the preference degree of a user group corresponding to each frame of picture/a plurality of continuous frames of pictures in the network video, and the preference degree can be counted in the modes of video barrage quantity, hotspot record quantity and the like so as to acquire the traffic value of each frame of picture or a plurality of continuous frames of pictures in the network video. For example, when the number of barrages of several continuous frames of pictures in the network video is greater than that of other frames, the higher the flow value representing the several continuous frames of pictures is, the higher the corresponding heat is.
In addition, a favorite plug-in can be arranged in an interface where the network video is located, and when a user encounters a funny or particularly favorite clip while watching the network video, the user can trigger the favorite plug-in so as to perform hotspot recording on the current clip; if the number of the hotspot records of a certain segment in the network video is more, the higher the heat representing the segment is, the larger the flow is.
After the network server acquires the flow data of the network video, calculating the average flow value of the network video by combining the video duration; finding out the video frame number with the flow value higher than the average flow value in the network video, acquiring the audio content corresponding to the video frame number, converting the audio content into characters, and performing part-of-speech screening on the characters to acquire hot words contained in the characters; the screening rule can be set in a user-defined mode in advance; and marking the screened hot words and sentences as primary network words and storing the primary network words and sentences in the network word knowledge base.
After all network videos with the heat degree up to the standard in the target address are analyzed, network expressions obtained by analyzing each network video are recorded in the network expression knowledge base, and the occurrence frequency of each network expression in the knowledge base is recorded; if a plurality of network expressions with extremely high similarity exist in the network expression knowledge base, the network expressions with extremely high similarity are classified into the same network expression, and the occurrence frequency of the network expressions with extremely high similarity is summarized. And the manager of the knowledge base can also manually split the network expressions which are classified into one class according to the actual situation.
In this embodiment, in addition to recording the network expressions with high heat and large traffic, the future network expressions may be predicted, that is, a video frame number in which the traffic value in the network video is lower than the average traffic value and the traffic difference between the traffic value and the average traffic value is within a set range is retrieved, and the content played in the video frame number still belongs to the content in the heat video, although the current heat is not particularly high, the recorded content is still known by the public, and it may also be developed into the network expressions in the future, so that the audio content of the video frame number is analyzed to obtain the heat sentences contained in the audio content, and the heat sentences are stored in the network expression knowledge base as the secondary network expressions.
In the network expression knowledge base, the primary network expression belongs to the current network expression with high heat and large flow, and the heat and the flow of the secondary network expression are lower than those of the primary network expression, but the secondary network expression still can be known by the public in the future, so the secondary network expression is written into the network expression knowledge base as the secondary network expression. After a system identifies a primary network expression and a secondary network expression from a network video, a network expression knowledge base records the writing times of each network expression and calculates the use frequency of each network expression in the network expression knowledge base; in the network expression knowledge base, the same or similar network expressions are combined, and the use frequency of the combined network expressions is correspondingly increased.
Meanwhile, when the network expressions are written into the network expression knowledge base, the popularity time of each network expression is recorded, and the popularity time is the publishing time of the network video corresponding to the network expressions; for example, if the release time of the network video is 5 months in 2020, the hotness time of the network expression identified in the network video is 5 months in 2020. If the same network expression is identified by a plurality of network videos with different times, the latest network video publishing time is taken as the popularity time of the network expression.
The network server weights each network expression in the network expression knowledge base according to the popularity time of the network expression, and then calculates the word popularity of each network expression in the network expression knowledge base by combining the use frequency of the network expression; if the use frequency of the network expression A is high and the corresponding weight is large, the word heat degree of the network expression A is the highest; if the usage frequency of the network expression B is high, but the weight value of the network expression B is small, the word popularity of the network expression B is lower than that of the network expression A; if the usage frequency of the network expression C is low and the weight thereof is small, the word popularity of the network expression C is minimum. The present embodiment combines the circulation time and the usage frequency of the network expression on the internet to calculate and update the popularity of the network expression, so that the network expression recorded in the network expression knowledge base flows and matches the current popular network expression on the internet as much as possible.
When the word popularity of any network expression in the network expression knowledge base is lower than the popularity threshold value, the network expression is described to be popular, but the popularity of the network expression is not high at present, the network expression is marked as a three-level network expression and is stored in the network expression knowledge base.
The network expression recorded in the network expression knowledge base can be identified through the network video and can be directly downloaded in the internet; that is, the network server may obtain the network text from the specified target website, the content of the network text records the network expression that the target network has counted, and directly obtain the network expression of the target website and store the network expression in the network expression knowledge base. In addition, the network expressions collected by the user can be imported into the knowledge base in a manual import mode so as to expand the number of words in the knowledge base. When the network text or the network expression which is automatically introduced is repeated with the network expression obtained by network video identification, the word heat of the network expression can be increased; if the network text or the network expressions imported by the administrator collide with the network expressions obtained by network video identification, the administrator of the knowledge base can edit the network expressions in the knowledge base manually. Meanwhile, the network expression in the network expression knowledge base is also marked with a word source, and the source can be network video, network text or self-import.
After the network expression knowledge base is constructed and updated in the mode, the official text can be corrected, and whether the official text uses the network expressions or not is identified. Acquiring a target text through a proofreading server, wherein the target text is an imported or downloaded official text; and carrying out keyword and sentence division on the target text, traversing each divided keyword and sentence, comparing the keyword and sentence with the network expression knowledge base, and triggering corresponding word reminding according to a comparison result. The method of word and sentence division can be performed by the word and sentence division rule of the natural language processing in the prior art, which is disclosed in the prior art and will not be described in detail herein.
And comparing the divided keyword sentences with the network expression knowledge base, namely comparing the keyword sentences with the primary network expressions, the secondary network expressions and the tertiary network expressions in the network expression knowledge base respectively, if the comparison similarity between the keyword sentences and any one of the network expressions at any level is higher than a preset threshold value, triggering word reminding at the corresponding level according to the level of the network expressions, and pushing source information corresponding to the network expressions. If the similarity between a keyword sentence in the official text and a primary network term in the network term knowledge base is higher than a preset threshold value, generating a primary term reminder for the keyword sentence in the official text; and if the similarity between another keyword sentence in the official text and one secondary network term in the network term knowledge base is higher than a preset threshold value, generating a secondary term reminder for the keyword sentence in the official text. The reminding modes corresponding to the word reminding with different grades are different, and the keyword sentence for the first-level word reminding is marked with red; the keyword sentence of the secondary word reminding is marked as yellow; and the keyword sentences reminded by the third-level words are marked as green.
Meanwhile, the source information of the network expression can be displayed in a spring mode or in a designated interface area while the word reminding is generated, namely the network expression is from a network video, a network text or a self-importing mode; the source information can also display the real meaning of the network expression and the application scene of the network expression, and the information of the real meaning and the scene application can be stored in the network expression knowledge base after being searched by the internet, so that the network expression knowledge base can be used in an off-line state.
Example two
The embodiment provides an official document proofreading system based on a knowledge base, which executes the official document proofreading method based on the knowledge base according to the embodiment one, wherein the system comprises a network server and a proofreading server connected with the network server;
the network server is used for acquiring real-time network data, analyzing the heat condition of the real-time network data to determine network expression, and constructing or updating a network expression knowledge base;
the proofreading server inputs a target text through an input device, performs keyword and sentence division on the target text, traverses each divided keyword and sentence and compares the keyword and sentence with the network expression knowledge base, and triggers corresponding word reminding according to a comparison result.
The embodiment can update the network term knowledge base in real time, compares the keyword sentences in the official manuscript with the network term knowledge base, identifies whether the network terms exist in the official manuscript or not, and can accurately proofread the official manuscript by the proofreader under the word reminding of the system, thereby improving the accuracy of the official manuscript.
In some embodiments, there is also provided an electronic device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor implementing the method of repository-based official document proofreading in embodiment one when executing the computer program; in addition, a computer-readable storage medium is provided, on which a computer program is stored, which when executed, implements the above-mentioned method for collation of official documents based on a knowledge base.
The system, the device and the storage medium in this embodiment are based on multiple aspects of the same inventive concept, and the method implementation process has been described in detail in the foregoing, so that those skilled in the art can clearly understand the structure and implementation process of the system, the device and the storage medium in this embodiment according to the foregoing description, and for the sake of brevity of the description, no further description is provided here.
The above embodiments are only preferred embodiments of the present invention, and the scope of the present invention should not be limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are intended to be covered by the claims.
Claims (10)
1. A official document proofreading method based on a knowledge base is characterized by comprising the following steps:
acquiring real-time network data, analyzing the heat condition of the real-time network data to determine network expression, and constructing or updating a network expression knowledge base;
acquiring a target text, carrying out keyword and sentence division on the target text, traversing each divided keyword and sentence, comparing the keyword and sentence with the network expression knowledge base, and triggering corresponding word reminding according to the comparison similarity between the keyword and the network expression in the network expression knowledge base.
2. The method of checking official documents based on a knowledge base of claim 1, wherein said real-time network data includes network video with a hot standard obtained from a target address; the popularity is the preference degree of a user group to the network video or the network text in the statistical time period; and the target address is self-defined according to the user setting.
3. The method of claim 2, wherein the network expression is determined by:
acquiring flow data of the network video, and calculating an average flow value of the network video by combining video duration;
and calling out the video frame number of which the flow value is higher than the average flow value in the network video, analyzing the audio content of the video frame number to obtain the hot words contained in the video frame number, and storing the hot words as primary network words in the network word knowledge base.
4. The method for official document proofreading based on the knowledge base of claim 3, wherein when acquiring the traffic data of the network video, the method further comprises:
and calling out video frame numbers of which the flow value is lower than the average flow value and the flow difference value between the flow value and the average flow value is within a set range in the network video, analyzing the audio content of the video frame numbers to obtain the heat words contained in the video frame numbers, and storing the heat words as secondary network expression in the network expression knowledge base.
5. The method for official document proofreading based on the knowledge base of claim 4, wherein when acquiring the traffic data of the network video, the method further comprises:
calculating the use frequency of each network expression in the network expression knowledge base, acquiring the release time of the network video, and weighting each network expression in the network expression knowledge base according to the release time to calculate the word popularity of each network expression in the network expression knowledge base;
when the word popularity of any network expression is lower than the popularity threshold, the network expression is marked as a three-level network expression.
6. The method of claim 1, wherein the real-time network data further comprises network expressions counted by a target website, and the network expressions of the target website are directly obtained and stored in the network expression knowledge base.
7. The method for official document proofreading based on a knowledge base as claimed in claim 1, wherein the method for comparing the keyword sentences with the network term knowledge base comprises:
and comparing the keyword sentences with the network expressions in the network expression knowledge base respectively, if the comparison similarity between the keyword sentences and any one of the network expressions is higher than a preset threshold value, triggering word-using reminding of a corresponding level according to the level of the network expression, and pushing source information corresponding to the network expression.
8. A system for official document proofreading based on a knowledge base, which is characterized by executing the method for official document proofreading based on the knowledge base as claimed in any one of claims 1 to 7, and the system comprises:
the network server is used for acquiring real-time network data, analyzing the heat condition of the real-time network data to determine network expressions, and constructing or updating a network expression knowledge base;
and the proofreading server is used for acquiring a target text, performing keyword-sentence division on the target text, traversing each divided keyword-sentence and comparing the keyword-sentence with the network expression knowledge base, and triggering corresponding word reminding according to a comparison result.
9. An electronic device, comprising a processor, a memory, and a computer program stored on the memory and running on the processor, wherein the processor executes the computer program to implement the method for collation of official documents based on a knowledge base according to any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program is configured to implement the method for proofreading an official document based on a knowledge base according to any one of claims 1 to 7 when executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211356334.3A CN115408490A (en) | 2022-11-01 | 2022-11-01 | Official document proofreading method, system and equipment based on knowledge base and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211356334.3A CN115408490A (en) | 2022-11-01 | 2022-11-01 | Official document proofreading method, system and equipment based on knowledge base and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115408490A true CN115408490A (en) | 2022-11-29 |
Family
ID=84169241
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211356334.3A Pending CN115408490A (en) | 2022-11-01 | 2022-11-01 | Official document proofreading method, system and equipment based on knowledge base and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115408490A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9124623B1 (en) * | 2013-06-20 | 2015-09-01 | Symantec Corporation | Systems and methods for detecting scam campaigns |
CN104978523A (en) * | 2014-11-06 | 2015-10-14 | 哈尔滨安天科技股份有限公司 | Malicious sample capture method and system based on network hot word recognition |
CN108519970A (en) * | 2018-02-06 | 2018-09-11 | 平安科技(深圳)有限公司 | The identification method of sensitive information, electronic device and readable storage medium storing program for executing in text |
CN113705225A (en) * | 2021-09-07 | 2021-11-26 | 北京北大方正电子有限公司 | Sensitive word data processing method and device and electronic equipment |
CN113763949A (en) * | 2021-07-22 | 2021-12-07 | 南方电网深圳数字电网研究院有限公司 | Speech recognition correction method, electronic device, and computer-readable storage medium |
CN115186657A (en) * | 2022-07-28 | 2022-10-14 | 北京网景盛世技术开发中心 | Error sensitive information detection method, device, computer equipment and storage medium |
-
2022
- 2022-11-01 CN CN202211356334.3A patent/CN115408490A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9124623B1 (en) * | 2013-06-20 | 2015-09-01 | Symantec Corporation | Systems and methods for detecting scam campaigns |
CN104978523A (en) * | 2014-11-06 | 2015-10-14 | 哈尔滨安天科技股份有限公司 | Malicious sample capture method and system based on network hot word recognition |
CN108519970A (en) * | 2018-02-06 | 2018-09-11 | 平安科技(深圳)有限公司 | The identification method of sensitive information, electronic device and readable storage medium storing program for executing in text |
CN113763949A (en) * | 2021-07-22 | 2021-12-07 | 南方电网深圳数字电网研究院有限公司 | Speech recognition correction method, electronic device, and computer-readable storage medium |
CN113705225A (en) * | 2021-09-07 | 2021-11-26 | 北京北大方正电子有限公司 | Sensitive word data processing method and device and electronic equipment |
CN115186657A (en) * | 2022-07-28 | 2022-10-14 | 北京网景盛世技术开发中心 | Error sensitive information detection method, device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4580885B2 (en) | Scene information extraction method, scene extraction method, and extraction apparatus | |
US9456170B1 (en) | Automated caption positioning systems and methods | |
US20180307667A1 (en) | Travel guide generating method and system | |
CN111274442B (en) | Method for determining video tag, server and storage medium | |
JP2008077495A (en) | Conference support apparatus, conference support method and conference support program | |
CN102855317A (en) | Multimode indexing method and system based on demonstration video | |
CN112541095B (en) | Video title generation method and device, electronic equipment and storage medium | |
US11361759B2 (en) | Methods and systems for automatic generation and convergence of keywords and/or keyphrases from a media | |
EP3706014A1 (en) | Methods, apparatuses, devices, and storage media for content retrieval | |
WO2019187842A1 (en) | Illegal content search device, illegal content search method, and program | |
US11947635B2 (en) | Illegal content search device, illegal content search method, and program | |
CN111914566A (en) | Automatic comment generation method | |
CN115408490A (en) | Official document proofreading method, system and equipment based on knowledge base and storage medium | |
JP2004240488A (en) | Document managing device | |
CN115577147A (en) | Visual information map retrieval method and device, electronic equipment and storage medium | |
CN112818984A (en) | Title generation method and device, electronic equipment and storage medium | |
JP6530002B2 (en) | CONTENT SEARCH DEVICE, CONTENT SEARCH METHOD, PROGRAM | |
JP6830917B2 (en) | Illegal content search device, illegal content search method and program | |
JP6632564B2 (en) | Illegal content search device, illegal content search method, and program | |
WO2019187920A1 (en) | Illegal content search device, illegal content search method, and program | |
KR20210098135A (en) | Apparatus, method and computer program for analyzing query data | |
CN110888896A (en) | Data searching method and data searching system thereof | |
JP6621437B2 (en) | Illegal content search device, illegal content search method, and program | |
CN117221669B (en) | Bullet screen generation method and device | |
CN117333800B (en) | Cross-platform content operation optimization method and system based on artificial intelligence |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221129 |
|
RJ01 | Rejection of invention patent application after publication |