CN111695014A - Method, system, device and storage medium for automatically generating manuscripts based on AI (artificial intelligence) - Google Patents
Method, system, device and storage medium for automatically generating manuscripts based on AI (artificial intelligence) Download PDFInfo
- Publication number
- CN111695014A CN111695014A CN202010376133.4A CN202010376133A CN111695014A CN 111695014 A CN111695014 A CN 111695014A CN 202010376133 A CN202010376133 A CN 202010376133A CN 111695014 A CN111695014 A CN 111695014A
- Authority
- CN
- China
- Prior art keywords
- news
- data
- manuscript
- database
- preset
- 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 46
- 238000013473 artificial intelligence Methods 0.000 title claims description 42
- 238000005516 engineering process Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 4
- 238000012552 review Methods 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 4
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008676 import Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241000233805 Phoenix Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000010171 animal model Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012545 processing Methods 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
- G06F16/90—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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F16/903—Querying
- G06F16/9032—Query formulation
-
- 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
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses a method, a system, a device and a storage medium for automatically generating manuscripts based on AI, wherein the method comprises the following steps: searching manuscript data based on a network technology, and establishing a database according to the manuscript data; acquiring a keyword, and acquiring news data from a database or the Internet according to the keyword; and combining the news data with a preset AI algorithm to automatically generate a news initial draft, and auditing the news initial draft to obtain a final manuscript. The invention only needs to input key words, automatically searches related news data from a database or the Internet, and quickly generates news manuscripts by combining the news data and AI technology without manually collecting materials and writing the manuscripts, thereby greatly improving the manuscript generation efficiency and being widely applied to the technical field of information processing.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method, a system, an apparatus, and a storage medium for automatically generating manuscripts based on AI.
Background
News is valuable in the timeliness of news, such as breaking or breaking news events that would have adverse consequences if the news could not be broadcast in the first place. For news at break time, the traditional way is: the manual work is collected the material, writes the news manuscript after the manual work, reports again, and the manual work can't accomplish 24 hours and await the opportune moment, and collects the material and write the manuscript through artificial mode and need consume a large amount of time, is difficult to satisfy the requirement of in time and quick output news manuscript.
Disclosure of Invention
In order to solve the above technical problems, it is an object of the present invention to provide a method, system, apparatus and storage medium capable of timely and fast production of news manuscripts.
The first technical scheme adopted by the invention is as follows:
a method for automatically generating manuscripts based on AI comprises the following steps:
searching manuscript data based on a network technology, and establishing a database according to the manuscript data;
acquiring a keyword, and acquiring news data from a database or the Internet according to the keyword;
and combining the news data with a preset AI algorithm to automatically generate a news initial draft, and auditing the news initial draft to obtain a final manuscript.
Further, the step of collecting the manuscript data based on the network technology and establishing a database according to the manuscript data specifically comprises the following steps:
capturing manuscript data from a preset website by using a preset web crawler model, wherein the manuscript data comprises at least one of character information, picture information, video information or model information;
and classifying and storing the manuscript data according to a preset mode to build a database.
Further, the step of automatically generating the news initial draft by combining the news data and a preset AI algorithm specifically includes:
determining a news type according to the news data, and acquiring a corresponding news template from a preset template database according to the news type;
and filling the news data into a news template by adopting a preset AI algorithm to generate a news initial draft.
Further, the method also comprises the step of establishing a manuscript module library, which specifically comprises the following steps:
after obtaining the historical news manuscript, classifying the historical news manuscript;
respectively extracting type features, corpus features and structural features of various historical news manuscripts;
training a neural network by taking the historical news manuscripts with the same extracted features as a training set to obtain a news template;
wherein, the various types of news manuscripts correspond to a plurality of news templates.
Further, the step of auditing the news initial draft specifically includes at least one of the following steps:
detecting sentence segments with the same content in the news initial draft by adopting a duplicate checking technology, and deleting the same sentence segments;
and detecting the sensitive words in the news primary draft by combining a preset sensitive word bank, and replacing the detected sensitive words.
Further, the method also comprises a step of generating a data graph, which specifically comprises the following steps:
detecting and acquiring data information in the news primary draft, and generating a data graph by combining the acquired data information and a preset graph database, wherein the data graph comprises at least one of a bar graph, a line graph, a pie graph, a radar chart and a scatter diagram.
Further, the manuscript data includes at least one of news manuscript, public opinion manuscript, thesis document and comment data.
The second technical scheme adopted by the invention is as follows:
a system for automatically generating a contribution based on AI, comprising:
the database establishing module is used for collecting the manuscript data based on the network technology and establishing a database according to the manuscript data;
the data acquisition module is used for acquiring keywords and acquiring news data from a database or the Internet according to the keywords;
and the manuscript generation module is used for automatically generating a news initial draft by combining the news data and a preset AI algorithm, and obtaining a final manuscript after the news initial draft is checked.
Further, the database building module comprises a crawler searching unit and a classification storage unit;
the crawler searching unit is used for grabbing manuscript data from a preset website by using a preset web crawler model, wherein the manuscript data comprises at least one of character information, picture information, video information or model information;
and the classification storage unit is used for classifying and storing the manuscript data according to a preset mode to build a database.
Further, the manuscript generation module comprises a template selection unit and a data filling unit;
the template selection unit is used for determining news types according to the news data and acquiring corresponding news templates from a preset template database according to the news types;
and the data filling unit is used for filling the news data into the news template by adopting a preset AI algorithm to generate a news initial draft.
The third technical scheme adopted by the invention is as follows:
an apparatus for automatically generating a contribution based on AI, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The fourth technical scheme adopted by the invention is as follows:
a storage medium having stored therein processor-executable instructions for performing the method as described above when executed by a processor.
The invention has the beneficial effects that: the invention only needs to input key words, automatically searches related news data from a database or the Internet, and quickly generates news manuscripts by combining the news data and AI technology without manually collecting materials and writing the manuscripts, thereby greatly improving the efficiency of generating the manuscripts.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for automatically generating manuscripts based on AI in an embodiment;
fig. 2 is a block diagram illustrating a system for automatically generating manuscripts based on AI according to an embodiment.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention.
It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature or indirectly fixed or connected to the other feature. Furthermore, the descriptions of upper, lower, left, right, etc. used in the present disclosure are only relative to the mutual positional relationship of the constituent parts of the present disclosure in the drawings. As used in this disclosure, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any combination of one or more of the associated listed items.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element of the same type from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure. The use of any and all examples, or exemplary language ("e.g.," such as "or the like") provided herein, is intended merely to better illuminate embodiments of the invention and does not pose a limitation on the scope of the invention unless otherwise claimed.
As shown in fig. 1, the present embodiment provides a method for automatically generating manuscripts based on AI, which includes the following steps:
s101, collecting manuscript data based on a network technology, and establishing a database according to the manuscript data.
In this embodiment, downloaded manuscript data, for example, downloadable poster data, news manuscript data, and yearbook data of a relevant department, may be collected from a network based on big data; the manuscript data can also be intercepted through a website page, for example, relevant manuscript data is downloaded from a new wave network, a phoenix network or a CCTV network page. Specifically, the manuscript data includes at least one of news manuscript, public opinion manuscript, thesis document and comment data.
The step of establishing the database by acquiring the document data on the web page specifically includes steps S1011 to S1012:
s1011, capturing manuscript data from a preset website by using a preset web crawler model, wherein the manuscript data comprises at least one of character information, picture information, video information or model information;
and S1012, classifying and storing the manuscript data according to a preset mode to build a database.
In this embodiment, the distributed crawler is used to capture the document data from a website, where the document data includes at least one of text information, picture information, video information, or model information, where the website for capturing the data may be a website such as internet, phoenix, Tencent, and the like, and the model information includes a human face model, an animal model, and the like. Specifically, in the crawling process, codes with manuscript data can be crawled aiming at the network page, and codes of other peripheral advertisement data or link jump data are not crawled. Classifying the captured manuscript data, wherein the data classification can be classified according to the types of news, such as classification of international news and social news, classification of entertainment news and public opinion data, and classification of patent, thesis literature and scientific magazine information; the data file can also be classified according to the format of the data file, such as the classification of only characters, the classification of coexistence of the characters and the graphics, and the classification of pictures and judgment. The specific classification is performed according to actual needs, and is not specifically limited herein. And after the data are classified and stored, a database is finally formed. It should be noted that the database is not always changed after being formed, but is updated in real time according to the searched manuscript data to ensure that the database includes the latest message, so that the generated information has higher timeliness.
S102, obtaining keywords, and obtaining news data from a database or the Internet according to the keywords.
When a user needs to edit a manuscript, news data are automatically searched and obtained from a pre-established database by inputting keywords, for example, when a flight and a loss of contact are input, news data which are recently lost about the flight are searched and obtained; or when inputting the keywords of 'Wangzhaoqiang' and 'divorce', searching and acquiring the latest entertainment news data about the Wangzhaoqiang divorce; or when the keyword 'sportsbook' is input, the drawing numbers of the nearest sportsbook and news data of the winning situation are searched and obtained. When the corresponding news data can not be searched from the database, the news data can be directly downloaded from the Internet.
And S103, combining the news data with a preset AI algorithm to automatically generate a news initial draft, and auditing the news initial draft to obtain a final manuscript.
The AI algorithm may analyze news data using an existing neural network algorithm, and organically combine the news data obtained from a plurality of genres to generate a first draft. In a simple mode, the time data in the data can be identified and then typeset according to the time sequence; in a complex mode, the connection relation among the data can be identified through training, typesetting is carried out by combining the connection relation, meanwhile, a corresponding format template needs to be selected according to the content (including characters, pictures and the like) of the data, and then the news data is written into the template. The step S103 specifically includes steps S1031 to S1032:
s1031, determining news types according to the news data, and acquiring corresponding news templates from a preset template database according to the news types;
s1032, filling the news data into a news template by adopting a preset AI algorithm, and generating a news initial draft.
The establishing step of the template database comprises the steps of A1-A3:
a1, after obtaining the historical news manuscript, classifying the historical news manuscript;
a2, respectively extracting the type characteristics, the corpus characteristics and the structural characteristics of various historical news manuscripts;
a3, training a neural network by taking the same type of historical news manuscript with extracted features as a training set to obtain a news template; wherein, the various types of news manuscripts correspond to a plurality of news templates.
A large number of historical news manuscripts are obtained in advance, wherein the historical news manuscripts are previous news documents and comprise image-text information, typesetting information and the like. The type features are type information of articles, such as papers, news, patents, review articles and the like, and each type of articles can be further divided, for example, the type information of news comprises news information with pictures and news information without pictures. The corpus characteristic sentence characteristic and the word characteristic are specifically used for analyzing the semantics of sentences, for example, the semantics of scientific and technical papers and the semantics of news are different, and document types can be distinguished by identifying different semantics. The structural characteristics are the typesetting structure of the manuscript, and comprise different types of article frames, such as a main title, a subheading (abstract), a text and the like, and also comprise the typesetting of characters and pictures in the text.
After obtaining the news data, first judging the type of the news data, for example, specifically, the type of the news draft with the image and text, and then composing the news data according to the format of the news template by obtaining the corresponding news template, thereby generating a news initial draft. The step of checking the news initial draft can adopt manual checking or machine automation mode to check specifically; the adoption of the mode of machine automation mode auditing can greatly improve the efficiency and is more suitable for urgent manuscripts. The automatic manuscript examining specifically comprises the following steps of S1033-S1034:
s1033, detecting that the news initial draft has sentence segments with the same content by adopting a duplicate checking technology, and deleting the same sentence segments;
and S1034, detecting the sensitive words in the news primary draft by combining with a preset sensitive word bank, and replacing the detected sensitive words.
Since the manuscript data stored in the database are obtained from a plurality of websites, the same news event and different description modes exist, so that the news manuscript needs to be subjected to duplicate checking processing, paragraphs with approximately the same content are found, and paragraphs with the same content are deleted. Some words may relate to politically sensitive topics, and the related sensitive words need to be shielded, for example, if the sensitive words exist in the content downloaded from a foreign website, the sensitive words may be replaced by "+" signs.
As a further optional implementation, the method further includes a step of generating a data graph, specifically:
detecting and acquiring data information in the news primary draft, and generating a data graph by combining the acquired data information and a preset graph database, wherein the data graph comprises at least one of a bar graph, a line graph, a pie graph, a radar chart and a scatter diagram.
Aiming at the fact that some news manuscripts have associated data, data information in the manuscripts is obtained, for example, annual report data about import and export of China is stored, and import and export data of the past year and import and export data of the present year are stored, the data are compared through obtaining the data of the same type, and a data graph is generated by combining a preset model in a graph database, so that the generated manuscripts are more visual.
The embodiment can quickly search news data from the database based on the keywords, automatically generate the news initial draft, reduce the time consumption of manual information search and writing, greatly improve the draft output efficiency, reduce the draft output cost, and is suitable for the reports of the news such as emergent emergencies.
As shown in fig. 2, this embodiment further provides a system for automatically generating manuscripts based on AI, which includes:
the database establishing module is used for collecting the manuscript data based on the network technology and establishing a database according to the manuscript data;
the data acquisition module is used for acquiring keywords and acquiring news data from a database or the Internet according to the keywords;
and the manuscript generation module is used for automatically generating a news initial draft by combining the news data and a preset AI algorithm, and obtaining a final manuscript after the news initial draft is checked.
The system for automatically generating manuscripts based on AI according to the embodiment of the present invention can execute the method for automatically generating manuscripts based on AI according to the embodiment of the present invention, and can execute any combination of the implementation steps of the method embodiment, and has the corresponding functions and advantages of the method.
The embodiment also provides a device for automatically generating manuscripts based on the AI, which comprises:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The device for automatically generating manuscripts based on AI according to the embodiment of the invention can execute the method for automatically generating manuscripts based on AI provided by the embodiment of the method of the invention, can execute any combination of the implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
The present embodiments also provide a storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform the method as described above.
The storage medium of this embodiment may execute the method for automatically generating a manuscript based on AI according to the method embodiment of the present invention, may execute any combination of the implementation steps of the method embodiment, and has corresponding functions and advantageous effects of the method.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein.
A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.
Claims (10)
1. A method for automatically generating manuscripts based on AI (artificial intelligence), which is characterized by comprising the following steps:
searching manuscript data based on a network technology, and establishing a database according to the manuscript data;
acquiring a keyword, and acquiring news data from a database or the Internet according to the keyword;
and combining the news data with a preset AI algorithm to automatically generate a news initial draft, and auditing the news initial draft to obtain a final manuscript.
2. The AI-based automatic manuscript generation method according to claim 1, wherein the step of collecting manuscript data and creating a database according to the manuscript data based on the web technology comprises the following steps:
capturing manuscript data from a preset website by using a preset web crawler model, wherein the manuscript data comprises at least one of character information, picture information, video information or model information;
and classifying and storing the manuscript data according to a preset mode to build a database.
3. The method according to claim 2, wherein the step of automatically generating an initial news draft by combining news data and a preset AI algorithm comprises:
determining a news type according to the news data, and acquiring a corresponding news template from a preset template database according to the news type;
and filling the news data into a news template by adopting a preset AI algorithm to generate a news initial draft.
4. The AI-based automatic manuscript generation method according to claim 3, further comprising a step of creating a manuscript module library, specifically:
after obtaining the historical news manuscript, classifying the historical news manuscript;
respectively extracting type features, corpus features and structural features of various historical news manuscripts;
training a neural network by taking the historical news manuscripts with the same extracted features as a training set to obtain a news template;
wherein, the various types of news manuscripts correspond to a plurality of news templates.
5. The AI-based automatic contribution generating method of claim 1, wherein the step of reviewing the news initial draft comprises at least one of:
detecting sentence segments with the same content in the news initial draft by adopting a duplicate checking technology, and deleting the same sentence segments;
and detecting the sensitive words in the news primary draft by combining a preset sensitive word bank, and replacing the detected sensitive words.
6. The AI-based automatic manuscript generation method of claim 3, further comprising a step of generating a data map, specifically:
detecting and acquiring data information in the news primary draft, and generating a data graph by combining the acquired data information and a preset graph database, wherein the data graph comprises at least one of a bar graph, a line graph, a pie graph, a radar chart and a scatter diagram.
7. The AI-based automatic contribution generating method of any of claims 1-6, wherein the contribution data comprises at least one of news contribution, public opinion contribution, paper literature, and review data.
8. A system for automatically generating a contribution based on AI, comprising:
the database establishing module is used for collecting the manuscript data based on the network technology and establishing a database according to the manuscript data;
the data acquisition module is used for acquiring keywords and acquiring news data from a database or the Internet according to the keywords;
and the manuscript generation module is used for automatically generating a news initial draft by combining the news data and a preset AI algorithm, and obtaining a final manuscript after the news initial draft is checked.
9. An apparatus for automatically generating a contribution based on AI, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, the at least one program causes the at least one processor to implement a method for automatically generating manuscripts based on AI according to any one of claims 1 to 7.
10. A storage medium having stored therein processor-executable instructions, which when executed by a processor, are configured to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010376133.4A CN111695014A (en) | 2020-05-07 | 2020-05-07 | Method, system, device and storage medium for automatically generating manuscripts based on AI (artificial intelligence) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010376133.4A CN111695014A (en) | 2020-05-07 | 2020-05-07 | Method, system, device and storage medium for automatically generating manuscripts based on AI (artificial intelligence) |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111695014A true CN111695014A (en) | 2020-09-22 |
Family
ID=72476505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010376133.4A Pending CN111695014A (en) | 2020-05-07 | 2020-05-07 | Method, system, device and storage medium for automatically generating manuscripts based on AI (artificial intelligence) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695014A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417825A (en) * | 2020-11-20 | 2021-02-26 | 广州欢网科技有限责任公司 | Auxiliary system is write to news manuscript |
| CN112733516A (en) * | 2020-12-31 | 2021-04-30 | 京东数字科技控股股份有限公司 | Method, device, equipment and storage medium for processing instant messages |
| CN113157937A (en) * | 2021-03-04 | 2021-07-23 | 浙报融媒体科技(浙江)有限责任公司 | Machine real-time automatic manuscript writing system and method based on flow calculation model |
| CN114925668A (en) * | 2022-05-20 | 2022-08-19 | 电子科技大学 | System, method and storage medium for automatically generating news |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123269A (en) * | 2014-07-16 | 2014-10-29 | 华中科技大学 | Semi-automatic publication generation method and system based on template |
| CN106776523A (en) * | 2017-01-22 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | News speed report generation method and device based on artificial intelligence |
| CN108073561A (en) * | 2017-12-18 | 2018-05-25 | 广东广业开元科技有限公司 | The edit methods and Press release of a kind of Press release are write robot system |
| CN110188349A (en) * | 2019-05-21 | 2019-08-30 | 清华大学深圳研究生院 | A kind of automation writing method based on extraction-type multiple file summarization method |
-
2020
- 2020-05-07 CN CN202010376133.4A patent/CN111695014A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123269A (en) * | 2014-07-16 | 2014-10-29 | 华中科技大学 | Semi-automatic publication generation method and system based on template |
| CN106776523A (en) * | 2017-01-22 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | News speed report generation method and device based on artificial intelligence |
| CN108073561A (en) * | 2017-12-18 | 2018-05-25 | 广东广业开元科技有限公司 | The edit methods and Press release of a kind of Press release are write robot system |
| CN110188349A (en) * | 2019-05-21 | 2019-08-30 | 清华大学深圳研究生院 | A kind of automation writing method based on extraction-type multiple file summarization method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417825A (en) * | 2020-11-20 | 2021-02-26 | 广州欢网科技有限责任公司 | Auxiliary system is write to news manuscript |
| CN112733516A (en) * | 2020-12-31 | 2021-04-30 | 京东数字科技控股股份有限公司 | Method, device, equipment and storage medium for processing instant messages |
| CN112733516B (en) * | 2020-12-31 | 2024-04-09 | 京东科技控股股份有限公司 | Method, device, equipment and storage medium for processing quick message |
| CN113157937A (en) * | 2021-03-04 | 2021-07-23 | 浙报融媒体科技(浙江)有限责任公司 | Machine real-time automatic manuscript writing system and method based on flow calculation model |
| CN114925668A (en) * | 2022-05-20 | 2022-08-19 | 电子科技大学 | System, method and storage medium for automatically generating news |
| CN114925668B (en) * | 2022-05-20 | 2023-04-07 | 电子科技大学 | System, method and storage medium for automatically generating news |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695014A (en) | Method, system, device and storage medium for automatically generating manuscripts based on AI (artificial intelligence) | |
| CN108932294B (en) | Resume data processing method, device, equipment and storage medium based on index | |
| JP5021640B2 (en) | Detect, store, index, and search means for leveraging data on user activity, attention, and interests | |
| US9646077B2 (en) | Time-series analysis based on world event derived from unstructured content | |
| CN112101335B (en) | APP violation monitoring method based on OCR and transfer learning | |
| US20110078206A1 (en) | Tagging method and apparatus based on structured data set | |
| US10210211B2 (en) | Code searching and ranking | |
| EP3270303A1 (en) | An automated monitoring and archiving system and method | |
| CN103473369A (en) | Semantic-based information acquisition method and semantic-based information acquisition system | |
| CN112015962A (en) | Government affair intelligent big data center system architecture | |
| WO2020101479A1 (en) | System and method to detect and generate relevant content from uniform resource locator (url) | |
| CN112818200A (en) | Data crawling and event analyzing method and system based on static website | |
| CN115937887A (en) | Method and device for extracting document structured information, electronic equipment and storage medium | |
| CN112000929A (en) | Cross-platform data analysis method, system, equipment and readable storage medium | |
| CN116151233A (en) | Data labeling and generating method, model training method, device and medium | |
| CN116089732B (en) | User preference identification method and system based on advertisement click data | |
| KR20100103001A (en) | Issue analyzing system and issue data generation method | |
| CN111859108A (en) | Public opinion system search word recommendation system | |
| US11314793B2 (en) | Query processing | |
| CN116521729A (en) | Information classification searching method and device based on elastic search | |
| CN113407678B (en) | Knowledge graph construction method, device and equipment | |
| CN115186240A (en) | Social network user alignment method, device and medium based on relevance information | |
| CN113569132A (en) | Information retrieval display method and system | |
| CN114969467A (en) | Data analysis and classification method and device, computer equipment and storage medium | |
| KR20080028031A (en) | System extracting and displaying keyword and contents related with the keyword and method using the 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200922 |
|
| RJ01 | Rejection of invention patent application after publication |