CN110807305A - Manuscript generation method and system for replacing keywords - Google Patents
Manuscript generation method and system for replacing keywords Download PDFInfo
- Publication number
- CN110807305A CN110807305A CN201910963015.0A CN201910963015A CN110807305A CN 110807305 A CN110807305 A CN 110807305A CN 201910963015 A CN201910963015 A CN 201910963015A CN 110807305 A CN110807305 A CN 110807305A
- Authority
- CN
- China
- Prior art keywords
- manuscript
- manuscripts
- main body
- similar
- replacing
- 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 22
- 241000282414 Homo sapiens Species 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 229920001621 AMOLED Polymers 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Landscapes
- Document Processing Apparatus (AREA)
Abstract
The invention relates to a manuscript generation method and system for replacing keywords. The method comprises the following steps: receiving a manuscript subject matter input by a user; removing the target main body keywords from the theme of the manuscript to obtain the manuscript to be matched; matching a plurality of similar manuscripts according to the manuscripts to be matched; selecting one of a plurality of similar manuscripts as a template manuscript; replacing each sentence in the template manuscript with a similar sentence matched from manuscripts except the template manuscript in the plurality of similar manuscripts respectively to obtain manuscripts to be replaced; and replacing the main body key words to be replaced in the manuscript to be replaced with the target main body key words. The invention can self-learn the draft style of each manuscript, has rich content and strong readability, is similar to the normal draft style of human beings, can be widely applied to all walks of life, and reduces the difficulty of draft writing by using the method, so that common people can write professional manuscripts of all walks of life.
Description
Technical Field
The invention relates to the field of text processing, in particular to a manuscript generation method and system for replacing keywords.
Background
At present, there are some manuscript generation methods in the market, which define some fixed article templates manually, and perform main body replacement to form manuscripts, and such manuscripts can only be applied in industries with relatively standard manuscript structures. For example, a sports game report can be formed by making several templates of game report manuscripts in the background and changing old competitors, time, place, team, scores, etc. into new information.
The existing manuscript generation method has the defects that manuscripts generated by applying a fixed template are uniform in style, mechanical, free of too much emotion and deep viewpoint description, and the generated manuscripts are rigid, can only be applied to specific industries such as sports, finance and sports generally, and cannot meet the requirements of real manuscripts on flexibility and variety.
Disclosure of Invention
In view of the above technical problems, the present invention provides a method and system for generating a manuscript capable of replacing a keyword.
The technical scheme for solving the technical problems is as follows: a manuscript generation method for replacing keywords comprises the following steps:
receiving a manuscript subject matter input by a user;
removing the target main body keywords from the manuscript subject to obtain a manuscript to be matched;
matching a plurality of similar manuscripts according to the manuscripts to be matched;
selecting one of the similar manuscripts as a template manuscript;
replacing each sentence in the template manuscript with a similar sentence matched from manuscripts except the template manuscript in the plurality of similar manuscripts respectively to obtain manuscripts to be replaced;
and replacing the main body key words to be replaced in the manuscript to be replaced with the target main body key words.
The invention has the beneficial effects that: the method breaks through the limitation of a fixed template, does not need to manually set the fixed manuscript template, can self-learn the manuscript writing style of each manuscript, generates various manuscripts by replacing keywords, has rich content and strong readability, is similar to the normal manuscript writing style of human beings instead of looking like the manuscripts generated by machines, can continuously and autonomously learn various manuscript styles, can be widely applied to various industries, reduces the difficulty in writing manuscripts by using the method, and enables ordinary people to write professional manuscripts of various industries.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, the removing of the target subject keyword from the manuscript theme specifically includes:
identifying target subject keywords from the manuscript subject matter through semantic analysis;
and removing the target main body key words.
Further, the matching of multiple similar manuscripts according to the manuscripts to be matched specifically includes:
and matching a plurality of similar manuscripts in the network data crawled from the network by utilizing a network crawler technology according to the manuscripts to be matched.
Further, the selecting one of the similar manuscripts as a template manuscript specifically includes:
and selecting one of the similar manuscripts with the highest similarity to the manuscripts to be matched as the template manuscripts.
Further, the replacing the main body keyword to be replaced in the manuscript to be replaced with the target main body keyword specifically includes:
identifying a main body keyword to be replaced from the manuscript main subject through semantic analysis;
replacing the main body key words to be replaced with blank spaces;
receiving a target subject keyword entered by a user at a space.
In order to achieve the above object, the present invention further provides a system for generating a manuscript capable of replacing a keyword, comprising:
the receiving module is used for receiving manuscript subject matters input by a user;
the deleting module is used for removing the target main body keywords from the theme of the manuscript to obtain the manuscript to be matched;
the matching module is used for matching a plurality of similar manuscripts according to the manuscripts to be matched;
the selection module is used for selecting one of the similar manuscripts as a template manuscript;
the first replacement module is used for replacing each sentence in the template manuscript with a similar sentence matched from manuscripts except the template manuscript in the plurality of similar manuscripts to obtain manuscripts to be replaced;
and the second replacement module is used for replacing the main body key words to be replaced in the manuscript to be replaced with the target main body key words.
Further, the deleting module specifically includes:
a first recognition unit configured to recognize a target subject keyword from the manuscript subject matter by semantic analysis;
and the deleting unit is used for removing the target main body key words.
Further, the matching module is specifically configured to:
and matching a plurality of similar manuscripts in the network data crawled from the network by utilizing a network crawler technology according to the manuscripts to be matched.
Further, the selection module is specifically configured to:
and selecting one of the similar manuscripts with the highest similarity to the manuscripts to be matched as the template manuscripts.
Further, the second replacement module specifically includes:
a second recognition unit for recognizing a subject keyword to be replaced from the manuscript subject by semantic analysis;
the replacing unit is used for replacing the main body key words to be replaced with blank spaces;
the receiving unit is used for receiving the target main body key words which are input by the user at the blank spaces.
Drawings
Fig. 1 is a flowchart of a manuscript generation method for replacing a keyword according to an embodiment of the present invention;
fig. 2 is a block diagram of a document generation system for replacing keywords according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart of a manuscript generation method for replacing a keyword according to an embodiment of the present invention, as shown in fig. 1, the method includes:
s1, receiving the manuscript subject inputted by the user;
s2, removing the target main body keywords from the theme of the manuscript to obtain the manuscript to be matched;
s3, matching a plurality of similar manuscripts according to the manuscripts to be matched;
s4, selecting one of the similar manuscripts as a template manuscript;
s5, replacing each sentence in the template manuscript with a similar sentence matched from manuscripts except the template manuscript in the plurality of similar manuscripts respectively to obtain manuscripts to be replaced;
s6, replacing the main body key words to be replaced in the manuscript to be replaced with the target main body key words.
Specifically, after a user inputs a section of manuscript subject to be written, target main body keywords such as brands, products, names of people and the like are firstly identified and removed from the manuscript subject through semantic analysis to obtain a manuscript to be matched, and then a plurality of similar manuscripts are matched according to the manuscript to be matched, namely, historical articles with inconsistent subjects and similar events are found from massive manuscripts crawled through network through verbs and adjectives in the subject.
After the manuscripts of the batch of similar events are found, under the condition that the front-back sequence and the logic structure of the articles are kept unchanged, one of the multiple similar manuscripts with the highest similarity with the manuscripts to be matched is selected as a template manuscript, each sentence of the template manuscript is matched with a similar sentence, and the similar expression is changed for each sentence, so that the meaning is unchanged and the statement is changed. And replacing the manuscript after the similar sentence is replaced, and removing the main key words in the manuscript to form spaces. The blank space part is filled by the manuscript writer, and the manuscript writer inputs the main key words in the manuscript to be written into the blank space according to the theme of the manuscript to form a brand new manuscript.
The method for generating the manuscript replacing the keywords comprehensively utilizes semantic analysis, a natural language processing technology, a similarity matching algorithm, a web crawler technology and a big data processing technology, breaks through the limitation of a fixed template, does not need to manually set the fixed manuscript template, can self-learn the manuscript writing style of each manuscript, generates various manuscripts by replacing the keywords, has rich contents and strong readability, is similar to the normal manuscript writing style of human beings instead of looking like a manuscript generated by a machine, can autonomously learn various manuscript styles, can be widely applied to various industries, reduces the difficulty in writing the manuscripts by using the method, and enables ordinary people to write professional manuscripts of various industries.
Fig. 2 is a block diagram of a structure of a manuscript generation system for replacing a keyword according to an embodiment of the present invention, and as shown in fig. 2, the system includes:
the receiving module is used for receiving manuscript subject matters input by a user;
the deleting module is used for removing the target main body keywords from the theme of the manuscript to obtain the manuscript to be matched;
the matching module is used for matching a plurality of similar manuscripts according to the manuscripts to be matched;
the selection module is used for selecting one of the similar manuscripts as a template manuscript;
the first replacement module is used for replacing each sentence in the template manuscript with a similar sentence matched from manuscripts except the template manuscript in the plurality of similar manuscripts to obtain manuscripts to be replaced;
and the second replacement module is used for replacing the main body key words to be replaced in the manuscript to be replaced with the target main body key words.
Optionally, in this embodiment, the deleting module specifically includes:
a first recognition unit configured to recognize a target subject keyword from the manuscript subject matter by semantic analysis;
and the deleting unit is used for removing the target main body key words.
Optionally, in this embodiment, the matching module is specifically configured to:
and matching a plurality of similar manuscripts in the network data crawled from the network by utilizing a network crawler technology according to the manuscripts to be matched.
Optionally, in this embodiment, the selecting module is specifically configured to:
and selecting one of the similar manuscripts with the highest similarity to the manuscripts to be matched as the template manuscripts.
Optionally, in this embodiment, the second replacement module specifically includes:
a second recognition unit for recognizing a subject keyword to be replaced from the manuscript subject by semantic analysis;
the replacing unit is used for replacing the main body key words to be replaced with blank spaces;
the receiving unit is used for receiving the target main body key words which are input by the user at the blank spaces.
One embodiment based on the present invention is as follows:
for example, writing a new machine publishing manuscript of a vivo mobile phone, firstly, finding a template manuscript by words such as a new machine and publishing of a subject keyword as follows:
in the era of increasing screen occupation and reducing bang above the screen dedicated to most manufacturers, Vivo ingeniously creates a pop-up self-shooting camera, realizes the presentation of a complete screen by using a built-in camera, and ensures full-screen experience.
Unfortunately, there is currently only a leakage map for NEX 2 and we do not have much reliable information about the specification. However, the original Vivo NEX was equipped with a 6.59 inch Super AMOLED screen, with a cellcepron 845 processor and with 8GB memory, and the foreign media indicated that it would be highly desirable to see the same configuration or better on the next generation of cell phones.
Then, sentence replacement is carried out on the template manuscript, and the main keywords in the template manuscript are deducted as follows:
firstly, the screen ____ does not adopt ____ nor ____ full-face screen, but a style of appearance ____ with higher screen occupation ratio ____ is provided, the screen occupation ratio reaches ____%, and meanwhile, the color value of the mobile phone is greatly improved.
____ at the beginning of its release, ____ borderless technology makes the cell phone have ____ inch screen visual experience the same as ____ inch cell phone, meanwhile, ____ processor is loaded at the time, ____ gB memory is labeled, ____ and ____ storage specifications are selectable, and ____ large memory is equipped at the highest.
Then filling in the main content of the manuscript to be written to form a new manuscript as follows:
the mobile phone is characterized in that a screen is firstly adopted, a Liuhai screen or a water drop full-face screen is not adopted for glowing, a glamour full-view screen with high appearance ratio and screen occupation ratio is provided, the screen occupation ratio is up to 91.28%, and meanwhile, the color value of the mobile phone is greatly improved.
Glorious v20 enables the mobile phone to have the visual experience of a 6.4-inch screen by an ultra-wide frameless technology at the beginning of the release of the mobile phone, and meanwhile, a kylin 980 processor is mounted at the moment, a 64gB memory is matched, two storage specifications of 64G and 128G are selectable, and a maximum 256G memory is matched.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A manuscript generation method for replacing keywords is characterized by comprising the following steps:
receiving a manuscript subject matter input by a user;
removing the target main body keywords from the manuscript subject to obtain a manuscript to be matched;
matching a plurality of similar manuscripts according to the manuscripts to be matched;
selecting one of the similar manuscripts as a template manuscript;
replacing each sentence in the template manuscript with a similar sentence matched from manuscripts except the template manuscript in the plurality of similar manuscripts respectively to obtain manuscripts to be replaced;
and replacing the main body key words to be replaced in the manuscript to be replaced with the target main body key words.
2. The method as claimed in claim 1, wherein the removing of the target subject keyword from the theme of the manuscript specifically comprises:
identifying target subject keywords from the manuscript subject matter through semantic analysis;
and removing the target main body key words.
3. The method for generating manuscripts replacing keywords according to claim 1, wherein the matching of multiple similar manuscripts according to the manuscripts to be matched specifically comprises:
and matching a plurality of similar manuscripts in the network data crawled from the network by utilizing a network crawler technology according to the manuscripts to be matched.
4. The method for generating a manuscript substituting for a keyword according to claim 1, wherein selecting one of the plurality of similar manuscripts as a template manuscript specifically comprises:
and selecting one of the similar manuscripts with the highest similarity to the manuscripts to be matched as the template manuscripts.
5. The method for generating a keyword-replaceable manuscript according to any one of claims 1 to 4, wherein the replacing the main body keyword to be replaced in the manuscript to be replaced with the target main body keyword specifically comprises:
identifying a main body keyword to be replaced from the manuscript main subject through semantic analysis;
replacing the main body key words to be replaced with blank spaces;
receiving a target subject keyword entered by a user at a space.
6. A manuscript generation system for replacing a keyword, comprising:
the receiving module is used for receiving manuscript subject matters input by a user;
the deleting module is used for removing the target main body keywords from the theme of the manuscript to obtain the manuscript to be matched;
the matching module is used for matching a plurality of similar manuscripts according to the manuscripts to be matched;
the selection module is used for selecting one of the similar manuscripts as a template manuscript;
the first replacement module is used for replacing each sentence in the template manuscript with a similar sentence matched from manuscripts except the template manuscript in the plurality of similar manuscripts to obtain manuscripts to be replaced;
and the second replacement module is used for replacing the main body key words to be replaced in the manuscript to be replaced with the target main body key words.
7. The system for generating a manuscript substituting for a keyword according to claim 6, wherein the deleting module specifically comprises:
a first recognition unit configured to recognize a target subject keyword from the manuscript subject matter by semantic analysis;
and the deleting unit is used for removing the target main body key words.
8. The system of claim 6, wherein the matching module is specifically configured to:
and matching a plurality of similar manuscripts in the network data crawled from the network by utilizing a network crawler technology according to the manuscripts to be matched.
9. The system of claim 6, wherein the selection module is specifically configured to:
and selecting one of the similar manuscripts with the highest similarity to the manuscripts to be matched as the template manuscripts.
10. The system for generating a manuscript substituting for a keyword according to any one of claims 6 to 9, wherein the second substituting module specifically comprises:
a second recognition unit for recognizing a subject keyword to be replaced from the manuscript subject by semantic analysis;
the replacing unit is used for replacing the main body key words to be replaced with blank spaces;
the receiving unit is used for receiving the target main body key words which are input by the user at the blank spaces.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910963015.0A CN110807305A (en) | 2019-10-11 | 2019-10-11 | Manuscript generation method and system for replacing keywords |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910963015.0A CN110807305A (en) | 2019-10-11 | 2019-10-11 | Manuscript generation method and system for replacing keywords |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110807305A true CN110807305A (en) | 2020-02-18 |
Family
ID=69488216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910963015.0A Pending CN110807305A (en) | 2019-10-11 | 2019-10-11 | Manuscript generation method and system for replacing keywords |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110807305A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651220A (en) * | 2021-01-28 | 2021-04-13 | 宁夏智诚安环科技发展股份有限公司四川分公司 | Environmental impact evaluation report generation method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503255A (en) * | 2016-11-15 | 2017-03-15 | 科大讯飞股份有限公司 | Based on the method and system that description text automatically generates article |
| CN108470064A (en) * | 2018-03-26 | 2018-08-31 | 黑龙江省经济管理干部学院 | A kind of news release generation method based on intelligent robot |
| CN109657223A (en) * | 2018-12-18 | 2019-04-19 | 安徽省泰岳祥升软件有限公司 | A kind of automatic writing method of official document and device |
| US20190228064A1 (en) * | 2014-10-30 | 2019-07-25 | International Business Machines Corporation | Generation apparatus, generation method, and program |
-
2019
- 2019-10-11 CN CN201910963015.0A patent/CN110807305A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190228064A1 (en) * | 2014-10-30 | 2019-07-25 | International Business Machines Corporation | Generation apparatus, generation method, and program |
| CN106503255A (en) * | 2016-11-15 | 2017-03-15 | 科大讯飞股份有限公司 | Based on the method and system that description text automatically generates article |
| CN108470064A (en) * | 2018-03-26 | 2018-08-31 | 黑龙江省经济管理干部学院 | A kind of news release generation method based on intelligent robot |
| CN109657223A (en) * | 2018-12-18 | 2019-04-19 | 安徽省泰岳祥升软件有限公司 | A kind of automatic writing method of official document and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651220A (en) * | 2021-01-28 | 2021-04-13 | 宁夏智诚安环科技发展股份有限公司四川分公司 | Environmental impact evaluation report generation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9336299B2 (en) | Acquisition of semantic class lexicons for query tagging | |
| Sun et al. | Deep LSTM networks for online Chinese handwriting recognition | |
| US7962507B2 (en) | Web content mining of pair-based data | |
| CN105205699A (en) | User label and hotel label matching method and device based on hotel comments | |
| CN111488931A (en) | Article quality evaluation method, article recommendation method and corresponding devices | |
| US20190286931A1 (en) | Method and system for automatic image caption generation | |
| Chen et al. | Large-scale tag-based font retrieval with generative feature learning | |
| Adar et al. | CommandSpace: modeling the relationships between tasks, descriptions and features | |
| US20210303864A1 (en) | Method and apparatus for processing video, electronic device, medium and product | |
| CN109978139B (en) | Method, system, electronic device and storage medium for automatically generating description of picture | |
| CN111078893A (en) | Method for efficiently acquiring and identifying linguistic data for dialog meaning graph in large scale | |
| CN108345612A (en) | A kind of question processing method and device, a kind of device for issue handling | |
| Fang et al. | Image captioning with word level attention | |
| CN106095912A (en) | For the method and apparatus generating expanding query word | |
| CN111125457A (en) | Deep cross-modal Hash retrieval method and device | |
| CN111553138B (en) | Auxiliary writing method and device for standardizing content structure document | |
| US11928418B2 (en) | Text style and emphasis suggestions | |
| CN110807305A (en) | Manuscript generation method and system for replacing keywords | |
| Rigaud | Segmentation and indexation of complex objects in comic book images | |
| Prakash et al. | Information extraction in unstructured multilingual web documents | |
| CN107784112A (en) | Short text data Enhancement Method, system and detection authentication service platform | |
| CN116977992A (en) | Text information identification method, apparatus, computer device and storage medium | |
| CN111125387B (en) | Multimedia list generation and naming method and device, electronic equipment and storage medium | |
| CN114332476A (en) | Method, device, electronic equipment, storage medium and product for identifying dimensional language | |
| O'Donovan | Learning design: aesthetic models for color, layout, and typography |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200218 |