CN111475625A - News manuscript generation method and system based on knowledge graph - Google Patents
News manuscript generation method and system based on knowledge graph Download PDFInfo
- Publication number
- CN111475625A CN111475625A CN202010387447.4A CN202010387447A CN111475625A CN 111475625 A CN111475625 A CN 111475625A CN 202010387447 A CN202010387447 A CN 202010387447A CN 111475625 A CN111475625 A CN 111475625A
- Authority
- CN
- China
- Prior art keywords
- manuscript
- user
- data
- news
- knowledge
- 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 43
- 230000002996 emotional effect Effects 0.000 claims abstract description 24
- 239000000463 material Substances 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000013481 data capture Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000005406 washing 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a news manuscript generation method and a system based on a knowledge graph, which comprises the following steps: acquiring a title, a manuscript type or an emotional tendency of a manuscript to be authored set by a user; extracting keywords of a title of a news manuscript to be authored; according to the manuscript types, emotional tendency and the keywords of the titles, performing semantic search in a pre-constructed knowledge graph; inputting information obtained by semantic search into a user interest point recommendation model, and outputting the sequenced information; the sorted information is obtained by searching the semantic meanings and is sorted according to the interest degree of the user from high to low; acquiring a selection result of the user on the recommendation information, and taking the selection result of the user on the recommendation information as a basic material for creating the news manuscript; and processing the material created by the news manuscript to obtain an initial news manuscript.
Description
Technical Field
The disclosure relates to the technical field of news manuscript writing, in particular to a news manuscript generation method and system based on a knowledge map.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The robot is used for content production, the general working principle is that the key word extraction and matching algorithm is used for extracting the main information of content creation, the objective information is analyzed, compared and calculated, the key content is extracted, and the extracted content is spliced for the second time by the aid of a built-in template to form an article.
In the authoring process, the theme information of the manuscript is generated by data capture and random extraction, an authoring main body cannot be customized, the authoring content can only be used as information reference, and the method cannot be applied to actual business production and has no actual application value.
Disclosure of Invention
In order to solve the defects of the prior art, the disclosure provides a news manuscript generation method and system based on a knowledge graph;
in a first aspect, the present disclosure provides a method for generating a news article based on a knowledge-graph;
a news manuscript generation method based on a knowledge graph comprises the following steps:
acquiring a title, a manuscript type or an emotional tendency of a manuscript to be authored set by a user;
extracting keywords of a title of a news manuscript to be authored;
according to the manuscript types, emotional tendency and the keywords of the titles, performing semantic search in a pre-constructed knowledge graph;
inputting information obtained by semantic search into a user interest point recommendation model, and outputting the sequenced information; the sorted information is obtained by searching the semantic meanings and is sorted according to the interest degree of the user from high to low;
acquiring a selection result of the user on the recommendation information, and taking the selection result of the user on the recommendation information as a basic material for creating the news manuscript;
and processing the material created by the news manuscript to obtain an initial news manuscript.
In a second aspect, the present disclosure provides a system for generating a news article based on a knowledge-graph;
the news manuscript generating system based on the knowledge graph comprises:
an acquisition module configured to: acquiring a title, a manuscript type or an emotional tendency of a manuscript to be authored set by a user;
an extraction module configured to: extracting keywords of a title of a news manuscript to be authored;
a semantic search module configured to: according to the manuscript types, emotional tendency and the keywords of the titles, performing semantic search in a pre-constructed knowledge graph;
a ranking module configured to: inputting information obtained by semantic search into a user interest point recommendation model, and outputting the sequenced information; the sorted information is obtained by searching the semantic meanings and is sorted according to the interest degree of the user from high to low;
a processing module configured to: acquiring a selection result of the user on the recommendation information, and taking the selection result of the user on the recommendation information as a basic material for creating the news manuscript; and processing the material created by the news manuscript to obtain an initial news manuscript.
In a third aspect, the present disclosure also provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method of the first aspect is performed.
In a fourth aspect, the present disclosure also provides a computer-readable storage medium for storing computer instructions which, when executed by a processor, perform the method of the first aspect.
Compared with the prior art, the beneficial effect of this disclosure is:
the method comprises the steps of utilizing a knowledge graph to assist in producing content of a specific theme, utilizing a big data technology to capture, clean and arrange data to form a knowledge base, utilizing an N L P natural language processing technology to classify, analyze and extract data and entities of knowledge to build a material base based on the knowledge graph, analyzing a content creation theme set by a user through semantic understanding, matching the knowledge of the existing material base, assisting in creating manuscripts and finally creating manuscripts with practical prices.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
FIG. 1 is a diagram information example of the first embodiment;
FIG. 2 is a system architecture of the first embodiment;
FIG. 3 is a flowchart of user authoring of the first embodiment;
fig. 4 is a manuscript writing column of the robot of the first embodiment;
fig. 5 is an intelligent content production system of the first embodiment.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. 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 to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiment I provides a news manuscript generation method based on a knowledge graph;
a news manuscript generation method based on a knowledge graph comprises the following steps:
s101: acquiring a title, a manuscript type or an emotional tendency of a manuscript to be authored set by a user;
s102: extracting keywords of a title of a news manuscript to be authored;
s103: according to the manuscript types, emotional tendency and the keywords of the titles, performing semantic search in a pre-constructed knowledge graph;
s104: inputting information obtained by semantic search into a user interest point recommendation model, and outputting the sequenced information; the sorted information is obtained by searching the semantic meanings and is sorted according to the interest degree of the user from high to low;
s105: acquiring a selection result of the user on the recommendation information, and taking the selection result of the user on the recommendation information as a basic material for creating the news manuscript;
s106: and processing the material created by the news manuscript to obtain an initial news manuscript.
It should be understood that in S101, by acquiring the article category of the news manuscript to be authored and the emotional tendency of the news manuscript to be authored, the accuracy of manuscript authoring can be improved.
For example, in S101, the title of the news manuscript to be authored includes, for example: the title of the manuscript "create warm education in Jinan".
For example, in S101, the article categories of the news articles to be authored include, for example: education, civilian or emotional.
For example, in S101, the emotional tendency of the news manuscript to be authored includes, for example: positive, negative or neutral.
In the step S102, the keywords of the title are obtained by performing N L P natural language processing to perform word segmentation processing on the title content, and extracting the keywords according to the occurrence frequency and weight of each word segmentation in the content.
Further, in the step S103, according to the article type, emotional tendency, and keyword of the title, semantic search is performed in the pre-constructed knowledge graph; the method comprises the following specific steps: and matching the keywords of the manuscript types, the emotional tendency and the titles with the contents in a pre-constructed knowledge map by utilizing semantic search, and forming manuscript main body elements according to a pre-set manuscript template structure.
Further, in S103, the pre-constructed knowledge graph is constructed by the steps of:
s103a 1: acquiring an authoring field content source selected by a user;
s103a 2: performing data capture operation on the content source of the authoring field;
s103a 3: data cleaning is carried out on the captured data;
s103a 4: classifying the cleaned data to form a data category;
s103a 5: performing entity extraction on each type of data;
s103a 6: and constructing a graph database stored by taking an entity as a unit, and taking an entity-relationship-entity or entity-attribute-property value triple as a basic expression mode of a fact, wherein all data stored in the graph database form an entity relationship network to form a knowledge graph.
And acquiring knowledge, namely processing the structured and unstructured data acquired in the steps to extract structured data which can be understood and calculated by a computer for further analysis and utilization.
And (5) extracting the relation. The relation extraction is to automatically find the semantic relation between named entities from the text by using various technologies and map the relation in the text to entity relation triples.
Attributes are primarily specific to an entity to enable a complete description of the entity.
And (5) event extraction. An event is an occurrence or change in state of one or more actions taken in by one or more characters occurring at a particular point in time or time, within a particular geographic area.
And identifying knowledge. Based on knowledge acquisition, fusion, modeling, calculation and application, description and engagement of knowledge are performed to form knowledge expression as comprehensive as possible, so that the machine shows behaviors similar to human beings by learning the knowledge.
The sorted knowledge objects including basic attribute knowledge, associated knowledge, event knowledge, time sequence knowledge and resource knowledge are stored, knowledge inquiry, knowledge calculation and knowledge cognition of knowledge maps are facilitated, and efficiency is improved.
And integrating knowledge of the loosely-coupled sources combed in the steps by knowledge fusion to construct synthetic resources for supplementing incomplete knowledge, wherein the knowledge fusion comprises data layer knowledge fusion, concept layer knowledge fusion and cross-language knowledge fusion. By utilizing knowledge fusion technology, implicit or valuable new knowledge is acquired through acquisition, matching, integration, mining and other processing of knowledge on numerous dispersed and heterogeneous resources, meanwhile, the structure and the connotation of the knowledge are optimized, and knowledge service is provided.
And (4) knowledge modeling. And establishing a data model of the knowledge map by means of the knowledge formed in the steps, and describing the knowledge through the model. The knowledge graph construction foundation is established through knowledge modeling, so that a lot of unnecessary and repetitive knowledge acquisition work is avoided, the knowledge graph construction efficiency is effectively improved, and the field data fusion cost is reduced.
In the knowledge modeling process, a technical implementation mode combining manual modeling and semi-automatic modeling is introduced, a knowledge modeling evaluation system is introduced, knowledge with low confidence coefficient is abandoned, and the quality of a knowledge base is guaranteed.
The completeness of knowledge is improved and the coverage of knowledge is enlarged by using the techniques of knowledge statistics, graph mining, knowledge reasoning and the like. And wide material support is provided for the later manuscript authoring process. The information of the figure is shown in figure 1.
Illustratively, the authoring domain content sources include one or more of the following: a website, WeChat, microblog, newspaper, or television.
For example, the data cleansing of S103a3 includes, for example: in the process of establishing the knowledge graph, data management work such as data source combing and cleaning is required, and work personnel such as editors and journalists who know service scenes are required to complete the data management work, so that work such as text extraction and data labeling is involved, and through the data cleaning in the mode, the graph database is more accurate and comprehensive to construct and is used for supporting intelligent retrieval.
It should be appreciated that the data washing of S103a3 may assist in removing dirty data, and reduce the influence of invalid data.
Further, S103a 4: classifying the cleaned data to form a data category; the method comprises the following specific steps:
processing the cleaned data by using an N L P natural language model to obtain processed data;
classifying the processed data according to article categories;
and classifying the processed data according to emotional tendency.
Illustratively, the data categories include, but are not limited to, sports, finance, entertainment, fashion, and the like.
Illustratively, the emotional tendencies include, but are not limited to, positive, negative, or neutral.
Further, S103a 5: performing entity extraction on each type of data; the method comprises the following specific steps:
and extracting manuscript entities from the stored data, combing the corresponding knowledge points of the manuscript through main body extraction, and providing data support for the construction of the knowledge map.
Illustratively, the contribution entities include, but are not limited to, one or more of people, time, place, institution, and post.
It should be understood that, in the S103, the conventional search engine, taking keyword retrieval as a core technology, finds out and returns information matching with the keyword from the massive information through keyword comparison, and this search mode is a conventional machine search and does not query and give a result according to a human thinking mode. The search can be performed according to knowledge correlation by means of an intelligent search engine built by knowledge graph technology.
Further, in S104, the user interest point recommendation model is obtained through training; the specific training steps include:
constructing a neural network model;
constructing a training set; the training set is a user history search record of the interest degree of a known user;
and inputting the training set into a neural network model for training, wherein the obtained trained neural network model is the user interest point recommendation model.
Further, in S106, processing a material created from the news manuscript to obtain an initial news manuscript; the method comprises the following specific steps: and processing the material created by the news manuscript by using a TextRank algorithm or a probability sentence selection algorithm to obtain an initial news manuscript.
Further, the method further comprises:
s107: and editing the initial news manuscript to form a final news manuscript.
Further, the method further comprises:
s108: recording an editing operation event of a user, and acquiring a user feedback log;
s109: and optimizing the user image, optimizing the user interest point recommendation model and optimizing the knowledge graph according to the user feedback log.
And the editing operation event is, for example, addition, deletion, modification and the like of the document by the user.
Further, the user representation is optimized; the method comprises the following specific steps: by analyzing big data of a behavior log of a user, a user portrait is outlined according to user behaviors through an intelligent algorithm, and more accurate services are provided for the user based on the user portrait.
Further, optimizing the user interest point recommendation model; the method comprises the following specific steps: and analyzing and optimizing according to the selection condition and the modification editing action of the user historical composition manuscript, and sorting out a recommendation model aiming at the user by combining the user portrait.
Further, optimizing the knowledge graph; the method comprises the following specific steps:
and optimizing a recommendation algorithm and a content production algorithm according to the selection condition and the secondary editing condition of the user on the system recommendation manuscript.
The overall system architecture is shown in fig. 3, the flow chart for the application system is shown in fig. 2,
1. by means of the technical scheme, manuscript collection and writing of sports, finance and economics and agricultural product prices are completed, and the stock market summary of the day can be counted and analyzed and compared. The production and application effects are shown in the attached figure 4:
2. by means of the technical scheme, the built news creation service auxiliary production system can realize intelligent semantic search, intelligent building of knowledge bases and knowledge map construction. The production and application effects are shown in the attached figure 5:
the second embodiment provides a news manuscript generation system based on the knowledge graph;
the news manuscript generating system based on the knowledge graph comprises:
an acquisition module configured to: acquiring a title, a manuscript type or an emotional tendency of a manuscript to be authored set by a user;
an extraction module configured to: extracting keywords of a title of a news manuscript to be authored;
a semantic search module configured to: according to the manuscript types, emotional tendency and the keywords of the titles, performing semantic search in a pre-constructed knowledge graph;
a ranking module configured to: inputting information obtained by semantic search into a user interest point recommendation model, and outputting the sequenced information; the sorted information is obtained by searching the semantic meanings and is sorted according to the interest degree of the user from high to low;
a processing module configured to: acquiring a selection result of the user on the recommendation information, and taking the selection result of the user on the recommendation information as a basic material for creating the news manuscript; and processing the material created by the news manuscript to obtain an initial news manuscript.
It should be noted here that the acquiring module, the extracting module, the semantic searching module, the sorting module and the processing module correspond to steps S101 to S106 in the first embodiment, and the modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the contents disclosed in the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
In the foregoing embodiments, the descriptions of the embodiments have different emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical functional division, and in actual implementation, there may be other divisions, for example, multiple modules may be combined or integrated into another system, or some features may be omitted, or not executed.
In a third embodiment, the present embodiment further provides an electronic device, which includes a memory, a processor, and computer instructions stored in the memory and executed on the processor, where the computer instructions, when executed by the processor, implement the method in the first embodiment.
In a fourth embodiment, the present embodiment further provides a computer-readable storage medium for storing computer instructions, and the computer instructions, when executed by a processor, implement the method of the first embodiment.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. A news manuscript generation method based on a knowledge graph is characterized by comprising the following steps:
acquiring a title, a manuscript type or an emotional tendency of a manuscript to be authored set by a user;
extracting keywords of a title of a news manuscript to be authored;
according to the manuscript types, emotional tendency and the keywords of the titles, performing semantic search in a pre-constructed knowledge graph;
inputting information obtained by semantic search into a user interest point recommendation model, and outputting the sequenced information; the sorted information is obtained by searching the semantic meanings and is sorted according to the interest degree of the user from high to low;
acquiring a selection result of the user on the recommendation information, and taking the selection result of the user on the recommendation information as a basic material for creating the news manuscript;
and processing the material created by the news manuscript to obtain an initial news manuscript.
2. The method of claim 1, wherein semantic searches are performed in a pre-constructed knowledge graph based on the article type, emotional tendency, and keyword of title; the method comprises the following specific steps: and matching the keywords of the manuscript types, the emotional tendency and the titles with the contents in a pre-constructed knowledge map by utilizing semantic search, and forming manuscript main body elements according to a pre-set manuscript template structure.
3. The method of claim 1, wherein the pre-constructed knowledge-graph, the constructing step comprises:
acquiring an authoring field content source selected by a user;
performing data capture operation on the content source of the authoring field;
data cleaning is carried out on the captured data;
classifying the cleaned data to form a data category;
performing entity extraction on each type of data;
and constructing a graph database stored by taking an entity as a unit, and taking an entity-relationship-entity or entity-attribute-property value triple as a basic expression mode of a fact, wherein all data stored in the graph database form an entity relationship network to form a knowledge graph.
4. The method of claim 3, wherein the cleaned data is sorted into data categories; the method comprises the following specific steps:
processing the cleaned data by using an N L P natural language model to obtain processed data;
classifying the processed data according to article categories;
and classifying the processed data according to emotional tendency.
5. The method of claim 3, wherein the entity extraction is performed for each type of data; the method comprises the following specific steps:
and extracting manuscript entities from the stored data, combing the corresponding knowledge points of the manuscript through main body extraction, and providing data support for the construction of the knowledge map.
6. The method of claim 1, wherein the user point of interest recommendation model is derived by training; the specific training steps include:
constructing a neural network model;
constructing a training set; the training set is a user history search record of the interest degree of a known user;
and inputting the training set into a neural network model for training, wherein the obtained trained neural network model is the user interest point recommendation model.
7. The method of claim 1, wherein material authored by the news contribution is processed to obtain an initial news contribution; the method comprises the following specific steps: processing the material created by the news manuscript by using a TextRank algorithm or a probability sentence selection algorithm to obtain an initial news manuscript;
or,
the method further comprises the following steps: editing the initial news manuscript to form a final news manuscript;
recording an editing operation event of a user, and acquiring a user feedback log;
and optimizing the user image, optimizing the user interest point recommendation model and optimizing the knowledge graph according to the user feedback log.
8. The news manuscript generation system based on the knowledge map is characterized by comprising the following steps:
an acquisition module configured to: acquiring a title, a manuscript type or an emotional tendency of a manuscript to be authored set by a user;
an extraction module configured to: extracting keywords of a title of a news manuscript to be authored;
a semantic search module configured to: according to the manuscript types, emotional tendency and the keywords of the titles, performing semantic search in a pre-constructed knowledge graph;
a ranking module configured to: inputting information obtained by semantic search into a user interest point recommendation model, and outputting the sequenced information; the sorted information is obtained by searching the semantic meanings and is sorted according to the interest degree of the user from high to low;
a processing module configured to: acquiring a selection result of the user on the recommendation information, and taking the selection result of the user on the recommendation information as a basic material for creating the news manuscript; and processing the material created by the news manuscript to obtain an initial news manuscript.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executable on the processor, the computer instructions when executed by the processor performing the method of any of claims 1-7.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010387447.4A CN111475625A (en) | 2020-05-09 | 2020-05-09 | News manuscript generation method and system based on knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010387447.4A CN111475625A (en) | 2020-05-09 | 2020-05-09 | News manuscript generation method and system based on knowledge graph |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111475625A true CN111475625A (en) | 2020-07-31 |
Family
ID=71762273
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010387447.4A Pending CN111475625A (en) | 2020-05-09 | 2020-05-09 | News manuscript generation method and system based on knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111475625A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112612867A (en) * | 2020-11-24 | 2021-04-06 | 中国传媒大学 | News manuscript propagation analysis method, computer readable storage medium and electronic device |
CN112818261A (en) * | 2021-01-27 | 2021-05-18 | 沈阳美行科技有限公司 | Navigation method and device based on POI (Point of interest) knowledge graph and electronic equipment |
CN113220901A (en) * | 2021-05-11 | 2021-08-06 | 中国科学院自动化研究所 | Writing concept auxiliary system and network system based on enhanced intelligence |
CN113849462A (en) * | 2021-09-16 | 2021-12-28 | 广东创意热店互联网科技有限公司 | Intelligent recommendation method and system for network materials, computer equipment and medium |
CN113961811A (en) * | 2021-10-28 | 2022-01-21 | 平安科技(深圳)有限公司 | Conversational recommendation method, device, equipment and medium based on event map |
CN114595671A (en) * | 2020-12-07 | 2022-06-07 | 腾讯科技(深圳)有限公司 | Recommendation information generation method and device, storage medium and computing device |
CN115858824A (en) * | 2023-02-28 | 2023-03-28 | 北京朗知网络传媒科技股份有限公司 | Intelligent generation method and device for interactive digital media article |
CN118170899A (en) * | 2024-05-09 | 2024-06-11 | 珠海传媒融创科技有限公司 | AIGC-based media news manuscript generation method and related device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109558492A (en) * | 2018-10-16 | 2019-04-02 | 中山大学 | A kind of listed company's knowledge mapping construction method and device suitable for event attribution |
CN110210881A (en) * | 2018-02-28 | 2019-09-06 | 中兴通讯股份有限公司 | A kind of user interest prediction technique, apparatus and system |
CN110277086A (en) * | 2019-06-25 | 2019-09-24 | 中国科学院自动化研究所 | Phoneme synthesizing method, system and electronic equipment based on dispatching of power netwoks knowledge mapping |
CN110851622A (en) * | 2019-11-12 | 2020-02-28 | 北京搜狐互联网信息服务有限公司 | Text generation method and device |
-
2020
- 2020-05-09 CN CN202010387447.4A patent/CN111475625A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110210881A (en) * | 2018-02-28 | 2019-09-06 | 中兴通讯股份有限公司 | A kind of user interest prediction technique, apparatus and system |
CN109558492A (en) * | 2018-10-16 | 2019-04-02 | 中山大学 | A kind of listed company's knowledge mapping construction method and device suitable for event attribution |
CN110277086A (en) * | 2019-06-25 | 2019-09-24 | 中国科学院自动化研究所 | Phoneme synthesizing method, system and electronic equipment based on dispatching of power netwoks knowledge mapping |
CN110851622A (en) * | 2019-11-12 | 2020-02-28 | 北京搜狐互联网信息服务有限公司 | Text generation method and device |
Non-Patent Citations (1)
Title |
---|
王卫东, 武汉大学出版社 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112612867A (en) * | 2020-11-24 | 2021-04-06 | 中国传媒大学 | News manuscript propagation analysis method, computer readable storage medium and electronic device |
CN114595671A (en) * | 2020-12-07 | 2022-06-07 | 腾讯科技(深圳)有限公司 | Recommendation information generation method and device, storage medium and computing device |
CN112818261A (en) * | 2021-01-27 | 2021-05-18 | 沈阳美行科技有限公司 | Navigation method and device based on POI (Point of interest) knowledge graph and electronic equipment |
CN113220901A (en) * | 2021-05-11 | 2021-08-06 | 中国科学院自动化研究所 | Writing concept auxiliary system and network system based on enhanced intelligence |
CN113849462A (en) * | 2021-09-16 | 2021-12-28 | 广东创意热店互联网科技有限公司 | Intelligent recommendation method and system for network materials, computer equipment and medium |
CN113961811A (en) * | 2021-10-28 | 2022-01-21 | 平安科技(深圳)有限公司 | Conversational recommendation method, device, equipment and medium based on event map |
CN113961811B (en) * | 2021-10-28 | 2024-04-05 | 平安科技(深圳)有限公司 | Event map-based conversation recommendation method, device, equipment and medium |
CN115858824A (en) * | 2023-02-28 | 2023-03-28 | 北京朗知网络传媒科技股份有限公司 | Intelligent generation method and device for interactive digital media article |
CN118170899A (en) * | 2024-05-09 | 2024-06-11 | 珠海传媒融创科技有限公司 | AIGC-based media news manuscript generation method and related device |
CN118170899B (en) * | 2024-05-09 | 2024-07-12 | 珠海传媒融创科技有限公司 | AIGC-based media news manuscript generation method and related device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111475625A (en) | News manuscript generation method and system based on knowledge graph | |
Salloum et al. | Mining social media text: extracting knowledge from Facebook | |
CN106776711B (en) | Chinese medical knowledge map construction method based on deep learning | |
JP6309644B2 (en) | Method, system, and storage medium for realizing smart question answer | |
CN107180045B (en) | Method for extracting geographic entity relation contained in internet text | |
KR101713831B1 (en) | Apparatus for recommending document and method for recommending document | |
CN105528437B (en) | A kind of question answering system construction method extracted based on structured text knowledge | |
CN107205016B (en) | Retrieval method of Internet of things equipment | |
CN110990590A (en) | Dynamic financial knowledge map construction method based on reinforcement learning and transfer learning | |
US20090307213A1 (en) | Suffix Tree Similarity Measure for Document Clustering | |
Sarica et al. | Engineering knowledge graph for keyword discovery in patent search | |
CN110188349A (en) | A kind of automation writing method based on extraction-type multiple file summarization method | |
CN103955529A (en) | Internet information searching and aggregating presentation method | |
CN112861990A (en) | Topic clustering method and device based on keywords and entities and computer-readable storage medium | |
CN109522396B (en) | Knowledge processing method and system for national defense science and technology field | |
CN112149422B (en) | Dynamic enterprise news monitoring method based on natural language | |
CN116010564A (en) | Construction method of rice pest question-answering system based on multi-mode knowledge graph | |
Sandhiya et al. | A review of topic modeling and its application | |
CN103226601A (en) | Method and device for image search | |
Ren et al. | Resource recommendation algorithm based on text semantics and sentiment analysis | |
CN109948128B (en) | Auxiliary editing system | |
CN114238735B (en) | Intelligent internet data acquisition method | |
CN115905554A (en) | Chinese academic knowledge graph construction method based on multidisciplinary classification | |
Lehmberg | Web table integration and profiling for knowledge base augmentation | |
CN113779981A (en) | Recommendation method and device based on pointer network and knowledge graph |
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 |