CN109543049B - Method and system for automatically pushing materials according to writing characteristics - Google Patents
Method and system for automatically pushing materials according to writing characteristics Download PDFInfo
- Publication number
- CN109543049B CN109543049B CN201811410440.9A CN201811410440A CN109543049B CN 109543049 B CN109543049 B CN 109543049B CN 201811410440 A CN201811410440 A CN 201811410440A CN 109543049 B CN109543049 B CN 109543049B
- Authority
- CN
- China
- Prior art keywords
- composition
- keywords
- model
- library
- keyword
- 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.)
- Active
Links
Images
Landscapes
- Machine Translation (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides a method and a system for automatically pushing materials aiming at writing characteristics, wherein the method comprises the following steps: acquiring a composition model essay, and establishing a model library according to the composition model essay; classifying said composition paradigm in said paradigm library; analyzing all classified composition model texts and extracting writing characteristic keywords; scanning a network resource library according to the writing characteristic keywords to screen corresponding composition materials; and pushing the composition materials to a user. The invention searches the corresponding composition materials according to the preference and conception of the user, and improves the pertinence and the efficiency of using the materials.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method and a system for automatically pushing materials according to authoring features.
Background
With the rapid development of the internet, people's lives become more and more intelligent, and therefore people are also more and more accustomed to using intelligent terminals to fulfill various requirements. And along with the increasing maturity of the related technology of artificial intelligence, the intelligent degree of various terminals is also higher and higher. Therefore, people are also increasingly used to use intelligent terminals to achieve their purposes.
In the process of learning and writing, students need to continuously accumulate excellent composition materials in order to improve self writing ability, so that corresponding composition materials such as good words and good sentences or graceful paragraphs need to be searched according to self preferences and concepts, but the traditional keyword search has the characteristics of low efficiency and poor style pertinence, so that the students need to spend a great deal of time to screen the appropriate composition materials.
Therefore, there is a need for a method and system for automatically pushing material according to the writing features.
Disclosure of Invention
The invention aims to provide a method and a system for automatically pushing materials according to writing characteristics, so that corresponding composition materials can be searched according to the preference and conception of a user, and the pertinence and the efficiency of using the materials are improved.
The technical scheme provided by the invention is as follows:
the invention provides a method for automatically pushing materials aiming at writing characteristics, which comprises the following steps:
acquiring a composition model essay, and establishing a model library according to the composition model essay;
classifying said composition paradigm in said paradigm library;
extracting writing characteristic keywords according to all classified composition model texts;
scanning a network resource library according to the writing characteristic keywords to screen corresponding composition materials;
and pushing the composition materials to a user.
Further, the obtaining of the composition model document comprises, before the creating of the model library according to the composition model document:
acquiring keywords and keyword categories, and establishing a keyword library according to the keywords;
and classifying the keywords in the keyword library according to the keyword categories.
Further, the extracting of the writing feature keywords according to the composition model texts of all the classifications specifically includes:
analyzing the composition model and essay commonalities belonging to the same category one by one, and extracting similar writing characteristic keywords according to the composition model and essay commonalities;
and weighting all similar writing characteristic keywords to obtain the writing characteristic keywords.
Further, the step of analyzing the composition model essay commonalities belonging to the same category one by one, and the step of extracting similar writing characteristic keywords according to the composition model essay commonalities specifically includes:
acquiring the composition model essays of the same category in the model library;
matching the composition model texts of the same category with the keyword library one by one to obtain matching keywords in each composition model text, wherein the matching keywords are the keywords in the composition model texts of the same category which are consistent with the matching results of the keyword library;
acquiring a matched keyword category corresponding to the matched keyword according to the keyword library;
statistically analyzing the probability of all matched keyword categories in the composition model texts of the same category;
and extracting one or more matched keyword categories as the same writing characteristic keywords according to the probability.
Further, the screening of the corresponding composition materials according to the writing characteristic keyword scanning network resource library specifically comprises:
scanning the network resource pool;
acquiring composition materials corresponding to the writing characteristic keywords from the network resource library;
and marking the composition materials according to the classification category of the corresponding composition model essay.
The invention also provides a system for automatically pushing the materials aiming at the writing characteristics, which comprises the following steps:
the model library establishing module is used for acquiring a composition model essay and establishing a model library according to the composition model essay;
the model sentence classification module is used for classifying the composition model sentences in the model library established by the model library establishing module;
the extracting module is used for extracting writing characteristic keywords according to all classified composition model texts in the model text classifying module;
the screening module is used for scanning a network resource library to screen corresponding composition materials according to the writing characteristic keywords extracted by the extraction module;
and the pushing module is used for pushing the composition materials screened by the screening module to a user.
Further, the method also comprises the following steps:
the word bank establishing module is used for acquiring keywords and keyword categories and establishing a keyword bank according to the keywords;
and the keyword classification module is used for classifying the keywords in the keyword library established by the word library establishing module according to the keyword categories.
Further, the extraction module specifically includes:
the extraction unit analyzes the composition model text commonalities belonging to the same category one by one and extracts similar writing characteristic keywords according to the composition model text commonalities;
and the weighting unit is used for weighting all the similar writing characteristic keywords extracted by the extraction unit to obtain the writing characteristic keywords.
Further, the extraction unit specifically includes:
the model essay acquisition subunit is used for acquiring the same type of the composition model essays in the model library;
the matching subunit matches the composition model texts of the same category acquired by the acquiring subunit with the keyword library one by one to obtain matching keywords in each composition model text, wherein the matching keywords are keywords in the composition model texts of the same category which are consistent with the matching result of the keyword library;
a category obtaining subunit, configured to obtain, according to the keyword library, a matching keyword category corresponding to the matching keyword obtained by the matching subunit;
the analysis subunit is used for carrying out statistical analysis on the probability of the occurrence of all the matched keyword categories in the composition norms of the same category acquired by the category acquisition subunit;
and the extracting subunit extracts one or more matched keyword categories as the similar writing characteristic keywords according to the probability acquired by the analyzing subunit.
Further, the screening module specifically includes:
the scanning unit is used for scanning the network resource library;
the acquisition unit is used for acquiring composition materials corresponding to the writing characteristic keywords from the network resource library acquired by the scanning unit;
and the marking unit is used for marking the composition materials acquired by the acquisition unit according to the classification type of the corresponding composition model texts.
The method and the system for automatically pushing the materials aiming at the writing characteristics can bring at least one of the following beneficial effects:
1. in the invention, by analyzing the commonalities of composition and model texts belonging to the same classification, similar writing characteristic keywords can be more accurately extracted.
2. According to the method and the device, the corresponding writing characteristic keywords are obtained by weighting the similar writing characteristic keywords of all types and are used for screening composition materials.
3. In the invention, the corresponding composition materials are searched according to the preference and conception of the user, and the pertinence and the efficiency of using the materials are improved.
Drawings
The above features, technical features, advantages and implementations of a method and system for automatically pushing material for authoring features are further described in the following detailed description of preferred embodiments in an explicitly understandable manner in connection with the accompanying drawings.
FIG. 1 is a flow chart of a first embodiment of a method for automatically pushing material according to the present invention;
FIG. 2 is a flow chart of a second embodiment of a method for automatically pushing material according to the present invention;
FIG. 3 is a flow chart of a third embodiment of the method for automatically pushing material according to the authoring feature of the present invention;
FIG. 4 is a flow chart of a fourth embodiment of the method for automatically pushing material according to the authoring feature of the present invention;
fig. 4 and 5 are flowcharts illustrating a fifth embodiment of the method for automatically pushing materials according to the authoring feature of the present invention;
fig. 6 is a schematic structural diagram of a sixth embodiment of the system for automatically pushing materials according to the authoring feature of the present invention;
fig. 7 is a schematic structural diagram of a seventh embodiment of the system for automatically pushing materials according to the authoring feature of the present invention;
fig. 8 is a schematic structural diagram of an eighth embodiment of the system for automatically pushing materials according to the authoring feature of the present invention;
fig. 9 is a schematic structural diagram of a ninth embodiment of the system for automatically pushing materials according to the authoring feature of the present invention;
fig. 10 is a schematic structural diagram of a tenth embodiment of the system for automatically pushing materials according to the authoring feature of the present invention.
The reference numbers illustrate:
1000 system for automatically pushing materials
1100 model library establishment module
1200 model sentence classification module
1300 extraction module 1310 extracting unit 1311 model essay obtaining subunit 1312 matching subunit
1313 Category acquisition subunit 1314 analysis subunit 1315 extraction subunit
1320 weighting unit
1400 screening module 1410 scans cells 1420 obtains cells 1430 and marks cells
1500 push module
1600 word bank building module
1700 keyword classification module
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
For the sake of simplicity, only the parts relevant to the present invention are schematically shown in the drawings, and they do not represent the actual structure as a product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically illustrated or only labeled. In this document, "one" means not only "only one" but also a case of "more than one".
A first embodiment of the present invention, as shown in fig. 1, is a method for automatically pushing material according to writing features, including:
s100, a composition model essay is obtained, and a model library is established according to the composition model essay.
S200 categorizing the essay norms in the normed library.
Specifically, a large number of composition norms are obtained, and a normal library is established according to the obtained composition norms. The method comprises the steps of obtaining relevant information of each composition model essay, wherein the relevant information comprises information of sex, grade, character, hobbies and the like of authors of the composition model essays, and then classifying the composition model essays according to the relevant information, wherein the same composition model essay can be classified under a plurality of different categories.
S300, analyzing all classified composition model texts to extract writing characteristic keywords.
S400, scanning the network resource library according to the writing characteristic keywords to screen corresponding composition materials.
And S500, pushing the composition materials to a user.
Specifically, the characteristics of all composition model texts are analyzed, writing characteristic keywords are summarized and extracted, a network resource library is scanned, composition materials corresponding to the writing characteristic keywords are screened, and then the composition materials are pushed to a user.
In the embodiment, by analyzing the commonalities of composition model texts belonging to the same category, similar writing characteristic keywords are extracted more accurately, and then all types of similar writing characteristic keywords are weighted to obtain corresponding writing characteristic keywords for screening composition materials.
A second embodiment of the present invention is an optimized embodiment of the first embodiment, and as shown in fig. 2, the second embodiment includes:
s100, a composition model essay is obtained, and a model library is established according to the composition model essay.
S200 categorizing the essay norms in the normed library.
S300, analyzing all classified composition model texts to extract writing characteristic keywords.
S400, scanning the network resource library according to the writing characteristic keywords to screen corresponding composition materials.
The step S400 of screening corresponding composition materials according to the writing characteristic keyword scanning network repository specifically includes:
s410, scanning the network resource library.
Specifically, a network resource library is scanned, and the network resource library contains a large amount of composition materials, but all the composition materials are not arranged or only roughly arranged, so that a user can hardly search the composition materials needed by the user quickly and accurately.
S420, acquiring composition materials corresponding to the writing characteristic keywords from the network resource library.
Specifically, the composition materials in the network resource library are matched with the writing characteristic keywords when the network resource library is scanned, so that the composition materials corresponding to the extracted writing characteristic keywords in the network resource library are obtained.
S430, marking the composition materials according to the classification categories of the corresponding composition models.
Specifically, the writing keywords are extracted according to the composition model essay, and the composition model essay is classified according to related information (information such as sex, age, character and the like of author of the composition model essay) in the model essay, so that composition materials corresponding to the obtained writing characteristic keywords are marked according to classification types of the corresponding composition model essay.
And S500, pushing the composition materials to a user.
In the embodiment, the writing characteristic keywords are extracted, and then the network resource library is scanned according to the writing characteristic keywords, so that composition materials meeting conditions are quickly and accurately screened from a large number of composition materials in the network resource library.
A third embodiment of the present invention is a preferable embodiment of the first embodiment, and as shown in fig. 3, the third embodiment includes:
s010 obtains the keywords and the keyword categories, and establishes a keyword library according to the keywords.
Specifically, keywords and corresponding keyword categories are obtained, the keyword categories are named after the name, use superimposed words, good sentences or graceful paragraphs, and then a keyword library is established according to the obtained keywords for subsequent identification of the keywords contained in composition models.
S020 according to the keyword category, classifying the keywords in the keyword library.
Specifically, since the keyword categories are intersected with each other, the keywords may be classified in the keyword library according to the keyword categories, and the same keyword may belong to a plurality of different keyword categories.
S100, a composition model essay is obtained, and a model library is established according to the composition model essay.
S200 categorizing the essay norms in the normed library.
S300, analyzing all classified composition model texts to extract writing characteristic keywords.
S400, scanning the network resource library according to the writing characteristic keywords to screen corresponding composition materials.
The step S400 of screening corresponding composition materials according to the writing characteristic keyword scanning network repository specifically includes:
s410, scanning the network resource library.
S420, acquiring composition materials corresponding to the writing characteristic keywords from the network resource library.
S430, marking the composition materials according to the classification categories of the corresponding composition models.
And S500, pushing the composition materials to a user.
In the embodiment, the keyword library is established by acquiring the keywords, so that the keywords contained in the composition text can be conveniently and rapidly determined in the follow-up process, and in addition, the acquired keywords are classified in the keyword library according to the keyword categories, so that the categories of the keywords contained in the composition text can be conveniently determined.
A fourth embodiment of the present invention is a preferable embodiment of the first embodiment, and as shown in fig. 4, the fourth embodiment includes:
s100, a composition model essay is obtained, and a model library is established according to the composition model essay.
S200 categorizing the essay norms in the normed library.
S300, analyzing all classified composition model texts to extract writing characteristic keywords.
The step S300 of analyzing the composition and model essay of all the categories and extracting the writing feature keywords specifically includes:
s310, the composition model essay commonalities belonging to the same category are analyzed one by one, and similar writing characteristic keywords are extracted according to the composition model essay commonalities.
Specifically, the commonalities of the composition model texts belonging to the same category in the model library are counted and analyzed one by one, and then keywords are extracted according to the commonalities of the composition model texts obtained through statistics to serve as the similar writing characteristic keywords of the corresponding category.
S320, weighting all similar writing characteristic keywords to obtain the writing characteristic keywords.
Specifically, all the obtained similar writing characteristic keywords of different types are weighted to obtain the writing characteristic keywords, wherein the weighting mode can be set by a system in a unified manner or by a user according to respective requirements.
S400, scanning the network resource library according to the writing characteristic keywords to screen corresponding composition materials.
The step S400 of screening corresponding composition materials according to the writing characteristic keyword scanning network repository specifically includes:
s410, scanning the network resource library.
S420, acquiring composition materials corresponding to the writing characteristic keywords from the network resource library.
S430, marking the composition materials according to the classification categories of the corresponding composition models.
And S500, pushing the composition materials to a user.
In the embodiment, the writing characteristic keywords are obtained by weighting all the similar writing characteristic keywords of different types, and different writing characteristic keywords are obtained correspondingly in different weighting modes, so that the writing characteristic keywords are adjusted by a user according to the requirement of the user on the composition materials by changing the weighting mode, and the composition materials of different types are obtained.
A fifth embodiment of the present invention is a preferable embodiment of the first embodiment, and as shown in fig. 4 and 5, includes:
s100, a composition model essay is obtained, and a model library is established according to the composition model essay.
S200 categorizing the essay norms in the normed library.
S300, analyzing all classified composition model texts to extract writing characteristic keywords.
The step S300 of analyzing the composition and model essay of all the categories and extracting the writing feature keywords specifically includes:
s310, the composition model essay commonalities belonging to the same category are analyzed one by one, and similar writing characteristic keywords are extracted according to the composition model essay commonalities.
The step S310 of analyzing the composition and model essay commonalities belonging to the same category one by one, and the extracting of similar writing feature keywords according to the composition and model essay commonalities specifically includes:
s311, the composition norms of the same category in the normal library are obtained.
Specifically, the obtained composition norms are classified according to the related information of the composition norms in the normal library, and the composition norms belonging to the same category in the normal library, such as the composition norms containing famous names or the composition norms using words of superposition, are obtained.
S312, matching the composition model texts in the same category with the keyword library one by one to obtain matching keywords in each composition model text, wherein the matching keywords are the keywords in the composition model texts in the same category which are consistent with the matching results of the keyword library.
Specifically, the composition model texts of the same category are matched with the keywords in the keyword library one by one to obtain the matched keywords in each composition model text, and the same composition model text may include a plurality of matched keywords due to the factors of the composition model text.
S313, the matched keyword category corresponding to the matched keyword is obtained according to the keyword library.
Specifically, since all the keywords in the keyword library are classified according to the keyword categories, the matching keyword categories corresponding to the obtained matching keywords can be obtained according to the keyword library. The same composition model as described above may contain a plurality of matching keywords, and there may be a plurality of matching keywords different from each other, but the corresponding matching keywords have the same category.
S314, the probability of all the matched keyword categories in the composition norms of the same category is analyzed statistically.
Specifically, the probability of all matched keyword categories in composition norms of the same category is statistically analyzed. Even though the composition model texts belong to the same category, the contained keywords are not completely the same, so the probability of each matched keyword category is statistically analyzed, and then the matched keyword categories are sorted according to the probability, or the matched keyword categories are sorted according to the user-defined rule.
S315, one or more matched keyword categories are extracted according to the probability to serve as the similar writing characteristic keywords.
Specifically, one or more matched keyword categories are extracted according to the arrangement sequence of the probabilities or the user-defined rule to serve as similar writing characteristic keywords, and the similar writing characteristic keywords are keywords with commonalities in composition model texts belonging to the same category.
S320, weighting all similar writing characteristic keywords to obtain the writing characteristic keywords.
S400, scanning the network resource library according to the writing characteristic keywords to screen corresponding composition materials.
The step S400 of screening corresponding composition materials according to the writing characteristic keyword scanning network repository specifically includes:
s410, scanning the network resource library.
S420, acquiring composition materials corresponding to the writing characteristic keywords from the network resource library.
S430, marking the composition materials according to the classification categories of the corresponding composition models.
And S500, pushing the composition materials to a user.
In this embodiment, the composition model texts belonging to the same category are compared with the keywords in the keyword library one by one to determine similar writing characteristic keywords, and then the writing characteristic keywords are determined according to the similar writing characteristic keywords of the composition model texts of all categories, so as to screen composition materials required by the user.
A sixth embodiment of the present invention, as shown in fig. 6, is a system 1000 for automatically pushing material according to writing features, including:
the model library establishing module 1100 obtains the composition model essay and establishes the model library according to the composition model essay.
A model sentence classification module 1200 for classifying the composition model in the model library created by the model library creation module 1100.
Specifically, the model library creating module 1100 obtains a large amount of composition model essays, and creates a model library according to the obtained composition model essays. Obtaining relevant information of each composition model essay, wherein the relevant information comprises information of sex, grade, character, hobby and the like of authors of the composition model essay, and then classifying the composition model essay by the model essay classifying module 1200 according to the relevant information respectively, wherein the same composition model essay may be classified under a plurality of different categories.
The extracting module 1300 extracts writing feature keywords according to all classified composition and model texts in the model text classifying module 1200.
The screening module 1400 scans the network resource library to screen corresponding composition materials according to the writing characteristic keywords extracted by the extracting module 1300.
The pushing module 1400 pushes the composition materials screened by the screening module 1400 to a user.
Specifically, the characteristics of all composition paradigms are analyzed, the extraction module 1300 summarizes and extracts the writing characteristic keywords, the screening module 1400 scans the network resource library, screens composition materials corresponding to the writing characteristic keywords, and then pushes the composition materials to the user.
In the embodiment, by analyzing the commonalities of composition model texts belonging to the same category, similar writing characteristic keywords are extracted more accurately, and then all types of similar writing characteristic keywords are weighted to obtain corresponding writing characteristic keywords for screening composition materials.
A seventh embodiment of the present invention is a preferable embodiment of the first embodiment, and as shown in fig. 7, the seventh embodiment includes:
the model library establishing module 1100 obtains the composition model essay and establishes the model library according to the composition model essay.
A model sentence classification module 1200 for classifying the composition model in the model library created by the model library creation module 1100.
The extracting module 1300 extracts writing feature keywords according to all classified composition and model texts in the model text classifying module 1200.
The screening module 1400 scans the network resource library to screen corresponding composition materials according to the writing characteristic keywords extracted by the extracting module 1300.
The screening module 1400 specifically includes:
a scanning unit 1410, scanning the network resource pool.
Specifically, the scanning unit 1410 scans a network resource library, which contains a large amount of composition materials, but all the composition materials are not sorted or only roughly sorted, so that it is difficult for a user to quickly and accurately search the composition materials needed by the user.
The obtaining unit 1420 obtains composition materials corresponding to the writing feature keywords from the network resource library obtained by the scanning unit 1410.
Specifically, when the network repository is scanned, composition materials in the network repository are matched with the writing characteristic keywords, so that the obtaining unit 1420 obtains the composition materials corresponding to the extracted writing characteristic keywords in the network repository.
The marking unit 1430 marks the composition material acquired by the acquiring unit 1420 according to the classification category of the corresponding composition model.
Specifically, since the composition keywords are extracted according to the composition model essay, and the composition model essay is classified according to the related information (information such as the sex, age, character, and the like of the author of the composition model essay) in the model essay, the marking unit 1430 marks the composition materials corresponding to the obtained composition feature keywords according to the classification categories of the composition model essay.
The pushing module 1400 pushes the composition materials screened by the screening module 1400 to a user.
In the embodiment, the writing characteristic keywords are extracted, and then the network resource library is scanned according to the writing characteristic keywords, so that composition materials meeting conditions are quickly and accurately screened from a large number of composition materials in the network resource library.
An eighth embodiment of the present invention is a preferable embodiment of the first embodiment, and as shown in fig. 8, the eighth embodiment includes:
the word bank establishing module 1600 obtains the keywords and the keyword categories, and establishes the keyword bank according to the keywords.
Specifically, the word stock establishing module 1600 obtains keywords and corresponding keyword categories, which are celebrity, use stop words, good sentences or graceful paragraphs, and then establishes a keyword stock according to the obtained keywords for subsequent recognition of the keywords contained in the composition model.
The keyword classification module 1700 classifies the keywords in the keyword library established by the word library establishing module 1600 according to the keyword category.
Specifically, since the keyword categories are intersected with each other, the keyword classification module 1700 classifies the keywords in the keyword library according to the keyword categories, and the same keyword may belong to a plurality of different keyword categories.
The model library establishing module 1100 obtains the composition model essay and establishes the model library according to the composition model essay.
A model sentence classification module 1200 for classifying the composition model in the model library created by the model library creation module 1100.
The extracting module 1300 extracts writing feature keywords according to all classified composition and model texts in the model text classifying module 1200.
The screening module 1400 scans the network resource library to screen corresponding composition materials according to the writing characteristic keywords extracted by the extracting module 1300.
The screening module 1400 specifically includes:
a scanning unit 1410, scanning the network resource pool.
The obtaining unit 1420 obtains composition materials corresponding to the writing feature keywords from the network resource library obtained by the scanning unit 1410.
The marking unit 1430 marks the composition material acquired by the acquiring unit 1420 according to the classification category of the corresponding composition model.
The pushing module 1400 pushes the composition materials screened by the screening module 1400 to a user.
In the embodiment, the keyword library is established by acquiring the keywords, so that the keywords contained in the composition text can be conveniently and rapidly determined in the follow-up process, and in addition, the acquired keywords are classified in the keyword library according to the keyword categories, so that the categories of the keywords contained in the composition text can be conveniently determined.
A ninth embodiment of the present invention is a preferable embodiment of the first embodiment, and as shown in fig. 9, the ninth embodiment includes:
the model library establishing module 1100 obtains the composition model essay and establishes the model library according to the composition model essay.
A model sentence classification module 1200 for classifying the composition model in the model library created by the model library creation module 1100.
The extracting module 1300 extracts writing feature keywords according to all classified composition and model texts in the model text classifying module 1200.
The extraction module 1300 specifically includes:
the extracting unit 1310 analyzes the composition and model text commonalities belonging to the same category one by one, and extracts similar writing characteristic keywords according to the composition and model text commonalities.
Specifically, the commonalities of the composition norms belonging to the same category in the exemplar library are counted and analyzed one by one, and then the extracting unit 1310 extracts the keywords according to the commonalities of the composition norms obtained by the counting as the similar writing characteristic keywords of the corresponding category.
The weighting unit 1320 weights all the similar writing feature keywords extracted by the extracting unit 1310 to obtain the writing feature keywords.
Specifically, the weighting unit 1320 weights all the obtained similar writing feature keywords of different types to obtain the writing feature keywords, where the weighting modes can be set by a system or by users according to their respective requirements.
The screening module 1400 scans the network resource library to screen corresponding composition materials according to the writing characteristic keywords extracted by the extracting module 1300.
The screening module 1400 specifically includes:
a scanning unit 1410, scanning the network resource pool.
The obtaining unit 1420 obtains composition materials corresponding to the writing feature keywords from the network resource library obtained by the scanning unit 1410.
The marking unit 1430 marks the composition material acquired by the acquiring unit 1420 according to the classification category of the corresponding composition model.
The pushing module 1400 pushes the composition materials screened by the screening module 1400 to a user.
In the embodiment, the writing characteristic keywords are obtained by weighting all the similar writing characteristic keywords of different types, and different writing characteristic keywords are obtained correspondingly in different weighting modes, so that the writing characteristic keywords are adjusted by a user according to the requirement of the user on the composition materials by changing the weighting mode, and the composition materials of different types are obtained.
A tenth embodiment of the present invention is a preferable embodiment of the first embodiment, and as shown in fig. 10, the tenth embodiment includes:
the model library establishing module 1100 obtains the composition model essay and establishes the model library according to the composition model essay.
A model sentence classification module 1200 for classifying the composition model in the model library created by the model library creation module 1100.
The extracting module 1300 extracts writing feature keywords according to all classified composition and model texts in the model text classifying module 1200.
The extraction module 1300 specifically includes:
the extracting unit 1310 analyzes the composition and model text commonalities belonging to the same category one by one, and extracts similar writing characteristic keywords according to the composition and model text commonalities.
The extracting unit 1310 specifically includes:
the model essay obtaining subunit 1311 obtains the same category of the model essays in the model library.
Specifically, the template library classifies the acquired template texts according to the related information of the template texts, and the template acquisition subunit 1311 acquires template texts belonging to the same category in the template library, such as template texts all including famous people or template texts all using stop words.
The matching subunit 1312 matches the composition model texts of the same category acquired by the acquiring subunit with the keyword library one by one to obtain matching keywords in each composition model text, where the matching keywords are keywords in the composition model texts of the same category that match the matching result of the keyword library.
Specifically, the matching sub-unit 1312 matches the keywords of the composition model essay and the keyword library, which are obtained from the same category, one by one to obtain the matching keywords of each composition model essay, where the same composition model essay may include a plurality of matching keywords due to the size factor of the composition model essay.
A category obtaining subunit 1313, obtains, from the keyword library, a matching keyword category corresponding to the matching keyword obtained by the matching subunit 1312.
Specifically, since all the keywords in the keyword library are classified according to the keyword class, the class acquisition subunit 1313 can acquire the matching keyword class corresponding to the obtained matching keyword from the keyword library. The same composition model as described above may contain a plurality of matching keywords, and there may be a plurality of matching keywords different from each other, but the corresponding matching keywords have the same category.
An analyzing subunit 1314, statistically analyzing the probability of occurrence of all the matching keyword categories in the composition norms of the same category acquired by the category acquiring subunit 1313.
Specifically, the analysis subunit 1314 statistically analyzes the probabilities of occurrence of all the matching keyword categories in the composition norms of the same category. Even though the composition model texts belong to the same category, the contained keywords are not completely the same, so the analysis subunit 1314 statistically analyzes the probability of occurrence of each matching keyword category, and then sorts the matching keyword categories according to the probability, or sorts the matching keyword categories according to the user-defined rules.
An extracting sub-unit 1315, extracts one or more of the matching keyword categories as the same-kind writing feature keywords according to the probability acquired by the analyzing sub-unit 1314.
Specifically, the extracting sub-unit 1315 extracts one or more matching keyword categories as writing-alike feature keywords, which are keywords having commonality in composition paradigms belonging to the same category, according to the ranking order of the probabilities or a user-defined rule.
The weighting unit 1320 weights all the similar writing feature keywords extracted by the extracting unit 1310 to obtain the writing feature keywords.
The screening module 1400 scans the network resource library to screen corresponding composition materials according to the writing characteristic keywords extracted by the extracting module 1300.
The screening module 1400 specifically includes:
a scanning unit 1410, scanning the network resource pool.
The obtaining unit 1420 obtains composition materials corresponding to the writing feature keywords from the network resource library obtained by the scanning unit 1410.
The marking unit 1430 marks the composition material acquired by the acquiring unit 1420 according to the classification category of the corresponding composition model.
The pushing module 1400 pushes the composition materials screened by the screening module 1400 to a user.
In this embodiment, the composition model texts belonging to the same category are compared with the keywords in the keyword library one by one to determine similar writing characteristic keywords, and then the writing characteristic keywords are determined according to the similar writing characteristic keywords of the composition model texts of all categories, so as to screen composition materials required by the user.
It should be noted that the above embodiments can be freely combined as necessary. The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (6)
1. A method for automatically pushing materials aiming at writing characteristics is characterized by comprising the following steps:
acquiring keywords and keyword categories, and establishing a keyword library according to the keywords;
classifying the keywords in the keyword library according to the keyword categories;
acquiring a composition model essay, and establishing a model library according to the composition model essay;
classifying said composition paradigm in said paradigm library;
extracting writing characteristic keywords according to all classified composition model texts;
scanning a network resource library according to the writing characteristic keywords to screen corresponding composition materials;
pushing the composition materials to a user;
the extracting of the writing characteristic keywords according to the composition model texts of all the classifications specifically comprises the following steps:
analyzing the composition model and essay commonalities belonging to the same category one by one, and extracting similar writing characteristic keywords according to the composition model and essay commonalities;
and weighting all similar writing characteristic keywords to obtain the writing characteristic keywords.
2. The method according to claim 1, wherein the step of analyzing the composition model essay commonalities belonging to the same category one by one, and the step of extracting similar composition feature keywords according to the composition model essay commonalities specifically comprises:
acquiring the composition model essays of the same category in the model library;
matching the composition model texts of the same category with the keyword library one by one to obtain matching keywords in each composition model text, wherein the matching keywords are the keywords in the composition model texts of the same category which are consistent with the matching results of the keyword library;
acquiring a matched keyword category corresponding to the matched keyword according to the keyword library;
statistically analyzing the probability of all matched keyword categories in the composition model texts of the same category;
and extracting one or more matched keyword categories as the same writing characteristic keywords according to the probability.
3. The method for automatically pushing materials according to the authoring features of any one of claims 1-2, wherein the step of screening corresponding composition materials according to the authoring feature keyword scanning web resource library specifically comprises:
scanning the network resource pool;
acquiring composition materials corresponding to the writing characteristic keywords from the network resource library;
and marking the composition materials according to the classification category of the corresponding composition model essay.
4. A system for automatically pushing material for authoring features, comprising:
the word bank establishing module is used for acquiring keywords and keyword categories and establishing a keyword bank according to the keywords;
the keyword classification module is used for classifying the keywords in the keyword library established by the word library establishing module according to the keyword categories;
the model library establishing module is used for acquiring a composition model essay and establishing a model library according to the composition model essay;
the model sentence classification module is used for classifying the composition model sentences in the model library established by the model library establishing module;
the extracting module is used for extracting writing characteristic keywords according to all classified composition model texts in the model text classifying module;
the screening module is used for scanning a network resource library to screen corresponding composition materials according to the writing characteristic keywords extracted by the extraction module;
the pushing module is used for pushing the composition materials screened by the screening module to a user;
wherein, the extraction module specifically comprises:
the extraction unit analyzes the composition model text commonalities belonging to the same category one by one and extracts similar writing characteristic keywords according to the composition model text commonalities;
and the weighting unit is used for weighting all the similar writing characteristic keywords extracted by the extraction unit to obtain the writing characteristic keywords.
5. The system for automatically pushing stories for authoring features as claimed in claim 4, wherein said extracting unit comprises:
the model essay acquisition subunit is used for acquiring the same type of the composition model essays in the model library;
the matching subunit matches the composition model texts of the same category acquired by the acquiring subunit with the keyword library one by one to obtain matching keywords in each composition model text, wherein the matching keywords are keywords in the composition model texts of the same category which are consistent with the matching result of the keyword library;
a category obtaining subunit, configured to obtain, according to the keyword library, a matching keyword category corresponding to the matching keyword obtained by the matching subunit;
the analysis subunit is used for carrying out statistical analysis on the probability of the occurrence of all the matched keyword categories in the composition norms of the same category acquired by the category acquisition subunit;
and the extracting subunit extracts one or more matched keyword categories as the similar writing characteristic keywords according to the probability acquired by the analyzing subunit.
6. The system for automatically pushing materials according to the authoring features of any one of claims 4-5, wherein the filtering module specifically comprises:
the scanning unit is used for scanning the network resource library;
the acquisition unit is used for acquiring composition materials corresponding to the writing characteristic keywords from the network resource library acquired by the scanning unit;
and the marking unit is used for marking the composition materials acquired by the acquisition unit according to the classification type of the corresponding composition model texts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811410440.9A CN109543049B (en) | 2018-11-23 | 2018-11-23 | Method and system for automatically pushing materials according to writing characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811410440.9A CN109543049B (en) | 2018-11-23 | 2018-11-23 | Method and system for automatically pushing materials according to writing characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109543049A CN109543049A (en) | 2019-03-29 |
| CN109543049B true CN109543049B (en) | 2021-09-07 |
Family
ID=65850157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811410440.9A Active CN109543049B (en) | 2018-11-23 | 2018-11-23 | Method and system for automatically pushing materials according to writing characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109543049B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113724543B (en) * | 2021-08-27 | 2024-02-06 | 读书郎教育科技有限公司 | System and method for training of looking at picture and writing |
| CN116628125B (en) * | 2023-04-14 | 2024-01-30 | 湘南学院 | Method and auxiliary device for extracting keywords of clinical image diagnosis report |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699602A (en) * | 2013-12-13 | 2014-04-02 | 北京奇虎科技有限公司 | Model essay webpage database establishing method and device |
| CN104572899A (en) * | 2014-12-25 | 2015-04-29 | 北京锐安科技有限公司 | Article processing method and article processing device |
| CN108763516A (en) * | 2018-05-31 | 2018-11-06 | 悦未来科技（深圳）有限公司 | Write exchange method, device and computer readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6275758B2 (en) * | 2016-03-01 | 2018-02-07 | Ｎｅｃパーソナルコンピュータ株式会社 | Information processing system, information processing method, and program |
-
2018
- 2018-11-23 CN CN201811410440.9A patent/CN109543049B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699602A (en) * | 2013-12-13 | 2014-04-02 | 北京奇虎科技有限公司 | Model essay webpage database establishing method and device |
| CN104572899A (en) * | 2014-12-25 | 2015-04-29 | 北京锐安科技有限公司 | Article processing method and article processing device |
| CN108763516A (en) * | 2018-05-31 | 2018-11-06 | 悦未来科技（深圳）有限公司 | Write exchange method, device and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109543049A (en) | 2019-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN108959270B (en) | Entity linking method based on deep learning | |
| CN105824959B (en) | Public opinion monitoring method and system | |
| CN106886580B (en) | Image emotion polarity analysis method based on deep learning | |
| CN104063427A (en) | Expression input method and device based on semantic understanding | |
| CN108038099B (en) | Low-frequency keyword identification method based on word clustering | |
| CN110968684A (en) | Information processing method, device, equipment and storage medium | |
| CN109446376B (en) | Method and system for classifying voice through word segmentation | |
| KR20120109943A (en) | Emotion classification method for analysis of emotion immanent in sentence | |
| CN102279890A (en) | Sentiment word extracting and collecting method based on micro blog | |
| CN107679070B (en) | Intelligent reading recommendation method and device and electronic equipment | |
| CN110472257A (en) | A kind of MT engine assessment preferred method and system based on sentence pair | |
| CN112395410A (en) | Entity extraction-based industry public opinion recommendation method and device and electronic equipment | |
| CN109492105A (en) | A kind of text sentiment classification method based on multiple features integrated study | |
| CN110910175A (en) | Tourist ticket product portrait generation method | |
| CN109543049B (en) | Method and system for automatically pushing materials according to writing characteristics | |
| CN111460100A (en) | Criminal legal document and criminal name recommendation method and system | |
| Hamid et al. | Bengali slang detection using state-of-the-art supervised models from a given text | |
| CN116882414B (en) | Automatic comment generation method and related device based on large-scale language model | |
| CN111736804B (en) | Method and device for identifying App key function based on user comment | |
| CN107908749A (en) | A kind of personage's searching system and method based on search engine | |
| CN111859955A (en) | Public opinion data analysis model based on deep learning | |
| Wibawa et al. | Sentiment analysis on user satisfaction level of cellular data service using the k-Nearest Neighbor (k-NN) algorithm | |
| CN110750712A (en) | Software security requirement recommendation method based on data driving | |
| CN115510269A (en) | Video recommendation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |