CN104731960A - Method, device and system for generating video abstraction based on electronic commerce webpage content - Google Patents
Method, device and system for generating video abstraction based on electronic commerce webpage content Download PDFInfo
- Publication number
- CN104731960A CN104731960A CN201510156125.8A CN201510156125A CN104731960A CN 104731960 A CN104731960 A CN 104731960A CN 201510156125 A CN201510156125 A CN 201510156125A CN 104731960 A CN104731960 A CN 104731960A
- Authority
- CN
- China
- Prior art keywords
- keyword
- text
- webpage
- ontology
- text snippet
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Abstract
The invention relates to the field of video generation, in particular to a method, device and system for generating a video abstraction based on electronic commerce webpage content. The method, device and system can generate the video abstraction based on the target electronic commerce webpage text content, and the video abstraction is displayed on a target electronic commerce webpage. When a user browses the corresponding electronic commerce webpage, the product introduction information can be obtained by watching the video abstraction. Compared with the mode that an existing electronic commerce website introduces products through pictures and words, the time cost spent by a user for reading the product introductions on the electronic commerce webpage can be saved.
Description
Technical field
The present invention relates to video and generate field, in particular to method, the Apparatus and system of making a summary based on ecommerce webpage content generating video.
Background technology
The website that e-commerce website is exactly enterprise, mechanism or individual set up on the internet, be enterprise, mechanism or individual carry out infrastructure and the information platform of ecommerce, being the interactive window implementing ecommerce, is a kind of means being engaged in ecommerce.
Existing e-commerce website, commodity displaying generally describes commodity based on word and picture.Current user is by increasing approach, and such as mobile phone, panel computer, TV etc., obtain the content of buyer's guide.What the application of existing ecommerce class obtained buyer's guide from e-commerce website is also main mainly with word picture.
On existing e-commerce website, the shortcoming of buyer's guide is that the time cost that user reads word improves relatively in content quick Consumption Age, is unfavorable for that e-commerce website word introduces commodity to user.
Summary of the invention
The object of the present invention is to provide a kind of method, Apparatus and system based on ecommerce webpage content generating video summary, the mode of making a summary with generating video introduces the commodity on webpage to user, to save the time cost of buyer's guide on user's read electronic commercial affairs webpage.
First aspect, embodiments provides a kind of method based on ecommerce webpage content generating video summary, comprising: the text snippet extracting target electronic commercial affairs webpage text content; Resolve described text snippet, obtain the keyword in described text snippet; Semantic analysis is carried out to described keyword, obtains described keyword Ontology; Based on described keyword Ontology, from internet, retrieve corresponding picture or video, formation background figure, formation background figure; Based on described keyword Ontology, from the grammar database preestablished, obtain the animation template corresponding with described keyword; Described text snippet is converted into voice data; Play up rule according to presetting, the synthesis of described Background, described animation template and described voice data is played up as video file.
In conjunction with first aspect, embodiments provide the first possible embodiment of first aspect, wherein, the text snippet of described extraction target electronic commercial affairs webpage text content comprises: based on web page interlinkage, obtain ecommerce webpage; Remove the additional information in described ecommerce webpage, wherein said additional information comprise following one or more: advertisement, picture, video, framework and chart; Extract the content of text of the described ecommerce webpage after additional information belonging to removing; From described content of text, win emphasis statement form described text snippet.
In conjunction with first aspect, embodiments provide the embodiment that the second of first aspect is possible, wherein, described emphasis statement of winning from described content of text forms described text snippet, comprising: calculate the similarity between every two statements in described content of text successively; According to the result of calculation of described similarity, to the statement classification in described content of text; According to the result of described classification, from every quasi-sentence, extract statement respectively combine, obtain candidate's summary; From described candidate's summary, choose the candidate minimum with pre-set text length of summarization difference makes a summary as the summary texts of described ecommerce webpage, and wherein said pre-set text length of summarization is determined according to video length to be generated and the bright read rate of text snippet preset.
In conjunction with first aspect, embodiments provide the 4th kind of possible embodiment of first aspect, wherein, the described text snippet of described parsing, obtains the keyword in described text snippet, comprising: carry out participle to described text snippet; Word template in the word obtained after described participle and described grammar database is compared, the part of speech of the word obtained after determining participle; According to the judged result of described part of speech, from the word after participle, choose noun and the number keyword as described text snippet.
In conjunction with first aspect, embodiments provide the 5th kind of possible embodiment of first aspect, wherein, described semantic analysis is carried out to described keyword, obtain described keyword Ontology, comprise: in described grammar database, retrieve described keyword, obtain all ontology describings relevant to described keyword; Utilize network ontology language OWL from all ontology describings of described keyword, determine keyword Ontology under current context.
In conjunction with first aspect, embodiments provide the 6th kind of possible embodiment of first aspect, wherein, described according to preset play up rule, the synthesis of described Background, described animation template and described voice data is played up as video file, comprising: the mapping relations setting keyword described in described voice data, the Background corresponding with described keyword and animation template; According to described mapping relations, synthesis is carried out to described Background, described animation template and described voice data and plays up.
Second aspect, the embodiment of the present invention additionally provides a kind of device based on ecommerce webpage content generating video summary, comprising: extraction module, for extracting the text snippet of target electronic commercial affairs webpage text content; Keyword acquisition module, for resolving described text snippet, obtains the keyword in described text snippet; Semantic module, for carrying out semantic analysis to described keyword, obtains described keyword Ontology; Background forms module, for based on described keyword Ontology, retrieves corresponding picture or video, formation background figure from internet; Animation template acquisition module, for based on described keyword Ontology, obtains the animation template corresponding with described keyword from the grammar database preset; Audio conversion module, for being converted into voice data by described text snippet; Video Composition module, for playing up rule according to presetting, plays up the synthesis of described Background, described animation template and described voice data as video file.
In conjunction with second aspect, embodiments provide the first possible embodiment of second aspect, wherein, described keyword acquisition module, comprising: participle unit, for carrying out participle to described text snippet; Part of speech determining unit, for the word template in the word obtained after described participle and described grammar database is compared, the part of speech of the word obtained after determining participle; Unit chosen in keyword, for the judged result according to described part of speech, chooses noun and the number keyword as described text snippet from the word after participle.
The third aspect, the embodiment of the present invention additionally provides a kind of system based on ecommerce webpage content generating video summary, comprising: user side and the e-commerce server end be connected by internet with user side; Described e-commerce server end comprises the device based on ecommerce webpage content generating video summary as described in second aspect and the first possible embodiment of second aspect.
Method, Apparatus and system based on ecommerce webpage content generating video summary that the embodiment of the present invention provides, can make a summary by based target ecommerce webpage content of text generating video, and displayed on target electronic commercial affairs webpage by video frequency abstract.User is when browsing respective electronic commercial affairs webpage, buyer's guide information can be obtained by the mode of watching video frequency abstract, compare the mode of existing e-commerce website by picture and character introduction commodity, the time cost of buyer's guide on user's read electronic commercial affairs webpage can be saved.
For making above-mentioned purpose of the present invention, feature and advantage become apparent, preferred embodiment cited below particularly, and coordinate appended accompanying drawing, be described in detail below.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment below, be to be understood that, the following drawings illustrate only some embodiment of the present invention, therefore the restriction to scope should be counted as, for those of ordinary skill in the art, under the prerequisite not paying creative work, other relevant accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 shows the method flow schematic diagram based on ecommerce webpage content generating video summary that the embodiment of the present invention 1 provides;
Fig. 2 shows the method flow schematic diagram based on ecommerce webpage content generating video summary that the embodiment of the present invention 2 provides;
Fig. 3 shows the method flow schematic diagram based on ecommerce webpage content generating video summary that the embodiment of the present invention 3 provides;
Fig. 4 shows the method flow schematic diagram based on ecommerce webpage content generating video summary that the embodiment of the present invention 4 provides;
Fig. 5 shows the method flow schematic diagram based on ecommerce webpage content generating video summary that the embodiment of the present invention 5 provides;
Fig. 6 shows the structure intention of the device based on ecommerce webpage content generating video summary that the embodiment of the present invention 6 provides;
Fig. 7 shows the structural representation based on keyword acquisition module in the device of ecommerce webpage content generating video summary that the embodiment of the present invention 7 provides;
Fig. 8 shows the system connection diagram based on ecommerce webpage content generating video summary that the embodiment of the present invention 8 provides.
Embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.The assembly of the embodiment of the present invention describing and illustrate in usual accompanying drawing herein can be arranged with various different configuration and design.Therefore, below to the detailed description of the embodiments of the invention provided in the accompanying drawings and the claimed scope of the present invention of not intended to be limiting, but selected embodiment of the present invention is only represented.Based on embodiments of the invention, the every other embodiment that those skilled in the art obtain under the prerequisite not making creative work, all belongs to the scope of protection of the invention.
Embodiment 1:
The present embodiment 1 provides a kind of method based on ecommerce webpage content generating video summary, and its schematic flow sheet is Fig. 1, and main processing steps comprises:
Step S101: the text snippet extracting target electronic commercial affairs webpage text content.
Text ecommerce webpage being introduced merchandise news may be succinct not, user needs more time cost to obtain buyer's guide information on webpage, can with comparatively succinctly and the relatively complete commodity introduced to user on ecommerce webpage by the text snippet extracting ecommerce webpage content of text.
In addition; ecommerce webpage is except the text introducing merchandise news; usually other additional informations are also comprised; such as be attached with on ecommerce webpage advertisement, picture, video, framework and or chart etc.; these additional informations are not effective content of buyer's guide; therefore, before the text snippet extracting ecommerce webpage content of text, the additional information on ecommerce webpage can first be removed.
Step S102, parsing text snippet, obtain the keyword in text snippet.
Keyword in text snippet comprises the key message of buyer's guide, by extracting the key message of acquisition buyer's guide that keyword can be easy.By this step, the keyword of buyer's guide can be obtained, for subsequent step provides key word information.
Step S103, semantic analysis is carried out to keyword, obtain keyword Ontology.
Body is the clear and definite normalized illustration of generalities, provides the basic terms and relation that form association area vocabulary, and the definition specifying the rule of these vocabulary extensions utilizing these terms and relation to form.Utilize Ontology, can obtain the basic description of commodity, the such as ontology describing of " shirt " is " dress ornament ".A word may have multiple ontology describing, and the ontology describing of such as " apple " can be " fruit ", also can be " company ", therefore needs to determine the keyword Ontology under current context.This step is carried out semantic analysis to keyword and is obtained keyword Ontology, so that correct making a summary based on ecommerce webpage content generating video in subsequent step.
Step S104, based on keyword Ontology, from internet, retrieve corresponding picture or video, formation background figure;
Synthetic video summary needs material.According to keyword Ontology, in internet search engine, retrieve corresponding picture or video, formation background figure, as the material of synthetic video summary in subsequent step.
Step S105, based on keyword Ontology, from the grammar database preestablished, obtain the animation template corresponding with keyword;
Store the animation template that different terms Ontology is corresponding in grammar database, according to keyword Ontology, corresponding animation template can be obtained from grammar database.Template corresponding for different keyword is pieced together, the teaming method generating complete video summary can be obtained.
Step S106, text snippet is converted into voice data;
Namely utilize corresponding software that text snippet is changed into voice data, the audio material of making a summary using this voice data as synthetic video.In video frequency abstract, introduce commodity in the mode of audio frequency to user, compare character introduction, easier, save the time of user.
Step S107, play up rule according to presetting, the synthesis of Background, animation template and institute voice data is played up as video file.
Playing up generating video file, have corresponding software and play up rule, playing up rule according to presetting, Background, animation template and institute's voice data synthesis are played up as video file.During synthesis render video, the mapping relations of keyword, the Background corresponding with keyword and animation template in setting audio data; According to mapping relations, synthesis is carried out to Background, animation template and voice data and plays up.Such as keyword 1 occurs when the 3rd second in audio frequency, and occur next keyword when the 5th second in audio frequency, then the Background of keyword 1 correspondence represents between the 3rd second and the 5th second according to animation template.By the method, the audio frequency in video frequency abstract and image are coincide, better introduces commodity to user.
The present embodiment 1 provides a kind of method based on ecommerce webpage content generating video summary, can make a summary by based target ecommerce webpage content of text generating video, and is displayed on target electronic commercial affairs webpage by video frequency abstract.User is when browsing respective electronic commercial affairs webpage, buyer's guide information can be obtained by the mode of watching video frequency abstract, compare the mode of existing e-commerce website by picture and character introduction commodity, the time cost of buyer's guide on user's read electronic commercial affairs webpage can be saved.
Embodiment 2:
The present embodiment 2 provides a kind of preferably based on the method for ecommerce webpage content generating video summary on the basis of embodiment 1, and its schematic flow sheet is Fig. 2, and key step comprises:
Step S201, based on web page interlinkage, obtain ecommerce webpage;
The address of web page interlinkage can be user when accessing ecommerce webpage, to the current E-commerce web page address that e-commerce server sends; Also can be e-commerce server scanning obtain respective electronic business web site on all addresses introducing the ecommerce webpage of commodity.E-commerce server, based on the web page interlinkage obtained, obtains respective electronic commerce Net page information.
Step S202, the additional information removed in ecommerce webpage, wherein additional information comprise following one or more: advertisement, picture, video, framework and chart;
On the ecommerce webpage that e-commerce server obtains, except comprising character introduction corresponding to commodity, also may there be other incoherent additional informations, such as advertisement, picture, video, framework and chart, this additional information is utterly useless for understanding merchandise news, the therefore step S202 additional information removed on e-business network page.
The content of text of the ecommerce webpage after step S203, extraction removal additional information;
After eliminating the additional information on ecommerce webpage, e-commerce server obtains the text message be introduced commodity, so that based on text message generating video summary corresponding on ecommerce webpage in step afterwards.
Step S204, win from content of text emphasis statement composition text snippet.
Buyer's guide on ecommerce webpage may be succinct not, containing more word, user needs the buyer's guide information on more time cost acquisition webpage, therefore, need from content of text, win emphasis statement composition text snippet, to introduce the commodity on ecommerce webpage to user more compactly, save the time cost that user obtains merchandise news.
Step S205, parsing text snippet, obtain the keyword in text snippet.
This step obtains the keyword of buyer's guide, for subsequent step provides key word information.
Step S206, semantic analysis is carried out to keyword, obtain keyword Ontology.
The semantic analysis that this step obtains keyword obtains Ontology, so that correct making a summary based on ecommerce webpage content generating video in subsequent step.
Step S207, based on keyword Ontology, from internet, retrieve corresponding picture or video, formation background figure;
This step obtains Background, as the material of synthetic video summary in subsequent step.
Step S208, based on keyword Ontology, from the grammar database preestablished, obtain the animation template corresponding with keyword;
This step can obtain the mode of generating video summary.
Step S209, text snippet is converted into voice data;
Text snippet is changed into voice data by this step, the audio material of making a summary using this voice data as synthetic video.
Step S210, play up rule according to presetting, the synthesis of Background, animation template and institute voice data is played up as video file.
This step plays up generating video file.
Compared with a kind of method provided based on method and the embodiment 1 of ecommerce webpage content generating video summary that the present embodiment 2 provides, its course of work is identical with advantage, repeats no more.
Embodiment 3:
The present embodiment 3 provides a kind of preferably based on the method for ecommerce webpage content generating video summary on the basis of embodiment 2, and its schematic flow sheet is Fig. 3, and key step comprises:
Step S301, based on web page interlinkage, obtain ecommerce webpage;
This step obtains respective electronic commercial affairs webpage.
Step S302, the additional information removed in ecommerce webpage, wherein additional information comprise following one or more: advertisement, picture, video, framework and chart;
This step additional information removed on e-business network page.
The content of text of the ecommerce webpage after step S303, extraction removal additional information;
This step obtains the text message be introduced commodity.
Similarity in step S304, successively calculating content of text between every two statements.
Similar statement comprises similar information usually.For simplicity, the complete commodity introduced to user on ecommerce webpage, according to similarity by statement classification in content of text, in each class, a statement can be proposed, the commodity introduced to user on ecommerce webpage that so just can be succinct, complete.
Between concrete calculating two statements, the method for similarity is:
First, the quantity sum of total word in current two statements is calculated;
Calculate the sum of all words simultaneously appeared in current two words, its sum is larger, then think that between two statements, similarity is larger;
Secondly, by the length mean value of quantity sum divided by current two statements, the similarity of current two statements is obtained;
In this method, the length of definition statement is the number of words in statement.By the sum of all words that appears in current two the words mean value divided by the number of words of two statements simultaneously, obtain the similarity of current two statements, namely the word that two statements are total is more, and two mean lengths of utterance are shorter, then think that between two statements, similarity is larger.The similarity between two statements can be obtained easily by the method.Such as, two words in content of text are respectively statement 1 and statement 2; Comprise 4 words in statement 1, each word length is 2 words, is respectively word 1, word 2, word 3, word 4; Comprise 6 words in statement 2, each word length is 2 words, is respectively word 3, word 4, word 5, word 6, word 7, word 8.Word 3 and word 4 totally 2 words are had in statement 1 and statement 2; Statement 1 length is 8 words, and statement 2 length is 12 words, and these two mean lengths of utterance are 10 words; Therefore the similarity of statement 1 and statement 2 is 0.2.
Utilize said method, the similarity between every two statements in content of text can be calculated.
Step S305, result of calculation according to similarity, to the statement classification in content of text;
Result according to step S304 calculating gives all statement classifications, such as, if the similarity between statement 1 and statement 2 is greater than the similarity between statement 1 and other all statements and the similarity between statement 1 and statement 2 is greater than average similarity between statement, then statement 1 and statement 2 are divided into a class; Otherwise statement 1 is divided into different classes from statement 2.Through by statement classification, can think that the statement in same class have expressed the same meaning; All classes are all extracted a statement, the commodity summary info introduced to user on ecommerce webpage that can be complete, succinct, save the time cost that user obtains buyer's guide.
Step S306, according to classification result, from every quasi-sentence, extract statement respectively combine, obtain candidate summary;
The content of text obtained above can be classified according to the similarity between statement, and the statement in content of text is divided into multiple class, may have the statement of Similar content in each class containing more than one.If therefrom do not extract summary, then buyer's guide is very loaded down with trivial details.From every quasi-sentence, extract a statement respectively, candidate's summary can be obtained, the commodity introduced to user on ecommerce webpage that can be complete, succinct.May contain many statements in the class of each statement, the candidate of acquisition summary also has multiple scheme, needs to take suitable scheme by follow-up step.
Step S307, choose the candidate minimum with pre-set text length of summarization difference and make a summary as the summary texts of ecommerce webpage from candidate's summary, wherein pre-set text length of summarization is determined according to video length to be generated and the bright read rate of text snippet that presets.
Pre-set text length of summarization is determined according to video length to be generated and the bright read rate of text snippet preset, and such as video length is decided to be 1 minute, and the bright read rate of text snippet is decided to be 120 words per minute clocks, then pre-set text length of summarization is decided to be 120 words.In multiple text snippets that step 1d3 obtains, need to filter out suitable text snippet.Candidate minimum with the text snippet length difference preset in multiple text snippet makes a summary and is chosen for the summary texts of ecommerce webpage.When there is multiple scheme and making content of text length of summarization identical, adopt the scheme extracting the most front statement.The text sentence such as obtained can be divided into two classes, wherein statement 1 and statement 3 are classes, statement 2 and statement 4 are another classes, statement 1 adds length that the number of words of statement 2 and the minimum and statement 1 of pre-set text length of summarization difference add statement 2 and equals the length that statement 3 adds statement 4, now statement 1 is the statement occurred at first in text, then text snippet is made up of statement 1 and statement 2.Text snippet is obtained, the commodity introduced to user on target electronic commercial affairs webpage that can be complete, succinct by this step.
Step S308, parsing text snippet, obtain the keyword in text snippet.
This step can obtain the keyword of buyer's guide, for subsequent step provides key word information.
Step S309, semantic analysis is carried out to keyword, obtain keyword Ontology.
The semantic analysis that this step obtains keyword obtains Ontology, so that correct making a summary based on ecommerce webpage content generating video in subsequent step.
Step S310, based on keyword Ontology, from internet, retrieve corresponding picture or video, formation background figure;
This step obtains Background, as the material of synthetic video summary in subsequent step.
Step S311, based on keyword Ontology, from the grammar database preestablished, obtain the animation template corresponding with keyword;
This step can obtain the mode of generating video summary.
Step S312, text snippet is converted into voice data;
Text snippet is changed into voice data by this step, the audio material of making a summary using this voice data as synthetic video.
Step S313, play up rule according to presetting, the synthesis of Background, animation template and institute voice data is played up as video file.
This step plays up generating video file.
Embodiment 4:
The present embodiment 4 provides a kind of preferably based on the method for ecommerce webpage content generating video summary on the basis of embodiment 1, and its schematic flow sheet is Fig. 4, and key step comprises:
The text snippet of step S401, extraction target electronic commercial affairs webpage text content.
This step obtains text snippet, the commodity introduced to user on target electronic commercial affairs webpage that can be complete, succinct.
Step S402, participle is carried out to text snippet;
Be base unit with Chinese character in the statement of Chinese statement, there is no point word information in similar English statement, therefore first participle is carried out to text snippet, obtain point word information in text snippet.
Step S403, by the word obtained after participle with preset grammar database in word template compare, the part of speech of the word obtained after determining participle;
Word template is stored in grammar database.By the word obtained after participle and the word template in the grammar database preset are compared, the part of speech of the word obtained after determining participle, namely word is the part of speech division of noun, verb, number, measure word, pronoun, adjective, adverbial word, preposition, conjunction, auxiliary word, onomatopoeia and interjection.Similar function word such as adverbial word, preposition, conjunction, auxiliary word, onomatopoeia and interjection do not comprise key message usually, by the word obtained after participle and the word template in the grammar database preset are compared, the part of speech of the word obtained after determining participle, can more quick obtaining keyword.
Step S404, judged result according to part of speech, choose noun and the number keyword as text snippet from the word after participle.
In ecommerce webpage, the keyword of buyer's guide is noun and number, and noun describes title and the classified information of commodity, and number describes the size of commodity, weight and pricing information.Be extracted the noun in text snippet and number, the key message of buyer's guide can be obtained.
Step S405, semantic analysis is carried out to keyword, obtain keyword Ontology.
The semantic analysis that this step obtains keyword obtains Ontology, so that correct making a summary based on ecommerce webpage content generating video in subsequent step.
Step S406, based on keyword Ontology, from internet, retrieve corresponding picture or video, formation background figure;
This step obtains Background, as the material of synthetic video summary in subsequent step.
Step S407, based on keyword Ontology, from the grammar database preestablished, obtain the animation template corresponding with keyword;
This step can obtain the mode of generating video summary.
Step S408, text snippet is converted into voice data;
Text snippet is changed into voice data by this step, the audio material of making a summary using this voice data as synthetic video.
Step S409, play up rule according to presetting, the synthesis of Background, animation template and institute voice data is played up as video file.
This step plays up generating video file.
Embodiment 5:
The present embodiment 5 provides a kind of preferably based on the method for ecommerce webpage content generating video summary on the basis of embodiment 1, and its schematic flow sheet is Fig. 5, and key step comprises:
The text snippet of step S501, extraction target electronic commercial affairs webpage text content.
This step obtains text snippet, the commodity introduced to user on target electronic commercial affairs webpage that can be complete, succinct.
Step S502, parsing text snippet, obtain the keyword in text snippet.
This step obtains the keyword of buyer's guide, for subsequent step provides key word information.
Step S503, preset grammar database in search key, obtain all ontology describings relevant to keyword;
Store ontology describing corresponding to each word, search key in grammar database in the grammar database preset, all ontology describings relevant to keyword can be obtained.Such as, by retrieval grammar database, the ontology describing obtaining " shirt " is " dress ornament ".
Step S504, utilize network ontology language OWL from all ontology describings of keyword, determine keyword Ontology under current context.
Keyword may contain multiple ontology describing, such as " apple ", may be " fruit ", also may be " company ", now, keyword Ontology under OWL can be utilized to determine current context, obtains the correct description of keyword, so that correct making a summary based on ecommerce webpage content generating video in subsequent step.
Step S505, based on keyword Ontology, from internet, retrieve corresponding picture or video, formation background figure;
This step obtains Background, as the material of synthetic video summary in subsequent step.
Step S506, based on keyword Ontology, from the grammar database preestablished, obtain the animation template corresponding with keyword;
This step can obtain the template of generating video summary.
Step S507, text snippet is converted into voice data;
Text snippet is changed into voice data by this step, the audio material of making a summary using this voice data as synthetic video.。
Step S508, play up rule according to presetting, the synthesis of Background, animation template and institute voice data is played up as video file.
This step plays up generating video file.
Embodiment 6:
The present embodiment 6 provides a kind of device based on ecommerce webpage content generating video summary, and its structural representation, as Fig. 6, comprising:
Extraction module 21, for extracting the text snippet of target electronic commercial affairs webpage text content;
Keyword acquisition module 22, for resolving text snippet, obtains the keyword in text snippet;
Semantic module 23, for carrying out semantic analysis to keyword, obtains keyword Ontology;
Background forms module 24, for based on keyword Ontology, retrieves corresponding picture or video, formation background figure from internet;
Animation template acquisition module 25, for based on keyword Ontology, obtains the animation template corresponding with keyword from the grammar database preestablished;
Audio conversion module 26, for being converted into voice data by text snippet;
Video Composition module 27, for playing up rule according to presetting, plays up the synthesis of Background, animation template and voice data as video file.
A kind of device based on ecommerce webpage content generating video summary that the present embodiment 6 provides, extracts the text snippet of target electronic commercial affairs webpage text content by extraction module 21; Then resolved the text snippet of extraction by keyword acquisition module 22, obtain the keyword in text snippet; Afterwards, semantic module 23 analysis of key word obtains keyword Ontology, then forms module 24 based on keyword Ontology by Background, retrieves corresponding picture or video, formation background figure from internet; By animation template acquisition module 25 based on keyword Ontology, from the grammar database preestablished, obtain the animation template corresponding with keyword; Text snippet is converted into voice data by audio conversion module 26; Finally, Video Composition module 27 plays up rule according to presetting, and plays up the synthesis of Background, animation template and voice data into video file.When user accesses ecommerce webpage, can see on webpage based on respective electronic commercial affairs web page contents generating video summary.
The present embodiment 6 provides a kind of device based on ecommerce webpage content generating video summary, can make a summary by based target ecommerce webpage content of text generating video, and is displayed on target electronic commercial affairs webpage by video frequency abstract.User is when browsing respective electronic commercial affairs webpage, buyer's guide information can be obtained by the mode of watching video frequency abstract, compare the mode of existing e-commerce website by picture and character introduction commodity, the time cost of buyer's guide on user's read electronic commercial affairs webpage can be saved.
Embodiment 7:
The present embodiment 7 provides a kind of device based on ecommerce webpage content generating video summary on the basis of embodiment 6, and wherein keyword acquisition module 22 structural representation is as shown in Figure 7, comprising:
Participle unit 22a, for carrying out participle to text snippet;
Part of speech determining unit 22b, for the word obtained after participle and the word template in the grammar database preset are compared, the part of speech of the word obtained after determining participle;
Unit 22c chosen in keyword, for the judged result according to part of speech, chooses noun and the number keyword as text snippet from the word after participle.
Embodiment 8:
The present embodiment 8 provide a kind of based on ecommerce webpage content generating video summary system, comprising: user side 31 and e-commerce server end 32, user side 21 is connected by internet with e-commerce server end 32, and its connection diagram as shown in Figure 8.
E-commerce server end 32 comprise as embodiment 6 or 7 provide based on ecommerce webpage content generating video summary device.
E-commerce server end 32 generates based on ecommerce webpage content generating video summary, when user accesses ecommerce webpage by user side 21, can see based on respective electronic commercial affairs web page contents generating video summary on webpage.
The present embodiment 8 provides a kind of system based on ecommerce webpage content generating video summary, can make a summary by based target ecommerce webpage content of text generating video, and is displayed on target electronic commercial affairs webpage by video frequency abstract.User is when browsing respective electronic commercial affairs webpage, buyer's guide information can be obtained by the mode of watching video frequency abstract, compare the mode of existing e-commerce website by picture and character introduction commodity, the time cost of buyer's guide on user's read electronic commercial affairs webpage can be saved.
In this embodiment, user side 31 can be any one in the application of iPhone mobile phone, the application of iPad panel computer, Android phone application, the application of Android panel computer, TV set-top box application, the application of WindowS platform software, the application of Mac platform software, IE browser plug-in unit, Chrome browser plug-in and Firefox browser plug-in.
E-commerce website end 32 can be any one in WordpreSS plug-in unit, Drupal plug-in unit, Joomla plug-in unit, Mediawiki plug-in unit, DiScuz plug-in unit, PhpWind plug-in unit and webpage javaScript script.
Each device that the embodiment of the present invention provides and module, its technique effect realizing principle and generation is identical with preceding method embodiment, is concise and to the point description, and the not mentioned part of this embodiment part can with reference to corresponding contents in preceding method embodiment.
In several embodiments that the application provides, should be understood that disclosed system, apparatus and method can realize by another way.Device embodiment described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, again such as, multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some communication interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with the protection domain of claim.
Claims (10)
1., based on a method for ecommerce webpage content generating video summary, it is characterized in that, comprising:
Extract the text snippet of target electronic commercial affairs webpage text content;
Resolve described text snippet, obtain the keyword in described text snippet;
Semantic analysis is carried out to described keyword, obtains described keyword Ontology;
Based on described keyword Ontology, from internet, retrieve corresponding picture or video, formation background figure;
Based on described keyword Ontology, from the grammar database preestablished, obtain the animation template corresponding with described keyword;
Described text snippet is converted into voice data;
Play up rule according to presetting, the synthesis of described Background, described animation template and described voice data is played up as video file.
2. method according to claim 1, is characterized in that, the text snippet of described extraction target electronic commercial affairs webpage text content, comprising:
Based on web page interlinkage, obtain ecommerce webpage;
Remove the additional information in described ecommerce webpage, wherein said additional information comprise following one or more: advertisement, picture, video, framework and chart;
Extract the content of text of the described ecommerce webpage after additional information belonging to removing;
From described content of text, win emphasis statement form described text snippet.
3. method according to claim 2, is characterized in that, described emphasis statement of winning from described content of text forms described text snippet, comprising:
Calculate the similarity between every two statements in described content of text successively;
According to the result of calculation of described similarity, to the statement classification in described content of text;
According to the result of described classification, from every quasi-sentence, extract statement respectively combine, obtain candidate's summary;
From described candidate's summary, choose the candidate minimum with pre-set text length of summarization difference makes a summary as the summary texts of described ecommerce webpage, and wherein said pre-set text length of summarization is determined according to video length to be generated and the bright read rate of text snippet preset.
4. method according to claim 3, is characterized in that, the described similarity calculated successively in described content of text between every two statements, comprising:
Calculate the quantity sum of total word in current two statements;
By the length mean value of described quantity sum divided by current two statements, obtain the similarity of current two statements;
Method according to the similarity obtaining current two statements calculates the similarity in described content of text between every two statements.
5. method according to claim 1, is characterized in that, the described text snippet of described parsing, obtains the keyword in described text snippet, comprising:
Participle is carried out to described text snippet;
Word template in the word obtained after described participle and described grammar database is compared, the part of speech of the word obtained after determining participle;
According to the judged result of described part of speech, from the word after participle, choose noun and the number keyword as described text snippet.
6. method according to claim 1, is characterized in that, describedly carries out semantic analysis to described keyword, obtains described keyword Ontology, comprising:
In described grammar database, retrieve described keyword, obtain all ontology describings relevant to described keyword;
Utilize network ontology language OWL from all ontology describings of described keyword, determine keyword Ontology under current context.
7. method according to claim 1, is characterized in that, described according to preset play up rule, by described Background, described animation template and described voice data synthesis play up as video file, comprising:
Set the mapping relations of keyword described in described voice data, the Background corresponding with described keyword and animation template;
According to described mapping relations, synthesis is carried out to described Background, described animation template and described voice data and plays up.
8., based on a device for ecommerce webpage content generating video summary, it is characterized in that, comprising:
Extraction module, for extracting the text snippet of target electronic commercial affairs webpage text content;
Keyword acquisition module, for resolving described text snippet, obtains the keyword in described text snippet;
Semantic module, for carrying out semantic analysis to described keyword, obtains described keyword Ontology;
Background forms module, for based on described keyword Ontology, retrieves corresponding picture or video, formation background figure from internet;
Animation template acquisition module, for based on described keyword Ontology, obtains the animation template corresponding with described keyword from the grammar database preset;
Audio conversion module, for being converted into voice data by described text snippet;
Video Composition module, for playing up rule according to presetting, plays up the synthesis of described Background, described animation template and described voice data as video file.
9. device according to claim 8, is characterized in that, described keyword acquisition module, comprising:
Participle unit, for carrying out participle to described text snippet;
Part of speech determining unit, for the word template in the word obtained after described participle and described grammar database is compared, the part of speech of the word obtained after determining participle;
Unit chosen in keyword, for the judged result according to described part of speech, chooses noun and the number keyword as described text snippet from the word after participle.
10., based on a system for ecommerce webpage content generating video summary, it is characterized in that, comprising: user side and the e-commerce server end be connected by internet with user side;
Described e-commerce server end comprises as claimed in claim 8 or 9 based on the device of ecommerce webpage content generating video summary.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510156125.8A CN104731960B (en) | 2015-04-03 | 2015-04-03 | Method, apparatus and system based on ecommerce webpage content generation video frequency abstract |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510156125.8A CN104731960B (en) | 2015-04-03 | 2015-04-03 | Method, apparatus and system based on ecommerce webpage content generation video frequency abstract |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104731960A true CN104731960A (en) | 2015-06-24 |
| CN104731960B CN104731960B (en) | 2018-03-09 |
Family
ID=53455847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510156125.8A Expired - Fee Related CN104731960B (en) | 2015-04-03 | 2015-04-03 | Method, apparatus and system based on ecommerce webpage content generation video frequency abstract |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104731960B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504304A (en) * | 2016-09-14 | 2017-03-15 | 厦门幻世网络科技有限公司 | A kind of method and device of animation compound |
| CN107832382A (en) * | 2017-10-30 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Method, apparatus, equipment and storage medium based on word generation video |
| CN108470036A (en) * | 2018-02-06 | 2018-08-31 | 北京奇虎科技有限公司 | A kind of method and apparatus that video is generated based on story text |
| WO2018214772A1 (en) * | 2017-05-22 | 2018-11-29 | 腾讯科技（深圳）有限公司 | Media data processing method and apparatus, and storage medium |
| CN109325135A (en) * | 2018-10-26 | 2019-02-12 | 平安科技（深圳）有限公司 | Text based video generation method, device, computer equipment and storage medium |
| CN109949078A (en) * | 2019-03-01 | 2019-06-28 | 北京金堤科技有限公司 | Promotion message treating method and apparatus |
| CN110309351A (en) * | 2018-02-14 | 2019-10-08 | 阿里巴巴集团控股有限公司 | Video image generation, device and the computer system of data object |
| CN111294640A (en) * | 2018-12-07 | 2020-06-16 | 北京京东尚科信息技术有限公司 | Information display method, information selling method, information display device, information selling device, storage medium and electronic equipment |
| CN112287168A (en) * | 2020-10-30 | 2021-01-29 | 北京有竹居网络技术有限公司 | Method and apparatus for generating video |
| WO2021098310A1 (en) * | 2019-11-18 | 2021-05-27 | 北京沃东天骏信息技术有限公司 | Video generation method and device, and terminal and storage medium |
| CN113905254A (en) * | 2021-09-03 | 2022-01-07 | 前海人寿保险股份有限公司 | Video synthesis method, device, system and readable storage medium |
| CN114363701A (en) * | 2021-12-29 | 2022-04-15 | 四川启睿克科技有限公司 | Method for converting web page into short video |
| WO2023202361A1 (en) * | 2022-04-22 | 2023-10-26 | 北京有竹居网络技术有限公司 | Video generation method and apparatus, medium, and electronic device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100306232A1 (en) * | 2009-05-28 | 2010-12-02 | Harris Corporation | Multimedia system providing database of shared text comment data indexed to video source data and related methods |
| CN103324760A (en) * | 2013-07-11 | 2013-09-25 | 中国农业大学 | Method and system for automatically generating nutrition health education video through commentary file |
| CN103559214A (en) * | 2013-10-11 | 2014-02-05 | 中国农业大学 | Method and device for automatically generating video |
-
2015
- 2015-04-03 CN CN201510156125.8A patent/CN104731960B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100306232A1 (en) * | 2009-05-28 | 2010-12-02 | Harris Corporation | Multimedia system providing database of shared text comment data indexed to video source data and related methods |
| CN103324760A (en) * | 2013-07-11 | 2013-09-25 | 中国农业大学 | Method and system for automatically generating nutrition health education video through commentary file |
| CN103559214A (en) * | 2013-10-11 | 2014-02-05 | 中国农业大学 | Method and device for automatically generating video |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504304B (en) * | 2016-09-14 | 2019-09-24 | 厦门黑镜科技有限公司 | A kind of method and device of animation compound |
| CN106504304A (en) * | 2016-09-14 | 2017-03-15 | 厦门幻世网络科技有限公司 | A kind of method and device of animation compound |
| WO2018214772A1 (en) * | 2017-05-22 | 2018-11-29 | 腾讯科技（深圳）有限公司 | Media data processing method and apparatus, and storage medium |
| CN108965737A (en) * | 2017-05-22 | 2018-12-07 | 腾讯科技（深圳）有限公司 | media data processing method, device and storage medium |
| CN108965737B (en) * | 2017-05-22 | 2022-03-29 | 腾讯科技（深圳）有限公司 | Media data processing method, device and storage medium |
| CN107832382A (en) * | 2017-10-30 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Method, apparatus, equipment and storage medium based on word generation video |
| CN108470036A (en) * | 2018-02-06 | 2018-08-31 | 北京奇虎科技有限公司 | A kind of method and apparatus that video is generated based on story text |
| CN110309351A (en) * | 2018-02-14 | 2019-10-08 | 阿里巴巴集团控股有限公司 | Video image generation, device and the computer system of data object |
| CN109325135A (en) * | 2018-10-26 | 2019-02-12 | 平安科技（深圳）有限公司 | Text based video generation method, device, computer equipment and storage medium |
| CN109325135B (en) * | 2018-10-26 | 2023-08-08 | 平安科技（深圳）有限公司 | Text-based video generation method, device, computer equipment and storage medium |
| CN111294640A (en) * | 2018-12-07 | 2020-06-16 | 北京京东尚科信息技术有限公司 | Information display method, information selling method, information display device, information selling device, storage medium and electronic equipment |
| CN109949078A (en) * | 2019-03-01 | 2019-06-28 | 北京金堤科技有限公司 | Promotion message treating method and apparatus |
| CN109949078B (en) * | 2019-03-01 | 2020-11-03 | 北京金堤科技有限公司 | Promotion information processing method and device |
| WO2021098310A1 (en) * | 2019-11-18 | 2021-05-27 | 北京沃东天骏信息技术有限公司 | Video generation method and device, and terminal and storage medium |
| CN112287168A (en) * | 2020-10-30 | 2021-01-29 | 北京有竹居网络技术有限公司 | Method and apparatus for generating video |
| CN113905254A (en) * | 2021-09-03 | 2022-01-07 | 前海人寿保险股份有限公司 | Video synthesis method, device, system and readable storage medium |
| CN113905254B (en) * | 2021-09-03 | 2024-03-29 | 前海人寿保险股份有限公司 | Video synthesis method, device, system and readable storage medium |
| CN114363701A (en) * | 2021-12-29 | 2022-04-15 | 四川启睿克科技有限公司 | Method for converting web page into short video |
| WO2023202361A1 (en) * | 2022-04-22 | 2023-10-26 | 北京有竹居网络技术有限公司 | Video generation method and apparatus, medium, and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104731960B (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104731959A (en) | Video abstraction generating method, device and system based on text webpage content | |
| CN104731960A (en) | Method, device and system for generating video abstraction based on electronic commerce webpage content | |
| JP5449633B1 (en) | Advertisement translation device, advertisement display device, and advertisement translation method | |
| US20150278359A1 (en) | Method and apparatus for generating a recommendation page | |
| US10402479B2 (en) | Method, server, browser, and system for recommending text information | |
| US9015168B2 (en) | Device and method for generating opinion pairs having sentiment orientation based impact relations | |
| CN105354183A (en) | Analytic method, apparatus and system for internet comments of household electrical appliance products | |
| US10394886B2 (en) | Electronic device, computer-implemented method and computer program | |
| CN106649778B (en) | Interaction method and device based on deep question answering | |
| CN103984741A (en) | Method and system for extracting user attribute information | |
| CN109558513A (en) | A kind of content recommendation method, device, terminal and storage medium | |
| JP5442401B2 (en) | Behavior information extraction system and extraction method | |
| CN111178056A (en) | Deep learning based file generation method and device and electronic equipment | |
| CN112230838A (en) | Article processing method, article processing device, article processing equipment and computer readable storage medium | |
| US20160092915A1 (en) | Method and system of enhancing online contents value | |
| CN113038175B (en) | Video processing method and device, electronic equipment and computer readable storage medium | |
| KR101542417B1 (en) | Method and apparatus for learning user preference | |
| KR101526872B1 (en) | Advertising providing method including literary style changing step | |
| JP4774087B2 (en) | Movie evaluation method, apparatus and program | |
| CN110019702B (en) | Data mining method, device and equipment | |
| CN106959945B (en) | Method and device for generating short titles for news based on artificial intelligence | |
| CN114691926A (en) | Information display method and electronic equipment | |
| CN113240447A (en) | Advertisement pushing method and device, storage medium and server | |
| KR101008996B1 (en) | Sequential web site moving system using voice guide message | |
| JP5638051B2 (en) | Information providing system, information providing apparatus, information providing method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180309 |