CN110245339A - Article generation method, device, equipment and storage medium - Google Patents
Article generation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110245339A CN110245339A CN201910536677.XA CN201910536677A CN110245339A CN 110245339 A CN110245339 A CN 110245339A CN 201910536677 A CN201910536677 A CN 201910536677A CN 110245339 A CN110245339 A CN 110245339A
- Authority
- CN
- China
- Prior art keywords
- place
- paragraph
- information
- article
- sequence
- 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
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the present invention proposes a kind of article generation method, device, equipment and storage medium, and method therein includes: to determine that article to be generated needs each place for including according to track;Paragraph corresponding with each place is generated according to the first information in each place;According to the sequence on the in-orbit mark in place, sequence of the corresponding paragraph in place in article to be generated is determined;Each paragraph is combined according to the sequence of each paragraph to generate article.The method of the embodiment of the present invention efficiently and conveniently can help user to automatically generate article.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of article generation method, device, equipment and storage to be situated between
Matter.
Background technique
Current travelling planning article or travel notes article are mostly human-editeds, and time-consuming and cost is huge.One is needed thus
A simple effective method helps user to automatically generate travelling planning article or travel notes article.
Summary of the invention
The embodiment of the present invention provides a kind of article generation method, device, equipment and storage medium, to solve in the prior art
One or more technical problems.
In a first aspect, the embodiment of the invention provides a kind of article generation methods, comprising:
Determine that article to be generated needs each place for including according to track;
Paragraph corresponding with each place is generated according to the first information in each place;
According to sequence of the place on track, determine the corresponding paragraph in the place in the article to be generated
Sequentially;
Each paragraph is combined according to the sequence of each paragraph to generate article.
In one embodiment, the first information includes text information and candidate image, according to the first of each place
Information generates paragraph corresponding with each place, comprising:
Obtain an at least candidate image corresponding with the place;
Obtain a plurality of types of text informations corresponding with the place;
According to the type of the text information, sequence of the text information in the corresponding paragraph in the place is determined;
It is inserted into the candidate image between different types of text information, generates paragraph corresponding with the place.
In one embodiment, an at least candidate image corresponding with the place is obtained, comprising:
Detect whether the corresponding quantity for uploading image in the place meets preset value;
If it is not, then obtaining candidate image corresponding with the place from knowledge mapping.
In one embodiment, the first information further includes the image recommended information of the candidate image, according to each
The first information in place generates paragraph corresponding with each place, further includes:
Identify the entity information in the candidate image;
It is that described image recommended information is added in the candidate image according to the entity information.
In one embodiment, a plurality of types of text informations corresponding with the place, including following manner are obtained
In at least two:
The text information of basic content type is obtained from map client database;
The text information of encyclopaedia type is obtained from knowledge mapping;
Obtain the text information of strategy type.
In one embodiment, each paragraph is combined to generate article according to the sequence of each paragraph, comprising:
According to second information in the corresponding place of two neighboring paragraph, the transition between two neighboring paragraph is generated
Section;
Each paragraph is combined according to the sequence of each paragraph, and adds corresponding changeover portion between two neighboring paragraph, with life
At the article.
In one embodiment, second information includes coordinate, according to the corresponding place of two neighboring paragraph
The second information, generate the changeover portion between two neighboring paragraph, comprising:
Obtain corresponding first tracing point in the first place and the second place and the second tracing point;
First tracing point and second tracing point are separately converted to the first coordinate and the second coordinate, described first
Coordinate and second coordinate are latitude and longitude coordinates;
According to first coordinate and second coordinate, determine between first place and second place away from
From;
According to the distance between first place and second place, generate the corresponding paragraph in first place with
Changeover portion between the corresponding paragraph in second place.
In one embodiment, second information includes feature label, corresponding according to two neighboring paragraph
Second information in place, generates the changeover portion between two neighboring paragraph, comprising:
At least one candidate label in the place is obtained from map client database and/or knowledge mapping;
If candidate's label have it is multiple, according to different degree of each candidate label in multiple candidate labels from more
The characteristics of choosing the place in a candidate's label label;
According to label the characteristics of label the characteristics of the first place and the second place, the corresponding paragraph in first place is generated
Changeover portion between paragraph corresponding with second place.
In one embodiment, second information includes interest point information, is respectively corresponded according to two neighboring paragraph
Place the second information, generate the changeover portion between two neighboring paragraph, comprising:
Obtain the multiple points of interest for meeting preset range at a distance from the first place;
Using second place as the point of interest in first place, the interest point information of each point of interest is described, is generated
Changeover portion between the corresponding paragraph in first place paragraph corresponding with second place.
Second aspect, the embodiment of the present invention provide a kind of article generating means, comprising:
Location-determining module, for determining that article to be generated needs each place for including according to track;
Paragraph generation module, for generating paragraph corresponding with each place according to the first information in each place;
Sequence determining module determines that the corresponding paragraph in the place exists for the sequence according to the place on track
Sequence in the article to be generated;
Composite module combines each paragraph for the sequence according to each paragraph to generate article.
In one embodiment, the composite module includes:
Changeover portion generates submodule, for the second information according to the corresponding place of two neighboring paragraph, generates phase
Changeover portion between adjacent two paragraphs;
Combination addition submodule for combining each paragraph according to the sequence of each paragraph, and adds between two neighboring paragraph
Add corresponding changeover portion, to generate the article.
The third aspect, the embodiment of the invention provides a kind of article generating device, the function of the equipment can be by hard
Part is realized, corresponding software realization can also be executed by hardware.The hardware or software include one or more and above-mentioned function
It can corresponding module.
It include processor and memory in the structure of the equipment in a possible design, the memory is used for
Storage supports the equipment to execute the program of above-mentioned article generation method, the processor is configured to for executing the storage
The program stored in device.The equipment can also include communication interface, be used for and other equipment or communication.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage mediums, set for storing article generation
Standby computer software instructions used comprising for executing program involved in above-mentioned article generation method.
The method of the embodiment of the present invention determines that article to be generated needs the place for including based on track, and according to the of place
One information generates the descriptive paragraph in the place, and then the sequence of each paragraph is determined according to track, can automatically generate article.This
The method of inventive embodiments can efficiently and conveniently help user to generate article.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing description
Schematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is further
Aspect, embodiment and feature, which will be, to be readily apparent that.
Detailed description of the invention
In the accompanying drawings, unless specified otherwise herein, otherwise indicate the same or similar through the identical appended drawing reference of multiple attached drawings
Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention
Disclosed some embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 shows the flow chart of article generation method according to an embodiment of the present invention.
Fig. 2 shows a kind of flow charts of the article generation method of embodiment according to an embodiment of the present invention.
Fig. 3 shows the flow chart of the article generation method of another embodiment according to an embodiment of the present invention.
Fig. 4-1 shows a kind of structural block diagram of one of module of article generating means according to an embodiment of the present invention.
Fig. 4-2 shows a kind of structural block diagram of one of module of article generating means according to an embodiment of the present invention.
Fig. 4-3 shows a kind of structural block diagram of one of module of article generating means according to an embodiment of the present invention.
Fig. 4-4 shows a kind of structural block diagram of one of module of article generating means according to an embodiment of the present invention.
Fig. 5 shows the structural block diagram of article generating means according to an embodiment of the present invention.
Fig. 6 shows the structural block diagram of the article generating means in a kind of embodiment according to an embodiment of the present invention.
Fig. 7 shows the structural block diagram of article generating device according to an embodiment of the present invention.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.
Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Fig. 1 shows the flow chart of article generation method according to an embodiment of the present invention.As shown in Figure 1, the embodiment of the present invention
Article generation method may include:
Step S101, determine that article to be generated needs each place for including according to track.
In the present embodiment, track can be the track to be gone on a journey of user's planning, or user has travelled later trip
Play route.Each tracing point on track is played according to planning order or actually and is sequentially arranged.Tracing point is corresponding with place, Ke Yigen
Determine that article to be generated needs each place for including according to each tracing point.
Step S102, paragraph corresponding with each place is generated according to the first information in each place.
That is, the corresponding paragraph in the place can be generated according to the first information in the place for each place.Its
In, paragraph can be one or more snippets, and this embodiment is not limited.Each paragraph is for describing one place.
The first information may include text information and candidate image.Text information may include the text of basic content type
At least one of information, the text information of encyclopaedia type and text information of strategy type.
The text information of basic content type may include title, address, open hour, evaluation, ticket information etc..One
In kind embodiment, the text information of basic content type can be obtained from map client database.Wherein, map end can be
The application program (Application, APP) of map style.May include in map client database map datum, on map to ground
The data such as title, address, open hour, evaluation, the ticket information of point.
In one embodiment, the text information of encyclopaedia type can be obtained from knowledge mapping.Knowledge mapping passes through
By the theory of the subjects such as applied mathematics, graphics, Information Visualization Technology, information science and method and meterological citation analysis,
The methods of Co-occurrence Analysis combines, and nuclear structure, developing history, the forward position neck of subject are visually shown using visual map
Domain and whole Knowledge framework reach the modern theory of Multidisciplinary Integration purpose.In the present embodiment, knowledge mapping is in addition to can wrap
Visual map is included, can also include the various encyclopaedia data on internet.
In one example, can encyclopaedia data to form web page carry out dissection process, to extract the text of encyclopaedia type
Word information.If the text information content extracted is more, such as number of words or sentence quantity are more than setting, then can be from extracting
Text information intercept a part of (such as 50 words or 3 sentences), obtain the text information of the encyclopaedia type for generating article.
In one embodiment, strategy type can be obtained from the travel site or travel notes article on internet
Text information.
The image that candidate image can upload for user.In one example, the method for the present embodiment can be according to upload
Image in carry location information and each place location information, for the images match one place.Wherein, in image
Included location information, can by the capture apparatus of image, the position is generated when shooting, can also have according in image
There is the entity of geographical indication to determine.It in another example, can be the specified location information of image and various regions according to user
The location information of point, for the images match one place.Candidate image may be the image obtained from knowledge mapping.Into one
Step ground, the low-quality images obtained from knowledge mapping can be filtered out.Low-quality images may include with advertisement or trade mark
(logo) image, the image that can not also be known including low resolution etc..
In one example, the text information got may only have a seed type or two types, then can be in text
It is inserted into candidate image after or before word information, generates paragraph.Alternatively, being inserted into candidate figure between two kinds of text information
Picture generates paragraph.
In one embodiment, as shown in Fig. 2, may include: in step s 102
Step S201, an at least candidate image corresponding with the place is obtained;
Step S202, a plurality of types of text informations corresponding with the place are obtained;
Step S203, according to the type of the text information, determine the text information in the corresponding paragraph in the place
In sequence;
Step S204, it is inserted into the candidate image between different types of text information, generates corresponding with the place
Paragraph.
That is, if the text information got includes the text information of two or more (including two kinds) types,
Can determine sequence of the text information in paragraph according to the type of text information, so the text information of adjacent type it
Between be inserted into one or more candidate image, to generate paragraph.
Such as: using the text information of encyclopaedia type as the first segment in paragraph, and 1~3 time is inserted into after first segment
Select picture;Using the text information of basic content type as the second segment in paragraph, and after second end be inserted into 1~2 other
Candidate picture;Using the text information of strategy type as the third section in paragraph, candidate image can be inserted after third section,
Candidate picture can also be not inserted into.
It should be noted that be not each adjacent two type text information between be intended to insertion candidate image, can be with
It is configured according to the quantity of candidate image.
It in one embodiment, in step s 201 may include: the corresponding number for uploading image in the detection place
Whether amount meets preset value;If it is not, then obtaining candidate image corresponding with the place from knowledge mapping.
If the quantity for the upload image that the corresponding user in a certain place uploads meets preset value, i.e. quantity is more, then may be used
Image will be uploaded as candidate image.If the corresponding discrepancy of quantity for uploading image in a certain place closes preset value, such as quantity
It is less or do not have, then candidate image corresponding with the place can be obtained from knowledge mapping.
In one embodiment, the first information can also include the image recommended information of candidate image.In step S102
In can also include: entity information in the identification candidate image;It is candidate image addition according to the entity information
Described image recommended information.
Such as: region convolutional neural networks (Region-Convolutional Neural Networks, R- can be based on
) or an identification model (You Only Look Once, YOLO) or more box detector (the Single Shot of single-shot CNN
MultiBox Detector, SSD) etc. models, identify candidate image in entity, obtain entity information.Then, according to entity
Information adds image recommended information above or below candidate image.Such as: the Forbidden City has been recognized in candidate image, then may be used
To add image recommended information " the Forbidden City " in the lower section of candidate image.Another example is: having recognized sunset clouds and event in candidate image
Palace then can add image recommended information " the Forbidden City under sunset clouds " in the lower section of candidate image.
As shown in Figure 1, the article generation method of the embodiment of the present invention further include:
Step S103, the sequence according to the place on track determines the corresponding paragraph in the place described to be generated
At the sequence in article;
Step S104, each paragraph is combined to generate article according to the sequence of each paragraph.
Each place is corresponding with tracing point, can determine corresponding place according to sequence of the tracing point on track
Then sequence of the paragraph in article to be generated combines each paragraph according to the sequence of each paragraph and generates article, such as travelling planning text
Chapter or travel notes article.
In one embodiment, as shown in figure 3, may include: in step S104
Step S301, according to second information in the corresponding place of two neighboring paragraph, generate two neighboring paragraph it
Between changeover portion;
Step S302, each paragraph is combined according to the sequence of each paragraph, and adds corresponding mistake between two neighboring paragraph
Section is crossed, to generate the article.
That is, after the sequence that each paragraph has been determined, it can be in two adjacent paragraphs, such as the first paragraph and second
Changeover portion is added between paragraph, and then generates article.Wherein, corresponding first place of the first paragraph, corresponding second ground of the second paragraph
Point.According to second information in the first place and second information in the second place, generate between the first paragraph and the second paragraph
Changeover portion.Wherein, the second information may include coordinate, feature label, interest point information etc..
It in one embodiment, may include: that the first place of acquisition and the second place respectively correspond in step S301
The first tracing point and the second tracing point;By first tracing point and second tracing point be separately converted to the first coordinate and
Second coordinate, first coordinate and second coordinate are latitude and longitude coordinates;According to first coordinate and described second
Coordinate determines the distance between first place and second place;According to first place and second place
The distance between, generate the changeover portion between the corresponding paragraph in first place paragraph corresponding with second place.
In one example, tracing point can be chosen from selection on map or from the menu that APP is provided by user
It arrives, therefore, it is necessary to the tracing points for choosing user to be converted to the coordinate that map end APP can be identified, such as Mercator's coordinate.Another
It can be latitude and longitude coordinates by the coordinate transformation that map end APP can be identified in one example.Therefore, the coordinate of the present embodiment
It can be Mercator's coordinate, or latitude and longitude coordinates.
It is possible to further determine the distance between the first place and the second place according to the first coordinate and the second coordinate,
And then generate the changeover portion between the first paragraph and the second paragraph.Such as: it is calculated between the first place and the second place
Distance is 10 kilometers, then the changeover portion between the first paragraph and the second paragraph can for " at 10 kilometers of the first place of distance place, and also
There is the second place ".
It in one embodiment, may include: to be obtained from map client database and/or knowledge mapping in step S301
Take at least one candidate label in the place;If candidate's label have it is multiple, according to each candidate label multiple
The characteristics of different degree in candidate label chooses the place from multiple candidate labels label;It is marked according to the characteristics of the first place
Label and label the characteristics of the second place generate between the corresponding paragraph in first place paragraph corresponding with second place
Changeover portion.
In one example, the candidate label in a certain place has multiple, then can according to the characteristics of candidate label from multiple
Selected in candidate label one it is optimal as the place the characteristics of label.Such as: it can be by the word frequency of each candidate label
(Term Frequency, TF)-inverse document frequency (Inverse Document Frequency, IDF) value is as candidate
The different degree of label determines feature label according to the TF-IDF value of each candidate label.In another example, a certain place
Candidate label only one, then can be directly using candidate's label as label the characteristics of the place.
Further, according to label the characteristics of label the characteristics of the first place and the second place, the first paragraph and the are generated
Changeover portion between two paragraphs.Such as: label is famous scenic spot the characteristics of the first place, and label is humanity the characteristics of the second place
Famous scenic spot, then the changeover portion between the first paragraph and the second paragraph can be " after having gone sight-seeing this famous scenic spot of the first place, to swim
Look at humane famous scenic spot, such as the second place ".
It in one embodiment, may include: to obtain to meet default model at a distance from the first place in step S301
The multiple points of interest enclosed;Using second place as the point of interest in first place, the point of interest letter of each point of interest is described
Breath generates the changeover portion between the corresponding paragraph in first place paragraph corresponding with second place.
From map client database, the point of interest (Point of Interest) on each place periphery can be obtained.Example
Such as: using the place at a distance from the first place within a preset range as the POI in the first place.It is possible to further by second
POI of the place as the first place generates the changeover portion between the first paragraph and the second paragraph, such as " the first place periphery also
There is the second place ".
In the embodiment of the present invention, the track to be gone on a journey that can be planned according to user generates travelling planning article, can also root
According to the Route Generation travel notes article of playing of user.Place can be sight spot.It should be noted that in the embodiment of the present invention, sight spot
Including but not limited to charge scenic spot, free scenic spot, the place played for user etc..The present invention is introduced by taking sight spot as an example below to implement
The article generating means of example, the APP can execute the article generation method of any description above.
As shown in Fig. 4-1, article generating means may include user data processing module, for receiving the number of user's upload
According to.The data that user uploads may include trace information (tracing point that such as user chooses) and pictorial information (blit picture as above).
In one example, X-type engine (Engine X, NGINX) can be used as background service, in fact in the method for the embodiment of the present invention
When receive the request sent of user, and obtain from request the data that user uploads.
User data processing module can be also used for pre-processing trace information.Such as: tracing point is converted into ground
The coordinate that figure end APP can be identified.User data processing module can be also used for pre-processing pictorial information.Such as: know
Not Shang Chuan entity information in image, used for being subsequently generated article.User data processing module can be also used for picture mapping.
Such as: according to the location information for the location information and tracing point (or sight spot) for uploading image, the upload of same tracing point will be belonged to
Image is polymerize, and then is obtained belonging to the one or more of same tracing point and uploaded image.
As shown in the Fig. 4-2, article generating means can also include map end data processing module, for according to user trajectory
(trace information) obtains each sight spot, and essential information (the text letter of basic content type in sight spot is obtained from map client database
Breath).The title at such as sight spot, address, open hour, evaluation, ticket information.Map end data processing module can be also used for by
The coordinate that map end APP can be identified is converted into latitude and longitude coordinates (scenic spot location), for being subsequently generated text such as Mercator's coordinate
Chapter uses.Map end data processing module can be also used for determining sight spot label according to the TF-IDF value of the candidate label at sight spot
(the characteristics of sight spot label).In turn, sight spot normal data may include sight spot essential information, sight spot label and scenic spot location.
As shown in Fig. 4-3, article generating means can also include knowledge mapping data processing module, for according to sight spot name
Claim to obtain sight spot encyclopaedia (text information of encyclopaedia type), sight spot picture (candidate image), sight spot periphery (POI), sight spot strategy
(text information of strategy type) and other sight spot related datas (other kinds of text information).
As shown in Fig. 4-4, article generating means can also include text generation module, for according to rail each in user trajectory
The sequence of mark point is each sights.Text generation module can be also used for generating the first section of article.Such as: by online
Travel notes type related article is obtained, and takes its first section as reference, and then generates multiple sections of first templates, and then raw based on section head template
At the first section of article.Text generation module can be also used for generating the changeover portion between two sight spots, and generate each sight spot
Sight spot paragraph.Further, text generation module can be also used for generating article title.Such as: the mark that user can be specified
Topic is used as article title, can also be according to pre-configured template generation article title.
It should be noted that the sight spot in above-mentioned article generating means is only a kind of example in place, i.e., in foregoing description,
Sight spot can also be replaced with into place.
People tourism when, what is seen and heard that people like in travelling is recorded, some be by picture, some
It is that a travelling travel notes article is converted into finally by the combination design to these pictures and text, due to being related to by text
To the correlation of individual subscriber, the article of generation can be described as thousand people, thousand face in addition, when people carry out travelling planning, need to make
Fixed travelling planning article, such as road book.There is presently no the methods for automatically generating these types of articles.
The method of the embodiment of the present invention by determining that article to be generated needs the place for including based on trace information, and according to
The first information in place generates the descriptive paragraph in the place, and then the sequence of each paragraph is determined according to trace information, can be certainly
It is dynamic to generate article.Further, the mistake section section between the two places can also be generated according to second information in two places,
Make to generate the more clear and more coherent smoothness of article.It, can be with knowledge based map, to enrich life when obtaining the first information and the second information
At the material of article, keep the article generated more lively more professional.The method of the embodiment of the present invention can efficiently and conveniently help to use
Family generates article, and solving user, time-consuming, selects the various problems such as difficulty.Further, the method for the embodiment of the present invention can be real
When help user to generate one's own article, and souvenir can be saved or be shared with friend, meet user to high-quality
While servicing demand, the commercial value of Related product is also improved.
Fig. 5 shows the result block diagram of article generating means according to an embodiment of the present invention.As shown in figure 5, the device can be with
Include:
Location-determining module 501, for determining that article to be generated needs each place for including according to track;
Paragraph generation module 502, for generating paragraph corresponding with each place according to the first information in each place;
Sequence determining module 503 determines the corresponding paragraph in the place for the sequence according to the place on track
Sequence in the article to be generated;
Composite module 504 combines each paragraph for the sequence according to each paragraph to generate article.
In one embodiment, paragraph generation module 502 may include:
First acquisition submodule, for obtaining an at least candidate image corresponding with the place;
Second acquisition submodule, for obtaining a plurality of types of text informations corresponding with the place;
First determines that submodule determines the text information in the place for the type according to the text information
Sequence in corresponding paragraph;
It is inserted into submodule, for being inserted into the candidate image between different types of text information, is generated with described
The corresponding paragraph of point.
In one embodiment, the first acquisition submodule may include:
Detection unit, for detecting whether the corresponding quantity for uploading image in the place meets preset value;
Acquiring unit, in a case of no, candidate image corresponding with the place being obtained from knowledge mapping.
In one embodiment, the first information further includes the image recommended information of the candidate image, and paragraph is raw
May include: at module 502
Identify submodule, for identification the entity information in the candidate image;
Submodule is added, for being that described image recommended information is added in the candidate image according to the entity information.
In one embodiment, the second acquisition submodule can be used at least two in following manner:
The text information of basic content type is obtained from map client database;
The text information of encyclopaedia type is obtained from knowledge mapping;
Obtain the text information of strategy type.
In one embodiment, as shown in fig. 6, composite module 504 may include:
Changeover portion generates submodule 601, for the second information according to the corresponding place of two neighboring paragraph, generates
Changeover portion between two neighboring paragraph;
Combination addition submodule 602, for combining each paragraph according to the sequence of each paragraph, and between two neighboring paragraph
Corresponding changeover portion is added, to generate the article.
In one embodiment, second information includes coordinate, and changeover portion generates submodule 601 and may include:
First acquisition unit, for obtaining the first place and corresponding first tracing point in the second place and the second track
Point;
Conversion unit, for first tracing point and second tracing point to be separately converted to the first coordinate and second
Coordinate, first coordinate and second coordinate are latitude and longitude coordinates;
Distance determining unit, for determining first place and institute according to first coordinate and second coordinate
State the distance between second place;
First Transition section generation unit, for generating according to the distance between first place and second place
Changeover portion between the corresponding paragraph in first place paragraph corresponding with second place.
In one embodiment, second information includes feature label, and changeover portion generates submodule 601 and can wrap
It includes:
Second acquisition unit, for obtained from map client database and/or knowledge mapping the place at least one
Candidate label;
Selection unit, in the case where the candidate label has multiple, according to each candidate label in multiple candidates
The characteristics of different degree in label chooses the place from multiple candidate labels label;
Second changeover portion generation unit, for according to label the characteristics of label the characteristics of the first place and the second place, life
At the changeover portion between the corresponding paragraph in first place paragraph corresponding with second place.
In one embodiment, second information includes interest point information, and changeover portion generates submodule 601 and can wrap
It includes:
Third acquiring unit, for obtaining the multiple points of interest for meeting preset range at a distance from the first place;
Third crosses section section generation unit, for using second place as the point of interest in first place, description to be each
The interest point information of point of interest generates the mistake between the corresponding paragraph in first place paragraph corresponding with second place
Cross section.
The function of each module in each device of the embodiment of the present invention may refer to the corresponding description in the above method, herein not
It repeats again.
Fig. 7 shows the structural block diagram of article generating device according to an embodiment of the present invention.As shown in fig. 7, the equipment can be with
Include: memory 701 and processor 702, the computer program that can be run on processor 702 is stored in memory 701.Institute
State the article generation method realized in above-described embodiment when processor 702 executes the computer program.701 He of memory
The quantity of processor 702 can be one or more.
The equipment can also include:
Communication interface 703 carries out data interaction for being communicated with external device.
Memory 701 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-
Volatile memory), a for example, at least magnetic disk storage.
If memory 701, processor 702 and the independent realization of communication interface 703, memory 701,702 and of processor
Communication interface 703 can be connected with each other by bus and complete mutual communication.The bus can be Industry Standard Architecture
Structure (ISA, Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral
Component Interconnect) bus or extended industry-standard architecture (EISA, Extended Industry
Standard Architecture) bus etc..The bus can be divided into address bus, data/address bus, control bus etc..For
Convenient for indicating, only indicated with a thick line in Fig. 7, it is not intended that an only bus or a type of bus.
Optionally, in specific implementation, if memory 701, processor 702 and communication interface 703 are integrated in one piece of core
On piece, then memory 701, processor 702 and communication interface 703 can complete mutual communication by internal interface.
The embodiment of the invention provides a kind of computer readable storage mediums, are stored with computer program, the program quilt
Processor realizes any method in above-described embodiment when executing.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden
It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise
Clear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable read-only memory
(CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other suitable Jie
Matter, because can then be edited, be interpreted or when necessary with other for example by carrying out optical scanner to paper or other media
Suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In readable storage medium storing program for executing.The storage medium can be read-only memory, disk or CD etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement,
These should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claim
It protects subject to range.
Claims (13)
1. a kind of article generation method characterized by comprising
Determine that article to be generated needs each place for including according to track;
Paragraph corresponding with each place is generated according to the first information in each place;
According to sequence of the place on track, determine that the corresponding paragraph in the place is suitable in the article to be generated
Sequence;
Each paragraph is combined according to the sequence of each paragraph to generate article.
2. the method according to claim 1, wherein the first information includes text information and candidate image,
Paragraph corresponding with each place is generated according to the first information in each place, comprising:
Obtain an at least candidate image corresponding with the place;
Obtain a plurality of types of text informations corresponding with the place;
According to the type of the text information, sequence of the text information in the corresponding paragraph in the place is determined;
It is inserted into the candidate image between different types of text information, generates paragraph corresponding with the place.
3. according to the method described in claim 2, it is characterized in that, obtaining at least one corresponding with the place candidate figure
Picture, comprising:
Detect whether the corresponding quantity for uploading image in the place meets preset value;
If it is not, then obtaining candidate image corresponding with the place from knowledge mapping.
4. according to the method described in claim 2, it is characterized in that, the first information further includes the image of the candidate image
Recommended information generates paragraph corresponding with each place according to the first information in each place, further includes:
Identify the entity information in the candidate image;
It is that described image recommended information is added in the candidate image according to the entity information.
5. according to the method described in claim 2, it is characterized in that, obtaining a plurality of types of text letters corresponding with the place
Breath, including at least two in following manner:
The text information of basic content type is obtained from map client database;
The text information of encyclopaedia type is obtained from knowledge mapping;
Obtain the text information of strategy type.
6. method according to any one of claims 1 to 5, which is characterized in that combine each paragraph according to the sequence of each paragraph
To generate article, comprising:
According to second information in the corresponding place of two neighboring paragraph, the changeover portion between two neighboring paragraph is generated;
Each paragraph is combined according to the sequence of each paragraph, and adds corresponding changeover portion between two neighboring paragraph, to generate
State article.
7. according to the method described in claim 6, it is characterized in that, second information includes coordinate, according to two neighboring section
The second information for falling corresponding place, generates the changeover portion between two neighboring paragraph, comprising:
Obtain corresponding first tracing point in the first place and the second place and the second tracing point;
First tracing point and second tracing point are separately converted to the first coordinate and the second coordinate, first coordinate
It is latitude and longitude coordinates with second coordinate;
According to first coordinate and second coordinate, the distance between first place and second place are determined;
According to the distance between first place and second place, generate the corresponding paragraph in first place with it is described
Changeover portion between the corresponding paragraph in second place.
8. according to the method described in claim 6, it is characterized in that, second information includes feature label, according to adjacent two
Second information in the corresponding place of a paragraph, generates the changeover portion between two neighboring paragraph, comprising:
At least one candidate label in the place is obtained from map client database and/or knowledge mapping;
If candidate's label have it is multiple, according to different degree of each candidate label in multiple candidate labels from multiple times
Select the characteristics of place is chosen in label label;
According to label the characteristics of label the characteristics of the first place and the second place, the corresponding paragraph in first place and institute are generated
State the changeover portion between the corresponding paragraph in the second place.
9. according to the method described in claim 6, it is characterized in that, second information includes interest point information, according to adjacent
Second information in the corresponding place of two paragraphs, generates the changeover portion between two neighboring paragraph, comprising:
Obtain the multiple points of interest for meeting preset range at a distance from the first place;
Using second place as the point of interest in first place, the interest point information of each point of interest described, described in generation
Changeover portion between the corresponding paragraph in first place paragraph corresponding with second place.
10. a kind of article generating means characterized by comprising
Location-determining module, for determining that article to be generated needs each place for including according to track;
Paragraph generation module, for generating paragraph corresponding with each place according to the first information in each place;
Sequence determining module determines the corresponding paragraph in the place described for the sequence according to the place on track
Sequence in article to be generated;
Composite module combines each paragraph for the sequence according to each paragraph to generate article.
11. device according to claim 10, which is characterized in that the composite module includes:
Changeover portion generates submodule, for the second information according to the corresponding place of two neighboring paragraph, generates adjacent two
Changeover portion between a paragraph;
Combination addition submodule for combining each paragraph according to the sequence of each paragraph, and adds phase between two neighboring paragraph
The changeover portion answered, to generate the article.
12. a kind of article generating device characterized by comprising
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors
Realize method as claimed in any one of claims 1-9 wherein.
13. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the program is held by processor
Method as claimed in any one of claims 1-9 wherein is realized when row.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910536677.XA CN110245339B (en) | 2019-06-20 | 2019-06-20 | Article generation method, article generation device, article generation equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910536677.XA CN110245339B (en) | 2019-06-20 | 2019-06-20 | Article generation method, article generation device, article generation equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110245339A true CN110245339A (en) | 2019-09-17 |
CN110245339B CN110245339B (en) | 2023-04-18 |
Family
ID=67888498
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910536677.XA Active CN110245339B (en) | 2019-06-20 | 2019-06-20 | Article generation method, article generation device, article generation equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110245339B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021115144A1 (en) * | 2019-12-13 | 2021-06-17 | 汉海信息技术(上海)有限公司 | Publishing of social information |
CN113807055A (en) * | 2021-09-22 | 2021-12-17 | 北京百度网讯科技有限公司 | Method and apparatus for editing information |
Citations (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05181855A (en) * | 1991-09-04 | 1993-07-23 | Fujitsu Ltd | Data registration backup device |
US6279017B1 (en) * | 1996-08-07 | 2001-08-21 | Randall C. Walker | Method and apparatus for displaying text based upon attributes found within the text |
JP2009223446A (en) * | 2008-03-14 | 2009-10-01 | Mitsubishi Space Software Kk | Data distribution device, data distribution method and data distribution program |
CN101694669A (en) * | 2009-10-16 | 2010-04-14 | 北京灵图软件技术有限公司 | Pace note making method, device thereof, pace note making and sharing system |
US20110282649A1 (en) * | 2010-05-13 | 2011-11-17 | Rene Waksberg | Systems and methods for automated content generation |
CN103246710A (en) * | 2013-04-22 | 2013-08-14 | 张经纶 | Method and device for automatically generating multimedia travel notes |
US20140181645A1 (en) * | 2012-12-21 | 2014-06-26 | Microsoft Corporation | Semantic searching using zoom operations |
CN104331515A (en) * | 2014-11-27 | 2015-02-04 | 惠州Tcl移动通信有限公司 | Method and system for generating travel journal automatically |
CN106248072A (en) * | 2016-07-15 | 2016-12-21 | 上海跑下去网络科技有限公司 | A kind of processing method of interesting electronics road book |
CN106462888A (en) * | 2014-05-28 | 2017-02-22 | 富士通株式会社 | Ordering program, ordering device, and ordering method |
CN106663087A (en) * | 2014-10-01 | 2017-05-10 | 株式会社日立制作所 | Text generation system |
US20170169032A1 (en) * | 2015-12-12 | 2017-06-15 | Hewlett-Packard Development Company, L.P. | Method and system of selecting and orderingcontent based on distance scores |
CN106933789A (en) * | 2015-12-30 | 2017-07-07 | 阿里巴巴集团控股有限公司 | Tourism strategy generation method and generation system |
CN106970898A (en) * | 2017-03-31 | 2017-07-21 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating article |
CN107066622A (en) * | 2017-05-11 | 2017-08-18 | 山东慧行天下文化传媒有限公司 | Play personal letter automatic creation system and method based on intelligent guide guide system |
CN107145482A (en) * | 2017-03-28 | 2017-09-08 | 百度在线网络技术(北京)有限公司 | Article generation method and device, equipment and computer-readable recording medium based on artificial intelligence |
WO2018092016A1 (en) * | 2016-11-19 | 2018-05-24 | Yogesh Chunilal Rathod | Providing location specific point of interest and guidance to create visual media rich story |
CN108268613A (en) * | 2017-12-29 | 2018-07-10 | 广州都市圈网络科技有限公司 | Tour schedule generation method, electronic equipment and storage medium based on semantic analysis |
WO2018150244A1 (en) * | 2017-02-18 | 2018-08-23 | Yogesh Chunilal Rathod | Registering, auto generating and accessing unique word(s) including unique geotags |
CN109388708A (en) * | 2018-06-15 | 2019-02-26 | 云天弈(北京)信息技术有限公司 | A kind of personalized customization authoring system |
CN109446505A (en) * | 2018-10-31 | 2019-03-08 | 广东小天才科技有限公司 | A kind of model essay generation method and system |
CN109614558A (en) * | 2018-12-10 | 2019-04-12 | 湘潭大学 | A kind of more locating travel log automatic generation methods and system |
CN109657043A (en) * | 2018-12-14 | 2019-04-19 | 北京百度网讯科技有限公司 | Automatically generate the method, apparatus, equipment and storage medium of article |
CN109743589A (en) * | 2018-12-26 | 2019-05-10 | 百度在线网络技术(北京)有限公司 | Article generation method and device |
US20190147042A1 (en) * | 2017-11-14 | 2019-05-16 | Microsoft Technology Licensing, Llc | Automated travel diary generation |
CN109784165A (en) * | 2018-12-12 | 2019-05-21 | 平安科技(深圳)有限公司 | Generation method, device, terminal and the storage medium of poem content |
-
2019
- 2019-06-20 CN CN201910536677.XA patent/CN110245339B/en active Active
Patent Citations (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05181855A (en) * | 1991-09-04 | 1993-07-23 | Fujitsu Ltd | Data registration backup device |
US6279017B1 (en) * | 1996-08-07 | 2001-08-21 | Randall C. Walker | Method and apparatus for displaying text based upon attributes found within the text |
JP2009223446A (en) * | 2008-03-14 | 2009-10-01 | Mitsubishi Space Software Kk | Data distribution device, data distribution method and data distribution program |
CN101694669A (en) * | 2009-10-16 | 2010-04-14 | 北京灵图软件技术有限公司 | Pace note making method, device thereof, pace note making and sharing system |
US20110282649A1 (en) * | 2010-05-13 | 2011-11-17 | Rene Waksberg | Systems and methods for automated content generation |
US20140181645A1 (en) * | 2012-12-21 | 2014-06-26 | Microsoft Corporation | Semantic searching using zoom operations |
CN103246710A (en) * | 2013-04-22 | 2013-08-14 | 张经纶 | Method and device for automatically generating multimedia travel notes |
CN106462888A (en) * | 2014-05-28 | 2017-02-22 | 富士通株式会社 | Ordering program, ordering device, and ordering method |
CN106663087A (en) * | 2014-10-01 | 2017-05-10 | 株式会社日立制作所 | Text generation system |
CN104331515A (en) * | 2014-11-27 | 2015-02-04 | 惠州Tcl移动通信有限公司 | Method and system for generating travel journal automatically |
US20170169032A1 (en) * | 2015-12-12 | 2017-06-15 | Hewlett-Packard Development Company, L.P. | Method and system of selecting and orderingcontent based on distance scores |
CN106933789A (en) * | 2015-12-30 | 2017-07-07 | 阿里巴巴集团控股有限公司 | Tourism strategy generation method and generation system |
CN106248072A (en) * | 2016-07-15 | 2016-12-21 | 上海跑下去网络科技有限公司 | A kind of processing method of interesting electronics road book |
WO2018092016A1 (en) * | 2016-11-19 | 2018-05-24 | Yogesh Chunilal Rathod | Providing location specific point of interest and guidance to create visual media rich story |
WO2018150244A1 (en) * | 2017-02-18 | 2018-08-23 | Yogesh Chunilal Rathod | Registering, auto generating and accessing unique word(s) including unique geotags |
CN107145482A (en) * | 2017-03-28 | 2017-09-08 | 百度在线网络技术(北京)有限公司 | Article generation method and device, equipment and computer-readable recording medium based on artificial intelligence |
CN106970898A (en) * | 2017-03-31 | 2017-07-21 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating article |
CN107066622A (en) * | 2017-05-11 | 2017-08-18 | 山东慧行天下文化传媒有限公司 | Play personal letter automatic creation system and method based on intelligent guide guide system |
US20190147042A1 (en) * | 2017-11-14 | 2019-05-16 | Microsoft Technology Licensing, Llc | Automated travel diary generation |
CN108268613A (en) * | 2017-12-29 | 2018-07-10 | 广州都市圈网络科技有限公司 | Tour schedule generation method, electronic equipment and storage medium based on semantic analysis |
CN109388708A (en) * | 2018-06-15 | 2019-02-26 | 云天弈(北京)信息技术有限公司 | A kind of personalized customization authoring system |
CN109446505A (en) * | 2018-10-31 | 2019-03-08 | 广东小天才科技有限公司 | A kind of model essay generation method and system |
CN109614558A (en) * | 2018-12-10 | 2019-04-12 | 湘潭大学 | A kind of more locating travel log automatic generation methods and system |
CN109784165A (en) * | 2018-12-12 | 2019-05-21 | 平安科技(深圳)有限公司 | Generation method, device, terminal and the storage medium of poem content |
CN109657043A (en) * | 2018-12-14 | 2019-04-19 | 北京百度网讯科技有限公司 | Automatically generate the method, apparatus, equipment and storage medium of article |
CN109743589A (en) * | 2018-12-26 | 2019-05-10 | 百度在线网络技术(北京)有限公司 | Article generation method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021115144A1 (en) * | 2019-12-13 | 2021-06-17 | 汉海信息技术(上海)有限公司 | Publishing of social information |
CN113807055A (en) * | 2021-09-22 | 2021-12-17 | 北京百度网讯科技有限公司 | Method and apparatus for editing information |
Also Published As
Publication number | Publication date |
---|---|
CN110245339B (en) | 2023-04-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Netzel et al. | User performance and reading strategies for metro maps: An eye tracking study | |
Murrieta-Flores et al. | GIS and Literary History: Advancing Digital Humanities research through the Spatial Analysis of historical travel writing and topographical literature | |
Preuss | The conceptualisation and measurement of mega sport event legacies | |
Ooms et al. | Listen to the map user: cognition, memory, and expertise | |
CN104794171B (en) | Mark the method and device of picture geographical location information | |
Kent | Trust me, I’ma cartographer: Post-truth and the problem of acritical cartography | |
CN110647886A (en) | Interest point marking method and device, computer equipment and storage medium | |
CN109710705A (en) | Map point of interest treating method and apparatus | |
Giardina et al. | Physical culture, ethnography and the body: Theory, method and praxis | |
Wood | Visualizing personal progress in participatory sports cycling events | |
Wang et al. | Hierarchical route maps for efficient navigation | |
CN110245339A (en) | Article generation method, device, equipment and storage medium | |
CN109388725A (en) | The method and device scanned for by video content | |
Lloyd et al. | Cartographic veracity in medieval mapping: analyzing geographical variation in the Gough Map of Great Britain | |
Roby | Experiencing geometry in Roman surveyors’ texts | |
Tateosian et al. | Story-telling maps generated from semantic representations of events | |
JP2013232238A5 (en) | Live video providing system | |
Edler et al. | Elevating streets in urban topographic maps improves the speed of map-reading | |
Zohar et al. | GIScience integrated with computer vision for the examination of old engravings and drawings | |
Blaise et al. | Citizen contributions and minor heritage: feedback on modeling and visualising an information mash-up | |
Yifei et al. | RESEARCH ON VISUALLY PERCEIVED IMAGE AND STRATEGIES FOR VISTA VIEW SYSTEM IMPROVEMENT OF THE JINSITAO WATERFRONT OF SHICHAHAI IN BEIJING. | |
Bianchetti | Raisz’s physiographic method of landform mapping | |
Field | Gravity is your friend but every turn is a leap of faith: Design and testing a schematic map for ski resort trails | |
WO2019030551A1 (en) | Method for applying metadata to immersive media files | |
Huth et al. | Judging and Visualizing the Quality of Spatio-Temporal Data on the Kakamega-Nandi Forest Area in West Kenya |
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 |