CN110245339B - Article generation method, article generation device, article generation equipment and storage medium - Google Patents
Article generation method, article generation device, article generation equipment and storage medium Download PDFInfo
- Publication number
- CN110245339B CN110245339B CN201910536677.XA CN201910536677A CN110245339B CN 110245339 B CN110245339 B CN 110245339B CN 201910536677 A CN201910536677 A CN 201910536677A CN 110245339 B CN110245339 B CN 110245339B
- Authority
- CN
- China
- Prior art keywords
- information
- paragraphs
- place
- article
- generating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
Abstract
The embodiment of the invention provides an article generation method, an article generation device, article generation equipment and a storage medium, wherein the method comprises the following steps: determining each place which needs to be included in the article to be generated according to the track; generating paragraphs respectively corresponding to the places according to the first information of the places; determining the sequence of paragraphs corresponding to the places in the article to be generated according to the sequence of the places on the track; the paragraphs are combined in their order to generate the article. The method of the embodiment of the invention can efficiently and conveniently help the user to automatically generate the article.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to an article generation method, apparatus, device, and storage medium.
Background
Most of the current travel planning articles or tourist articles are edited manually, and are time-consuming and high in cost. There is a need for a simple and efficient method to assist a user in automatically generating a travel plan article or a travel note article.
Disclosure of Invention
The embodiment of the invention provides an article generation method, an article generation device, article generation equipment and a storage medium, and aims to solve one or more technical problems in the prior art.
In a first aspect, an embodiment of the present invention provides an article generation method, including:
determining each place which needs to be included in the article to be generated according to the track;
generating paragraphs respectively corresponding to the places according to the first information of the places;
determining the sequence of the paragraphs corresponding to the places in the article to be generated according to the sequence of the places on the track;
the paragraphs are combined in their order to generate the article.
In one embodiment, the first information includes text information and candidate images, and the generating of paragraphs corresponding to respective locations from the first information of the respective locations includes:
acquiring at least one candidate image corresponding to the place;
acquiring various types of character information corresponding to the places;
determining the sequence of the text information in the paragraph corresponding to the place according to the type of the text information;
and inserting the candidate image between different types of text information to generate a paragraph corresponding to the place.
In one embodiment, acquiring at least one candidate image corresponding to the location comprises:
detecting whether the number of uploaded images corresponding to the place meets a preset value or not;
and if not, acquiring a candidate image corresponding to the position from the knowledge graph.
In one embodiment, the first information further includes image introduction information of the candidate image, and the first information for each location generates a paragraph corresponding to each location, and the method further includes:
identifying entity information in the candidate image;
and adding the image introduction information to the candidate image according to the entity information.
In one embodiment, acquiring multiple types of text information corresponding to the location includes at least two of the following modes:
acquiring character information of a basic content type from a map database;
acquiring encyclopedic type character information from a knowledge graph;
and acquiring character information of the strategy type.
In one embodiment, combining paragraphs in their order to generate an article comprises:
generating a transition section between two adjacent paragraphs according to second information of the places corresponding to the two adjacent paragraphs respectively;
and combining the paragraphs according to the sequence of the paragraphs, and adding corresponding transition sections between two adjacent paragraphs to generate the article.
In an embodiment, the second information includes coordinates, and the generating a transition segment between two adjacent paragraphs according to the second information of the locations corresponding to the two adjacent paragraphs respectively includes:
acquiring a first track point and a second track point which respectively correspond to the first location and the second location;
respectively converting the first track point and the second track point into a first coordinate and a second coordinate, wherein the first coordinate and the second coordinate are longitude and latitude coordinates;
determining the distance between the first place and the second place according to the first coordinate and the second coordinate;
and generating a transition section between the paragraph corresponding to the first location and the paragraph corresponding to the second location according to the distance between the first location and the second location.
In one embodiment, the second information includes a feature tag, and the generating a transition segment between two adjacent paragraphs according to the second information of the locations corresponding to the two adjacent paragraphs respectively includes:
obtaining at least one candidate tag of the place from a map-side database and/or a knowledge graph;
if the candidate tags are multiple, selecting characteristic tags of the place from the multiple candidate tags according to the importance degree of each candidate tag in the multiple candidate tags;
and generating a transition section between the paragraph corresponding to the first place and the paragraph corresponding to the second place according to the feature label of the first place and the feature label of the second place.
In one embodiment, the second information includes interest point information, and the generating a transition segment between two adjacent paragraphs according to the second information of the locations corresponding to the two adjacent paragraphs respectively includes:
acquiring a plurality of interest points of which the distances from the first place accord with a preset range;
and taking the second location as the interest point of the first location, describing interest point information of each interest point, and generating a transition section between the paragraph corresponding to the first location and the paragraph corresponding to the second location.
In a second aspect, an embodiment of the present invention provides an article generating apparatus, including:
the position determining module is used for determining each position which needs to be included in the article to be generated according to the track;
the paragraph generating module is used for generating paragraphs respectively corresponding to the places according to the first information of the places;
the order determining module is used for determining the order of the paragraphs corresponding to the places in the article to be generated according to the order of the places on the track;
and the combining module is used for combining the paragraphs according to the sequence of the paragraphs to generate the article.
In one embodiment, the combination module comprises:
the transition section generation submodule is used for generating a transition section between two adjacent paragraphs according to second information of the places corresponding to the two adjacent paragraphs respectively;
and the combination and addition submodule is used for combining the paragraphs according to the sequence of the paragraphs and adding corresponding transition sections between two adjacent paragraphs to generate the article.
In a third aspect, an embodiment of the present invention provides an article generating device, where functions of the device may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described functions.
In one possible design, the apparatus includes a processor and a memory, the memory is used for storing a program supporting the apparatus to execute the article generation method, and the processor is configured to execute the program stored in the memory. The device may also include a communication interface for communicating with other devices or a communication network.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium for storing computer software instructions for an article generation apparatus, which includes a program for executing the article generation method described above.
The method of the embodiment of the invention determines the places required to be included by the article to be generated based on the track, generates the descriptive paragraphs of the places according to the first information of the places, further determines the sequence of each paragraph according to the track, and can automatically generate the article. The method of the embodiment of the invention can efficiently and conveniently help the user to generate the article.
The foregoing summary is provided for the purpose of description only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will be readily apparent by reference to the drawings and following detailed description.
Drawings
In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.
Fig. 1 shows a flowchart of an article generation method according to an embodiment of the present invention.
Fig. 2 shows a flowchart of an article generation method according to an embodiment of the present invention.
Fig. 3 shows a flowchart of an article generation method according to another implementation of an embodiment of the present invention.
Fig. 4-1 is a block diagram showing a structure of one of modules of an article generation apparatus according to an embodiment of the present invention.
Fig. 4-2 shows a block diagram of a structure of one of the modules of an article generating apparatus according to an embodiment of the present invention.
Fig. 4-3 are block diagrams showing the structure of one of the modules of an article generation apparatus according to an embodiment of the present invention.
Fig. 4-4 are block diagrams showing the structure of one of the modules of an article generation apparatus according to an embodiment of the present invention.
Fig. 5 is a block diagram showing the structure of an article generation apparatus according to an embodiment of the present invention.
Fig. 6 is a block diagram showing a configuration of an article generation apparatus in an embodiment according to an embodiment of the present invention.
Fig. 7 shows a block diagram of the structure of an article generation apparatus according to an embodiment of the present invention.
Detailed Description
In the following, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.
Fig. 1 shows a flowchart of an article generation method according to an embodiment of the present invention. As shown in fig. 1, the article generation method according to the embodiment of the present invention may include:
and S101, determining each place which needs to be included in the article to be generated according to the track.
In this embodiment, the track may be a to-be-traveled track planned by the user, or may be a play route after the user has traveled. The track points on the track are arranged according to the planning sequence or the actual playing sequence. The track points correspond to corresponding places, and the places required to be included in the article to be generated can be determined according to the track points.
In step S102, paragraphs corresponding to the respective locations are generated based on the first information of the respective locations.
That is, for each location, the paragraph corresponding to the location may be generated according to the first information of the location. The paragraph may be one or more segments, and this embodiment is not limited. Each paragraph is used to describe a place.
The first information may include text information and candidate images. The text information may include at least one of basic content type text information, encyclopedia type text information, and strategy type text information.
The text information of the basic content type may include a name, an address, an open time, a rating, ticket information, and the like. In one embodiment, the text information of the basic content type can be obtained from a map-side database. The map terminal may be a map-type Application (APP). The map-side database may include map data, names of places on the map, addresses, opening times, evaluations, ticket information, and the like.
In one embodiment, encyclopedic-type textual information may be obtained from a knowledge graph. The knowledge graph combines theories and methods of applying subjects such as mathematics, graphics, information visualization technology, information science and the like with methods such as metrology citation analysis, co-occurrence analysis and the like, and utilizes the visualized graph to vividly show the core structure, development history, frontier field and overall knowledge framework of the subjects so as to achieve the modern theory of multi-subject fusion. In this embodiment, the knowledge graph may include various encyclopedic data on the internet in addition to the visualized graph.
In one example, encyclopedia data in the form of a web page may be parsed to extract textual information of the encyclopedia type. If the content of the extracted text information is large, for example, the number of words or the number of sentences exceeds a set value, a part (for example, 50 words or 3 sentences) of the extracted text information can be cut out to obtain encyclopedic type text information for generating articles.
In one embodiment, the text information of the strategy type can be obtained from a travel website or a tourist article on the internet.
The candidate image may be an image uploaded by the user. In one example, the method of this embodiment may match a place for the image according to the location information carried in the uploaded image and the location information of each place. The position information carried in the image can be generated by the position of the shooting equipment of the image during shooting, and can also be determined according to an entity with geographical identification in the image. In another example, one location may be matched for an image according to location information specified by a user for the image and location information of each location. The candidate images may also be images taken from a knowledge-graph. Further, low quality images obtained from the knowledge-graph may be filtered out. The low quality image may include an image with an advertisement or trademark (logo), and may also include an image with unclear low resolution or the like.
In one example, the text information obtained may be of only one type or two types, and then the candidate image may be inserted after or before the text information to generate the paragraph. Alternatively, a candidate image is inserted between the two types of character information to generate a paragraph.
In one embodiment, as shown in fig. 2, step S102 may include:
step S201, acquiring at least one candidate image corresponding to the place;
step S202, acquiring various types of character information corresponding to the places;
step S203, determining the sequence of the text information in the paragraph corresponding to the place according to the type of the text information;
and S204, inserting the candidate images among different types of character information to generate a paragraph corresponding to the place.
That is, if the acquired text information includes more than two (including two) types of text information, the order of the text information in the paragraph may be determined according to the types of the text information, and one or more candidate images may be inserted between adjacent types of text information to generate the paragraph.
For example: taking the encyclopedic type character information as a first section in the paragraph, and inserting 1-3 candidate pictures after the first section; taking the text information of the basic content type as a second section in the paragraph, and inserting 1-2 other candidate pictures behind the second section; and taking the character information of the strategy type as a third section in the paragraph, and inserting the candidate image after the third section or not inserting the candidate image.
It should be noted that the candidate images are not inserted between every two adjacent types of text information, and may be set according to the number of the candidate images.
In one embodiment, step S201 may include: detecting whether the number of uploaded images corresponding to the place meets a preset value or not; and if not, acquiring a candidate image corresponding to the position from the knowledge graph.
If the number of uploaded images uploaded by a user corresponding to a certain location meets a preset value, namely the number of uploaded images is large, the uploaded images can be used as candidate images. If the number of uploaded images corresponding to a certain location does not meet a preset value, such as a small number or no number, candidate images corresponding to the location can be obtained from the knowledge graph.
In one embodiment, the first information may further include image introduction information of the candidate image. Step S102 may further include: identifying entity information in the candidate image; and adding the image introduction information to the candidate image according to the entity information.
For example: the entity in the candidate image can be identified based on a model such as a Region-Convolutional Neural network (R-CNN) or a primary identification model (YOLO) or a Single Shot multi-box Detector (SSD), so as to obtain entity information. Then, image introduction information is added above or below the candidate image according to the entity information. For example: if a misery is identified in the candidate image, the image introduction information "misery" may be added below the candidate image. Another example is: if the sunset and the palace are identified in the candidate image, image introduction information "the palace under sunset" may be added below the candidate image.
As shown in fig. 1, the article generation method according to the embodiment of the present invention further includes:
step S103, determining the sequence of the paragraphs corresponding to the places in the article to be generated according to the sequence of the places on the track;
and step S104, combining the paragraphs according to the sequence of the paragraphs to generate the article.
Each place corresponds to a track point, the sequence of paragraphs of the corresponding place in the article to be generated can be determined according to the sequence of the track points on the track, and then the paragraphs are combined according to the sequence of the paragraphs to generate the article, such as a travel planning article or a tourist note article.
In one embodiment, as shown in fig. 3, step S104 may include:
step S301, generating a transition section between two adjacent paragraphs according to second information of the places corresponding to the two adjacent paragraphs respectively;
step S302, combining the paragraphs according to the sequence of the paragraphs, and adding corresponding transition sections between two adjacent paragraphs to generate the article.
That is, after the order of the paragraphs is determined, a transition segment may be added between two adjacent paragraphs, such as a first paragraph and a second paragraph, to generate an article. The first section corresponds to a first place, and the second section corresponds to a second place. And generating a transition section between the first section and the second section according to the second information of the first place and the second information of the second place. The second information may include coordinates, feature tags, point of interest information, and the like.
In one embodiment, step S301 may include: acquiring a first track point and a second track point which respectively correspond to the first location and the second location; respectively converting the first track points and the second track points into first coordinates and second coordinates, wherein the first coordinates and the second coordinates are longitude and latitude coordinates; determining a distance between the first location and the second location according to the first coordinate and the second coordinate; and generating a transition section between the paragraph corresponding to the first location and the paragraph corresponding to the second location according to the distance between the first location and the second location.
In one example, the track point may be selected from a map or from a menu provided by the APP by the user, and therefore, the track point selected by the user needs to be converted into a coordinate that can be recognized by the map end APP, such as a mercator coordinate. In another example, coordinates that the map end APP can recognize may be converted into longitude and latitude coordinates. Therefore, the coordinates of the present embodiment may be mercator coordinates, and may also be latitude and longitude coordinates.
Further, a distance between the first location and the second location may be determined according to the first coordinate and the second coordinate, thereby generating a transition segment between the first paragraph and the second paragraph. For example: if the distance between the first location and the second location is 10 km, the transition segment between the first segment and the second segment may be "at 10 km from the first location, and also the second location".
In one embodiment, step S301 may include: obtaining at least one candidate tag of the place from a map-side database and/or a knowledge graph; if the candidate tags are multiple, selecting characteristic tags of the place from the multiple candidate tags according to the importance degree of each candidate tag in the multiple candidate tags; and generating a transition section between the paragraph corresponding to the first place and the paragraph corresponding to the second place according to the feature label of the first place and the feature label of the second place.
In one example, if there are multiple candidate tags for a location, a best tag can be selected from the multiple candidate tags as the feature tag of the location according to the features of the candidate tags. For example: the Term Frequency (TF) -Inverse text Frequency Index (IDF) value of each candidate tag can be used as the importance of the candidate tag, and the feature tag is determined according to the TF-IDF value of each candidate tag. In another example, if there is only one candidate tag for a location, the candidate tag can be directly used as the feature tag of the location.
And further, generating a transition section between the first section and the second section according to the characteristic label of the first place and the characteristic label of the second place. For example: the feature label of the first place is a landscape victory place, and the feature label of the second place is a human victory place, and the transition section between the first section and the second section may be "after visiting the landscape victory place of the first place, visit the human victory place, such as the second place".
In one embodiment, step S301 may include: acquiring a plurality of interest points of which the distances from the first place accord with a preset range; and taking the second location as the interest point of the first location, describing interest point information of each interest point, and generating a transition section between the paragraph corresponding to the first location and the paragraph corresponding to the second location.
The points of Interest (Point of Interest) around each location can be obtained from the map-side database. For example: and taking the place with the distance from the first place within the preset range as the POI of the first place. Further, a second location may be used as the POI of the first location, and a transition between the first paragraph and the second paragraph is generated, such as "there is a second location around the first location".
In the embodiment of the invention, the travel planning article can be generated according to the to-be-traveled path planned by the user, and the travel memory article can also be generated according to the playing route of the user. The location may be a sight. It should be noted that, in the embodiment of the present invention, the scenic spots include, but are not limited to, pay scenic spots, free scenic spots, locations for users to play, and the like. In the following, the scenic spot is taken as an example to describe the article generation apparatus according to the embodiment of the present invention, and the APP may execute any of the above-described article generation methods.
As shown in fig. 4-1, the article generating device may include a user data processing module for receiving data uploaded by a user. The data uploaded by the user may include track information (e.g., track points selected by the user) and picture information (e.g., uploaded images). In one example, the method of the embodiment of the present invention may use an Engine X (Engine X, NGINX) as a background service, receive a request sent by a user in real time, and obtain data uploaded by the user from the request.
The user data processing module may also be configured to pre-process the trajectory information. For example: and converting the track points into coordinates which can be identified by the map end APP. The user data processing module can also be used for preprocessing the picture information. For example: and identifying entity information in the uploaded image for subsequent article generation. The user data processing module may also be used for picture mapping. For example: and aggregating the uploaded images belonging to the same track point according to the position information of the uploaded images and the position information of the track point (or the scenic spot) to obtain one or more uploaded images belonging to the same track point.
As shown in fig. 4-2, the article generating apparatus may further include a map-end data processing module, configured to obtain each sight spot according to a user track (track information), and obtain basic information (text information of a basic content type) of the sight spot from a map-end database. Such as the name, address, open time, rating, ticket information, etc. of the attraction. The map end data processing module can also be used for converting coordinates which can be identified by the map end APP, such as mercator coordinates, into longitude and latitude coordinates (positions of scenic spots) for subsequent article generation. The map-side data processing module may also be configured to determine sight tags (feature tags for sights) based on the TF-IDF values of the candidate tags for sights. Further, the attraction standard data may include attraction base information, attraction tags, and attraction locations.
As shown in fig. 4-3, the article generation apparatus may further include a knowledge map data processing module, configured to obtain scenic spot encyclopedia (encyclopedia type text information), scenic spot pictures (candidate images), scenic spot surroundings (POI), scenic spot skimming (skimming type text information), and other scenic spot related data (other types of text information) according to the scenic spot name.
As shown in fig. 4-4, the article generating apparatus may further include a text generating module, configured to sort the scenic spots according to the sequence of the track points in the user track. The word generation module may also be used to generate a first segment of an article. For example: the method comprises the steps of obtaining travel note type related articles on the internet, taking the head section of the articles as a reference, further generating a plurality of section head templates, and further generating the head section of the articles based on the section head templates. The text generation module may also be used to generate a transition segment between two sights and to generate a sight paragraph for each sight. Further, the word generation module can be used for generating article titles. For example: the title designated by the user may be used as the title of the article, or the title of the article may be generated according to a preset template.
It should be noted that the scenic spots in the article generation apparatus are only examples of one type of location, that is, in the above description, the scenic spots may be replaced with locations.
When people travel, people like to record what people see during travel, some are pictures and some are texts, and finally the combined concept of the pictures and the texts is converted into a travel record article. There is currently no method for automatically generating these types of articles.
The method of the embodiment of the invention can automatically generate the article by determining the places to be included in the article to be generated based on the track information, generating the descriptive paragraphs of the places according to the first information of the places and further determining the sequence of each paragraph according to the track information. Furthermore, the section between the two places can be generated according to the second information of the two places, so that the generated article is smoother and smoother. When the first information and the second information are obtained, the knowledge graph can be based, so that materials of the generated article are enriched, and the generated article is more vivid and professional. The method of the embodiment of the invention can efficiently and conveniently help the user to generate the article, and solves various problems of long time consumption, difficult selection and the like of the user. Furthermore, the method provided by the embodiment of the invention can help the user generate the article belonging to the user in real time, can save the mementos or share the articles to friends, and can improve the commercial value of related products while meeting the requirements of the user on high-quality service.
Fig. 5 shows a resulting block diagram of an article generation apparatus according to an embodiment of the present invention. As shown in fig. 5, the apparatus may include:
a location determining module 501, configured to determine, according to the track, each location that the article to be generated needs to include;
a paragraph generating module 502, configured to generate paragraphs corresponding to the respective locations according to the first information of the respective locations;
a sequence determining module 503, configured to determine, according to a sequence of the location on the track, a sequence of the paragraph corresponding to the location in the article to be generated;
a combining module 504 for combining the paragraphs in order of the paragraphs to generate the article.
In one embodiment, the paragraph generation module 502 may include:
a first obtaining sub-module, configured to obtain at least one candidate image corresponding to the location;
the second acquisition submodule is used for acquiring various types of character information corresponding to the places;
the first determining submodule is used for determining the sequence of the text information in the paragraph corresponding to the place according to the type of the text information;
and the inserting sub-module is used for inserting the candidate images among different types of text information to generate paragraphs corresponding to the places.
In one embodiment, the first obtaining sub-module may include:
the detection unit is used for detecting whether the number of uploaded images corresponding to the place meets a preset value or not;
and the acquisition unit is used for acquiring the candidate image corresponding to the position from the knowledge graph in the negative condition.
In one embodiment, the first information further includes image introduction information of the candidate image, and the paragraph generation module 502 may include:
the identification sub-module is used for identifying entity information in the candidate image;
and the adding sub-module is used for adding the image introduction information to the candidate image according to the entity information.
In one embodiment, the second acquisition submodule may be used in at least two of the following ways:
acquiring character information of basic content types from a map database;
acquiring encyclopedic type text information from a knowledge graph;
and acquiring character information of the strategy type.
In one embodiment, as shown in fig. 6, the combining module 504 may include:
the transition section generation submodule 601 is configured to generate a transition section between two adjacent paragraphs according to second information of locations corresponding to the two adjacent paragraphs respectively;
and the combination adding sub-module 602 is configured to combine the paragraphs according to the order of the paragraphs, and add a corresponding transition segment between two adjacent paragraphs to generate the article.
In one embodiment, the second information includes coordinates, and the transition segment generation sub-module 601 may include:
the first acquisition unit is used for acquiring a first track point and a second track point which respectively correspond to the first place and the second place;
the conversion unit is used for converting the first track points and the second track points into first coordinates and second coordinates respectively, and the first coordinates and the second coordinates are longitude and latitude coordinates;
a distance determining unit configured to determine a distance between the first location and the second location according to the first coordinate and the second coordinate;
and the first transition section generating unit is used for generating a transition section between the paragraph corresponding to the first location and the paragraph corresponding to the second location according to the distance between the first location and the second location.
In one embodiment, the second information includes a feature tag, and the transition segment generation sub-module 601 may include:
the second acquisition unit is used for acquiring at least one candidate label of the place from a map-side database and/or a knowledge graph;
the selecting unit is used for selecting the characteristic tags of the places from the candidate tags according to the importance degree of each candidate tag in the candidate tags under the condition that the candidate tags are multiple;
and the second transition section generating unit is used for generating a transition section between the paragraph corresponding to the first location and the paragraph corresponding to the second location according to the characteristic label of the first location and the characteristic label of the second location.
In one embodiment, the second information includes interest point information, and the transition segment generation sub-module 601 may include:
the third acquisition unit is used for acquiring a plurality of interest points of which the distances from the first place accord with a preset range;
and the third section generation unit is used for taking the second place as the interest point of the first place, describing the interest point information of each interest point and generating a transition section between the section corresponding to the first place and the section corresponding to the second place.
The functions of each module in each apparatus in the embodiments of the present invention may refer to the corresponding description in the above method, and are not described herein again.
Fig. 7 shows a block diagram of the structure of an article generation apparatus according to an embodiment of the present invention. As shown in fig. 7, the apparatus may include: a memory 701 and a processor 702, the memory 701 having stored therein a computer program operable on the processor 702. The processor 702, when executing the computer program, implements the article generation method in the above-described embodiments. The number of the memory 701 and the processor 702 may be one or more.
The apparatus may further include:
the communication interface 703 is used for communicating with an external device and performing data interactive transmission.
If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the memory 701, the processor 702 and the communication interface 703 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.
Optionally, in a specific implementation, if the memory 701, the processor 702, and the communication interface 703 are integrated on a chip, the memory 701, the processor 702, and the communication interface 703 may complete mutual communication through an internal interface.
An embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and the computer program is used for implementing the method of any one of the above embodiments when being executed by a processor.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried out in the method of implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (13)
1. An article generation method, comprising:
determining each place which needs to be included in the article to be generated according to the track;
generating paragraphs respectively corresponding to the places according to the first information of the places;
determining the sequence of the paragraphs corresponding to the places in the article to be generated according to the sequence of the places on the track;
combining the paragraphs according to the sequence of the paragraphs to generate an article;
the generating of paragraphs corresponding to the respective locations according to the first information of the respective locations includes:
acquiring various types of character information corresponding to the places; wherein the types include an encyclopedia type, a base content type, and an attack type;
and determining the sequence of the text information in the paragraph corresponding to the place according to the type of the text information.
2. The method according to claim 1, wherein the first information further includes candidate images, and the generating paragraphs respectively corresponding to the respective locations according to the first information of the respective locations comprises:
acquiring at least one candidate image corresponding to the place;
and inserting the candidate image between different types of text information to generate a paragraph corresponding to the place.
3. The method of claim 2, wherein obtaining at least one candidate image corresponding to the location comprises:
detecting whether the number of uploaded images corresponding to the place meets a preset value or not;
and if not, acquiring a candidate image corresponding to the position from the knowledge graph.
4. The method according to claim 2, wherein the first information further includes image introduction information of the candidate image, and wherein paragraphs respectively corresponding to the respective locations are generated based on the first information of the respective locations, and further comprising:
identifying entity information in the candidate image;
and adding the image introduction information to the candidate image according to the entity information.
5. The method of claim 2, wherein obtaining multiple types of textual information corresponding to the location comprises at least two of:
acquiring character information of a basic content type from a map database;
acquiring encyclopedic type character information from a knowledge graph;
and acquiring character information of the strategy type.
6. The method of any of claims 1 to 5, wherein combining paragraphs in order of paragraphs to generate an article comprises:
generating a transition section between two adjacent paragraphs according to second information of the places corresponding to the two adjacent paragraphs respectively;
and combining the paragraphs according to the sequence of the paragraphs, and adding corresponding transition sections between two adjacent paragraphs to generate the article.
7. The method according to claim 6, wherein the second information includes coordinates, and generating a transition segment between two adjacent paragraphs according to the second information of the locations corresponding to the two adjacent paragraphs respectively comprises:
acquiring a first track point and a second track point which respectively correspond to the first location and the second location;
respectively converting the first track point and the second track point into a first coordinate and a second coordinate, wherein the first coordinate and the second coordinate are longitude and latitude coordinates;
determining the distance between the first place and the second place according to the first coordinate and the second coordinate;
and generating a transition section between the paragraph corresponding to the first location and the paragraph corresponding to the second location according to the distance between the first location and the second location.
8. The method according to claim 6, wherein the second information includes a feature tag, and generating a transition segment between two adjacent paragraphs according to the second information of the locations corresponding to the two adjacent paragraphs respectively comprises:
obtaining at least one candidate tag of the place from a map-side database and/or a knowledge graph;
if the candidate tags are multiple, selecting characteristic tags of the place from the multiple candidate tags according to the importance degree of each candidate tag in the multiple candidate tags;
and generating a transition section between the paragraph corresponding to the first place and the paragraph corresponding to the second place according to the feature label of the first place and the feature label of the second place.
9. The method according to claim 6, wherein the second information includes interest point information, and generating a transition segment between two adjacent paragraphs according to the second information of the locations corresponding to the two adjacent paragraphs respectively comprises:
acquiring a plurality of interest points of which the distances from the first place accord with a preset range;
and taking a second place as the interest point of the first place, describing interest point information of each interest point, and generating a transition section between the paragraph corresponding to the first place and the paragraph corresponding to the second place.
10. An article generation apparatus, comprising:
the position determining module is used for determining each position which needs to be included in the article to be generated according to the track;
the paragraph generating module is used for generating paragraphs respectively corresponding to the places according to the first information of the places;
the order determining module is used for determining the order of the paragraphs corresponding to the places in the article to be generated according to the order of the places on the track;
the combination module is used for combining the paragraphs according to the sequence of the paragraphs to generate an article;
wherein the first information includes text information, and the paragraph generation module is specifically configured to:
acquiring various types of character information corresponding to the places; wherein the types include an encyclopedia type, a base content type, and an attack type;
and determining the sequence of the text information in the paragraph corresponding to the place according to the type of the text information.
11. The apparatus of claim 10, wherein the combining module comprises:
the transition section generation submodule is used for generating a transition section between two adjacent paragraphs according to second information of the places corresponding to the two adjacent paragraphs respectively;
and the combination and addition submodule is used for combining the paragraphs according to the sequence of the paragraphs and adding corresponding transition sections between two adjacent paragraphs to generate the article.
12. An article generation device, comprising:
one or more processors;
storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-9.
13. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 9.
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 CN110245339A (en) | 2019-09-17 |
| CN110245339B true 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) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111144076B (en) * | 2019-12-13 | 2023-06-02 | 汉海信息技术(上海)有限公司 | Social information publishing method and device |
| 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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009223446A (en) * | 2008-03-14 | 2009-10-01 | Mitsubishi Space Software Kk | Data distribution device, data distribution method and data distribution program |
| CN106462888A (en) * | 2014-05-28 | 2017-02-22 | 富士通株式会社 | Ordering program, ordering device, and ordering method |
| 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 |
Family Cites Families (22)
| 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 |
| CN101694669B (en) * | 2009-10-16 | 2012-07-04 | 北京灵图软件技术有限公司 | Pace note making method, device thereof, pace note making and sharing system |
| US8457948B2 (en) * | 2010-05-13 | 2013-06-04 | Expedia, Inc. | Systems and methods for automated content generation |
| US9576049B2 (en) * | 2012-12-21 | 2017-02-21 | Microsoft Technology Licensing, Llc | 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 |
| US10496756B2 (en) * | 2014-10-01 | 2019-12-03 | Hitachi, Ltd. | Sentence creation system |
| CN104331515B (en) * | 2014-11-27 | 2018-05-08 | 惠州Tcl移动通信有限公司 | A kind of method and system for automatically generating tourism diary |
| 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 |
| CN106933789B (en) * | 2015-12-30 | 2023-06-20 | 阿里巴巴集团控股有限公司 | Travel attack 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 |
| CN107145482B (en) * | 2017-03-28 | 2020-10-30 | 百度在线网络技术（北京）有限公司 | Article generation method and device based on artificial intelligence, equipment and readable medium |
| 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 |
| US10909321B2 (en) * | 2017-11-14 | 2021-02-02 | Microsoft Technology Licensing, Llc | Automated travel diary generation |
| CN108268613B (en) * | 2017-12-29 | 2022-07-08 | 广州都市圈网络科技有限公司 | Tourism journey generation method based on semantic analysis, electronic equipment and storage medium |
| CN109388708B (en) * | 2018-06-15 | 2022-05-31 | 云天弈（北京）信息技术有限公司 | Personalized customized writing 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 |
| CN109614558B (en) * | 2018-12-10 | 2021-01-12 | 湘潭大学 | Multi-positioning travel log automatic generation method 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 |
| CN109657043B (en) * | 2018-12-14 | 2022-01-04 | 北京百度网讯科技有限公司 | Method, device and equipment for automatically generating article and storage medium |
| CN109743589B (en) * | 2018-12-26 | 2021-12-14 | 百度在线网络技术（北京）有限公司 | Article generation method and device |
-
2019
- 2019-06-20 CN CN201910536677.XA patent/CN110245339B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009223446A (en) * | 2008-03-14 | 2009-10-01 | Mitsubishi Space Software Kk | Data distribution device, data distribution method and data distribution program |
| CN106462888A (en) * | 2014-05-28 | 2017-02-22 | 富士通株式会社 | Ordering program, ordering device, and ordering method |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110245339A (en) | 2019-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10387776B2 (en) | Recurrent neural network architectures which provide text describing images | |
| US20120016578A1 (en) | Outdoor to indoor navigation system | |
| CN109543680A (en) | Location determining method, appliance arrangement and the medium of point of interest | |
| Brabyn et al. | Using viewsheds, GIS, and a landscape classification to tag landscape photographs | |
| CN108229364B (en) | Building contour generation method and device, computer equipment and storage medium | |
| CN110245339B (en) | Article generation method, article generation device, article generation equipment and storage medium | |
| Rice et al. | Crowdsourced Geospatial Data: A report on the emerging phenomena of crowdsourced and user-generated geospatial data | |
| KR102195999B1 (en) | Method, device and system for processing image tagging information | |
| CN107909088B (en) | Method, apparatus, device and computer storage medium for obtaining training samples | |
| CN110659409B (en) | Point of interest (POI) recommendation method and device | |
| CN110647886A (en) | Interest point marking method and device, computer equipment and storage medium | |
| CN109710705A (en) | Map point of interest treating method and apparatus | |
| CN110727816A (en) | Method and device for determining interest point category | |
| CN108681393A (en) | Translation display methods, device, computing device and medium based on augmented reality | |
| CN111340015B (en) | Positioning method and device | |
| CN109858318A (en) | The classification recognition methods of landscape image and device | |
| CN109978430A (en) | A kind of method, apparatus, server and storage medium parsing station address | |
| CN108491387B (en) | Method and apparatus for outputting information | |
| CN110516162A (en) | A kind of information recommendation method, device, equipment and storage medium | |
| US20170169192A1 (en) | Inserting structured content in itemized reports | |
| CN112256967A (en) | Travel recommendation method, device, equipment and storage medium | |
| CN111143454A (en) | Text output method and device and readable storage medium | |
| JP2010128042A (en) | Map data management system | |
| CN111125272B (en) | Regional characteristic acquisition method, regional characteristic acquisition device, computer equipment and medium | |
| CN108874360B (en) | Panoramic content positioning method and device |
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 |