WO2017114177A1 - 旅游攻略生成方法和生成系统 - Google Patents
旅游攻略生成方法和生成系统 Download PDFInfo
- Publication number
- WO2017114177A1 WO2017114177A1 PCT/CN2016/110232 CN2016110232W WO2017114177A1 WO 2017114177 A1 WO2017114177 A1 WO 2017114177A1 CN 2016110232 W CN2016110232 W CN 2016110232W WO 2017114177 A1 WO2017114177 A1 WO 2017114177A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- travel
- strategy
- keyword
- template
- user
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/131—Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/174—Form filling; Merging
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Definitions
- the present application relates to the field of Internet information processing, and in particular, to a travel strategy generation method and generation system.
- an embodiment of the present application discloses a method for generating a travel strategy, including the following steps:
- a travel strategy is automatically generated.
- Another embodiment of the present application discloses a method for generating a travel strategy, including:
- a further embodiment of the present application discloses a travel strategy generation system, including:
- a keyword receiving module configured to receive at least one keyword input by a user
- a topic category determining module configured to match each of the keywords with pre-stored travel keywords to determine a topic category corresponding to each of the keywords
- the Raiders template selection module is configured to determine a current Raiders template from multiple Raider templates according to the matching result
- the travel strategy generating module is configured to automatically generate a travel strategy according to the keyword and the current strategy template.
- Another embodiment of the present application discloses a travel strategy generation system, including:
- the input interface provides a module for providing a keyword input interface for the user to input at least one keyword
- a keyword sending module configured to send the keyword input by the user to a server, where the server determines a topic category and a strategy template according to the keyword input by the user;
- the travel strategy receiving module is configured to receive a travel strategy generated by the server according to the keyword.
- the user is prevented from making a travel guide.
- the problem of time-consuming and laborious writing of a large amount of text improves the enthusiasm of the user to make a strategy.
- the embodiment of the present application can save a lot of time for making a strategy and improve efficiency.
- FIG. 1 is a flowchart of a travel strategy generation method according to a first embodiment of the present application.
- FIG. 2 is a block diagram of a travel strategy generation system of a second embodiment of the present application.
- FIG. 3 is a flowchart of a method for generating a travel strategy according to a third embodiment of the present application.
- FIG. 4 is a flowchart of a method for generating a travel strategy according to a fourth embodiment of the present application.
- FIG. 5 is a block diagram of a travel strategy generation system according to a fifth embodiment of the present application.
- FIG. 6 is a block diagram of a travel strategy generation system according to a sixth embodiment of the present application.
- FIG. 7 is a schematic flowchart of a method for generating a travel strategy according to an embodiment of the present application.
- FIG. 8 is a schematic diagram of input content and output content of a travel strategy generation method according to an embodiment of the present application.
- FIG. 9 is a schematic diagram of input content and output content of a travel strategy generation method according to an embodiment of the present application.
- One of the core ideas of the present application is to determine a topic category corresponding to each of the keywords by receiving at least one keyword input by the user and matching each of the keywords with the pre-stored travel topic keywords; Determining a current strategy template from a plurality of strategy templates; automatically generating a travel strategy according to the keyword and the current strategy template.
- the method and system for generating a travel strategy provided by the present application avoids a large number of textbooks that a user makes in a travel guide. The problem of writing time and effort has increased the enthusiasm of users to make strategies.
- FIG. 1 is a flowchart of a method for generating a travel strategy according to a first embodiment of the present application.
- the travel strategy generation method of the first embodiment of the present application can be applied to, for example, a server, and the method includes the following steps:
- Step S101 receiving at least one keyword input by a user
- the server may receive text input by the user having a plurality of keywords including, for example, travel routes, vehicles, meals, accommodation, and the like.
- the user can input text through the information input interface.
- FIG. 7 is a schematic diagram of input and output of the travel strategy generation method according to an embodiment of the present application.
- the prompt displayed on the input interface may be “Please input the tourist attraction in order, the vehicle is represented by brackets”, and the user may input the text according to the prompt, and the input text is for example “ Liulang Wenyu (walking) Jingci Temple (7 Road) Leifeng Pagoda, the text contains a number of keywords: Liulang Wenyu, walking, Jingci Temple, 7 Road, Leifeng Pagoda.
- the client sends the keyword to the server, and the server receives the keyword input by the user.
- Step S102 matching each of the keywords with the pre-stored travel subject words, and determining a topic category corresponding to each of the keywords;
- the server may pre-store a plurality of travel keywords, each of which corresponds to a topic category.
- the topic category corresponding to the travel keyword is the topic category corresponding to the keyword.
- one of the keywords input by the user is “Leifeng Tower”
- the theme category of the travel theme word “Leifeng Tower” pre-stored by the server is “attraction”, which can be used to determine the keyword “Leifeng Tower”.
- the subject category is "Attractions.” Another keyword input by the user is “7-way”, and the theme category corresponding to the tourist keyword “7-way” stored in the server is “vehicle”, and the theme category corresponding to the keyword “7-way” can be determined as “vehicle”. ". These travel keywords can be pre-stored in the server's database.
- Step S103 Determine, according to the matching result, a current strategy template from multiple attack templates.
- the current strategy template can be determined from multiple attack templates in the server according to the result of the keyword and the travel keyword matching.
- the text input by the user is “(7-way) Leifeng Pagoda”, and the server recognizes the keywords included in the “7-way” and “Leifeng Tower”.
- the three templates of the server are: “Sit () To ()”, “to () tasting ()”, “live in ()”, you can select the first template according to the result of the match, that is, "sit () to ()” as the current strategy template.
- Step S104 automatically generating a travel strategy according to the keyword and the current strategy template
- the server can input the "7 Way” and “Leifeng Tower” according to the keywords entered by the user, and the current Raiders template “Sit() to ()", respectively, “7 Way” and “Leifeng Tower” respectively Fill in the blank fill-in area of the current Raiders template, and automatically generate a “sit 7 to Leifeng Tower” travel guide.
- the method for generating a travel strategy proposed by the first embodiment of the present application can avoid the problem that the user writes a large amount of text in the travel strategy, which is time-consuming and laborious, and improves the enthusiasm of the user to make a strategy.
- the travel strategy generation method proposed by the embodiment of the present application can save a lot of time for making a strategy and improve efficiency.
- FIG. 2 is a flow chart showing a method for generating a travel strategy according to a second embodiment of the present application.
- the travel strategy generation method of the second embodiment of the present application can be applied to, for example, a server, and the method includes the following steps:
- multiple original Raiders texts can be obtained from the server's database.
- the database has stored the Raiders data under various categories; for example, if the classification is classified according to the tourist attractions of each city, the database stores data classified according to each tourist attraction of each city.
- the tourism subject words are extracted from each of the original Raiders texts, and a strategy template for at least one blank fill-in area is left after the travel theme is extracted. Extracting travel themes can be done by grammar The analysis identifies the nouns in the original Raiders text and other ways to achieve them.
- the original Raiders text of a certain paragraph is: “Take the train to Hangzhou East Railway Station, take the subway to Longxiang Bridge, walk out to the lakeside, and enjoy the delicious snacks in Hangzhou.
- Yongjinmen, to Liulang Wenyu tour to the Jingci Temple, Leifeng Tower, Taiziwan, Sudi, Huagang Guanyu, Tiger Run and Liuhe Tower, and finally take the 4 bus to a park, night view of West Lake Park Music Fountain, overnight in Hangzhou Dujinsheng Hotel.”
- the tourist keywords extracted from the above user input text include: “train”, “train east station”, “metro”, “longxiang bridge”, “lakeside”, “knowing taste”, “Hangzhou”, “West Lake” “Yongjinmen”, “Liu Lang Wen”, “Jingci Temple”, “Leifeng Tower”, “Prince Bay”, “Su Di”, “Huagang Guanyu”, “Tiger Run”, “Six Harmony Tower”, “ 4 Road”, “One Park”, “Three Parks”, “Music Fountain”, “Du Jinsheng Hotel”.
- the tourism keywords can be classified into different themes according to the theme category, such as: “train”, “train station”, “metro”, “longxiang bridge”, “lakeside”, “know” “View”, “West Lake”, “Yongjinmen” can be classified as “vehicle: train, subway”, “train station: East Railway Station”, “Station: Longxiang Bridge”, “Sights: Lakeside, West Lake, Yongjinmen “, Restaurant: Knowing the taste.”
- the vehicle, the train station and the scenic spot are the subject words.
- the relevant corpus and the current mature information extraction method can be utilized, and will not be described here.
- topic corpus list can have the following data form:
- step S201 after extracting the tourism keyword, the strategy template of the blank space with multiple blanks formed after extracting the tourism keyword is:
- each blank fill-in area is associated with the topic category corresponding to the travel subject word by the extracted travel subject words, for example, the travel keyword corresponding to the two blank fill-in areas in the first sentence of the strategy template is “ “Train” and “Hangzhou East railway Station”, the subject categories corresponding to the two tourism keywords are “vehicle” and “train station”, respectively, and the two blank fill-in areas in the first sentence of the strategy template are associated with The subject categories are "vehicle” and "train station”.
- S204 Receive at least one keyword input by a user.
- step S101 is the same as or similar to step S101 in the first embodiment, and details are not described herein again.
- step S204 may occur before any of the steps S201 to S203, or may occur simultaneously with any of the steps S201 to S203, and the present application does not limit the order in which the step S204 occurs, and the steps S201 to S203 Interrelationship.
- This step may be the same as or similar to step S102 in the first embodiment.
- the pre-stored travel topic may be a plurality of travel keywords extracted in step S201, and the topic category may be more in step S202.
- the step S206 is to determine, according to the matching result, the step of determining the current template from the multiple template templates, which may include:
- S2061 Search for, according to each topic category obtained by the matching, a template of the strategy including the topic categories from the multiple template templates.
- a Raiders template containing both of the above subject categories can be selected from all the Raider templates.
- the server recognizes the keywords included in the “7-way” and “Leifeng Tower”, it matches the tourism keyword of the server. It can be seen that the theme category corresponding to "7 Road” is “vehicle”, and the theme category corresponding to "Leifeng Tower” is “attraction”, and the three templates of the server are: “Sit() to ()", “ Go to () Tasting ()", “Living in ()”, and “Sit() to ()” This is the first blank fill-in area in the Raiders template.
- the subject category is "Transport", the second blank.
- the theme category corresponding to the fill-in area is “attraction”; the second blank fill-in area in the second guide template “to () tasting ()” corresponds to the theme category “hotel”, the second blank fill-in area
- the corresponding theme category is “Gourmet”, and the theme category of the blank fill-in area of the third strategy template “live in ()” is “hotel”, and the server corresponds to the theme corresponding to the keyword included in the text input by the user.
- Category determine the first Raiders template "Sit() to ( )" is the current strategy template.
- the step S207 that is, the step of automatically generating a travel strategy according to the keyword and the current strategy template includes:
- S2071 Fill the at least one keyword into the blank fill-in area of the current Raiders template according to the topic category, and automatically generate the travel strategy.
- the selected current template is, for example, "sit() to ()", and the first blank fill-in area corresponds to the subject category as "vehicle”, and the second blank fill-in area corresponds to
- the theme category is “Attraction”
- the user can input text according to the prompt "Please enter the tourist attraction in order, and the vehicle is indicated by the brackets", and the input text is, for example, "Liu Lang Wen (Walk) Jingci Temple (7 Road) Leifeng Pagoda” .
- Use the travel keywords in the database to enter each user input A keyword corresponds to the corresponding topic category, and selects a current strategy template containing all the corresponding categories from the multiple template templates, and then fills in the blank fill-in area corresponding to the keyword input by the user, and automatically generates the travel strategy text.
- the output travel guide text can be:
- step S2061 in the step of searching for a strategy template including the topic categories from multiple attack templates according to each topic category obtained by the matching, each of the strategy templates has a preset algorithm.
- the emotional dimension score when the number of the strategy templates including all the corresponding topic categories is plural, step S2061 further includes:
- S2063 classify the selected strategy templates including all the corresponding topic categories according to the emotional dimension score
- S2064 accepts the user's selection information and uses the Raiders template selected by the user as the current strategy template.
- step S2061 the step of obtaining the sentiment dimension score by each of the Raider templates according to a preset algorithm comprises:
- the descriptor may be "Osmanthus fragrans", the direction word may be “rich”, and the degree word may be "very";
- the descriptor may be "Osmanthus fragrans", the direction word may be “rich”, and the degree word may be "very";
- S2061e normalize the sentiment dimension scores of the plurality of clauses, and obtain an sentiment dimension score of the Raiders template obtained based on the original Raiders text decomposition.
- the above normalization may be, for example, adding the average of the scores of each clause to obtain the emotional dimension score of the entire strategy template.
- the Raiders template simply removes the descriptive words and does not affect the emotions, the emotional scores can be directly associated with the Raiders template.
- the presentations can be classified according to the emotion dimensions for the user to select. For example, after the user inputs "Liu Lang Wen Yu (walking) Jingci Temple (7 Road) Leifeng Tower", you can choose a different strategy template for emotional scores. For example, if you select the first template with an emotional score of 4, you can get: “Go to Liu Lang Wen, first. I felt the infinite spring. Then I walked a short distance to the Jingci Temple. The temple was very solemn and made people feel the different atmosphere. When the time was small, we took the 7-way car and went to the Leifeng Pagoda. The story has always been my favorite, and I feel very good at it.” The Raiders text;
- the user can also select the second template with an emotional score of 1, for example, "you can go to Liulang Wenyi first, the scenery is acceptable; then walk a short distance to the Jingci Temple, there is no special feeling. Then we catch up. 7-way car, went to Leifeng Tower, just a simple tower.” Raiders text.
- the travel strategy generation method proposed by the second embodiment of the present application not only can the travel strategy be automatically generated, but also the problem that the user writes a large amount of text in the travel strategy is time-consuming and labor-intensive, and the enthusiasm of the user to make the strategy is improved, and the user can be made choose the appropriate emotions to make the travel strategy more humane.
- FIG. 3 is a flow chart showing a method for generating a travel strategy according to a third embodiment of the present application. As shown in FIG. 3, the travel strategy generation method of the third embodiment of the present application can be applied to, for example, a server.
- the step of filling the thumbnail image may be added.
- the travel strategy generation method may further include:
- S105 Read a picture uploaded by a user, and identify picture information of the picture.
- the user-uploaded picture is read, and the picture information of the picture is recognized;
- the picture information includes a place where the picture is taken and/or an attraction and/or a scene on the picture, and the location where the picture is taken can be identified, Attractions, scenery, etc., to achieve this function, it is necessary to use some manually labeled data to obtain a model after training using a convolutional neural network (CNN), and then use the model to identify the corresponding attractions. Since the technology for identifying pictures is a mature technology, here No longer.
- the picture can be inserted into the travel guide text according to the rule of "inserting the corresponding picture in the order of the spots in the text, under the text".
- the travel strategy generating method of the embodiment may further include the following steps:
- S1051 Select a picture whose picture quality is higher than a preset threshold as a picture to be inserted.
- the quality score of the picture can be calculated, and the picture whose quality score is lower than the threshold can be deleted; the function can be obtained by using the manually labeled data by using the convolutional neural network (CNN) to obtain the model, and then using the image.
- the model calculates the quality score for the image, and finally deletes the image with low quality, that is, the image whose quality score is lower than the threshold preset by the system. Calculating picture quality scores is also a mature technology and will not be described here.
- the travel strategy generation method proposed by the third embodiment of the present application not only can the travel strategy be automatically generated, but also the problem that the user writes a large amount of text in the travel strategy is time-consuming and laborious, and the enthusiasm of the user to make the strategy is improved, and the picture can be matched with the picture.
- the realization of the illustrated effect makes the obtained travel strategy more humane and more aesthetic.
- the travel strategy proposed by the embodiment of the present application is performed before each keyword is matched with the pre-stored travel topic in step S102 or step S205 to determine the topic category corresponding to each keyword.
- the production method may further include the following steps:
- the preset tourist attraction data may be, for example, third party travel data, including translation names and aliases of some place names, which may be used to proofread the user input text in order to ensure the correctness of the travel strategy.
- third party travel data including translation names and aliases of some place names, which may be used to proofread the user input text in order to ensure the correctness of the travel strategy.
- fuzzy search technology you can use the "fuzzy search” approach. The process is to use high-quality travel text (can be crawled by crawler) to get the word frequency of each correct word, then calculate the correct road name and the edit distance of the required correction path name, and finally select the "word frequency / edit distance" the largest Words. By this method, for example, it is possible to correct the "flushing door" to "the golden gate”.
- the method may further include:
- the solution of the present application may further include the step 100 of classifying the Raiders data according to a specific classification in the database.
- the "specific classification” here may be, for example, an attraction.
- FIG. 8 is a schematic diagram showing input content and output content of a travel strategy generation method according to an embodiment of the present application. As shown in FIG. 8 , according to the method for generating a travel strategy of the present application, after inputting a simple text, a detailed and emotional strategy with a picture can be obtained, which improves the aesthetic and readability of the strategy.
- FIG. 9 is a schematic flowchart of a method for generating a travel strategy according to an embodiment of the present application, which can be regarded as a combination of the foregoing three embodiments.
- a person skilled in the art can combine and draw a plurality of embodiments to form a new solution, which are all within the scope of the present application.
- FIG. 4 is a flowchart of a method for generating a travel strategy according to a fourth embodiment of the present invention. As shown in FIG. 4, the method for generating a travel strategy can be applied to a client. The method can include the following steps:
- the client can provide an input interface for the user to input text having a plurality of keywords including, for example, travel routes, vehicles, meals, accommodation, and the like.
- the user can enter text, for example, through an information input interface.
- the prompt displayed on the input interface may be “please input tourist attractions in order, and the vehicle is indicated by brackets”, and the user may input according to the prompts.
- the input text is, for example, "Liu Lang Wen (Walk) Jingci Temple (7 Road) Leifeng Pagoda", the text contains a number of keywords: Liulang Wenyi, walking, Jingci Temple, 7 Road, Leifeng Pagoda.
- S402. Send the keyword input by the user to the server, where the server determines the topic category and the strategy template according to the keyword input by the user.
- the client can send the keyword to the server, and the server determines the topic category and the strategy template, and the server can pre-store the tourism keyword, and each travel keyword corresponds to In a topic category.
- the topic category corresponding to the travel keyword is the topic category corresponding to the keyword.
- one of the keywords entered by the user is “Leifeng Tower”
- the theme category of the travel theme word “Leifeng Tower” pre-stored by the server is “attraction”, which can determine the topic category corresponding to the keyword “Leifeng Tower”.
- the current strategy template may be determined from multiple attack templates in the server according to the result of the keyword sent by the client and the matching of the topic keywords.
- the user input text sent by the client is “(7-way) Leifeng Pagoda”
- the server identifies the keywords included in the “7-way” and “Leifeng Tower”.
- the three attack templates of the server are: “ Sit () to (), “to () tasting ()", “live in ()", you can select the first template according to the matching result, that is, "sit () to ()” as the current Raiders template.
- the server can use the keywords "7 Way” and “Leifeng Tower” entered by the user, and the current Raiders template “Sit () to ()", “7 Way” and “Leifeng Tower” Fill in the blank fill-in area of the Raiders template, and automatically generate a “sit 7 to Leifeng Tower” travel guide.
- the client may receive a travel strategy generated by the server according to the keyword.
- the travel strategy generated according to the keyword is obtained by filling the keyword into the strategy template;
- the strategy template includes at least one blank fill-in area, and each blank fill-in area is associated with one The subject category, the keyword is correspondingly filled in the blank fill-in area according to the associated topic category.
- the subject category is obtained by categorizing a plurality of travel subject words respectively extracted from a plurality of original Raiders texts, wherein each of the travel subject words corresponds to a subject category; the Raiders template is based on extracting travel subject words The original Raiders text is generated.
- the original Raiders text of a certain paragraph is: “Take the train to Hangzhou East Railway Station, take the subway to Longxiang Bridge, walk out to the lakeside, and enjoy the delicious snacks in Hangzhou.
- Yongjinmen, to Liulang Wenyu tour to the Jingci Temple, Leifeng Tower, Taiziwan, Sudi, Huagang Guanyu, Tiger Run and Liuhe Tower, and finally take the 4 bus to a park, night view of West Lake Park Music Fountain, overnight in Hangzhou Dujinsheng Hotel.”
- the tourist keywords extracted from the above user input text include: “train”, “train east station”, “metro”, “longxiang bridge”, “lakeside”, “knowing taste”, “Hangzhou”, “West Lake” “Yongjinmen”, “Liu Lang Wen”, “Jingci Temple”, “Leifeng Tower”, “Prince Bay”, “Su Di”, “Huagang Guanyu”, “Tiger Run”, “Six Harmony Tower”, “ 4 Road”, “One Park”, “Three Parks”, “Music Fountain”, “Du Jinsheng Hotel”.
- Travel keywords can be classified into different themes according to the theme category, such as: “train”, “train east station”, “metro”, “longxiang bridge”, “lakeside”, “knowing taste”, "west lake” "Yongjinmen” can be classified as “transportation: train, subway”, “train station: East Railway Station”, “Station: Longxiang Bridge”, “Sights: Lakeside, West Lake, Yongjinmen”, “Restaurant: Knowing View”.
- the vehicle, the train station and the scenic spot are the subject words.
- the relevant corpus and the current mature information extraction method can be utilized, and will not be described here.
- topic corpus list can have the following data form:
- the template template of the original blank Raiders text with multiple blank fill-in areas formed after the travel theme is extracted is:
- each blank fill-in area is associated with the topic category corresponding to the travel subject word by the extracted travel subject words, for example, the travel keyword corresponding to the two blank fill-in areas in the first sentence of the strategy template is “ “Train” and “Hangzhou East railway Station”, the subject categories corresponding to the two tourism keywords are “vehicle” and “train station”, respectively, and the two blank fill-in areas in the first sentence of the strategy template are associated with The subject categories are "vehicle” and "train station”.
- the travel strategy generation method can not only automatically generate a travel strategy, but also avoids the problem that the user writes a large amount of text in the travel strategy, which is time-consuming and laborious, and improves the enthusiasm of the user to make the strategy.
- the step of providing a keyword input interface for the user to input at least one keyword for displaying the specified input format is preferably a keyword input interface for the user to input at least one keyword for displaying the specified input format.
- the prompt displayed on the input interface may be “please input tourist attractions in order, and the vehicle is indicated by brackets”, and the user may input text according to the prompt, and the input text is for example “ Liulang Wenyu (walking) Jingci Temple (7 Road) Leifeng Tower.
- the step of sending the keyword input by the user to the server for the server to determine the topic category and the strategy template according to the keyword input by the user, the plurality of the template templates are multiple,
- the step of receiving the travel strategy generated by the server according to the keyword includes:
- the method further includes:
- the server when the server filters out a plurality of main words corresponding to each keyword including user input
- the Raiders template of the title category the server can use each Raiders template to generate a travel strategy and send it to the client.
- the user When the user receives multiple travel strategies, the user will select the travel strategy that one of the seats ultimately selects.
- the client sends the selection information input by the user to the server, and receives the travel strategy that the user finally selects returned by the server.
- the method further includes:
- the plurality of travel tactics returned by the server are classified and displayed according to the emotional dimension score associated with each of the Raiders templates.
- each of the strategy template associations has an emotional dimension score, which can be obtained by steps S2061a to S2061e in the second embodiment.
- the emotion dimension can be scored.
- the travel strategy generated by the Raiders template with a score of 5 is divided into one category, and the Raiders template with a score of 4 is divided into one type of display.
- the travel strategy generating method further includes: providing an interface for inputting a picture, and uploading a picture input by the user to the server.
- the steps of receiving the travel strategy generated by the server according to the keyword include:
- the server inserts the picture into the travel strategy generated according to the keyword to form a travel guide with pictures.
- the travel strategy generation method can not only automatically generate a travel strategy, but also avoids the problem that the user writes a large amount of text in the travel strategy, which is time-consuming and laborious, and improves the enthusiasm of the user to make the strategy. Moreover, the user can select the corresponding emotions and cooperate with the pictures to realize the effect of the pictures and texts, so that the obtained travel strategy is more humanized and more aesthetic.
- FIG. 5 shows a travel strategy generation system according to a fifth embodiment of the present application.
- the travel strategy generation system 500 includes:
- the keyword receiving module 501 is configured to receive at least one keyword input by the user
- the topic category determining module 502 is configured to match each of the keywords with pre-stored travel keywords to determine a topic category corresponding to each of the keywords;
- the Raiders template selection module 503 is configured to determine a current Raider template from multiple Raider templates according to the matching result
- the travel strategy generating module 504 is configured to automatically generate a travel strategy according to the keyword and the current strategy template.
- the travel strategy generation system further includes:
- the tourism keyword extraction module 505 is configured to separately extract a plurality of travel theme words from the plurality of original Raiders texts;
- a tourism keyword categorization module 506 configured to classify the plurality of travel keywords according to a topic category, such that each of the travel keywords corresponds to a topic category;
- the Raiders template generating module 507 is configured to generate a Raiders template having a plurality of blank fill-in areas based on the original Raiders text extracted from the travel subject words; wherein each of the blank fill-in areas associates the travel with the extracted travel keywords The subject category corresponding to the subject heading.
- the strategy template selection module is used to:
- a plurality of Raiders templates are searched for the template including the topic categories.
- the travel strategy generation module is configured to:
- the travel strategy is automatically generated in the blank fill-in area.
- the travel strategy generation system further includes:
- the text correction module 508 is configured to perform text correction on the keyword by using preset tourist attraction data.
- each of the attack templates has an emotional dimension score obtained according to a preset algorithm
- the attack template selection module 503 includes:
- a template selection submodule configured to select a strategy template that includes all the corresponding topic categories from the multiple template templates
- a template classification sub-module for classifying the selected strategy templates including all the corresponding topic categories according to the emotional dimension score
- the template determining sub-module is configured to accept the selection information of the user, and use the Raiders template selected by the user as the current Raiders template.
- the travel strategy generating system further includes an emotional scoring module, and the emotional scoring module includes:
- the corpus establishes a sub-module for establishing three corpora of description, direction, and degree; the corpus includes a term and a corresponding score parameter;
- a text decomposition sub-module configured to decompose the original Raider text into a plurality of clauses by punctuation and connection words;
- the sentiment dimension score obtaining sub-module is configured to obtain an emotional dimension score of the clause based on the parsed word of the “degree” part and the word of the “direction” part according to the parsed corpus;
- a normalization sub-module for normalizing the emotional dimension scores of the plurality of clauses
- the sentiment dimension score of the Raiders template obtained based on the original Raiders text decomposition.
- system further includes:
- a picture reading and identifying module 509 configured to read a picture uploaded by a user, and identify picture information of the picture
- the picture insertion module 510 is configured to insert the picture into a corresponding position in the generated travel strategy according to the picture information.
- the picture information includes a location at which the picture was taken and/or an attraction and/or a scene on the picture.
- system further includes:
- the picture selection module 511 is configured to select a picture whose picture quality is higher than a preset threshold as a picture to be inserted.
- system further includes:
- the travel strategy sending module 512 is configured to send the generated travel strategy to the user.
- the travel strategy generation system proposed by the fifth embodiment of the present invention can avoid the problem that the user writes a large amount of text in the travel strategy, which is time-consuming and laborious, and improves the enthusiasm of the user to make the strategy. For users who frequently travel to travel in a batch, the travel guide needs to be written in batches.
- the travel strategy generation method proposed by the embodiment of the present application can save a lot of time for making a strategy and improve efficiency.
- the travel strategy generation system 600 includes:
- the input interface providing module 601 is configured to provide a keyword input interface for the user to input at least one keyword
- a keyword sending module 602 configured to send the keyword input by the user to a server, Determining, by the server, a topic category and a strategy template according to keywords input by the user;
- the travel guide receiving module 603 is configured to receive a travel strategy generated by the server according to the keyword.
- the travel strategy generated according to the keyword is obtained by filling the keyword into the strategy template;
- the strategy template includes at least one blank fill-in area, and each blank fill-in area Associated with one of the subject categories, the keywords are correspondingly filled in the blank fill-in area according to the associated topic category.
- the subject category is obtained by categorizing a plurality of travel subject words respectively extracted from a plurality of original Raider texts, wherein each of the travel subject words corresponds to a subject category; the Raiders template is based on extraction The original Raiders text of the travel theme was generated.
- the input interface providing module is for displaying a specified input format.
- the keyword sending module is configured to send the keyword input by the user to a server, and the server determines, according to the keyword input by the user, a topic category and multiple attack templates;
- the travel guide receiving module 603 includes:
- a preliminary receiving submodule configured to receive a plurality of travel strategies generated by the server according to keywords
- the final travel guide receiving sub-module is configured to receive the travel guide finally selected by the user returned by the server.
- system further includes:
- the category display module 604 is configured to classify the plurality of travel guides returned by the server according to the sentiment dimension scores associated with each of the Raiders templates.
- system further includes:
- the picture input interface providing module 605 is configured to provide an interface for inputting pictures, and upload a picture input by the user to the server.
- the travel strategy receiving module 603 is configured to receive a travel strategy that is returned by the server and includes a picture input by the user.
- the travel strategy generation system proposed by the sixth embodiment of the present application can avoid the problem that the user writes a large amount of text in the travel strategy, which is time-consuming and laborious, and improves the enthusiasm of the user to make a strategy.
- the travel strategy generation method proposed by the embodiment of the present application can save a lot of time for making a strategy and improve efficiency.
- the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.
- embodiments of the embodiments of the present application can be provided as a method, apparatus, or computer program product. Therefore, the embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, embodiments of the present application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
- computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
- the computer device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
- the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
- RAM random access memory
- ROM read only memory
- Memory is an example of a computer readable medium.
- Computer readable media includes both permanent and non-persistent, removable and non-removable media.
- Information storage can be implemented by any method or technology. Information can be computer readable Orders, data structures, modules of programs, or other data.
- Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
- computer readable media does not include non-persistent computer readable media, such as modulated data signals and carrier waves.
- Embodiments of the present application are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG.
- These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal device to produce a machine such that instructions are executed by a processor of a computer or other programmable data processing terminal device
- Means are provided for implementing the functions specified in one or more of the flow or in one or more blocks of the flow chart.
- the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
- the instruction device implements the functions specified in one or more blocks of the flowchart or in a flow or block of the flowchart.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- User Interface Of Digital Computer (AREA)
- Machine Translation (AREA)
- Document Processing Apparatus (AREA)
Abstract
Description
Claims (38)
- 一种旅游攻略生成方法,其特征在于,包括如下步骤:接收用户输入的至少一个关键词;将每一个所述关键词与预存的旅游主题词匹配,确定每一个所述关键词对应的主题类别;根据匹配结果,从多个攻略模板中确定当前攻略模板;根据所述关键词和所述当前攻略模板,自动生成旅游攻略。
- 如权利要求1所述的旅游攻略生成方法,其特征在于,在将每一个所述关键词与预存的旅游主题词匹配的步骤之前,还包括:从多个原始攻略文本中分别提取多个旅游主题词;将所述多个旅游主题词按照主题类别归类,使每一个所述旅游主题词对应一个主题类别;基于提取了旅游主题词的原始攻略文本,生成具有多个空白填空区的攻略模板;其中,每一个所述空白的填空区通过所提取的旅游主题词关联该旅游主题词对应的主题类别。
- 如权利要求2所述的旅游攻略生成方法,其特征在于,所述根据匹配结果,从多个攻略模板中确定当前攻略模板的步骤包括:根据匹配得到各主题类别,从多个攻略模板中查找包括所述各主题类别的攻略模板。
- 如权利要求3所述的旅游攻略生成方法,其特征在于,所述根据所述关键词和所述当前攻略模板,自动生成旅游攻略的步骤包括:将所述至少一个关键词按照所述主题类别填入所述当前攻略模板的空白的填空区中,自动生成所述旅游攻略。
- 如权利要求1所述旅游攻略生成方法,其特征在于,在将每一个所 述关键词与预存的旅游主题词匹配,确定每一个所述关键词对应的主题类别之前,所述方法还包括:利用预设的旅游景点数据,对所述关键词进行文本校正。
- 如权利要求3所述旅游攻略生成方法,其特征在于,每一个所述攻略模板具有一个按照预设算法获得的情感维度得分;当包含所有相应主题类别的攻略模板为多个时,所述根据匹配得到各主题类别,从多个攻略模板中查找包括所述各主题类别的攻略模板的步骤进一步包括:从上述多个攻略模板中选择出包含所有相应主题类别的攻略模板;按照情感维度得分,将所选择出的包含所有相应主题类别的攻略模板进行分类;接受用户的选择信息,以用户选择的攻略模板作为当前攻略模板。
- 如权利要求6所述旅游攻略生成方法,其特征在于,每一个所述攻略模板按照预设算法获得情感维度得分的步骤包括:建立描述、方向、程度三个语料库,所述语料库包括词条和对应分值参数;将所述原始攻略文本按标点和连接词分解为多个分句;根据中文语法将每一个所述分句解析成“描述”、“方向”和“程度”部分;对照所述语料库,基于解析后的所述“程度”部分的词和所述“方向”部分的词,得到该分句的情感维度得分;将所述多个分句的情感维度得分进行归一化,获得基于所述原始攻略文本分解得到的攻略模板的情感维度得分。
- 如权利要求1所述的旅游攻略生成方法,其特征在于,所述方法还包括:读取用户上传的图片,识别所述图片的图片信息;根据所述的图片信息,将所述图片插入到所生成的旅游攻略中的相应位置。
- 如权利要求8所述的旅游攻略生成方法,其特征在于,所述图片信息包括拍摄图片的地点、所述图片上的景点和/或景物。
- 如权利要求8所述的旅游攻略生成方法,其特征在于,在根据所述的图片信息,将所述图片插入到所生成的旅游攻略中的相应位置之前,所述方法还包括:选取图片质量高于预设阈值的图片作为待插入图片。
- 如权利要求1-10中任一项所述的旅游攻略生成方法,其特征在于,所述方法还包括:将所生成的旅游攻略发送给用户。
- 一种旅游攻略生成方法,其特征在于,包括:提供关键词输入界面,供用户输入至少一个关键词;将所述用户输入的关键词发送至服务器,供服务器根据所述用户输入的关键词确定主题类别和攻略模板;接收所述服务器返回的根据所述关键词生成的旅游攻略。
- 如权利要求12所述的旅游攻略生成方法,其特征在于,所述根据关键词生成的旅游攻略通过将所述的关键词填入所述攻略模板中获得;所述攻略模板包括至少一个空白的填空区,每一个空白的填空区关联一个所述主题类别,所述关键词根据所关联的主题类别对应地填入所述空白的填空区中。
- 如权利要求13所述的旅游攻略生成方法,其特征在于,所述主题类别通过从多个原始攻略文本中分别提取的多个旅游主题词归类获得,其中每一个所述旅游主题词对应一个主题类别;所述攻略模板基于提取了 旅游主题词的原始攻略文本生成。
- 如权利要求12所述的旅游攻略生成方法,其特征在于,所述提供关键词输入界面,供用户输入至少一个关键词的步骤中,所述输入界面用于显示指定的输入格式。
- 如权利要求12所述的旅游攻略生成方法,其特征在于,所述将所述用户输入的关键词发送至服务器,供服务器根据所述用户输入的关键词确定主题类别和攻略模板的步骤中,所述攻略模板为多个;所述接收所述服务器返回的根据关键词生成的旅游攻略的步骤包括:接收所述服务器返回的根据关键词生成的多个旅游攻略;所述方法还包括:将用户输入的选择信息发送至所述服务器;以及接收服务器返回的所述用户最终选择的旅游攻略。
- 如权利要求16所述的旅游攻略生成方法,其特征在于,在所述接收所述服务器返回的根据关键词生成的多个旅游攻略的步骤之后,所述方法还包括:将所述服务器返回的多个旅游攻略按照每一个所述攻略模板关联的情感维度得分进行分类展示。
- 如权利要求12所述的旅游攻略生成方法,其特征在于,所述方法还包括:提供图片输入的界面,将用户输入的图片上传至所述服务器。
- 如权利要求18所述的旅游攻略生成方法,其特征在于,接收所述服务器返回的根据关键词生成的旅游攻略的步骤包括:接收所述服务器返回的包含用户输入的图片的旅游攻略。
- 一种旅游攻略生成系统,其特征在于,包括:关键词接收模块,用于接收用户输入的至少一个关键词;主题类别确定模块,用于将每一个所述关键词与预存的旅游主题词匹配,确定每一个所述关键词对应的主题类别;攻略模板选择模块,用于根据匹配结果,从多个攻略模板中确定当前攻略模板;旅游攻略生成模块,用于根据所述关键词和所述当前攻略模板,自动生成旅游攻略。
- 如权利要求20所述的旅游攻略生成系统,其特征在于,所述系统还包括:旅游主题词提取模块,用于从多个原始攻略文本中分别提取多个旅游主题词;旅游主题词归类模块,用于将所述多个旅游主题词按照主题类别归类,使每一个所述旅游主题词对应一个主题类别;攻略模板生成模块,用于基于提取了旅游主题词的原始攻略文本,生成具有多个空白填空区的攻略模板;其中,每一个所述空白的填空区通过所提取的旅游主题词关联该旅游主题词对应的主题类别。
- 如权利要求21所述的旅游攻略生成系统,其特征在于,所述攻略模板选择模块用于:根据匹配得到的各主题类别,从多个攻略模板中查找包括所述各主题类别的攻略模板。
- 如权利要求22所述的旅游攻略生成系统,其特征在于,所述旅游攻略生成模块用于:将所述至少一个关键词按照所述主题类别填入所述当前攻略模板的空白的填空区中,自动生成所述旅游攻略。
- 如权利要求20所述旅游攻略生成系统,其特征在于,所述系统还 包括:文本校正模块,用于利用预设的旅游景点数据,对所述关键词进行文本校正。
- 如权利要求22所述的旅游攻略生成系统,其特征在于,每一个所述攻略模板具有一个按照预设算法获得的情感维度得分;当包含所有相应主题类别的攻略模板为多个时,所述攻略模板选择模块包括:模板选择子模块,用于从上述多个攻略模板中选择出包含所有相应主题类别的攻略模板;模板分类子模块,用于按照情感维度得分,将所选择出的包含所有相应主题类别的攻略模板进行分类;模板确定子模块,用于接受用户的选择信息,以用户选择的攻略模板作为当前攻略模板。
- 如权利要求25所述的旅游攻略生成系统,其特征在于,所述系统还包括情感打分模块,所述情感打分模块包括:语料库建立子模块,用于建立描述、方向、程度三个语料库;所述语料库包括词条和对应分值参数;文本分解子模块,用于将所述原始攻略文本按标点和连接词分解为多个分句;文本解析子模块,用于根据中文语法将每一个所述分句解析成“描述”、“方向”和“程度”部分;情感维度得分获得子模块,用于对照所述语料库,基于解析后的所述“程度”部分的词和所述“方向”部分的词,得到该分句的情感维度得分;归一化子模块,用于将所述多个分句的情感维度得分进行归一化,获得基于所述原始攻略文本分解得到的攻略模板的情感维度得分。
- 如权利要求20所述的旅游攻略生成系统,其特征在于,所述系统还包括:图片读取识别模块,用于读取用户上传的图片,识别所述图片的图片信息;图片插入模块,用于根据所述的图片信息,将所述图片插入到所生成的旅游攻略中的相应位置。
- 如权利要求27所述的旅游攻略生成系统,其特征在于,所述图片信息包括拍摄图片的地点、所述图片上的景点和/或景物。
- 如权利要求27所述的旅游攻略生成系统,其特征在于,所述系统还包括:图片选择模块,用于选取图片质量高于预设阈值的图片作为待插入图片。
- 如权利要求20-29中任一项所述的旅游攻略生成系统,其特征在于,所述系统还包括:旅游攻略发送模块,用于将所生成的旅游攻略发送给用户。
- 一种旅游攻略生成系统,其特征在于,包括:输入界面提供模块,用于提供关键词输入界面,供用户输入至少一个关键词;关键词发送模块,用于将所述用户输入的关键词发送至服务器,供服务器根据所述用户输入的关键词确定主题类别和攻略模板;旅游攻略接收模块,用于接收所述服务器返回的根据所述关键词生成的旅游攻略。
- 如权利要求31所述的旅游攻略生成系统,其特征在于,所述根据关键词生成的旅游攻略通过将所述的关键词填入所述攻略模板中获得;所述攻略模板包括至少一个空白的填空区,每一个空白的填空区关联一个所 述主题类别,所述关键词根据所关联的主题类别对应地填入所述空白的填空区中。
- 如权利要求32所述的旅游攻略生成系统,其特征在于,所述主题类别通过从多个原始攻略文本中分别提取的多个旅游主题词归类获得,其中每一个所述旅游主题词对应一个主题类别;所述攻略模板基于提取了旅游主题词的原始攻略文本生成。
- 如权利要求31所述的旅游攻略生成系统,其特征在于,所述输入界面提供模块用于显示指定的输入格式。
- 如权利要求31所述的旅游攻略生成系统,其特征在于,所述关键词发送模块用于将所述用户输入的关键词发送至服务器,供服务器根据所述用户输入的关键词确定主题类别和多个攻略模板;所述旅游攻略接收模块包括:初步接收子模块,用于接收所述服务器返回的根据关键词生成的多个旅游攻略;选择信息发送子模块,用于将用户输入的选择信息发送至所述服务器;以及最终旅游攻略接收子模块,用于接收服务器返回的所述用户最终选择的旅游攻略。
- 如权利要求35所述的旅游攻略生成系统,其特征在于,所述系统还包括:分类展示模块,用于将所述服务器返回的多个旅游攻略按照每一个所述攻略模板关联的情感维度得分进行分类展示。
- 如权利要求31所述的旅游攻略生成系统,其特征在于,所述系统还包括:图片输入界面提供模块,用于提供图片输入的界面,将用户输入的图片上传至所述服务器。
- 如权利要求37所述的旅游攻略生成系统,其特征在于,所述旅游攻略接收模块用于接收所述服务器返回的包含用户输入的图片的旅游攻略。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2018534542A JP2019504410A (ja) | 2015-12-30 | 2016-12-16 | 旅行ガイド生成方法及びシステム |
| KR1020187017863A KR20180098265A (ko) | 2015-12-30 | 2016-12-16 | 여행 가이드 생성 방법 및 시스템 |
| US16/024,442 US20180307667A1 (en) | 2015-12-30 | 2018-06-29 | Travel guide generating method and system |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511021481.5A CN106933789B (zh) | 2015-12-30 | 2015-12-30 | 旅游攻略生成方法和生成系统 |
| CN201511021481.5 | 2015-12-30 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US16/024,442 Continuation US20180307667A1 (en) | 2015-12-30 | 2018-06-29 | Travel guide generating method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017114177A1 true WO2017114177A1 (zh) | 2017-07-06 |
Family
ID=59225924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/110232 Ceased WO2017114177A1 (zh) | 2015-12-30 | 2016-12-16 | 旅游攻略生成方法和生成系统 |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US20180307667A1 (zh) |
| JP (1) | JP2019504410A (zh) |
| KR (1) | KR20180098265A (zh) |
| CN (1) | CN106933789B (zh) |
| WO (1) | WO2017114177A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101973642B1 (ko) * | 2018-08-31 | 2019-09-02 | 서울대학교산학협력단 | 텍스트 자동 생성을 위한 인터랙티브 시스템 및 방법 |
Families Citing this family (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110019201B (zh) * | 2017-10-09 | 2023-03-07 | 阿里巴巴集团控股有限公司 | 一种生成结构化数据的方法、装置及系统 |
| CN109977390B (zh) * | 2017-12-27 | 2023-11-03 | 北京搜狗科技发展有限公司 | 一种生成文本的方法及装置 |
| CN108052494B (zh) * | 2017-12-28 | 2021-09-14 | 掌阅科技股份有限公司 | 漫画书生成方法、电子设备及计算机存储介质 |
| CN108363697B (zh) * | 2018-03-08 | 2022-02-22 | 腾讯科技(深圳)有限公司 | 文本信息生成方法、装置、存储介质及设备 |
| CN108829651A (zh) * | 2018-04-17 | 2018-11-16 | 平安科技(深圳)有限公司 | 一种公文处理的方法、装置、终端设备及存储介质 |
| CN108694160B (zh) | 2018-05-15 | 2021-01-22 | 北京三快在线科技有限公司 | 文章生成方法、设备及存储介质 |
| CN110807147B (zh) * | 2018-08-03 | 2023-05-02 | 阿里巴巴集团控股有限公司 | 旅游信息生成方法、生成装置、存储介质和处理器 |
| CN110245339B (zh) * | 2019-06-20 | 2023-04-18 | 北京百度网讯科技有限公司 | 文章生成方法、装置、设备和存储介质 |
| CN110609991B (zh) * | 2019-09-10 | 2023-09-19 | 卓尔智联(武汉)研究院有限公司 | 文本生成方法、电子装置及存储介质 |
| TWI742450B (zh) * | 2019-10-16 | 2021-10-11 | 財團法人工業技術研究院 | 企劃書的自動化產生系統及其方法 |
| CN111191127B (zh) * | 2019-12-24 | 2023-02-03 | 重庆特斯联智慧科技股份有限公司 | 一种基于关联分析算法的旅行推荐方法和系统 |
| CN111241282B (zh) * | 2020-01-14 | 2023-09-08 | 北京百度网讯科技有限公司 | 文本主题生成方法、装置及电子设备 |
| WO2021261987A1 (en) * | 2020-06-22 | 2021-12-30 | Mimos Berhad | System and method for providing destination recommendation to travelers |
| CN112069347B (zh) * | 2020-09-04 | 2024-05-24 | 中国平安人寿保险股份有限公司 | 游记生成方法、装置、计算机设备及可读存储介质 |
| KR20220120975A (ko) * | 2021-02-24 | 2022-08-31 | 이승재 | 사용자 주도형 여행 설계 서버 및 방법 |
| WO2022240405A1 (en) * | 2021-05-12 | 2022-11-17 | Genesys Cloud Services, Inc. | System and method of automatic topic detection in text |
| CN113268961A (zh) * | 2021-06-07 | 2021-08-17 | 维沃移动通信(杭州)有限公司 | 游记生成方法及装置 |
| US20230009267A1 (en) * | 2021-07-06 | 2023-01-12 | Ebay Inc. | Visual facet search engine |
| CN114077828A (zh) * | 2021-10-28 | 2022-02-22 | 广州炒米信息科技有限公司 | 基于区块链的电子合同签署方法、装置、设备及存储介质 |
| CN115203555B (zh) * | 2022-07-15 | 2024-03-19 | 重庆工商大学 | 一种基于大数据的景区景点推荐方法及系统 |
| JP7699876B1 (ja) * | 2024-12-25 | 2025-06-30 | 株式会社令和トラベル | システム、プログラムおよび文章情報製造方法 |
| CN121146179A (zh) * | 2025-09-11 | 2025-12-16 | 武汉理工大学 | 基于tft模型的旅游需求预测方法及装置、存储介质 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279863A (zh) * | 2013-06-08 | 2013-09-04 | 北京创腾科技有限公司 | 报告文档的自动生成方法和系统 |
| CN103425741A (zh) * | 2013-07-16 | 2013-12-04 | 北京中科汇联信息技术有限公司 | 一种信息展示方法和装置 |
| US20140358890A1 (en) * | 2013-06-04 | 2014-12-04 | Sap Ag | Question answering framework |
| CN104298727A (zh) * | 2014-09-26 | 2015-01-21 | 广州金山移动科技有限公司 | 一种基于文档的模板匹配方法及装置 |
| CN104933020A (zh) * | 2015-07-17 | 2015-09-23 | 北京奇虎科技有限公司 | 基于模板生成目标文档的方法及装置 |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020052913A1 (en) * | 2000-09-06 | 2002-05-02 | Teruhiro Yamada | User support apparatus and system using agents |
| JP2005136604A (ja) * | 2003-10-29 | 2005-05-26 | Seiko Epson Corp | 電子写真アルバム作成支援装置及び方法 |
| JP4937671B2 (ja) * | 2006-08-11 | 2012-05-23 | ソフトバンクモバイル株式会社 | 生活記録作成システムおよびその制御方法 |
| JP2008226235A (ja) * | 2007-02-14 | 2008-09-25 | Shinseiki:Kk | 情報フィードバックシステム、情報フィードバック方法、情報管理サーバ、情報管理方法及びプログラム |
| JP4462331B2 (ja) * | 2007-11-05 | 2010-05-12 | ソニー株式会社 | 撮像装置、制御方法、プログラム |
| US8315849B1 (en) * | 2010-04-09 | 2012-11-20 | Wal-Mart Stores, Inc. | Selecting terms in a document |
| CN103885983B (zh) * | 2012-12-21 | 2017-09-01 | 阿里巴巴集团控股有限公司 | 一种旅游线路的确定方法、优化方法以及装置 |
| GB2510584A (en) * | 2013-02-07 | 2014-08-13 | Paneleven Ltd | Personalising bank and similar cards |
| CN103246710A (zh) * | 2013-04-22 | 2013-08-14 | 张经纶 | 一种多媒体旅游游记的自动生成方法及装置 |
| CN103699626B (zh) * | 2013-12-20 | 2017-02-01 | 华南理工大学 | 一种微博用户个性化情感倾向分析方法及系统 |
-
2015
- 2015-12-30 CN CN201511021481.5A patent/CN106933789B/zh active Active
-
2016
- 2016-12-16 JP JP2018534542A patent/JP2019504410A/ja active Pending
- 2016-12-16 KR KR1020187017863A patent/KR20180098265A/ko not_active Withdrawn
- 2016-12-16 WO PCT/CN2016/110232 patent/WO2017114177A1/zh not_active Ceased
-
2018
- 2018-06-29 US US16/024,442 patent/US20180307667A1/en not_active Abandoned
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358890A1 (en) * | 2013-06-04 | 2014-12-04 | Sap Ag | Question answering framework |
| CN103279863A (zh) * | 2013-06-08 | 2013-09-04 | 北京创腾科技有限公司 | 报告文档的自动生成方法和系统 |
| CN103425741A (zh) * | 2013-07-16 | 2013-12-04 | 北京中科汇联信息技术有限公司 | 一种信息展示方法和装置 |
| CN104298727A (zh) * | 2014-09-26 | 2015-01-21 | 广州金山移动科技有限公司 | 一种基于文档的模板匹配方法及装置 |
| CN104933020A (zh) * | 2015-07-17 | 2015-09-23 | 北京奇虎科技有限公司 | 基于模板生成目标文档的方法及装置 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101973642B1 (ko) * | 2018-08-31 | 2019-09-02 | 서울대학교산학협력단 | 텍스트 자동 생성을 위한 인터랙티브 시스템 및 방법 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106933789B (zh) | 2023-06-20 |
| CN106933789A (zh) | 2017-07-07 |
| JP2019504410A (ja) | 2019-02-14 |
| KR20180098265A (ko) | 2018-09-03 |
| US20180307667A1 (en) | 2018-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017114177A1 (zh) | 旅游攻略生成方法和生成系统 | |
| CN108959256B (zh) | 短文本的生成方法、装置、存储介质和终端设备 | |
| Cotter | Discourse and media | |
| Groarke | Going multimodal: What is a mode of arguing and why does it matter? | |
| CN107391706B (zh) | 一种基于移动互联网的城市旅游问答系统 | |
| US20180357211A1 (en) | Constructing a Narrative Based on a Collection of Images | |
| CN109145281B (zh) | 语音识别方法、装置及存储介质 | |
| US20150340024A1 (en) | Language Modeling Using Entities | |
| De Klerk | Corpus linguistics and world Englishes: An analysis of Xhosa English | |
| CN107679226A (zh) | 基于主题的旅游本体构建方法 | |
| US12306891B2 (en) | Integration of web and media snippets into map applications | |
| Tolfo et al. | Gentrification in the media: the eviction of critical class perspective | |
| CA3082402A1 (en) | Systems and methods for adaptive proper name entity recognition and understanding | |
| CN111914157A (zh) | 一种基于用户偏好的旅游方案生成方法和系统 | |
| WO2021225085A1 (ja) | 情報処理システム、情報処理方法、情報処理プログラム、およびサーバ | |
| CN110245286B (zh) | 一种基于数据挖掘的旅行推荐方法及装置 | |
| US20250265278A1 (en) | Map search method and apparatus, server, terminal, and storage medium | |
| CN113254668B (zh) | 一种基于场景纬度的知识图谱构建方法及系统 | |
| TW201828166A (zh) | 旅遊攻略產生方法和產生系統 | |
| CN114036317A (zh) | 一种旅游知识图谱模型确定方法及装置 | |
| Sadoff | An eclectic methodology for analyzing film music | |
| Giouli et al. | Placing multi-modal, and multi-lingual Data in the Humanities Domain on the Map: the Mythotopia Geo-tagged Corpus | |
| Sezen et al. | Female agencies and subjectivities in Film and Television | |
| HK1239863B (zh) | 旅游攻略生成方法和生成系统 | |
| CN106934056B (zh) | 一种基于概率图模型的个性化旅游游记推荐方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16880967 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 20187017863 Country of ref document: KR Kind code of ref document: A |
|
| ENP | Entry into the national phase |
Ref document number: 2018534542 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 16880967 Country of ref document: EP Kind code of ref document: A1 |