CN105718547A - Tour guide method and system based on scenic spot label - Google Patents
Tour guide method and system based on scenic spot label Download PDFInfo
- Publication number
- CN105718547A CN105718547A CN201610032030.XA CN201610032030A CN105718547A CN 105718547 A CN105718547 A CN 105718547A CN 201610032030 A CN201610032030 A CN 201610032030A CN 105718547 A CN105718547 A CN 105718547A
- Authority
- CN
- China
- Prior art keywords
- video
- sight spot
- target
- information
- tab
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7844—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using original textual content or text extracted from visual content or transcript of audio data
Abstract
The invention provides a tour guide method and system based on a scenic spot label. The tour guide method comprises the following steps: determining a tourist position through the positioning information of mobile equipment, and determining target scenic spot information corresponding to the tourist position according to the tourist position; searching in a media library according to the target scenic spot information, and independently obtaining a corresponding scenic spot video, wherein the scenic spot video comprises a plurality of established video labels; independently matching the target scenic spot information with the video labels in the scenic spot video to obtain a target label corresponding to the target scenic spot information; and loading a video clip corresponding to the target label. The target scenic spot information is determined on the basis of positioning information, the target scenic spot information is independently matched with the video label in the scenic spot videos found in the media library to obtain the target label corresponding to the target scenic spot information so as to obtain the corresponding video clip, so that the scenic spot video can support a fine scenic spot introduction, and the rich degree of information is improved.
Description
Technical field
The present invention relates to self-help guide, in particular it relates to one pinpoints matching process and system based on sight spot label on map and sight spot video tab.
Background technology
Along with the living standard of people constantly improves, pursue higher material life, utilize weekend and the festivals or holidays upper household of band, relative, friend's out on tours to spend a holiday, to relax, observe and learn from real life, get close to nature, cultivate one's taste.
The mode of current out on tours has several as follows: self-driving is gone on a tour, and goes on a tour with group.Self-driving is gone on a tour needs the good every thing of schedule ahead, cumbersome, but expense is relatively low, and degree of freedom is high, and sight spot history-related is not known about；Going on a tour with group, simple and fast is convenient, costly, is freely restricted, and guide can explain the history at sight spot, but people is too many, listens inconvenience.In this case, applying and bear self-help guide service, individual goes on a tour and can individually rent guide interpreting at sight spot, and price is high.Today of the Internet high speed development, again change the life of people, various self-help guide app occurs.
Existing self-help guide app, as donkey mark is conducted a sightseeing tour, 51 guides etc..This guide's mode, according to personalized preference, selects the content play, plays the language used.App is not by anyone restriction, cheap, simple to operate, the deep favor by visitor.Self-help guide app currently on the market be all simply based on GPS location realize call broadcasting, what namely GPS location was fixed is a point, can only the audio frequency at this little sight spot of Play Server end correspondence storage, not only server end is safeguarded highly difficult, and reduces the abundant degree of information.
Summary of the invention
For defect of the prior art, it is an object of the invention to provide one and pinpoint matching process and system based on sight spot label on map and sight spot video tab.
The guidance method based on sight spot label provided according to an aspect of the present invention, comprises the steps:
Step S1: determine visitor location by the location information of mobile equipment, determine, according to described visitor location, the target sight spot information that described visitor location is corresponding；
Step S2: make a look up in media library according to described target sight spot information, respectively obtains the sight spot video of correspondence, and described sight spot video includes multiple set video tab；
Step S3: by each being mated with the video tab in the video of described sight spot by described target sight spot information, obtain the target labels that described target sight spot information is corresponding；
Step S4: load the video segment that described target labels is corresponding.
Preferably, described video tab generates in the following way:
By speech recognition technology, the voice in video information being converted to word, search the high frequency vocabulary in word, utilize knowledge base that high frequency vocabulary is judged, record edits the described normalized result of high frequency vocabulary as described video tab.
Preferably, described media library is set up in the following way:
Appearance position according to described video tab, is respectively divided into video segment by described video information；
Described video tab is formed media library with the corresponding storage respectively of described video segment.
Preferably, according to described visitor location determine sight spot information mode particularly as follows:
-calculate the distance between described visitor location and contiguous multiple sight spots, using the sight spot information at corresponding sight spot minimum for the distance between visitor location with sight spot as target sight spot information.
Preferably, described step S3, when described target sight spot information is each mated with the video tab in the video of described sight spot, comprise the steps:
Step S301: mated respectively by described target sight spot information sight spot each with media library video, chooses the target video of correspondence；
Step S302: extract video tab the highest with the matching degree of described target sight spot information in described target video as target labels.
It is preferably, described when described target sight spot information is mated respectively with each sight spot video,
Extract the video information that described sight spot video is corresponding；Described video information includes: summary texts that described sight spot video is corresponding, title, title that the place page is corresponding, text that the place page is corresponding；
Described target sight spot information is mated with described video information, chooses the highest sight spot video of described video information Corresponding matching degree as described target video.
Preferably, described step S3 includes:
Step S301: extract video tab corresponding in the video of each sight spot respectively by the given class of sight spot video, form each given class sight spot each self-corresponding tag set of video；
Step S302: described target sight spot information is made directly with the tag set of each given class respectively and mates, choose target labels by matching degree.
Preferably, during video segment corresponding to the described target labels of described loading, each target labels is set weight by described matching degree, plays out by weight selecting video fragment in each video segment of Corresponding matching.
Preferably, also comprise the steps:
The visit scope that visitor is corresponding is determined according to visitor location；Wherein, described visit scope is provided with tourist road；
The target sight spot information that described visitor location is corresponding is determined according to described visitor location, particularly as follows:
Determine the visit direction on described tourist road of current visitor；
The target sight spot information that described visitor location is corresponding respectively is pre-determined according to visit direction；
The video segment that the described target labels of described loading is corresponding, particularly as follows: according to video segment corresponding to the pre-loaded described target labels in described visit direction.
Guide system based on sight spot label provided by the invention, including such as lower module:
Module is determined at target sight spot, for determining visitor location by the location information of mobile equipment, determines, according to described visitor location, the target sight spot information that described visitor location is corresponding；
Sight spot video retrieval module, for making a look up in media library according to described target sight spot information, respectively obtains the sight spot video of correspondence, and described sight spot video includes multiple set video tab；
Target labels coupling acquisition module, by each being mated with the video tab in the video of described sight spot by described target sight spot information, obtains the target labels that described target sight spot information is corresponding；
Video segment load-on module, for loading the video segment that described target labels is corresponding.
Preferably, described video tab generates in the following way:
By speech recognition technology, the voice in video information being converted to word, search the high frequency vocabulary in word, utilize knowledge base that high frequency vocabulary is judged, record edits the described normalized result of high frequency vocabulary as described video tab.12, the guide system based on sight spot label according to claim 10 or 11, it is characterised in that described media library is set up in the following way:
Appearance position according to described video tab, is respectively divided into video segment by described video information；
Described video tab is formed media library with the corresponding storage respectively of described video segment.
Preferably, according to described visitor location determine sight spot information mode particularly as follows:
-calculate the distance between described visitor location and contiguous multiple sight spots, using the sight spot information at corresponding sight spot minimum for the distance between visitor location with sight spot as target sight spot information.
Preferably, described target labels coupling acquisition module includes such as lower module:
Sight spot video matching module, for being mated respectively by described target sight spot information sight spot each with media library video, chooses the target video of correspondence；
Target labels acquisition module, for extracting video tab the highest with the matching degree of described target sight spot information in described target video as target labels.
It is preferably, described when described target sight spot information is mated respectively with each sight spot video,
Extract the video information that described sight spot video is corresponding；Described video information includes: summary texts that described sight spot video is corresponding, title, title that the place page is corresponding, text that the place page is corresponding；
Described target sight spot information is mated with described video information, chooses the highest sight spot video of described video information Corresponding matching degree as described target video.
Preferably, described target labels coupling acquisition module includes:
Tag set generation module, for extracting video tab corresponding in the video of each sight spot respectively by the given class of sight spot video, forms each given class sight spot each self-corresponding tag set of video；
Target labels acquisition module, mates for being made directly with the tag set of each given class respectively by described target sight spot information, chooses target labels by matching degree.
Preferably, during video segment corresponding to the described target labels of described loading, each target labels is set weight by described matching degree, plays out by weight selecting video fragment in each video segment of Corresponding matching.
Preferably, also include such as lower module:
Target sight spot information determines module, for determining, according to visitor location, the visit scope that visitor is corresponding；Wherein, described visit scope is provided with tourist road；
For determining that described visitor location is corresponding according to described visitor location, particularly as follows:
Determine the visit direction on described tourist road of current visitor；
The target sight spot information that described visitor location is corresponding respectively is pre-determined according to visit direction；
The video segment that the described target labels of described loading is corresponding, particularly as follows: according to video segment corresponding to the pre-loaded described target labels in described visit direction.
Compared with prior art, the present invention has following beneficial effect:
1, the present invention is based on location information and determines target sight spot information, target sight spot information is each mated with the video tab in the sight spot video found in media library, obtain the target labels that target sight spot information is corresponding, and then obtain the video segment of correspondence, it is thus possible to make sight spot video to support, trickle sight spot is introduced, improve the abundant degree of information, and need not strictly carry out file and call, reduce the maintenance intensity of information.
2, decapacitation of the present invention free sight spot label on map selects outside video, also support self-defined sight spot label, just can be shown on map after self-defining sight spot labeling requirement manager examination & verification, so that video tab is diversified, support trickle sight spot further, facilitate visitor to select.
3, sight spot of the present invention label is supported multilingual, can provide convenient for visitor all over the world.
Accompanying drawing explanation
By reading detailed description non-limiting example made with reference to the following drawings, the other features, objects and advantages of the present invention will become more apparent upon:
Fig. 1 is the flow chart of steps of the guidance method in the present invention based on sight spot label；
Fig. 2 is the structural representation of the guide system in the present invention based on sight spot label；
Fig. 3 is based on a kind of flow chart of steps of step 3 in the guidance method of sight spot label in the present invention；
Fig. 4 is based on the another kind of flow chart of steps of step 3 in the guidance method of sight spot label in the present invention.
Detailed description of the invention
Below in conjunction with specific embodiment, the present invention is described in detail.Following example will assist in those skilled in the art and are further appreciated by the present invention, but do not limit the present invention in any form.It should be pointed out that, to those skilled in the art, without departing from the inventive concept of the premise, it is also possible to make some deformation and improvement.These broadly fall into protection scope of the present invention.
In tourism industry, the great majority adopted now or artificial guide or with a tourism, along with the tide of the Internet attacks, traditional guide's mode limitation is increasing, it has not been convenient to, expensive, not freely etc..The such phenomenon of the highly desirable change of visitor, under this demand, applies and bears automatic guiding service, and by automatic guiding app, new development occurs in tourism industry.Increasing visitor selects to install automatic guiding app, reaches the purpose of automatic guiding.Do now the software company of tourism industry, what major part adopted is be automatically positioned guide service, the sight spot calling correspondence according to location information is introduced, the information provided is very limited, the history of certain portrait of certain sight spot or certain building can not be accurate to, and by the label generated, label in the video of sight spot is mated, it is possible to solve this problem.
In the present embodiment, the guidance method based on sight spot label provided according to an aspect of the present invention, comprise the steps:
Step S1: determine visitor location by the location information of mobile equipment, determine, according to described visitor location, the target sight spot information that described visitor location is corresponding；
Step S2: make a look up in media library according to described target sight spot information, respectively obtains the sight spot video of correspondence, and described sight spot video includes multiple set video tab；
Step S3: by each being mated with the video tab in the video of described sight spot by described target sight spot information, obtain the target labels that described target sight spot information is corresponding；
Step S4: load the video segment that described target labels is corresponding.
When loading video segment, video segment is navigated to the position that target labels is corresponding by server, sets the language of video, video displaying ratio, the loading velocity of video, the definition of video, the pop-up etc. of video, can appreciate the video oneself liked.
In step S1, determine visitor location according to the location information of mobile equipment, determine the target sight spot information of visitor's periphery further according to described visitor location, particularly as follows:
-calculate the distance between multiple sight spots that described visitor location and periphery are contiguous, using the sight spot information at corresponding sight spot minimum for the distance between visitor location with sight spot as target sight spot information.Target sight spot information is sent to server end, is made a look up by the media library of server end.
In step S2, making a look up according to target sight spot information in media library, obtain the sight spot video of target sight spot information Corresponding matching, in this sight spot video, also include set video tab, described video tab generates in the following way:
Media library is set in advance in server end, when extracting video tab, by speech recognition technology, the voice in video information is converted to word, searches the high frequency vocabulary in word, and record edits described high frequency vocabulary as described video tab.
Such as, in determining Beihai park during the video tab of White Tower, " Beijing today " can will convert, by voice, the word that White Tower is introduced about the video information of White Tower introduction to, and search the high frequency vocabulary in the word that White Tower is introduced, specifically find " North Sea White Tower ", " concealed lamaist pagoda ", high frequency vocabulary such as " Jade Flowery Islets ", by knowledge base, these high frequency words are judged, the co-occurrence probabilities of these vocabulary and " White Tower " are more than given threshold, then all there is High relevancy with " White Tower ", then by " North Sea White Tower ", " concealed lamaist pagoda ", " Jade Flowery Islet " is all as the video tab of " White Tower ".
Described media library is set up in the following way:
Appearance position according to described video tab, is respectively divided into video segment by described video information；
Corresponding with described video segment for described video tab storage is formed media library.
Such as, about in the video information of White Tower introduction in " Beijing today ", according to video tab in " North Sea White Tower ", " concealed lamaist pagoda ", " Jade Flowery Islet " intercepts video segment in the video in " Beijing today ", i.e. the 3 ' 20 of " Beijing today " second collection " to 5 ' 34 " between video segment, the video segment that " White Tower " is introduced with by corresponding to video tab " North Sea White Tower ", " concealed lamaist pagoda ", " Jade Flowery Islet " structured storage that carries out, form media library.
In the present embodiment, in step S3, when described target sight spot information is each mated with the video tab in the video of described sight spot, comprise the steps:
Step S301: mated respectively by described target sight spot information sight spot each with media library video, chooses the target video of correspondence；Namely from each sight spot video of media library, the sight spot video mated the most with target sight spot information is extracted as target video；
When being mated respectively with each sight spot video by described target sight spot information, extract the video information that described sight spot video is corresponding；Described target sight spot information is mated with described video information, sees the matching degree that in video information, each key word is corresponding, choose the highest sight spot video of described video information Corresponding matching degree as described target video.Described video information includes: summary texts that described sight spot video is corresponding, title, title that the place page is corresponding, text that the place page is corresponding.
Step S302: extract video tab the highest with the matching degree of described target sight spot information in described target video as target labels, target video carries out binary search, extract in target video and choose the video tab mated the most as target labels, namely in the target video mated the most, choose the video tab that matching degree is best, further ensure matching effect, more agree with the target sight spot at visitor location place.
Such as, when visitor plays in Beihai park, position near White Tower, in media library, then make a look up the sight spot video of multiple North Sea White Tower, then extracting the corresponding video information of the sight spot video of all about North Sea White Tower, described video information includes summary texts corresponding to White Tower sight spot, North Sea video, the title of White Tower sight spot, North Sea video, title that video place, White Tower sight spot, the North Sea page is corresponding, text that video place, White Tower sight spot, the North Sea page is corresponding；
The corresponding video information of North Sea White Tower with the sight spot video of North Sea White Tower is mated, chooses video information matching degree corresponding to the sight spot video of North Sea White Tower the highest sight spot video target video as North Sea White Tower；And then extract video tab the highest with the matching degree of the sight spot information of North Sea White Tower in the target video of described North Sea White Tower as target labels.
In other embodiments, as one preferred embodiment, the video tab of each video of extracting directly, and combining target sight spot information mates, and obtains target labels, described step S3 comprises the steps:
Step S301: extract video tab corresponding in the video of each sight spot respectively by the given class of sight spot video, form each given class sight spot each self-corresponding tag set of video；In the present embodiment, each sight spot video of server end is grouped by given class, given class divides such as the label according to Manual definition such as " tourism ", " culture ", " history ", extract video tab corresponding in the video of each given class, form the video tab set that each given class is corresponding.
Step S302: described target sight spot information is made directly with the tag set of each given class respectively and mates, retrieve in each tag set respectively, the video tab of each given class mates target sight spot information, it is uniformly carried out screening by matching degree from tag set of all categories, thus choosing target labels, the follow-up video segment calling correspondence further according to target labels.
It is specially, when visitor plays in Beihai park, want the target video checking " North Sea White Tower ", then in the video tab pressing each given class of media library, extract multiple video tabs that in multiple sight spots video of " each North Sea White Tower ", each given class is corresponding respectively, " North Sea White Tower brief introduction " such as " tourism " classification, " concealed lamaist pagoda ", " Jade Flowery Islet ", " history built by North Sea White Tower " of " history " classification, " historical events that North Sea White Tower is relevant ", " the religion origin of North Sea White Tower " of " religion " classification etc. form each given class White Tower sight spot each self-corresponding tag set of video, the tag set of these given class mates according to target sight spot information, obtain the video tab of Corresponding matching of all categories, the video tab before row is chosen as target labels corresponding to target sight spot information by matching degree.
In step S4, during video segment corresponding to the described target labels of described loading, each target labels is set weight by described matching degree, plays out by weight selecting video fragment in each video segment of Corresponding matching.
Such as, when visitor plays in Beihai park, when wanting the target video checking " North Sea White Tower ", the weight of the target labels identical with North Sea White Tower is the highest, such as " North Sea White Tower brief introduction ", " history built by North Sea White Tower ", " the religion origin of North Sea White Tower "；The weight of the target labels close with North Sea White Tower meaning of a word secondly, such as " concealed lamaist pagoda "；The weight of the target labels being associated with North Sea White Tower meaning of a word is last, such as " Jade Flowery Islet ".
In other embodiments, the guidance method based on sight spot label provided by the invention also comprises the steps:
The visit scope that visitor is corresponding is determined according to visitor location；Wherein, described visit scope is provided with tourist road；
The target sight spot information that described visitor location is corresponding is determined according to described visitor location, particularly as follows:
Determine the visit direction on described tourist road of current visitor；
The target sight spot information that described visitor location is corresponding respectively is pre-determined according to visit direction；
The video segment that the described target labels of described loading is corresponding, particularly as follows: according to video segment corresponding to the pre-loaded described target labels in described visit direction.
Such as, when visitor is from behind the entrance Beihai park, Qianmen of Beihai park, start to walk to the left, the above-mentioned information of location acquisition of information by mobile equipment, and the tourist road according to Beihai park, visitor will go sight-seeing " beautiful urn " successively, " clock tower ", sight spots such as " draw victory booth " and " White Tower ", thus successively title corresponding for these sight spots and/or near synonym being sent to server end as target sight spot information according to visit direction, the media library of server is searched the sight spot video of these correspondences, the target labels of correspondence is obtained according to sight spot video matching, " beautiful urn " described in prestrain, " clock tower ", the video segment that the target labels of " draw victory booth " and " White Tower " is corresponding, thus when visitor searches described " beautiful urn " by target labels, " clock tower ", during video segment corresponding to the target labels of " draw victory booth " and " White Tower ", can directly play, wait without buffering.
According to the guidance method based on sight spot label provided by the invention, also comprise the steps:
When the user discover that described video information with described video tab not self-defined sight spot label to video information described time corresponding；
When described self-defined sight spot label is by after auditing, then setting up described self-defined sight spot label and video information corresponding relation.
Described sight spot video tab or described sight spot video subtab can pass through the carrying out of polyglot and set up；
Described video information is provided with captions storehouse；Described captions storehouse includes the letter of polyglot.
When using the guidance method based on sight spot label provided by the invention, the location information first passing through mobile equipment determines visitor location, namely realize being automatically positioned determining visitor location according to the GPS on mobile phone, as in " terra cotta warriors and horses museum ", determined, according to described visitor location, the target sight spot information that described visitor location is corresponding；Described target sight spot information includes " Lin Lan road, Lintong District ", " terra cotta warriors and horses museum ", " Qin Shihuang Tomb " and " the eighth-largest miracle ".
When visitor wants when checking the video segment in " terra cotta warriors and horses museum ", location information according to GPS can obtain the location information in " hole ", and " Lin Lan road, Lintong District ", " terra cotta warriors and horses museum " and " the eighth-largest miracle " etc. are the upper key word in " hole ", there is High relevancy, then these words are all as target sight spot information, can make a look up in the media library pre-set as key word according to these target sight spot informations, respectively obtain " Lin Lan road, Lintong District ", the sight spot video that the key word such as " terra cotta warriors and horses museum " and " the eighth-largest miracle " is corresponding, the present embodiment is the 5th collection matching degree in documentary film " legion of resurrection " is the highest, using this video as target video, described sight spot video includes multiple set video tab, such as " hole ", " world in ancient times ", " No. two holes " etc.；
By the video tab that target sight spot information " hole " is concentrated with the 5th in documentary film " legion of resurrection " is each mated, obtain target sight spot information " hole " target labels that sight spot information is corresponding " hole ", the video tab that target sight spot information " the eighth-largest miracle " is concentrated with the 5th in documentary film " legion of resurrection " is each mated, obtain target sight spot information " the eighth-largest miracle " target labels that sight spot information is corresponding " world in ancient times ", and then load the video segment that described target labels " world in ancient times " is corresponding with " hole " the 5th concentration in " legion of resurrection ", and according to matching degree, this video segment is gradually issued to the hands machine of user, described video segment is play for user.
The guide system based on sight spot label provided according to an aspect of the present invention, based on the guide system of sight spot label, it is characterised in that include such as lower module:
Module is determined at target sight spot, for determining visitor location by the location information of mobile equipment, determines, according to described visitor location, the target sight spot information that described visitor location is corresponding；
Sight spot video retrieval module, for making a look up in media library according to described target sight spot information, respectively obtains the sight spot video of correspondence, and described sight spot video includes multiple set video tab；
Target labels coupling acquisition module, by each being mated with the video tab in the video of described sight spot by described target sight spot information, obtains the target labels that described target sight spot information is corresponding；
Video segment load-on module, for loading the video segment that described target labels is corresponding.
Described video tab generates in the following way:
Media library is set in advance in service end, when extracting video tab, by speech recognition technology, the voice in video information is converted to word, searches the high frequency vocabulary in word, and record edits described high frequency vocabulary as described video tab.
Such as, in determining Beihai park during the video tab of White Tower, " Beijing today " can will convert, by voice, the word that White Tower is introduced about the video information of White Tower introduction to, and search the high frequency vocabulary in the word that White Tower is introduced, specifically find " North Sea White Tower ", " concealed lamaist pagoda ", high frequency vocabulary such as " Jade Flowery Islets ", by knowledge base, these high frequency words are judged, the co-occurrence probabilities of these vocabulary and " White Tower " are more than given threshold, then all there is High relevancy with " White Tower ", then by " North Sea White Tower ", " concealed lamaist pagoda ", " Jade Flowery Islet " is as the video tab of " White Tower ".
Described media library is set up in the following way:
Appearance position according to described video tab, is respectively divided into video segment by described video information；
Corresponding with described video segment for described video tab storage is formed media library.
Such as, about in the video information of White Tower introduction in " Beijing today ", according to video tab in " North Sea White Tower ", " concealed lamaist pagoda ", " Jade Flowery Islet " intercepts video segment in the video in " Beijing today ", i.e. the 3 ' 20 of " Beijing today " second collection " to 5 ' 34 " between video segment, the video segment " White Tower " introduced by the structured storage that carries out corresponding in " North Sea White Tower ", " concealed lamaist pagoda ", " Jade Flowery Islet ", forms media library with video tab.
In the present embodiment, described target labels coupling acquisition module includes such as lower module:
Sight spot video matching module, for being mated respectively by described target sight spot information sight spot each with media library video, chooses the target video of correspondence；Namely from each sight spot video of media library, the sight spot video mated the most with target sight spot information is extracted as target video；
When being mated respectively with each sight spot video by described target sight spot information, extract the video information that described sight spot video is corresponding；Described target sight spot information is mated with described video information, sees the matching degree that in video information, each key word is corresponding, choose the highest sight spot video of described video information Corresponding matching degree as described target video.Described video information includes: summary texts that described sight spot video is corresponding, title, title that the place page is corresponding, text that the place page is corresponding.
Target labels acquisition module, for extracting video tab the highest with the matching degree of described target sight spot information in described target video as target labels.Target video carries out binary search, extract in target video and choose the video tab mated the most as target labels, namely in the target video mated the most, choose the video tab that matching degree is best, further ensure matching effect, more agree with the target sight spot at visitor location place.
Such as, when visitor plays in Beihai park, at White Tower adnexa, in media library, then make a look up the sight spot video of multiple North Sea White Tower, then extracting the corresponding video information of the sight spot video of all about North Sea White Tower, described video information includes summary texts corresponding to White Tower sight spot, North Sea video, the title of White Tower sight spot, North Sea video, title that video place, White Tower sight spot, the North Sea page is corresponding, text that video place, White Tower sight spot, the North Sea page is corresponding；
The corresponding video information of North Sea White Tower with the sight spot video of North Sea White Tower is mated, chooses video information matching degree corresponding to the sight spot video of North Sea White Tower the highest sight spot video target video as North Sea White Tower；And then extract video tab the highest with the matching degree of the sight spot information of North Sea White Tower in the target video of described North Sea White Tower as target labels.
In other embodiments, as one preferred embodiment, the video tab of each video of extracting directly, and combining target sight spot information mates, and obtains target labels, described target labels coupling acquisition module includes:
Tag set generation module, for extracting video tab corresponding in the video of each sight spot respectively by the given class of sight spot video, forms each given class sight spot each self-corresponding tag set of video；In the present embodiment, each sight spot video of server end is grouped by given class, given class divides such as the label according to Manual definition such as " tourism ", " culture ", " history ", extract video tab corresponding in the video of each given class, form the video tab set that each given class is corresponding.
Target labels acquisition module, mate for described target sight spot information is made directly with the tag set of each given class respectively, retrieve in each tag set respectively, the video tab of each given class mates target sight spot information, it is uniformly carried out screening by matching degree from tag set of all categories, thus choosing target labels, the follow-up video segment calling correspondence further according to target labels.
It is specially, when visitor plays in Beihai park, want the target video checking " North Sea White Tower ", then in the video tab pressing each given class of media library, extract multiple video tabs that in multiple sight spots video of " each North Sea White Tower ", each given class is corresponding respectively, " North Sea White Tower brief introduction " such as " tourism " classification, " concealed lamaist pagoda ", " Jade Flowery Islet ", " history built by North Sea White Tower " of " history " classification, " historical events that North Sea White Tower is relevant ", " the religion origin of North Sea White Tower " of " religion " classification etc. form each given class White Tower sight spot each self-corresponding tag set of video, the tag set of these given class mates according to target sight spot information, obtain the video tab of Corresponding matching of all categories, the video tab before row is chosen as target labels corresponding to target sight spot information by matching degree.
During video segment corresponding to the described target labels of described loading, each target labels is set weight by described matching degree, plays out by weight selecting video fragment in each video segment of Corresponding matching.
Such as, when visitor plays in Beihai park, wanting the target video checking " North Sea White Tower ", the weight of the target labels identical with North Sea White Tower is the highest, such as " North Sea White Tower brief introduction ", " history built by North Sea White Tower ", " the religion origin of North Sea White Tower "；The weight of the target labels close with North Sea White Tower meaning of a word secondly, such as " concealed lamaist pagoda "；The weight of the target labels being associated with North Sea White Tower meaning of a word is last, such as " Jade Flowery Islet ".
Guide system based on sight spot label provided by the invention, also includes such as lower module:
Target sight spot information determines module, for determining, according to visitor location, the visit scope that visitor is corresponding；Wherein, described visit scope is provided with tourist road；
For determining that described visitor location is corresponding according to described visitor location, particularly as follows:
Determine the visit direction on described tourist road of current visitor；
The target sight spot information that described visitor location is corresponding respectively is pre-determined according to visit direction；
The video segment that the described target labels of described loading is corresponding, particularly as follows: according to video segment corresponding to the pre-loaded described target labels in described visit direction.
Such as, when visitor is from behind the entrance Beihai park, Qianmen of Beihai park, start to walk to the left, the above-mentioned information of location acquisition of information by mobile equipment, and the tourist road according to Beihai park, visitor will go sight-seeing " beautiful urn " successively, " clock tower ", sight spots such as " draw victory booth " and " White Tower ", thus according to visit direction prestrain successively " beautiful urn ", " clock tower ", the video segment that the target labels of " draw victory booth " and " White Tower " is corresponding, thus when visitor searches described " beautiful urn " by target labels, " clock tower ", during video segment corresponding to the target labels of " draw victory booth " and " White Tower ", can directly play, wait without buffering.
When the user discover that described video information with described video tab not self-defined sight spot label to video information described time corresponding；
When described self-defined sight spot label is by after auditing, then setting up described self-defined sight spot label and video information corresponding relation.
Described sight spot video tab or described sight spot video subtab can pass through the carrying out of polyglot and set up；
Described video information is provided with captions storehouse；Described captions storehouse includes the letter of polyglot.
When using the guide system based on sight spot label provided by the invention, the location information first passing through mobile equipment determines visitor location, namely realize being automatically positioned determining visitor location according to the GPS on mobile phone, as in " terra cotta warriors and horses museum ", determined, according to described visitor location, the target sight spot information that described visitor location is corresponding；Described target sight spot information includes " Lin Lan road, Lintong District ", " terra cotta warriors and horses museum ", " Qin Shihuang Tomb " and " the eighth-largest miracle ".
When visitor wants when checking the video segment in " terra cotta warriors and horses museum ", location information according to GPS can obtain the location information in " hole ", and " Lin Lan road, Lintong District ", " terra cotta warriors and horses museum " and " the eighth-largest miracle " etc. are the upper key word in " hole ", there is High relevancy, then these words are all as target sight spot information, can make a look up in the media library pre-set as key word according to these target sight spot informations, respectively obtain " Lin Lan road, Lintong District ", the sight spot video that the key word such as " terra cotta warriors and horses museum " and " the eighth-largest miracle " is corresponding, the present embodiment is the 5th collection matching degree in documentary film " legion of resurrection " is the highest, using this video as target video, described sight spot video includes multiple set video tab, such as " hole ", " world in ancient times ", " No. two holes " etc.；
By the video tab that target sight spot information " hole " is concentrated with the 5th in documentary film " legion of resurrection " is each mated, obtain target sight spot information " hole " target labels that sight spot information is corresponding " hole ", the video tab that target sight spot information " the eighth-largest miracle " is concentrated with the 5th in documentary film " legion of resurrection " is each mated, obtain target sight spot information " the eighth-largest miracle " target labels that sight spot information is corresponding " world in ancient times ", and then load the video segment that described target labels " world in ancient times " is corresponding with " hole " the 5th concentration in " legion of resurrection ", and according to matching degree, this video segment is gradually issued to the hands machine of user, described video segment is play for user.
In the present embodiment, the present invention is based on location information and determines target sight spot information, target sight spot information is each mated with the video tab in the sight spot video found in media library, obtain the target labels that target sight spot information is corresponding, and then obtaining the video segment of correspondence such that it is able to trickle sight spot is introduced to make sight spot video to support, improves the abundant degree of information, and need not strictly carry out file and call, reduce the maintenance intensity of information.Decapacitation of the present invention free sight spot label on map selects outside video, also support self-defined sight spot label, just can be shown on map after self-defining sight spot labeling requirement manager examination & verification, so that video tab is diversified, support trickle sight spot further, facilitate visitor to select.Sight spot of the present invention label is supported multilingual, can provide convenient for visitor all over the world.
Above specific embodiments of the invention are described.It is to be appreciated that the invention is not limited in above-mentioned particular implementation, those skilled in the art can make various deformation or amendment within the scope of the claims, and this has no effect on the flesh and blood of the present invention.
Claims (13)
1. the guidance method based on sight spot label, it is characterised in that comprise the steps:
Step S1: determine visitor location by the location information of mobile equipment, determine, according to described visitor location, the target sight spot information that described visitor location is corresponding；
Step S2: make a look up in media library according to described target sight spot information, respectively obtains the sight spot video of correspondence, and described sight spot video includes multiple set video tab；
Step S3: by each being mated with the video tab in the video of described sight spot by described target sight spot information, obtain the target labels that described target sight spot information is corresponding；
Step S4: load the video segment that described target labels is corresponding.
2. the guidance method based on sight spot label according to claim 1, it is characterised in that described video tab generates in the following way:
By speech recognition technology, the voice in video information being converted to word, search the high frequency vocabulary in word, utilize knowledge base that high frequency vocabulary is judged, record edits the described normalized result of high frequency vocabulary as described video tab.
3. the guidance method based on sight spot label according to claim 1 and 2, it is characterised in that described media library is set up in the following way:
Appearance position according to described video tab, is respectively divided into video segment by described video information；
Described video tab is formed media library with the corresponding storage respectively of described video segment.
4. the guidance method based on sight spot label according to claim 1, it is characterised in that according to described visitor location determine sight spot information mode particularly as follows:
-calculate the distance between described visitor location and contiguous multiple sight spots, using the sight spot information at corresponding sight spot minimum for the distance between visitor location with sight spot as target sight spot information.
5. the guidance method based on sight spot label according to claim 1, it is characterised in that described step S3, when each being mated with the video tab in the video of described sight spot by described target sight spot information, comprises the steps:
Step S301: mated respectively by described target sight spot information sight spot each with media library video, chooses the target video of correspondence；
Step S302: extract video tab the highest with the matching degree of described target sight spot information in described target video as target labels.
6. the guidance method based on sight spot label according to claim 5, it is characterised in that described when described target sight spot information is mated respectively with each sight spot video,
Extract the video information that described sight spot video is corresponding；Described video information includes: summary texts that described sight spot video is corresponding, title, title that the place page is corresponding, text that the place page is corresponding；
Described target sight spot information is mated with described video information, chooses the highest sight spot video of described video information Corresponding matching degree as described target video.
7. the guidance method based on sight spot label according to claim 1, it is characterised in that described step S3 includes:
Step S301: extract video tab corresponding in the video of each sight spot respectively by the given class of sight spot video, form each given class sight spot each self-corresponding tag set of video；
Step S302: described target sight spot information is made directly with the tag set of each given class respectively and mates, choose target labels by matching degree.
8. the guidance method based on sight spot label according to claim 1 or 7, it is characterized in that, during video segment corresponding to the described target labels of described loading, each target labels is set weight by described matching degree, plays out by weight selecting video fragment in each video segment of Corresponding matching.
9. the guidance method based on sight spot label according to claim 1, it is characterised in that also comprise the steps:
The visit scope that visitor is corresponding is determined according to visitor location；Wherein, described visit scope is provided with tourist road；
The target sight spot information that described visitor location is corresponding is determined according to described visitor location, particularly as follows:
Determine the visit direction on described tourist road of current visitor；
The target sight spot information that described visitor location is corresponding respectively is pre-determined according to visit direction；
The video segment that the described target labels of described loading is corresponding, particularly as follows: according to video segment corresponding to the pre-loaded described target labels in described visit direction.
10. the guide system based on sight spot label, it is characterised in that include such as lower module:
Module is determined at target sight spot, for determining visitor location by the location information of mobile equipment, determines, according to described visitor location, the target sight spot information that described visitor location is corresponding；
Sight spot video retrieval module, for making a look up in media library according to described target sight spot information, respectively obtains the sight spot video of correspondence, and described sight spot video includes multiple set video tab；
Target labels coupling acquisition module, by each being mated with the video tab in the video of described sight spot by described target sight spot information, obtains the target labels that described target sight spot information is corresponding；
Video segment load-on module, for loading the video segment that described target labels is corresponding.
11. the guide system based on sight spot label according to claim 10, it is characterised in that
Described target labels coupling acquisition module includes such as lower module:
Sight spot video matching module, for being mated respectively by described target sight spot information sight spot each with media library video, chooses the target video of correspondence；
Target labels acquisition module, for extracting video tab the highest with the matching degree of described target sight spot information in described target video as target labels.
12. the guide system based on sight spot label according to claim 11, it is characterised in that described when described target sight spot information is mated respectively with each sight spot video,
Extract the video information that described sight spot video is corresponding；Described video information includes: summary texts that described sight spot video is corresponding, title, title that the place page is corresponding, text that the place page is corresponding；
Described target sight spot information is mated with described video information, chooses the highest sight spot video of described video information Corresponding matching degree as described target video.
13. the guide system based on sight spot label according to claim 10, it is characterised in that described target labels coupling acquisition module includes:
Tag set generation module, for extracting video tab corresponding in the video of each sight spot respectively by the given class of sight spot video, forms each given class sight spot each self-corresponding tag set of video；
Target labels acquisition module, mates for being made directly with the tag set of each given class respectively by described target sight spot information, chooses target labels by matching degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610032030.XA CN105718547B (en) | 2016-01-18 | 2016-01-18 | Guidance method based on sight spot label and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610032030.XA CN105718547B (en) | 2016-01-18 | 2016-01-18 | Guidance method based on sight spot label and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105718547A true CN105718547A (en) | 2016-06-29 |
| CN105718547B CN105718547B (en) | 2018-11-13 |
Family
ID=56147247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610032030.XA Expired - Fee Related CN105718547B (en) | 2016-01-18 | 2016-01-18 | Guidance method based on sight spot label and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105718547B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106412623A (en) * | 2016-10-26 | 2017-02-15 | 山东浪潮商用系统有限公司 | Dynamic background implementation method enabling content relevancy |
| CN106550268A (en) * | 2016-12-26 | 2017-03-29 | Tcl集团股份有限公司 | Method for processing video frequency and video process apparatus |
| CN107659891A (en) * | 2016-07-25 | 2018-02-02 | 杨汉瑜 | Travel information is shown and voice synchronous playing system and method |
| WO2018094573A1 (en) * | 2016-11-22 | 2018-05-31 | Volkswagen (China) Investment Co., Ltd. | Method and apparatus for processing a video |
| CN108257062A (en) * | 2017-12-28 | 2018-07-06 | 合肥壹佰教育科技有限公司 | A kind of cultural spreading Intelligentized regulating and controlling system |
| CN108521587A (en) * | 2018-04-03 | 2018-09-11 | 优视科技有限公司 | Short method for processing video frequency, device and mobile terminal |
| CN109005382A (en) * | 2018-06-27 | 2018-12-14 | 深圳市轱辘汽车维修技术有限公司 | A kind of video acquisition management method and server |
| CN109189957A (en) * | 2018-08-30 | 2019-01-11 | 维沃移动通信有限公司 | A kind of processing method and equipment of media data |
| CN110929091A (en) * | 2019-11-18 | 2020-03-27 | 江苏燕宁工程科技集团有限公司 | Query method and system for road operation and maintenance video inspection |
| CN111131904A (en) * | 2019-12-31 | 2020-05-08 | 维沃移动通信有限公司 | Video playing method and head-mounted electronic equipment |
| CN111506771A (en) * | 2020-04-22 | 2020-08-07 | 上海极链网络科技有限公司 | Video retrieval method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810276A (en) * | 2014-02-14 | 2014-05-21 | 王强 | Video search method and device |
| RU2013147482A (en) * | 2013-10-25 | 2015-04-27 | Открытое акционерное общество "Красногорский завод им. С.А. Зверева" | COMMANDER COMBINED AIM AND OBSERVATION COMPLEX |
| CN104700751A (en) * | 2015-01-28 | 2015-06-10 | 深圳市元征科技股份有限公司 | Scenic spot information acquisition method and device |
-
2016
- 2016-01-18 CN CN201610032030.XA patent/CN105718547B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2013147482A (en) * | 2013-10-25 | 2015-04-27 | Открытое акционерное общество "Красногорский завод им. С.А. Зверева" | COMMANDER COMBINED AIM AND OBSERVATION COMPLEX |
| CN103810276A (en) * | 2014-02-14 | 2014-05-21 | 王强 | Video search method and device |
| CN104700751A (en) * | 2015-01-28 | 2015-06-10 | 深圳市元征科技股份有限公司 | Scenic spot information acquisition method and device |
Non-Patent Citations (2)
| Title |
|---|
| SARADA PRASAD GOCHHAYAT.ETC: "An efficient way of providing information in ubiquitous tourist system", 《2015 6TH INTERNATIONAL CONFERENCE OF INFORMATION AND COMMUNICATION TECHNOLOGY FOR EMBEDDED SYSTEMS》 * |
| 刘应成: "基于智能手机的导游系统设计", 《计算机应用与软件》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107659891A (en) * | 2016-07-25 | 2018-02-02 | 杨汉瑜 | Travel information is shown and voice synchronous playing system and method |
| CN106412623A (en) * | 2016-10-26 | 2017-02-15 | 山东浪潮商用系统有限公司 | Dynamic background implementation method enabling content relevancy |
| CN109983760A (en) * | 2016-11-22 | 2019-07-05 | 大众汽车（中国）投资有限公司 | Method for processing video frequency and equipment |
| WO2018094573A1 (en) * | 2016-11-22 | 2018-05-31 | Volkswagen (China) Investment Co., Ltd. | Method and apparatus for processing a video |
| CN109983760B (en) * | 2016-11-22 | 2021-12-21 | 大众汽车（中国）投资有限公司 | Video processing method and device |
| US11107502B2 (en) | 2016-11-22 | 2021-08-31 | Volkswagen Aktiengesellschaft | Method and apparatus for processing a video |
| CN106550268A (en) * | 2016-12-26 | 2017-03-29 | Tcl集团股份有限公司 | Method for processing video frequency and video process apparatus |
| CN106550268B (en) * | 2016-12-26 | 2020-08-07 | Tcl科技集团股份有限公司 | Video processing method and video processing device |
| CN108257062A (en) * | 2017-12-28 | 2018-07-06 | 合肥壹佰教育科技有限公司 | A kind of cultural spreading Intelligentized regulating and controlling system |
| CN108521587B (en) * | 2018-04-03 | 2021-06-29 | 阿里巴巴（中国）有限公司 | Short video processing method and device and mobile terminal |
| CN108521587A (en) * | 2018-04-03 | 2018-09-11 | 优视科技有限公司 | Short method for processing video frequency, device and mobile terminal |
| CN109005382A (en) * | 2018-06-27 | 2018-12-14 | 深圳市轱辘汽车维修技术有限公司 | A kind of video acquisition management method and server |
| CN109189957A (en) * | 2018-08-30 | 2019-01-11 | 维沃移动通信有限公司 | A kind of processing method and equipment of media data |
| CN110929091A (en) * | 2019-11-18 | 2020-03-27 | 江苏燕宁工程科技集团有限公司 | Query method and system for road operation and maintenance video inspection |
| CN111131904A (en) * | 2019-12-31 | 2020-05-08 | 维沃移动通信有限公司 | Video playing method and head-mounted electronic equipment |
| CN111131904B (en) * | 2019-12-31 | 2022-03-22 | 维沃移动通信有限公司 | Video playing method and head-mounted electronic equipment |
| CN111506771A (en) * | 2020-04-22 | 2020-08-07 | 上海极链网络科技有限公司 | Video retrieval method, device, equipment and storage medium |
| CN111506771B (en) * | 2020-04-22 | 2021-04-02 | 上海极链网络科技有限公司 | Video retrieval method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105718547B (en) | 2018-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105718547A (en) | Tour guide method and system based on scenic spot label | |
| CN102646022B (en) | Method and device for obtaining candidate | |
| CN101650958B (en) | Extraction method and index establishment method of movie video scene fragment | |
| CN105094760B (en) | A kind of picture indicia method and device | |
| CN103914513B (en) | A kind of entity input method and device | |
| KR20180025121A (en) | Method and apparatus for inputting information | |
| CN109635295B (en) | Poetry retrieval method and system based on semantic analysis | |
| CN102289322A (en) | Method and system for processing handwriting | |
| CN103631819A (en) | Method and system for naming picture | |
| CN103150356B (en) | A kind of the general demand search method and system of application | |
| CN102855317B (en) | A kind of multi-mode indexing means and system based on demonstration video | |
| CN101840406A (en) | Place name searching device and system | |
| CN102650993A (en) | Index establishing and searching methods, devices and systems for audio-video file | |
| JP2016061954A (en) | Interactive device, method and program | |
| CN110019852A (en) | Multimedia resource searching method and device | |
| CN104090968B (en) | The method and apparatus that a kind of intelligent information is pushed | |
| CN109977382A (en) | Verse generates the training method of model, writes the poem method and device automatically | |
| CN104199837A (en) | Information output method and electronic equipment | |
| CN102970618A (en) | Video on demand method based on syllable identification | |
| CN107679128A (en) | Information display method and device, electronic equipment and storage medium | |
| CN106653015A (en) | Speech recognition method by and apparatus for robot | |
| CN104679755A (en) | Voice frequency searching method, voice frequency searching device and terminal | |
| CN110008314B (en) | Intention analysis method and device | |
| Tseng et al. | A mobile environment for Chinese language learning | |
| CN110134817A (en) | A kind of storage method of recording file, searching method and relevant apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181113 Termination date: 20200118 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |