CN107679189A - A kind of point of interest update method, device, server and medium - Google Patents
A kind of point of interest update method, device, server and medium Download PDFInfo
- Publication number
- CN107679189A CN107679189A CN201710920000.7A CN201710920000A CN107679189A CN 107679189 A CN107679189 A CN 107679189A CN 201710920000 A CN201710920000 A CN 201710920000A CN 107679189 A CN107679189 A CN 107679189A
- Authority
- CN
- China
- Prior art keywords
- interest
- point
- updated
- feature
- sample
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of point of interest update method, device, server and medium, it is related to geographical information technology neighborhood.This method includes：Obtain point of interest to be updated；Based on the feature of point of interest to be updated, the point of interest to be updated is classified；According to classification results, based on different classes of corresponding different default more new standards, the point of interest to be updated is updated.A kind of point of interest update method, device, server and medium provided in an embodiment of the present invention; realize and be updated according to the feature of point of interest; so as to improve the accuracy rate of point of interest renewal; and then solve new point of interest and can not update on line; the problem of old, failure point of interest can not be cleaned out in time, and important point of interest cannot be protected.
Description
Technical field
The present embodiments relate to geographical information technology neighborhood, more particularly to a kind of point of interest update method, device, service
Device and medium.
Background technology
The figure shown in electronic map is substantially made up of point-line-surface, important composition portion of the point of interest as point data
It is part indispensable in electronic map to divide；Any building that can be named in theory, region and certain sense point
Interest point data is can serve as to be shown, for example, Tian An-men, certain restaurant, cell, parking lot, bus station etc..
It is to the update method of interest point in electronic map currently：Using the upper offline mechanism of unified standard, to electronically
Point of interest in figure is updated.Exemplified by offline, lower line standard requires that accuracy rate is 90%, even from 10,000 points of interest
The 100 sample points of interest extracted are found by factual survey, wherein more than 90 points of interest are that reality has been not present, then
10,000 points of interest are sought unity of action offline.So as to cause, it is actually to deposit that 1,000 points of interest are there may be in 10,000 points of interest
, and by by mistake offline.Similarly, if the 100 sample points of interest extracted from 10,000 points of interest are found by factual survey, its
In only 60 points of interest be that reality has been not present, then by 10,000 points of interest it is unified do not perform it is offline.So as to cause, 1
It is to not actually exist that 6,000 points of interest are there may be in ten thousand points of interest, and can not be by offline situation.
Inventor has found that the existing update method to point of interest has following defect during the present invention is realized:Newly
Point of interest can not update on line, it is old, failure point of interest can not be cleaned out in time；And important interest
Point cannot be protected.
The content of the invention
The present invention provides a kind of point of interest update method, device, server and medium, to realize the feature according to point of interest
It is updated, can not be updated to so as to improve the accuracy rate of point of interest renewal, and then solve new point of interest on line, it is old
, the point of interest of failure can not be cleaned out in time, and the problem of important point of interest cannot be protected.
In a first aspect, the embodiments of the invention provide a kind of point of interest update method, applied to server, this method bag
Include：
Obtain point of interest to be updated；
Based on the feature of point of interest to be updated, the point of interest to be updated is classified；
According to classification results, based on different classes of corresponding different default more new standards, the interest to be updated is clicked through
Row renewal.
Further, the feature based on point of interest to be updated, the point of interest to be updated is classified, including：
Based on the feature of point of interest to be updated, the disaggregated model completed according to training in advance, to the point of interest to be updated
Classified.
Further, before point of interest to be updated is obtained, in addition to：
Build sample interest point data collection；
Determine the feature of the point of interest；
According to the feature of the sample interest point data collection and the point of interest, the disaggregated model is trained and surveyed
Examination.
Further, sample interest point data collection is built, including：
According to default structure rule, the corresponding sample interest point data each classified is filtered out from pre-stored data.
Further, the feature of the point of interest includes：Categorical attribute, retrieval amount, positioning amount, base map mark, basis ground
At least one of thing, set membership, brand and data mobility.
Further, the disaggregated model is trained and tested, including：
Based on the proportionate relationship between the different classification preset stored amounts, concentrate and determine from the sample interest point data
The training of the different classifications and the quantity of test sample point of interest；
Using the sample interest point data of the different classifications of the quantity, the disaggregated model is trained and surveyed
Examination.
Further, the disaggregated model is trained and tested, including：
After testing the disaggregated model, whether the accuracy rate and recall rate that judge the disaggregated model are more than
Set accuracy rate threshold value and setting recall rate threshold value；
If so, then complete the training to the disaggregated model.
Further, according to classification results, based on different classes of corresponding different default more new standards, to described to be updated
Point of interest is updated, including：
More new standard is set according to corresponding to the affiliated classification of the point of interest to be updated, to the point of interest to be updated
Basic field is modified, and the point of interest to be updated is reached the standard grade or offline processing.
Further, the feature based on point of interest to be updated, carrying out classification to the point of interest to be updated includes：
According to the feature of the point of interest to be updated, the importance and mutability of the point of interest to be updated are determined；
It is at least two by the Partition for Interest Points to be updated according to the importance and mutability of the point of interest to be updated
Classification.
Second aspect, the embodiment of the present invention additionally provide a kind of point of interest updating device, applied to server, the device bag
Include：
Acquisition module, for obtaining point of interest to be updated；
Sort module, for the feature based on point of interest to be updated, the point of interest to be updated is classified；
Update module, for according to classification results, based on different classes of corresponding different default more new standards, being treated to described
Renewal point of interest is updated.
Further, sort module includes：
Taxon, for the feature based on point of interest to be updated, the disaggregated model completed according to training in advance, to described
Point of interest to be updated is classified.
Further described point of interest updating device, in addition to：
Sample builds module, for before point of interest to be updated is obtained, building sample interest point data collection；
Characteristic determination module, for determining the feature of the point of interest；
Training module, for the feature according to the sample interest point data collection and the point of interest, to the classification mould
Type is trained and tested.
Further, sample structure module includes：
Sample construction unit, for according to default structure rule, the corresponding sample each classified to be filtered out from pre-stored data
This interest point data.
Further, update module includes：
Updating block, for setting more new standard corresponding to the affiliated classification according to the point of interest to be updated, to described
The basic field of point of interest to be updated, and the point of interest to be updated is reached the standard grade or offline processing.
The third aspect, the embodiment of the present invention additionally provide a kind of server, and the server includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes the point of interest update method as described in any in claim 1-9.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer-readable recording medium, are stored thereon with computer
Program, the point of interest update method as described in any in claim 1-9 is realized when the program is executed by processor.
The embodiment of the present invention is classified, so by the feature according to point of interest to be updated to the point of interest to be updated
Afterwards to the sorted point of interest to be updated, it is updated based on different classes of corresponding different default more new standards.Realize
It is updated according to the feature of point of interest, so as to improve the accuracy rate of point of interest renewal.Meanwhile for different classes of point of interest
Using different default more new standards, wanted for example, presetting reaching the standard grade in more new standard corresponding to variable category of interest with offline
Ask setting lower, so that new point of interest is updated on line, old, failure point of interest is cleaned out in time；It is important
Category of interest corresponding to preset reaching the standard grade in more new standard and it is offline require to set it is high, to be protected to important point of interest
Shield.
Brief description of the drawings
Fig. 1 is a kind of flow chart for point of interest update method that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow chart for point of interest update method that the embodiment of the present invention two provides；
Fig. 3 is a kind of flow chart for point of interest update method that the embodiment of the present invention three provides；
Fig. 4 is a kind of flow chart to disaggregated model training and test that the embodiment of the present invention three provides；
Fig. 5 is a kind of classification results schematic diagram that the embodiment of the present invention three provides；
Fig. 6 is a kind of structural representation for point of interest updating device that the embodiment of the present invention four provides；
Fig. 7 is a kind of structural representation for server that the embodiment of the present invention five provides.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of flow chart for point of interest update method that the embodiment of the present invention one provides.The present embodiment is applicable to
Situation about being updated to the point of interest in electronic map.This method can be performed by a kind of point of interest updating device, the dress
Putting can be realized by the mode of software and/or hardware.Typically, the device can be configured at server corresponding to electronic map
In.Referring to Fig. 1, the point of interest update method that the present embodiment provides includes：
S110, obtain point of interest to be updated.
Specifically, obtaining the mode of point of interest to be updated can be, server obtains according to predetermined period and setting order
Point of interest in electronic map, as point of interest to be updated；Or when the renewal request for receiving terminal to server transmission
When, the point of interest in electronic map is obtained according to setting order, as point of interest to be updated；Or when server detects use
When family logs in map of navigation electronic client by terminal, the point of interest in electronic map is obtained according to setting order, as treating
Update point of interest.
S120, the feature based on point of interest to be updated, the point of interest to be updated is classified.
Wherein, the feature of point of interest to be updated is the characteristics of point of interest is different from other points of interest.Pass through interest to be updated
The feature of point can determine certain attribute of point of interest to be updated, such as importance, mutability etc..According to one or more attributes
The point of interest to be updated can be carried out to the division of at least one classification, for example, by the feature of above-mentioned point of interest to be updated,
The importance and mutability of point of interest are determined, then the importance and mutability according to point of interest, by Partition for Interest Points to be updated
For at least two classifications.
Specifically, the feature of above-mentioned point of interest to be updated can include：Categorical attribute, retrieval amount, positioning amount, base map mark
At least one of note, basic atural object, set membership, brand and data mobility.
Wherein, categorical attribute is one or more attributes of point of interest, for example, equally can be point of interest importance and/
Or mutability.Categorical attribute can directly determine by the existing label to point of interest and classification information, can also be by being marked to this
The operation result that label and classification information further set strategy determines.For example, two are carried out to point of interest label using setting strategy
Used after suboptimization；Specific setting strategy can utilize interest point name suffix attribute map tags and trusted sources' label
The methods of ballot.
For convenience of the mark to categorical attribute, for different classifications attribute, centrifugal pump 0,1, -1 etc. can be normalized to, will
The centrifugal pump is as categorical attribute value.So that categorical attribute is mutability as an example, wherein 0 representative is not variable, such as：Real estate, basis
Atural object, shopping center, means of transportation, tourist attractions, incorporated business, government organs, school, hospital, small towns village etc., 1 represents easily
Become, such as：Hotel, cuisines, amusement and recreation, finance, service for life, beauty etc., -1 represents other situations.Optionally, can be direct
Using categorical attribute value as above-mentioned categorical attribute, such as 0 represents that the point of interest is not variable, and 1 represents that the point of interest is variable, and 2 represent
The point of interest is extremely important, and 3 represent that the point of interest is important, and 4 represent that the point of interest is inessential etc.；It can also be arrived by label mapping
Specific property value, realizes the mark of categorical attribute, for example, by mutability label mapping to property value 0 represent not variable,
By importance label mapping to property value 0 represent extremely important.
Retrieval amount refers to number of clicks of the point of interest in client setting time section, shows number and/or detection number.
Specifically first retrieval amount can be by size segmented, then be described using Category Attributes value is set.Wherein, setting time section can be with
Set as needed, can be typically one month.
Mobile client is surfed the Net in certain point of interest by connecting the wireless network of the point of interest, and the data can be stored to fixed
Position big data, by counting in setting time section, the quantity of different point of interest connection wireless terminals in big data is positioned, as fixed
Position amount.Similar to the processing mode of retrieval amount, first positioning amount can be segmented by size, then using set Category Attributes value come
Description.Wherein, setting time section can equally be set as needed, can be typically one month.
Base map mark refers to whether point of interest shows in the base map of electronic map, and it can be directly from bottom corresponding to electronic map
Obtained in figure, specifically can describe whether point of interest shows on base map with 0 and 1, such as point of interest is described in map with 1
Show.Wherein, base map is only elementary contour and for marking and drawing or representing the maps of geographic information contents.
Basic atural object reaction is whether point of interest is basic atural object, wherein basic atural object represents natural or artificial on ground
The fixed object of formation.Specific basic atural object can obtain from the existing terrain object attribute of point of interest.It is if it is understood that emerging
Interest point is basic atural object, then the point of interest is not variable point of interest.
Set membership refers to the relations of dependence between point of interest, if the sub- point of interest for depending on current interest point is more, table
It is more probably not variable data to show the point of interest.
Brand refers to whether point of interest has chain brand to mark, and can specifically be described with 0 or 1.
Data movement refers to that within the cycle regular hour variation frequency of interest point data can reflect the point of interest
Mutability.
Typically, the feature based on point of interest to be updated, carrying out classification to the point of interest to be updated includes：
According to the feature of the point of interest to be updated, the importance and mutability of the point of interest to be updated are determined；
It is at least two by the Partition for Interest Points to be updated according to the importance and mutability of the point of interest to be updated
Classification.
Optionally, can be by the way that the setting attribute of the feature of point of interest to be updated and character pair be determined into rule is carried out
Judge, determine the importance and mutability of point of interest；Then according to the importance and mutability of determination, with setting importance threshold value
Compare with mutability threshold value, be at least two classifications by the Partition for Interest Points to be updated；Point of interest to be updated can also be utilized
Feature carry out model structure, point of interest to be updated is classified automatically using the model of structure.
S130, according to classification results, based on different classes of corresponding different default more new standards, to the interest to be updated
Point is updated.
Wherein, feature-set of the more new standard according to different classes of corresponding point of interest is preset, for example, variable interest class
Reaching the standard grade in not corresponding default more new standard requires that setting is lower with offline；Renewal mark is preset corresponding to important category of interest
Reaching the standard grade in standard requires to set height with offline.
Typically, according to classification results, based on different classes of corresponding different default more new standards, to described to be updated emerging
Interest point is updated, including：
More new standard is set according to corresponding to the affiliated classification of the point of interest to be updated, to the point of interest to be updated
Basic field is modified, and the point of interest to be updated is reached the standard grade or offline processing.
Wherein, basic field is to identify the significant field of point of interest, such as interest point name.
Notice that reaching the standard grade in the present embodiment refers to point of interest being updated in electronic map, it is offline to refer to point of interest from electricity
Deleted in sub- map.
Specifically, reach the standard grade includes with offline processing：The mounting and merging of point of interest.Wherein, mounting refers to current interest
Point is established with the point of interest showed in electronic map and associated, and is then associated display, and specific mounting is hung including basis again
Connect and mounted with details.Basis mounting is to close the basic field of point of interest of the current interest point data with showing in electronic map
Connection, details mounting are to associate current interest point data with the details page of the point of interest showed in electronic map.
Wherein, details page is the introduction to the details of point of interest, meets to set in click point of interest or displaying ratio chi
During certainty ratio chi condition, shown.
Above-mentioned merging is that the point of interest for being directed to the point of interest that does not mount or repeating is carried out, specifically can be according to setting
It is fixed to merge rule, multiple points of interest for not mounting or repeating are merged into one.Wherein, setting merging rule can be according to need
Set, can specifically combine the influence factors such as importance, mutability and the on-line time of point of interest and be set.
The technical scheme of the embodiment of the present invention, by the feature according to point of interest to be updated, to the point of interest to be updated
Classified, then to the sorted point of interest to be updated, entered based on different classes of corresponding different default more new standards
Row renewal.Realization is updated according to the feature of point of interest, so as to improve the accuracy rate of point of interest renewal.Meanwhile for difference
The point of interest of classification uses different default more new standards, for example, being preset corresponding to variable category of interest in more new standard
Reach the standard grade with it is offline require to set it is lower so that new point of interest is updated on line, the old, point of interest that fails in time by
Clean out；Preset reaching the standard grade in more new standard corresponding to important category of interest to require to set height with offline, with to important
Point of interest is protected.
Embodiment two
Fig. 2 is a kind of flow chart for point of interest update method that the embodiment of the present invention two provides.The present embodiment is above-mentioned
Itd is proposed on the basis of embodiment, the alternative classified using disaggregated model to point of interest to be updated.Referring to Fig. 2, sheet
The point of interest update method that embodiment provides includes：
S210, structure sample interest point data collection.
Typically, sample interest point data collection is built, can be included：
According to default structure rule, the corresponding sample interest point data each classified is filtered out from pre-stored data.
Wherein, presetting structure rule can be set according to specific category, specifically may determine that the interest of corresponding classification
Whether the feature of point meets to set feature request, if satisfied, the then sample interest using the point of interest of the category as corresponding classification
Point data.
S220, the feature for determining the point of interest.
The feature of point of interest is consistent with the feature of the point of interest to be updated described in above-described embodiment one herein, herein no longer
Repeat.Specifically, the feature of above-mentioned point of interest to be updated can include：Categorical attribute, retrieval amount, positioning amount, base map mark, base
At least one of plinth atural object, set membership, brand and data mobility.
S230, the feature according to the sample interest point data collection and the point of interest, are instructed to the disaggregated model
Practice and test.
Wherein, the disaggregated model can be the model based on Adaboost algorithm, based on post-class processing
The model or other models of (Classification And Regression Tree, CART), the feature of disaggregated model with
Based on discrete features, higher is required, it is necessary to which output category confidence level, can be typically gradient lifting to the disposal ability of feature
Set (Gradient Boosting Decison Tree, GBDT) model.
To improve the training accuracy rate of disaggregated model, the disaggregated model is trained and tested, including：
Proportionate relationship between preset stored amount based on the different classifications, concentrated from the sample interest point data true
The training of the fixed different classifications and the quantity of test sample point of interest；
Using the sample interest point data of the different classifications of the quantity, the disaggregated model is trained and surveyed
Examination.
Exemplary, if there are first category and second category, and the preset stored amount of the two is respectively 100,000 points of interest
With 200,000 points of interest, then according to the preset stored amount ratio 1 of the two:2, concentrated from sample interest point data and select 10,000 first
The sample point of interest of the sample point of interest of classification and 20,000 second categories, or the sample point of interest and 80,000 of 40,000 first category
The sample point of interest of individual second category, the disaggregated model is trained and tested.
To ensure the accuracy rate of disaggregated model training, the disaggregated model is trained and tested, can be included：
After testing the disaggregated model, whether the accuracy rate and recall rate that judge the disaggregated model are more than
Set accuracy rate threshold value and setting recall rate threshold value；
If so, then complete the training to the disaggregated model.
S240, point of interest to be updated is obtained, determine the feature of the point of interest to be updated.
S250, the feature based on the point of interest to be updated, the disaggregated model completed according to training in advance, are treated more to described
New interest point is classified.
S260, according to classification results, based on different classes of corresponding different default more new standards, to the interest to be updated
Point is updated.
The technical scheme of the embodiment of the present invention, point of interest to be updated is classified by disaggregated model, because the machine of being based on
The disaggregated model of device study has self-organizing, adaptive and self-learning ability, and being particularly suitable for processing needs while consider many factors
With condition, inaccurate and fuzzy information-processing problem.So as to improve the classification accuracy to point of interest to be updated.
Embodiment three
Fig. 3 is a kind of flow chart for point of interest update method that the embodiment of the present invention three provides.The present embodiment is above-mentioned
A kind of alternative proposed on the basis of embodiment.Referring to Fig. 3, the point of interest update method that the present embodiment provides includes：
S310, structure sample interest point data collection.
Wherein, sample interest point data collection includes two parts：Training data and test data, data composition mainly include
Five sources below：Superelevation essence class, high-precision class, weak variable class, strong variable class and the data without retrieval class.To improve the essence of model
Accuracy, it is desirable to which training sample distribution is as balanced as possible, can farthest portray all data distribution situations.Data set construction
Basic ideas are：Tactful preliminary delineation and the artificial screening that becomes more meticulous, it is specific as follows：
First screened from existing interest point data base using setting selection rule with Primary Location, then manually to instruction
Practice set and carry out purification acquisition.Wherein, setting selection rule can be set with reference to the feature of above-mentioned point of interest.
For example, the data for weak variable class：The first not mutability in basic atural object, categorical attribute and retrieval amount etc.
Carry out Primary Location；For the data of strong variable class：First not mutability, data source and retrieval amount in categorical attribute etc.
Carry out Primary Location；For the data without retrieval class：First using the data that retrieval amount is 0 as the data without retrieval class.
Typically, superelevation essence class, high-precision class, weak variable class, strong variable class and the preset stored amount without retrieval class are respectively：
50w, 100w, 800w, 1200w and 2300w points of interest.Wherein, number of the sample interest point data collection proportioning mode in table 1
Amount is matched.
Table 1
Wherein, 500,000 data are used for the training for making disaggregated model, and the test that 300,000 data are used to do disaggregated model is tested
Card.
S320, the feature for determining the point of interest.
S330, the feature according to the sample interest point data collection and the point of interest, are instructed to the disaggregated model
Practice and test.
Specifically, the accuracy rate requirement to disaggregated model is 95%, recall rate requirement is 80%.
S340, point of interest to be updated is obtained, determine the feature of the point of interest to be updated.
S350, the feature based on the point of interest to be updated, the disaggregated model completed according to training in advance, are treated more to described
New interest point is classified, wherein the classification includes：Superelevation essence class, high-precision class, weak variable class, strong variable class and without retrieval
Class.
Wherein superelevation essence class is epochmaking to have superelevation retrieval amount, superelevation positioning amount, extremely not variable superfrequency emerging
Interesting, data scale is 500,000；High-precision class is important, has high retrieval amount, high positioning amount, not variable high frequency point of interest,
Data scale is 1,000,000；The positioning of 3rd class is that emphasis ensures data accuracy, supports the deep bid quality of data, has mutability
Weak point of interest, data scale are 8,000,000, and such point of interest can include:Real estate, shopping center, means of transportation, tourism scape
The point of interest of the classes such as point, incorporated business, government organs, medical treatment；The positioning of 4th class is the coverage rate and rope that emphasis ensures data
Draw it is ageing, support deep bid data cover, the strong point of interest of mutability, data scale be 12,000,000, such point of interest can wrap
Include：Hotel, cuisines, amusement and recreation, finance, service for life and beauty's class point of interest；The positioning of 5th class is to combine user search
Behavior, circulated to other classes, retrieval end subscriber clicks on less or without click point of interest, and data scale is 23,000,000.
S360, according to classification results, based on different classes of corresponding different default more new standards, to the interest to be updated
Point is updated.
Specifically, default more new standard is corresponding to superelevation essence class：Meet that modification authority can just be carried out to such data
Modification, while accuracy rate, which is at least 99%, to be required to modification content, concrete modification rule is that basic field does not allow to change, and is not permitted
Perhaps basis mounting, it is allowed to which details are mounted, and such point of interest is retained after merging.So as to ensure accuracy rate and non-duplicate rate.
More new standard is preset corresponding to high-precision class is：Concrete modification rule is that the modification to basic field performs first post-trial hair
Or the standard examined afterwards is first sent out, but require that modification accuracy rate is at least 99%, it is allowed to basis mounting, also require that modification accuracy rate extremely
It is 99% less, it is allowed to which details are mounted, and such point of interest is retained after merging.Wherein, first post-trial hair is first to audit to deliver afterwards；After first sending out
It is first to deliver and then audited together by user to examine, and is fed back.
More new standard is preset corresponding to 3rd class is：Concrete modification rule, the modification content of basic field require accuracy rate
At least 95%, it is allowed to basis mounting, but require that accuracy rate is at least 99%, it is allowed to which details mount, according to click volume during merging
Direction, preferentially retain high click volume point of interest.Integral Thought is the principle for adhering to " sternly enter and sternly go out " offline in data.
More new standard is preset corresponding to 4th class is：Concrete modification rule, the modification content of basic field require accuracy rate
At least 95%, it is allowed to basis mounting, but require that accuracy rate is at least 95%, it is allowed to which details mount, according to click volume during merging
Direction, preferentially retain high click volume point of interest.Integral Thought is the principle for adhering to " width enters width and gone out " offline in data.
More new standard is preset corresponding to 5th class is：Concrete modification rule, the modification content of basic field require accuracy rate
At least 95%, it is allowed to basis mounting, but require that accuracy rate is at least 99%, it is allowed to which details mount, and are preferentially merged during merging.
By being merged for point of interest, so as to be circulated to other classes.
Referring to Fig. 4, the training to above-mentioned disaggregated model and test in actual applications can be described as：It is determined that setting training
Quantity, superelevation essence class, high-precision class, weak variable class, strong variable class and without retrieval class data as training data；Extraction training number
According to feature；Using the feature of the training data of extraction, it is trained based on selected disaggregated model；It is determined that setting test quantity
, superelevation essence class, high-precision class, weak variable class, strong variable class and without retrieval class data as test data；Extract test data
Feature；Using the feature of the test data of extraction, the current class model obtained to training is tested；Calculate current class mould
The confidence level of type, judge whether to meet sets requirement；If not satisfied, then assessing current class model, and tied assessing
Fruit feeds back to training data, continues to be trained disaggregated model；If satisfied, then terminating to train, the instruction to disaggregated model is completed
Practice.
The technical scheme of the embodiment of the present invention, by the way that point of interest to be updated is divided into 5 classes according to mutability and importance
Not, and for the point of interest of 5 classifications corresponding different default more new standards are performed respectively.So that new point of interest energy
Update on line, old, failure point of interest can be cleaned out in time, and important point of interest is protected.
The above method takes full advantage of map point of interest big data advantage and powerful data mining ability, the point of interest for allowing map to show
Faster, more update complete, more accurately, make graphical user untired by interest point informations such as expired, failure, missing or loss of learnings
Disturb, obtain user and more trust.
Meanwhile referring to Fig. 5, prediction is modeled to the value of point of interest, mutability etc. by machine learning model, is based on
Powerful disaggregated model, it can realize and quickly circulate between inhomogeneity data, allow the important high-precision class of the data flow excess of imports and high-precision class
Protection domain, allow variable and low click volume, low value data to flow into the 3rd class, the 4th class and the 5th class, so may be used
It is unhappy to reduce the data that user frequently encountered when using map to greatest extent, not entirely, the experience of inaccurate flaw.
Example IV
Fig. 6 is a kind of structural representation for point of interest updating device that the embodiment of the present invention four provides.Referring to Fig. 6, this reality
Applying the point of interest updating device of example offer includes：Acquisition module 10, sort module 20 and update module 30.
Wherein, acquisition module 10, for obtaining point of interest to be updated；Sort module 20, for based on point of interest to be updated
Feature, the point of interest to be updated is classified；Update module 30, for according to classification results, based on different classes of right
The difference answered presets more new standard, and the point of interest to be updated is updated.
The point of interest updating device that the embodiment of the present invention is provided can perform the interest that any embodiment of the present invention is provided
Point update method, possesses the corresponding functional module of execution method and beneficial effect.
Further, sort module 20 includes：Taxon.
Wherein, taxon, for the feature based on point of interest to be updated, the disaggregated model completed according to training in advance,
The point of interest to be updated is classified.
Further, described point of interest updating device, in addition to：Sample structure module, characteristic determination module and training
Module.
Wherein, sample structure module, for before point of interest to be updated is obtained, building sample interest point data collection；
Characteristic determination module, for determining the feature of the point of interest；
Training module, for the feature according to the sample interest point data collection and the point of interest, to the classification mould
Type is trained and tested.
Specifically, the feature of the point of interest includes：Categorical attribute, retrieval amount, positioning amount, base map mark, basic atural object,
At least one of set membership, brand and data mobility.
Further, sample structure module includes：Sample construction unit.
Wherein, sample construction unit, for according to default structure rule, corresponding each classification to be filtered out from pre-stored data
Sample interest point data.
Further, update module includes：Updating block.
Wherein, updating block, it is right for setting more new standard corresponding to the affiliated classification according to the point of interest to be updated
The basic field of the point of interest to be updated, and the point of interest to be updated is reached the standard grade or offline processing.
Further, training module, including：Quantity determining unit and training unit.
Wherein, quantity determining unit, for based on the proportionate relationship between the different classification preset stored amounts, from described
Sample interest point data concentrates the quantity of the training for determining the different classifications and test sample point of interest；
Training unit, for the sample interest point data of the different classifications using the quantity, to the classification mould
Type is trained and tested.
Further, training module, in addition to：Unit is completed in judging unit and training.
Wherein, judging unit, for after testing the disaggregated model, judging the accurate of the disaggregated model
Whether rate and recall rate are more than setting accuracy rate threshold value and setting recall rate threshold value；
Unit is completed in training, for if so, then completing the training to the disaggregated model.
Further, sort module 20 includes：Characteristics determining unit and category division unit.
Wherein, characteristics determining unit, for the feature according to the point of interest to be updated, the point of interest to be updated is determined
Importance and mutability；
Category division unit, will be described to be updated emerging for the importance and mutability according to the point of interest to be updated
Interest point is divided at least two classifications.
Embodiment five
Fig. 7 is a kind of structural representation for server that the embodiment of the present invention five provides.Fig. 7 is shown suitable for being used for realizing
The block diagram of the exemplary servers 12 of embodiment of the present invention.The server 12 that Fig. 7 is shown is only an example, should not be to this
The function and use range of inventive embodiments bring any restrictions.
As shown in fig. 7, server 12 is showed in the form of universal computing device.The component of server 12 can be included but not
It is limited to：One or more processor or processing unit 16, system storage 28, connection different system component (including system
Memory 28 and processing unit 16) bus 18.
Bus 18 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.Lift
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, MCA (MAC)
Bus, enhanced isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) bus.
Server 12 typically comprises various computing systems computer-readable recording medium.These media can be it is any being capable of being serviced
The usable medium that device 12 accesses, including volatibility and non-volatile media, moveable and immovable medium.
System storage 28 can include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Server 12 may further include other removable/nonremovable
, volatile/non-volatile computer system storage medium.Only as an example, it is not removable to can be used for read-write for storage system 34
Dynamic, non-volatile magnetic media (Fig. 7 do not show, commonly referred to as " hard disk drive ").Although not shown in Fig. 7, it can provide
For the disc driver to may move non-volatile magnetic disk (such as " floppy disk ") read-write, and to may move anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.Memory 28 can include at least one program product,
The program product has one group of (for example, at least one) program module, and these program modules are configured to perform each implementation of the invention
The function of example.
Program/utility 40 with one group of (at least one) program module 42, such as memory 28 can be stored in
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
Routine data, the realization of network environment may be included in each or certain combination in these examples.Program module 42 is usual
Perform the function and/or method in embodiment described in the invention.
Server 12 can also be logical with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.)
Letter, can also enable a user to the equipment communication interacted with the server 12 with one or more, and/or with causing the server
12 any equipment (such as network interface card, the modem etc.) communications that can be communicated with one or more of the other computing device.
This communication can be carried out by input/output (I/O) interface 22.Also, server 12 can also pass through network adapter 20
With one or more network (such as LAN (LAN), wide area network (WAN) and/or public network, such as internet) communication.
As illustrated, network adapter 20 is communicated by bus 18 with other modules of server 12.It should be understood that although do not show in figure
Go out, server 12 can be combined and use other hardware and/or software module, included but is not limited to：Microcode, device driver,
Redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 is stored in program in system storage 28 by operation, so as to perform various function application and
Data processing, such as realize the point of interest update method that the embodiment of the present invention is provided.
Embodiment seven
The embodiment of the present invention seven additionally provides a kind of computer-readable recording medium, is stored thereon with computer program, should
The point of interest update method as described in any in claim 1-9 is realized when program is executed by processor.
The computer-readable storage medium of the embodiment of the present invention, any of one or more computer-readable media can be used
Combination.Computer-readable medium can be computer-readable signal media or computer-readable recording medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any combination above.The more specifically example (non exhaustive list) of computer-readable recording medium includes：Tool
There are the electrical connections of one or more wires, portable computer diskette, hard disk, random access memory (RAM), read-only storage
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any includes or the tangible medium of storage program, the program can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium beyond storage medium is read, the computer-readable medium, which can send, propagates or transmit, to be used for
By instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc., or above-mentioned any appropriate combination.
It can be write with one or more programming languages or its combination for performing the computer that operates of the present invention
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Also include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
Fully perform, partly perform on the user computer on the user computer, the software kit independent as one performs, portion
Divide and partly perform or performed completely on remote computer or server on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as carried using Internet service
Pass through Internet connection for business).
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (16)
- A kind of 1. point of interest update method, applied to server, it is characterised in that including：Obtain point of interest to be updated；Based on the feature of point of interest to be updated, the point of interest to be updated is classified；According to classification results, based on different classes of corresponding different default more new standards, the point of interest to be updated is carried out more Newly.
- 2. point of interest update method according to claim 1, it is characterised in that the feature based on point of interest to be updated is right The point of interest to be updated is classified, including：Based on the feature of point of interest to be updated, the disaggregated model completed according to training in advance, the point of interest to be updated is carried out Classification.
- 3. point of interest update method according to claim 2, it is characterised in that before point of interest to be updated is obtained, also Including：Build sample interest point data collection；Determine the feature of the point of interest；According to the feature of the sample interest point data collection and the point of interest, the disaggregated model is trained and tested.
- 4. point of interest update method according to claim 3, it is characterised in that structure sample interest point data collection, including：According to default structure rule, the corresponding sample interest point data each classified is filtered out from pre-stored data.
- 5. point of interest update method according to claim 3, it is characterised in that the feature of the point of interest includes：Classification At least one of attribute, retrieval amount, positioning amount, base map mark, basic atural object, set membership, brand and data mobility.
- 6. point of interest update method according to claim 3, it is characterised in that the disaggregated model is trained and surveyed Examination, including：Based on the proportionate relationship between the different classification preset stored amounts, concentrated from the sample interest point data and determine difference The training of the classification and the quantity of test sample point of interest；Using the sample interest point data of the different classifications of the quantity, the disaggregated model is trained and tested.
- 7. point of interest update method according to claim 3, it is characterised in that the disaggregated model is trained and surveyed Examination, including：After testing the disaggregated model, whether the accuracy rate and recall rate that judge the disaggregated model are more than setting Accuracy rate threshold value and setting recall rate threshold value；If so, then complete the training to the disaggregated model.
- 8. point of interest update method according to claim 1, it is characterised in that according to classification results, based on different classes of Corresponding different default more new standards, are updated to the point of interest to be updated, including：More new standard is set according to corresponding to the affiliated classification of the point of interest to be updated, to the basis of the point of interest to be updated Field is modified, and the point of interest to be updated is reached the standard grade or offline processing.
- 9. point of interest update method according to claim 1, it is characterised in that the feature based on point of interest to be updated is right The point of interest to be updated, which carries out classification, to be included：According to the feature of the point of interest to be updated, the importance and mutability of the point of interest to be updated are determined；It is at least two classes by the Partition for Interest Points to be updated according to the importance and mutability of the point of interest to be updated Not.
- A kind of 10. point of interest updating device, applied to server, it is characterised in that including：Acquisition module, for obtaining point of interest to be updated；Sort module, for the feature based on point of interest to be updated, the point of interest to be updated is classified；Update module, for according to classification results, more new standards being preset based on different classes of corresponding difference, to described to be updated Point of interest is updated.
- 11. point of interest updating device according to claim 10, it is characterised in that sort module includes：Taxon, for the feature based on point of interest to be updated, the disaggregated model completed according to training in advance, treated more to described New interest point is classified.
- 12. point of interest updating device according to claim 11, it is characterised in that also include：Sample builds module, for before point of interest to be updated is obtained, building sample interest point data collection；Characteristic determination module, for determining the feature of the point of interest；Training module, for the feature according to the sample interest point data collection and the point of interest, the disaggregated model is entered Row training and test.
- 13. point of interest updating device according to claim 12, it is characterised in that sample structure module includes：Sample construction unit, for according to default structure rule, it is emerging that the corresponding sample each classified to be filtered out from pre-stored data Interesting point data.
- 14. point of interest updating device according to claim 10, it is characterised in that update module includes：Updating block, for setting more new standard corresponding to the affiliated classification according to the point of interest to be updated, treated more to described The basic field of new point of interest, and the point of interest to be updated is reached the standard grade or offline processing.
- 15. a kind of server, it is characterised in that the server includes：One or more processors；Storage device, for storing one or more programs,When one or more of programs are by one or more of computing devices so that one or more of processors are real The now point of interest update method as described in any in claim 1-9.
- 16. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The point of interest update method as described in any in claim 1-9 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710920000.7A CN107679189A (en) | 2017-09-30 | 2017-09-30 | A kind of point of interest update method, device, server and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710920000.7A CN107679189A (en) | 2017-09-30 | 2017-09-30 | A kind of point of interest update method, device, server and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107679189A true CN107679189A (en) | 2018-02-09 |
Family
ID=61138721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710920000.7A Pending CN107679189A (en) | 2017-09-30 | 2017-09-30 | A kind of point of interest update method, device, server and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107679189A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108833527A (en) * | 2018-06-08 | 2018-11-16 | 腾讯大地通途（北京）科技有限公司 | A kind of point of interest inserting method and relevant device |
| CN108875013A (en) * | 2018-06-19 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Handle the method and device of map datum |
| CN109145068A (en) * | 2018-07-12 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | map updating method and device |
| CN109241225A (en) * | 2018-08-27 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Point of interest competitive relation method for digging, device, computer equipment and storage medium |
| CN109634983A (en) * | 2018-12-13 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Recall determination method, apparatus, equipment and the medium of interest point information |
| CN109726992A (en) * | 2018-12-29 | 2019-05-07 | 北京百度网讯科技有限公司 | The appraisal procedure and device of task completion time |
| CN110163209A (en) * | 2019-05-24 | 2019-08-23 | 北京百度网讯科技有限公司 | Fail POI data method for digging, device, server and storage medium |
| CN110399445A (en) * | 2019-07-25 | 2019-11-01 | 腾讯科技（深圳）有限公司 | A kind of processing method of point of interest, device and equipment |
| WO2019228391A1 (en) * | 2018-05-31 | 2019-12-05 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for online to offline services |
| CN110555352A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术（北京）有限公司 | interest point identification method, device, server and storage medium |
| CN111061744A (en) * | 2018-10-17 | 2020-04-24 | 百度在线网络技术（北京）有限公司 | Graph data updating method and device, computer equipment and storage medium |
| CN111125550A (en) * | 2018-11-01 | 2020-05-08 | 百度在线网络技术（北京）有限公司 | Interest point classification method, device, equipment and storage medium |
| CN111126912A (en) * | 2019-12-23 | 2020-05-08 | 北京中交兴路信息科技有限公司 | Freight type identification method and device, storage medium and terminal for truck |
| CN111160471A (en) * | 2019-12-30 | 2020-05-15 | 腾讯云计算（北京）有限责任公司 | Method and device for processing point of interest data, electronic equipment and storage medium |
| CN111782978A (en) * | 2020-06-30 | 2020-10-16 | 北京百度网讯科技有限公司 | Method and device for processing point of interest data, electronic equipment and readable medium |
| CN111881796A (en) * | 2020-07-20 | 2020-11-03 | 北京百度网讯科技有限公司 | Method and device for mining failure interest points, electronic equipment and storage medium |
| CN112148990A (en) * | 2020-10-16 | 2020-12-29 | 北京百度网讯科技有限公司 | Content display method and device, electronic equipment and storage medium |
| CN112866628A (en) * | 2019-11-28 | 2021-05-28 | 浙江宇视科技有限公司 | Image collector name determining method and device, server and storage medium |
| CN113778977A (en) * | 2020-10-29 | 2021-12-10 | 北京京东尚科信息技术有限公司 | Data processing method and data processing device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488758A (en) * | 2013-09-24 | 2014-01-01 | 大陆汽车投资（上海）有限公司 | Interest point search method and navigation method |
| CN103512578A (en) * | 2012-06-18 | 2014-01-15 | 现代Mnsoft公司 | Navigation apparatus for updating objects by category and update method thereof |
| CN104123318A (en) * | 2013-04-28 | 2014-10-29 | 百度在线网络技术（北京）有限公司 | Method and system for displaying interest points in map |
| CN104216895A (en) * | 2013-05-31 | 2014-12-17 | 高德软件有限公司 | Method and device for generating POI data |
| CN105277207A (en) * | 2014-07-15 | 2016-01-27 | 福特全球技术公司 | Automated point of interest updates |
| CN105589899A (en) * | 2014-11-18 | 2016-05-18 | 北京四维图新科技股份有限公司 | Display method and display device of point of interest in electronic map |
| WO2016156936A1 (en) * | 2015-03-31 | 2016-10-06 | Yandex Europe Ag | System and method of ranking points of interest using photograph rating |
| US20160320197A1 (en) * | 2011-02-02 | 2016-11-03 | Mapquest, Inc. | Systems and methods for generating electronic map displays with points-of-interest information |
| CN107220358A (en) * | 2017-06-05 | 2017-09-29 | 江苏省基础地理信息中心 | The recommendation method and device of point of interest |
| CN107315750A (en) * | 2016-04-26 | 2017-11-03 | 斑马网络技术有限公司 | Electronic map figure layer display methods, device, terminal device and user interface system |
-
2017
- 2017-09-30 CN CN201710920000.7A patent/CN107679189A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160320197A1 (en) * | 2011-02-02 | 2016-11-03 | Mapquest, Inc. | Systems and methods for generating electronic map displays with points-of-interest information |
| CN103512578A (en) * | 2012-06-18 | 2014-01-15 | 现代Mnsoft公司 | Navigation apparatus for updating objects by category and update method thereof |
| CN104123318A (en) * | 2013-04-28 | 2014-10-29 | 百度在线网络技术（北京）有限公司 | Method and system for displaying interest points in map |
| CN104216895A (en) * | 2013-05-31 | 2014-12-17 | 高德软件有限公司 | Method and device for generating POI data |
| CN103488758A (en) * | 2013-09-24 | 2014-01-01 | 大陆汽车投资（上海）有限公司 | Interest point search method and navigation method |
| CN105277207A (en) * | 2014-07-15 | 2016-01-27 | 福特全球技术公司 | Automated point of interest updates |
| CN105589899A (en) * | 2014-11-18 | 2016-05-18 | 北京四维图新科技股份有限公司 | Display method and display device of point of interest in electronic map |
| WO2016156936A1 (en) * | 2015-03-31 | 2016-10-06 | Yandex Europe Ag | System and method of ranking points of interest using photograph rating |
| CN107315750A (en) * | 2016-04-26 | 2017-11-03 | 斑马网络技术有限公司 | Electronic map figure layer display methods, device, terminal device and user interface system |
| CN107220358A (en) * | 2017-06-05 | 2017-09-29 | 江苏省基础地理信息中心 | The recommendation method and device of point of interest |
Non-Patent Citations (4)
| Title |
|---|
| 《现代模具技术》编委会编: "《汽车覆盖件模具设计与制造》", 31 January 1998, 国防工业出版社 * |
| 孙庆耀等: "《空间位置信息服务系统原理和方法》", 28 February 2009, 西安地图出版社 * |
| 搜狐网: "欺诈预测机器学习模型设计：准确率和召回率", 《HTTP://WWW.SOHU.COM/A/129652736_609569》 * |
| 龚健雅: "《对地观测数据处理与分析研究进展》", 31 December 2007, 武汉大学出版社 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019228391A1 (en) * | 2018-05-31 | 2019-12-05 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for online to offline services |
| CN110785751A (en) * | 2018-05-31 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | System and method for online-to-offline services |
| CN110555352A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术（北京）有限公司 | interest point identification method, device, server and storage medium |
| CN108833527A (en) * | 2018-06-08 | 2018-11-16 | 腾讯大地通途（北京）科技有限公司 | A kind of point of interest inserting method and relevant device |
| CN108875013B (en) * | 2018-06-19 | 2022-05-27 | 百度在线网络技术（北京）有限公司 | Method and device for processing map data |
| CN108875013A (en) * | 2018-06-19 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Handle the method and device of map datum |
| CN109145068B (en) * | 2018-07-12 | 2021-06-04 | 百度在线网络技术（北京）有限公司 | Map updating method and device |
| CN109145068A (en) * | 2018-07-12 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | map updating method and device |
| CN109241225B (en) * | 2018-08-27 | 2022-03-25 | 百度在线网络技术（北京）有限公司 | Method and device for mining competition relationship of interest points, computer equipment and storage medium |
| US11232116B2 (en) | 2018-08-27 | 2022-01-25 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, computer device and storage medium for mining point of interest competitive relationship |
| CN109241225A (en) * | 2018-08-27 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Point of interest competitive relation method for digging, device, computer equipment and storage medium |
| CN111061744A (en) * | 2018-10-17 | 2020-04-24 | 百度在线网络技术（北京）有限公司 | Graph data updating method and device, computer equipment and storage medium |
| CN111061744B (en) * | 2018-10-17 | 2023-08-01 | 百度在线网络技术（北京）有限公司 | Graph data updating method and device, computer equipment and storage medium |
| CN111125550A (en) * | 2018-11-01 | 2020-05-08 | 百度在线网络技术（北京）有限公司 | Interest point classification method, device, equipment and storage medium |
| CN111125550B (en) * | 2018-11-01 | 2023-11-24 | 百度在线网络技术（北京）有限公司 | Point-of-interest classification method, device, equipment and storage medium |
| CN109634983A (en) * | 2018-12-13 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Recall determination method, apparatus, equipment and the medium of interest point information |
| CN109634983B (en) * | 2018-12-13 | 2021-03-30 | 百度在线网络技术（北京）有限公司 | Method, apparatus, device and medium for determining recall point of interest information |
| CN109726992A (en) * | 2018-12-29 | 2019-05-07 | 北京百度网讯科技有限公司 | The appraisal procedure and device of task completion time |
| CN110163209A (en) * | 2019-05-24 | 2019-08-23 | 北京百度网讯科技有限公司 | Fail POI data method for digging, device, server and storage medium |
| CN110399445A (en) * | 2019-07-25 | 2019-11-01 | 腾讯科技（深圳）有限公司 | A kind of processing method of point of interest, device and equipment |
| CN112866628B (en) * | 2019-11-28 | 2022-12-09 | 浙江宇视科技有限公司 | Image collector name determining method, device, server and storage medium |
| CN112866628A (en) * | 2019-11-28 | 2021-05-28 | 浙江宇视科技有限公司 | Image collector name determining method and device, server and storage medium |
| CN111126912A (en) * | 2019-12-23 | 2020-05-08 | 北京中交兴路信息科技有限公司 | Freight type identification method and device, storage medium and terminal for truck |
| CN111160471A (en) * | 2019-12-30 | 2020-05-15 | 腾讯云计算（北京）有限责任公司 | Method and device for processing point of interest data, electronic equipment and storage medium |
| CN111160471B (en) * | 2019-12-30 | 2023-04-07 | 腾讯云计算（北京）有限责任公司 | Interest point data processing method and device, electronic equipment and storage medium |
| CN111782978A (en) * | 2020-06-30 | 2020-10-16 | 北京百度网讯科技有限公司 | Method and device for processing point of interest data, electronic equipment and readable medium |
| CN111782978B (en) * | 2020-06-30 | 2024-05-31 | 北京百度网讯科技有限公司 | Method and device for processing interest point data, electronic equipment and readable medium |
| CN111881796A (en) * | 2020-07-20 | 2020-11-03 | 北京百度网讯科技有限公司 | Method and device for mining failure interest points, electronic equipment and storage medium |
| CN111881796B (en) * | 2020-07-20 | 2023-08-15 | 北京百度网讯科技有限公司 | Method and device for mining failure interest points, electronic equipment and storage medium |
| CN112148990A (en) * | 2020-10-16 | 2020-12-29 | 北京百度网讯科技有限公司 | Content display method and device, electronic equipment and storage medium |
| CN112148990B (en) * | 2020-10-16 | 2023-12-19 | 北京百度网讯科技有限公司 | Content display method and device, electronic equipment and storage medium |
| CN113778977A (en) * | 2020-10-29 | 2021-12-10 | 北京京东尚科信息技术有限公司 | Data processing method and data processing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107679189A (en) | A kind of point of interest update method, device, server and medium | |
| CN110008300B (en) | Method and device for determining alias of POI (Point of interest), computer equipment and storage medium | |
| US20240265038A1 (en) | Method and apparatus for dividing region, storage medium, and electronic device | |
| CN112861972B (en) | Site selection method and device for exhibition area, computer equipment and medium | |
| CN108182253B (en) | Method and apparatus for generating information | |
| US20230049839A1 (en) | Question Answering Method for Query Information, and Related Apparatus | |
| CN110674208B (en) | Method and device for determining position information of user | |
| CN112528639B (en) | Object recognition method and device, storage medium and electronic equipment | |
| CN110009379A (en) | A kind of building of site selection model and site selecting method, device and equipment | |
| CN110399445A (en) | A kind of processing method of point of interest, device and equipment | |
| CN117079148B (en) | Urban functional area identification method, device, equipment and medium | |
| CN112052848A (en) | Method and device for acquiring sample data in street labeling | |
| CN111738316A (en) | Image classification method and device for zero sample learning and electronic equipment | |
| CN111382138B (en) | POI data processing method, device, equipment and medium | |
| CN115033766A (en) | Data processing method, life circle display method and device, medium and equipment | |
| CN111126422A (en) | Industry model establishing method, industry determining method, industry model establishing device, industry determining equipment and industry determining medium | |
| CN108228904A (en) | For the method and apparatus of output information | |
| CN110069997B (en) | Scene classification method and device and electronic equipment | |
| CN118313676A (en) | Method and device for intelligent community participation type planning intelligent auxiliary decision making | |
| CN111325638A (en) | Hotel identification processing method, device, equipment and storage medium | |
| CN114925680A (en) | Logistics interest point information generation method, device, equipment and computer readable medium | |
| CN110781283B (en) | Chain brand word stock generation method and device and electronic equipment | |
| CN113158043A (en) | Intelligent tourism resource recommendation system adopting reinforcement learning and integrated learning | |
| CN111125272B (en) | Regional characteristic acquisition method, regional characteristic acquisition device, computer equipment and medium | |
| CN110175300A (en) | Point of interest POI processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180209 |