CN110516024A - Map search result shows method, apparatus, equipment and storage medium - Google Patents

Map search result shows method, apparatus, equipment and storage medium Download PDF

Info

Publication number
CN110516024A
CN110516024A CN201910818067.9A CN201910818067A CN110516024A CN 110516024 A CN110516024 A CN 110516024A CN 201910818067 A CN201910818067 A CN 201910818067A CN 110516024 A CN110516024 A CN 110516024A
Authority
CN
China
Prior art keywords
search
poi
search result
result
poi search
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
Application number
CN201910818067.9A
Other languages
Chinese (zh)
Other versions
CN110516024B (en
Inventor
张瑞昌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201910818067.9A priority Critical patent/CN110516024B/en
Publication of CN110516024A publication Critical patent/CN110516024A/en
Application granted granted Critical
Publication of CN110516024B publication Critical patent/CN110516024B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29Geographical information databases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9537Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

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 embodiment of the invention discloses a kind of map search results to show method, apparatus, equipment and storage medium, wherein this method comprises: obtaining the search need of user and POI search the results list of search need;According to the correlation of POI search result and search need each in POI search the results list, the Expressive Features of each POI search result are determined;According to the Expressive Features of each POI search result, in POI search the results list, the variance analysis result of each POI search result is obtained;According to the variance analysis of POI search result each in POI search the results list as a result, determine search need whether meet search result show scene and POI search the results list by force show folding position.The treatment effeciency for showing problem in map search system by force can be improved in the embodiment of the present invention, improves the accuracy for showing folding position for determining search result.

Description

Map search result shows method, apparatus, equipment and storage medium
Technical field
The present embodiments relate to field of computer technology more particularly to a kind of map search result show method, apparatus, Equipment and storage medium.
Background technique
In map search system, Qiang Zhanxian technology refers to the search need based on user, point of interest (POI, Point Of Interest) before search result returns to user, by show user demand by force as a result, fold non-user demand as a result, Reduce the technology that user selects cost.
Showing technology by force will solve the problems, such as to be to find the folding position POI.It generally will show problem by force at present to be converted into Classification problem solves, specifically, whether determining user's current search demand first with two disaggregated models of training in advance To show application scenarios by force;Show application scenarios by force if it is determined that belonging to, then determines that user works as using two other disaggregated models The corresponding POI search result of preceding search need shows folding position, and the position for folding maximum probability is determined as folding position. Such as based on search engine return all POI search results default sort, successively carry out two neighboring POI search result with The judgement of the correlative character difference of searching request, by the determining biggish two POI search results of correlative character difference it Between position as folding position, i.e., by the two search results rear search result and search result after it into Row folds.
The defect of above scheme is, will show problem by force and be converted into the progress substep solution of two class problems, low efficiency;And And determined during determining folding position by the difference considered between two adjacent POI search results, folding position Determine that accuracy is lower.
Summary of the invention
The embodiment of the present invention provides a kind of map search result and shows method, apparatus, equipment and storage medium, to improve ground Show the treatment effeciency of problem in graph search system by force, improves the accuracy for showing folding position for determining search result.
In a first aspect, the embodiment of the invention provides a kind of map search results to show method, this method comprises:
Obtain the search need of user and POI search the results list of described search demand;
According to the correlation of POI search result and described search demand each in described POI search the results list, determine described in The Expressive Features of each POI search result;
According to the Expressive Features of each POI search result, in described POI search the results list, each POI is obtained The variance analysis result of search result;
According to the variance analysis as a result, determining whether described search demand meets the strong of search result and show scene, with And described POI search the results list shows folding position.
Second aspect, the embodiment of the invention also provides a kind of map search result display device, which includes:
Search result list obtains module, for obtaining the search need of user and the POI search of described search demand The results list;
Expressive Features determining module, for according to POI search result each in described POI search the results list and described search The correlation of demand determines the Expressive Features of each POI search result;
Variance analysis result obtains module and searches for the Expressive Features according to each POI search result in the POI In rope the results list, the variance analysis result of each POI search result is obtained;
Show result determining module by force, for according to the variance analysis as a result, determine described search demand whether meet Search result show scene and described POI search the results list by force show folding position.
The third aspect, the embodiment of the invention also provides a kind of equipment, comprising:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing Device realizes that the map search result as described in any embodiment of the present invention shows method.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer Program realizes that the map search result as described in any embodiment of the present invention shows method when the program is executed by processor.
The embodiment of the present invention is by the Expressive Features according to each POI search result, in POI search the results list, obtains The variance analysis of each POI search result is as a result, realize the analysis above to POI search result each in search result list;According to The variance analysis of each POI search result as a result, determine whether the search need of user meets the strong of search result and show field simultaneously Scape and POI search the results list show folding position, solve the problems, such as to show by force in the prior art and need to utilize dual model Carry out substep solve the problems, such as caused by treatment effeciency it is lower, improve show by force in map search system problem processing effect Rate;Due to being not limited between POI search result adjacent in POI search the results list during Expressive Features variance analysis Feature difference analysis, pass through comprehensive point of Expressive Features otherness between POI search result each in POI search the results list Analysis, improves the accuracy for showing folding position of determining search result.
Detailed description of the invention
Fig. 1 is the flow chart that a kind of map search result disclosed by the embodiments of the present invention shows method;
Fig. 2 is the flow chart that another map search result disclosed by the embodiments of the present invention shows method;
Fig. 3 is one kind of the markup information of each POI search result in POI search the results list disclosed by the embodiments of the present invention Schematic diagram;
Fig. 4 is a kind of structural schematic diagram of map search result display device disclosed by the embodiments of the present invention;
Fig. 5 is a kind of structural schematic diagram of equipment disclosed by the embodiments of the present invention.
Specific 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 limiting the invention.It also should be noted that in order to just Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Fig. 1 is the flow chart that a kind of map search result disclosed by the embodiments of the present invention shows method, and the present embodiment can fit Show field in map search system, determining whether the current search need of user (query) meets the strong of search result Scape, and meet show scene by force when, determine the folding position that shows of search result, i.e., the search result showed by force and hide Search result boundary the case where, this method can be executed by map search result display device, which can use The mode of software and/or hardware is realized, and can be integrated in the arbitrary equipment with computing capability, such as server etc..
Map search system has differences with traditional information search system, and the POI result of map search is usually more Show in the terminal, the displayed page of POI result or display area are very limited in one side mobile terminal, are abundant It needs that the POI search result for search need of being close to the users is carried out selective exhibition as far as possible using the displayed page or display area Show, and it is other can then be hidden with the lower POI search result of user's search need correlation, the strong exhibition of this i.e. search result Existing problem;On the other hand, the POI search fruiting quantities of map search feedback are usually limited, and will not be searched for as conventional information It is quasi- by showing by force for POI search result there are a large amount of feedback search as a result, the POI of user's real demand is also very clear Determine the folding position of position search result, it is possible to reduce show the information redundancy of page presentation, reduce user and select POI search knot The operating cost of fruit.Therefore, Qiang Zhanxian problem is for optimizing the result displaying of map search system, control user demand, improving User's user satisfaction that graph search is applied over the ground is very crucial.
As shown in Figure 1, map search result provided in this embodiment shows method may include:
POI search the results list of S110, the search need for obtaining user and search need.
The search need of user can be determined by analyzing the search key of user.Illustratively, user enables Map search application in terminal inputs search key in search box, triggers searching request;Map search is applied user Searching request be sent to server, server is according to the search need of the search key analysis user for including in the searching request It asks, then collects relevant to user's search need POI search using *** maps as a result, i.e. POI search the results list. In the POI search the results list, putting in order for each POI search result is related with the sort algorithm of search engine itself, this Embodiment is not especially limited.POI search the results list that the present embodiment can be returned based on arbitrary *** maps, it is right The current search need of user whether meet search result show scene and POI search the results list by force show folding position It sets progress while determining.
S120, according to the correlation of POI search result and search need each in POI search the results list, determine that each POI is searched The Expressive Features of hitch fruit.
In POI search the results list, the Expressive Features of each POI search result are for describing the POI search result and using The degree of correlation of family search need.Specifically, the Expressive Features of POI search result can include but is not limited to: POI search result Correlation between the spatial information carried with text relevant feature, the POI search result of search need with search need is special Sign and the corresponding user feedback feature of POI search result etc..
Illustratively, POI search result and the text relevant feature of search need can include but is not limited to: search needs The POI for asking and being carried in editing distance, search need and the POI search result between the POI title that is carried in POI search result The semantic feature similitude and search need of editing distance, search need and POI search result between address information with Covering category feature between POI search result etc..Wherein, similar to the semantic feature of POI search result for search need Property, it can refer to: for example user's search need and POI search result be passed through into deep learning model respectively and obtain feature (embedding) then vector calculates the similarity between two vectors;For between search need and POI search result Category feature is covered, can be referred to: for example based on search data statistics, in POI search the results list of active user's search need In, overall result quantity in the list is accounted for based on the POI search fruiting quantities that identical search need is chosen by historical user Ratio, meanwhile, it can be to increase weight based on the POI search result that identical search need is chosen by historical user, to increase The correlation of strong the POI search result and user's search need.
The correlative character between spatial information that POI search result and search need carry can include but is not limited to: POI search result carry spatial positional information whether search need carry spatial positional information belonging to regional scope The distance between spatial position that interior and POI search result and search need carry etc..
The corresponding user feedback feature of POI search result can include but is not limited to: POI search result is needed in historical search Seek down user's ratio (i.e. the user of progress clicking operation with there are the ratios of the user of search need) and the POI being clicked (i.e. the POI search result is under historical search demand by history for probability that search result is clicked under historical search demand etc. User click number and historical user to each POI search result click total degree ratio).
S130, according to the Expressive Features of each POI search result, in POI search the results list, obtain each POI search knot The variance analysis result of fruit.
Illustratively, in POI search the results list, feature can be described to any two POI search result Variance analysis obtains the variance analysis result of each POI search result.
The Expressive Features of each POI search result can be indicated with the form of multi-C vector.Between different POI search results into The variance analysis of row Expressive Features can be used for measuring the correlation difference of different POI search results and user's search need.Time Go through each POI search in POI search the results list as a result, due to each POI search result with other each POI search knots The variance analysis of feature is described in fruit, and therefore, being equivalent to realizes each POI in POI search the results list based on Expressive Features The analysis above of search result.
S140, according to the variance analysis of POI search result each in POI search the results list as a result, determining the search of user Demand whether meet search result show scene and POI search the results list by force show folding position.
In the present embodiment, the variance analysis result of each POI search result is characterized in the POI search result and list and is remained The Expressive Features difference degree of remaining each POI search result integrates the difference of multiple POI search results in POI search the results list Different analysis is as a result, can determine whether user's search need meets the strong of search result and show scene, and each POI search knot The variance analysis result of fruit can be used for characterizing probability (the i.e. quilt that the POI search result is folded in POI search the results list Hide the probability showed).
If the variation tendency of the variance analysis result of each POI search result is unsatisfactory for presetting in POI search the results list Variation tendency (for measure variation fluctuating quantity), such as each POI search result variance analysis result variation tendency exist Biggish fluctuations, then it is assumed that the current search need symbol search result of user shows scene by force, meanwhile, variance analysis knot Fruit there are it is significantly different when corresponding two POI search results between position, that is, POI search the results list show folding position It sets, i.e., the search result in both of the aforesaid POI search result after rear POI search result and the result is hidden.
For example, including that multiple POI are searched in POI search the results list that *** maps are returned based on user's search need For rope as a result, being represented sequentially as x1, x2 ... xn traverses POI search the results list, until the 5th POI search result x5, with The otherness of the Expressive Features between 9 POI search results of residue in addition to x5 is smaller, however the 6th POI search result The otherness of Expressive Features between x6 and 9 POI search results of residue in addition to x6 becomes larger and the 6th POI search knot At least one POI search result (such as x7) after fruit x6, the difference of the Expressive Features between other 9 POI search results It is anisotropic also larger, it may be considered that user's current search demand, which meets the strong of search result, shows scene, the 5th POI search knot Between fruit x5 and the 6th POI search result x6 be demarcated as i.e. POI search the results list show folding position.
In addition, the variance analysis result of each POI search result can use the POI search result and POI search result When the Expressive Features difference of remaining POI search result is greater than or equal to the first preset threshold in list, other corresponding POI searches As a result quantitative proportion characterizes.For example, including 10 POI searches in POI search the results list as a result, the 5th POI search knot When Expressive Features difference is greater than or equal to the first preset threshold in fruit x5 and remaining 9 POI search results, it is corresponding other POI search fruiting quantities are 2, then the variance analysis result of POI search result x5 can be expressed as 20%;6th POI search knot When Expressive Features difference is greater than or equal to the first preset threshold in fruit x6 and remaining 9 POI search results, it is corresponding other POI search fruiting quantities are 4, then the variance analysis result of POI search result x6 can be expressed as 40%.POI search result x5 From the difference of the variance analysis result of POI search result x6 be greater than or equal to the second preset threshold (i.e. different POI search results Significant change occurs for variance analysis result), then the corresponding POI search of the boundary between POI search result x5 and POI search result x6 The results list shows folding position.Wherein each threshold value adaptability setting.
Unlike the prior art, the variance analysis result of each POI search result is not limited in the present embodiment Expressive Features variance analysis between two adjacent POI search results, but comprehensively considered each POI search result and its The difference of Expressive Features between his each POI search result, therefore, on the basis of raising shows the treatment effeciency of problem by force, The present embodiment also ensures the determination accuracy for showing folding position by force.Such as in the prior art, if currently belonging to open up by force Live scape, as long as the otherness between a certain POI search result and adjacent upper POI search result is larger, the POI search knot Fruit and search result later will be hidden;It is then to comprehensively consider a certain POI search result and column however in the present embodiment Otherness in table between remaining each POI search result, even if a certain POI search result and adjacent upper POI search knot Expressive Features otherness between fruit is larger, but it is between other POI search results in addition to upper POI search result Expressive Features otherness is smaller (probability for also indicating that the POI search result belongs to user demand result at this time is still larger), should POI search result, which will not be folded or hide, to be showed, i.e., will not be based on the Expressive Features difference between adjacent POI search result Property analysis determination show folding position, thus reduce by the search result of potential user demand hide probability.
If the change of divergence in POI search the results list between the variance analysis result of each POI search result is smaller, Think that the current search need of user is not inconsistent the strong of search result and shows scene.For example, (referring to multiple search for general demand scene As a result belong to user's real demand as a result, and there is no points of primary and secondary between multiple search results), *** maps return There are larger correlations with user's search need for any POI search result in the POI search the results list returned, therefore, any Expressive Features otherness between POI search result and other POI search results is smaller, whole to POI search the results list For, the variance analysis result overall trend variation of each POI search result is gentle;Or *** maps are returned The bad situation of the quality of each POI search result is (specifically by the POI quality evaluation of server settings in POI search the results list Mechanism determines), each POI search result and the correlation of user's search need are poor, and therefore, POI search the results list is whole Also lesser Expressive Features the change of divergence trend is presented on body.
The technical solution of the present embodiment is by the Expressive Features according to each POI search result, in POI search the results list In, the variance analysis of each POI search result is obtained as a result, realizing dividing above to POI search result each in search result list Analysis;According to the variance analysis of each POI search result as a result, determining whether the search need of user meets the strong of search result simultaneously Show scene and POI search the results list shows folding position, solves the problems, such as to show by force in the prior art and needs to utilize Dual model carry out substep solve the problems, such as caused by treatment effeciency it is lower, improve in map search system and show problem by force Treatment effeciency;Due to being not limited to POI search knot adjacent in POI search the results list during Expressive Features variance analysis Difference analysis between fruit, it is comprehensive by the Expressive Features otherness between POI search result each in POI search the results list Analysis, improves the accuracy and reasonability for showing folding position of determining search result.
Fig. 2 is the flow chart that another map search result disclosed by the embodiments of the present invention shows method, present embodiment It is further progress optimization and extension on the basis of the above embodiment, and it can be with optional skill each in above embodiment Art scheme combines.As shown in Fig. 2, this method may include:
POI search the results list of S210, the search need for obtaining user and search need.
S220, according to the correlation of POI search result and search need each in POI search the results list, determine that each POI is searched The Expressive Features of hitch fruit.
S230, acquisition training in advance show by force demand model.
S240, using demand model is showed by force, based on the Expressive Features of each POI search result, in POI search the results list In, obtain the variance analysis result of each POI search result.
Illustratively, in POI search the results list, can use training in advance shows demand model by force, searches to POI The variance analysis of feature is described in any two POI search result in rope the results list, obtains the difference of each POI search result Analyze result.Show demand model by force using training in advance, to any two POI search result in POI search the results list The variance analysis of feature is described, that is, refers to using each POI search result in POI search the results list as clock signal, Every time using any two clock signal as process object, sequence information processing is carried out.
S250, knot is searched for as a result, determining whether the search need of user meets according to the variance analysis of each POI search result Fruit show scene and POI search the results list by force show folding position.
I.e. in the present embodiment, can use training in advance shows demand model by force, and directly determining user's current search needs What the no correspondence of Seeking Truth showed by force scene and POI search the results list shows folding position.Compared with the prior art, it gets rid of used Normal shows Resolving probiems thinking by force, dispels except through problem conversion and relies on dual model and solve the problems, such as the thought showed by force, mentions High treatment effeciency, but also the follow-up maintenance cost of model can be reduced.
Based on the above technical solution, further, what acquisition was trained in advance, which shows demand model by force, includes:
Obtain the markup information of each POI search result in POI search the results list of historical search demand, wherein mark Information includes showing or hiding by force, and the scene that shows by force that historical search demand carries search result is applicable in label;
By historical search demand, POI search the results list including markup information and including the POI search of markup information As a result the Expressive Features of each POI search result in column, the input as model training;
By the markup information for showing and hiding by force in POI search the results list including markup information and historical search The scene that shows by force of demand is applicable in label, the output as model training;
It is output and input based on above-mentioned, using Recognition with Recurrent Neural Network learning algorithm, training is showed by force demand model.
Wherein, the markup information of each POI search result can be by manually marking determination, and Fig. 3 is as an example, show A kind of schematic diagram of the markup information of each POI search result in POI search the results list.Historical search demand and its is corresponding POI search the results list can be to be obtained and carrying out historical search behavioural analysis to a large amount of historical search users.Based on each The Expressive Features of POI search result, using Recognition with Recurrent Neural Network learning algorithm to POI search the results list of historical search demand Entirety is modeled, and learns the dependence of long range between POI search result, so that in the variance analysis process of Expressive Features In, the feature difference between each POI search result and other each POI search results can be comprehensively considered, it is ensured that show folding The accuracy and reasonability that position determines.Further, the Recognition with Recurrent Neural Network learning algorithm in the present embodiment includes two-way length Short-term memory Learning Algorithms (Bi-directional Long Short-Term Memory, BiLSTM), by means of two-way The advantage of shot and long term memory network learning algorithm fully considers during the Expressive Features difference analysis of POI search result Contextual information of each POI search result in POI search the results list, it is ensured that show folding position determine accuracy with Reasonability.
Illustratively, based on the POI search that two-way shot and long term memory network learning algorithm is to user's current search demand The results list is integrally modeled, it is assumed that successively there are tri- POI searches of A, B, C in POI search the results list as a result, POI is searched Hitch fruit A can have an impact to the markup information (annotation results for referring to ways of presentation) of POI search result B, C, influence size Coding is in the parameter of POI search result A to B and in the parameter of POI search result B to C.Specifically, in two-way shot and long term In memory network learning algorithm, each POI search result is handled as clock signal, is transmitted to from POI search result A During POI search result C, the Expressive Features of POI search result A and B can all influence the markup information of POI search result C. In turn, handle direction at another, during passing to POI search result A from POI search result C, POI search result C and The Expressive Features of B also can equally influence the markup information of POI search result A.
The technical solution of the present embodiment is by showing by force demand mould using training in advance in POI search the results list Type any POI search result in POI search the results list is described with other each POI search results the difference of feature Different analysis exports result according to model and determines whether the search need of user meets the strong of search result and show scene and POI Search result list shows folding position, in a manner of based on POI search the results list Direct Modeling, solves the prior art In show by force problem need using dual model carry out substep solve the problems, such as caused by treatment effeciency it is lower, improve map and search Show the treatment effeciency of problem in cable system by force;Due to being not limited to POI search result during Expressive Features variance analysis Difference analysis in list between adjacent POI search result, by POI search result each in POI search the results list it Between Expressive Features otherness comprehensive analysis, improve the accuracy and reasonability for showing folding position of determining search result.
Fig. 4 is a kind of structural schematic diagram of map search result display device disclosed by the embodiments of the present invention, the present embodiment It is applicable in map search system, determines whether the current search need of user meets the strong of search result and show scene, And meet show scene by force when, determine the folding position that shows of search result, i.e., the search result showed by force and hide The case where boundary of search result.Map search result display device provided in this embodiment can use software and/or hardware Mode realize, and can be integrated in the arbitrary equipment with computing capability, such as server etc..
As shown in figure 4, map search result display device provided in this embodiment may include that search result list obtains Module 310, Expressive Features determining module 320, variance analysis result obtain module 330 and show result determining module 340 by force, In:
Search result list obtains module 310, for obtaining the search need of user and the POI search knot of search need Fruit list;
Expressive Features determining module 320, for according to POI search result each in POI search the results list and search need Correlation, determine the Expressive Features of each POI search result;
Variance analysis result obtains module 330, for the Expressive Features according to each POI search result, in POI search result In list, the variance analysis result of each POI search result is obtained;
Show result determining module 340 by force, for according to variance analysis as a result, determine user search need whether meet Search result show scene and POI search the results list by force show folding position.
Optionally, the Expressive Features of POI search result include: the text relevant spy of POI search result and search need Correlative character and POI search result between sign, POI search result and the spatial information of search need carrying is corresponding User feedback feature.
Optionally, variance analysis result acquisition module 330 includes:
Model acquiring unit shows demand model for obtaining the strong of training in advance;
Variance analysis result acquiring unit, for using demand model is showed by force, the description based on each POI search result to be special Sign, in POI search the results list, obtains the variance analysis result of each POI search result.
Optionally, model acquiring unit includes:
Markup information obtains subelement, each POI search knot in POI search the results list for obtaining historical search demand The markup information of fruit, wherein markup information includes showing or hiding by force, and historical search demand carries showing by force for search result Scene is applicable in label;
Model training, which inputs, determines subelement, for arranging historical search demand, the POI search result including markup information Table and including markup information POI search result column in each POI search result Expressive Features, as the defeated of model training Enter;
Model training export determine subelement, for by include markup information POI search the results list in show by force and The scene that shows by force of hiding markup information and historical search demand is applicable in label, the output as model training;
Model training subelement, for based on outputting and inputting, using Recognition with Recurrent Neural Network learning algorithm, training to obtain strong Show demand model.
Optionally, Recognition with Recurrent Neural Network learning algorithm includes two-way shot and long term memory network learning algorithm.
Map search result display device provided by the embodiment of the present invention can be performed any embodiment of that present invention and be provided Map search result show method, have the corresponding functional module of execution method and beneficial effect.It is not detailed in the present embodiment The content of description can be with reference to the description in any means embodiment of the present invention.
Fig. 5 is a kind of structural schematic diagram of equipment disclosed by the embodiments of the present invention.Fig. 5, which is shown, to be suitable for being used to realizing this hair The block diagram of the example devices 412 of bright embodiment.The equipment 412 that Fig. 5 is shown is only an example, should not be to of the invention real The function and use scope for applying example bring any restrictions.Equipment 412 can be arbitrary the equipment with computing capability, including but It is not limited to server.
As shown in figure 5, equipment 412 is showed in the form of common apparatus.The component of equipment 412 can include but is not limited to: One or more processor 416, storage device 428 connect different system components (including storage device 428 and processor 416) bus 418.
Bus 418 indicates one of a few class bus structures or a variety of, including storage device bus or storage device control Device processed, peripheral bus, graphics acceleration port, processor or total using the local of any bus structures in a variety of bus structures Line.For example, these architectures include but is not limited to industry standard architecture (Industry Subversive Alliance, ISA) bus, microchannel architecture (Micro Channel Architecture, MAC) bus is enhanced Isa bus, Video Electronics Standards Association (Video Electronics Standards Association, VESA) local are total Line and peripheral component interconnection (Peripheral Component Interconnect, PCI) bus.
Equipment 412 typically comprises a variety of computer system readable media.These media can be it is any can be by equipment The usable medium of 412 access, including volatile and non-volatile media, moveable and immovable medium.
Storage device 428 may include the computer system readable media of form of volatile memory, such as arbitrary access Memory (Random Access Memory, RAM) 430 and/or cache memory 432.Equipment 412 can be wrapped further Include other removable/nonremovable, volatile/non-volatile computer system storage mediums.Only as an example, storage system 434 can be used for reading and writing immovable, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although It is not shown in Fig. 5, the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and To removable anonvolatile optical disk, such as CD-ROM (Compact Disc Read-Only Memory, CD-ROM), number Optic disk (Digital Video Disc-Read Only Memory, DVD-ROM) or other optical mediums) read-write CD drive Dynamic device.In these cases, each driver can be connected by one or more data media interfaces with bus 418.It deposits Storage device 428 may include at least one program product, which has one group of (for example, at least one) program module, this A little program modules are configured to perform the function of various embodiments of the present invention.
Program/utility 440 with one group of (at least one) program module 442 can store in such as storage dress It sets in 428, such program module 442 includes but is not limited to operating system, one or more application program, other program moulds It may include the realization of network environment in block and program data, each of these examples or certain combination.Program module 442 usually execute function and/or method in embodiment described in the invention.
Equipment 412 can also be logical with one or more external equipments 414 (such as keyboard, direction terminal, display 424 etc.) Letter, can also be enabled a user to one or more terminal interact with the equipment 412 communicate, and/or with make the equipment 412 Any terminal (such as network interface card, modem etc.) communication that can be communicated with one or more of the other computing terminal.This Kind communication can be carried out by input/output (I/O) interface 422.Also, equipment 412 can also by network adapter 420 with One or more network (such as local area network (Local Area Network, LAN), wide area network (Wide Area Network, WAN) and/or public network, for example, internet) communication.As shown in figure 5, network adapter 420 passes through bus 418 and equipment 412 Other modules communication.It should be understood that although not shown in the drawings, other hardware and/or software mould can be used with bonding apparatus 412 Block, including but not limited to: microcode, device driver, redundant processor, external disk drive array, disk array (Redundant Arrays of Independent Disks, RAID) system, tape drive and data backup storage system System etc..
The program that processor 416 is stored in storage device 428 by operation, thereby executing various function application and number According to processing, such as realize that map search result provided by any embodiment of the invention shows method, this method may include:
Obtain the search need of user and POI search the results list of described search demand;
According to the correlation of POI search result and described search demand each in described POI search the results list, determine described in The Expressive Features of each POI search result;
According to the Expressive Features of each POI search result, in described POI search the results list, each POI is obtained The variance analysis result of search result;
According to the variance analysis as a result, determining whether described search demand meets the strong of search result and show scene, with And described POI search the results list shows folding position.
The embodiment of the invention also discloses a kind of computer readable storage mediums, are stored thereon with computer program, the journey It is realized when sequence is executed by processor as map search result provided by any embodiment of the invention shows method, this method can be with Include:
Obtain the search need of user and POI search the results list of described search demand;
According to the correlation of POI search result and described search demand each in described POI search the results list, determine described in The Expressive Features of each POI search result;
According to the Expressive Features of each POI search result, in described POI search the results list, each POI is obtained The variance analysis result of search result;
According to the variance analysis as a result, determining whether described search demand meets the strong of search result and show scene, with And described POI search the results list shows folding position.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media Combination.Computer-readable medium can be computer-readable signal media or computer readable storage 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 above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD- ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate 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 other than storage medium is read, which can send, propagates or transmit and be used for By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++, It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion Divide and partially executes or executed on remote computer or terminal completely on the remote computer on the user computer.It is relating to And in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or extensively Domain net (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as provided using Internet service Quotient is connected by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation, It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.

Claims (12)

1. a kind of map search result shows method characterized by comprising
Obtain the search need of user and POI search the results list of described search demand;
According to the correlation of POI search result and described search demand each in described POI search the results list, determine described each The Expressive Features of POI search result;
According to the Expressive Features of each POI search result, in described POI search the results list, each POI search is obtained As a result variance analysis result;
According to the variance analysis as a result, determining whether described search demand meets the strong of search result and show scene, Yi Jisuo That states POI search the results list shows folding position.
2. the method according to claim 1, wherein the Expressive Features of the POI search result include: that POI is searched The spatial information that the text relevant feature of hitch fruit and described search demand, POI search result and described search demand carry Between the corresponding user feedback feature of correlative character and POI search result.
3. the method according to claim 1, wherein according to the Expressive Features of each POI search result, in institute It states in POI search the results list, obtains the variance analysis result of each POI search result, comprising:
Obtain training in advance shows by force demand model;
Show demand model by force using described, based on the Expressive Features of each POI search result, in the POI search result In list, the variance analysis result of each POI search result is obtained.
4. according to the method described in claim 3, it is characterized in that, it is described acquisition in advance training by force show demand model, wrap It includes:
Obtain the markup information of each POI search result in POI search the results list of historical search demand, wherein the mark Information includes showing or hiding by force, and the scene that shows by force that the historical search demand carries search result is applicable in label;
By the historical search demand, POI search the results list including markup information and the POI including markup information The Expressive Features of each POI search result in search result column, the input as model training;
By the markup information for showing and hiding by force in described POI search the results list including markup information and the history The scene that shows by force of search need is applicable in label, the output as model training;
It is output and input based on described, using Recognition with Recurrent Neural Network learning algorithm, training obtains described showing demand model by force.
5. according to the method described in claim 4, it is characterized in that, the Recognition with Recurrent Neural Network learning algorithm includes two-way length Phase memory network learning algorithm.
6. a kind of map search result display device characterized by comprising
Search result list obtains module, for obtaining the search need of user and the POI search result of described search demand List;
Expressive Features determining module, for according to POI search result each in described POI search the results list and described search demand Correlation, determine the Expressive Features of each POI search result;
Variance analysis result obtains module, for the Expressive Features according to each POI search result, in the POI search knot In fruit list, the variance analysis result of each POI search result is obtained;
Show result determining module by force, for according to the variance analysis as a result, determine described search demand whether meet search As a result show scene and described POI search the results list by force show folding position.
7. device according to claim 6, which is characterized in that the Expressive Features of the POI search result include: that POI is searched The spatial information that the text relevant feature of hitch fruit and described search demand, POI search result and described search demand carry Between the corresponding user feedback feature of correlative character and POI search result.
8. device according to claim 6, which is characterized in that the variance analysis result obtains module and includes:
Model acquiring unit shows demand model for obtaining the strong of training in advance;
Variance analysis result acquiring unit, for showing demand model by force using described, based on retouching for each POI search result Feature is stated, in described POI search the results list, obtains the variance analysis result of each POI search result.
9. device according to claim 8, which is characterized in that the model acquiring unit includes:
Markup information obtains subelement, each POI search result in POI search the results list for obtaining historical search demand Markup information, wherein the markup information includes showing or hiding by force, and the historical search demand carries the strong of search result Show scene and is applicable in label;
Model training, which inputs, determines subelement, for arranging the historical search demand, the POI search result including markup information The Expressive Features of table and each POI search result in the POI search result column including markup information, as model training Input;
Model training export determine subelement, for will show by force in described POI search the results list including markup information with The scene that shows by force of hiding markup information and the historical search demand is applicable in label, as the defeated of model training Out;
Model training subelement, for being output and input based on described, using Recognition with Recurrent Neural Network learning algorithm, training obtains institute It states and shows demand model by force.
10. device according to claim 9, which is characterized in that the Recognition with Recurrent Neural Network learning algorithm includes two-way length Short-term memory Learning Algorithms.
11. a kind of equipment characterized by comprising
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real Now as map search result as claimed in any one of claims 1 to 5 shows method.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor It is realized when execution as map search result as claimed in any one of claims 1 to 5 shows method.
CN201910818067.9A 2019-08-30 2019-08-30 Map search result display method, device, equipment and storage medium Active CN110516024B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910818067.9A CN110516024B (en) 2019-08-30 2019-08-30 Map search result display method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910818067.9A CN110516024B (en) 2019-08-30 2019-08-30 Map search result display method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN110516024A true CN110516024A (en) 2019-11-29
CN110516024B CN110516024B (en) 2022-05-20

Family

ID=68628800

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910818067.9A Active CN110516024B (en) 2019-08-30 2019-08-30 Map search result display method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN110516024B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117540113A (en) * 2023-11-27 2024-02-09 南京联迪信息***股份有限公司 Geographic position information searching method, system, equipment and storage medium
CN117540113B (en) * 2023-11-27 2024-08-02 南京联迪信息***股份有限公司 Geographic position information searching method and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103377204A (en) * 2012-04-18 2013-10-30 腾讯科技(深圳)有限公司 Displaying method and device for map search results
CN103440306A (en) * 2013-08-23 2013-12-11 百度在线网络技术(北京)有限公司 Search result showing method and device
CN104615620A (en) * 2014-06-24 2015-05-13 腾讯科技(深圳)有限公司 Map search type identification method and device and map search method and system
CN108647225A (en) * 2018-03-23 2018-10-12 浙江大学 A kind of electric business grey black production public sentiment automatic mining method and system
US20190163714A1 (en) * 2016-06-27 2019-05-30 Beijing Baidu Netcom Science And Technology Co., Ltd. Search result aggregation method and apparatus based on artificial intelligence and search engine

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103377204A (en) * 2012-04-18 2013-10-30 腾讯科技(深圳)有限公司 Displaying method and device for map search results
CN103440306A (en) * 2013-08-23 2013-12-11 百度在线网络技术(北京)有限公司 Search result showing method and device
CN104615620A (en) * 2014-06-24 2015-05-13 腾讯科技(深圳)有限公司 Map search type identification method and device and map search method and system
US20190163714A1 (en) * 2016-06-27 2019-05-30 Beijing Baidu Netcom Science And Technology Co., Ltd. Search result aggregation method and apparatus based on artificial intelligence and search engine
CN108647225A (en) * 2018-03-23 2018-10-12 浙江大学 A kind of electric business grey black production public sentiment automatic mining method and system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117540113A (en) * 2023-11-27 2024-02-09 南京联迪信息***股份有限公司 Geographic position information searching method, system, equipment and storage medium
CN117540113B (en) * 2023-11-27 2024-08-02 南京联迪信息***股份有限公司 Geographic position information searching method and system

Also Published As

Publication number Publication date
CN110516024B (en) 2022-05-20

Similar Documents

Publication Publication Date Title
CN109618222B (en) A kind of splicing video generation method, device, terminal device and storage medium
US11521221B2 (en) Predictive modeling with entity representations computed from neural network models simultaneously trained on multiple tasks
CN110503124A (en) Vision like numeral image is identified based on the perceptual property that user selects using based on deep neural network model
CN109657054A (en) Abstraction generating method, device, server and storage medium
JP6756079B2 (en) Artificial intelligence-based ternary check method, equipment and computer program
CN108932220A (en) article generation method and device
CN109271542A (en) Cover determines method, apparatus, equipment and readable storage medium storing program for executing
CN112200041B (en) Video motion recognition method and device, storage medium and electronic equipment
CN110222780A (en) Object detecting method, device, equipment and storage medium
CN108062377A (en) The foundation of label picture collection, definite method, apparatus, equipment and the medium of label
CN111709406A (en) Text line identification method and device, readable storage medium and electronic equipment
CN109918513A (en) Image processing method, device, server and storage medium
CN109919077A (en) Gesture recognition method, device, medium and calculating equipment
CN109858024B (en) Word2 vec-based room source word vector training method and device
CN106775272A (en) System of selection, device and electronic equipment
CN111353519A (en) User behavior recognition method and system, device with AR function and control method thereof
CN117149944B (en) Multi-mode situation emotion recognition method and system based on wide time range
CN110263218A (en) Video presentation document creation method, device, equipment and medium
CN113869371A (en) Model training method, clothing fine-grained segmentation method and related device
CN116955591A (en) Recommendation language generation method, related device and medium for content recommendation
CN108614872A (en) Course content methods of exhibiting and device
CN113762303B (en) Image classification method, device, electronic equipment and storage medium
CN110909768A (en) Method and device for acquiring marked data
CN114677402A (en) Poster text layout, poster generation method and related device
WO2021104274A1 (en) Image and text joint representation search method and system, and server 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
GR01 Patent grant
GR01 Patent grant