CN110516024B - Map search result display method, device, equipment and storage medium - Google Patents
Map search result display method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110516024B CN110516024B CN201910818067.9A CN201910818067A CN110516024B CN 110516024 B CN110516024 B CN 110516024B CN 201910818067 A CN201910818067 A CN 201910818067A CN 110516024 B CN110516024 B CN 110516024B
- Authority
- CN
- China
- Prior art keywords
- search result
- poi
- poi search
- search
- requirement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
-
- 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
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 map search result display method, a map search result display device, map search result display equipment and a storage medium, wherein the method comprises the following steps: acquiring a search requirement of a user and a POI search result list of the search requirement; determining the description characteristics of each POI search result according to the relevance of each POI search result in the POI search result list and the search requirement; acquiring a difference analysis result of each POI search result in a POI search result list according to the description characteristics of each POI search result; and determining whether the search requirement accords with a strong display scene of the search result and a display folding position of the POI search result list according to the difference analysis result of each POI search result in the POI search result list. The embodiment of the invention can improve the processing efficiency of the strong display problem in the map search system and improve the accuracy of determining the display folding position of the search result.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a map search result display method, device, equipment and storage medium.
Background
In a map search system, a strong presentation technology refers to a technology for reducing the selection cost of a user by strongly presenting a user demand result and folding a non-user demand result before returning a Point of Interest (POI) search result to the user based on the search demand of the user.
The problem to be solved by the strong exhibition technology is to find the POI folding position. At present, the strong presentation problem is generally converted into a classification problem to be solved, specifically, firstly, a pre-trained binary classification model is used for determining whether the current search requirement of a user is a strong presentation application scene; and if the POI search result belongs to the strong display application scene, determining the display folding position of the POI search result corresponding to the current search requirement of the user by using another two-classification model, and determining the position with the maximum folding probability as the folding position. For example, based on the default ranking of all the POI search results returned by the search engine, the determination of the difference between the two adjacent POI search results and the correlation characteristics of the search request is sequentially performed, and the position between the two POI search results with the determined correlation characteristics having the larger difference is used as the folding position, that is, the later search result and the later search result in the two POI search results are folded.
The defects of the scheme are that the strong display problem is converted into two types of problems to be solved step by step, and the efficiency is low; moreover, the determination of the folding position by considering the difference between the adjacent two POI search results is less accurate.
Disclosure of Invention
The embodiment of the invention provides a map search result display method, a map search result display device, map search result display equipment and a storage medium, which are used for improving the processing efficiency of a strong display problem in a map search system and improving the accuracy of determining the display folding position of a search result.
In a first aspect, an embodiment of the present invention provides a map search result presentation method, where the method includes:
acquiring a search requirement of a user and a POI search result list of the search requirement;
determining the description characteristics of each POI search result according to the relevance of each POI search result in the POI search result list and the search requirement;
according to the description characteristics of the POI search results, obtaining the difference analysis results of the POI search results in the POI search result list;
and determining whether the search requirement meets a strong display scene of a search result and a display folding position of the POI search result list according to the difference analysis result.
In a second aspect, an embodiment of the present invention further provides a map search result presentation apparatus, where the apparatus includes:
the system comprises a search result list acquisition module, a search result search module and a search result search module, wherein the search result list acquisition module is used for acquiring a search requirement of a user and a POI search result list of the search requirement;
the description feature determination module is used for determining the description features of the POI search results according to the relevance of the POI search results in the POI search result list and the search requirements;
a difference analysis result acquisition module, configured to acquire a difference analysis result of each POI search result in the POI search result list according to the description feature of each POI search result;
and the strong display result determining module is used for determining whether the search requirement accords with a strong display scene of the search result and the display folding position of the POI search result list according to the difference analysis result.
In a third aspect, an embodiment of the present invention further provides an apparatus, including:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a map search result presentation method as in any embodiment of the invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a map search result presentation method according to any embodiment of the present invention.
According to the embodiment of the invention, the difference analysis result of each POI search result is obtained in the POI search result list according to the description characteristics of each POI search result, so that the above analysis of each POI search result in the search result list is realized; according to the difference analysis result of each POI search result, whether the search requirement of the user accords with the strong display scene of the search result and the display folding position of the POI search result list is determined, the problem that the processing efficiency is low due to the fact that the strong display problem needs to be solved step by using double models in the prior art is solved, and the processing efficiency of the strong display problem in the map search system is improved; because the feature difference analysis process is not limited to feature difference analysis between adjacent POI search results in the POI search result list, the accuracy of determining the display folding position of the search results is improved through comprehensive analysis of the feature difference between the POI search results in the POI search result list.
Drawings
FIG. 1 is a flowchart of a method for presenting a map search result according to an embodiment of the present invention;
FIG. 2 is a flowchart of another map search result presentation method disclosed in an embodiment of the present invention;
fig. 3 is a schematic diagram of annotation information of each POI search result in the POI search result list disclosed in the embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a map search result presentation apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus disclosed in the embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Fig. 1 is a flowchart of a method for displaying a map search result disclosed in an embodiment of the present invention, where this embodiment is applicable to a map search system, and determines whether a current search requirement (query) of a user meets a strong display scenario of a search result, and when the current search requirement (query) meets the strong display scenario, determines a display folding position of the search result, that is, a boundary between the strong display search result and a hidden search result.
The map search system is different from the traditional information search system, the POI results of map search are usually more displayed in the mobile terminal, on one hand, the display page or the display area of the POI results in the mobile terminal is very limited, the POI search results close to the search requirements of the user need to be selectively displayed as much as possible in order to fully utilize the display page or the display area, and other POI search results with low relevance to the search requirements of the user can be hidden, namely the strong display problem of the search results; on the other hand, the number of POI search results fed back by map search is usually limited, a large number of feedback search results are not existed like the traditional information search, the POI really required by the user is very clear, the folding position of the search result is accurately positioned through the strong display of the POI search result, the information redundancy displayed on the display page can be reduced, and the operation cost of selecting the POI search result by the user is reduced. Therefore, the strong presentation problem is very critical to optimize the result presentation of the map search system, control the user's needs, and improve the user's satisfaction with the use of the map search application.
As shown in fig. 1, the map search result presentation method provided in this embodiment may include:
s110, obtaining the search requirement of the user and a POI search result list of the search requirement.
The search requirement of the user can be determined by analyzing the search keyword of the user. Illustratively, a user starts a map search application on the terminal, inputs a search keyword in a search box and triggers a search request; the map search application sends a search request of a user to the server, the server analyzes the search requirement of the user according to a search keyword included in the search request, and then a map search engine is used for collecting POI search results related to the search requirement of the user, namely a POI search result list. In the POI search result list, the arrangement order of the POI search results is related to the ranking algorithm of the search engine itself, and this embodiment is not limited in particular. The embodiment can simultaneously determine whether the current search requirement of the user meets the strong display scene of the search result and the display folding position of the POI search result list based on the POI search result list returned by any map search engine.
And S120, determining the description characteristics of each POI search result according to the relevance of each POI search result in the POI search result list and the search requirement.
In the POI search result list, the description characteristics of each POI search result are used to describe the degree of relevance of the POI search result to the search requirement of the user. In particular, the descriptive features of the POI search results may include, but are not limited to: the method comprises the steps of obtaining a POI search result, obtaining a search requirement, obtaining a text relevance characteristic of the POI search result and the search requirement, obtaining a relevance characteristic between the POI search result and spatial information carried by the search requirement, obtaining a user feedback characteristic corresponding to the POI search result and the like.
Exemplary textual relevance characteristics of POI search results to search requirements may include, but are not limited to: editing distance between the search requirement and the POI name carried in the POI search result, editing distance between the search requirement and the POI address information carried in the POI search result, semantic feature similarity between the search requirement and the POI search result, coverage class feature between the search requirement and the POI search result, and the like. The semantic feature similarity between the search requirement and the POI search result may be: for example, feature (embedding) vectors are obtained by respectively passing the search requirements of the user and the POI search results through a deep learning model, and then the similarity between the two vectors is calculated; for the coverage class characteristics between the search requirement and the POI search result, the following may be mentioned: for example, based on the search data statistics, in the POI search result list of the search requirement of the current user, the number of POI search results selected by the historical user based on the same search requirement is in proportion to the total number of results in the list, and meanwhile, the weight can be added to the POI search results selected by the historical user based on the same search requirement to enhance the relevance of the POI search results and the search requirement of the user.
The correlation characteristics between the POI search results and the spatial information carried by the search requirements may include, but are not limited to: whether the spatial position information carried by the POI search result is in the area range to which the spatial position information carried by the search requirement belongs, the distance between the POI search result and the spatial position carried by the search requirement and the like.
The user feedback features corresponding to the POI search results may include, but are not limited to: the ratio of the users who click the POI search result under the historical search requirement (i.e. the ratio of the users who perform the click operation to the users who have the search requirement), the probability of the POI search result being clicked under the historical search requirement, and the like (i.e. the ratio of the number of times that the POI search result is clicked by the historical users under the historical search requirement to the total number of times that the historical users click each POI search result).
And S130, acquiring a difference analysis result of each POI search result in the POI search result list according to the description characteristics of each POI search result.
For example, in the POI search result list, the difference analysis of the description characteristics may be performed on any two POI search results, so as to obtain a difference analysis result of each POI search result.
The descriptive features of each POI search result may be represented in the form of a multi-dimensional vector. The difference analysis of the description characteristics between different POI search results can be used for measuring the relevance difference between the different POI search results and the search requirements of the user. And traversing each POI search result in the POI search result list, and performing description feature difference analysis on each POI search result and each other POI search result, so that the above analysis of each POI search result in the POI search result list is realized on the basis of the description feature.
S140, determining whether the search requirement of the user meets the strong display scene of the search result and the display folding position of the POI search result list according to the difference analysis result of each POI search result in the POI search result list.
In this embodiment, the difference analysis result of each POI search result represents the difference degree between the POI search result and the description feature of each POI search result remaining in the list, and by integrating the difference analysis results of the multiple POI search results in the POI search result list, it can be determined whether the search requirement of the user meets the strong display scene of the search result, and the difference analysis result of each POI search result can be used to represent the probability (i.e., the probability of being hidden and displayed) that the POI search result is folded in the POI search result list.
If the variation trend of the difference analysis result of each POI search result in the POI search result list does not satisfy the preset variation trend (used for measuring variation fluctuation degree), for example, the variation trend of the difference analysis result of each POI search result has a large fluctuation change, it is considered that the user strongly displays the scene of the search result of the current search requirement symbol, and meanwhile, the difference analysis result has a position between two corresponding POI search results which are obviously different, that is, a display folding position of the POI search result list, that is, both the rear POI search result and the search result after the POI search result in the two POI search results are hidden.
For example, the map search engine includes a plurality of POI search results, which are sequentially denoted as x1, x2 … … xn, in the POI search result list returned by the map search engine based on the search requirement of the user, and traverses the POI search result list until the 5 th POI search result x5, the difference of the description characteristics between the remaining 9 POI search results except x5 is small, whereas the difference of the description characteristics between the 6 th POI search result x6 and the remaining 9 POI search results except x6 is large, and at least one POI search result (e.g., x7) after the 6 th POI search result x6, the difference in descriptive characteristics from the other 9 POI search results is also large, the current search requirement of the user can be considered to be in accordance with the strong presentation scene of the search result, and the boundary between the 5 th POI search result x5 and the 6 th POI search result x6 is the presentation folding position of the POI search result list.
In addition, the difference analysis result of each POI search result can be characterized by using the quantity proportion of the corresponding other POI search results when the difference between the POI search result and the description characteristics of the remaining POI search results in the POI search result list is greater than or equal to a first preset threshold. For example, the POI search result list includes 10 POI search results, and when the difference between the 5 th POI search result x5 and the description feature in the remaining 9 POI search results is greater than or equal to the first preset threshold, the number of the corresponding other POI search results is 2, and the difference analysis result of the POI search result x5 may be represented as 20%; when the difference between the feature description in the 6 th POI search result x6 and the feature description in the remaining 9 POI search results is greater than or equal to the first preset threshold, the number of the corresponding other POI search results is 4, and the difference analysis result of the POI search result x6 may be represented as 40%. If the difference between the POI search result x5 and the difference analysis result of the POI search result x6 is greater than or equal to the second preset threshold (i.e., the difference analysis results of different POI search results significantly change), the boundary between the POI search result x5 and the POI search result x6 corresponds to the displayed folding position of the POI search result list. Wherein each threshold can be set adaptively.
Different from the prior art, in the embodiment, the difference analysis result of each POI search result is not limited to the description feature difference analysis between two adjacent POI search results, but the difference of the description features between each POI search result and each other POI search result is comprehensively considered, so that the embodiment also ensures the accuracy of determining the strong display folding position on the basis of improving the processing efficiency of the strong display problem. For example, in the prior art, if the current scene belongs to a strong presentation scene, as long as the difference between a certain POI search result and an adjacent previous POI search result is large, the POI search result and subsequent search results are hidden; however, in this embodiment, differences between a certain POI search result and the remaining POI search results in the list are comprehensively considered, and even if the difference between the description features of the certain POI search result and the previous adjacent POI search result is large, the differences between the description features of the certain POI search result and the other POI search results except the previous POI search result are small (at this time, it is also indicated that the probability that the POI search result belongs to the result required by the user is still large), the POI search result is not displayed in a folded or hidden manner, that is, the display folding position is not determined based on the analysis of the difference between the description features of the adjacent POI search results, so that the probability of hiding the search result required by the potential user is reduced.
And if the difference change among the difference analysis results of the POI search results in the POI search result list is small, the current search requirement of the user is considered not to be in accordance with the strong display scene of the search results. For example, for a general demand scene (that is, a plurality of search results all belong to a result really demanded by a user and no primary and secondary scores exist among the plurality of search results), any POI search result in a POI search result list returned by a map search engine has a large correlation with the search demand of the user, so that the difference of the description characteristics between any POI search result and other POI search results is small, and the overall trend of the difference analysis result of each POI search result is gentle on the whole POI search result list; or for the situation that the quality of each POI search result in the POI search result list returned by the map search engine is not good (specifically determined by the POI quality evaluation mechanism set by the server), the relevance between each POI search result and the search requirement of the user is poor, so that the POI search result list as a whole also presents a smaller variation trend of the description feature difference.
According to the technical scheme of the embodiment, the difference analysis result of each POI search result is obtained in the POI search result list according to the description characteristics of each POI search result, so that the above analysis of each POI search result in the search result list is realized; according to the difference analysis result of each POI search result, whether the search requirement of the user accords with the strong display scene of the search result and the display folding position of the POI search result list is determined, the problem that the processing efficiency is low due to the fact that the strong display problem needs to be solved step by using double models in the prior art is solved, and the processing efficiency of the strong display problem in the map search system is improved; because the difference analysis process of the description characteristics is not limited to the difference analysis between the adjacent POI search results in the POI search result list, the accuracy and the reasonability of the display folding position of the search result are improved through the comprehensive analysis of the difference of the description characteristics between the POI search results in the POI search result list.
Fig. 2 is a flowchart of another map search result presentation method disclosed in the embodiment of the present invention, and the present embodiment is further optimized and expanded based on the above embodiment, and may be combined with various optional technical solutions in the above embodiment. As shown in fig. 2, the method may include:
s210, obtaining the search requirement of the user and a POI search result list of the search requirement.
And S220, determining the description characteristics of each POI search result according to the relevance of each POI search result in the POI search result list and the search requirement.
And S230, acquiring a pre-trained strong exhibition requirement model.
S240, acquiring a difference analysis result of each POI search result in the POI search result list by using the strong display demand model and based on the description characteristics of each POI search result.
Illustratively, in the POI search result list, a pre-trained strong presentation requirement model may be used to perform difference analysis of description characteristics on any two POI search results in the POI search result list, so as to obtain a difference analysis result of each POI search result. And performing description characteristic difference analysis on any two POI search results in the POI search result list by using a pre-trained strong display requirement model, namely, taking each POI search result in the POI search result list as a time sequence signal, and performing sequence information processing by taking any two time sequence signals as processing objects each time.
And S250, determining whether the search requirement of the user accords with the strong display scene of the search result and the display folding position of the POI search result list according to the difference analysis result of each POI search result.
That is, in this embodiment, it may be directly determined whether the current search requirement of the user corresponds to the strong presentation scene and the presentation folding position of the POI search result list by using a pre-trained strong presentation requirement model. Compared with the prior art, the method gets rid of the conventional idea of solving the strong presentation problem, removes the idea of solving the strong presentation problem by relying on a dual model through problem conversion, improves the processing efficiency, and can reduce the subsequent maintenance cost of the model.
On the basis of the above technical solution, further, the obtaining of the pre-trained strong exhibition requirement model includes:
acquiring marking information of each POI search result in a POI search result list of historical search requirements, wherein the marking information comprises strong display or hiding, and the historical search requirements carry strong display scene applicable labels of the search results;
taking the historical search requirements, the POI search result list comprising the labeling information and the description characteristics of each POI search result in the POI search result list comprising the labeling information as the input of model training;
the marked information which is strongly displayed and hidden in the POI search result list comprising the marked information and the applicable label of the strong display scene of the historical search requirement are used as the output of model training;
and training to obtain a strong display demand model by utilizing a recurrent neural network learning algorithm based on the input and the output.
The labeling information of each POI search result may be determined by manual labeling, and fig. 3 shows a schematic diagram of the labeling information of each POI search result in the POI search result list as an example. The historical search requirements and the corresponding POI search result list can be obtained by performing historical search behavior analysis on a large number of historical search users. Based on the description characteristics of each POI search result, a cyclic neural network learning algorithm is utilized to model the whole POI search result list required by historical search, and the long-distance dependency relationship between the POI search results is learned, so that the characteristic difference between each POI search result and other POI search results can be comprehensively considered in the difference analysis process of the description characteristics, and the accuracy and the reasonability of the determination of the folding position are ensured to be displayed. Further, the recurrent neural network learning algorithm in this embodiment includes a bidirectional Long Short Term Memory network learning algorithm (bilst), and by virtue of the advantages of the bidirectional Long Short Term Memory network learning algorithm, context information of each POI search result in the POI search result list is fully considered in the description feature difference analysis process of the POI search results, so that the accuracy and the reasonability of determining the folding position are ensured to be displayed.
Illustratively, the bidirectional long-short term memory-based network learning algorithm models the whole POI search result list required by the user for the current search, and assuming that A, B, C three POI search results sequentially exist in the POI search result list, the POI search result a has an influence on the marking information (i.e., the marking result indicating the presentation mode) of the POI search result B, C, and the influence is encoded in the parameters of the POI search results a to B and the parameters of the POI search results B to C. Specifically, in the bidirectional long and short term memory network learning algorithm, each POI search result is processed as a time sequence signal, and in the process of transmitting the POI search result a to the POI search result C, the description characteristics of the POI search results a and B affect the labeling information of the POI search result C. Conversely, in another processing direction, the description characteristics of the POI search results C and B also affect the labeling information of the POI search result a in the process of passing from the POI search result C to the POI search result a.
According to the technical scheme of the embodiment, a pre-trained strong display demand model is utilized in a POI search result list to perform difference analysis on the description characteristics of any POI search result in the POI search result list and other POI search results, whether the search demand of a user accords with a strong display scene of the search result and the display folding position of the POI search result list is determined according to a model output result, and the problem of low processing efficiency caused by the fact that the strong display problem needs to be solved step by utilizing double models in the prior art is solved in a mode of direct modeling based on the POI search result list, and the processing efficiency of the strong display problem in a map search system is improved; because the difference analysis process of the description characteristics is not limited to the difference analysis between adjacent POI search results in the POI search result list, the accuracy and the reasonableness of the display folding position of the search result are improved through the comprehensive analysis of the difference of the description characteristics between the POI search results in the POI search result list.
Fig. 4 is a schematic structural diagram of a map search result presentation apparatus according to an embodiment of the present invention, which is applicable to a map search system, and is configured to determine whether a current search requirement of a user meets a strong presentation scenario of a search result, and determine a presentation folding position of the search result when the current search requirement meets the strong presentation scenario, that is, a boundary between the strong presentation search result and a hidden search result. The map search result presentation apparatus provided in this embodiment may be implemented in a software and/or hardware manner, and may be integrated on any device with computing capability, such as a server.
As shown in fig. 4, the map search result presentation apparatus provided in this embodiment may include a search result list obtaining module 310, a description feature determining module 320, a difference analysis result obtaining module 330, and a strong presentation result determining module 340, where:
a search result list obtaining module 310, configured to obtain a search requirement of a user and a POI search result list of the search requirement;
the description feature determining module 320 is configured to determine a description feature of each POI search result according to a correlation between each POI search result in the POI search result list and a search requirement;
a difference analysis result obtaining module 330, configured to obtain a difference analysis result of each POI search result in the POI search result list according to the description feature of each POI search result;
and the strong display result determining module 340 is configured to determine whether the search requirement of the user meets a strong display scene of the search result and a display folding position of the POI search result list according to the difference analysis result.
Optionally, the feature of describing the POI search result includes: the method comprises the steps of obtaining a POI search result and a search requirement, obtaining a text relevance characteristic of the POI search result and the search requirement, obtaining a relevance characteristic between the POI search result and spatial information carried by the search requirement, and obtaining a user feedback characteristic corresponding to the POI search result.
Optionally, the difference analysis result obtaining module 330 includes:
the model acquisition unit is used for acquiring a pre-trained strong exhibition demand model;
and the difference analysis result acquisition unit is used for acquiring the difference analysis result of each POI search result in the POI search result list based on the description characteristics of each POI search result by utilizing the strong display demand model.
Optionally, the model obtaining unit includes:
the system comprises a labeling information acquisition subunit, a search result display subunit and a search result display subunit, wherein the labeling information acquisition subunit is used for acquiring labeling information of each POI search result in a POI search result list of historical search requirements, the labeling information comprises strong display or hiding, and the historical search requirements carry strong display scene applicable labels of the search results;
the model training input determining subunit is used for taking the historical search requirements, the POI search result list comprising the labeling information and the description characteristics of each POI search result in the POI search result list comprising the labeling information as the input of model training;
the model training output determining subunit is used for taking labeling information which is strongly displayed and hidden in the POI search result list including the labeling information and a strong display scene applicable label of a historical search requirement as the output of model training;
and the model training subunit is used for training to obtain a strong display demand model by utilizing a recurrent neural network learning algorithm based on input and output.
Optionally, the recurrent neural network learning algorithm comprises a bidirectional long-short term memory network learning algorithm.
The map search result display device provided by the embodiment of the invention can execute the map search result display method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Reference may be made to the description of any method embodiment of the invention that is not explicitly described in this embodiment.
Fig. 5 is a schematic structural diagram of an apparatus disclosed in the embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary device 412 suitable for use in implementing embodiments of the present invention. The device 412 shown in fig. 5 is only an example and should not impose any limitation on the functionality or scope of use of embodiments of the present invention. Device 412 may be any device with computing capabilities including, but not limited to, a server.
As shown in fig. 5, the device 412 is in the form of a general purpose device. The components of device 412 may include, but are not limited to: one or more processors 416, a storage device 428, and a bus 418 that couples the various system components including the storage device 428 and the processors 416.
A program/utility 440 having a set (at least one) of program modules 442 may be stored, for instance, in storage 428, such program modules 442 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. The program modules 442 generally perform the functions and/or methodologies of the described embodiments of the invention.
The device 412 may also communicate with one or more external devices 414 (e.g., keyboard, pointing terminal, display 424, etc.), one or more terminals that enable a user to interact with the device 412, and/or any terminal (e.g., network card, modem, etc.) that enables the device 412 to communicate with one or more other computing terminals. Such communication may occur via input/output (I/O) interfaces 422. Further, the device 412 may also communicate with one or more networks (e.g., a Local Area Network (LAN), Wide Area Network (WAN), and/or a public Network, such as the internet) via the Network adapter 420. As shown in FIG. 5, network adapter 420 communicates with the other modules of device 412 via bus 418. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the device 412, including but not limited to: microcode, device drivers, Redundant processors, external disk drive Arrays, RAID (Redundant Arrays of Independent Disks) systems, tape drives, and data backup storage systems, among others.
The processor 416 executes various functional applications and data processing by executing programs stored in the storage device 428, for example, implementing a map search result presentation method provided by any embodiment of the present invention, which may include:
acquiring a search requirement of a user and a POI search result list of the search requirement;
determining the description characteristics of each POI search result according to the relevance of each POI search result in the POI search result list and the search requirement;
according to the description characteristics of the POI search results, obtaining the difference analysis results of the POI search results in the POI search result list;
and determining whether the search requirement meets a strong display scene of a search result and a display folding position of the POI search result list according to the difference analysis result.
The embodiment of the invention also discloses a computer readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method for displaying the map search result provided by any embodiment of the invention is realized, and the method can comprise the following steps:
acquiring a search requirement of a user and a POI search result list of the search requirement;
determining the description characteristics of each POI search result according to the relevance of each POI search result in the POI search result list and the search requirement;
according to the description characteristics of the POI search results, obtaining the difference analysis results of the POI search results in the POI search result list;
and determining whether the search requirement meets a strong display scene of a search result and a display folding position of the POI search result list according to the difference analysis result.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or terminal. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (12)
1. A map search result presentation method is characterized by comprising the following steps:
acquiring a search requirement of a user and a POI search result list of the search requirement;
determining the description characteristics of each POI search result according to the correlation between each POI search result in the POI search result list and the search requirement;
according to the description characteristics of the POI search results, obtaining the difference analysis results of the POI search results in the POI search result list;
determining whether the search requirement meets a strong display scene of a search result and a display folding position of the POI search result list according to the difference analysis result;
wherein, the determining whether the search requirement meets a strong display scene of a search result and a display folding position of the POI search result list according to the difference analysis result comprises:
when the variation trend of the difference analysis result of each POI search result in the POI search result list does not meet the preset variation trend, determining that the search requirement of the user meets the strong display scene of the search result; meanwhile, when the difference value of the difference analysis results is greater than or equal to a preset threshold value, determining the position between the two corresponding POI search results, namely the display folding position of the POI search result list;
wherein, the obtaining of the difference analysis result of each POI search result in the POI search result list according to the description feature of each POI search result includes:
and in the POI search result list, performing difference analysis of description characteristics on any two POI search results to obtain a difference analysis result of each POI search result.
2. The method of claim 1, wherein the descriptive characteristics of the POI search results comprise: the method comprises the steps of obtaining a POI search result and a search requirement, obtaining a text relevance characteristic of the POI search result and the search requirement, obtaining a relevance characteristic between the POI search result and spatial information carried by the search requirement, and obtaining a user feedback characteristic corresponding to the POI search result.
3. The method according to claim 1, wherein obtaining a difference analysis result of each POI search result in the POI search result list according to the description feature of each POI search result comprises:
acquiring a pre-trained strong display demand model;
and acquiring a difference analysis result of each POI search result in the POI search result list based on the description characteristics of each POI search result by utilizing the strong display demand model.
4. The method of claim 3, wherein the obtaining a pre-trained strong exposure requirement model comprises:
obtaining marking information of each POI search result in a POI search result list of historical search requirements, wherein the marking information comprises strong display or hiding, and the historical search requirements carry strong display scene applicable labels of the search results;
taking the historical search requirements, a POI search result list comprising marking information and the description characteristics of each POI search result in the POI search result list comprising marking information as the input of model training;
taking the labeling information which is strongly displayed and hidden in the POI search result list comprising the labeling information and the label which is suitable for the strong display scene of the historical search requirement as the output of model training;
and training to obtain the strong display demand model by utilizing a cyclic neural network learning algorithm based on the input and the output.
5. The method of claim 4, wherein the recurrent neural network learning algorithm comprises a two-way long-short term memory network learning algorithm.
6. A map search result presentation apparatus, comprising:
the search result list acquisition module is used for acquiring a search requirement of a user and a POI search result list of the search requirement;
the description feature determination module is used for determining the description features of the POI search results according to the relevance of the POI search results in the POI search result list and the search requirements;
a difference analysis result acquisition module, configured to acquire a difference analysis result of each POI search result in the POI search result list according to the description feature of each POI search result;
the strong display result determining module is used for determining whether the search requirement accords with a strong display scene of a search result and the display folding position of the POI search result list according to the difference analysis result;
wherein, the determining whether the search requirement meets a strong display scene of a search result and a display folding position of the POI search result list according to the difference analysis result comprises:
when the variation trend of the difference analysis result of each POI search result in the POI search result list does not meet the preset variation trend, determining that the search requirement of the user meets the strong display scene of the search result; meanwhile, when the difference value of the difference analysis results is greater than or equal to a preset threshold value, determining the position between the two corresponding POI search results, namely the display folding position of the POI search result list;
the difference analysis result acquisition module is further configured to perform difference analysis of description characteristics on any two POI search results in the POI search result list to obtain a difference analysis result of each POI search result.
7. The apparatus of claim 6, wherein the descriptive characteristics of the POI search results comprise: the method comprises the steps of obtaining a POI search result and a search requirement, obtaining a text relevance characteristic of the POI search result and the search requirement, obtaining a relevance characteristic between the POI search result and spatial information carried by the search requirement, and obtaining a user feedback characteristic corresponding to the POI search result.
8. The apparatus of claim 6, wherein the difference analysis result obtaining module comprises:
the model acquisition unit is used for acquiring a pre-trained strong exhibition demand model;
and the difference analysis result acquisition unit is used for acquiring the difference analysis result of each POI search result in the POI search result list based on the description characteristics of each POI search result by utilizing the strong display demand model.
9. The apparatus of claim 8, wherein the model obtaining unit comprises:
the system comprises a labeling information acquisition subunit, a search result display subunit and a search result display subunit, wherein the labeling information acquisition subunit is used for acquiring labeling information of each POI search result in a POI search result list of historical search requirements, the labeling information comprises strong display or hiding, and the historical search requirements carry strong display scene applicable labels of the search results;
the model training input determining subunit is used for taking the historical search requirements, the POI search result list comprising the labeling information and the description characteristics of each POI search result in the POI search result list comprising the labeling information as the input of model training;
a model training output determining subunit, configured to use, as output of model training, labeling information that is strongly displayed and hidden in the POI search result list including the labeling information and an applicable label of the strong display scene of the historical search requirement;
and the model training subunit is used for training to obtain the strong display demand model by utilizing a recurrent neural network learning algorithm based on the input and the output.
10. The apparatus of claim 9, wherein the recurrent neural network learning algorithm comprises a two-way long-short term memory network learning algorithm.
11. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a map search result presentation method as claimed in any one of claims 1-5.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a map search result presentation method according to any one of claims 1 to 5.
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 CN110516024A (en) | 2019-11-29 |
| CN110516024B true 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) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117540113A (en) * | 2023-11-27 | 2024-02-09 | 南京联迪信息系统股份有限公司 | Geographic position information searching method, system, equipment and storage medium |
Citations (4)
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096037A (en) * | 2016-06-27 | 2016-11-09 | 北京百度网讯科技有限公司 | Search Results polymerization based on artificial intelligence, device and search engine |
-
2019
- 2019-08-30 CN CN201910818067.9A patent/CN110516024B/en active Active
Patent Citations (4)
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110516024A (en) | 2019-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109240576B (en) | Image processing method and device in game, electronic device and storage medium | |
| CN110390054B (en) | Interest point recall method, device, server and storage medium | |
| US10733197B2 (en) | Method and apparatus for providing information based on artificial intelligence | |
| CN107832662B (en) | Method and system for acquiring image annotation data | |
| US11475588B2 (en) | Image processing method and device for processing image, server and storage medium | |
| CN109408829B (en) | Method, device, equipment and medium for determining readability of article | |
| CN107909088B (en) | Method, apparatus, device and computer storage medium for obtaining training samples | |
| US20210166014A1 (en) | Generating document summary | |
| CN113806588B (en) | Method and device for searching video | |
| CN111738791B (en) | Text processing method, device, equipment and storage medium | |
| CN111124863B (en) | Intelligent device performance testing method and device and intelligent device | |
| CN117011581A (en) | Image recognition method, medium, device and computing equipment | |
| CN111310065A (en) | Social contact recommendation method and device, server and storage medium | |
| CN113762303B (en) | Image classification method, device, electronic equipment and storage medium | |
| CN110516024B (en) | Map search result display method, device, equipment and storage medium | |
| CN111125550A (en) | Interest point classification method, device, equipment and storage medium | |
| WO2021104274A1 (en) | Image and text joint representation search method and system, and server and storage medium | |
| US8996984B2 (en) | Automatic visual preview of non-visual data | |
| CN107239209B (en) | Photographing search method, device, terminal and storage medium | |
| CN110704650A (en) | OTA picture tag identification method, electronic device and medium | |
| US11842165B2 (en) | Context-based image tag translation | |
| CN115017385A (en) | Article searching method, device, equipment and storage medium | |
| CN114817590A (en) | Path storage method, path query method and device, medium and electronic equipment | |
| CN111124862B (en) | Intelligent device performance testing method and device and intelligent device | |
| CN110276001B (en) | Checking page identification method and device, computing equipment and 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 |