CN104166659B - A kind of map datum sentences the method and system of weight - Google Patents
A kind of map datum sentences the method and system of weight Download PDFInfo
- Publication number
- CN104166659B CN104166659B CN201310185832.0A CN201310185832A CN104166659B CN 104166659 B CN104166659 B CN 104166659B CN 201310185832 A CN201310185832 A CN 201310185832A CN 104166659 B CN104166659 B CN 104166659B
- Authority
- CN
- China
- Prior art keywords
- interest
- query
- points
- interest points
- directed
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000005295 random walk Methods 0.000 claims abstract description 15
- 238000012216 screening Methods 0.000 claims description 9
- 238000009825 accumulation Methods 0.000 claims 4
- 238000010586 diagram Methods 0.000 description 4
- 241000283690 Bos taurus Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of methods that map datum sentences weight, comprising: generates digraph according to the number of clicks of point of interest in the search result of User action log statistical query word, and according to the corresponding relationship of query word, point of interest and number of clicks；According to the digraph, the similarity between point of interest is obtained using Random Walk Algorithm；When the similarity of two points of interest is greater than preset threshold, determine described two points of interest for repeated data；The present invention also provides the systems that a kind of map datum sentences weight.The technical solution provided according to the present invention can effectively identify duplicate point of interest in electronic map application.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the field of internet application, in particular to a method and a system for judging repetition of map data.
[ background of the invention ]
With the popularization of Geographic Information Systems (GISs), data such as names and profiles of places in which people are interested, such as government offices, sightseeing spots, hotels, restaurants, shopping malls, hospitals, and the like, are introduced into electronic maps, and the places in which people are interested are referred to as points of Interest (POIs).
When the electronic map is used, more than one interest point is provided for a user as a search result according to query (query word) input by the user, but the data sources of the interest points in the current electronic map application are more and more complicated, so that repeated interest points appear in the search result, interference is generated on the user, when the user cannot identify which interest point needs to be known, all the interest points in the search result are clicked, manual screening is further performed, and therefore, in order to guarantee the effectiveness and reliability of the interest points and improve the uniqueness, the interest points need to be subjected to judgment and reprocessing.
At present, the method for judging the weight of an interest point is as follows: starting from the data of the interest points, such as the names, addresses, longitude and latitude coordinates and the like of the interest points, the names of the interest points are firstly analyzed, the core words of the names are extracted, then whether the names of the adjacent interest points have the same core words with the names of the current interest points or not is judged according to the longitude and latitude coordinates of the interest points, and whether the interest points are repeated or not is comprehensively judged. The disadvantage of this method for judging the weight of the interest point is: whether the interest points are repeated is judged only according to the data of the interest points, such as names and addresses, if the interest points have other names or the interest points have differences of only a few characters, the judgment of the interest points fails, for example, the two groups of interest points are repeated, but the two groups of interest points cannot be identified by the current judgment method, so that the identification rate of the repeated interest points in the current interest point judgment method is low.
[ summary of the invention ]
The invention provides a method and a system for judging the repetition of map data, which can effectively identify repeated interest points in electronic map application.
The specific technical scheme of the invention is as follows:
according to a preferred embodiment of the present invention, a method for judging duplication of map data includes:
counting the number of clicks of interest points in the search results of the query words according to the user behavior logs, and generating a directed graph according to the corresponding relation among the query words, the interest points and the number of clicks;
according to the directed graph, obtaining similarity between interest points by using a random walk algorithm;
and when the similarity of the two interest points is greater than a preset threshold value, judging that the two interest points are repeated data.
In the method, the query term is obtained by screening the query term in the user click log according to the general demand.
In the above method, the directed graph includes more than one directed edge;
the two ends of the directed edge are respectively a query word and an interest point;
the directional direction of the directional edge is that the interest point points to the query word;
and the weighted value of the directed edge is the click frequency of the interest point.
In the above method, the obtaining of the similarity between the points of interest by using the random walk algorithm specifically includes:
for each interest point, dividing the weight value of the directed edge of the interest point by the sum of the weight values of the directed edges connected with the interest point to obtain the normalized probability of the directed edge;
taking the interest point as a starting point, and walking to query words of an opposite end through all directed edges connected with the interest point; after the query term of the opposite end is reached, the query term of the opposite end is taken as a starting point, the interest point of the opposite end of the query term is walked through a directed edge connected with the query term until the preset iteration times are reached, and the iteration is stopped to obtain all paths of two interest points;
multiplying the normalized probability of the directed edge in each path to obtain the probability of the path;
and accumulating the probabilities of all paths of the two interest points to obtain the similarity of the two interest points.
A system for map data re-determination, comprising: the device comprises a generating unit, a counting unit and a judging unit; wherein,
the generating unit is used for counting the click times of the interest points in the search results of the query words according to the user behavior logs and generating a directed graph according to the corresponding relation among the query words, the interest points and the click times;
the statistical unit is used for obtaining the similarity between the interest points by utilizing a random walk algorithm according to the directed graph generated by the generating unit;
and the judging unit is used for judging that the two interest points are repeated data when the similarity of the two interest points is greater than a preset threshold value.
In the system, the query term is obtained by screening the query term in the user click log according to the general demand.
In the system, the directed graph includes more than one directed edge;
the two ends of the directed edge are respectively a query word and an interest point;
the directional direction of the directional edge is that the interest point points to the query word;
and the weighted value of the directed edge is the click frequency of the interest point.
In the above system, when the statistical unit obtains the similarity between the points of interest by using the random walk algorithm, the statistical unit specifically includes:
for each interest point, dividing the weight value of the directed edge of the interest point by the sum of the weight values of the directed edges connected with the interest point to obtain the normalized probability of the directed edge;
taking the interest point as a starting point, and walking to query words of an opposite end through all directed edges connected with the interest point; after the query term of the opposite end is reached, the query term of the opposite end is taken as a starting point, the interest point of the opposite end of the query term is walked through a directed edge connected with the query term until the preset iteration times are reached, and the iteration is stopped to obtain all paths of two interest points;
multiplying the normalized probability of the directed edge in each path to obtain the probability of the path;
and accumulating the probabilities of all paths of the two interest points to obtain the similarity of the two interest points.
According to the technical scheme, the invention has the following beneficial effects:
the POI clustering is carried out based on the user click log, repeated data which cannot be covered by POI judgment at present can be effectively identified, repeated interest points in the electronic map application are effectively identified, and the identification rate and the accuracy rate of the repeated interest points are improved.
[ description of the drawings ]
FIG. 1 is a flow chart illustrating a preferred embodiment of a method for implementing a map data re-determination according to the present invention;
FIG. 2 is an exemplary diagram of a directed graph in the present invention;
fig. 3 is a schematic structural diagram of a system for implementing the map data re-determination according to a preferred embodiment of the present invention.
[ detailed description ] embodiments
The basic idea of the invention is: counting the number of clicks of interest points in the search results of the query words according to the user behavior logs, and generating a directed graph according to the corresponding relation among the query words, the interest points and the number of clicks; according to the directed graph, obtaining similarity between interest points by using a random walk algorithm; and when the similarity of the two interest points is greater than a preset threshold value, judging that the two interest points are repeated data.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
The invention provides a method for judging the weight of map data, fig. 1 is a schematic flow chart of a preferred embodiment of the method for realizing the weight judgment of the map data, and as shown in fig. 1, the preferred embodiment comprises the following steps:
and step S101, obtaining the query words searched by the user according to the user click log, and removing the universal demand query words.
Specifically, the user click log in the latest period of time is obtained from the background server, for example, the user click log in the latest month may be obtained, where the user click log includes a query searched by the user and a POI clicked by the user in a search result of the query.
Obtaining a query set of a user in a recent period of time from the user click log, screening the query set according to a preset universal demand word list, identifying a universal demand query from the query set, and deleting the identified universal demand query from the query set; for example, a universal demand query such as "gourmet", "hotel" or "school" is deleted from the query set.
When the general demand search is carried out, the POI clicked in the search result by the user is dispersed, the repeated POI can not be clicked generally, but the repeated POI can be clicked by the user in the accurate search, so that the query of the user needs to be screened, and the general demand query is removed.
Step S102, counting the number of clicks of the interest points in the search result of the query word according to the user behavior log, and generating a directed graph according to the corresponding relation among the query word, the interest points and the number of clicks.
Specifically, for the query obtained after screening, the electronic map application provides more than one POI in the search result for the user to select, for example, the query word in the electronic map application is "cattle street post office", and the search result is two POIs of "cattle street post office" and "north jing city south area post office" respectively; in the preferred embodiment, for each query obtained after screening, counting the number of clicks of each POI under the query within a recent period of time according to the user click log; for example, the number of clicks of a POI under each query in the last month can be counted.
After the number of clicks of the POI clicked by the user is obtained, generating a query input by the user, the POI in the search result of the query and a corresponding relation of the number of clicks of the POI, wherein more than one POI can exist in one search result of the query, and each POI has one number of clicks; here, if the correspondence is directly used to identify duplicate POIs, the accuracy of the identified duplicate POIs is low because only click information of one query is used, and if duplicate POIs are identified using multiple correspondences, the relationships between POIs can be identified using click information of multiple queries, and the accuracy of the identified POIs is high; for example, for query1, if a user clicks POI a and POI B, it cannot be determined that POI a and POI B are duplicate POIs, but for query1, query2 and query3, if the user clicks POI a and POI B, POIA and POI B are more likely to be duplicate POIs; based on the principle, in the preferred embodiment, a directed graph needs to be generated according to a query input by a user, a POI clicked by the user in a search result of the query, and a corresponding relationship of the click times of the POI, wherein in the directed graph, if there is a click from the query to the POI, a directed edge is formed, each directed edge has two nodes, one is a starting point and the other is an end point, the direction of the directed edge is the POI pointing query, which indicates that the POI is a POI under the query, so that the POI is the starting point and the query is the end point, and the click times of the POI in the corresponding relationship are used as weighted values of the directed edge; here, since the present invention is to obtain the relationship between POIs, a POI is used as a starting point of a directed edge.
Fig. 2 is an exemplary diagram of a directed graph in the present invention, and as shown in fig. 2, POI a points to query2 and query4, POIB points to query1, POI C points to query2, and POI D points to query2 and query4, respectively, indicating that for query1, the user clicks POI B, for query2, the user clicks POI a, POI C, and POI D, for query3, the user does not click any POI, and for query4, the user clicks POI a and POI D.
And S103, obtaining the similarity between the interest points by utilizing a random walk algorithm according to the directed graph, and judging that the two interest points with the similarity larger than a preset threshold are repeated data.
Specifically, according to the directed graph generated in step S102, in the preferred embodiment, the calculating by using a random walk (random walk) algorithm to obtain the similarity between the POIs specifically includes:
firstly, each POI has more than one directed edge connected to the POI, each directed edge has a weight value, and the weight value of each directed edge is divided by the sum of the weight values of the directed edges connected to the POI to obtain the normalized probability of the directed edge, that is: the sum of the normalized probabilities of the directed edges connected to the same POI is equal to 1; by the method, the corresponding normalized probability can be calculated for each directed edge of each POI, so that the corresponding normalized probability can be calculated for all directed edges in the directed graph.
Then, for each POI, taking the POI as a starting point, moving to the query of the opposite end through all directed edges connected with the POI, and when moving to the query of the opposite end through the directed edges, the probability of each directed edge is the same; after the query of an opposite end is reached, the query is taken as a starting point, the POI of the opposite end of the query is walked through the directed edge connected with the query, iteration is carried out in this way until the preset iteration times are reached, all paths from one POI to another POI can be obtained after the iteration is stopped, each path comprises more than two directed edges, the normalized probability of the directed edge in each path is multiplied to obtain the probability of the path, and the probabilities of all paths from one POI to another POI are accumulated to obtain the similarity of the two POIs; the iteration number may be pre-configured according to a requirement, for example, the iteration number is generally configured to be 4 times in actual application.
And comparing the calculated similarity with a preset threshold value, and judging that the two POIs with the similarity larger than the preset threshold value are repeated data.
For example, as shown in fig. 2, there are two routes from POI a to POI D, i.e., POI a → query2 → POI D and POI a → query4 → POI D, and thus the similarity of POI a and POI D is equal to the sum of the probabilities of the two routes, and the probability of POI a → query2 → POI D route is equal to the product of the normalized probability of the directional edge from POI a to query2 and the normalized probability of the directional edge from query2 to POI D.
If the search result of the same query contains repeated data, probability difference of the user clicking the repeated data is small, if the user clicks two identical POIs for many times under multiple queries, probability that the two POIs are the repeated data is high, and thus, in the generated directed graph, multiple paths exist between the two POIs, sum of the paths is large, similarity of the two POIs is high, and if the similarity is larger than a preset threshold, the two POIs are judged to be the repeated data, as shown in FIG. 2, POIs corresponding to query2 and query4 are POI A and POI D, and the probability that the POI A and the POI D are the repeated data is high as counted by the method.
In order to implement the above method, the present invention further provides a system for determining the weight of the map data, fig. 3 is a schematic structural diagram of a preferred embodiment of the system for determining the weight of the map data, as shown in fig. 3, a generating unit 30, a counting unit 31, and a weight determining unit 32; wherein,
the generating unit 30 is configured to count click times of interest points in search results of the query term according to the user behavior log, and generate a directed graph according to a corresponding relationship between the query term, the interest points, and the click times;
the statistical unit 31 is configured to obtain similarity between the points of interest by using a random walk algorithm according to the directed graph generated by the generating unit 30;
the repeated judging unit 32 is configured to judge that the two interest points are repeated data when the similarity of the two interest points is greater than a preset threshold.
The query term is obtained by screening the query terms in the user click log according to the universal demand.
Wherein the directed graph comprises more than one directed edge; the two ends of the directed edge are respectively a query word and an interest point; the directional direction of the directional edge is that the interest point points to the query word; and the weighted value of the directed edge is the click frequency of the interest point.
When the statistical unit 31 obtains the similarity between the points of interest by using the random walk algorithm, specifically, the method includes:
for each interest point, dividing the weight value of the directed edge of the interest point by the sum of the weight values of the directed edges connected with the interest point to obtain the normalized probability of the directed edge;
taking the interest point as a starting point, and walking to query words of an opposite end through all directed edges connected with the interest point; after the query term of the opposite end is reached, the query term of the opposite end is taken as a starting point, the interest point of the opposite end of the query term is walked through a directed edge connected with the query term until the preset iteration times are reached, and the iteration is stopped to obtain all paths of two interest points;
multiplying the normalized probability of the directed edge in each path to obtain the probability of the path;
and accumulating the probabilities of all paths of the two interest points to obtain the similarity of the two interest points.
According to the technical scheme, the repeated judgment is not carried out according to the data of the interest points, the POI clustering is carried out based on the click logs of the user, repeated data which cannot be covered by the current online POI repeated judgment can be effectively identified, repeated interest points in the electronic map application are effectively identified, and the identification rate and the accuracy rate of the repeated interest points are improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A method for judging the repetition of map data is characterized by comprising the following steps:
counting the number of clicks of interest points in the search results of the query words according to the user behavior logs, and generating a directed graph according to the corresponding relation among the query words, the interest points and the number of clicks;
according to the directed graph, utilizing a random walk algorithm to obtain probability accumulation of all paths between interest points, and taking the probability accumulation as the similarity between the interest points;
and when the similarity of the two interest points is greater than a preset threshold value, judging that the two interest points are repeated data.
2. The method according to claim 1, wherein the query term is obtained by performing a general demand query term screening on the query terms in the user click log.
3. The method of claim 1,
the directed graph includes more than one directed edge;
the two ends of the directed edge are respectively a query word and an interest point;
the directional direction of the directional edge is that the interest point points to the query word;
and the weighted value of the directed edge is the click frequency of the interest point.
4. The method according to claim 3, wherein the obtaining the similarity between the interest points by using the random walk algorithm is specifically:
for each interest point, dividing the weight value of the directed edge of the interest point by the sum of the weight values of the directed edges connected with the interest point to obtain the normalized probability of the directed edge;
taking the interest point as a starting point, and walking to query words of an opposite end through all directed edges connected with the interest point; after the query term of the opposite end is reached, the query term of the opposite end is taken as a starting point, the interest point of the opposite end of the query term is walked through a directed edge connected with the query term until the preset iteration times are reached, and the iteration is stopped to obtain all paths of two interest points;
multiplying the normalized probability of the directed edge in each path to obtain the probability of the path;
and accumulating the probabilities of all paths of the two interest points to obtain the similarity of the two interest points.
5. A system for determining duplication of map data, the system comprising: the device comprises a generating unit, a counting unit and a judging unit; wherein,
the generating unit is used for counting the click times of the interest points in the search results of the query words according to the user behavior logs and generating a directed graph according to the corresponding relation among the query words, the interest points and the click times;
the statistical unit is used for obtaining the probability accumulation of all paths between the interest points by utilizing a random walk algorithm according to the directed graph generated by the generating unit and taking the probability accumulation as the similarity between the interest points;
and the judging unit is used for judging that the two interest points are repeated data when the similarity of the two interest points is greater than a preset threshold value.
6. The system according to claim 5, wherein the query term is obtained by performing a general demand query term screening on the query terms in the user click log.
7. The system of claim 5,
the directed graph includes more than one directed edge;
the two ends of the directed edge are respectively a query word and an interest point;
the directional direction of the directional edge is that the interest point points to the query word;
and the weighted value of the directed edge is the click frequency of the interest point.
8. The system according to claim 7, wherein the statistical unit, when obtaining the similarity between the interest points by using the random walk algorithm, specifically:
for each interest point, dividing the weight value of the directed edge of the interest point by the sum of the weight values of the directed edges connected with the interest point to obtain the normalized probability of the directed edge;
taking the interest point as a starting point, and walking to query words of an opposite end through all directed edges connected with the interest point; after the query term of the opposite end is reached, the query term of the opposite end is taken as a starting point, the interest point of the opposite end of the query term is walked through a directed edge connected with the query term until the preset iteration times are reached, and the iteration is stopped to obtain all paths of two interest points;
multiplying the normalized probability of the directed edge in each path to obtain the probability of the path;
and accumulating the probabilities of all paths of the two interest points to obtain the similarity of the two interest points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310185832.0A CN104166659B (en) | 2013-05-20 | 2013-05-20 | A kind of map datum sentences the method and system of weight |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310185832.0A CN104166659B (en) | 2013-05-20 | 2013-05-20 | A kind of map datum sentences the method and system of weight |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104166659A CN104166659A (en) | 2014-11-26 |
| CN104166659B true CN104166659B (en) | 2019-03-08 |
Family
ID=51910478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310185832.0A Active CN104166659B (en) | 2013-05-20 | 2013-05-20 | A kind of map datum sentences the method and system of weight |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104166659B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570046A (en) * | 2016-03-02 | 2017-04-19 | 合网络技术（北京）有限公司 | Method and device for recommending relevant search data based on user operation behavior |
| CN107462253B (en) * | 2016-06-06 | 2019-01-11 | 腾讯科技（深圳）有限公司 | A kind of navigation data processing method, apparatus and system |
| CN109635053B (en) * | 2018-10-31 | 2021-01-12 | 百度在线网络技术（北京）有限公司 | Map quality inspection method, device, system and storage medium |
| CN113255398B (en) * | 2020-02-10 | 2023-08-18 | 百度在线网络技术（北京）有限公司 | Point of interest weight judging method, device, equipment and storage medium |
| CN112507223B (en) * | 2020-12-10 | 2023-06-23 | 北京百度网讯科技有限公司 | Data processing method, device, electronic equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101026627A (en) * | 2007-03-15 | 2007-08-29 | 上海交通大学 | Multi-source data fusion system based on rule and certainty factor |
| CN101350032A (en) * | 2008-09-23 | 2009-01-21 | 胡辉 | Method for judging whether web page content is identical or not |
| CN101477554A (en) * | 2009-01-16 | 2009-07-08 | 西安电子科技大学 | User interest based personalized meta search engine and search result processing method |
| CN103036921A (en) * | 2011-09-29 | 2013-04-10 | 北京新媒传信科技有限公司 | User behavior analysis system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025737B (en) * | 2006-02-22 | 2011-08-17 | 王东 | Attention degree based same source information search engine aggregation display method |
-
2013
- 2013-05-20 CN CN201310185832.0A patent/CN104166659B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101026627A (en) * | 2007-03-15 | 2007-08-29 | 上海交通大学 | Multi-source data fusion system based on rule and certainty factor |
| CN101350032A (en) * | 2008-09-23 | 2009-01-21 | 胡辉 | Method for judging whether web page content is identical or not |
| CN101477554A (en) * | 2009-01-16 | 2009-07-08 | 西安电子科技大学 | User interest based personalized meta search engine and search result processing method |
| CN103036921A (en) * | 2011-09-29 | 2013-04-10 | 北京新媒传信科技有限公司 | User behavior analysis system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104166659A (en) | 2014-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104080054B (en) | A kind of acquisition methods and device of exception point of interest | |
| CN108170793B (en) | Vehicle semantic track data-based dwell point analysis method and system | |
| Dredze et al. | Carmen: A twitter geolocation system with applications to public health | |
| CN109478184B (en) | Identifying, processing, and displaying clusters of data points | |
| CN104166659B (en) | A kind of map datum sentences the method and system of weight | |
| CN103220376B (en) | Method for positioning IP (Internet Protocol) by position data of mobile terminal | |
| US9049549B2 (en) | Method and apparatus for probabilistic user location | |
| Han et al. | A stacking-based approach to twitter user geolocation prediction | |
| US9159030B1 (en) | Refining location detection from a query stream | |
| CN104850649B (en) | A kind of method and system that point of interest sampling is carried out on map | |
| CN104572955A (en) | System and method for determining POI name based on clustering | |
| CN110263117B (en) | Method and device for determining POI (Point of interest) data | |
| CN103808325A (en) | Method and device for generating traffic travel scheme | |
| CN105550221B (en) | Information search method and device | |
| WO2017008653A1 (en) | Poi service provision method, poi data processing method and device | |
| WO2016107352A1 (en) | System and method for determining poi name and for determining validity of poi information | |
| Kilic et al. | Effects of reverse geocoding on OpenStreetMap tag quality assessment | |
| Lee et al. | A probabilistic place extraction algorithm based on a superstate model | |
| CN106940189B (en) | Classical line acquisition method and device in navigation system | |
| US10783169B1 (en) | Inferring user interests from geo-location reports | |
| TW202146850A (en) | Processing apparatus and method for determining road names | |
| CN113923184A (en) | IP positioning reference point extraction method, device and readable storage medium | |
| CN112861023A (en) | Map information processing method, map information processing apparatus, map information processing device, storage medium, and program product | |
| CN107508925A (en) | A kind of method and apparatus for being used to determine the regional information of IP address | |
| CN112966192A (en) | Region address naming method and device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |