CN107908761B - Keyword extraction method and device based on geographic position - Google Patents
Keyword extraction method and device based on geographic position Download PDFInfo
- Publication number
- CN107908761B CN107908761B CN201711193955.3A CN201711193955A CN107908761B CN 107908761 B CN107908761 B CN 107908761B CN 201711193955 A CN201711193955 A CN 201711193955A CN 107908761 B CN107908761 B CN 107908761B
- Authority
- CN
- China
- Prior art keywords
- behavior feature
- behavior
- specified
- feature word
- word
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 45
- 230000006399 behavior Effects 0.000 claims description 349
- 238000007635 classification algorithm Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000003066 decision tree Methods 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 8
- 239000000758 substrate Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
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
One or more embodiments of the present specification disclose a keyword extraction method and apparatus based on a geographic location, so as to implement diversity of keyword extraction. The method comprises the following steps: acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position; acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position; and determining keywords related to the specified geographic position according to the first behavior characteristic word and/or the second behavior characteristic word.
Description
Technical Field
The present disclosure relates to the field of information mining technologies, and in particular, to a method and an apparatus for extracting keywords based on geographic locations.
Background
Keyword extraction has important application in the fields of information retrieval, natural language processing and the like. The keyword extraction is used as a way for rapidly acquiring the document theme, and brings much convenience to the life and work of the user, for example, the intention of the user is rapidly known according to the search keyword of the user, so that some useful information is recommended to the user according to the intention of the user. However, in many aspects, the keyword extraction mostly adopts a method of mining keywords from document contents, and is relatively single, so that the method has a large perfection space.
Disclosure of Invention
One or more embodiments of the present disclosure provide a method and an apparatus for extracting keywords based on geographic locations, so as to achieve diversity of keyword extraction.
To solve the above technical problem, one or more embodiments of the present specification are implemented as follows:
in one aspect, one or more embodiments of the present specification provide a keyword extraction method based on a geographic location, including:
acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position;
and determining keywords related to the specified geographic position according to the first behavior characteristic word and/or the second behavior characteristic word.
Optionally, the obtaining a first behavior feature word of the first class of users based on the designated geographic location includes:
determining a time at which the first class of users is located at the specified geographic location;
acquiring behavior information of the first class of users aiming at the specified geographic position within a preset time period before the time of locating at the specified geographic position;
and determining the first behavior feature word according to the behavior information.
Optionally, the behavior information includes at least one of search behavior information and browsing behavior information; the first behavior feature words comprise at least one of search words and browsing words.
Optionally, the determining, according to the first behavior feature word and/or the second behavior feature word, a keyword related to the specified geographic location includes:
training the plurality of first behavior feature words and the plurality of second behavior feature words by using a specified second classification algorithm to obtain contribution values of the first behavior feature words to the specified geographic position;
and selecting at least one first behavior feature word as a keyword related to the specified geographic position according to the contribution value.
Optionally, the training, by using a specified second classification algorithm, the plurality of first behavior feature words and the plurality of second behavior feature words respectively to obtain a contribution value of each first behavior feature word to the specified geographic location includes:
determining contribution values of the first behavior feature words to the designated geographic position according to the occurrence rates of the first behavior feature words in the first behavior feature words and the second behavior feature words;
wherein the contribution value is proportional to the occurrence rate of the first behavior feature word in the plurality of first behavior feature words and inversely proportional to the occurrence rate of the first behavior feature word in the plurality of second behavior feature words.
Optionally, the specified two-classification algorithm includes at least one of a logistic regression algorithm and an iterative decision tree algorithm.
Optionally, the designated geographic location is foreign, and the unspecified geographic location is domestic.
Optionally, the designated geographic location is a designated country, and the unspecified geographic location is a country other than the designated country.
Optionally, the obtaining of the geographical location information of the target user includes:
and acquiring the geographical position information of the target user according to the Location Based Service (LBS).
In another aspect, one or more embodiments of the present specification provide a keyword extraction apparatus based on a geographic location, including:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module acquires the geographical position information of a target user and determines the user type of the target user according to the geographical position information, and the user type comprises a first type of user located at a specified geographical position and/or a second type of user located at a non-specified geographical position;
the second obtaining module is used for obtaining a first behavior feature word of the first type of users based on the appointed geographic position and/or obtaining a second behavior feature word of the second type of users based on the non-appointed geographic position;
and the determining module is used for determining the keywords related to the specified geographic position according to the first behavior characteristic word and/or the second behavior characteristic word.
Optionally, the second obtaining module includes:
the first determining unit is used for determining the time when the first class of users are located at the specified geographic position;
the first acquisition unit is used for acquiring the behavior information of the first class of users aiming at the specified geographic position in a preset time period before the time of locating the first class of users at the specified geographic position;
and the second determining unit is used for determining the first behavior feature word according to the behavior information.
Optionally, the behavior information includes at least one of search behavior information and browsing behavior information; the first behavior feature words comprise at least one of search words and browsing words.
Optionally, the determining module includes:
the training unit is used for training the first behavior feature words and the second behavior feature words respectively by using a specified second classification algorithm so as to obtain contribution values of the first behavior feature words to the specified geographic position respectively;
and the selection unit is used for selecting at least one first behavior characteristic word as a keyword related to the specified geographic position according to the contribution value.
Optionally, the training unit is further configured to:
determining contribution values of the first behavior feature words to the designated geographic position according to the occurrence rates of the first behavior feature words in the first behavior feature words and the second behavior feature words;
wherein the contribution value is proportional to the occurrence rate of the first behavior feature word in the plurality of first behavior feature words and inversely proportional to the occurrence rate of the first behavior feature word in the plurality of second behavior feature words.
Optionally, the specified two-classification algorithm includes at least one of a logistic regression algorithm and an iterative decision tree algorithm.
Optionally, the designated geographic location is foreign, and the unspecified geographic location is domestic.
Optionally, the designated geographic location is a designated country, and the unspecified geographic location is a country other than the designated country.
Optionally, the first obtaining module includes:
and the second acquisition unit acquires the geographical position information of the target user according to the Location Based Service (LBS).
In another aspect, one or more embodiments of the present specification provide a keyword extraction apparatus based on a geographic location, including:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position;
and determining keywords related to the specified geographic position according to the first behavior characteristic word and/or the second behavior characteristic word.
In yet another aspect, one or more embodiments of the present specification provide a storage medium storing computer-executable instructions that, when executed, implement the following:
acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position;
and determining keywords related to the specified geographic position according to the first behavior characteristic word and/or the second behavior characteristic word.
By adopting the technical scheme of one or more embodiments of the specification, the user type of the target user is determined according to the geographical position information by acquiring the geographical position information of the target user, the first behavior characteristic word of the first class of users based on the designated geographical position is acquired, and/or the second behavior characteristic word of the second class of users based on the non-designated geographical position is acquired, and then the keyword related to the designated geographical position is determined according to the first behavior characteristic word and/or the second behavior characteristic word. Therefore, the technical scheme can automatically dig out the keywords related to the specified geographic position based on the geographic position information and the behavior characteristic words of various target users, and compared with the traditional method which only can extract the keywords from the document, the method has the advantages that the keyword extraction diversity is improved, the extracted keywords can better accord with the user behaviors, and the coverage rate is wider.
Drawings
In order to more clearly illustrate one or more embodiments or technical solutions in the prior art in the present specification, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in one or more embodiments of the present specification, and other drawings can be obtained by those skilled in the art without inventive exercise.
FIG. 1 is a schematic flow chart diagram of a method for geographic location based keyword extraction in accordance with one embodiment of the present description;
FIG. 2 is a schematic flow chart of a method for extracting keywords based on geographic location according to a specific embodiment of the present disclosure;
FIG. 3 is a schematic flow chart diagram of a method for extracting keywords based on geographic location according to a second embodiment of the present disclosure;
FIG. 4 is a schematic block diagram of a geographic location based keyword extraction apparatus in accordance with an embodiment of the present description;
fig. 5 is a schematic block diagram of a keyword extraction apparatus based on a geographic location according to an embodiment of the present specification.
Detailed Description
One or more embodiments of the present disclosure provide a keyword extraction method and apparatus based on a geographic location, so as to implement diversity of keyword extraction.
In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments of the present disclosure without making any creative effort shall fall within the protection scope of one or more of the embodiments of the present disclosure.
Fig. 1 is a schematic flow chart of a method for extracting keywords based on geographic location according to an embodiment of the present specification, as shown in fig. 1, the method includes:
step S102, obtaining the geographical position information of the target user, and determining the user type of the target user according to the geographical position information.
The user types comprise a first type of users located at a specified geographic position and/or a second type of users located at a non-specified geographic position. The division of the designated geographic location from the non-designated geographic location may be based on whether it is cross-border, whether it is located in a country, whether it is located in a city, etc. For example, when a designated geographic location is abroad (i.e., cross-border), a non-designated geographic location is domestic; when the designated geographic location is Beijing, the non-designated geographic location is a city other than Beijing.
And step S104, acquiring a first behavior characteristic word of the first type of users based on the designated geographic position, and/or acquiring a second behavior characteristic word of the second type of users based on the non-designated geographic position.
In one embodiment, the behavior feature words may include search words, browsing words, and the like. The search terms include terms searched by the target user and related to the specified geographic location, for example, in the search behavior information of the target user for the specified geographic location (such as the grand link), it is recorded that the target user views a related search result by searching the "grand link travel strategy", and the "grand link travel strategy" is the search terms. The browsing words include keywords in the document contents browsed by the target user, for example, if the target user browses the document "big company travel strategy", the keywords "travel strategy", "seashore road", etc. in the document are the browsing words.
And step S106, determining keywords related to the specified geographic position according to the first behavior characteristic words and/or the second behavior characteristic words.
By adopting the technical scheme of one or more embodiments of the specification, the user type of the target user is determined according to the geographical position information by acquiring the geographical position information of the target user, the first behavior characteristic word of the first class of users based on the designated geographical position is acquired, and/or the second behavior characteristic word of the second class of users based on the non-designated geographical position is acquired, and then the keyword related to the designated geographical position is determined according to the first behavior characteristic word and/or the second behavior characteristic word. Therefore, the technical scheme can automatically dig out the keywords related to the specified geographic position based on the geographic position information and the behavior characteristic words of various target users, and compared with the traditional method which only can extract the keywords from the document, the method has the advantages that the keyword extraction diversity is improved, the extracted keywords can better accord with the user behaviors, and the coverage rate is wider.
The following describes a keyword extraction method based on geographic location in detail.
Step S102 is executed first, that is, geographical location information of the target user is obtained, and the user type of the target user is determined according to the geographical location information.
In one embodiment, the geographical Location information of the target user may be obtained according to LBS (Location Based Service). LBS is a value added service that obtains the location Information of the terminal user through the radio communication network or external positioning mode of the telecom mobile operator, and provides corresponding service for the user under the support of the GIS (Geographic Information System) platform.
The user types of the target users include a first type of users located at a specified geographic location and/or a second type of users located at a non-specified geographic location. The division of the designated geographic location from the non-designated geographic location may be based on whether it is cross-border, whether it is located in a country, whether it is located in a city, etc. For example, when a designated geographic location is abroad (i.e., cross-border), a non-designated geographic location is domestic; when the designated geographic location is Beijing, the non-designated geographic location is a city other than Beijing.
The term "located at a specified geographical location" as used herein does not mean that the user is currently located at the specified geographical location, but means that the acquired geographical location information of the target user includes information of the specified geographical location, that is, the target user was located at the specified geographical location for a certain period of time. If the target user is located at the designated geographical position in a certain time period, the target user can be considered to belong to a first class of users; otherwise, if the target user is not located in the designated geographic location, the target user may be considered to belong to a second class of users located in a non-designated geographic location. Therefore, when acquiring the geographical location information of the target user, only the geographical location information of the target user within a period of time may be acquired, such as acquiring the geographical location information of the target user within the last month.
For example, the designated geographic location is a singapore, and if the target user is determined to be located on the singapore according to the geographic location information of the target user in the last month, the target user is indicated to belong to a first class of users located at the designated geographic location, namely the singapore; if the target user is determined not to be located in the singapore according to the geographical location information of the target user in the last month, the target user is indicated to belong to a second class of users located in non-specified geographical locations (namely, other countries except the singapore).
After the user type of the target user is determined, step S104 is continuously performed, that is, a first behavior feature word of the first type of user based on the designated geographic location is acquired, and/or a second behavior feature word of the second type of user based on the non-designated geographic location is acquired.
In one embodiment, when determining the first behavioral characteristic word, a time when the first type of user is located at the specified geographic location may be first determined; secondly, acquiring behavior information of the first class of users aiming at the specified geographic position in a preset time period before the time; and then determining a first behavior feature word according to the behavior information.
The behavior information may include search behavior information, browsing behavior information, and the like. For example, if the designated geographic location is a hyperlink, the search behavior information and the browsing behavior information of the target user for the hyperlink can be obtained according to the search behavior (e.g., searching for the hyperlink travel strategy) and the browsing behavior (e.g., browsing the article recommended by the hyperlink food) executed by the target user and related to the hyperlink.
In order to ensure the accuracy of keyword extraction by the acquired behavior information, the preset time period should not be set to a long time period in general, and may be set to a time period within 10 days, half a month, or 1 month before the time when the target user is located at the designated geographical location. For example, the preset time period is a time period within 10 days before the time when the target user is located at the designated geographic location, and assuming that the time when the target user is located at the designated geographic location — beijing is determined to be 2017, 10 and 15 days, behavior information for the designated geographic location — beijing within 10 days before 2017, 10 and 15 days (i.e., between 2017, 10 and 5 days, and 2017, 10 and 15 days) can be acquired.
The first behavior feature word comprises at least one of a search word and a browsing word. The search terms include terms searched by the first type of users and related to the specified geographic location, for example, in the search behavior information of the first type of users for the specified geographic location (such as the world wide web), it is recorded that the first type of users view related search results by searching for "world wide web travel strategy", and the "world wide web travel strategy" is the search terms. The browsing words include keywords in the document contents browsed by the first type of user, for example, if the first type of user browses the document "big-link travel strategy", the keywords "travel strategy", "seashore road", etc. in the document are the browsing words.
The second behavior feature word is obtained in a similar manner to the first behavior feature word, except that the geographic location for which the second behavior feature word is targeted may be in a wider range. For example, if it is known that the second type of user is located in a city, such as beijing, shanghai, or san, other than the designated geographic location, according to the geographic location information of the second type of user, the second behavior feature word may be extracted from the words, which are searched by the second type of user, related to the cities, such as beijing, shanghai, and san, or the keyword may be extracted from the document contents, which are browsed by the second type of user, related to the cities, such as beijing, shanghai, and san.
After the first behavior feature word and the second behavior feature word are obtained, step S106 is continuously executed, that is, the keyword related to the specified geographic location is determined according to the first behavior feature word and/or the second behavior feature word.
In one embodiment, when determining the keyword related to the designated geographic location, a plurality of first behavior feature words and a plurality of second behavior feature words may be trained by using a designated two-classification algorithm, so as to obtain a contribution value of each first behavior feature word to the designated geographic location; and then according to the contribution value of each first behavior feature word to the appointed geographic position, selecting at least one first behavior feature word from the plurality of first behavior feature words as a keyword related to the appointed geographic position.
The two-classification algorithm can be any one of two classification algorithms such as a logistic regression algorithm and an iterative decision tree algorithm. Specifically, the plurality of first behavior feature words and the plurality of second behavior feature words may be used as input for specifying a classification algorithm, so that the classifier is trained on the input data. Since the two classification algorithms such as the logistic regression algorithm and the iterative decision tree algorithm are the prior art, the detailed description is omitted.
When a plurality of first behavior feature words and a plurality of second behavior feature words are trained, the contribution value of each first behavior feature word to the designated geographic position can be determined according to the occurrence rate of each first behavior feature word in the plurality of first behavior feature words and the occurrence rate of each first behavior feature word in the plurality of second behavior feature words. The contribution value of the first behavior feature word is in direct proportion to the occurrence rate of the first behavior feature word in a plurality of first behavior feature words and in inverse proportion to the occurrence rate of the first behavior feature word in a plurality of second behavior feature words.
N first behavior feature words are obtained according to behavior information of a first class of users aiming at a specified geographic position, and M second behavior feature words are obtained according to behavior information of a second class of users aiming at a non-specified geographic position. If the occurrence rate of a certain first behavior feature word in the N first behavior feature words is high, and the occurrence rate of the first behavior feature word in the M second behavior feature words is low, it indicates that the contribution value of the first behavior feature word to the specified geographic location is high.
In determining the contribution value of each first behavior feature word to the designated geographic location, an occurrence rate threshold value X among the N first behavior feature words and an occurrence rate threshold value Y among the M second behavior feature words may be set in advance. If the occurrence rate of a certain first behavior feature word in the N first behavior feature words is higher than the occurrence rate threshold X, and the occurrence rate of a certain first behavior feature word in the M second behavior feature words is lower than the occurrence rate threshold Y, it may be determined that the contribution value of the first behavior feature word to the specified geographic location is high, and thus it may be determined that the first behavior feature word is a keyword related to the specified geographic location.
The contribution value of the first behavioral feature word to the specified geographic location can be characterized in a weighted manner. The weight range is 0 to 1. Namely, in the range of 0-1, the higher the weight value is, the higher the contribution value of the first behavior feature word to the designated geographic position is; conversely, the lower the weight value, the lower the contribution value of the first behavior feature word to the designated geographic location. The weight values are related to the occurrence rate of the first behavior feature words in the N first behavior feature words and the occurrence rate of the first behavior feature words in the M second behavior feature words, wherein the higher the occurrence rate of the first behavior feature words in the N first behavior feature words is, and the lower the occurrence rate of the first behavior feature words in the M second behavior feature words is, the higher the corresponding weight values are.
It should be noted that, if the occurrence rate of a certain first behavior feature word is high only in the N first behavior feature words, and the occurrence rate of a certain first behavior feature word in the M second behavior feature words is ambiguous, the contribution value of the certain first behavior feature word to the designated geographic location cannot be determined. The reason is that some behavior characteristic words belong to behavior characteristic words which are possibly shared by the designated geographic position and the non-designated geographic position, and whether the target user is located at the designated geographic position or not is possible to execute the behavior information related to the behavior characteristic words.
For example, a geographic location is designated as domestic and an unspecified geographic location is abroad. Assuming that the acquired first behavior feature word and the acquired second behavior feature word both include a word "starbucks", since the target user performs behavior information related to the "starbucks", such as searching for the "starbucks" for positioning or browsing an article related to the "starbucks", both the occurrence rate of the behavior feature word "starbucks" in the first behavior feature word and the occurrence rate of the behavior feature word "starbucks" in the second behavior feature word are high, and in this case, the behavior feature word "starbucks" does not belong to a keyword related to a specified geographic location.
Two specific embodiments are used below to illustrate the keyword extraction method based on geographic location provided in this specification.
Example one
Fig. 2 is a schematic flowchart of a keyword extraction method based on geographic location according to a specific embodiment of the present disclosure. In the first embodiment, the designated geographical location is foreign, and the unspecified geographical location is domestic. As shown in fig. 2, the method includes:
step S201, obtaining geographical location information of a plurality of target users in a recent period of time, and determining a user type of each target user according to the geographical location information.
The user types include a first type of users located abroad (i.e., users who travel across the border) and a second type of users located domestically.
Step S202, N first behavior feature words of a first class of users based on foreign countries are obtained, and M second behavior feature words of a second class of users based on domestic are obtained.
In this step, when the first behavior feature word is obtained, a time that the first type of user is located abroad may be first determined, then behavior information of the first type of user that is specific to the foreign country within a preset time period before the time (for example, within 10 days before the time) is obtained, such as search or browse keywords, articles, and the like related to the foreign country, and then the first behavior feature word is obtained according to the behavior information, for example, the keywords related to the foreign country searched by the first type of user are taken as the first behavior feature word, and the keywords in the articles related to the foreign country browsed by the first type of user are extracted as the first behavior feature word.
When the second behavior feature word is obtained, the time when the second type of user is located in the country may be determined first. The second type of user is not located abroad in the latest period of time, so that the time is the time corresponding to the geographic position information; then, acquiring the behavior information of the first class of users aiming at the country in a preset time period before the time (for example, within 10 days before the time), such as searching or browsing keywords, articles and the like related to the country, and further acquiring a second behavior feature word according to the behavior information, for example, using the keywords related to the country searched by the second class of users as the second behavior feature word, and extracting the keywords in the articles related to the country browsed by the second class of users as the second behavior feature word.
Step S203, training the N first behavior feature words and the M second behavior feature words respectively by using a specified two-classification algorithm.
Step S204, in the training process, judging whether the occurrence rate of each first behavior feature word in the N first behavior feature words is higher than a preset threshold value X and the occurrence rate of each first behavior feature word in the M second behavior feature words is lower than a preset threshold value Y; if yes, go to step S205; if not, go to step S206.
In step S205, the first behavior feature word is determined to be a keyword related to the cross-border tour.
In step S206, it is determined that the first behavior feature word is not a keyword related to the cross-border tour.
By adopting the technical scheme of the first embodiment of the specification, keywords related to cross-border travel can be automatically mined based on the first behavior characteristic words of the first class of users based on foreign countries and the second behavior characteristic words of the second class of users based on domestic countries, compared with the traditional method which can only extract keywords from documents, the method has the advantages that the variety of keyword extraction is improved, the extracted keywords can better accord with user behaviors, and the coverage rate is wider.
Example two
Fig. 3 is a schematic flowchart of a keyword extraction method based on geographic location according to a second embodiment of the present disclosure. In the second embodiment, the designated geographical location is singapore, and the unspecified geographical location is a country other than singapore. As shown in fig. 3, the method includes:
step S301, obtaining geographical position information of a plurality of target users in a latest period of time, and determining the user type of each target user according to the geographical position information.
The user types comprise first type users located in Singapore and second type users located in other countries.
Step S302, N first behavior feature words of the first type of users based on the Singapore are obtained, and M second behavior feature words of the second type of users based on other countries are obtained.
In this step, when the first behavior feature word is obtained, first, the time when the first type of user is located on the singapore may be determined, then, behavior information of the first type of user for the singapore in a preset time period before the time (for example, in 10 days before the time) is obtained, such as a keyword, an article and the like related to the singapore, and then, the first behavior feature word is obtained according to the behavior information, for example, the keyword related to the singapore searched by the first type of user is used as the first behavior feature word, and the keyword in the article related to the singapore browsed by the first type of user is extracted and used as the first behavior feature word.
When the second behavior feature word is obtained, the time when the second type of user is located in other countries may be determined first. The second type of user is not located in other countries in the latest period of time, so that the time is the time corresponding to the geographic position information; then, behavior information of the first type of user for other countries in a preset time period before the time (for example, in 10 days before the time) is obtained, such as searching or browsing keywords, articles and the like related to the other countries, and then a second behavior feature word is obtained according to the behavior information, for example, the keywords related to the other countries searched by the second type of user are used as the second behavior feature word, and the keywords in the articles related to the other countries browsed by the second type of user are extracted and used as the second behavior feature word.
Step S303, training the N first behavior feature words and the M second behavior feature words respectively by using a specified two-classification algorithm.
Step S304, in the training process, judging whether each first behavior feature word has the occurrence rate higher than a preset threshold value X in the N first behavior feature words and does not appear in the M second behavior feature words; if yes, go to step S305; if not, go to step S306.
In the second embodiment, considering that the behavior information of the user when the user goes to a specific country is more pertinent, when determining whether the first behavior feature word belongs to the keyword related to singapore, the determination criterion is different from the criterion of the cross-border travel keyword, that is, as long as the occurrence rate of a certain first behavior feature word in the N first behavior feature words is higher and the certain first behavior feature word does not appear in the M second behavior feature words, the certain first behavior feature word can be considered to belong to the keyword related to singapore.
Of course, other judgment bases can be set besides the judgment bases; for example, whether the occurrence rate of each first behavior feature word in the N first behavior feature words is higher than a preset threshold X and the occurrence rate of each first behavior feature word in the M second behavior feature words is lower than a preset threshold Y is determined; or only judging whether the occurrence rate of each first behavior feature word in the N first behavior feature words is higher than a preset threshold value X; and so on.
In step S305, the first behavior feature word is determined to be a keyword related to singapore.
Step S306, determining that the first behavior feature word is not a keyword related to Singapore.
By adopting the technical scheme of the second embodiment of the specification, keywords related to singapore can be automatically mined based on the first behavior characteristic words of the first class of users based on singapore and the second behavior characteristic words of the second class of users based on other countries, compared with the traditional method which can only extract keywords from documents, the method has the advantages that the variety of keyword extraction is improved, the extracted keywords are more targeted and can better accord with user behaviors, and the coverage rate is wider.
In summary, particular embodiments of the present subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may be advantageous.
Based on the same idea, the geographic location-based keyword extraction method provided in one or more embodiments of the present specification further provides a geographic location-based keyword extraction device.
Fig. 4 is a schematic block diagram of a keyword extraction apparatus based on a geographic location according to an embodiment of the present specification. As shown in fig. 4, the apparatus includes:
the first obtaining module 410 is used for obtaining the geographical position information of the target user and determining the user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
the second obtaining module 420 is configured to obtain a first behavior feature word of the first type of user based on the designated geographic location, and/or obtain a second behavior feature word of the second type of user based on the non-designated geographic location;
the determining module 430 determines the keyword related to the specified geographic location according to the first behavior feature word and/or the second behavior feature word.
Optionally, the second obtaining module 420 includes:
the first determining unit is used for determining the time when the first type of users are located at the designated geographic position;
the first acquisition unit is used for acquiring the behavior information of the first class of users aiming at the appointed geographical position in a preset time period before the time of the first class of users aiming at the appointed geographical position;
and the second determining unit is used for determining the first behavior characteristic word according to the behavior information.
Optionally, the behavior information includes at least one of search behavior information and browsing behavior information; the first behavior feature word comprises at least one of a search word and a browsing word.
Optionally, the determining module 430 includes:
the training unit is used for respectively training the plurality of first behavior feature words and the plurality of second behavior feature words by using a specified second classification algorithm so as to obtain contribution values of the first behavior feature words to the specified geographic position;
and the selection unit selects at least one first behavior characteristic word as a keyword related to the specified geographic position according to the contribution value.
Optionally, the training unit is further configured to:
determining the contribution value of each first behavior feature word to the designated geographic position according to the occurrence rate of each first behavior feature word in the plurality of first behavior feature words and the occurrence rate of each first behavior feature word in the plurality of second behavior feature words;
the contribution value is proportional to the occurrence rate of the first behavior feature word in the plurality of first behavior feature words and is inversely proportional to the occurrence rate of the first behavior feature word in the plurality of second behavior feature words.
Optionally, the two-classification algorithm comprises at least one of a logistic regression algorithm and an iterative decision tree algorithm.
Optionally, the designated geographic location is foreign and the unspecified geographic location is domestic.
Alternatively, the designated geographic location is a designated country and the unspecified geographic location is a country other than the designated country.
Optionally, the first obtaining module includes:
and a second acquisition unit acquiring the geographical location information of the target user according to the location based service LBS.
By adopting the device in one or more embodiments of the present specification, the geographic location information of the target user is obtained, the user type of the target user is determined according to the geographic location information, the first behavior feature word of the first type of user based on the specified geographic location is obtained, and/or the second behavior feature word of the second type of user based on the non-specified geographic location is obtained, and then the keyword related to the specified geographic location is determined according to the first behavior feature word and/or the second behavior feature word. Therefore, the technical scheme can automatically dig out the keywords related to the specified geographic position based on the geographic position information and the behavior characteristic words of various target users, and compared with the traditional method which only can extract the keywords from the document, the method has the advantages that the keyword extraction diversity is improved, the extracted keywords can better accord with the user behaviors, and the coverage rate is wider.
It should be understood by those skilled in the art that the geographic location-based keyword extraction apparatus in fig. 4 can be used to implement the geographic location-based keyword extraction method described above, and the detailed description thereof should be similar to that of the method described above, and is not repeated herein in order to avoid complexity.
Based on the same idea, one or more embodiments of the present specification further provide a keyword extraction device based on a geographic location, as shown in fig. 5. The keyword extraction apparatus based on geographic location may have a large difference due to different configurations or performances, and may include one or more processors 501 and a memory 502, and the memory 502 may store one or more stored applications or data. Memory 502 may be, among other things, transient or persistent storage. The application program stored in memory 502 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for a geographic location based keyword extraction facility. Still further, the processor 501 may be configured to communicate with the memory 502 to execute a series of computer-executable instructions in the memory 502 on a geographic location based keyword extraction device. The geographic location based keyword extraction apparatus may also include one or more power sources 503, one or more wired or wireless network interfaces 504, one or more input-output interfaces 505, one or more keyboards 506.
In particular, in this embodiment, the geographic location based keyword extraction apparatus includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the geographic location based keyword extraction apparatus, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for:
acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position;
and determining keywords related to the specified geographic position according to the first behavior characteristic word and/or the second behavior characteristic word.
Optionally, the computer executable instructions, when executed, may further cause the processor to:
determining a time at which the first class of users is located at the specified geographic location;
acquiring behavior information of the first class of users aiming at the specified geographic position within a preset time period before the time of locating at the specified geographic position;
and determining the first behavior feature word according to the behavior information.
Optionally, the behavior information includes at least one of search behavior information and browsing behavior information; the first behavior feature words comprise at least one of search words and browsing words.
Optionally, the computer executable instructions, when executed, may further cause the processor to:
training the plurality of first behavior feature words and the plurality of second behavior feature words by using a specified second classification algorithm to obtain contribution values of the first behavior feature words to the specified geographic position;
and selecting at least one first behavior feature word as a keyword related to the specified geographic position according to the contribution value.
Optionally, the computer executable instructions, when executed, may further cause the processor to:
determining contribution values of the first behavior feature words to the designated geographic position according to the occurrence rates of the first behavior feature words in the first behavior feature words and the second behavior feature words;
wherein the contribution value is proportional to the occurrence rate of the first behavior feature word in the plurality of first behavior feature words and inversely proportional to the occurrence rate of the first behavior feature word in the plurality of second behavior feature words.
Optionally, the specified two-classification algorithm includes at least one of a logistic regression algorithm and an iterative decision tree algorithm.
Optionally, the designated geographic location is foreign, and the unspecified geographic location is domestic.
Optionally, the designated geographic location is a designated country, and the unspecified geographic location is a country other than the designated country.
Optionally, the computer executable instructions, when executed, may further cause the processor to:
and acquiring the geographical position information of the target user according to the Location Based Service (LBS).
One or more embodiments of the present specification also propose a computer-readable storage medium storing one or more programs, the one or more programs including instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the above-mentioned geographic location-based keyword extraction device method, and in particular to perform:
acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position;
and determining keywords related to the specified geographic position according to the first behavior characteristic word and/or the second behavior characteristic word.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.
One skilled in the art will recognize that one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
One or more embodiments of the present specification are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only one or more embodiments of the present disclosure, and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of claims of one or more embodiments of the present specification.
Claims (16)
1. A keyword extraction method based on geographic positions comprises the following steps:
acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position;
training the occurrence rate of each first behavior feature word in the plurality of first behavior feature words and the occurrence rate of each second behavior feature word in the plurality of second behavior feature words by using a specified second classification algorithm, and determining the contribution value of each first behavior feature word to the specified geographic position;
wherein the contribution value is proportional to the occurrence rate of the first behavior feature word in the plurality of first behavior feature words and inversely proportional to the occurrence rate of the first behavior feature word in the plurality of second behavior feature words;
and selecting at least one first behavior feature word as a keyword related to the specified geographic position according to the contribution value.
2. The method of claim 1, wherein the obtaining of the first behavior feature word of the first class of users based on the designated geographic location comprises:
determining a time at which the first class of users is located at the specified geographic location;
acquiring behavior information of the first class of users aiming at the specified geographic position within a preset time period before the time of locating at the specified geographic position;
and determining the first behavior feature word according to the behavior information.
3. The method of claim 2, the behavior information comprising at least one of search behavior information, browse behavior information; the first behavior feature words comprise at least one of search words and browsing words.
4. The method of claim 1, the specified classification algorithm comprising at least one of a logistic regression algorithm, an iterative decision tree algorithm.
5. The method of claim 1, the designated geographic location being foreign and the unspecified geographic location being domestic.
6. The method of claim 1, the designated geographic location being a designated country and the non-designated geographic location being a country other than the designated country.
7. The method of claim 1, obtaining geographic location information of a target user, comprising:
and acquiring the geographical position information of the target user according to the Location Based Service (LBS).
8. A keyword extraction apparatus based on a geographic location, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module acquires the geographical position information of a target user and determines the user type of the target user according to the geographical position information, and the user type comprises a first type of user located at a specified geographical position and/or a second type of user located at a non-specified geographical position;
the second obtaining module is used for obtaining a first behavior feature word of the first type of users based on the appointed geographic position and/or obtaining a second behavior feature word of the second type of users based on the non-appointed geographic position;
the determining module is used for training the occurrence rate of each first behavior feature word in the plurality of first behavior feature words and the occurrence rate of each second behavior feature word in the plurality of second behavior feature words by using a specified second classification algorithm, and determining the contribution value of each first behavior feature word to the specified geographic position;
wherein the contribution value is proportional to the occurrence rate of the first behavior feature word in the plurality of first behavior feature words and inversely proportional to the occurrence rate of the first behavior feature word in the plurality of second behavior feature words;
and selecting at least one first behavior feature word as a keyword related to the specified geographic position according to the contribution value.
9. The apparatus of claim 8, wherein the first and second electrodes are disposed on opposite sides of the substrate,
the second acquisition module includes:
the first determining unit is used for determining the time when the first class of users are located at the specified geographic position;
the first acquisition unit is used for acquiring the behavior information of the first class of users aiming at the specified geographic position in a preset time period before the time of locating the first class of users at the specified geographic position;
and the second determining unit is used for determining the first behavior feature word according to the behavior information.
10. The apparatus of claim 9, the behavior information comprising at least one of search behavior information, browse behavior information; the first behavior feature words comprise at least one of search words and browsing words.
11. The apparatus of claim 8, the specified classification algorithm comprising at least one of a logistic regression algorithm, an iterative decision tree algorithm.
12. The apparatus of claim 8, the designated geographic location being foreign and the unspecified geographic location being domestic.
13. The apparatus of claim 8, the designated geographic location being a designated country and the non-designated geographic location being a country other than the designated country.
14. The apparatus of claim 8, the first acquisition module comprising:
and the second acquisition unit acquires the geographical position information of the target user according to the Location Based Service (LBS).
15. A keyword extraction apparatus based on a geographical location, comprising:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position;
training the occurrence rate of each first behavior feature word in the plurality of first behavior feature words and the occurrence rate of each second behavior feature word in the plurality of second behavior feature words by using a specified second classification algorithm, and determining the contribution value of each first behavior feature word to the specified geographic position;
wherein the contribution value is proportional to the occurrence rate of the first behavior feature word in the plurality of first behavior feature words and inversely proportional to the occurrence rate of the first behavior feature word in the plurality of second behavior feature words;
and selecting at least one first behavior feature word as a keyword related to the specified geographic position according to the contribution value.
16. A storage medium storing computer-executable instructions that, when executed, implement the following:
acquiring geographical position information of a target user, and determining a user type of the target user according to the geographical position information, wherein the user type comprises a first type of users located at a specified geographical position and/or a second type of users located at a non-specified geographical position;
acquiring a first behavior characteristic word of the first class of users based on the appointed geographic position, and/or acquiring a second behavior characteristic word of the second class of users based on the non-appointed geographic position;
training the occurrence rate of each first behavior feature word in the plurality of first behavior feature words and the occurrence rate of each second behavior feature word in the plurality of second behavior feature words by using a specified second classification algorithm, and determining the contribution value of each first behavior feature word to the specified geographic position;
wherein the contribution value is proportional to the occurrence rate of the first behavior feature word in the plurality of first behavior feature words and inversely proportional to the occurrence rate of the first behavior feature word in the plurality of second behavior feature words;
and selecting at least one first behavior feature word as a keyword related to the specified geographic position according to the contribution value.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711193955.3A CN107908761B (en) | 2017-11-24 | 2017-11-24 | Keyword extraction method and device based on geographic position |
| PCT/CN2018/104495 WO2019100811A1 (en) | 2017-11-24 | 2018-09-07 | Method and device for extracting keyword on the basis of geographic location |
| TW107133134A TWI711933B (en) | 2017-11-24 | 2018-09-20 | Method and device for extracting keywords based on geographic location |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711193955.3A CN107908761B (en) | 2017-11-24 | 2017-11-24 | Keyword extraction method and device based on geographic position |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107908761A CN107908761A (en) | 2018-04-13 |
| CN107908761B true CN107908761B (en) | 2020-10-02 |
Family
ID=61848256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711193955.3A Active CN107908761B (en) | 2017-11-24 | 2017-11-24 | Keyword extraction method and device based on geographic position |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN107908761B (en) |
| TW (1) | TWI711933B (en) |
| WO (1) | WO2019100811A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908761B (en) * | 2017-11-24 | 2020-10-02 | 阿里巴巴集团控股有限公司 | Keyword extraction method and device based on geographic position |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412888A (en) * | 2013-07-19 | 2013-11-27 | 百度在线网络技术（北京）有限公司 | Point of interest (POI) identification method and device |
| CN103744940A (en) * | 2013-12-31 | 2014-04-23 | 北京百度网讯科技有限公司 | Method and equipment for determining recommended keywords based on geographic position of information releaser |
| CN104834721A (en) * | 2015-05-12 | 2015-08-12 | 百度在线网络技术（北京）有限公司 | Search processing method and device based on positions |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101062927B1 (en) * | 2011-01-04 | 2011-09-07 | (주)올라웍스 | Method, system and computer-readable recording medium for recommending other users or objects by considering at least one user's preference |
| CN107291713B (en) * | 2016-03-30 | 2021-02-23 | 阿里巴巴（中国）有限公司 | Prompting method, terminal and server for searching keywords of interest points |
| CN107908761B (en) * | 2017-11-24 | 2020-10-02 | 阿里巴巴集团控股有限公司 | Keyword extraction method and device based on geographic position |
-
2017
- 2017-11-24 CN CN201711193955.3A patent/CN107908761B/en active Active
-
2018
- 2018-09-07 WO PCT/CN2018/104495 patent/WO2019100811A1/en active Application Filing
- 2018-09-20 TW TW107133134A patent/TWI711933B/en active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412888A (en) * | 2013-07-19 | 2013-11-27 | 百度在线网络技术（北京）有限公司 | Point of interest (POI) identification method and device |
| CN103744940A (en) * | 2013-12-31 | 2014-04-23 | 北京百度网讯科技有限公司 | Method and equipment for determining recommended keywords based on geographic position of information releaser |
| CN104834721A (en) * | 2015-05-12 | 2015-08-12 | 百度在线网络技术（北京）有限公司 | Search processing method and device based on positions |
Also Published As
| Publication number | Publication date |
|---|---|
| TWI711933B (en) | 2020-12-01 |
| TW201926086A (en) | 2019-07-01 |
| CN107908761A (en) | 2018-04-13 |
| WO2019100811A1 (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9189280B2 (en) | Tracking large numbers of moving objects in an event processing system | |
| CN107040886B (en) | Information determination method and device | |
| KR20100068468A (en) | Method, apparatus and computer program product for performing a visual search using grid-based feature organization | |
| CN109246230B (en) | Information pushing method and device | |
| CN101986672B (en) | Message processing method and device | |
| CN103198077A (en) | Classified lexicon management method and device | |
| JP2014528627A (en) | Data classification | |
| CN107463422A (en) | Code dispositions method and device, electronic equipment | |
| CN103473085B (en) | Method and equipment for loading target application on mobile terminal | |
| KR101508583B1 (en) | Semantic searching system and method for smart device | |
| CN107908761B (en) | Keyword extraction method and device based on geographic position | |
| CN106202366A (en) | A kind of image processing method, Apparatus and system | |
| CN105389398A (en) | Picture photographing and searching method and device | |
| CN110475204B (en) | Method, device and equipment for analyzing reverse address of geographic fence | |
| JP2014142783A (en) | Information processing apparatus and program | |
| CN107657474B (en) | Method for determining business circle boundary and server | |
| CN106503197B (en) | A method of extracting android system Baidu map base station data | |
| CN104915401A (en) | GIS (gheographic information system) information updating method and system | |
| CN108009877B (en) | Information mining method and device | |
| Liu et al. | GB-Tree: An efficient LBS location data indexing method | |
| CN110968580B (en) | Method and device for creating data storage structure | |
| CN106020780A (en) | Picture loading apparatus and method | |
| CN105912671A (en) | Method and device for cleaning up useless files | |
| US20160283990A1 (en) | Apparatus, System, Method, Computer Program, and Computer Program Product For Generating Activity Information For a Cell | |
| JP6360089B2 (en) | Portable information terminal, portable information terminal control method, and program |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1253983 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200921 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200921 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240222 Address after: Guohao Times City # 20-01, 128 Meizhi Road, Singapore Patentee after: Advanced Nova Technology (Singapore) Holdings Ltd. Country or region after: Singapore Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Patentee before: Innovative advanced technology Co.,Ltd. Country or region before: Cayman Islands |