CN109800361A - A kind of method for digging of interest point name, device, electronic equipment and storage medium - Google Patents
A kind of method for digging of interest point name, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109800361A CN109800361A CN201910110277.2A CN201910110277A CN109800361A CN 109800361 A CN109800361 A CN 109800361A CN 201910110277 A CN201910110277 A CN 201910110277A CN 109800361 A CN109800361 A CN 109800361A
- Authority
- CN
- China
- Prior art keywords
- search
- point name
- interest point
- poi
- sessions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of method for digging of interest point name, device, electronic equipment and storage mediums.The described method includes: obtaining the search sessions of each user in historical search log;The corresponding interest point name pair of each search sessions is determined according to the search sessions of each user;Wherein, the interest point name of the interest point name centering belongs to the same search sessions;Determine each interest point name to corresponding search characteristics in predetermined search characteristics library;According to the corresponding interest point name pair of each search sessions and each interest point name to corresponding search characteristics, the interest point name of each interest point name centering is excavated.The digging efficiency of interest point name not only can be improved, it can also be ensured that the accuracy rate of interest point name.
Description
Technical field
The present embodiments relate to Internet technical field more particularly to a kind of method for digging of interest point name, device,
Electronic equipment and storage medium.
Background technique
There is a large amount of anchor point in electronic map, for example, the restaurant marked on map, hotel, sight spot, charge station etc.,
These anchor points are that user may will do it inquiry or want the point of interest (Point of Interest, POI) reached.
Under normal circumstances, the same point of interest has multiple and different titles, for example, some point of interest can there are two
Title is respectively as follows: " Yonghe Palace Temple " and " lamasery ";At this point, " Yonghe Palace Temple " can be used as the original title of the point of interest;This is original
Title is the already existing title in existing electronic map;" lamasery " can be used as the candidate name of the point of interest;It should
Candidate name is the title being not present in existing electronic map.In existing electronic map database, it is likely that do not have
All titles comprising a point of interest.For example, be the point of interest of " Yonghe Palace Temple " for original title, the data in electronic map
" Yonghe Palace Temple " this original title is only existed in library, and " lamasery " this candidate name may be not present.So, if user makes
When with the point of interest that search name in electronic map is " lamasery ", since " lama being not present in the database in electronic map
This candidate name of mausoleum ", therefore user can not just find this point of interest.
In order to promote the search experience of user, needs the candidate name to each point of interest to excavate, then will excavate
Candidate name out adds in electronic map database.In the method for digging of existing interest point name, people is generallyd use
Work mode excavates interest point name, and not only digging efficiency is lower, but also accuracy rate not can guarantee yet.
Summary of the invention
In view of this, the embodiment of the present invention provides method for digging, device, electronic equipment and the storage of a kind of interest point name
The digging efficiency of interest point name not only can be improved in medium, it can also be ensured that the accuracy rate of interest point name.
In a first aspect, the embodiment of the invention provides a kind of method for digging of interest point name, which comprises
The search sessions of each user are obtained in historical search log;
The corresponding interest point name pair of each search sessions is determined according to the search sessions of each user;Wherein, described emerging
The interest point name of interest point title centering belongs to the same search sessions;
Determine each interest point name to corresponding search characteristics in predetermined search characteristics library;
According to the corresponding interest point name pair of each search sessions and each interest point name to corresponding search characteristics,
The interest point name of each interest point name centering is excavated.
In the above-described embodiments, the search sessions that each user is obtained in historical search log, comprising:
Whole POI search words and each POI search word that each user is obtained in the historical search log are corresponding
Search time;
It is right with it to be divided into whole POI search words of each user according to each POI search word corresponding search time
In the search sessions answered;Wherein, all POI search words in each search sessions come from the same user.
In the above-described embodiments, the search sessions according to each user determine the corresponding point of interest of each search sessions
Title pair, comprising:
The POI search word in each search sessions is determined in the search sessions of each user;
Every two POI search phrase in each search sessions is combined into an interest point name pair, as each search meeting
Talk about corresponding interest point name pair.
In the above-described embodiments, described to determine each interest point name to corresponding in predetermined search characteristics library
Search characteristics, comprising:
Determine each interest point name to corresponding search result feature in predetermined search result feature database;Its
In, the interest point name is to including: the first interest point name and the second interest point name;
Determine each interest point name to corresponding user behavior characteristics in predetermined user behavior characteristics library;Its
In, the user behavior characteristics include: the search temperature feature and each interest point name pair of first interest point name
Search co-occurrence feature.
In the above-described embodiments, described to be called the roll according to the corresponding interest point name pair of each search sessions and each interest
Claim to excavate the interest point name of each interest point name centering corresponding search characteristics, comprising:
The corresponding interest point name pair of each search sessions and each interest point name is defeated to corresponding search characteristics
Enter into discrimination model trained in advance;
Each interest point name is got to corresponding differentiation probability value by the discrimination model;
According to each interest point name to corresponding differentiation probability value and predetermined discrimination threshold, each interest is determined
Point title is to corresponding differentiation result.
Second aspect, the embodiment of the invention provides a kind of excavating gear of interest point name, described device includes: to obtain
Module, determining module and excavation module;Wherein,
The acquisition module, for obtaining the search sessions of each user in historical search log;
The determining module, for determining that the corresponding interest of each search sessions is called the roll according to the search sessions of each user
Title pair;Wherein, the interest point name of the interest point name centering belongs to the same search sessions;It is special in predetermined search
It levies and determines each interest point name to corresponding search characteristics in library;
The excavation module, for according to the corresponding interest point name pair of each search sessions and each interest point name
To corresponding search characteristics, the interest point name of each interest point name centering is excavated.
In the above-described embodiments, the acquisition module includes: acquisition submodule and division submodule;Wherein,
The acquisition submodule, for obtained in the historical search log each user whole POI search words and
Each POI search word corresponding search time;
The division submodule, for according to each POI search word corresponding search time by whole POI of each user
Search term is divided into corresponding search sessions;Wherein, all POI search words in each search sessions are from same
User.
In the above-described embodiments, the determining module, it is each specifically for being determined in the search sessions of each user
POI search word in search sessions;Every two POI search phrase in each search sessions is combined into an interest point name pair,
As the corresponding interest point name pair of each search sessions.
In the above-described embodiments, the determining module is specifically used for determining in predetermined search result feature database
Each interest point name is to corresponding search result feature;Wherein, the interest point name to include: the first interest point name and
Second interest point name;Determine each interest point name to corresponding user behavior in predetermined user behavior characteristics library
Feature;Wherein, the user behavior characteristics include: first interest point name search temperature feature and each point of interest
The search co-occurrence feature of title pair.
In the above-described embodiments, the excavation module is specifically used for the corresponding interest point name pair of each search sessions
And each interest point name is input to corresponding search characteristics in discrimination model trained in advance;Pass through the discrimination model
Each interest point name is got to corresponding differentiation probability value;According to each interest point name to corresponding differentiation probability value and
Predetermined discrimination threshold determines each interest point name to corresponding differentiation result.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, comprising:
One or more processors;
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the method for digging of interest point name described in any embodiment of that present invention.
Fourth aspect, the embodiment of the invention provides a kind of storage mediums, are stored thereon with computer program, the program quilt
The method for digging of interest point name described in any embodiment of that present invention is realized when processor executes.
The present invention applies example and proposes method for digging, device, electronic equipment and the storage medium of a kind of interest point name, first exists
The search sessions of each user are obtained in historical search log;Then each search meeting is determined according to the search sessions of each user
Talk about corresponding interest point name pair;Determine that each interest point name is special to corresponding search in predetermined search characteristics library
Sign;It is right further according to the corresponding interest point name pair of each search sessions and each interest point name to corresponding search characteristics
The interest point name of each interest point name centering is excavated.That is, in the inventive solutions, it can basis
The search sessions of each user determine the corresponding interest point name pair of each search sessions;Determining each interest point name pair
Corresponding search characteristics and then according to the corresponding interest point name pair of each search sessions and each interest point name to right
The search characteristics answered excavate the interest point name of each interest point name centering.And in existing interest point name
In method for digging, generallys use manual type and excavate interest point name, not only digging efficiency is lower, but also accuracy rate can not also protect
Card.Therefore, compared to the prior art, the embodiment of the present invention proposes the method for digging of interest point name, device, electronic device and
The digging efficiency of interest point name not only can be improved in storage medium, it can also be ensured that the accuracy rate of interest point name;Also,
The technical solution realization of the embodiment of the present invention is simple and convenient, it is universal to be convenient for, and the scope of application is wider.
Detailed description of the invention
Fig. 1 is the flow diagram of the method for digging for the interest point name that the embodiment of the present invention one provides;
Fig. 2 is the flow diagram of the method for digging of interest point name provided by Embodiment 2 of the present invention;
Fig. 3 is the flow diagram of the method for digging for the interest point name that the embodiment of the present invention three provides;
Fig. 4 is the first structure diagram of the excavating gear for the interest point name that the embodiment of the present invention four provides;
Fig. 5 is the second structural schematic diagram of the excavating gear for the interest point name that the embodiment of the present invention four provides;
Fig. 6 is the structural schematic diagram for the electronic equipment that the embodiment of the present invention five provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
In description, only some but not all contents related to the present invention are shown in the drawings.
Embodiment one
Fig. 1 is the flow diagram for the method for digging of interest point name that the embodiment of the present invention one provides, and this method can be with
By interest point name excavating gear perhaps electronic equipment come execute the device or electronic equipment can be by software and/or hard
The mode of part realizes that the device or electronic equipment can integrate in any smart machine with network communicating function.Such as
Shown in Fig. 1, the method for digging of interest point name be may comprise steps of:
S101, the search sessions that each user is obtained in historical search log.
In a specific embodiment of the present invention, electronic equipment can obtain the search of each user in historical search log
Session.Specifically, electronic equipment can first obtain whole POI search words of each user and each in historical search log
POI search word corresponding search time;Then according to each POI search word corresponding search time by the whole of each user
POI search word is divided into corresponding search sessions;Wherein, all POI search words in each search sessions are from same
One user.For example, it is assumed that the historical search log of some user includes N number of POI search word, be respectively as follows: POI search word 1,
POI search word 2 ..., POI search word N;Wherein, N is the natural number greater than 1;Wherein, the corresponding search time of POI search word 1
For search time 1, the corresponding search time of POI search word 2 be search time 2 ..., POI search word N corresponding search time be
Search time N.In a specific embodiment of the present invention, if the difference of two continuous POI search word corresponding search times
Less than or equal to preset threshold, indicate that the two continuous POI search words belong to the same search sessions;If two continuous
POI search word corresponding search time difference be greater than preset threshold, indicate the two connection POI search word be not belonging to together
One search sessions.
S102, the corresponding interest point name pair of each search sessions is determined according to the search sessions of each user;Wherein, emerging
The interest point name of interest point title centering belongs to the same search sessions.
In a specific embodiment of the present invention, electronic equipment can determine each search according to the search sessions of each user
The corresponding interest point name pair of session;Wherein, the interest point name of interest point name centering belongs to the same search sessions.Example
Such as, it is assumed that the historical search log of some user may include N number of POI search word, be respectively as follows: POI search word 1, POI search
Word 2 ..., POI search word N;Wherein, N is the natural number greater than 1;Wherein, when the corresponding search time of POI search word 1 is search
Between 1, the corresponding search time of POI search word 2 be search time 2 ..., POI search word N corresponding search time be search time
N.Assuming that search time 2 corresponding with the search term 2 corresponding search time 1 of POI search word 1 is less than preset threshold, POI is indicated
Search term 1 and POI search word 2 belong to the same search sessions, therefore, POI search word 1 and POI search word 2 can be determined as
The corresponding interest point name pair of the search sessions.Assume again that the corresponding search time 2 of POI search word 2 corresponding with search term 3 searches
The rope time 3 is less than preset threshold, indicates that POI search word 2 and POI search word 3 also belong to the same search sessions, therefore, also
POI search word 2 and POI search word 3 can be determined as to the corresponding interest point name pair of the search sessions.
S103, determine each interest point name to corresponding search characteristics in predetermined search characteristics library.
In a specific embodiment of the present invention, electronic equipment can determine each emerging in predetermined search characteristics library
Interest point title is to corresponding search characteristics.Specifically, electronic equipment can determine in predetermined search result feature database
Each interest point name is to corresponding search result feature;Wherein, interest point name is to including: the first interest point name and second
Interest point name;In a specific embodiment of the present invention, it is desirable that interest point name centering, second POI search word can correspond to
A POI in electronic map database;Determine that second POI search word can correspond to one in electronic map database
The method of POI is: user is searched when searching for second POI search word by available to second POI of POI search engine
The search result of rope word, and the POI in the search result of second POI search word is clicked, the POI of click is just used as second
The corresponding POI of POI search word.In addition, electronic equipment can also be determined in predetermined user behavior characteristics library it is each emerging
Interest point title is to corresponding user behavior characteristics;Wherein, user behavior characteristics include: that the search temperature of the first interest point name is special
The search co-occurrence feature of sign and each interest point name pair.
S104, according to the corresponding interest point name pair of each search sessions and each interest point name to corresponding search
Feature excavates the interest point name of each interest point name centering.
In a specific embodiment of the present invention, electronic equipment can be according to the corresponding interest point name pair of each search sessions
And each interest point name excavates corresponding search characteristics to the interest point name of each interest point name centering.
Specifically, electronic equipment can be by the corresponding interest point name pair of each search sessions and each interest point name to corresponding
Search characteristics are input in discrimination model trained in advance;Each interest point name is arrived to right by the way that the discrimination model is available
The differentiation probability value answered;According to each interest point name to corresponding differentiation probability value and predetermined discrimination threshold, determine
Each interest point name is to corresponding differentiation result.For example, for interest point name to (POI search word 1, POI search word 2),
POI search word 2 is the original title of the POI;The original title is the already existing title in existing electronic map;POI
Search term 1 is the doubtful candidate name of the POI;The doubtful candidate name be prepare in existing electronic map be added it is alternative
Title.In this step, electronic equipment can be by interest point name to (POI search word 1, POI search word 2) and the point of interest
Title is input to corresponding search characteristics in discrimination model trained in advance;Assuming that getting the interest by the discrimination model
Point title is 80% to corresponding differentiation probability value;Assuming that predetermined discrimination threshold is 50%;It can then determine that POI is searched
Rope word 1 is the candidate name of the corresponding POI of POI search word 2.
The method for digging for the interest point name that the embodiment of the present invention proposes first obtains each user in historical search log
Search sessions;Then the corresponding interest point name pair of each search sessions is determined according to the search sessions of each user;Pre-
First determine each interest point name to corresponding search characteristics in determining search characteristics library;It is corresponding further according to each search sessions
Interest point name pair and each interest point name to corresponding search characteristics, to the point of interest of each interest point name centering
Title is excavated.That is, in the inventive solutions, can be determined according to the search sessions of each user each
The corresponding interest point name pair of search sessions;Determine each interest point name to corresponding search characteristics and then according to
Each corresponding interest point name pair of search sessions and each interest point name are to corresponding search characteristics, to each point of interest
The interest point name of title centering is excavated.And in the method for digging of existing interest point name, generally use artificial side
Formula excavates interest point name, and not only digging efficiency is lower, but also accuracy rate not can guarantee yet.Therefore, compared to the prior art, originally
The method for digging for the interest point name that inventive embodiments propose, not only can be improved the digging efficiency of interest point name, can be with
Guarantee the accuracy rate of interest point name;Also, the technical solution realization of the embodiment of the present invention is simple and convenient, it is universal to be convenient for, and is applicable in
Range is wider.
Embodiment two
Fig. 2 is the flow diagram of the method for digging of interest point name provided by Embodiment 2 of the present invention.As shown in Fig. 2,
The method for digging of interest point name may comprise steps of:
S201, whole POI search words that each user is obtained in historical search log and each POI search word are corresponding
Search time.
In a specific embodiment of the present invention, electronic equipment can obtain the whole of each user in historical search log
POI search word and each POI search word corresponding search time.For example, it is assumed that the historical search log of some user can be with
Including N number of POI search word, be respectively as follows: POI search word 1, POI search word 2 ..., POI search word N;Wherein, N is oneself greater than 1
So number;Wherein, the corresponding search time of POI search word 1 is search time 1, the corresponding search time of POI search word 2 is search
Time 2 ..., POI search word N corresponding search time be search time N.
S202, according to each POI search word corresponding search time by whole POI search words of each user be divided into
In its corresponding search sessions;Wherein, all POI search words in each search sessions come from the same user.
In a specific embodiment of the present invention, electronic equipment can be incited somebody to action according to each POI search word corresponding search time
Whole POI search words of each user are divided into corresponding search sessions;Wherein, all in each search sessions
POI search word comes from the same user.Specifically, in a specific embodiment of the present invention, if two continuous POI search words
The difference of corresponding search time is less than or equal to preset threshold, and it is same to indicate that the two continuous POI search words belong to
Search sessions;If the difference of two continuous POI search word corresponding search times is greater than preset threshold, the two connection are indicated
The POI search word of system is not belonging to the same search sessions.For example, it is assumed that the corresponding search time 1 of POI search word 1 and search term 2
Corresponding search time 2 is less than preset threshold, indicates that POI search word 1 and POI search word 2 belong to the same search sessions, because
This, in this step, POI search word 1 and POI search word 2 can be divided into the search sessions by electronic equipment;It assumes again that
Search time 3 corresponding with the search term 3 corresponding search time 2 of POI search word 2 is less than preset threshold, indicates POI search word
2 and POI search word 3 also belong to the same search sessions, therefore, in this step, electronic equipment can also be by POI search word 2
It is divided into the search sessions with POI search word 3.
S203, POI search word in each search sessions is determined in the search sessions of each user.
In a specific embodiment of the present invention, electronic equipment can determine each search in the search sessions of each user
POI search word in rope session.For example, it is assumed that the search sessions of some user include three POI search words, it is respectively as follows: POI
Search term q1, POI search word q2 and POI search word q3;In this step, electronic equipment can be determined in the search sessions
POI search word q1, POI search word q2 and POI search word q3.
S204, every two POI search phrase in each search sessions is combined into an interest point name pair, is searched as each
The corresponding interest point name pair of rope session.
In a specific embodiment of the present invention, electronic equipment can be by every two POI search phrase in each search sessions
It is combined into an interest point name pair, as the corresponding interest point name pair of each search sessions.For example, it is assumed that some user
Search sessions include three POI search words, are respectively as follows: POI search word q1, POI search word q2 and POI search word q3;In this step
In rapid, POI search word q1 and POI search word q2 group can be combined into an interest point name pair by electronic equipment, as the search
The corresponding interest point name pair of session;POI search word q2 and POI search word q3 group can also be combined into an interest point name
It is right, as the corresponding interest point name pair of the search sessions;POI search word q1 and POI search word q3 group can also be combined into one
A interest point name pair, as the corresponding interest point name pair of the search sessions.
S205, determine each interest point name to corresponding search characteristics in predetermined search characteristics library.
In a specific embodiment of the present invention, electronic equipment can determine each emerging in predetermined search characteristics library
Interest point title is to corresponding search characteristics.Specifically, electronic equipment can determine in predetermined search result feature database
Each interest point name is to corresponding search result feature;Wherein, interest point name is to including: the first interest point name and second
Interest point name;In a specific embodiment of the present invention, it is desirable that interest point name centering, second POI search word can correspond to
A POI in electronic map database;Determine that second POI search word can correspond to one in electronic map database
The method of POI is: user is searched when searching for second POI search word by available to second POI of POI search engine
The search result of rope word, and the POI in the search result of second POI search word is clicked, the POI of click is just used as second
The corresponding POI of POI search word.In addition, electronic equipment can also be determined in predetermined user behavior characteristics library it is each emerging
Interest point title is to corresponding user behavior characteristics;Wherein, user behavior characteristics include: that the search temperature of the first interest point name is special
The search co-occurrence feature of sign and each interest point name pair.
S206, according to the corresponding interest point name pair of each search sessions and each interest point name to corresponding search
Feature excavates the interest point name of each interest point name centering.
In a specific embodiment of the present invention, electronic equipment can be according to the corresponding interest point name pair of each search sessions
And each interest point name excavates corresponding search characteristics to the interest point name of each interest point name centering.
Specifically, electronic equipment can be by the corresponding interest point name pair of each search sessions and each interest point name to corresponding
Search characteristics are input in discrimination model trained in advance;Each interest point name is arrived to right by the way that the discrimination model is available
The differentiation probability value answered;According to each interest point name to corresponding differentiation probability value and predetermined discrimination threshold, determine
Each interest point name is to corresponding differentiation result.For example, for interest point name to (POI search word 1, POI search word 2),
POI search word 2 is the original title of the POI;The original title is the already existing title in existing electronic map;POI
Search term 1 is the doubtful candidate name of the POI;The doubtful candidate name be prepare in existing electronic map be added it is alternative
Title.In this step, electronic equipment can be by interest point name to (POI search word 1, POI search word 2) and the point of interest
Title is input to corresponding search characteristics in discrimination model trained in advance;Assuming that getting the interest by the discrimination model
Point title is 80% to corresponding differentiation probability value;Assuming that predetermined discrimination threshold is 50%;It can then determine that POI is searched
Rope word 1 is the candidate name of the corresponding POI of POI search word 2.
The method for digging for the interest point name that the embodiment of the present invention proposes first obtains each user in historical search log
Search sessions;Then the corresponding interest point name pair of each search sessions is determined according to the search sessions of each user;Pre-
First determine each interest point name to corresponding search characteristics in determining search characteristics library;It is corresponding further according to each search sessions
Interest point name pair and each interest point name to corresponding search characteristics, to the point of interest of each interest point name centering
Title is excavated.That is, in the inventive solutions, can be determined according to the search sessions of each user each
The corresponding interest point name pair of search sessions;Determine each interest point name to corresponding search characteristics and then according to
Each corresponding interest point name pair of search sessions and each interest point name are to corresponding search characteristics, to each point of interest
The interest point name of title centering is excavated.And in the method for digging of existing interest point name, generally use artificial side
Formula excavates interest point name, and not only digging efficiency is lower, but also accuracy rate not can guarantee yet.Therefore, compared to the prior art, originally
The method for digging for the interest point name that inventive embodiments propose, not only can be improved the digging efficiency of interest point name, can be with
Guarantee the accuracy rate of interest point name;Also, the technical solution realization of the embodiment of the present invention is simple and convenient, it is universal to be convenient for, and is applicable in
Range is wider.
Embodiment three
Fig. 3 is the flow diagram of the method for digging for the interest point name that the embodiment of the present invention three provides.As shown in figure 3,
The method for digging of interest point name may comprise steps of:
S301, whole POI search words that each user is obtained in historical search log and each POI search word are corresponding
Search time.
In a specific embodiment of the present invention, electronic equipment can obtain the whole of each user in historical search log
POI search word and each POI search word corresponding search time.For example, it is assumed that the historical search log of some user can be with
Including N number of POI search word, be respectively as follows: POI search word 1, POI search word 2 ..., POI search word N;Wherein, N is oneself greater than 1
So number;Wherein, the corresponding search time of POI search word 1 is search time 1, the corresponding search time of POI search word 2 is search
Time 2 ..., POI search word N corresponding search time be search time N.
S302, according to each POI search word corresponding search time by whole POI search words of each user be divided into
In its corresponding search sessions;Wherein, all POI search words in each search sessions come from the same user.
In a specific embodiment of the present invention, electronic equipment can be incited somebody to action according to each POI search word corresponding search time
Whole POI search words of each user are divided into corresponding search sessions;Wherein, all in each search sessions
POI search word comes from the same user.Specifically, in a specific embodiment of the present invention, if two continuous POI search words
The difference of corresponding search time is less than or equal to preset threshold, and it is same to indicate that the two continuous POI search words belong to
Search sessions;If the difference of two continuous POI search word corresponding search times is greater than preset threshold, the two connection are indicated
The POI search word of system is not belonging to the same search sessions.For example, it is assumed that the corresponding search time 1 of POI search word 1 and search term 2
Corresponding search time 2 is less than preset threshold, indicates that POI search word 1 and POI search word 2 belong to the same search sessions, because
This, in this step, POI search word 1 and POI search word 2 can be divided into the search sessions by electronic equipment;It assumes again that
Search time 3 corresponding with the search term 3 corresponding search time 2 of POI search word 2 is less than preset threshold, indicates POI search word
2 and POI search word 3 also belong to the same search sessions, therefore, in this step, electronic equipment can also be by POI search word 2
It is divided into the search sessions with POI search word 3.
S303, POI search word in each search sessions is determined in the search sessions of each user.
In a specific embodiment of the present invention, electronic equipment can determine each search in the search sessions of each user
POI search word in rope session.For example, it is assumed that the search sessions of some user include three POI search words, it is respectively as follows: POI
Search term q1, POI search word q2 and POI search word q3;In this step, electronic equipment can be determined in the search sessions
POI search word q1, POI search word q2 and POI search word q3.
S304, every two POI search phrase in each search sessions is combined into an interest point name pair, is searched as each
The corresponding interest point name pair of rope session.
In a specific embodiment of the present invention, electronic equipment can be by every two POI search phrase in each search sessions
It is combined into an interest point name pair, as the corresponding interest point name pair of each search sessions.For example, it is assumed that some user
Search sessions include three POI search words, are respectively as follows: POI search word q1, POI search word q2 and POI search word q3;In this step
In rapid, POI search word q1 and POI search word q2 group can be combined into an interest point name pair by electronic equipment, as the search
The corresponding interest point name pair of session;POI search word q2 and POI search word q3 group can also be combined into an interest point name
It is right, as the corresponding interest point name pair of the search sessions;POI search word q1 and POI search word q3 group can also be combined into one
A interest point name pair, as the corresponding interest point name pair of the search sessions.
S305, determine that each interest point name is special to corresponding search result in predetermined search result feature database
Sign.
In a specific embodiment of the present invention, electronic equipment can determine respectively in predetermined search result feature database
A interest point name is to corresponding search result feature.The search result of universal search engine effect in correlation is fine, right
In interest point name to (qi, qj), if qiIt is qjCandidate name, then qiSearch result be likely to contain qjThe word of representative
Symbol string;Conversely, occurring q in search resultjThe probability of the character string of representative is very low.Therefore, in a specific embodiment of the present invention,
Electronic equipment can use qiAs the search term of universal search engine, search result is obtained in universal search engine, is then existed
Q is counted in search resultjThe number of appearance, as the interest point name to corresponding search result feature.Here, universal search
Engine is the search engine for searching for POI and non-POI;POI search engine is used exclusively for the search engine of search POI.
S306, determine that each interest point name is special to corresponding user behavior in predetermined user behavior characteristics library
Sign;Wherein, the search temperature feature and each interest point name that user behavior characteristics include: the first interest point name are to searching
Suo Gongxian feature.
In a specific embodiment of the present invention, electronic equipment can determine respectively in predetermined user behavior characteristics library
A interest point name is to corresponding user behavior characteristics;Wherein, user behavior characteristics include: the search heat of the first interest point name
Spend the search co-occurrence feature of feature and each interest point name pair.Specifically, for interest point name to (qi, qj), if qi
Search temperature feature it is very low, then indicate qiAnd qjIndicate that the probability of the same POI will be very low.In addition, qiAnd qjSame
Occurred in a search sessions, then qiAnd qjIndicate that the probability of the same POI will be very high.In specific embodiments of the present invention
In, the search co-occurrence feature of each interest point name pair may include: the co-occurrence number of each interest point name pair, each interest
The transition probability of point title pair and the mutual information of each interest point name pair.Specifically, for interest point name to (qi, qj), it should
The co-occurrence number of interest point name pair are as follows: in a certain historical period in the search sessions of all users, qiAnd qjOccur jointly
Number cnt (the q of search sessionsi, qj);The transition probability of the interest point name pair are as follows: all users in a certain historical period
In search sessions, the number cnt (q of the search sessions of the co-occurrence of the interest point name pairi, qj) and qjAppearance search sessions
Number cnt (qj) ratio;Formula is expressed asThe mutual information of the interest point name pair indicates qiAnd qj
Between interdependency;It is formulated asWherein, cnt (qi, qj)
In search sessions for users all in a certain historical period, qiAnd qjThe number of the search sessions occurred jointly;cnt(qi)
In search sessions for users all in a certain historical period, qiThe number of the search sessions of appearance;cnt(qi) it is a certain
In historical period in the search sessions of all users, qjThe number of the search sessions of appearance.
S307, according to the corresponding interest point name pair of each search sessions and each interest point name to corresponding search
Feature excavates the interest point name of each interest point name centering.
In a specific embodiment of the present invention, electronic equipment can be according to the corresponding interest point name pair of each search sessions
And each interest point name excavates corresponding search characteristics to the interest point name of each interest point name centering.
Specifically, electronic equipment can be by the corresponding interest point name pair of each search sessions and each interest point name to corresponding
Search characteristics are input in discrimination model trained in advance;Each interest point name is arrived to right by the way that the discrimination model is available
The differentiation probability value answered;According to each interest point name to corresponding differentiation probability value and predetermined discrimination threshold, determine
Each interest point name is to corresponding differentiation result.For example, for interest point name to (POI search word 1, POI search word 2),
POI search word 2 is the original title of the POI;The original title is the already existing title in existing electronic map;POI
Search term 1 is the doubtful candidate name of the POI;The doubtful candidate name be prepare in existing electronic map be added it is alternative
Title.In this step, electronic equipment can be by interest point name to (POI search word 1, POI search word 2) and the point of interest
Title is input to corresponding search characteristics in discrimination model trained in advance;Assuming that getting the interest by the discrimination model
Point title is 80% to corresponding differentiation probability value;Assuming that predetermined discrimination threshold is 50%;It can then determine that POI is searched
Rope word 1 is the candidate name of POI search word.
The method for digging for the interest point name that the embodiment of the present invention proposes first obtains each user in historical search log
Search sessions;Then the corresponding interest point name pair of each search sessions is determined according to the search sessions of each user;Pre-
First determine each interest point name to corresponding search characteristics in determining search characteristics library;It is corresponding further according to each search sessions
Interest point name pair and each interest point name to corresponding search characteristics, to the point of interest of each interest point name centering
Title is excavated.That is, in the inventive solutions, can be determined according to the search sessions of each user each
The corresponding interest point name pair of search sessions;Determine each interest point name to corresponding search characteristics and then according to
Each corresponding interest point name pair of search sessions and each interest point name are to corresponding search characteristics, to each point of interest
The interest point name of title centering is excavated.And in the method for digging of existing interest point name, generally use artificial side
Formula excavates interest point name, and not only digging efficiency is lower, but also accuracy rate not can guarantee yet.Therefore, compared to the prior art, originally
The method for digging for the interest point name that inventive embodiments propose, not only can be improved the digging efficiency of interest point name, can be with
Guarantee the accuracy rate of interest point name;Also, the technical solution realization of the embodiment of the present invention is simple and convenient, it is universal to be convenient for, and is applicable in
Range is wider.
Example IV
Fig. 4 is the first structure diagram of the excavating gear for the interest point name that the embodiment of the present invention four provides.Such as Fig. 4 institute
Show, the excavating gear of interest point name described in the embodiment of the present invention may include: to obtain module 401, determining module 402 and dig
Dig module 403;Wherein,
The acquisition module 401, for obtaining the search sessions of each user in historical search log;
The determining module 402, for determining the corresponding interest of each search sessions according to the search sessions of each user
Point title pair;Wherein, the interest point name of the interest point name centering belongs to the same search sessions;It is searched predetermined
Determine each interest point name to corresponding search characteristics in rope feature database;
The excavation module 403, for according to the corresponding interest point name pair of each search sessions and each point of interest
Title excavates corresponding search characteristics to the interest point name of each interest point name centering.
Fig. 5 is the second structural schematic diagram of the excavating gear for the interest point name that the embodiment of the present invention four provides.Such as Fig. 5 institute
Show, the acquisition module 401 includes: acquisition submodule 4011 and division submodule 4012;Wherein,
The acquisition submodule 4011, for obtaining whole POI searches of each user in the historical search log
Word and each POI search word corresponding search time;
The division submodule 4012, for according to each POI search word corresponding search time by the complete of each user
Portion's POI search word is divided into corresponding search sessions;Wherein, all POI search words in each search sessions come from
The same user.
Further, the determining module 402, specifically for determining each search in the search sessions of each user
POI search word in session;Every two POI search phrase in each search sessions is combined into an interest point name pair, as
The corresponding interest point name pair of each search sessions.
Further, it is each to be specifically used for the determination in predetermined search result feature database for the determining module 402
Interest point name is to corresponding search result feature;Wherein, the interest point name is to including: the first interest point name and second
Interest point name;Determine that each interest point name is special to corresponding user behavior in predetermined user behavior characteristics library
Sign;Wherein, the user behavior characteristics include: that the search temperature feature of first interest point name and each interest are called the roll
The search co-occurrence feature of title pair.
Further, the excavation module 403, be specifically used for the corresponding interest point name pair of each search sessions and
Each interest point name is input to corresponding search characteristics in discrimination model trained in advance;It is obtained by the discrimination model
To each interest point name to corresponding differentiation probability value;According to each interest point name to corresponding differentiation probability value and in advance
Determining discrimination threshold determines each interest point name to corresponding differentiation result.
Method provided by any embodiment of the invention can be performed in the excavating gear of above-mentioned interest point name, has the side of execution
The corresponding functional module of method and beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to the present invention is any
The method for digging for the interest point name that embodiment provides.
Embodiment five
Fig. 6 is the structural schematic diagram for the electronic equipment that the embodiment of the present invention five provides.Fig. 6, which is shown, to be suitable for being used to realizing this
The block diagram of the example electronic device of invention embodiment.The electronic equipment 12 that Fig. 6 is shown is only an example, should not be to this
The function and use scope of inventive embodiments bring any restrictions.
As shown in fig. 6, electronic equipment 12 is showed in the form of universal computing device.The component of electronic equipment 12 may include
But be not limited to: one or more processor or processing unit 16, system storage 28, connect different system components (including
System storage 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Electronic equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be electric
The usable medium that sub- equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Electronic equipment 12 may further include other removable/not removable
Dynamic, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for read and write can not
Mobile, non-volatile magnetic media (Fig. 6 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 6, Ke Yiti
For the disc driver for being read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to moving non-volatile light
The CD drive of disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver
It can be connected by one or more data media interfaces with bus 18.Memory 28 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform of the invention each
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiment described in the invention.
Electronic equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.)
Communication, can also be enabled a user to one or more equipment interact with the electronic equipment 12 communicate, and/or with make the electricity
Any equipment (such as network interface card, modem etc.) that sub- equipment 12 can be communicated with one or more of the other calculating equipment
Communication.This communication can be carried out by input/output (I/O) interface 22.Also, electronic equipment 12 can also be suitable by network
Orchestration 20 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet)
Communication.As shown, network adapter 20 is communicated by bus 18 with other modules of electronic equipment 12.Although should be understood that
It is not shown in Fig. 6, other hardware and/or software module can be used in conjunction with electronic equipment 12, including but not limited to: microcode,
Device driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage
System etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the method for digging of interest point name provided by the embodiment of the present invention.
Embodiment six
The embodiment of the present invention six provides a kind of computer storage medium.
The computer readable storage medium of the embodiment of the present invention, can be using one or more computer-readable media
Any combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer
Readable storage medium storing program for executing for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, dress
It sets or device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium wraps
It includes: there is the electrical connection of one or more conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable
Storage medium can be it is any include or storage program tangible medium, the program can be commanded execution system, device or
Device use or in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (12)
1. a kind of method for digging of interest point name, which is characterized in that the described method includes:
The search sessions of each user are obtained in historical search log;
The corresponding interest point name pair of each search sessions is determined according to the search sessions of each user;Wherein, the point of interest
The interest point name of title centering belongs to the same search sessions;
Determine each interest point name to corresponding search characteristics in predetermined search characteristics library;
According to the corresponding interest point name pair of each search sessions and each interest point name to corresponding search characteristics, to each
The interest point name of a interest point name centering is excavated.
2. the method according to claim 1, wherein described obtain searching for each user in historical search log
Rope session, comprising:
Whole point of interest POI search words and each POI search word that each user is obtained in the historical search log are corresponding
Search time;
Whole POI search words of each user are divided into according to each POI search word corresponding search time corresponding
In search sessions;Wherein, all POI search words in each search sessions come from the same user.
3. the method according to claim 1, wherein the search sessions according to each user determine each search
The corresponding interest point name pair of rope session, comprising:
The POI search word in each search sessions is determined in the search sessions of each user;
Every two POI search phrase in each search sessions is combined into an interest point name pair, as each search sessions pair
The interest point name pair answered.
4. the method according to claim 1, wherein the determination in predetermined search characteristics library is each
Interest point name is to corresponding search characteristics, comprising:
Determine each interest point name to corresponding search result feature in predetermined search result feature database;Wherein,
The interest point name is to including: the first interest point name and the second interest point name;
Determine each interest point name to corresponding user behavior characteristics in predetermined user behavior characteristics library;Wherein,
The search temperature feature and each interest point name that the user behavior characteristics include: first interest point name are to searching
Suo Gongxian feature.
5. the method according to claim 1, wherein described according to the corresponding interest point name of each search sessions
Pair and each interest point name to corresponding search characteristics, the interest point name of each interest point name centering is dug
Pick, comprising:
The corresponding interest point name pair of each search sessions and each interest point name are input to corresponding search characteristics
In advance in trained discrimination model;
Each interest point name is got to corresponding differentiation probability value by the discrimination model;
According to each interest point name to corresponding differentiation probability value and predetermined discrimination threshold, determine that each interest is called the roll
Claim to corresponding differentiation result.
6. a kind of excavating gear of interest point name, which is characterized in that described device includes: to obtain module, determining module and digging
Dig module;Wherein,
The acquisition module, for obtaining the search sessions of each user in historical search log;
The determining module, for determining the corresponding interest point name of each search sessions according to the search sessions of each user
It is right;Wherein, the interest point name of the interest point name centering belongs to the same search sessions;In predetermined search characteristics
Determine each interest point name to corresponding search characteristics in library;
The excavation module is used for according to the corresponding interest point name pair of each search sessions and each interest point name to right
The search characteristics answered excavate the interest point name of each interest point name centering.
7. device according to claim 6, which is characterized in that the acquisition module includes: acquisition submodule and divides sub
Module;Wherein,
The acquisition submodule, for obtaining whole POI search words of each user and each in the historical search log
POI search word corresponding search time;
The division submodule, for according to each POI search word corresponding search time by whole POI searches of each user
Word is divided into corresponding search sessions;Wherein, all POI search words in each search sessions come from the same use
Family.
8. device according to claim 6, it is characterised in that:
The determining module, specifically for determining the POI search in each search sessions in the search sessions of each user
Word;Every two POI search phrase in each search sessions is combined into an interest point name pair, it is corresponding as each search sessions
Interest point name pair.
9. device according to claim 6, it is characterised in that:
The determining module is specifically used for determining each interest point name to correspondence in predetermined search result feature database
Search result feature;Wherein, the interest point name is to including: the first interest point name and the second interest point name;Pre-
First determine each interest point name to corresponding user behavior characteristics in determining user behavior characteristics library;Wherein, the user
Behavioural characteristic includes: the search temperature feature of first interest point name and the search co-occurrence spy of each interest point name pair
Sign.
10. device according to claim 6, it is characterised in that:
The excavation module is specifically used for the corresponding interest point name pair of each search sessions and each interest point name pair
Corresponding search characteristics are input in discrimination model trained in advance;Each interest point name is got by the discrimination model
To corresponding differentiation probability value;According to each interest point name to corresponding differentiation probability value and predetermined discrimination threshold,
Determine each interest point name to corresponding differentiation result.
11. a kind of electronic equipment characterized by comprising
One or more processors;
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method for digging of the interest point name as described in any one of claims 1 to 5.
12. a kind of storage medium, is stored thereon with computer program, which is characterized in that the realization when program is executed by processor
The method for digging of interest point name as described in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910110277.2A CN109800361A (en) | 2019-02-11 | 2019-02-11 | A kind of method for digging of interest point name, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910110277.2A CN109800361A (en) | 2019-02-11 | 2019-02-11 | A kind of method for digging of interest point name, device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109800361A true CN109800361A (en) | 2019-05-24 |
Family
ID=66562011
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910110277.2A Pending CN109800361A (en) | 2019-02-11 | 2019-02-11 | A kind of method for digging of interest point name, device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109800361A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110457706A (en) * | 2019-08-15 | 2019-11-15 | 腾讯科技(深圳)有限公司 | Interest point name preference pattern training method, application method, device and storage medium |
CN111737537A (en) * | 2020-07-21 | 2020-10-02 | 杭州欧若数网科技有限公司 | POI recommendation method, device and medium based on graph database |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455552A (en) * | 2013-08-01 | 2013-12-18 | 百度在线网络技术(北京)有限公司 | Point-of-interest mining method and device based on terms of interest |
CN105224660A (en) * | 2015-09-30 | 2016-01-06 | 北京奇虎科技有限公司 | A kind of disposal route of map point of interest POI data and device |
US20170068683A1 (en) * | 2015-09-04 | 2017-03-09 | Google Inc. | Context based instant search suggestions |
CN107291914A (en) * | 2017-06-27 | 2017-10-24 | 达而观信息科技(上海)有限公司 | A kind of method and system for generating search engine inquiry expansion word |
CN107491537A (en) * | 2017-08-23 | 2017-12-19 | 北京百度网讯科技有限公司 | POI data excavation, information retrieval method, device, equipment and medium |
CN108345702A (en) * | 2018-04-10 | 2018-07-31 | 北京百度网讯科技有限公司 | Entity recommends method and apparatus |
-
2019
- 2019-02-11 CN CN201910110277.2A patent/CN109800361A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455552A (en) * | 2013-08-01 | 2013-12-18 | 百度在线网络技术(北京)有限公司 | Point-of-interest mining method and device based on terms of interest |
US20170068683A1 (en) * | 2015-09-04 | 2017-03-09 | Google Inc. | Context based instant search suggestions |
CN105224660A (en) * | 2015-09-30 | 2016-01-06 | 北京奇虎科技有限公司 | A kind of disposal route of map point of interest POI data and device |
CN107291914A (en) * | 2017-06-27 | 2017-10-24 | 达而观信息科技(上海)有限公司 | A kind of method and system for generating search engine inquiry expansion word |
CN107491537A (en) * | 2017-08-23 | 2017-12-19 | 北京百度网讯科技有限公司 | POI data excavation, information retrieval method, device, equipment and medium |
CN108345702A (en) * | 2018-04-10 | 2018-07-31 | 北京百度网讯科技有限公司 | Entity recommends method and apparatus |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110457706A (en) * | 2019-08-15 | 2019-11-15 | 腾讯科技(深圳)有限公司 | Interest point name preference pattern training method, application method, device and storage medium |
CN110457706B (en) * | 2019-08-15 | 2023-08-22 | 腾讯科技(深圳)有限公司 | Point-of-interest name selection model training method, using method, device and storage medium |
CN111737537A (en) * | 2020-07-21 | 2020-10-02 | 杭州欧若数网科技有限公司 | POI recommendation method, device and medium based on graph database |
CN111737537B (en) * | 2020-07-21 | 2020-11-27 | 杭州欧若数网科技有限公司 | POI recommendation method, device and medium based on graph database |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8515959B2 (en) | Method and apparatus for maintaining and navigating a non-hierarchical personal spatial file system | |
CN108897867A (en) | For the data processing method of knowledge question, device, server and medium | |
CN102893275A (en) | Automated social networking graph mining and visualization | |
CN105095281B (en) | A kind of web catalogue method for optimization analysis based on Web log mining | |
CN110275692A (en) | A kind of recommended method of phonetic order, device, equipment and computer storage medium | |
CN109325108A (en) | Inquiry processing method, device, server and storage medium | |
CN109800361A (en) | A kind of method for digging of interest point name, device, electronic equipment and storage medium | |
CN108932323A (en) | Determination method, apparatus, server and the storage medium of entity answer | |
CN107133263A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
CN109214417A (en) | The method for digging and device, computer equipment and readable medium that user is intended to | |
GB2569858A (en) | Constructing content based on multi-sentence compression of source content | |
CN109376173A (en) | A kind of data query method, apparatus, electronic equipment and storage medium | |
CN109492127A (en) | Data processing method, device, medium and calculating equipment | |
CN109246483A (en) | A kind of direct broadcasting room recommended method, device, equipment and storage medium | |
CN107832440A (en) | A kind of data digging method, device, server and computer-readable recording medium | |
CN108536702A (en) | A kind of related entities determine method, apparatus and computing device | |
CN110388933A (en) | Interest point search method, device, server and storage medium | |
CN110083677A (en) | Searching method, device, equipment and the storage medium of contact person | |
CN110515758A (en) | A kind of Fault Locating Method, device, computer equipment and storage medium | |
CN111984745B (en) | Database field dynamic expansion method, device, equipment and storage medium | |
CN110377748A (en) | Entity focus method for digging, device, computer equipment and storage medium | |
KR20040054901A (en) | Moving picture search system and method thereof | |
CN110175128A (en) | A kind of similar codes case acquisition methods, device, equipment and storage medium | |
US20210271637A1 (en) | Creating descriptors for business analytics applications | |
CN110287338A (en) | Industrial hot spot determines method, apparatus, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190524 |
|
RJ01 | Rejection of invention patent application after publication |