CN106407346A - Retrieval processing method and apparatus based on artificial intelligence - Google Patents
Retrieval processing method and apparatus based on artificial intelligence Download PDFInfo
- Publication number
- CN106407346A CN106407346A CN201610804040.0A CN201610804040A CN106407346A CN 106407346 A CN106407346 A CN 106407346A CN 201610804040 A CN201610804040 A CN 201610804040A CN 106407346 A CN106407346 A CN 106407346A
- Authority
- CN
- China
- Prior art keywords
- user
- retrieval
- information
- mated
- user tag
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- G06F16/9535—Search customisation based on user profiles and personalisation
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a retrieval processing method and apparatus based on artificial intelligence. The method comprises the following steps: setting feature information corresponding to a user label; matching the feature information with big data information of a user, and establishing a corresponding user label for the successfully matched user; and storing a corresponding relation between a user identifier and the user label so as to provide retrieval services for the user according to the corresponding relation. According to the method, the related user label is established for the corresponding user according to the big data information of the user so as to provide personalized retrieval services for the user according to the user label, and thus the retrieval performance is improved.
Description
Technical field
The present invention relates to technical field of information processing, more particularly, to a kind of search processing method based on artificial intelligence and dress
Put.
Background technology
Artificial intelligence (Artificial Intelligence), english abbreviation is AI.It is research, be developed for simulation,
Extend and extend the theory of intelligence of people, new science of technology of method, technology and application system.Artificial intelligence is to calculate
One branch of machine science, it attempts to understand essence of intelligence, and produce a kind of new can be in the way of human intelligence be similar
The intelligent machine made a response, the research in this field includes robot, speech recognition, image recognition, natural language processing and specially
Family's system etc..Wherein, the most important aspect of artificial intelligence is exactly speech recognition technology.
At present, search engine is widely used as the instrument meeting user search request, and search engine is defeated according to user
The searching request entering scans for, and Search Results are supplied to user.
However, different users Search Results interested are different, such as in the Search Results of certain star, vermicelli
User and domestic consumer Search Results interested are different, and vermicelli is interested in the stroke Search Results comprising star,
And domestic consumer is interested in the Search Results of the essential information comprising star, and search engine is only according to user input
Search word for user provide Search Results it is impossible to meet the individual demand of user, the search performance of search engine is not high.
Content of the invention
The purpose of the present invention is intended at least solve one of technical problem in correlation technique to a certain extent.
For this reason, the first of the present invention purpose is to propose a kind of search processing method based on artificial intelligence, the method
According to the big data information of user, set up associated user's label for corresponding user, in order to carry for user according to user tag
For personalized retrieval service, improve retrieval performance.
Second object of the present invention is to propose a kind of retrieval process device based on artificial intelligence.
To achieve these goals, the search processing method based on artificial intelligence of first aspect present invention embodiment, bag
Include:Characteristic information corresponding with user tag is set;Described characteristic information is mated with the big data information of user, for
Join successful user and set up corresponding user tag;Storage ID and the corresponding relation of user tag, so that according to described
Corresponding relation provides a user with retrieval service.
The search processing method based on artificial intelligence of the embodiment of the present invention, setting feature corresponding with user tag letter
Breath, characteristic information is mated with the big data information of user, sets up corresponding user tag for the user that the match is successful, deposit
Storage ID and the corresponding relation of user tag, to provide a user with retrieval service according to corresponding relation.Thus, according to
The big data information at family, sets up associated user's label for corresponding user, in order to provide the user individual character according to user tag
Change retrieval service, improve retrieval performance.
In addition, the search processing method based on artificial intelligence of the embodiment of the present invention, also there is the technology added as follows special
Levy:
In one embodiment of the invention, described characteristic information includes:Retrieval character information,
Described described characteristic information is mated with the big data information of user, including:
User's history retrieval behavioural information is filtered out from the big data information of described user;
Described retrieval character information is mated with described user's history retrieval behavioural information.
In one embodiment of the invention, described retrieval character information includes one or more of following information:
The search rate of the key word mating with described user tag;
The click frequency of the Search Results type mated with described user tag;
The click frequency of the search content mated with described user tag;
The concern time with described user tag matching content.
In one embodiment of the invention, described characteristic information also includes:User's characteristic information,
After described retrieval character information is mated with described user's history retrieval information, also include:
User's portrait information is filtered out from the big data information of described user;
Described user's characteristic information is mated with described user portrait information.
In one embodiment of the invention, after the corresponding relation of described storage ID and user tag, also
Including:
Receive and comprise ID and the retrieval request of query statement;
Inquire about described corresponding relation and obtain user tag corresponding with described ID;
Detect whether there is the user tag mated with described query statement;
If it is present inspection corresponding with described inquiry request is fed back according to the user tag mated with described query statement
Hitch fruit.
In one embodiment of the invention, the described user tag detecting whether that presence is mated with described query statement,
Including:
Query statement corresponding retrieval type according to acquisition of information is retrieved in default normalization;
Detect whether to exist with the attaching relation of user tag according to default retrieval type and mate with described query statement
User tag.
To achieve these goals, the retrieval process device based on artificial intelligence of second aspect present invention embodiment, bag
Include:Setup module, for arranging characteristic information corresponding with user tag;Matching module, for by described characteristic information and use
The big data information at family is mated;Set up module, for setting up corresponding user tag for the user that the match is successful;Storage mould
Block, for storing the corresponding relation of ID and user tag, to provide a user with retrieval clothes according to described corresponding relation
Business.
The retrieval process device based on artificial intelligence of the embodiment of the present invention, setting feature corresponding with user tag letter
Breath, characteristic information is mated with the big data information of user, sets up corresponding user tag for the user that the match is successful, deposit
Storage ID and the corresponding relation of user tag, to provide a user with retrieval service according to corresponding relation.Thus, according to
The big data information at family, sets up associated user's label for corresponding user, in order to provide the user individual character according to user tag
Change retrieval service, improve retrieval performance.
In addition, the retrieval process device based on artificial intelligence of the embodiment of the present invention, also there is the technology added as follows special
Levy:
In one embodiment of the invention, described characteristic information includes:Retrieval character information, described matching module bag
Include:
First screening unit, for filtering out user's history retrieval behavioural information from the big data information of described user;
First matching unit, for carrying out described retrieval character information and described user's history retrieval behavioural information
Join.
In one embodiment of the invention, described retrieval character information includes one or more of following information:
The search rate of the key word mating with described user tag;
The click frequency of the Search Results type mated with described user tag;
The click frequency of the search content mated with described user tag;
The concern time with described user tag matching content.
In one embodiment of the invention, described characteristic information also includes:User's characteristic information, described matching module bag
Include:
Second screening unit, for filtering out user's portrait information from the big data information of described user;
Second matching unit, for being mated described user's characteristic information with described user portrait information.
In one embodiment of the invention, also include:
Receiver module, comprises ID and the retrieval request of query statement for receiving;
Acquisition module, obtains user tag corresponding with described ID for inquiring about described corresponding relation;
, for detecting whether there is the user tag mated with described query statement in detection module;
Feedback module, for exist mate with described query statement user tag when, according to described query statement
The user tag of coupling feeds back retrieval result corresponding with described inquiry request.
In one embodiment of the invention, described detection module includes:
Acquiring unit, for query statement corresponding retrieval type according to default normalization retrieval acquisition of information;
Detector unit, for according to the attaching relation of default retrieval type and user tag detect whether presence with described
The user tag of query statement coupling.
The aspect that the present invention adds and advantage will be set forth in part in the description, and partly will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description
The above-mentioned and/or additional aspect of the present invention and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and easy to understand, wherein:
Fig. 1 is the flow chart of the search processing method based on artificial intelligence according to an embodiment of the invention;
Fig. 2 is the interface schematic diagram that existing search engine provides retrieval result;
Fig. 3 is the flow chart of the search processing method based on artificial intelligence in accordance with another embodiment of the present invention;
Fig. 4 (a)-Fig. 4 (b) is retrieval result interface according to an embodiment of the invention schematic diagram;
Fig. 5 is the structural representation of the retrieval process device based on artificial intelligence according to an embodiment of the invention;
Fig. 6 is the structural representation of the retrieval process device based on artificial intelligence in accordance with another embodiment of the present invention;
Fig. 7 is the structural representation according to another embodiment of the present invention based on the retrieval process device of artificial intelligence;
Fig. 8 is the structural representation according to further embodiment of the present invention based on the retrieval process device of artificial intelligence;
And
Fig. 9 is the structural representation according to a still further embodiment of the present invention based on the retrieval process device of artificial intelligence.
Specific embodiment
Embodiments of the invention are described below in detail, the example of described embodiment is shown in the drawings, wherein from start to finish
The element that same or similar label represents same or similar element or has same or like function.Below with reference to attached
The embodiment of figure description is exemplary it is intended to be used for explaining the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings search processing method based on artificial intelligence and the device of the embodiment of the present invention are described.
Fig. 1 is the flow chart of the search processing method based on artificial intelligence according to an embodiment of the invention.As Fig. 1 institute
Show, the method includes:
S110, arranges characteristic information corresponding with user tag.
S120, characteristic information is mated with the big data information of user, sets up corresponding for the user that the match is successful
User tag.
Generally, search engine, when providing the user retrieval service, enters line retrieval according to the query statement of user input, will
The retrieval result meeting user's General Main demand searching is supplied to user.
Such as, if as shown in Fig. 2 the query statement of user input is the name of certain star, search engine can be by
According to the General Main demand of general user, the essential informations such as the age of this performer, date of birth are supplied to user.
However, under some application scenarios, user has individual demand to retrieval result, such as vermicelli user,
, when certain star's information of input enters line retrieval, different from domestic consumer, it wishes that the retrieval result obtaining is star's stroke for it
And the relevant information such as star's focus.And the mode of above-mentioned offer retrieval service, provide the user only according to General Main demand
Retrieval result is it is impossible to meet the individual demand of user.
In order to solve the above problems, the present invention proposes a kind of search processing method based on artificial intelligence, can be in difference
Application scenarios under, provide the user the retrieval result meeting its individual demand.
Specifically, in actual implementation process, arrange characteristic information corresponding with user tag, wherein, user tag and
The individual demand of user is related, such as, can be vermicelli label, music severe fan's label, caricature fan's label, trip
Trip fan's label etc..
And then, characteristic information is mated with the big data information of user, if the big data information of user and feature
Information matches success, then set up user tag corresponding with characteristic information for the user that the match is successful, wherein, should be directed to a use
The user tag that family is set up can be one or multiple.
Wherein, the big data information of user can include user implement retrieval behavior when, the term of input, click on
The exercise question of Search Results, site preferences, template preference, browse duration, age, sex etc..
It should be appreciated that according to the difference of concrete application scene, above-mentioned characteristic information corresponding with user tag is permissible
Comprise different contents:
The first example, under some application scenarios, the retrieval information characteristics of embodiment in the history retrieval behavior of user, that is,
The user tag of user's subordinate can be reflected, thus, the information of this feature can include retrieval character information.
Wherein, retrieval character information may include search rate and the user tag of the key word mating with user tag
The click frequency of search content that the click frequency of Search Results type joined is mated with user tag and mating with user tag
One or more of the concern time of content.
For example, when user tag is for vermicelli label, its corresponding retrieval character information may include with star for closing
The search rate of keyword, to the search-type comprising star's information, (such as mhkc, microblogging etc. comprise the social activity of a large amount of star's information
Software) click frequency, the click frequency to the search content comprising star's information, to the various contents comprising star's information
Browse concern time such as duration etc..
Thus, in this example, by characteristic information and the big data information of user carry out mating including:Big number from user
It is believed that filtering out user's history retrieval behavioural information in breath, and retrieval character information is mated with the historical behavior of user,
If the match is successful, set up corresponding user tag for the user that the match is successful.
For example, from the big data information of user, filter out and retrieve behavioural information with user's history, such as filter out
Search rate with star as key word, to the search-type comprising star's information, (such as mhkc, microblogging etc. comprise a large amount of stars
The social software of information) click frequency, the click frequency to the search content comprising star's information, to comprising star's information
Various contents browse concern time such as duration etc..
And then, corresponding for vermicelli label retrieval character is mated with the retrieval behavior of above-mentioned user's history, if with bright
Star is that the search rate of key word is higher, and to the search-type comprising star's information, (such as mhkc, microblogging etc. comprise a large amount of stars
The social software of information) click frequency higher, higher, bright to comprising to the click frequency of the search content comprising star's information
The various contents of star information to browse the concern time such as duration longer etc., then set up vermicelli label for this user.
Wherein, in order to improve the accuracy setting up user tag, improve the efficiency setting up user tag, by retrieval character
When information is mated with the big data information of user, can be carried out based on history retrieval behavior and the retrieval character in Dan Tian
Join, and then obtain the history retrieval behavioural information of the user that the match is successful, based on the history retrieval behavioural informations of continuously many days with
Retrieval character information is mated, thus setting up corresponding user tag for the user that the match is successful.
Second example, under some application scenarios, the retrieval character information of user is it is impossible to accurate reflect user
The user tag of subordinate, even if the retrieval character information of user is similar to, due to user's characteristic information such as its age, sex, occupations
Difference, may corresponding user tag difference.
In this example, after retrieval character information is mated with user's history retrieval information, also can be from user's
Filter out user's portrait information in big data information, and user's characteristic information and user information of drawing a portrait is mated, think
Join successful user and set up corresponding user tag.
Wherein, user's portrait information may include the essential informations such as user's sex, age of user, user's occupation.
For example, after retrieval character information being mated with user's history retrieval behavioural information, user A and B goes through
History retrieve behavior, retrieval character information matches corresponding with cosplay fan's label, however the age of user A be 40 years old, duty
Industry is cloth provider, and the age of user B is 16 years old, and occupation is student, after mating with user's characteristic information, is that user A builds
Found the user tag of Japanese cloth fan, be that user B sets up cosplay fan's label.
S130, the corresponding relation of storage ID and user tag, to provide a user with retrieval according to corresponding relation
Service.
It is appreciated that prestoring the corresponding relation of ID and user tag, thus when user enters line retrieval, obtaining
Take user tag corresponding with this searching request, in order to corresponding retrieval service is provided a user with according to this Checking label, full
The individual demand of sufficient user.
Wherein it is desired to explanation, according to the difference of concrete application scene, above-mentioned ID is different, can be user
Account, the geographical position IP of user, ID of user etc., here is not limited.
For example, prestoring the corresponding user tag of ID C is travel enthusiasts label, thus in user C
When scanning for, the search word of input is " Guilin ", and acquisition user tag corresponding with this searching request is travel enthusiasts mark
Signing, thus providing a user with the coordinate indexing service in tourism in Guilin, meeting the individual demand of user.
In sum, the search processing method based on artificial intelligence of the embodiment of the present invention, setting is corresponding with user tag
Characteristic information, characteristic information is mated with the big data information of user, is set up corresponding use for the user that the match is successful
Family label, the corresponding relation of storage ID and user tag, to provide a user with retrieval service according to corresponding relation.By
This, according to the big data information of user, set up associated user's label for corresponding user, in order to be user according to user tag
Personalized retrieval service is provided, improves retrieval performance.
Based on above example, in order to more comprehensively describe the retrieval process based on artificial intelligence of the embodiment of the present invention
Method, below in conjunction with the accompanying drawings, in conjunction with the processing procedure for the search behavior on line, describe in detail the embodiment of the present invention based on
The search processing method of artificial intelligence:
Fig. 3 is the flow chart of the search processing method based on artificial intelligence in accordance with another embodiment of the present invention, such as Fig. 3
Shown, after above-mentioned steps S130, the method also includes:
S210, receives and comprises ID and the retrieval request of query statement.
S220, inquiry corresponding relation obtains user tag corresponding with ID.
Specifically, receive the retrieval request comprising ID and query statement, ID is inquired about according to ID
With the corresponding relation of user tag, obtain user tag corresponding with this ID.
S230, detects whether there is the user tag mated with query statement.
In actual applications, even if there is user tag corresponding with ID, this user tag is likely to and currently
Query statement and mismatch.
Such as, after receiving the retrieval request comprising ID and query statement " what today eats ", according to user
Mark inquiry ID and the corresponding relation of user tag, acquisition user tag corresponding with this ID is " music weight
Degree fan " is then it is assumed that this user tag with query statement and mismatches.
Thus, after obtaining user tag corresponding with ID, need the use detecting whether to mate with query statement
Family label, to decide whether to provide the user corresponding personalized retrieval service.
It should be noted that according to the difference of concrete application scene, detecting whether there is the user mated with query statement
The mode of label is different, is exemplified below:
The first example, by user tag according to the retrieval classification of type of query statement, such as, by user tag " Sichuan cuisine
Fan ", " Hunan cuisine fan " belong to " cuisines " class etc..And then, according to query statement corresponding retrieval type, determination can be
No exist and this corresponding user tag of retrieval type.
Specifically, acquisition of information query statement corresponding retrieval type can be retrieved according to default normalization.
Wherein, the theme that information can accurately according to query statement is retrieved in above-mentioned default normalization, identifies that it is right
The retrieval type answered, such as, when the query statement of input is " what today eats ", or when " eating nice going " etc., default
It is " cuisines " that normalization retrieval information then obtains query statement corresponding retrieval type;Again such as, when input inquiry sentence is " sea
The moulding that Zei Wang road flies ", or when " Vampire Knight schoolmate " etc., default normalization retrieval information then obtains query statement pair
The retrieval type answered is " animation ".
And then, can detect whether exist and query statement according to the attaching relation of default retrieval type and user tag
The user tag joined.
For example, when acquisition retrieval corresponding with query statement type is " cuisines ", according to default retrieval type
With the attaching relation of user tag, detect whether there is the user tag related to " cuisines ".
Second example, can be by identifying the key word in query statement, as the key word in query statement and user
Label is mated, and then, can detect whether exist and query statement according to the size of query statement and user tag similarity
The user tag of coupling.
For example, the pass when the query statement of user input is " the best place to go of tourism ", in identification query statement
Keyword is " tourism ", and this key word is mated with user tag, to detect whether to exist and the higher user of " tourism " similarity
Label.
S240, if it is present feed back retrieval corresponding with inquiry request according to the user tag that query statement mates
Result.
Specifically, if there is the user tag mated with query statement, then in order to meet the individual demand of user, can
According to the corresponding retrieval result fed back with the user tag that query statement mates with inquiry request.
For example, as shown in Fig. 4 (a), when the name that the query statement in retrieval request is certain star, according to inspection
ID in rope request, obtains vermicelli and the food enthusiasts that user tag corresponding with ID is this star.
And then, there is the user tag mated with this query statement in detection, then, as shown in Fig. 4 (a), feed back the row of this star
The information of the vermicellis such as journey information, focus, microblogging concern.
In another embodiment of the present invention, if there is no the user tag mated with query statement, then according to logical
With main demand feedback retrieval result.
For example, as shown in Fig. 4 (b), when the name that the query statement in retrieval request is certain star, according to inspection
ID in rope request, acquisition user tag corresponding with ID is food enthusiasts.
And then, there is not the user tag mated with this query statement in detection, then, as shown in Fig. 4 (b), feed back this star's
The information of the passerbys such as encyclopaedia concern.
In sum, the search processing method based on artificial intelligence of the embodiment of the present invention, receive comprise ID and
The retrieval request of query statement, inquiry corresponding relation obtain user tag corresponding with ID, and detect whether exist and
The user tag of query statement coupling, thus if it is present according to the user tag feedback mated with query statement and inquiry
Ask corresponding retrieval result.Thus, when there is the user tag mated with query statement, full according to this user tag feedback
The retrieval result of sufficient users ' individualized requirement, improves the satisfaction to retrieval result for the user.
In order to realize above-described embodiment, the invention allows for a kind of retrieval process device based on artificial intelligence, Fig. 5 is
The structural representation of the retrieval process device based on artificial intelligence according to an embodiment of the invention, as shown in figure 5, this is based on
The retrieval process device of artificial intelligence includes:Setup module 10, matching module 20, set up module 30 and memory module 40.
Wherein, setup module 10, for arranging characteristic information corresponding with user tag.
Matching module 20, for being mated characteristic information with the big data information of user.
In one embodiment of the invention, Fig. 6 is the inspection based on artificial intelligence in accordance with another embodiment of the present invention
The structural representation of rope processing meanss, as shown in fig. 6, on the basis of as shown in Figure 5, matching module 20 includes the first screening list
Unit 21 and the first matching unit 22.
Wherein, the first screening unit 21, for filtering out user's history retrieval behavior letter from the big data information of user
Breath.
First matching unit 22, for being mated retrieval character information with user's history retrieval behavioural information.
Wherein, the search rate of key word that retrieval character information includes mating with user tag is mated with user tag
The click frequency of search content mated with user tag of the click frequency of Search Results type and in mating with user tag
One or more of concern time held.
In another embodiment of the present invention, Fig. 7 is based on artificial intelligence's according to another embodiment of the present invention
The structural representation of retrieval process device, as shown in fig. 7, on the basis of as shown in Figure 5, matching module 20 includes the second screening
Unit 23 and the second matching unit 24.
Wherein, the second screening unit 23, for filtering out user's portrait information from the big data information of user.
Second matching unit 24, for being mated user's characteristic information with user's portrait information.
Set up module 30, for setting up corresponding user tag for the user that the match is successful.
Memory module 40, for storing the corresponding relation of ID and user tag so that according to corresponding relation to
Family provides retrieval service.
It should be noted that the aforementioned explanation to the search processing method based on artificial intelligence, it is also applied for this
The retrieval process device based on artificial intelligence of bright embodiment, it is realized principle and is similar to, for the present invention based on artificial intelligence's
The details not disclosed in retrieval process device embodiment, will not be described here.
In sum, the search processing method based on artificial intelligence of the embodiment of the present invention, setting is corresponding with user tag
Characteristic information, characteristic information is mated with the big data information of user, is set up corresponding use for the user that the match is successful
Family label, the corresponding relation of storage ID and user tag, to provide a user with retrieval service according to corresponding relation.By
This, according to the big data information of user, set up associated user's label for corresponding user, in order to be user according to user tag
Personalized retrieval service is provided, improves retrieval performance.
Fig. 8 is the structural representation according to further embodiment of the present invention based on the retrieval process device of artificial intelligence,
As shown in figure 8, on the basis of as shown in Figure 5, should also including receiver module 50, obtain based on the retrieval process device of artificial intelligence
Delivery block 60, detection module 70 and feedback module 80.
Wherein, receiver module 50, comprise ID and the retrieval request of query statement for receiving.
Acquisition module 60, obtains user tag corresponding with ID for inquiring about corresponding relation.
, for detecting whether there is the user tag mated with query statement in detection module 70.
In one embodiment of the invention, Fig. 9 is the inspection according to a still further embodiment of the present invention based on artificial intelligence
The structural representation of rope processing meanss, as shown in figure 9, on the basis of as shown in Figure 8, this detection module 70 can include obtaining
Unit 71 and detector unit 72.
Wherein, acquiring unit 71, for retrieving acquisition of information query statement corresponding retrieval class according to default normalization
Type.
Detector unit 72, for detecting whether to exist according to the attaching relation of default retrieval type and user tag and looking into
Ask the user tag of statement matching.
Feedback module 80, for when there is the user tag mated with query statement, according to mate with query statement
User tag feeds back retrieval result corresponding with inquiry request.
It should be noted that the aforementioned explanation to the search processing method based on artificial intelligence, it is also applied for this
The retrieval process device based on artificial intelligence of bright embodiment, it is realized principle and is similar to, for the present invention based on artificial intelligence's
The details not disclosed in retrieval process device embodiment, will not be described here.
In sum, the retrieval process device based on artificial intelligence of the embodiment of the present invention, receive comprise ID and
The retrieval request of query statement, inquiry corresponding relation obtain user tag corresponding with ID, and detect whether exist and
The user tag of query statement coupling, thus if it is present according to the user tag feedback mated with query statement and inquiry
Ask corresponding retrieval result.Thus, when there is the user tag mated with query statement, full according to this user tag feedback
The retrieval result of sufficient users ' individualized requirement, improves the satisfaction to retrieval result for the user.
Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or hint relative importance
Or the implicit quantity indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Implicitly include at least one this feature.In describing the invention, " multiple " are meant that at least two, such as two, three
Individual etc., unless otherwise expressly limited specifically.
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy describing with reference to this embodiment or example
Point is contained at least one embodiment or the example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be in office
Combine in an appropriate manner in one or more embodiments or example.Additionally, in the case of not conflicting, the skill of this area
The feature of the different embodiments described in this specification or example and different embodiment or example can be tied by art personnel
Close and combine.
Although embodiments of the invention have been shown and described above it is to be understood that above-described embodiment is example
Property it is impossible to be interpreted as limitation of the present invention, those of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (12)
1. a kind of search processing method based on artificial intelligence is it is characterised in that comprise the following steps:
Characteristic information corresponding with user tag is set;
Described characteristic information is mated with the big data information of user, is set up corresponding user's mark for the user that the match is successful
Sign;
Storage ID and the corresponding relation of user tag, to provide a user with retrieval service according to described corresponding relation.
2. the method for claim 1 is it is characterised in that described characteristic information includes:Retrieval character information,
Described described characteristic information is mated with the big data information of user, including:
User's history retrieval behavioural information is filtered out from the big data information of described user;
Described retrieval character information is mated with described user's history retrieval behavioural information.
3. method as claimed in claim 2 it is characterised in that described retrieval character information include one of following information or
Multiple:
The search rate of the key word mating with described user tag;
The click frequency of the Search Results type mated with described user tag;
The click frequency of the search content mated with described user tag;
The concern time with described user tag matching content.
4. method as claimed in claim 2 is it is characterised in that described characteristic information also includes:User's characteristic information,
After described retrieval character information is mated with described user's history retrieval information, also include:
User's portrait information is filtered out from the big data information of described user;
Described user's characteristic information is mated with described user portrait information.
5. described method as arbitrary in claim 1-4 is it is characterised in that right in described storage ID and user tag
After should being related to, also include:
Receive and comprise ID and the retrieval request of query statement;
Inquire about described corresponding relation and obtain user tag corresponding with described ID;
Detect whether there is the user tag mated with described query statement;
If it is present according to user tag feedback retrieval corresponding with the described inquiry request knot mating with described query statement
Really.
6. method as claimed in claim 5 is it is characterised in that described detect whether there is the use mated with described query statement
Family label, including:
Query statement corresponding retrieval type according to acquisition of information is retrieved in default normalization;
Detect whether there is the use mated with described query statement according to default retrieval type with the attaching relation of user tag
Family label.
7. a kind of retrieval process device based on artificial intelligence is it is characterised in that include:
Setup module, for arranging characteristic information corresponding with user tag;
Matching module, for being mated described characteristic information with the big data information of user;
Set up module, for setting up corresponding user tag for the user that the match is successful;
Memory module, for storing the corresponding relation of ID and user tag, so that according to described corresponding relation to user
Retrieval service is provided.
8. device as claimed in claim 7 is it is characterised in that described characteristic information includes:Retrieval character information, described coupling
Module includes:
First screening unit, for filtering out user's history retrieval behavioural information from the big data information of described user;
First matching unit, for being mated described retrieval character information with described user's history retrieval behavioural information.
9. device as claimed in claim 8 it is characterised in that described retrieval character information include one of following information or
Multiple:
The search rate of the key word mating with described user tag;
The click frequency of the Search Results type mated with described user tag;
The click frequency of the search content mated with described user tag;
The concern time with described user tag matching content.
10. device as claimed in claim 8 is it is characterised in that described characteristic information also includes:User's characteristic information, described
Matching module includes:
Second screening unit, for filtering out user's portrait information from the big data information of described user;
Second matching unit, for being mated described user's characteristic information with described user portrait information.
11. such as claim 7-10 arbitrary described devices are it is characterised in that also include:
Receiver module, comprises ID and the retrieval request of query statement for receiving;
Acquisition module, obtains user tag corresponding with described ID for inquiring about described corresponding relation;
, for detecting whether there is the user tag mated with described query statement in detection module;
Feedback module, for when there is the user tag mated with described query statement, mating according to described query statement
User tag feed back retrieval result corresponding with described inquiry request.
12. devices as claimed in claim 11 are it is characterised in that described detection module includes:
Acquiring unit, for query statement corresponding retrieval type according to default normalization retrieval acquisition of information;
Detector unit, for detecting whether exist and described inquiry according to the attaching relation of default retrieval type and user tag
The user tag of statement matching.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610804040.0A CN106407346A (en) | 2016-09-06 | 2016-09-06 | Retrieval processing method and apparatus based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610804040.0A CN106407346A (en) | 2016-09-06 | 2016-09-06 | Retrieval processing method and apparatus based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106407346A true CN106407346A (en) | 2017-02-15 |
Family
ID=57998465
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610804040.0A Pending CN106407346A (en) | 2016-09-06 | 2016-09-06 | Retrieval processing method and apparatus based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106407346A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107357507A (en) * | 2017-06-29 | 2017-11-17 | 北京小米移动软件有限公司 | The method, apparatus and storage medium of sharing information |
CN107363862A (en) * | 2017-06-28 | 2017-11-21 | 重庆柚瓣家科技有限公司 | Social intercourse system based on robot |
CN108877334A (en) * | 2018-06-12 | 2018-11-23 | 广东小天才科技有限公司 | A kind of voice searches topic method and electronic equipment |
CN109002464A (en) * | 2017-06-06 | 2018-12-14 | 万事达卡国际公司 | The method and system suggested using the automatic report analysis of dialog interface and distribution |
CN109388753A (en) * | 2018-10-31 | 2019-02-26 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling information |
CN110083688A (en) * | 2019-05-10 | 2019-08-02 | 北京百度网讯科技有限公司 | Search result recalls method, apparatus, server and storage medium |
CN111753170A (en) * | 2020-07-04 | 2020-10-09 | 广州智云尚大数据科技有限公司 | Big data quick retrieval system and method |
CN112632378A (en) * | 2020-12-21 | 2021-04-09 | 高晓惠 | Information processing method based on big data and artificial intelligence and data server |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080140619A1 (en) * | 2006-12-07 | 2008-06-12 | Divesh Srivastava | Method and apparatus for using tag topology |
CN104462293A (en) * | 2014-11-27 | 2015-03-25 | 百度在线网络技术(北京)有限公司 | Search processing method and method and device for generating search result ranking model |
CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
-
2016
- 2016-09-06 CN CN201610804040.0A patent/CN106407346A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080140619A1 (en) * | 2006-12-07 | 2008-06-12 | Divesh Srivastava | Method and apparatus for using tag topology |
CN104462293A (en) * | 2014-11-27 | 2015-03-25 | 百度在线网络技术(北京)有限公司 | Search processing method and method and device for generating search result ranking model |
CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109002464A (en) * | 2017-06-06 | 2018-12-14 | 万事达卡国际公司 | The method and system suggested using the automatic report analysis of dialog interface and distribution |
CN109002464B (en) * | 2017-06-06 | 2023-01-06 | 万事达卡国际公司 | Method and system for automatic report analysis and distribution of suggestions using a conversational interface |
CN107363862B (en) * | 2017-06-28 | 2019-08-09 | 重庆柚瓣家科技有限公司 | Social intercourse system based on robot |
CN107363862A (en) * | 2017-06-28 | 2017-11-21 | 重庆柚瓣家科技有限公司 | Social intercourse system based on robot |
CN107357507A (en) * | 2017-06-29 | 2017-11-17 | 北京小米移动软件有限公司 | The method, apparatus and storage medium of sharing information |
CN108877334A (en) * | 2018-06-12 | 2018-11-23 | 广东小天才科技有限公司 | A kind of voice searches topic method and electronic equipment |
CN109388753A (en) * | 2018-10-31 | 2019-02-26 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling information |
CN110083688A (en) * | 2019-05-10 | 2019-08-02 | 北京百度网讯科技有限公司 | Search result recalls method, apparatus, server and storage medium |
CN110083688B (en) * | 2019-05-10 | 2022-03-25 | 北京百度网讯科技有限公司 | Search result recall method, device, server and storage medium |
CN111753170A (en) * | 2020-07-04 | 2020-10-09 | 广州智云尚大数据科技有限公司 | Big data quick retrieval system and method |
CN111753170B (en) * | 2020-07-04 | 2021-08-17 | 上海德吾信息科技有限公司 | Big data quick retrieval system and method |
CN112632378A (en) * | 2020-12-21 | 2021-04-09 | 高晓惠 | Information processing method based on big data and artificial intelligence and data server |
CN112632378B (en) * | 2020-12-21 | 2021-08-24 | 广东省信息网络有限公司 | Information processing method based on big data and artificial intelligence and data server |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106407346A (en) | Retrieval processing method and apparatus based on artificial intelligence | |
US8370358B2 (en) | Tagging content with metadata pre-filtered by context | |
US10896184B2 (en) | Method and system for capturing and exploiting user intent in a conversational interaction based information retrieval system | |
CN107735782B (en) | Image and text data hierarchical classifier | |
US9678989B2 (en) | System and method for use of images with recognition analysis | |
US7542610B2 (en) | System and method for use of images with recognition analysis | |
CN102007492B (en) | For the method and apparatus searching for the digital picture of several storages | |
CN103069415B (en) | Computer-implemented method, computer program and computer system for image procossing | |
US7386792B1 (en) | System and method for collecting, storing, managing and providing categorized information related to a document object | |
WO2019127832A1 (en) | Intelligent search method and apparatus, terminal, server, and storage medium | |
CN103902697B (en) | Combinatorial search method, client and server | |
EP3465475A1 (en) | Method for producing and distributing one or more customized media centric products | |
US10956948B2 (en) | System and method for hotel discovery and generating generalized reviews | |
CN105159937B (en) | Information-pushing method and device | |
CN110263180A (en) | It is intended to knowledge mapping generation method, intension recognizing method and device | |
JP2009526302A (en) | Method and system for tagging digital data | |
KR20110084413A (en) | System and method for context enhanced ad creation | |
JP2003518664A (en) | Method and system for constructing a personalized result set | |
CN107092608A (en) | A kind of search of destination object, recommendation method and apparatus | |
CN106919571A (en) | Obtain the method and device of the picture matched with search keyword | |
CN109213921A (en) | A kind of searching method and device of merchandise news | |
JP2009157500A (en) | Distribution server and distribution method | |
US20140289255A1 (en) | Application of community-defined descriptors to mobile content | |
CN110362732A (en) | A kind of method of information system content search | |
KR102270989B1 (en) | Artificial intelligence fashion coordination system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |
|
RJ01 | Rejection of invention patent application after publication |