CN108228665A - Determine object tag, the method and device for establishing tab indexes, object search - Google Patents
Determine object tag, the method and device for establishing tab indexes, object search Download PDFInfo
- Publication number
- CN108228665A CN108228665A CN201611197791.7A CN201611197791A CN108228665A CN 108228665 A CN108228665 A CN 108228665A CN 201611197791 A CN201611197791 A CN 201611197791A CN 108228665 A CN108228665 A CN 108228665A
- Authority
- CN
- China
- Prior art keywords
- label
- word
- keyword
- grouping
- participle
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The embodiment of the present application discloses a kind of determining object tag, the method and device for establishing tab indexes, object search.The method of the determining object tag includes:Corresponding first text message of the first object is obtained, first participle word collection corresponding with first object is obtained according to first text message;Correspondence based on preset label and keyword determines that the first participle word is concentrated and successfully segments word and candidate label corresponding with the participle word of the successful match with the Keywords matching in the default correspondence;Partly or entirely described candidate label is set as to the target labels of first object.The efficiency and accuracy of determining object tag can be improved.
Description
Technical field
This application involves digital information processing field, more particularly to a kind of determining object tag, establish tab indexes,
The method and device of object search.
Background technology
With the development of e-commerce, user can be bought on e-commerce platform needed for article.In the case of one kind, electricity
Quotient in order to ensure user can fast search to the product admired, can be that product sets label, and offer is searched according to label
The function of rope, to improve the matching degree of search result and user's expected result.In another case, electric business platform usual red-letter day
Period holds activity, sets label if product, can go out be suitble to the product of the festive events according to label fast selecting.Also
In the case of one kind, after for product, label is set, it can be recommended according to the label of setting and the matching degree of user preference for user
Meet the product of its preference.Therefore, in order to realize above-mentioned function, it usually needs the label of product is determined in advance.
The method of existing determining Product labelling has artificial marking method and participle matching algorithm.Artificial marking method, i.e.,
After staff checks product, suitable label is set for product.But since product quantity is numerous, artificial mark process will disappear
It consumes a large amount of human costs and execution speed is slower, be susceptible to the error situation of the wrong label of setting.Segmenting matching algorithm is typically,
Tally set is set, a pair text message associated with product carries out word segmentation processing and obtains multiple participle words corresponding with the product,
Obtained participle word is matched with the label in tally set, participle word is identical with the label in tally set, then can
The participle word to be set as to the label of the product.However, for the high near synonym of correlation degree, abbreviation word etc., it is existing
Participle matching algorithm can not realize matching.For example, there are label " Maldives " in tally set, and the corresponding participle word of product
Language includes " horse generation ", and " horse generation " is the abbreviation of " Maldives ", but can not successful match.For another example there is mark in tally set
It signs " diving ", and the corresponding participle word of product includes " latent sea ", " diving " is near synonym, but can not match into " latent sea "
Work(.
Invention content
A kind of method that the purpose of the embodiment of the present application is to provide determining object tag, establishes tab indexes, object search
And device, to improve the efficiency and accuracy that determine object tag and object search.
In order to solve the above technical problems, the embodiment of the present application provides a kind of determining object tag, establishes tab indexes, search
What the method and device of object was realized in:
A kind of method of determining object tag, including:
Obtain corresponding first text message of the first object;
First participle word collection corresponding with first object is obtained according to first text message;
Correspondence based on preset label and keyword determines that the first participle word is concentrated and described default pair
Keywords matching in should being related to successfully segments word and candidate mark corresponding with the participle word of the successful match
Label;
Partly or entirely described candidate label is set as to the target labels of first object.
A kind of method for establishing tab indexes, including:
It obtains and includes the tally set of multiple references object and outturn sample collection;
According to the label of the references object, the references object is grouped, and utilizes the text of the references object
The keyword of each grouping of this information extraction;
According to the keyword of each grouping of extraction and corresponding label, it is corresponding with keyword to form the label
Relationship.
A kind of method based on tag search object, including:
The multiple labels of user are supplied to, receive the information that user selects the first label from the multiple label;It is described to carry
The label of supply user is the label of tourism industry
The first label that user selects is sent to server, receive and show the server feedback with the first label
Corresponding at least one object.
A kind of device of determining object tag, including:
Word determining module is segmented, for obtaining corresponding first text message of the first object, according to first text
Information obtains first participle word collection corresponding with first object;First object is the merchandise items of tourism industry,
First text message includes at least one of following:Merchandise items title, merchandise items detail information, merchandise items category
Property information;
Candidate label determining module for the correspondence based on preset label and keyword, determines described first point
Word word concentrate with the default correspondence in Keywords matching successfully segment word and with the successful match
Segment the corresponding candidate label of word;
Target labels determining module, for partly or entirely described candidate label to be set as to the target of first object
Label.
A kind of device for establishing tab indexes, including:
References object acquisition module, for obtaining the sample sets for including multiple references object, the sample sets include ginseng
Examine the text message of object, the label of the references object and the references object;
Grouping and keyword extracting module for being grouped to the references object, and utilize the references object
Text message extracts the keyword of each grouping;
Corresponding relation building module, keyword and corresponding label for each grouping according to extraction are formed
The correspondence of the label and keyword.
A kind of client, including:
Input unit inputs information for receiving user;
Communication module is communicated to connect and is carried out data transmission for establishing;
Display, for displaying data;
Controller for the display to be controlled to show multiple labels, and controls the input equipment to receive user from institute
State the information that the first label is selected in multiple labels;The controller is additionally operable to the communication module is controlled to select user
One label is sent to server and receives at least one object corresponding with the first label of the server feedback;The control
Device is additionally operable to that the display is controlled to show at least one object corresponding with the first label;
The label is the label of tourism industry.
By above technical solution provided by the embodiments of the present application as it can be seen that determining object tag provided by the embodiments of the present application
Method determines candidate label according to the correspondence of preset label and keyword, object is determined further according to candidate label
Final target labels.The process for determining label is the process of Auto-matching, saves cost of labor, also avoids misplaying label
Situation, so as to improve the efficiency of determining object tag and accuracy.Simultaneously as the keyword provided is corresponding with label
In relationship, keyword may be differed with label, only needed in the present embodiment corresponding participle word and the Keywords matching of object into
Work(, it is possible to determine candidate label corresponding with the participle word, it is identical with label without segmenting word, therefore,
The accuracy of determining object tag can be improved.The method provided by the embodiments of the present application for establishing tab indexes, by language
Material is handled, it may be determined that the stronger word of relevance, such as synonym, abbreviation word etc..By setting the stronger word of relevance
The corresponding participle word of object can be carried out unification, so as to more accurately find participle by subject term and adjunct in language
Corresponding label improves the accuracy rate for determining label.In the method for object search provided by the embodiments of the present application, due to be searched
Object be to determine the object of label, can object search directly be gone out according to label filtration, search process is convenient and efficient.Together
When, in the method that object tag is determined due to the application, the accuracy rate of determining object tag is high, therefore, is searched using the application
The result accuracy rate that the method for rope object is searched for is also high, meets user and searches for expectation.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or it will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments described in application, for those of ordinary skill in the art, in the premise of not making the creative labor property
Under, it can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is the flow chart of method one embodiment that the application determines object tag;
Fig. 2 is the flow chart that the application determines another embodiment of the method for object tag;
Fig. 3 is the flow chart of method one embodiment that the application establishes tab indexes;
Fig. 4 is the flow chart of the method one embodiment of the application based on tag search object;
Fig. 5 is the module map of device one embodiment that the application determines object tag;
Fig. 6 is the module map that the application determines another embodiment of the device of object tag;
Fig. 7 is the module map of device one embodiment that the application establishes tab indexes;
Fig. 8 is composition schematic diagram of the application for a client embodiment of object search.
Specific embodiment
The embodiment of the present application provides a kind of determining object tag, the method and device for establishing tab indexes, object search.
In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with the application reality
The attached drawing in example is applied, the technical solution in the embodiment of the present application is clearly and completely described, it is clear that described implementation
Example is merely a part but not all of the embodiments of the present application.Based on the embodiment in the application, this field is common
Technical staff's all other embodiments obtained without creative efforts should all belong to the application protection
Range.
Fig. 1 is the flow chart of method one embodiment that the application determines object tag.With reference to Fig. 1, the determining object
The method of label may comprise steps of.
S101:Corresponding first text message of the first object is obtained, is obtained and described according to first text message
The corresponding first participle word collection of an object.
The object can be entity products, for example, it may be sight spot admission ticket, air ticket etc..The object can also be clothes
It is engaged in class product, for example, it may be national visa service, a guide service etc..
First object can be any one object in the object of multiple labels to be determined.It can will be with the first object phase
Associated text message is known as the first text message.First object can be the merchandise items of tourism industry.Described first
Text message can include at least one of following:Merchandise items title, merchandise items detail information, merchandise items attribute letter
Breath etc..
The merchandise items attribute information can be include it is at least one of following:The corresponding sight spot of merchandise items
Location, the corresponding departure place of merchandise items, merchandise items corresponding travel time, the corresponding mode of transportation of merchandise items, commodity pair
As corresponding expense, the corresponding sight spot feature of merchandise items etc..The merchandise items attribute information can be by merchandise items
Retailer provides.
In one embodiment, the merchandise items title can be the merchandise items mark that merchandise items retailer fills in
Topic.
In another embodiment, merchandise items title can also be pair automatically generated according to the attribute of merchandise items
As title.Specifically, can be according to the corresponding sight spot address of merchandise items, the corresponding departure place of merchandise items, merchandise items
The merchandise items title that corresponding travel time, the corresponding mode of transportation of merchandise items etc. automatically generate.A for example, merchandise items
For a vacation packages, attribute information can be as follows:Sight spot address is Chengdu, departure place is Shanghai, the travel time is New Year's Day, is handed over
Logical mode is aircraft, then, according to above-mentioned attribute information can generate the vacation packages it is entitled " New Year's Day Shanghai set out into
All round trip flights ".
It is described that first participle word collection corresponding with first object is obtained according to first text message, including:
Word segmentation processing is carried out to first text message, obtains several participle words;The participle word is counted, is determined
Participle word corresponding with the first object and the frequency for segmenting word;The participle word corresponding with the first object and participle word
The frequency of language forms first participle word collection corresponding with the first object.
In one embodiment, first participle word collection can also be characterized as word segmentation result table.Reference table 1, described point
In word result table, it can include:The frequency of the corresponding participle word of object identity, object and each participle word.Object identity
It can be used for unique mark object, can be title, number of object etc..
Table 1
S102:Correspondence based on preset label and keyword, determine the first participle word concentrate with it is described
Keywords matching in default correspondence successfully segments word and time corresponding with the participle word of the successful match
Select label.
With reference to table 2, the preset label and the correspondence of keyword can be used for characterizing a label and its corresponding
Keyword.One label can correspond to one or more keywords.One keyword can also correspond to one or more labels.
Table 2
Label | Keyword |
Island | Island, island, island, Maldives |
Sandy beach | Sandy beach, seabeach, outdoor bathing place |
Correspondence based on preset label and keyword, the participle word that the first participle word can be concentrated
Match with the keyword in default correspondence, if successful match, the corresponding label of the keyword of the successful match is made
For candidate label.
For example, the participle word that first participle word is concentrated includes:" Maldives " " island " and " sandy beach ".So, root
According to the label and the correspondence of keyword shown in table 2, include in table 2 with the above-mentioned successful keyword of participle word match:" horse
Er Daifu " " island " and " sandy beach ", then label " island " corresponding with the keyword of successful match and " sandy beach " as candidate
Label.
S103:Partly or entirely described candidate label is set as to the target labels of first object.
The target labels that partly or entirely described candidate label is set as to first object, including:
Specifically, it can be determined that whether the total number of candidate's label is less than or equal to the first object mesh of the setting
Mark the total number of label;If the determination result is YES, all candidate labels are set as to the target labels of the first object;If sentence
Disconnected result is no, and the part candidate label is set as to the target labels of the first object according to default selection rule.
The basis presets the target labels that the part candidate label is set as the first object by selection rule, including:
The candidate label according to the matching times selected part of candidate label, and the candidate label of selection is set as the first object
Target labels.The matching times of candidate's label include:The corresponding keyword of label concentrates participle word with first participle word
The number of the successful match of language.
For example, the participle word that first participle word is concentrated includes:" Maldives " " island " and " sandy beach ".According to table 1
In label and keyword correspondence, it may be determined that candidate label includes:" island " and " sandy beach ".If the first object is set
The total numbers of target labels be 3, then candidate label " island " and " sandy beach " can serve as the target labels of the first object.
If the total number for setting the target labels of the first object is 1, then needs to choose one in outgoing label " island " and " sandy beach "
As target labels.Due to participle word and corresponding keyword " Maldives ", " island " all successful match, then label
The matching times on " island " can be 2;Similarly, the matching times of label " sandy beach " can be 1.It is possible to choose " sea
Target labels of the island " as object.
Above-described embodiment provide determining object tag method, according to the correspondence of preset label and keyword come
It determines candidate's label, the final target labels of object is determined further according to candidate label.The process for determining label is Auto-matching
Process, save cost of labor, also avoid misplaying the situation of label, so as to improve the efficiency of determining object tag and standard
True property.Simultaneously as in the keyword and the correspondence of label that provide, keyword may be differed with label, the present embodiment
In only need the corresponding participle word and Keywords matching success of object, it is possible to determine candidate mark corresponding with the participle word
Label, it is identical with label without segmenting word, it is thus possible to improve the accuracy of determining object tag.
In another embodiment, the method for the determining object tag can also include:Industry corpus, institute are provided
It states industry corpus and includes near synonym vocabulary in the industry belonging to object.
The industry corpus can be the corpus of tourism industry.It can include the affiliated row of object in the near synonym table
Semantic same or similar word in industry.For example, it may be the full name and abbreviation of sight name.
In the near synonym table, multigroup near synonym can be included.
For each group of near synonym, subject term and adjunct can be included, the subject term and the adjunct can be nearly justice
Word.The subject term can be used for adjunct described in unified representation.For example, it for one group of near synonym " diving ", " deep diving ", " floats
It is latent ", wherein " diving " can be subject term, " deep diving " and " snorkeling " can be adjunct.
For one group of near synonym, subject term and adjunct can have correspondence.
With reference to Fig. 2, in the present embodiment, obtained according to first text message it is corresponding with first object
After first participle word collection, the method can also include S1011:Using in the industry corpus belonging to first object
Near synonym vocabulary, to the first participle word collection carry out near synonym replacement, obtain replaced first participle word collection.That
, it is described to determine that the first participle word concentration successfully segments word with the Keywords matching in the default correspondence
Language, specially:Determine the replaced first participle word concentrate with the Keywords matching in the default correspondence into
The participle word of work(.
Near synonym vocabulary in the industry corpus using belonging to the first object, to the first participle word collection into
Row near synonym are replaced, and are obtained replaced first participle word collection, can specifically be included:The first participle word is inquired to concentrate
Participle word whether be adjunct in the near synonym vocabulary, corresponded to if so, the participle word is replaced with the adjunct
Subject term.
In one scenario, it is assumed that former first participle word collection can be as shown in table 1, according in tourism industry corpus
Near synonym table understands " diving " and " deep diving " near synonym, and " diving " is subject term, and " deep diving " is adjunct.It it is possible to will
" deep diving " that first participle word is concentrated in table 1 replaces with " diving ", meanwhile, it is superimposed its frequency.So, the first participle after update
Word is concentrated without participle word " deep diving ", while the frequency for segmenting word " diving " is updated to 21.Similarly, near synonym table
In, " Maldives " and " horse generation " is near synonym, and " Maldives " is subject term, and " horse generation " is its adjunct, then, it is updated
First participle word collection is referred to table 3.
Table 3
In above-described embodiment, by the way that the corresponding participle word of the first object can be concentrated to the near synonym table in corpus
Near synonym carry out unified representation, so as to more accurately find the corresponding label of participle, improve the accuracy rate for determining label.
In presently filed embodiment, the near synonym table in the corpus can be obtained according to following methods:It obtains
The corpus information in corpus is taken, determines the frequency of participle word corresponding with the corpus information and the participle word;
It determines the near synonym in the participle word, and determines the subject term and adjunct in the near synonym.
The corpus information can be the corpus information of an industry.For example, it may be the corpus information of tourism industry, packet
It includes:Travel notes, tourism objects introduction, Scenic spot introduction of passenger etc..
It can determine the frequency of participle word corresponding with the corpus information and the participle word, specifically:It can
To carry out word segmentation processing to the corpus information, the participle word of the corpus information is obtained;The corpus information can be counted
The frequency of each participle word.
The First Eigenvalue of the participle word of the corpus information can be calculated.The First Eigenvalue of the participle word can
To be the corresponding real vector of the participle word.The dimension of the real vector can be configured according to actual conditions, example
Can such as it refer to for 200 dimensions.
In one embodiment, word2vec algorithms may be used to calculate the corresponding real vector of participle word.
For example, may be used word2vec algorithms be calculated participle word " diving " real vector be [0.792 ,-
0.177, -0.107,0.109, -0.542 ...] and use word2vec algorithms that the reality for segmenting word " deep diving " is calculated
Number vector for [0.912, -0.2, -0.2,0.209, -0.742 ...].
The similarity of the First Eigenvalue can be less than to the participle word of second threshold as near synonym.The fisrt feature
The similarity of value includes:Segment the cosine similarity of the corresponding real vector of word.Second threshold can taking according to similarity
Value range determines.For example, when the value range of similarity is [0,1], the second threshold can be set as 0.8~0.9.
For example, it is assumed that second threshold is 0.8, the real vector of above-mentioned " diving " and the real vector of " deep diving " are calculated
Cosine similarity be 0.993, then, " diving " and " deep diving " can be determined as near synonym.
Can be using the highest participle word of the frequency near synonym as subject term, remaining participle word is as adjunct.
For example, for identical participle word " diving " semantic in table 2 and " deep diving ", the frequency of diving is 15, " deep diving "
The frequency be 6, then, can be by " diving " as subject term, " deep diving " is as adjunct.
With reference to Fig. 3, the embodiment of the present application also provides a kind of method for establishing tab indexes.Tab indexes are established by described
Method, the correspondence of label and keyword can be provided, the method for determining object tag to be applied to the application is implemented
Example.The method for establishing tab indexes may comprise steps of.
S301:Obtain the sample sets for including multiple references object.
It can include the text of references object, the label of the references object and the references object in the sample sets
Information.
The references object can pre-set the merchandise items of label.The references object can be tourism industry
In merchandise items.The label of the references object can be set based on the industry belonging to the references object.
The label of the references object can be to pre-set.
The text message of the references object can be text message associated with the references object.For example, can be with
It is title, detail information, attribute information of references object etc..
S302:According to the label of the references object, the references object is grouped, and utilizes the references object
Text message extract the keyword of each grouping.
The references object can be grouped according to the label of the references object.For example, can will have at least
The references object of one same label is divided into one group.
It should be noted that there may be identical references object in different grouping.For example, a references object, right
The label answered both comprising " island " or included " sandy beach ", then, which can both be used as label " island " this grouping
References object, can also be used as the references object of label " sandy beach " this grouping.
The number of references object after grouping in each grouping can be greater than or equal to first threshold.First threshold can root
It is chosen according to actual conditions.Under normal conditions, the value of first threshold is more than 50.
Using the text message of the references object, the keyword of each grouping can be extracted.Can specifically it include:To each
The text message of references object described in a grouping carries out word segmentation processing, forms the participle word collection of each grouping;According to word frequency-
The rate of falling document, it may be determined that the keyword that the participle word of each grouping is concentrated obtains the keyword of each grouping.
Segment TF-IDF (term frequency-inverse document frequency, the word frequency-literary of word
Shelves rate) characteristic value can be used for characterizing the class discrimination ability of the participle word.Under normal conditions, TF-IDF characteristic values are bigger,
Represent that the class discrimination ability of the participle word is stronger.Therefore, TF-IDF characteristic values are larger in each grouping M points can be chosen
The keyword that word word is concentrated as the participle word of each grouping.The M can be positive integer, and value can be according to practical need
It asks and is configured.
In another embodiment, can to each grouping participle word concentrate participle word into advance one
Step screening further according to word frequency-rate of falling document, determines the keyword that the participle word of each grouping after the screening is concentrated.
The participle word that the participle word to each grouping is concentrated, which carries out further screening, can specifically include:It can be with
The number ratio for filtering out co-occurrence number and references object in the grouping is more than the participle word for presetting ratio, after being screened
The participle word collection of each grouping.The co-occurrence number can be used to indicate that obtain the number of the references object of the participle word.
For example, the corresponding references object of a label " sandy beach " is 100, wherein the text message of 80 references object is carried out at participle
" seabeach " this participle word can be obtained after reason, then, the co-occurrence number of the participle word " seabeach " can be 80.Pass through
Calculate co-occurrence number and the number ratio of references object, it is possible to determine that the participle word is in the text envelope of the references object of the grouping
Whether often occur in breath.If the ratio is more than default ratio, then it is considered that the participle word is in the grouping reference pair
Often occur in the text message of elephant.The default ratio can be determined according to actual conditions.Under normal conditions, it is described default
The value range of ratio can be [0.7,1].The participle word more by screening co-occurrence number can to determine to close
The participle word that each grouping participle word of keyword is concentrated is more representative.
It certainly, can also be in the text envelope of the references object to each grouping it should be noted that in actual mechanical process
After breath carries out word segmentation processing, the larger participle word of TF-IDF characteristic values is first chosen, then chosen altogether from the participle word of selection
Occurrence number and the number ratio of the grouping references object are more than the participle word of default ratio as keyword.
In another embodiment, it is described form the participle word collection of each grouping after, the method can be with
Including:Using the near synonym vocabulary in the industry corpus of the references object, near synonym are carried out to the participle word collection and are replaced
It changes, obtains replaced participle word collection.So, the keyword that the participle word for determining each grouping is concentrated, tool
Body can be:Determine the keyword that the replaced participle word of each grouping is concentrated.
S303:According to the keyword of each grouping of extraction and corresponding label, the label and keyword are formed
Correspondence.
By above-described embodiment, the correspondence of label and keyword can be provided, it, can be quick by the correspondence
The corresponding label of object is easily determined, so as to improve the efficiency of determining label.Meanwhile keyword corresponding with label is
After being handled by reference to the text message of object determine, identified keyword can embody distinguish the label it is corresponding
The ability of object, therefore it provides label and the correspondence of keyword can improve the accuracy rate of determining label.
The embodiment of the present application also provides a kind of method of the object search based on label.The method of described search object can be with
For searching for the object that label is determined.With reference to Fig. 4, the method for described search object may comprise steps of.
S401:The multiple labels of user are supplied to, receive the information that user selects the first label from the multiple label.
It is described be supplied to user label can be tourism industry label.It is described to be supplied in multiple labels of user,
Each label can correspond at least one object.The label of the object can be according to object tag determining in the embodiment of the present application
Method determine.
The information that user selects the first label from the multiple label can be received.
S402:The first label that user selects is sent to server, receive and show the server feedback with the
The corresponding at least one object of one label.
The first label that user selects can be sent to server.Server can be screened according to first label
Object determines the method for determining object tag using the application the object of label, can directly filter out object tag
In include the object of first label.
The object corresponding with the first label filtering out can be one or multiple.It is for example, it may be more
A object includes first label.
Client can receive at least one object corresponding with the first label, and show user.
In the method for the object search based on label that above-described embodiment provides, since object to be searched has been to determine mark
The object of label directly can go out object search according to label filtration, and search process is convenient and efficient.Since the application determines object mark
In the method for label, the accuracy rate of determining object tag is high, therefore, the knot searched for using the method for the application object search
Fruit accuracy rate is also high, meets user and searches for expectation.
With reference to Fig. 5, the embodiment of the present application also provides a kind of device of determining object tag.The dress of the determining object tag
Putting can include:Segment word determining module 501, candidate label determining module 502 and target labels determining module 503.
The participle word determining module 501 can be used for obtaining corresponding first text message of the first object, according to institute
It states the first text message and obtains first participle word collection corresponding with first object.Specifically, the participle word determines
Module 501 can be used for carrying out word segmentation processing to first text message, obtain several participle words;The participle word
Determining module 501 can be used for counting the participle word, determine participle word corresponding with the first object and participle
The frequency of word;It the participle word corresponding with the first object and segments the frequency of word and forms corresponding with the first object the
One participle word collection.
Wherein, first object be tourism industry merchandise items, first text message include it is following in extremely
Few one kind:Merchandise items title, merchandise items detail information, merchandise items attribute information.
Candidate's label determining module 502, can be used for the correspondence based on preset label and keyword, determines
The first participle word concentrate with the Keywords matching in the default correspondence successfully segment word and with it is described
The corresponding candidate label of participle word of successful match.The correspondence of the preset label and keyword can characterize one
Label and its corresponding keyword.One label can correspond to one or more keywords.One keyword can also correspond to one
A or multiple labels.
The target labels determining module 503 can be used for partly or entirely described candidate label being set as first pair
The target labels of elephant.Specifically, the target labels determining module 503 can be used for judging that the total number of the candidate label is
The total number of no the first subject object label less than or equal to the setting;If the determination result is YES, the target labels are true
All candidate labels are set as the target labels of the first object by cover half block 503;If judging result is no, the target mark
The part candidate label is set as the target labels of the first object according to default selection rule by label determining module 503.
With reference to Fig. 6, in another embodiment, the device of the determining object tag can also include:Near synonym table
Module 504 and participle word replacement module 505 are provided.
The near synonym table provides module 504, may be used to provide industry corpus, and the industry corpus includes pair
As the near synonym vocabulary in affiliated industry.
The participle word replacement module 505, can be used for using in the industry corpus belonging to first object
Near synonym vocabulary carries out near synonym replacement to the first participle word collection, obtains replaced first participle word collection.
So, the label determining module 502 is used for the correspondence based on preset label and keyword, determines described
First participle word is concentrated successfully segments word with the Keywords matching in the default correspondence, is specifically as follows:Institute
Label determining module 502 is stated for the correspondence based on preset label and keyword, determines that the participle word replaces mould
The replaced first participle word of block is concentrated successfully segments word with the Keywords matching in the default correspondence.
The embodiment of the present application also provides a kind of device for establishing tab indexes.Pass through the dress of the family tab indexes of the application
Embodiment is put, the correspondence of label and keyword can be provided.With reference to Fig. 7, the device for establishing tab indexes can wrap
It includes:References object acquisition module 701, grouping and keyword extracting module 702 and corresponding relation building module 703.
The references object acquisition module 701 can be used for obtaining the sample sets for including multiple references object.The sample
Concentrate the text message for including references object, the label of the references object and the references object.
The grouping and keyword extracting module 702, can be used for being grouped the references object, and described in utilization
The text message of references object extracts the keyword of each grouping.
The corresponding relation building module 703 can be used for the keyword and correspondence of each grouping according to extraction
Label, form the correspondence of the label and keyword.
The application also provides a kind of client, for being based on tag search object.The client can be PC machine, notes
This computer, tablet computer, mobile phone, intelligent self-service terminal, intelligent wearable device etc..With reference to Fig. 8, the client can wrap
It includes:Input unit 801, communication module 802, controller 803 and display 804.
The input unit 801 inputs information for receiving user.
In presently filed embodiment, the input equipment is the equipment to computer input data and information.Specifically
Ground can be keyboard, mouse, camera, scanner, light pen, writing input board, joystick, speech input device etc..
The communication module 802 is communicated to connect and is carried out data transmission for establishing.
In presently filed embodiment, communication module 802 can be set according to ICP/IP protocol, and in the protocol frame
Lower carry out network communication.Specifically, it can be mobile radio network communication chip, such as GSM, CDMA;It can also be
Wifi chips;It can also be Bluetooth chip.
The display 804, for displaying data.
In presently filed embodiment, the display 804 can be by specifically passing by certain electronic document
Transfer device is shown to the show tools that human eye is re-reflected on screen.Specifically, it can be cathode-ray tube display
(CRT), plasma display (PDP), liquid crystal display (LCD) etc..
The controller 803, for the display 804 to be controlled to show multiple labels;And control the input equipment 801
Receive the information that user selects the first label from the multiple label;The controller 803 is additionally operable to control the communication mould
Block 802 by the first label that user selects be sent to server and receive the server feedback it is corresponding with the first label extremely
A few object;The controller 803 is additionally operable to that the display 804 is controlled to show described corresponding with the first label at least one
A object.
In the embodiment of the present application, the label can be the label of tourism industry.
In presently filed embodiment, the processor 803 can be implemented in any suitable manner.It is for example, described
Processor 803 can take such as microprocessor or processor and storage can be performed by (micro-) processor it is computer-readable
Computer-readable medium, logic gate, switch, the application-specific integrated circuit (Application of program code (such as software or firmware)
Specific Integrated Circuit, ASIC), the form of programmable logic controller (PLC) and embedded microcontroller etc..This
Apply and be not construed as limiting.
Above-described embodiment provide determining object tag device, establish tab indexes device and client respectively with
The embodiment of the method for the determining object tag of the application, the embodiment of the method for establishing tab indexes and the search pair based on label
The embodiment of the method for elephant is corresponding, performed by concrete function explanation can be contrasted with the present processes embodiment,
It can realize the present processes embodiment and reach the technique effect of method embodiment.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow is programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming a digital display circuit " integrated " on a piece of PLD, designs and make without asking chip maker
Dedicated IC chip 2.Moreover, nowadays, substitution manually makes IC chip, and this programming is also used instead mostly
" logic compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development
Seemingly, and the source code before compiling also handy specific programming language is write, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed are most generally used at present
Integrated Circuit Hardware Description Language) and Verilog2.Those skilled in the art
It will be apparent to the skilled artisan that it only needs method flow slightly programming in logic and being programmed into integrated circuit with above-mentioned several hardware description languages
In, it is possible to it is readily available the hardware circuit for realizing the logical method flow.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer of computer readable program code (such as software or firmware) that device and storage can be performed by (micro-) processor can
Read medium, logic gate, switch, application-specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and embedded microcontroller, the example of controller include but not limited to following microcontroller
Device:ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, are deposited
Memory controller is also implemented as a part for the control logic of memory.
It is also known in the art that other than realizing controller in a manner of pure computer readable program code, it is complete
Entirely can by by method and step carry out programming in logic come controller with logic gate, switch, application-specific integrated circuit, may be programmed
The form of logic controller and embedded microcontroller etc. realizes identical function.Therefore this controller is considered one kind
Hardware component, and the structure that can also be considered as to the device for being used to implement various functions included in it in hardware component.Or
Even, the device for being used to implement various functions can be considered as either the software module of implementation method can be Hardware Subdivision again
Structure in part.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by having the function of certain product.
For convenience of description, it is divided into various units during description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit is realized can in the same or multiple software and or hardware during application.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can
It is realized by the mode of software plus required general hardware platform.Based on such understanding, the technical solution essence of the application
On the part that the prior art contributes can be embodied in the form of software product in other words, in a typical configuration
In, computing device includes one or more processors (CPU), input/output interface, network interface and memory.The computer is soft
Part product can include some instructions and use so that a computer equipment (can be personal computer, server or network
Equipment etc.) perform method described in certain parts of each embodiment of the application or embodiment.The computer software product can
To store in memory, memory may include the volatile memory in computer-readable medium, random access memory
(RAM) and/or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer
The example of readable medium.Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by
Any method or technique come realize information store.Information can be computer-readable instruction, data structure, the module of program or its
His data.The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM
(SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), fast flash memory bank or other memory techniques, CD-ROM are read-only
Memory (CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic rigid disk storage or
Other magnetic storage apparatus or any other non-transmission medium, available for storing the information that can be accessed by a computing device.According to
Herein defines, and computer-readable medium does not include of short duration computer readable media (transitory media), such as modulation
Data-signal and carrier wave.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Point just to refer each other, and the highlights of each of the examples are difference from other examples.Especially for system reality
For applying example, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
The application can be used in numerous general or special purpose computing system environments or configuration.Such as:Personal computer, clothes
Business device computer, handheld device or portable device, multicomputer system, the system based on microprocessor, are put laptop device
Top box, programmable consumer-elcetronics devices, network PC, minicomputer, mainframe computer, including any of the above system or equipment
Distributed computing environment etc..
The application can be described in the general context of computer executable instructions, such as program
Module.Usually, program module includes routines performing specific tasks or implementing specific abstract data types, program, object, group
Part, data structure etc..The application can also be put into practice in a distributed computing environment, in these distributed computing environment, by
Task is performed and connected remote processing devices by communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage device.
Although depicting the application by embodiment, it will be appreciated by the skilled addressee that the application there are many deformation and
Variation is without departing from spirit herein, it is desirable to which appended claim includes these deformations and changes without departing from the application's
Spirit.
Claims (19)
- A kind of 1. method of determining object tag, which is characterized in that including:Corresponding first text message of the first object is obtained, is obtained according to first text message corresponding with first object First participle word collection;Correspondence based on preset label and keyword determines that the first participle word is concentrated and the default corresponding pass Keywords matching in system successfully segments word and candidate label corresponding with the participle word of the successful match;Partly or entirely described candidate label is set as to the target labels of first object.
- 2. according to the method described in claim 1, it is characterized in that, the method further includes:Industry corpus is provided, the industry corpus includes the near synonym vocabulary in the industry belonging to object;It is described first participle word collection corresponding with first object is obtained according to first text message after, also wrap It includes:Using the near synonym vocabulary in the industry corpus belonging to first object, the first participle word collection is carried out near Adopted word is replaced, and obtains replaced first participle word collection;It is described to determine that the first participle word concentration successfully segments word with the Keywords matching in the default correspondence Language, specially:Determine the replaced first participle word concentrate with the Keywords matching in the default correspondence into The participle word of work(.
- 3. method according to claim 1 or 2, which is characterized in that first object is the merchandise items of tourism industry, First text message includes at least one of following:Merchandise items title, merchandise items detail information, merchandise items category Property information.
- 4. according to the method described in claim 3, it is characterized in that, the merchandise items attribute information include it is following at least It is a kind of:The corresponding sight spot address of merchandise items, the corresponding departure place of merchandise items, merchandise items corresponding travel time, commodity The corresponding mode of transportation of object, the corresponding expense of merchandise items, the corresponding sight spot feature of merchandise items.
- 5. according to the method described in claim 1, it is characterized in that, the correspondence of the preset label and keyword is built Cube method, including:The sample sets for including multiple references object are obtained, the sample sets include the label of references object, the references object And the text message of the references object;According to the label of the references object, the references object is grouped, and utilizes the text envelope of the references object Breath extracts the keyword of each grouping;According to the keyword of each grouping of extraction and corresponding label, label pass corresponding with keyword is formed System.
- 6. according to the method described in claim 5, it is characterized in that, the text message using the references object extracts respectively The keyword of a grouping, including:Word segmentation processing is carried out to the text message of references object described in each grouping, forms the participle word collection of each grouping;According to word frequency-rate of falling document, determine the keyword that the participle word of each grouping is concentrated, obtain each grouping Keyword.
- 7. according to the method described in claim 6, it is characterized in that, the label of the references object is based on the references object Affiliated industry setting;After the participle word collection of each grouping of formation, further include:Using the near synonym vocabulary in the industry corpus of the references object, near synonym are carried out to the participle word collection and are replaced It changes, obtains replaced participle word collection;The keyword that the participle word for determining each grouping is concentrated, specially:Determine each replaced point of grouping The keyword that word word is concentrated.
- 8. the method according to claim 2 or 7, which is characterized in that near synonym vocabulary in the industry corpus is built Cube method, including:Corpus information in acquisition corpus, determining participle word corresponding with the corpus information and the participle word The frequency;The corpus information is the corpus information of tourism industry, is specifically included at least one of following:The travel notes of passenger, trip Swim the recommended information of merchandise items, the recommended information of tourist attractions;The First Eigenvalue of the participle word of the corpus information is calculated, the similarity of the First Eigenvalue is less than second threshold Word is segmented as near synonym;The First Eigenvalue of the participle word includes:The real vector of the participle word;Using the highest participle word of the frequency near synonym as subject term, remaining participle word is as adjunct.
- 9. according to the method described in claim 1, it is characterized in that, described be set as the by partly or entirely described candidate label The target labels of an object, including:The total number of first subject object label is set;Judge whether the total number of the candidate label is less than or equal to the total number of the first subject object label of the setting;If the determination result is YES, all candidate labels are set as to the target labels of the first object;If alternatively, judging result It is no, the part candidate label is set as to the target labels of the first object according to default selection rule.
- A kind of 10. method for establishing tab indexes, which is characterized in that including:It obtains and includes the tally set of multiple references object and outturn sample collection;According to the label of the references object, the references object is grouped, and utilizes the text envelope of the references object Breath extracts the keyword of each grouping;According to the keyword of each grouping of extraction and corresponding label, label pass corresponding with keyword is formed System.
- 11. according to the method described in claim 10, it is characterized in that, the label of the references object is based on the reference pair It is set as affiliated industry;Industry belonging to the references object is tourism industry.
- It is 12. according to the method described in claim 10, it is characterized in that, described each using the text message extraction of references object The keyword of grouping, specifically includes:Word segmentation processing is carried out to the text message of references object described in each grouping, forms the participle word collection of each grouping;According to word frequency-rate of falling document, determine the keyword that the participle word of each grouping is concentrated, obtain each grouping Keyword.
- 13. according to the method for claim 12, which is characterized in that determine the pass that the participle word of each grouping is concentrated Before keyword, further include:The participle word concentrated to the participle word of each grouping is further screenedIt is described according to word frequency-rate of falling document, determine the keyword that the participle word of each grouping is concentrated, obtain described each The keyword of grouping, specially:According to word frequency-rate of falling document, determine that the participle word of each grouping after the screening is concentrated Keyword.
- A kind of 14. method based on tag search object, which is characterized in that including:The multiple labels of user are supplied to, receive the information that user selects the first label from the multiple label;It is described to be supplied to The label of user is the label of tourism industry;The first label that user selects is sent to server, receives and shows the corresponding with the first label of the server feedback At least one object.
- 15. according to the method for claim 14, which is characterized in that the server feedback it is corresponding with the first label extremely A few object includes:The object of first label is included in the label of object.
- 16. a kind of device of determining object tag, which is characterized in that including:Word determining module is segmented, for obtaining corresponding first text message of the first object, according to first text message Obtain first participle word collection corresponding with first object;First object is the merchandise items of tourism industry, described First text message includes at least one of following:Merchandise items title, merchandise items detail information, merchandise items attribute letter Breath;Candidate label determining module for the correspondence based on preset label and keyword, determines the first participle word Language is concentrated successfully segments word and the participle with the successful match with the Keywords matching in the default correspondence The corresponding candidate label of word;Target labels determining module, for partly or entirely described candidate label to be set as to the target mark of first object Label.
- 17. device according to claim 16, which is characterized in that further include:Near synonym table provides module, and for providing industry corpus, the industry corpus is included in the industry belonging to object Near synonym vocabulary;Word replacement module is segmented, for utilizing the near synonym vocabulary in the industry corpus belonging to first object, to institute It states first participle word collection and carries out near synonym replacement, obtain replaced first participle word collection;The label determining module is used for the correspondence based on preset label and keyword, determines the first participle word It concentrates and successfully segments word with the Keywords matching in the default correspondence, specially:The label determining module is used In the correspondence based on preset label and keyword, the participle replaced first participle word of word replacement module is determined Language is concentrated successfully segments word with the Keywords matching in the default correspondence.
- 18. a kind of device for establishing tab indexes, which is characterized in that including:References object acquisition module, for obtaining the sample sets for including multiple references object, the sample sets include reference pair As, the label of the references object and the text message of the references object;Grouping and keyword extracting module for being grouped to the references object, and utilize the text of the references object The keyword of each grouping of information extraction;Corresponding relation building module, keyword and corresponding label for each grouping according to extraction, described in formation The correspondence of label and keyword.
- 19. a kind of client, which is characterized in that including:Input unit inputs information for receiving user;Communication module is communicated to connect and is carried out data transmission for establishing;Display, for displaying data;Controller for the display to be controlled to show multiple labels, and controls the input equipment to receive user from described more The information of the first label is selected in a label;The controller is additionally operable to the first mark that the communication module is controlled to select user Sign and issue at least one object corresponding with the first label given server and receive the server feedback;The controller is also For the display to be controlled to show at least one object corresponding with the first label;The label is the label of tourism industry.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611197791.7A CN108228665A (en) | 2016-12-22 | 2016-12-22 | Determine object tag, the method and device for establishing tab indexes, object search |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611197791.7A CN108228665A (en) | 2016-12-22 | 2016-12-22 | Determine object tag, the method and device for establishing tab indexes, object search |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108228665A true CN108228665A (en) | 2018-06-29 |
Family
ID=62655944
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611197791.7A Pending CN108228665A (en) | 2016-12-22 | 2016-12-22 | Determine object tag, the method and device for establishing tab indexes, object search |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108228665A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110083678A (en) * | 2019-03-12 | 2019-08-02 | 平安科技(深圳)有限公司 | A kind of electric business platform goods matching method, device and readable storage medium storing program for executing |
CN110245350A (en) * | 2019-05-29 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Official documents and correspondence is rewritten and update method, device and equipment |
CN110263161A (en) * | 2019-05-29 | 2019-09-20 | 阿里巴巴集团控股有限公司 | A kind of processing method of information, device and equipment |
CN110532449A (en) * | 2019-08-30 | 2019-12-03 | 盈盛智创科技(广州)有限公司 | A kind of processing method of service profile, device, equipment and storage medium |
CN110688844A (en) * | 2019-08-22 | 2020-01-14 | 阿里巴巴集团控股有限公司 | Text labeling method and device |
CN110879858A (en) * | 2019-11-13 | 2020-03-13 | 上海易点时空网络有限公司 | Data processing method and device for problem distribution |
CN111353071A (en) * | 2018-12-05 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Label generation method and device |
CN112883150A (en) * | 2021-01-21 | 2021-06-01 | 平安科技(深圳)有限公司 | Method, device, equipment and storage medium for distinguishing trademark words from general words |
CN112989118A (en) * | 2021-02-04 | 2021-06-18 | 北京奇艺世纪科技有限公司 | Video recall method and device |
CN113011182A (en) * | 2019-12-19 | 2021-06-22 | 北京多点在线科技有限公司 | Method, device and storage medium for labeling target object |
CN113051253A (en) * | 2021-04-15 | 2021-06-29 | 广州云族佳科技有限公司 | Method and device for constructing tag database |
CN113312484A (en) * | 2021-06-10 | 2021-08-27 | 支付宝(杭州)信息技术有限公司 | Object tag processing method and device |
CN114201973A (en) * | 2022-02-15 | 2022-03-18 | 深圳博士创新技术转移有限公司 | Resource pool object data mining method and system based on artificial intelligence |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060242135A1 (en) * | 2005-04-20 | 2006-10-26 | Microsoft Corporation | System and method for personalized search |
CN103064969A (en) * | 2012-12-31 | 2013-04-24 | 武汉传神信息技术有限公司 | Method for automatically creating keyword index table |
CN103442271A (en) * | 2013-09-11 | 2013-12-11 | 东莞市远峰科技有限公司 | Classified program searching method used for TV (Television) box |
CN105740404A (en) * | 2016-01-28 | 2016-07-06 | 上海晶赞科技发展有限公司 | Label association method and device |
CN105893478A (en) * | 2016-03-29 | 2016-08-24 | 广州华多网络科技有限公司 | Tag extraction method and equipment |
-
2016
- 2016-12-22 CN CN201611197791.7A patent/CN108228665A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060242135A1 (en) * | 2005-04-20 | 2006-10-26 | Microsoft Corporation | System and method for personalized search |
CN103064969A (en) * | 2012-12-31 | 2013-04-24 | 武汉传神信息技术有限公司 | Method for automatically creating keyword index table |
CN103442271A (en) * | 2013-09-11 | 2013-12-11 | 东莞市远峰科技有限公司 | Classified program searching method used for TV (Television) box |
CN105740404A (en) * | 2016-01-28 | 2016-07-06 | 上海晶赞科技发展有限公司 | Label association method and device |
CN105893478A (en) * | 2016-03-29 | 2016-08-24 | 广州华多网络科技有限公司 | Tag extraction method and equipment |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111353071A (en) * | 2018-12-05 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Label generation method and device |
CN110083678A (en) * | 2019-03-12 | 2019-08-02 | 平安科技(深圳)有限公司 | A kind of electric business platform goods matching method, device and readable storage medium storing program for executing |
CN110245350A (en) * | 2019-05-29 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Official documents and correspondence is rewritten and update method, device and equipment |
CN110263161A (en) * | 2019-05-29 | 2019-09-20 | 阿里巴巴集团控股有限公司 | A kind of processing method of information, device and equipment |
CN110263161B (en) * | 2019-05-29 | 2023-09-26 | 创新先进技术有限公司 | Information processing method, device and equipment |
CN110245350B (en) * | 2019-05-29 | 2023-04-07 | 创新先进技术有限公司 | Method, device and equipment for rewriting and updating file |
CN110688844A (en) * | 2019-08-22 | 2020-01-14 | 阿里巴巴集团控股有限公司 | Text labeling method and device |
CN110532449B (en) * | 2019-08-30 | 2022-05-31 | 盈盛智创科技(广州)有限公司 | Method, device, equipment and storage medium for processing service document |
CN110532449A (en) * | 2019-08-30 | 2019-12-03 | 盈盛智创科技(广州)有限公司 | A kind of processing method of service profile, device, equipment and storage medium |
CN110879858A (en) * | 2019-11-13 | 2020-03-13 | 上海易点时空网络有限公司 | Data processing method and device for problem distribution |
CN113011182B (en) * | 2019-12-19 | 2023-10-03 | 北京多点在线科技有限公司 | Method, device and storage medium for labeling target object |
CN113011182A (en) * | 2019-12-19 | 2021-06-22 | 北京多点在线科技有限公司 | Method, device and storage medium for labeling target object |
WO2022156115A1 (en) * | 2021-01-21 | 2022-07-28 | 平安科技(深圳)有限公司 | Trademark term and general term distinguishing method and apparatus, device, and storage medium |
CN112883150B (en) * | 2021-01-21 | 2023-07-25 | 平安科技(深圳)有限公司 | Method, device, equipment and storage medium for distinguishing trademark words from general words |
CN112883150A (en) * | 2021-01-21 | 2021-06-01 | 平安科技(深圳)有限公司 | Method, device, equipment and storage medium for distinguishing trademark words from general words |
CN112989118B (en) * | 2021-02-04 | 2023-08-18 | 北京奇艺世纪科技有限公司 | Video recall method and device |
CN112989118A (en) * | 2021-02-04 | 2021-06-18 | 北京奇艺世纪科技有限公司 | Video recall method and device |
CN113051253A (en) * | 2021-04-15 | 2021-06-29 | 广州云族佳科技有限公司 | Method and device for constructing tag database |
CN113312484A (en) * | 2021-06-10 | 2021-08-27 | 支付宝(杭州)信息技术有限公司 | Object tag processing method and device |
CN113312484B (en) * | 2021-06-10 | 2023-06-20 | 支付宝(杭州)信息技术有限公司 | Object tag processing method and device |
CN114201973A (en) * | 2022-02-15 | 2022-03-18 | 深圳博士创新技术转移有限公司 | Resource pool object data mining method and system based on artificial intelligence |
CN114201973B (en) * | 2022-02-15 | 2022-06-07 | 深圳博士创新技术转移有限公司 | Resource pool object data mining method and system based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108228665A (en) | Determine object tag, the method and device for establishing tab indexes, object search | |
JP7175276B2 (en) | Method, Client and Server for Displaying Service Objects and Processing Map Data | |
CN111507104B (en) | Method and device for establishing label labeling model, electronic equipment and readable storage medium | |
CN108509436A (en) | A kind of method, apparatus and computer storage media of determining recommended | |
CN108108373A (en) | A kind of name-matches method and device | |
CN107766349B (en) | Method, device, equipment and client for generating text | |
CN110019903A (en) | Generation method, searching method and terminal, the system of image processing engine component | |
CN112507068A (en) | Document query method and device, electronic equipment and storage medium | |
CN105608113B (en) | Judge the method and device of POI data in text | |
CN112541359B (en) | Document content identification method, device, electronic equipment and medium | |
CN109448793A (en) | The interest field identification of gene order, retrieval and infringement determination method, system | |
CN107391545A (en) | A kind of method classified to user, input method and device | |
CN113220835B (en) | Text information processing method, device, electronic equipment and storage medium | |
CN110209810A (en) | Similar Text recognition methods and device | |
CN109388801A (en) | The determination method, apparatus and electronic equipment of similar set of words | |
CN114595686A (en) | Knowledge extraction method, and training method and device of knowledge extraction model | |
CN107402945A (en) | Word stock generating method and device, short text detection method and device | |
CN110363190A (en) | A kind of character recognition method, device and equipment | |
CN113268615A (en) | Resource label generation method and device, electronic equipment and storage medium | |
CN112380847A (en) | Interest point processing method and device, electronic equipment and storage medium | |
CN106934006B (en) | Page recommendation method and device based on multi-branch tree model | |
CN113762109B (en) | Training method of character positioning model and character positioning method | |
CN107329964A (en) | A kind of text handling method and device | |
CN112528146B (en) | Content resource recommendation method and device, electronic equipment and storage medium | |
CN107688604A (en) | Data answering processing method, device and server |
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: 20180629 |
|
RJ01 | Rejection of invention patent application after publication |