CN110020151A - A kind of data processing method, device, electronic equipment and storage medium - Google Patents
A kind of data processing method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110020151A CN110020151A CN201711252207.8A CN201711252207A CN110020151A CN 110020151 A CN110020151 A CN 110020151A CN 201711252207 A CN201711252207 A CN 201711252207A CN 110020151 A CN110020151 A CN 110020151A
- Authority
- CN
- China
- Prior art keywords
- keyword
- site information
- term vector
- information
- vector
- 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.)
- Granted
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
-
- 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
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 embodiment of the invention provides a kind of data processing method, device, electronic equipment and storage mediums, to improve the accuracy that correlation determines.The method includes: to constitute the associated path of keyword and site information according to keyword and site information in target search result;According to the associated path and preset model, the first term vector of keyword and the second term vector of site information are determined;According to first term vector and the second term vector, the correlation of the keyword and site information is calculated.Without artificial classification processing, the accuracy that the degree of correlation determines is effectively improved.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of data processing method, a kind of data processing equipment,
A kind of electronic equipment and a kind of storage medium.
Background technique
With the development of network technology, various information needed for more and more users pass through network inquiry, such as inquire
The films and television programs of hot broadcast, the performance of hot game and extensive stock, seniority among brothers and sisters etc., so as to the result auxiliary based on inquiry
Carry out the selection of information.
It is fed back after usually needing to be ranked up query result in inquiry, some modes are beaten the quality of website
Point, but this mode does not account for the correlation between query word and website, ranking results may not meet the requirement of user,
And cause the reduction of search efficiency.And the mode of correlation is usually to determine phase according to classification between some determining keywords and website
Guan Xing, i.e., calculate the correlation of query word and website by the matching degree of classification, but the classification and classification of this mode
It is generally characterized by manually being arranged, the accuracy of classification can not be guaranteed, therefore the accuracy of correlation calculations is difficult to protect
Card, the sequence accuracy executed according to the correlation are relatively low.
Summary of the invention
The embodiment of the present invention is determined the technical problem to be solved is that a kind of data processing method is provided with improving correlation
Accuracy.
Correspondingly, the embodiment of the invention also provides a kind of data processing equipment, a kind of electronic equipment and a kind of storage Jie
Matter, to guarantee the implementation and application of the above method.
To solve the above-mentioned problems, the embodiment of the invention discloses a kind of data processing method, the method include: according to
According to keyword in target search result and site information, the associated path of keyword and site information is constituted;According to the association
Path and preset model determine the first term vector of keyword and the second term vector of site information;According to first word to
Amount and the second term vector, calculate the correlation of the keyword and site information.
Optionally, keyword and site information in the foundation target search result, composition keyword and site information
Associated path, comprising: determine multiple target search results, and extract keyword and the pass respectively from each target search result
The corresponding site information of keyword;Associated path is constituted using the keyword and the corresponding relationship of site information.
Optionally, described that associated path is constituted using the keyword and the corresponding relationship of site information, comprising: according to institute
The corresponding relationship for stating keyword and site information connects each keyword with corresponding site information, constitute the keyword and
The bigraph (bipartite graph) of site information;The associated path of the multiple keywords and site information is determined according to bigraph (bipartite graph).
Optionally, the associated path that the multiple keywords and site information are determined according to bigraph (bipartite graph), comprising: foundation
Keyword and site information are connected by random walk mode, generate multiple associated paths by the bigraph (bipartite graph).
Optionally, described according to associated path and preset model, determine the first term vector and site information of keyword
Second term vector, comprising: generate vector information according to the associated path, wherein the vector information includes the of keyword
Second path vector of one path vector and site information;The vector information is input in preset model, keyword is obtained
The first term vector and site information the second term vector.
Optionally, first term vector of foundation and the second term vector, it is related to site information to calculate the keyword
Property, comprising: selection keyword and site information;First term vector of keyword and the second term vector of site information are subjected to phase
Closing property calculates, and obtains the correlation between the keyword and site information.
Optionally, further includes: when executing setting business by query word, it is corresponding that query word is obtained from query result
Website information, wherein the setting business comprises at least one of the following: searching service recommends business;Using the query word as
Keyword inquires the correlation of corresponding keyword and site information using the website information as site information.
The embodiment of the invention also provides a kind of data processing equipments, comprising: path determination module, for being searched according to target
Keyword and site information in hitch fruit constitute the associated path of keyword and site information;Term vector determining module, for according to
According to the associated path and preset model, the first term vector of keyword and the second term vector of site information are determined;Correlation
Computing module, for calculating the correlation of the keyword and site information according to first term vector and the second term vector.
Optionally, the path determination module, comprising: data extracting sub-module, for determining multiple target search results,
And extract keyword and the corresponding site information of the keyword respectively from each target search result;Coordinates measurement submodule,
For constituting associated path using the corresponding relationship of the keyword and site information.
Optionally, the coordinates measurement submodule, comprising: bigraph (bipartite graph) generation unit, for according to the keyword and station
The corresponding relationship of point information, each keyword is connected with corresponding site information, constitutes the two of the keyword and site information
Portion's figure;Path determining unit, for determining the associated path of the multiple keywords and site information according to bigraph (bipartite graph).
Optionally, path determining unit, for according to the bigraph (bipartite graph), by random walk mode by keyword and website
Message linkage generates multiple associated paths.
Optionally, the term vector determining module, for generating vector information according to the associated path, wherein described
Vector information includes the second path vector of the first path vector sum site information of keyword;The vector information is input to
In preset model, the first term vector of keyword and the second term vector of site information are obtained.
Optionally, the correlation calculations module, for selecting keyword and site information;By the first word of keyword to
Second term vector of amount and site information carries out correlation calculations, obtains the correlation between the keyword and site information.
Optionally, further includes: dependence query module, for being tied from inquiry when executing setting business by query word
The corresponding website information of query word is obtained in fruit, wherein the setting business comprises at least one of the following: searching service, recommendation
Business;Corresponding keyword and website letter are inquired using the website information as site information using the query word as keyword
The correlation of breath.
The embodiment of the invention also provides a kind of readable storage medium storing program for executing, which is characterized in that the finger in the storage medium
When enabling the processor execution by electronic equipment, so that electronic equipment is able to carry out the data as described in any in the embodiment of the present invention
Processing method.
The embodiment of the invention also provides a kind of electronic equipment, which is characterized in that include memory and one or
More than one program, perhaps more than one program is stored in memory and is configured to by one or one for one of them
It includes the instruction for performing the following operation that a above processor, which executes the one or more programs: being searched according to target
Keyword and site information in hitch fruit constitute the associated path of keyword and site information;According to the associated path and in advance
If model, the first term vector of keyword and the second term vector of site information are determined;According to first term vector and second
Term vector calculates the correlation of the keyword and site information.
Optionally, keyword and site information in the foundation target search result, composition keyword and site information
Associated path, comprising: determine multiple target search results, and extract keyword and the pass respectively from each target search result
The corresponding site information of keyword;Associated path is constituted using the keyword and the corresponding relationship of site information.
Optionally, described that associated path is constituted using the keyword and the corresponding relationship of site information, comprising: according to institute
The corresponding relationship for stating keyword and site information connects each keyword with corresponding site information, constitute the keyword and
The bigraph (bipartite graph) of site information;The associated path of the multiple keywords and site information is determined according to bigraph (bipartite graph).
Optionally, the associated path that the multiple keywords and site information are determined according to bigraph (bipartite graph), comprising: foundation
Keyword and site information are connected by random walk mode, generate multiple associated paths by the bigraph (bipartite graph).
Optionally, described according to associated path and preset model, determine the first term vector and site information of keyword
Second term vector, comprising: generate vector information according to the associated path, wherein the vector information includes the of keyword
Second path vector of one path vector and site information;The vector information is input in preset model, keyword is obtained
The first term vector and site information the second term vector.
Optionally, first term vector of foundation and the second term vector, it is related to site information to calculate the keyword
Property, comprising: selection keyword and site information;First term vector of keyword and the second term vector of site information are subjected to phase
Closing property calculates, and obtains the correlation between the keyword and site information.
Optionally, executing the one or more programs by one or more than one processor includes to be also used to
The instruction performed the following operation: when executing setting business by query word, the corresponding net of query word is obtained from query result
Location information, wherein the setting business comprises at least one of the following: searching service recommends business;Using the query word as pass
Keyword inquires the correlation of corresponding keyword and site information using the website information as site information.
The embodiment of the present invention includes following advantages:
The embodiment of the present invention can constitute keyword and site information according to keyword in target search result and site information
Associated path, so that the associated path of keyword and site information is established according to a large amount of search results, then according to the pass
Join path and preset model, determines the first term vector of keyword and the second term vector of site information, and then calculate keyword
The accuracy that the degree of correlation determines is effectively improved without artificial classification processing with the correlation of site information.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of data processing method embodiment of the invention;
Fig. 2 is a kind of schematic diagram of associated path in the embodiment of the present invention;
Fig. 3 is a kind of schematic diagram of bigraph (bipartite graph) in the embodiment of the present invention;
Fig. 4 is the step flow chart of another data processing method embodiment of the invention;
Fig. 5 is a kind of structural block diagram of data processing equipment embodiment of the invention;
Fig. 6 is the structural block diagram of another data processing equipment embodiment of the invention;
Fig. 7 is the structural block diagram of coordinates measurement submodule in another data processing equipment embodiment of invention;
Fig. 8 is a kind of structural block diagram of electronic equipment for data processing shown according to an exemplary embodiment;
Fig. 9 is the structural schematic diagram of server in the embodiment of the present invention.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Referring to Fig.1, a kind of step flow chart of data processing method embodiment of the invention is shown, can specifically include
Following steps:
Step 102, according to keyword and site information in target search result, the association of keyword and site information is constituted
Path.
The association that search result is data basis to construct keyword and website can be used in the embodiment of the present invention.Wherein, mesh
Mark search result refers to the highest N number of search result of correlation in keyword and search result, can determine by various modes;
Keyword is the query word for executing the business such as search, inquiry, recommendation;Website, that is, website, site information refer in search result
The identification information of website, such as station address;Associated path refers to relevant keyword and the path that site information is constituted, and closes
Joining path can be random by keyword and its corresponding site information or according to certain rule series connection, such as two keywords and by same
One site information series connection, two site information can also be connected by the same keyword, i.e., two neighboring section in associated path
Point be have it is associated.Two neighboring node one is keyword in the associated path, another is site information, then two
Keyword is connected by site information, and two site information are connected also by keyword, a kind of example of associated path such as Fig. 2 institute
Show, which is keyword A1- site information B1- keyword A2- site information B2- ...-keyword An- site information
Bn……。
Keyword query can be obtained based on the inquiry log of search engine, such as select million at random from inquiry log
The keyword of grade, millions.Then search engine is crawled search result and is therefrom obtained target search result using the keyword,
Such as using the search result of homepage as target search result, N search result, can as target search result etc. before for another example obtaining
To be determined according to demand, so as to obtain the corresponding site information of the keyword from each search result, and then for every
A keyword corresponds to multiple site information, the associated path of keyword and site information is then established according to certain algorithm, i.e.,
By each keyword and site information to association, corresponding associated path is formed.
Wherein, search engine refers to according to certain strategy, collects letter from internet with specific computer program
Breath provides retrieval service for user, retrieval is obtained relevant information and shows user after carrying out tissue and processing to information
System.Common search engine includes Baidu (https: //www.baidu.com), search dog search (https: //
Www.sogo.com/) etc..The query word or keyword that user is inputted in a search engine are represented by query.Website letter
Breath is in the query result that search engine returns, and site information belonging to each webpage is represented by site, such as a result
Url=http: //www.jianpu.cn/g/zh/zhoujielun.htm, then site=www.jianpu.cn.
Step 104, according to the associated path and preset model, the first term vector and site information of keyword are determined
Second term vector.
Preset model is the model for training term vector, wherein model can also regard a kind of data acquisition system as, be according to number
It is constructed according to mathematical model, mathematical model is the science or engineering model with mathematical logic method and mathematics language constructing, mathematics
Model is for the feature or quantity dependence referring to certain things system, using mathematical linguistics, briefly or approximate earth's surface
A kind of mathematic(al) structure stated out, this mathematic(al) structure are the pure relationship knots that certain system come is depicted by means of mathematic sign
Structure.The skip-gram model that such as preset model is the language model of neural network, word2vec.
Preset model can be trained according to the associated path, so as to obtain the first term vector and website of keyword
Second term vector of information.Wherein, the vector information of each keyword, site information can be determined according to the associated path, then will
The vector information, which is input in preset model, carries out model training, so as to obtain the first term vector and website of each keyword
Second term vector of information.
Step 106, according to first term vector and the second term vector, it is related to site information to calculate the keyword
Property.
For any two keyword and site information, can using keyword the first term vector and site information the
Two term vectors calculate correlation, to obtain the correlation between any two keyword and site information.
To in the business such as being inquired, being searched for, is recommended, for the corresponding query result of query word, one to sort
A dimension can correlation between keyword and site information to improve the accuracy of sequence improve treatment effeciency.
To sum up, the association of keyword and site information can be constituted according to keyword in target search result and site information
Path, so that the associated path of keyword and site information is established according to a large amount of search results, then according to the associated path
And preset model, determine the first term vector of keyword and the second term vector of site information, and then calculate keyword and website
The correlation of information effectively improves the accuracy that similarity determines without artificial classification processing.And then according to the correlation
When being ranked up, the accuracy of sequence can be effectively improved.
In the embodiment of the present application, it is language in natural language processing that term vector (Word Embedding), which is also referred to as word insertion,
Say the general designation of model and representative learning technology.For conceptive, it refers to the higher-dimension sky the quantity that a dimension is all words
Between be embedded into the much lower vector row space of a dimension, each word or phrase are mapped as the vector in real number field.
Natural language processing (Neuro-Linguistic Programming, NLP) is computer science, artificial intelligence, linguistics pass
Infuse the field of the interaction between computer and the mankind (nature) language.It, which studies to be able to achieve between people and computer, uses nature
The various theory and methods of language progress efficient communication.Natural language processing be one melt linguistics, computer science, mathematics in
The science of one.
It is described according to keyword and site information in target search result in an alternative embodiment of the invention, it constitutes and closes
The associated path of keyword and site information, comprising: determine multiple target search results, and mentioned respectively from each target search result
Take keyword and the corresponding site information of the keyword;It is associated with using the keyword with the corresponding relationship of site information composition
Path.The corresponding search result of keyword can be crawled using search engine, target search knot is then extracted from search result
Fruit, then for the corresponding site information of keyword is extracted in each target search result, to obtain each keyword and website letter
The corresponding relationship of breath, the corresponding relationship according to keyword search to target search result in have site information determine, characterization
There is relevance between the keyword and site information.So as to establish the pass of keyword and site information according to the corresponding relationship
Join path, so that each keyword and site information are together in series.
Wherein, described that associated path is constituted using the keyword and the corresponding relationship of site information, comprising: according to described in
Each keyword is connected with corresponding site information, constitutes the keyword and station by the corresponding relationship of keyword and site information
The bigraph (bipartite graph) of point information;The associated path of multiple keywords and site information is determined according to bigraph (bipartite graph).According to the keyword and
The corresponding relationship of site information can connect each keyword with corresponding site information, i.e., a keyword corresponds to multiple stations
Point information, and a site information also may belong to multiple keywords, therefore will connect between keyword, site information, constitutes and closes
The bigraph (bipartite graph) of keyword and site information, then keyword and site information constitute the node of the bigraph (bipartite graph).Then to appoint in bigraph (bipartite graph)
Meaning node is starting point migration between the node of bigraph (bipartite graph), may make up an associated path, may make up a plurality of pass based on the bigraph (bipartite graph)
Join path.
Such as: the corresponding site information of keyword " Zhou Jielun ": www.a.com, www.b.com;Keyword " simple Love letter
The corresponding site information of spectrum ": www.a.com, www.b.com, www.c.com, www.e.com;The corresponding station of keyword " guitar spectrum "
Point information: www.c.com, www.d.com;Keyword " music score of Chinese operas is complete works of " corresponding site information: www.c.com, www.d.com,
www.e.com.It then may make up bigraph (bipartite graph) as shown in Figure 3.
A plurality of associated path then may make up based on the bigraph (bipartite graph), such as an associated path are as follows: Zhou Jielun-www.a.com- letter
Single love numbered musical notation-www.e.com- music score of Chinese operas complete works-www.d.com- ... etc.;A for another example paths are as follows: www.b.com- weeks Jie Lun-
Www.a.com- simple Love numbered musical notation-www.c.com- guitar spectrum-www.d.com- ... etc..
Wherein, bigraph (bipartite graph) is one of graph theory model, if G=(V, E) is a non-directed graph, if vertex V is divisible
For two mutually disjoint subsets (A, B), and two vertex i and j associated by each edge (i, j) in figure are belonging respectively to this
Two different vertex sets (i in A, j in B), then figure G is referred to as a bipartite graph (or bigraph (bipartite graph)).
So as to constitute bigraph (bipartite graph) based on the corresponding relationship of keyword and site information, and then obtain keyword and website
The path that information is constituted, convenient for the conversion of vector.
Referring to Fig. 4, the step flow chart of another data processing method embodiment of the invention is shown, specifically can wrap
Include following steps:
Step 402, multiple target search results are determined, and extract from each target search result keyword and described respectively
The corresponding site information of keyword.
Keyword query can be obtained based on the inquiry log of search engine, such as select million at random from inquiry log
The keyword of grade, millions.Then search engine is crawled search result and is therefrom obtained target search result using the keyword,
Such as using the search result of homepage as target search result, N search result, can as target search result etc. before for another example obtaining
To be determined according to demand.Site information therein is extracted for each search result again, as the corresponding website letter of the keyword
Breath, to obtain the corresponding multiple site information of a keyword, also, since a site information may be by multiple keywords
It searches, therefore a site information can also correspond to more keywords.
Step 404, the corresponding relationship according to the keyword and site information, by each keyword and corresponding site information
Connection, constitutes the bigraph (bipartite graph) of the keyword and site information.
After getting keyword and its corresponding site information by target search result, it can believe according to keyword and website
The corresponding relationship of breath connects each keyword with corresponding site information, i.e., related site information and keyword is connected
Get up.Shown in example as above, by keyword " Zhou Jielun " respectively with site information: www.a.com, www.b.com are connected, will be crucial
Word " simple Love numbered musical notation " difference site information: www.a.com, www.b.com, www.c.com, www.e.com connection, to build
The association of Zhou Jielun-www.a.com- simple Love numbered musical notation is stood, and same type of information will not be straight in the connection procedure
Connect connected, i.e., two keywords will not be connected directly, and two site information will not be connected directly, but keyword connection website letter
Breath, to constitute corresponding bigraph (bipartite graph), an example is as shown in Figure 3.
Step 406, the associated path of the multiple keywords and site information is determined according to bigraph (bipartite graph).
Then node can be arbitrarily chosen from the bigraph (bipartite graph) as starting point, come up based on the starting point in bigraph (bipartite graph) middle reaches
To the associated path of keyword and site information, one or more associations path is can be obtained in one of starting point, and in bigraph (bipartite graph)
Multiple nodes can be chosen as starting point, so that multiple associated paths can be obtained by a bigraph (bipartite graph).Wherein in bigraph (bipartite graph) middle reaches
The mode walked can be to be a variety of, and such as according to certain regular migration, for another example random walk etc. can be according to demand determination.
In one alternative embodiment, the associated path that multiple keywords and site information are determined according to bigraph (bipartite graph), packet
It includes: according to the bigraph (bipartite graph), keyword and site information being connected by random walk mode, generate multiple associated paths.If
By random walk mode, then node can be chosen as starting point, then according to the association random walk of bigraph (bipartite graph) interior joint, from
And keyword and site information are connected, generate corresponding associated path.
Wherein, random walk (Random Walk) refers to that the conserved quantity of any random walker institute band all respectively corresponds to
A diffusive transport law close to Brownian movement be the ideal mathematical state of Brownian movement, the embodiment of the present application can be based on
Bigraph (bipartite graph) runs Random Walk Algorithm and generates associated path.
Step 408, vector information is generated according to the associated path, wherein the vector information includes the of keyword
Second path vector of one path vector and site information.
Then the vector that keyword and site information can be determined by multiple associated paths, can be according to the associated path
Generate vector information, the second path vector of the first path vector sum preset model including keyword, wherein can be for each
Keyword obtains its first path vector, and obtains its second path vector for each site information.
Step 410, the vector information is input in preset model, obtains the first term vector and website letter of keyword
Second term vector of breath.
The training of preset model is carried out using associated path as training data, such as by the of keyword each in associated path
One path vector and the second path vector of site information are separately input in preset model.To the training preset model, hold
The corresponding iterative process of row model, so as to which the first term vector and site information of each keyword can be obtained based on this model
The second term vector.Thus each keyword and its corresponding site information for above-mentioned selection, it can be respectively according to corresponding
Vector indicates.The first term vector and the second term vector are to be referred to as in the embodiment of the present invention, for distinguishing characterization keyword and website
The vector of information.
Such as according to the skip-gram model in word2vec, keyword query and site information site are expressed as n
The form of dense vector is tieed up, and then acquires the correlation of query and site.Wherein, skip-gram one kind is for training term vector
Model, the term vector of context in certain window can be predicted according to input term vector, consequently facilitating determine keyword, stand
The term vector of point information.
Step 412, keyword and site information are selected.
Step 414, the first term vector of keyword and the second term vector of site information are subjected to correlation calculations, obtained
Correlation between the keyword and site information.
After the second term vector of the first term vector and site information that obtain each keyword, keyword and station can be chosen
Point information, then carries out correlation calculations by the first term vector of keyword and the second term vector of site information, obtains phase
Closing property value, so that it is determined that the correlation between any two keyword and site information out.
The calculation of correlation can be applied in various scenes between above-mentioned keyword and site information, be applicable in scene packet
Include but be not limited to search engine, recommender system etc., keyword and site information are indicated by way of vector, thus based on to
Amount calculates the correlation of the two, to be added in the scenes such as search, recommendation as a continuous feature, preferably optimization is searched
Suo Xiaoguo.When executing setting business by query word, the corresponding website information of query word is obtained from query result, wherein
The setting business comprises at least one of the following: searching service recommends business;It, will be described using the query word as keyword
Website information inquires the correlation of corresponding keyword and site information as site information.
Such as in search inquiry scene, after user inputs keyword, search engine is based on the keyword and scans for, and obtains
Corresponding search result, to believe website in the keyword and search result during being ranked up to search result
The correlation of breath combines the correlation of above-mentioned determination and other modes as one of sort by scan for result
Sequence.The relevance values between each keyword and site information can be stored in advance in actual treatment in the database, it can also be
The first term vector of each keyword and the second term vector of site information are stored in database, to obtain when needed corresponding
The first term vector and the second term vector calculate relevance values, as one of sort by number.
Similar with search inquiry scene in recommending scene, recommendation results matched for recommended keywords are applied, it can
The correlation for determining site information in keyword and recommendation results, one of the sort by as recommendation results, thus by searching
The accuracy of feedback result, improves treatment effeciency in the scenes such as rope inquiry, recommendation.
The embodiment of the present invention is this to associate two things by way of figure, using random walk strategy, generates
The vector form of two things, so as to directly calculate degree of correlation, this scheme is suitable for many emerging internets and produces
Product.For example news is recommended, the vector of user and news, such as advertisement CTR can be generated in we, can be by user and advertisement vector
Change etc..
The embodiment of the present invention excavates keyword query in combination with technologies such as the true intention of user and natural language processings
With the direct relation of site information site, the correlation calculations method of new slave query to site a kind of is provided.Pass through machine
Query and site vectorization is made it in same semantic space, by the correlation such as cosine for calculating vector by the method for study
Similarity, to improve the accuracy of similarity between query and site.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method
It closes, but those skilled in the art should understand that, embodiment of that present invention are not limited by the describe sequence of actions, because according to
According to the embodiment of the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and the related movement not necessarily present invention is implemented
Necessary to example.
The embodiment of the invention also provides a kind of input units, are applied to terminal device, and the terminal device, which has, to be touched
Screen and pressure sensitive device, the pressure sensitive device can perceive the pressure information operated on touch screen.
Referring to Fig. 5, show a kind of structural block diagram of data arrangement Installation practice of the invention, can specifically include as
Lower module:
Path determination module 502, for constituting keyword and station according to keyword and site information in target search result
The associated path of point information.
Term vector determining module 504, for according to the associated path and preset model, determine the first word of keyword to
Second term vector of amount and site information.
Correlation calculations module 506, for according to first term vector and the second term vector, calculate the keyword and
The correlation of site information.
To sum up, according to keyword and site information in target search result, the association road of keyword and site information is constituted
Diameter is associated with to establish keyword according to a large amount of search results with site information, then according to the associated path and default mould
Type determines the first term vector of keyword and the second term vector of site information, thus by keyword and website all in accordance with vector
Form indicates, and then it is true to effectively improve similarity without artificial classification processing for the correlation for calculating keyword and site information
Fixed accuracy.
Referring to Fig. 6, the structural block diagram of another data arrangement Installation practice of the invention is shown, can specifically include
Following module:
Path determination module 502, for constituting keyword and station according to keyword and site information in target search result
The associated path of point information.
Term vector determining module 504, for according to the associated path and preset model, determine the first word of keyword to
Second term vector of amount and site information.
Correlation calculations module 506, for according to first term vector and the second term vector, calculate the keyword and
The correlation of site information.
Dependence query module 508, for obtaining inquiry from query result when executing setting business by query word
The corresponding website information of word, wherein the setting business comprises at least one of the following: searching service recommends business;It is looked into described
Word is ask as keyword and inquires the correlation of corresponding keyword and site information using the website information as site information.
Wherein, the path determination module 502, comprising: data extracting sub-module 5022 and coordinates measurement submodule 5024,
Wherein:
Data extracting sub-module 5022, for determining multiple target search results, and from each target search result respectively
Extract keyword and the corresponding site information of the keyword;
Coordinates measurement submodule 5024, for being associated with road with the corresponding relationship of site information composition using the keyword
Diameter.
The coordinates measurement submodule 5024 as shown in Figure 7, comprising: bigraph (bipartite graph) generation unit 50242 and path determine
Unit 50244, in which:
Bigraph (bipartite graph) generation unit 50242, for the corresponding relationship according to the keyword and site information, by each keyword
It is connected with corresponding site information, constitutes the bigraph (bipartite graph) of the keyword and site information;
Path determining unit 50244, for determining the association road of multiple keywords and site information according to bigraph (bipartite graph)
Diameter.
Wherein, the path determining unit 50244 is used for according to the bigraph (bipartite graph), will be crucial by random walk mode
Word and site information series connection, generate multiple associated paths.
The term vector determining module 504, for generating vector information according to the associated path, wherein the vector
Information includes the second path vector of the first path vector sum site information of keyword;The vector information is input to default
In model, the first term vector of keyword and the second term vector of site information are obtained.
The correlation calculations module 506, for selecting keyword and site information;By the first term vector of keyword and
Second term vector of site information carries out correlation calculations, obtains the correlation between the keyword and site information.
The calculation of correlation can be applied in various scenes between above-mentioned keyword and site information, be applicable in scene packet
Include but be not limited to search engine, recommender system etc., keyword and site information are indicated by way of vector, thus based on to
Amount calculates the correlation of the two, to be added in the scenes such as search, recommendation as a continuous feature, preferably optimization is searched
Suo Xiaoguo.The embodiment of the present invention is this to associate two things by way of figure, using random walk strategy, generates
The vector form of two things, so as to directly calculate degree of correlation, this scheme is suitable for many emerging internets and produces
Product.For example news is recommended, the vector of user and news, such as advertisement CTR can be generated in we, can be by user and advertisement vector
Change etc..
The embodiment of the present invention excavates keyword query in combination with technologies such as the true intention of user and natural language processings
With the direct relation of site information site, the correlation calculations method of new slave query to site a kind of is provided.Pass through machine
Query and site vectorization is made it in same semantic space, by the correlation such as cosine for calculating vector by the method for study
Similarity, to improve the accuracy of similarity between query and site.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
Fig. 8 is shown according to an exemplary embodiment a kind of for showing the structural block diagram of the electronic equipment 800 of input.
For example, electronic equipment 800 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console put down
Panel device, Medical Devices, body-building equipment, personal digital assistant etc..
Referring to Fig. 8, electronic equipment 800 may include following one or more components: processing component 802, memory 804,
Power supply module 806, multimedia component 808, audio component 810, the interface 812 of input/output (I/O), sensor module 814,
And communication component 816.
The integrated operation of the usual controlling electronic devices 800 of processing component 802, such as with display, call, data are logical
Letter, camera operation and record operate associated operation.Processing element 802 may include one or more processors 820 to hold
Row instruction, to perform all or part of the steps of the methods described above.In addition, processing component 802 may include one or more moulds
Block, convenient for the interaction between processing component 802 and other assemblies.For example, processing component 802 may include multi-media module, with
Facilitate the interaction between multimedia component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in equipment 800.These data are shown
Example includes the instruction of any application or method for operating on electronic equipment 800, contact data, telephone directory number
According to, message, picture, video etc..Memory 804 can by any kind of volatibility or non-volatile memory device or they
Combination realize, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable
Programmable read only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, quick flashing
Memory, disk or CD.
Power supply module 806 provides electric power for the various assemblies of electronic equipment 800.Power supply module 806 may include power supply pipe
Reason system, one or more power supplys and other with for electronic equipment 800 generate, manage, and distribute the associated component of electric power.
Multimedia component 808 includes the screen of one output interface of offer between the electronic equipment 800 and user.
In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch surface
Plate, screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touches
Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding
The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments,
Multimedia component 808 includes a front camera and/or rear camera.When equipment 800 is in operation mode, as shot mould
When formula or video mode, front camera and/or rear camera can receive external multi-medium data.Each preposition camera shooting
Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 810 is configured as output and/or input audio signal.For example, audio component 810 includes a Mike
Wind (MIC), when electronic equipment 800 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone
It is configured as receiving external audio signal.The received audio signal can be further stored in memory 804 or via logical
Believe that component 816 is sent.In some embodiments, audio component 810 further includes a loudspeaker, is used for output audio signal.
I/O interface 812 provides interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 814 includes one or more sensors, for providing the state of various aspects for electronic equipment 800
Assessment.For example, sensor module 814 can detecte the state that opens/closes of equipment 800, the relative positioning of component, such as institute
The display and keypad that component is electronic equipment 800 are stated, sensor module 814 can also detect electronic equipment 800 or electronics
The position change of 800 1 components of equipment, the existence or non-existence that user contacts with electronic equipment 800,800 orientation of electronic equipment
Or the temperature change of acceleration/deceleration and electronic equipment 800.Sensor module 814 may include proximity sensor, be configured to
It detects the presence of nearby objects without any physical contact.Sensor module 814 can also include optical sensor, such as
CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, which can be with
Including acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between electronic equipment 800 and other equipment.
Electronic equipment 800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.Show at one
In example property embodiment, communication component 816 receives broadcast singal or broadcast from external broadcasting management system via broadcast channel
Relevant information.In one exemplary embodiment, the communication component 816 further includes near-field communication (NFC) module, short to promote
Cheng Tongxin.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band can be based in NFC module
(UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment 800 can be by one or more application specific integrated circuit (ASIC), number
Word signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 804 of instruction, above-metioned instruction can be executed by the processor 820 of electronic equipment 800 to complete the above method.Example
Such as, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, soft
Disk and optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of electronic equipment
When device executes, so that electronic equipment is able to carry out a kind of input method, which comprises according to crucial in target search result
Word and site information constitute the associated path of keyword and site information;According to the associated path and preset model, determines and close
First term vector of keyword and the second term vector of site information;According to first term vector and the second term vector, institute is calculated
State the correlation of keyword and site information.
Optionally, keyword and site information in the foundation target search result, composition keyword and site information
Associated path, comprising: determine multiple target search results, and extract keyword and the pass respectively from each target search result
The corresponding site information of keyword;Associated path is constituted using the keyword and the corresponding relationship of site information.
Optionally, described that associated path is constituted using the keyword and the corresponding relationship of site information, comprising: according to institute
The corresponding relationship for stating keyword and site information connects each keyword with corresponding site information, constitute the keyword and
The bigraph (bipartite graph) of site information;The associated path of the multiple keywords and site information is determined according to bigraph (bipartite graph).
Optionally, the associated path that the multiple keywords and site information are determined according to bigraph (bipartite graph), comprising: foundation
Keyword and site information are connected by random walk mode, generate multiple associated paths by the bigraph (bipartite graph).
Optionally, described according to associated path and preset model, determine the first term vector and site information of keyword
Second term vector, comprising: generate vector information according to the associated path, wherein the vector information includes the of keyword
Second path vector of one path vector and site information;The vector information is input in preset model, keyword is obtained
The first term vector and site information the second term vector.
Optionally, first term vector of foundation and the second term vector, it is related to site information to calculate the keyword
Property, comprising: selection keyword and site information;First term vector of keyword and the second term vector of site information are subjected to phase
Closing property calculates, and obtains the correlation between the keyword and site information.
Optionally, further includes: when executing setting business by query word, it is corresponding that query word is obtained from query result
Website information, wherein the setting business comprises at least one of the following: searching service recommends business;Using the query word as
Keyword inquires the correlation of corresponding keyword and site information using the website information as site information.
Fig. 9 is the structural schematic diagram of server in the embodiment of the present invention.The server 900 can be due to configuration or performance be different
Generate bigger difference, may include one or more central processing units (central processing units,
CPU) 922 (for example, one or more processors) and memory 932, one or more storage application programs 942 or
The storage medium 930 (such as one or more mass memory units) of data 944.Wherein, memory 932 and storage medium
930 can be of short duration storage or persistent storage.The program for being stored in storage medium 930 may include one or more modules
(diagram does not mark), each module may include to the series of instructions operation in server.Further, central processing unit
922 can be set to communicate with storage medium 930, and the series of instructions behaviour in storage medium 930 is executed on server 800
Make.
Server 900 can also include one or more power supplys 926, one or more wired or wireless networks
Interface 950, one or more input/output interfaces 958, one or more keyboards 956, and/or, one or one
The above operating system 941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..
The embodiment of the invention also provides a kind of electronic equipment, which is characterized in that include memory and one or
More than one program, perhaps more than one program is stored in memory and is configured to by one or one for one of them
It includes the instruction for performing the following operation that a above processor, which executes the one or more programs: being searched according to target
Keyword and site information in hitch fruit constitute the associated path of keyword and site information;According to the associated path and in advance
If model, the first term vector of keyword and the second term vector of site information are determined;According to first term vector and second
Term vector calculates the correlation of the keyword and site information.
Optionally, keyword and site information in the foundation target search result, composition keyword and site information
Associated path, comprising: determine multiple target search results, and extract keyword and the pass respectively from each target search result
The corresponding site information of keyword;Associated path is constituted using the keyword and the corresponding relationship of site information.
Optionally, described that associated path is constituted using the keyword and the corresponding relationship of site information, comprising: according to institute
The corresponding relationship for stating keyword and site information connects each keyword with corresponding site information, constitute the keyword and
The bigraph (bipartite graph) of site information;The associated path of the multiple keywords and site information is determined according to bigraph (bipartite graph).
Optionally, the associated path that the multiple keywords and site information are determined according to bigraph (bipartite graph), comprising: foundation
Keyword and site information are connected by random walk mode, generate multiple associated paths by the bigraph (bipartite graph).
Optionally, described according to associated path and preset model, determine the first term vector and site information of keyword
Second term vector, comprising: generate vector information according to the associated path, wherein the vector information includes the of keyword
Second path vector of one path vector and site information;The vector information is input in preset model, keyword is obtained
The first term vector and site information the second term vector.
Optionally, first term vector of foundation and the second term vector, it is related to site information to calculate the keyword
Property, comprising: selection keyword and site information;First term vector of keyword and the second term vector of site information are subjected to phase
Closing property calculates, and obtains the correlation between the keyword and site information.
Optionally, executing the one or more programs by one or more than one processor includes to be also used to
The instruction performed the following operation: when executing setting business by query word, the corresponding net of query word is obtained from query result
Location information, wherein the setting business comprises at least one of the following: searching service recommends business;Using the query word as pass
Keyword inquires the correlation of corresponding keyword and site information using the website information as site information.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can provide as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present invention be referring to according to the method for the embodiment of the present invention, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these
Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices
Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices
In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart
And/or in one or more blocks of the block diagram specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
It is situated between above to a kind of data processing method and device provided by the present invention, a kind of electronic equipment and a kind of storage
Matter is described in detail, and used herein a specific example illustrates the principle and implementation of the invention, above
The explanation of embodiment is merely used to help understand method and its core concept of the invention;Meanwhile for the general skill of this field
Art personnel, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion this
Description should not be construed as limiting the invention.
Claims (10)
1. a kind of data processing method, which is characterized in that the method includes:
According to keyword and site information in target search result, the associated path of keyword and site information is constituted;
According to the associated path and preset model, the first term vector of keyword and the second term vector of site information are determined;
According to first term vector and the second term vector, the correlation of the keyword and site information is calculated.
2. the method according to claim 1, wherein described according to keyword in target search result and website letter
Breath constitutes the associated path of keyword and site information, comprising:
It determines multiple target search results, and extracts keyword respectively from each target search result and the keyword is corresponding
Site information;
Associated path is constituted using the keyword and the corresponding relationship of site information.
3. according to the method described in claim 2, it is characterized in that, described closed using the keyword and the corresponding of site information
System constitutes associated path, comprising:
According to the corresponding relationship of the keyword and site information, each keyword is connected with corresponding site information, constitutes institute
State the bigraph (bipartite graph) of keyword and site information;
The associated path of the multiple keywords and site information is determined according to bigraph (bipartite graph).
4. according to the method described in claim 3, it is characterized in that, described determine multiple keywords and station according to bigraph (bipartite graph)
The associated path of point information, comprising:
According to the bigraph (bipartite graph), keyword and site information are connected by random walk mode, generate multiple associated paths.
5. the method according to claim 1, wherein described according to associated path and preset model, determining key
First term vector of word and the second term vector of site information, comprising:
Vector information is generated according to the associated path, wherein the vector information includes the first path vector sum of keyword
Second path vector of site information;
The vector information is input in preset model, obtain keyword the first term vector and site information the second word to
Amount.
6. the method according to claim 1, wherein the first term vector of the foundation and the second term vector, calculate
The correlation of the keyword and site information, comprising:
Select keyword and site information;
First term vector of keyword and the second term vector of site information are subjected to correlation calculations, obtain the keyword and
Correlation between site information.
7. the method according to claim 1, wherein further include:
When executing setting business by query word, the corresponding website information of query word is obtained from query result, wherein described
Setting business comprises at least one of the following: searching service recommends business;
Corresponding keyword and website letter are inquired using the website information as site information using the query word as keyword
The correlation of breath.
8. a kind of data processing equipment characterized by comprising
Path determination module, for constituting keyword and site information according to keyword and site information in target search result
Associated path;
Term vector determining module, for determining the first term vector and the station of keyword according to the associated path and preset model
Second term vector of point information;
Correlation calculations module, for calculating the keyword and website letter according to first term vector and the second term vector
The correlation of breath.
9. a kind of readable storage medium storing program for executing, which is characterized in that when the instruction in the storage medium is held by the processor of electronic equipment
When row, so that electronic equipment is able to carry out the data processing method as described in claim to a method 1-7 is any.
10. a kind of electronic equipment, which is characterized in that include memory and one or more than one program, wherein one
A perhaps more than one program is stored in memory and is configured to execute described one by one or more than one processor
A or more than one program includes the instruction for performing the following operation:
According to keyword and site information in target search result, the associated path of keyword and site information is constituted;
According to the associated path and preset model, the first term vector of keyword and the second term vector of site information are determined;
According to first term vector and the second term vector, the correlation of the keyword and site information is calculated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711252207.8A CN110020151B (en) | 2017-12-01 | 2017-12-01 | Data processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711252207.8A CN110020151B (en) | 2017-12-01 | 2017-12-01 | Data processing method and device, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110020151A true CN110020151A (en) | 2019-07-16 |
CN110020151B CN110020151B (en) | 2022-04-26 |
Family
ID=67185939
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711252207.8A Active CN110020151B (en) | 2017-12-01 | 2017-12-01 | Data processing method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110020151B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112883295A (en) * | 2019-11-29 | 2021-06-01 | 北京搜狗科技发展有限公司 | Data processing method, device and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110225180A1 (en) * | 2010-03-10 | 2011-09-15 | Alibaba Group Holding Limited | Guided search based on query model |
CN102789462A (en) * | 2011-05-18 | 2012-11-21 | 阿里巴巴集团控股有限公司 | Project recommendation method and system |
CN103294681A (en) * | 2012-02-23 | 2013-09-11 | 北京百度网讯科技有限公司 | Method and device for generating search result |
CN106484698A (en) * | 2015-08-25 | 2017-03-08 | 北京奇虎科技有限公司 | A kind of method for pushing of search keyword and device |
CN107122455A (en) * | 2017-04-26 | 2017-09-01 | 中国人民解放军国防科学技术大学 | A kind of network user's enhancing method for expressing based on microblogging |
CN107291914A (en) * | 2017-06-27 | 2017-10-24 | 达而观信息科技(上海)有限公司 | A kind of method and system for generating search engine inquiry expansion word |
-
2017
- 2017-12-01 CN CN201711252207.8A patent/CN110020151B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110225180A1 (en) * | 2010-03-10 | 2011-09-15 | Alibaba Group Holding Limited | Guided search based on query model |
CN102789462A (en) * | 2011-05-18 | 2012-11-21 | 阿里巴巴集团控股有限公司 | Project recommendation method and system |
CN103294681A (en) * | 2012-02-23 | 2013-09-11 | 北京百度网讯科技有限公司 | Method and device for generating search result |
CN106484698A (en) * | 2015-08-25 | 2017-03-08 | 北京奇虎科技有限公司 | A kind of method for pushing of search keyword and device |
CN107122455A (en) * | 2017-04-26 | 2017-09-01 | 中国人民解放军国防科学技术大学 | A kind of network user's enhancing method for expressing based on microblogging |
CN107291914A (en) * | 2017-06-27 | 2017-10-24 | 达而观信息科技(上海)有限公司 | A kind of method and system for generating search engine inquiry expansion word |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112883295A (en) * | 2019-11-29 | 2021-06-01 | 北京搜狗科技发展有限公司 | Data processing method, device and medium |
CN112883295B (en) * | 2019-11-29 | 2024-02-23 | 北京搜狗科技发展有限公司 | Data processing method, device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN110020151B (en) | 2022-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110297848B (en) | Recommendation model training method, terminal and storage medium based on federal learning | |
US11120078B2 (en) | Method and device for video processing, electronic device, and storage medium | |
CN109800325B (en) | Video recommendation method and device and computer-readable storage medium | |
CN108304441B (en) | Network resource recommendation method and device, electronic equipment, server and storage medium | |
KR20210053122A (en) | Method, apparatus and storage medium for training of neural network | |
CN103339623B (en) | It is related to the method and apparatus of Internet search | |
CN109145213B (en) | Historical information based query recommendation method and device | |
CN109918669B (en) | Entity determining method, device and storage medium | |
CN110232137B (en) | Data processing method and device and electronic equipment | |
CN111291069A (en) | Data processing method and device and electronic equipment | |
CN110399548A (en) | A kind of search processing method, device, electronic equipment and storage medium | |
CN111611490A (en) | Resource searching method, device, equipment and storage medium | |
CN113705210A (en) | Article outline generation method and device for generating article outline | |
CN112784142A (en) | Information recommendation method and device | |
CN110110207B (en) | Information recommendation method and device and electronic equipment | |
CN112307281A (en) | Entity recommendation method and device | |
CN117033799A (en) | Resource recommendation method, device, computer equipment and storage medium | |
CN111538830A (en) | French retrieval method, French retrieval device, computer equipment and storage medium | |
CN110929137B (en) | Article recommendation method, device, equipment and storage medium | |
CN111241844A (en) | Information recommendation method and device | |
CN116186197A (en) | Topic recommendation method, device, electronic equipment and storage medium | |
CN110110046B (en) | Method and device for recommending entities with same name | |
CN110020151A (en) | A kind of data processing method, device, electronic equipment and storage medium | |
CN111222011B (en) | Video vector determining method and device | |
CN112825076B (en) | Information recommendation method and device and electronic equipment |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20220926 Address after: 100084. Room 9, floor 01, cyber building, building 9, building 1, Zhongguancun East Road, Haidian District, Beijing Patentee after: BEIJING SOGOU TECHNOLOGY DEVELOPMENT Co.,Ltd. Patentee after: Beijing Sogou Network Technology Co.,Ltd. Address before: 100084. Room 9, floor 01, cyber building, building 9, building 1, Zhongguancun East Road, Haidian District, Beijing Patentee before: BEIJING SOGOU TECHNOLOGY DEVELOPMENT Co.,Ltd. |