CN107291835A - A kind of recommendation method and apparatus of search term - Google Patents
A kind of recommendation method and apparatus of search term Download PDFInfo
- Publication number
- CN107291835A CN107291835A CN201710397412.7A CN201710397412A CN107291835A CN 107291835 A CN107291835 A CN 107291835A CN 201710397412 A CN201710397412 A CN 201710397412A CN 107291835 A CN107291835 A CN 107291835A
- Authority
- CN
- China
- Prior art keywords
- search term
- product information
- user
- search
- similarity value
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses the recommendation method and apparatus of search term, it is related to field of computer technology.One embodiment of this method includes：The product information that the search term and user for obtaining user's input are clicked in the search term Query Result；According to the product information, acquisition can search all search terms of the product information, and the Similarity value of the search term and the search term of user input of acquisition is calculated respectively；According to Similarity value, recommend the search term obtained successively.The search term that the embodiment can be inputted according to user, the search carried out truly is recommended.
Description
Technical field
The present invention relates to the recommendation method and apparatus of field of computer technology, more particularly to a kind of search term.
Background technology
With the fast development of Internet technology, service provider provides the user with the service of increasingly hommization.Mutual
In the Internet services, when user inputs search term in internet to be scanned for, service provider is showing correlation for user
During search result, also the search intention of user is being understood.When search result can not meet the search purpose of user, by providing
The search term related to user's search term, to reduce the workload that user inputs neologisms；Attract to use by showing neologisms simultaneously
Family is further searched for, it is to avoid customer loss.
In process of the present invention is realized, inventor has found that at least there are the following problems in the prior art：Existing search clothes
Be engaged in provider, and simply the word of the simple search term inputted according to user carries out the recommendation of similar word in itself, is not carried out
Truly search is recommended.
The content of the invention
In view of this, the embodiment of the present invention provides a kind of recommendation method and apparatus of search term, can be inputted according to user
Search term, carry out search truly and recommend.
To achieve the above object, one side according to embodiments of the present invention is there is provided a kind of recommendation method of search term,
The product information clicked on including the search term and user that obtain user's input in the search term Query Result；According to the production
Product information, acquisition can search all search terms of the product information, and the search term of acquisition and the user are calculated respectively
The Similarity value of the search term of input；According to Similarity value, recommend the search term obtained successively.
Alternatively, it is described according to Similarity value, before the search term for recommending acquisition successively, in addition to：Obtain and the production
The product information of product information different model；According to the product information of the different model, acquisition can search the different shaped
All search terms of number product information；All search terms of different model product information and searching that the user inputs are calculated respectively
The Similarity value of rope word.
Alternatively, it is described according to Similarity value, before the search term for recommending acquisition successively, in addition to：Determine the difference
The Similarity value for the search term that the search term of type product information is inputted with the user is more than default similarity threshold；By institute
The search term for stating different model product information polymerize with the search term of the product information, then according to the search term after polymerization with
The Similarity value of the search term of user's input, recommends the search term after the polymerization of acquisition successively.
Alternatively, the Similarity value for the search term that the search term that acquisition is calculated respectively is inputted with the user, including：
According to default hierarchical structure, level classification is carried out to the search term that the search term and the user input, institute is then calculated
State the Similarity value for the search term that search term is inputted with the user.
Alternatively, before the search term for recommending acquisition successively according to Similarity value, in addition to：The Similarity value is carried out
Decay, the Similarity value after being decayed；According to the Similarity value after decay, recommend the search term obtained successively.
Alternatively, before the product information that the acquisition user clicks in the search term Query Result, in addition to：
The search term of user's input of acquisition is normalized.
Other side according to embodiments of the present invention, additionally provides a kind of recommendation apparatus of search term, including obtain mould
Block, the product information that search term and user for obtaining user's input are clicked in the search term Query Result；Calculate mould
Block, for according to the product information, acquisition can to search all search terms of the product information, calculates what is obtained respectively
The Similarity value for the search term that search term is inputted with the user；Recommending module, for according to Similarity value, recommending to obtain successively
Search term.
Alternatively, the computing module, is additionally operable to：Obtain the product information with the product information different model；According to
The product information of the different model, acquisition can search all search terms of the different model product information；Count respectively
Calculate the Similarity value of all search terms and the search term of user input of different model product information.
Alternatively, before the recommending module recommends the search term of acquisition according to Similarity value successively, it is additionally operable to：Determine institute
The Similarity value for stating the search term and the search term of user input of different model product information is more than default similarity threshold
Value；The search term of the different model product information is polymerize with the search term of the product information, then according to polymerization after
The Similarity value for the search term that search term is inputted with the user, recommends the search term after the polymerization of acquisition successively.
Alternatively, the computing module calculates the similarity of the search term and the search term of user input of acquisition respectively
Value, including：According to default hierarchical structure, level classification is carried out to the search term that the search term and the user input, so
The Similarity value for the search term that the search term is inputted with the user is calculated afterwards.
Alternatively, before the recommending module recommends the search term of acquisition according to Similarity value successively, it is additionally operable to：To described
Similarity value is decayed, the Similarity value after being decayed；According to the Similarity value after decay, recommend the search obtained successively
Word.
Alternatively, the acquisition module obtain the product information clicked in the search term Query Result of user it
Before, it is additionally operable to：The search term of user's input of acquisition is normalized.
Other side according to embodiments of the present invention, additionally provides a kind of electronic equipment, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes the method described in any of the above-described embodiment.
Other side according to embodiments of the present invention, additionally provides a kind of computer-readable medium, is stored thereon with meter
Calculation machine program, realizes the method described in any of the above-described embodiment when described program is executed by processor.
One embodiment in foregoing invention has the following advantages that or beneficial effect：Because being searched using according to user described
The product information clicked in rope word Query Result, come the technological means found search term and recommended, so overcoming does not have
The technical problem for truly searching for recommendation is realized, and then reaches the technology effect for effectively and rapidly recommending search term for user
Really.
The further effect that above-mentioned non-usual optional mode has adds hereinafter in conjunction with embodiment
With explanation.
Brief description of the drawings
Accompanying drawing is used to more fully understand the present invention, does not constitute inappropriate limitation of the present invention.Wherein：
Fig. 1 is that the embodiment of the present invention can apply to exemplary system architecture figure therein；
Fig. 2 is the schematic diagram of the main flow of the recommendation method of search term according to embodiments of the present invention；
Fig. 3 is the schematic diagram of the main flow of the recommendation method for the search term that embodiment is referred to according to the present invention；
Fig. 4 is the schematic diagram of the main modular of the recommendation apparatus of search term according to embodiments of the present invention；
Fig. 5 is adapted for the structural representation for realizing the terminal device of the embodiment of the present invention or the computer system of server
Figure.
Embodiment
The one exemplary embodiment of the present invention is explained below in conjunction with accompanying drawing, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
Arrive, various changes and modifications can be made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, eliminates the description to known function and structure in following description.
Fig. 1, which is shown, to be shown using the recommendation method of the search term of the embodiment of the present invention or the recommendation apparatus of search term
Example sexual system framework 100.
As shown in figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Medium of the network 104 to provide communication link between terminal device 101,102,103 and server 105.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted with using terminal equipment 101,102,103 by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, class of for example doing shopping application, net on terminal device 101,102,103
(merely illustrative) such as the application of page browsing device, searching class application, JICQ, mailbox client, social platform softwares.
Terminal device 101,102,103 can be the various electronic equipments browsed with display screen and supported web page, bag
Include but be not limited to smart mobile phone, tablet personal computer, pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services, for example, utilize terminal device 101,102,103 to user
The shopping class website browsed provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to receiving
To the data such as information query request carry out the processing such as analyzing, and by result (such as target push information, product letter
Breath -- merely illustrative) feed back to terminal device.
It should be noted that the recommendation method for the search term that the embodiment of the present invention is provided typically is performed by server 105,
Correspondingly, the recommendation apparatus of search term is generally positioned in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
Fig. 2 is the recommendation method of search term according to embodiments of the present invention, as shown in Fig. 2 the recommendation side of the search term
Method includes：
Step S201, the product letter that the search term and user for obtaining user's input are clicked in the search term Query Result
Breath.
As embodiment, the search term of user's input can be obtained, and sometimes user occur when inputting search term it is numerous
It is simplified obscure, that size write error, space deal with (space does not have a space, and should not space space), word order improperly is wrong
The problems such as mistake etc., if the search term for directly inputting user carries out follow-up processing, the search term finally recommended may be caused
It is inaccurate.It therefore, it can after the search term of user's input is obtained, the search term that user inputs be normalized.
That is, the search term inputted to user is arranged, some apparent errors are modified, making the search term of acquisition has
It is normative.
In addition, while the search term of user's input is obtained, in addition it is also necessary to obtain user in the search term Query Result
The product information of middle click, i.e., retrieve obtaining Query Result, then user is clicked in Query Result by inputting search term
Product information.For example：The search term of user's input is " refrigerator ", is then clicked in the Query Result of search term " refrigerator "
The information of product is " 258 liters of air-cooled frostless three-door refrigerators of Haier (Haier) BCD-258WDPM ".
Step S202, according to the product information, acquisition can search all search terms of the product information, respectively
Calculate the Similarity value for the search term that the search term obtained is inputted with the user.
In embodiment, the product information that can be clicked on according to user, retrodicting acquisition all can search the product
The search term of information.For example：Higher level's information that the product information can be found by default hierarchical structure is used as search
Word, can also be according to the historical record for searching the product information etc. method.Preferably, in order to obtain more accurate institute
The search term of product information is stated, the product information that can be clicked on according to user is searched in historical record and clicks on the product letter
Cease corresponding search term.Wherein, described historical record stores the search term that the product information of user's click is inputted with user
Mapping relations.For example：The product information that is stored with historical record is " 258 liters of Haier (Haier) BCD-258WDPM is air-cooled
The corresponding search term of frostless three-door refrigerator " is " Haier's refrigerator ", and corresponding search term is " three-door refrigerator ".
As a preferably embodiment, the similarity for the search term that the search term that obtains is inputted with the user is being calculated
During value, level classification can be carried out, so to the search term that the search term and the user input according to default hierarchical structure
The Similarity value for the search term that the search term is inputted with the user is calculated afterwards.For example：The search term is " refrigerator ", is obtained
Search term be " Haier's refrigerator ", according to default hierarchical structure, " refrigerator " be three-level, " Haier's refrigerator " be level Four, then " ice
Similarity value score is 1 between case " and " Haier's refrigerator ".
It is described obtaining in order to be supplied to the more search terms of user as step S202 further embodiments
While product information corresponding search term, the product information with the product information different model can also be obtained.Then, root
According to the product information of the different model, acquisition can search all search terms of the different model product information, then divide
Not Ji Suan different model product information the Similarity value of search term that inputs of all search terms and the user.For example：With production
The product information of product information " 258 liters of air-cooled frostless three-door refrigerators of Haier (Haier) BCD-258WDPM " different model is " Haier
(Haier) the air-cooled frostless three-door refrigerators of 248 liters of BCD-248WDPM ".
Step S203, according to Similarity value, recommends the search term obtained successively.
In embodiment, in order to recommend, user is more effective, accurate search term, can be first to the similar of acquisition
Angle value is screened, then is recommended.Preferably, a similarity threshold can be pre-set, the Similarity value obtained is judged
Whether it is more than the similarity threshold, is recommended if the Similarity value of the acquisition is more than the similarity threshold, if institute
The Similarity value for stating acquisition is less than or equal to the similarity threshold then without recommending.It should be noted that by Similarity value
Search term more than the similarity threshold is recommended just can to make user can be with when being inquired about using the search term
More product is searched, allows user that there are more selections.Further, can be according to similar when scanning for word recommendation
The descending of angle value recommends corresponding search term successively.
Another preferred embodiment, judges the search term of the different model product information and searching that the user inputs
The Similarity value of rope word whether be more than default similarity threshold, if more than if by the search term of the different model product information
It polymerize with the search term of the product information, it is then similar to search term that the user inputs according to the search term after polymerization
Angle value, recommends the search term after the polymerization of acquisition successively.If the search term of the different model product information and the user are defeated
Whether the Similarity value of the search term entered is less than or equal to default similarity threshold, then gives up the different model product information
Search term.Wherein, the search term of the different model product information is polymerize such as " sea with the search term of the product information
The air-cooled frostless three-door refrigerators of 258 liters of (Haier) BCD-258WDPM of that " and " 248 liters of wind of Haier (Haier) BCD-248WDPM
Cold frostless three-door refrigerator " can pass through search term " three-door refrigerator ", then just two " three-door refrigerators " can be merged into one
Individual " three-door refrigerator ".
In a preferred embodiment, in order to avoid some feature implementations cause the Similarity value calculated inaccurate
(advertising campaign of such as some category etc. and cause the exception of partial query word), can be carried out to the Similarity value now obtained
Decay, the Similarity value after being decayed.Then, according to the Similarity value after decay, the search term obtained is recommended successively.Enter one
Step, decay factor is：a-b*pow(day_pass,c).Wherein, a represents that (preferably, a value is 1 or 2) to initial weight；b
(preferably, b value is 1) (preferably, 0.08) c value is represents attenuation degree, b and c values are bigger, decays more severe with c；
It is because the corresponding rate of decay of two parameters is different using two parameters；Day_pass represents the number of days of process.Afterwards,
Similarity value will be obtained and be multiplied by the Similarity value after decay factor is decayed.
Fig. 3 is the schematic diagram of the main flow of the recommendation method for the search term that embodiment is referred to according to the present invention, described
The recommendation method of search term can include：
Step S301, obtains the search term of user's input, and the search term that user inputs is normalized.
Step S302, obtains the product information that user clicks in the search term Query Result.
Step S303, according to the product information, acquisition can search all search terms of the product information, respectively
Calculate the Similarity value for the search term that the search term obtained is inputted with the user.
It should be noted that step S303 and step S304 and step S305 is performed simultaneously, or step can also be first carried out
Rapid S303 performs step S304 and S305 again, or can also first carry out step S304 and S305 and perform step S303 again.
It is preferred that can be inputted in step S303 according to default hierarchical structure to the search term and the user
Search term carries out level classification, then calculates the Similarity value for the search term that the search term is inputted with the user.
Another preferably embodiment, product information that step S303 can be clicked on according to user, are looked into historical record
Look for the corresponding search term of the click product information.Wherein, described historical record store user click product information with
The mapping relations of the search term of user's input.
Step S304, obtains the product information with the product information different model, according to the product of the different model
Information, acquisition can search all search terms of the different model product information, and different model product information is calculated respectively
The Similarity value of search term that inputs of all search terms and the user.
Step S305, judges that the search term of the different model product information is similar to search term that the user inputs
Whether angle value is more than default similarity threshold, if carrying out step S306 more than if, if the progress step S307 less than or equal to if.
Step S306, the search term of the different model product information is polymerize with the search term of the product information, so
Step S308 is performed afterwards.
Step S307, gives up the search term of the different model product information, is then log out the flow.
Step S308, decays to the Similarity value of the search term after the polymerization of acquisition, the similarity after being decayed
Value.
Step S309, according to the descending of Similarity value after decay, recommends the search term obtained successively.
In addition, the specific implementation content of the recommendation method of search term described in embodiment is referred in the present invention, above
It has been described in detail, therefore has no longer illustrated in this duplicate contents in the recommendation method of the search term.
Fig. 4 is the recommendation apparatus of search term according to embodiments of the present invention, as shown in figure 4, the recommendation dress of the search term
Putting 400 includes acquisition module 401, computing module 402 and recommending module 403.Wherein, acquisition module 401 obtains user's input
The product information that search term and user click in the search term Query Result.Computing module 402 according to the product information,
Acquisition can search all search terms of the product information, and the search term of acquisition and searching that the user inputs are calculated respectively
The Similarity value of rope word.Finally, recommending module 403 recommends the search term obtained successively according to Similarity value.
Preferably, the acquisition module 401 can obtain the search term of user's input, and user is in input search term sometimes
When occur either traditional and simplified characters obscure, size write error, space deal with improperly (space does not have a space, and should not space space),
The problems such as word order mistake etc., if the search term for directly inputting user carries out follow-up processing, most pusher may be caused
The search term recommended is inaccurate.It therefore, it can after the search term of user's input is obtained, the search term that user inputs returned
One change is handled.
In one preferably embodiment, the computing module 402 is obtaining in order to be supplied to the more search terms of user
While taking the product information corresponding search term, the product information with the product information different model can also be obtained.
Then, according to the product information of the different model, acquisition can search all search of the different model product information
Word, then the Similarity value of all search terms and the search term of user input of different model product information is calculated respectively.
As one embodiment, the product information that the computing module 402 can be clicked on according to user is retrodicted and owned
The search term of the product information can be searched.For example：The product information can be found by default hierarchical structure
Higher level's information as search term, can also be according to the historical record for searching the product information etc. method.Preferably, it is
Obtain the search term of the more accurate product information, the product information that can be clicked on according to user, in historical record
Search and click on the corresponding search term of the product information.Wherein, described historical record stores the product information of user's click
The mapping relations of the search term inputted with user.
In addition, the recommending module 403 is in order to recommend, user is more effective, accurate search term, can be first right
The Similarity value of acquisition is screened, then is recommended.Preferably, a similarity threshold can be pre-set, judges to obtain
Similarity value whether be more than the similarity threshold, if the acquisition Similarity value be more than the similarity threshold if carry out
Recommend, without recommending if the Similarity value of the acquisition is less than or equal to the similarity threshold.Further, carrying out
When search term is recommended, corresponding search term can be recommended successively according to the descending of Similarity value.
In addition, the recommending module 403 can also judge the search term of the different model product information and the user
Whether the Similarity value of the search term of input is more than default similarity threshold, by the different model product information if being more than
Search term polymerize with the search term of the product information, the search then inputted according to the search term after polymerization and the user
The Similarity value of word, recommends the search term after the polymerization of acquisition successively.If search term and the institute of the different model product information
Whether the Similarity value for stating the search term of user's input is less than or equal to default similarity threshold, then gives up the different model
The search term of product information.
As another embodiment, the recommending module 403 causes the similar of calculating in order to avoid some feature implementations
Angle value is inaccurate, and the Similarity value now obtained can be decayed, the Similarity value after being decayed.Then, according to declining
Similarity value after subtracting, recommends the search term obtained successively.Further, decay factor is：a-b*pow(day_pass,c).
Wherein, a represents that (preferably, a value is 1 or 2) to initial weight；(preferably, b value is 1) (preferably, c value is with c to b
0.08) attenuation degree is represented, b and c values are bigger, decayed more severe；Using two parameters, declined because two parameters are corresponding
The rate of deceleration is different；Day_pass represents the number of days of process.Afterwards, Similarity value will be obtained to be multiplied by after decay factor decayed
Similarity value.
It should be noted that the specific implementation content of the recommendation apparatus in search term of the present invention, described above to search
It has been described in detail, therefore has no longer illustrated in this duplicate contents in the recommendation method of rope word.
Below with reference to Fig. 5, it illustrates suitable for for the computer system 500 for the terminal device for realizing the embodiment of the present invention
Structural representation.Terminal device shown in Fig. 5 is only an example, to the function of the embodiment of the present invention and should not use model
Shroud carrys out any limitation.
As shown in figure 5, computer system 500 includes CPU (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into program in random access storage device (RAM) 503 from storage part 508 and
Perform various appropriate actions and processing.In RAM 503, the system that is also stored with 500 operates required various programs and data.
CPU 501, ROM 502 and RAM503 are connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to always
Line 504.
I/O interfaces 505 are connected to lower component：Importation 506 including keyboard, mouse etc.；Penetrated including such as negative electrode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage part 508 including hard disk etc.；
And the communications portion 509 of the NIC including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net performs communication process.Driver 510 is also according to needing to be connected to I/O interfaces 505.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc., are arranged on driver 510, in order to read from it as needed
Computer program be mounted into as needed storage part 508.
Especially, according to embodiment disclosed by the invention, the process described above with reference to flow chart may be implemented as meter
Calculation machine software program.For example, embodiment disclosed by the invention includes a kind of computer program product, it includes being carried on computer
Computer program on computer-readable recording medium, the computer program, which is included, is used for the program code of the method shown in execution flow chart.
In such embodiment, the computer program can be downloaded and installed by communications portion 509 from network, and/or from can
Medium 511 is dismantled to be mounted.When the computer program is performed by CPU (CPU) 501, the system for performing the present invention
The above-mentioned functions of middle restriction.
It should be noted that the computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer-readable recording medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, system, device or the device of infrared ray or semiconductor, or it is any more than combination.Meter
The more specifically example of calculation machine readable storage medium storing program for executing can include but is not limited to：Electrical connection with one or more wires, just
Take formula computer disk, hard disk, random access storage device (RAM), read-only storage (ROM), erasable type and may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer-readable recording medium can any include or store journey
The tangible medium of sequence, the program can be commanded execution system, device or device and use or in connection.And at this
In invention, computer-readable signal media can be included in a base band or as the data-signal of carrier wave part propagation,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limit
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium beyond storage medium is read, the computer-readable medium, which can send, propagates or transmit, to be used for
Used by instruction execution system, device or device or program in connection.Included on computer-readable medium
Program code can be transmitted with any appropriate medium, be included but is not limited to：Wirelessly, electric wire, optical cable, RF etc., or above-mentioned
Any appropriate combination.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of various embodiments of the invention, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, a part for above-mentioned module, program segment or code is comprising one or more
Executable instruction for realizing defined logic function.It should also be noted that in some realizations as replacement, institute in square frame
The function of mark can also be with different from the order marked in accompanying drawing generation.For example, two square frames succeedingly represented are actual
On can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.Also
It is noted that the combination of each square frame in block diagram or flow chart and the square frame in block diagram or flow chart, can use and perform rule
Fixed function or the special hardware based system of operation realize, or can use the group of specialized hardware and computer instruction
Close to realize.
Being described in module involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described module can also be set within a processor, for example, can be described as：A kind of processor bag
Include acquisition module, computing module and recommending module.Wherein, the title of these modules is not constituted to the module under certain conditions
The restriction of itself, for example, acquisition module is also described as, " search term for sending user's input to the terminal connected is obtained
The module of request ".
As on the other hand, present invention also offers a kind of computer-readable medium, the computer-readable medium can be
Included in equipment described in above-described embodiment；Can also be individualism, and without be incorporated the equipment in.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the equipment, makes
Obtaining the equipment includes：The product information that the search term and user for obtaining user's input are clicked in the search term Query Result；
According to the product information, acquisition can search all search terms of the product information, the search term of acquisition is calculated respectively
The Similarity value of the search term inputted with the user；According to Similarity value, recommend the search term obtained successively.
Technical scheme according to embodiments of the present invention, the production that can be clicked on according to user in the search term Query Result
Product information, to find search term and be recommended, it is achieved thereby that effectively and rapidly recommending search term for user.
Above-mentioned embodiment, does not constitute limiting the scope of the invention.Those skilled in the art should be bright
It is white, depending on design requirement and other factors, can occur various modifications, combination, sub-portfolio and replacement.It is any
Modifications, equivalent substitutions and improvements made within the spirit and principles in the present invention etc., should be included in the scope of the present invention
Within.
Claims (14)
1. a kind of recommendation method of search term, it is characterised in that including：
The product information that the search term and user for obtaining user's input are clicked in the search term Query Result；
According to the product information, acquisition can search all search terms of the product information, and searching for acquisition is calculated respectively
The Similarity value for the search term that rope word is inputted with the user；
According to Similarity value, recommend the search term obtained successively.
2. according to the method described in claim 1, it is characterised in that described according to Similarity value, recommend the search obtained successively
Before word, in addition to：
Obtain the product information with the product information different model；
According to the product information of the different model, acquisition can search all search of the different model product information
Word；
The Similarity value of all search terms and the search term of user input of different model product information is calculated respectively.
3. method according to claim 2, it is characterised in that described according to Similarity value, recommends the search obtained successively
Before word, in addition to：
Determine that the Similarity value for the search term that the search term of the different model product information is inputted with the user is more than to preset
Similarity threshold；
The search term of the different model product information is polymerize with the search term of the product information, then according to polymerization after
The Similarity value for the search term that search term is inputted with the user, recommends the search term after the polymerization of acquisition successively.
4. according to the method described in claim 1, it is characterised in that the search term for calculating acquisition respectively and the user are defeated
The Similarity value of the search term entered, including：
According to default hierarchical structure, level classification, Ran Houji are carried out to the search term that the search term and the user input
Calculate the Similarity value for the search term that the search term is inputted with the user.
5. according to the method described in claim 1, it is characterised in that recommended successively according to Similarity value the search term that obtains it
Before, in addition to：
The Similarity value is decayed, the Similarity value after being decayed；
According to the Similarity value after decay, recommend the search term obtained successively.
6. according to any described methods of claim 1-5, it is characterised in that inquired about in the acquisition user in the search term
As a result before the product information of middle click, in addition to：
The search term of user's input of acquisition is normalized.
7. a kind of recommendation apparatus of search term, it is characterised in that including：
Acquisition module, the product letter that search term and user for obtaining user's input are clicked in the search term Query Result
Breath；
Computing module, for according to the product information, acquisition can to search all search terms of the product information, respectively
Calculate the Similarity value for the search term that the search term obtained is inputted with the user；
Recommending module, for according to Similarity value, recommending the search term obtained successively.
8. device according to claim 7, it is characterised in that the computing module, is additionally operable to：
Obtain the product information with the product information different model；
According to the product information of the different model, acquisition can search all search of the different model product information
Word；
The Similarity value of all search terms and the search term of user input of different model product information is calculated respectively.
9. device according to claim 8, it is characterised in that the recommending module recommends to obtain successively according to Similarity value
Search term before, be additionally operable to：
Determine that the Similarity value for the search term that the search term of the different model product information is inputted with the user is more than to preset
Similarity threshold；
The search term of the different model product information is polymerize with the search term of the product information, then according to polymerization after
The Similarity value for the search term that search term is inputted with the user, recommends the search term after the polymerization of acquisition successively.
10. device according to claim 7, it is characterised in that the computing module calculate respectively the search term of acquisition with
The Similarity value of the search term of user's input, including：
According to default hierarchical structure, level classification, Ran Houji are carried out to the search term that the search term and the user input
Calculate the Similarity value for the search term that the search term is inputted with the user.
11. device according to claim 7, it is characterised in that the recommending module recommends to obtain successively according to Similarity value
Before the search term obtained, it is additionally operable to：
The Similarity value is decayed, the Similarity value after being decayed；
According to the Similarity value after decay, recommend the search term obtained successively.
12. according to any described devices of claim 7-12, it is characterised in that the acquisition module is obtaining user described
Before the product information clicked in search term Query Result, it is additionally operable to：
The search term of user's input of acquisition is normalized.
13. a kind of electronic equipment, it is characterised in that including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processors are real
The existing method as described in any in claim 1-6.
14. a kind of computer-readable medium, is stored thereon with computer program, it is characterised in that described program is held by processor
The method as described in any in claim 1-6 is realized during row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710397412.7A CN107291835B (en) | 2017-05-31 | 2017-05-31 | Search term recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710397412.7A CN107291835B (en) | 2017-05-31 | 2017-05-31 | Search term recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107291835A true CN107291835A (en) | 2017-10-24 |
| CN107291835B CN107291835B (en) | 2020-12-22 |
Family
ID=60095051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710397412.7A Active CN107291835B (en) | 2017-05-31 | 2017-05-31 | Search term recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107291835B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145213A (en) * | 2018-08-22 | 2019-01-04 | 清华大学 | Inquiry recommended method and device based on historical information |
| CN110619076A (en) * | 2018-12-25 | 2019-12-27 | 北京时光荏苒科技有限公司 | Search term recommendation method and device, computer and storage medium |
| CN111475729A (en) * | 2020-04-07 | 2020-07-31 | 腾讯科技（深圳）有限公司 | Search content recommendation method and device |
| CN111538903A (en) * | 2020-04-17 | 2020-08-14 | 北京字节跳动网络技术有限公司 | Method and device for determining search recommended word, electronic equipment and computer readable medium |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334784A (en) * | 2008-07-30 | 2008-12-31 | 施章祖 | Computer auxiliary report and knowledge base generation method |
| CN102999619A (en) * | 2012-11-30 | 2013-03-27 | 北京奇虎科技有限公司 | Mobile terminal, server and method for realizing searching |
| CN103218719A (en) * | 2012-01-19 | 2013-07-24 | 阿里巴巴集团控股有限公司 | Method and system of e-commerce website navigation |
| CN103279565A (en) * | 2013-06-14 | 2013-09-04 | 北京艾德思奇科技有限公司 | Advertisement placement tracking method and system |
| CN103577473A (en) * | 2012-08-03 | 2014-02-12 | 纽海信息技术（上海）有限公司 | Classification and disambiguation method, classification and disambiguation device and system thereof |
| CN103914492A (en) * | 2013-01-09 | 2014-07-09 | 阿里巴巴集团控股有限公司 | Method for query term fusion, method for commodity information publish and method and system for searching |
| CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
| US20140359484A1 (en) * | 2013-05-28 | 2014-12-04 | Zooz Mobile Ltd. | System and method for provision of computerized one-stop invitations and elimination of duplicated data entry |
| CN104834698A (en) * | 2015-04-27 | 2015-08-12 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN104899276A (en) * | 2015-05-29 | 2015-09-09 | 百度在线网络技术（北京）有限公司 | Mobile search recommending method and apparatus |
| CN105069168A (en) * | 2015-08-28 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Search word recommendation method and apparatus |
| CN105068716A (en) * | 2015-08-11 | 2015-11-18 | 广东欧珀移动通信有限公司 | Information search method and device |
| CN105320706A (en) * | 2014-08-05 | 2016-02-10 | 阿里巴巴集团控股有限公司 | Processing method and device of search result |
| CN105630813A (en) * | 2014-10-30 | 2016-06-01 | 苏宁云商集团股份有限公司 | Keyword recommendation method and system based on user-defined template |
| CN105761101A (en) * | 2016-02-04 | 2016-07-13 | 云南今日游情科技有限公司 | High-precision advertisement push system and method of mobile terminal based on mutual selection |
| CN105930488A (en) * | 2016-05-03 | 2016-09-07 | 乐视控股（北京）有限公司 | Information search processing method and apparatus |
| CN106326259A (en) * | 2015-06-26 | 2017-01-11 | 苏宁云商集团股份有限公司 | Construction method and system for commodity labels in search engine, and search method and system |
| CN106407457A (en) * | 2016-09-30 | 2017-02-15 | 北京奇虎科技有限公司 | Method for recommending search terms and searching method and device |
-
2017
- 2017-05-31 CN CN201710397412.7A patent/CN107291835B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334784A (en) * | 2008-07-30 | 2008-12-31 | 施章祖 | Computer auxiliary report and knowledge base generation method |
| CN103218719A (en) * | 2012-01-19 | 2013-07-24 | 阿里巴巴集团控股有限公司 | Method and system of e-commerce website navigation |
| CN103577473A (en) * | 2012-08-03 | 2014-02-12 | 纽海信息技术（上海）有限公司 | Classification and disambiguation method, classification and disambiguation device and system thereof |
| CN102999619A (en) * | 2012-11-30 | 2013-03-27 | 北京奇虎科技有限公司 | Mobile terminal, server and method for realizing searching |
| CN103914492A (en) * | 2013-01-09 | 2014-07-09 | 阿里巴巴集团控股有限公司 | Method for query term fusion, method for commodity information publish and method and system for searching |
| US20140359484A1 (en) * | 2013-05-28 | 2014-12-04 | Zooz Mobile Ltd. | System and method for provision of computerized one-stop invitations and elimination of duplicated data entry |
| CN103279565A (en) * | 2013-06-14 | 2013-09-04 | 北京艾德思奇科技有限公司 | Advertisement placement tracking method and system |
| CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
| CN105320706A (en) * | 2014-08-05 | 2016-02-10 | 阿里巴巴集团控股有限公司 | Processing method and device of search result |
| CN105630813A (en) * | 2014-10-30 | 2016-06-01 | 苏宁云商集团股份有限公司 | Keyword recommendation method and system based on user-defined template |
| CN104834698A (en) * | 2015-04-27 | 2015-08-12 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN104899276A (en) * | 2015-05-29 | 2015-09-09 | 百度在线网络技术（北京）有限公司 | Mobile search recommending method and apparatus |
| CN106326259A (en) * | 2015-06-26 | 2017-01-11 | 苏宁云商集团股份有限公司 | Construction method and system for commodity labels in search engine, and search method and system |
| CN105068716A (en) * | 2015-08-11 | 2015-11-18 | 广东欧珀移动通信有限公司 | Information search method and device |
| CN105069168A (en) * | 2015-08-28 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Search word recommendation method and apparatus |
| CN105761101A (en) * | 2016-02-04 | 2016-07-13 | 云南今日游情科技有限公司 | High-precision advertisement push system and method of mobile terminal based on mutual selection |
| CN105930488A (en) * | 2016-05-03 | 2016-09-07 | 乐视控股（北京）有限公司 | Information search processing method and apparatus |
| CN106407457A (en) * | 2016-09-30 | 2017-02-15 | 北京奇虎科技有限公司 | Method for recommending search terms and searching method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145213A (en) * | 2018-08-22 | 2019-01-04 | 清华大学 | Inquiry recommended method and device based on historical information |
| CN110619076A (en) * | 2018-12-25 | 2019-12-27 | 北京时光荏苒科技有限公司 | Search term recommendation method and device, computer and storage medium |
| CN110619076B (en) * | 2018-12-25 | 2023-04-07 | 北京时光荏苒科技有限公司 | Search term recommendation method and device, computer and storage medium |
| CN111475729A (en) * | 2020-04-07 | 2020-07-31 | 腾讯科技（深圳）有限公司 | Search content recommendation method and device |
| CN111475729B (en) * | 2020-04-07 | 2023-07-25 | 腾讯科技（深圳）有限公司 | Search content recommendation method and device |
| CN111538903A (en) * | 2020-04-17 | 2020-08-14 | 北京字节跳动网络技术有限公司 | Method and device for determining search recommended word, electronic equipment and computer readable medium |
| CN111538903B (en) * | 2020-04-17 | 2023-03-31 | 抖音视界有限公司 | Method and device for determining search recommended word, electronic equipment and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107291835B (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107105031A (en) | Information-pushing method and device | |
| CN109460513A (en) | Method and apparatus for generating clicking rate prediction model | |
| CN107256267A (en) | Querying method and device | |
| CN107609890A (en) | A kind of method and apparatus of order tracking | |
| CN111444304B (en) | Search ordering method and device | |
| CN111061956A (en) | Method and apparatus for generating information | |
| CN107291835A (en) | A kind of recommendation method and apparatus of search term | |
| CN110276065B (en) | Method and device for processing item comments | |
| CN108776692A (en) | Method and apparatus for handling information | |
| CN107908615A (en) | A kind of method and apparatus for obtaining search term corresponding goods classification | |
| CN110020162A (en) | User identification method and device | |
| CN107346344A (en) | The method and apparatus of text matches | |
| CN107908662A (en) | The implementation method and realization device of search system | |
| CN110309142A (en) | The method and apparatus of regulation management | |
| CN107329583A (en) | A kind of method and apparatus for calculating associational word priority | |
| CN110866625A (en) | Promotion index information generation method and device | |
| CN107562941A (en) | Data processing method and its system | |
| US20180129664A1 (en) | System and method to recommend a bundle of items based on item/user tagging and co-install graph | |
| CN107634942A (en) | The method and apparatus for identifying malicious requests | |
| EP4134885A2 (en) | Method and apparatus of recommending data, electronic device, and medium | |
| CN112784861A (en) | Similarity determination method and device, electronic equipment and storage medium | |
| CN112734462B (en) | Information recommendation method, device, equipment and medium | |
| CN110766488A (en) | Method and device for automatically determining theme scene | |
| CN110032283A (en) | The method and apparatus that a kind of pair of associational word is ranked up | |
| CN113743906A (en) | Method and device for determining service processing strategy |
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 |