CN104298762A - Information providing method and information providing device - Google Patents
Information providing method and information providing device Download PDFInfo
- Publication number
- CN104298762A CN104298762A CN201410569578.9A CN201410569578A CN104298762A CN 104298762 A CN104298762 A CN 104298762A CN 201410569578 A CN201410569578 A CN 201410569578A CN 104298762 A CN104298762 A CN 104298762A
- Authority
- CN
- China
- Prior art keywords
- crucial phrase
- keyword
- node
- match
- successful
- 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
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to an information providing method and an information providing device. The information providing method comprises the following steps of extracting keywords in received contents to form a first keyword group; matching the first keyword group in a database which is stored with keyword groups and first information corresponding to the keyword groups and has a tree structure; outputting the first information corresponding to the first keyword group when the first keyword group is successfully matched in the database; and generating second information according to a keyword stored in a secondary junction of a junction with the last successfully matched keyword in the first keyword group when the first keyword group is not successfully matched in the database. By the information providing method, the keyword groups can be matched quickly, and answers of a user can be guided in the existing keyword group range in the tree structure, so that information can be provided for the user finally.
Description
Technical field
The disclosure relates to e-commerce field, particularly relates to a kind of method and the device that provide information.
Background technology
Current, people by ecommerce, namely carry out business transaction activity by electronic tools such as internets more and more.When carrying out business transaction activity, for user provides customer service more and more important, because the quality of customer service affects the marketing situation of product to a certain extent.Usually, customer service can be provided by the mode of online customer service, such as, can text chat, voice-enabled chat etc. be comprised.Contact staff and user can solve pre-sales, the relevant issues such as after sale of user to commodity effectively by the mode of chatting.
Along with number of users constantly increases, contact staff's faces enormous challenge.In order to provide customer service timely and effectively to ever-increasing user, modal method improves the efficiency of contact staff and increases the quantity of artificial customer service.But these two kinds of methods are all subject to a lot of restriction, cannot fundamentally solve the problem that cannot meet growing user.
Therefore, need badly and a kind ofly provide the method for information to improve the efficiency of customer service for user.
Summary of the invention
For overcoming Problems existing in correlation technique, the disclosure provides a kind of method and apparatus providing information.
According to the first aspect of disclosure embodiment, a kind of method providing information is provided, comprises:
Extract the keyword received in content and form the first crucial phrase;
Described first crucial phrase is mated in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase;
When in the database described in successful match during the first crucial phrase, export the first information that described first crucial phrase is corresponding;
When the described first crucial phrase of unsuccessful coupling in the database, generate the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
In one embodiment, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, comprising:
Obtain described crucial phrase and information corresponding to described crucial phrase;
According to preset matched rule perform first coupling step: by the N number of keyword in described crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, after making N=N+1, repeat described first coupling step; When mating unsuccessful, for the newly-built child node of described father node is to store N number of keyword, and after making N=N+1, repeat described first coupling step; Wherein, N is initially 1.
In one embodiment, describedly in the database of tree construction being previously stored with crucial phrase and information corresponding to crucial phrase, mate described first crucial phrase, comprising:
According to preset matched rule perform second coupling step: by the N number of keyword in described first crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, described second coupling step is repeated after making N=N+1, until to all keywords in described first crucial phrase, all the match is successful and last node that the match is successful is branch node, then determine the first crucial phrase described in successful match in the database; Otherwise, then the described first crucial phrase of unsuccessful coupling is in the database determined; Wherein, N is initially 1.
In one embodiment, described default matched rule comprises: when two keywords carrying out mating are synonyms, then the match is successful.
In one embodiment, when the described first crucial phrase of unsuccessful coupling in the database, after generating the second information according to the keyword in the child node of the node at last keyword place of successful match in described first crucial phrase, described method also comprises: from described child node, mate the keyword in the content again received, when it fails to match, using the keyword that again receives in content as the new first crucial phrase.
In one embodiment, described second information comprises: according to the keyword in the child node of the node at last keyword place of successful match in described first crucial phrase and the question sentence of inquiry template generation preset.
According to the second aspect of disclosure embodiment, a kind of device providing information is provided, comprises:
Extraction module, forms the first crucial phrase for extracting the keyword received in content;
First matching module, for mating described first crucial phrase in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase;
Output module, for when in the database described in successful match during the first crucial phrase, exports the first information that described first crucial phrase is corresponding;
Generation module, for when the described first crucial phrase of unsuccessful coupling in the database, generates the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
In one embodiment, described device also comprises:
Acquisition module, for obtaining described crucial phrase and information corresponding to described crucial phrase;
Second matching module, for according to preset matched rule perform first coupling step: by the N number of keyword in described crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, after making N=N+1, repeat described first coupling step; When mating unsuccessful, for the newly-built child node of the node storing N-1 keyword is to store N number of keyword, and after making N=N+1, repeat described first coupling step; Wherein, N is initially 1.
In one embodiment, described first matching module is used for: perform the second coupling step according to the matched rule preset: by the N number of keyword in described first crucial phrase in the N+1 layer node of described tree construction, father node is mate in the keyword of the node storage of the node of storage N-1 keyword, when the match is successful, described second coupling step is repeated after making N=N+1, until to all keywords in described first crucial phrase, all the match is successful and last node that the match is successful is branch node, then determine the first crucial phrase described in successful match in the database, otherwise, then the described first crucial phrase of unsuccessful coupling is in the database determined, wherein, N is initially 1.
In one embodiment, described default matched rule comprises: when two keywords carrying out mating are synonyms, then the match is successful.
In one embodiment, described device also comprises: the 3rd matching module, for mating the keyword in the content that again receives from described child node, when it fails to match, using the keyword that again receives in content as the new first crucial phrase.
In one embodiment, described second information comprises: according to the keyword in the child node of the node at last keyword place of successful match in described first crucial phrase and the question sentence of inquiry template generation preset.
According to the third aspect of disclosure embodiment, a kind of device providing information is provided, comprises:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Extract the keyword received in content and form the first crucial phrase;
Described first crucial phrase is mated in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase;
When in the database described in successful match during the first crucial phrase, export the first information that described first crucial phrase is corresponding;
When the described first crucial phrase of unsuccessful coupling in the database, generate the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: in a database with the crucial phrase that storage of data structure is made up of orderly keyword, and such storage mode can realize mating faster.And, when unsuccessful coupling, the keyword that can also store according to the child node of the node at last keyword place of successful match in crucial phrase generates the second information, this just means that the second information of generation has guided bone, the answer of user can be guided in tree construction in existing keyword class range, thus finally can provide information for user, solve the problem of user.Therefore, the method for information that provides in the present embodiment can make customer service more quickly and effectively.
Should be understood that, it is only exemplary and explanatory that above general description and details hereinafter describe, and can not limit the disclosure.
Accompanying drawing explanation
Accompanying drawing to be herein merged in instructions and to form the part of this instructions, shows and meets embodiment of the present disclosure, and is used from instructions one and explains principle of the present disclosure.
Fig. 1 is a kind of process flow diagram providing the method for information according to an exemplary embodiment.
Fig. 2 is a kind of process flow diagram setting up tree construction provided in the method for information according to an exemplary embodiment.
Fig. 3 is that a kind of according to an EXAMPLE Example provides the table structure set up in the method for information.
Fig. 4 is a kind of process flow diagram providing the method for information according to an exemplary embodiment.
Fig. 5 is a kind of process flow diagram providing the method for information according to an exemplary embodiment.
Fig. 6 is a kind of block diagram providing the device of information according to an exemplary embodiment.
Fig. 7 is a kind of block diagram providing the device of information according to an exemplary embodiment.
Fig. 8 is a kind of block diagram providing the device of information according to an exemplary embodiment.
Fig. 9 is the block diagram of a kind of device according to an exemplary embodiment.
Embodiment
Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the disclosure.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present disclosure are consistent.
Fig. 1 is a kind of process flow diagram providing the method for information according to an exemplary embodiment, as shown in Figure 1, provides the method for information to can be used for, in server, comprising the following steps:
In step s 11, extract the keyword received in content and form the first crucial phrase.
In step s 12, in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase, described first crucial phrase is mated; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase.
In step s 13, when in the database described in successful match during the first crucial phrase, the first information that described first crucial phrase is corresponding is exported.
In step S14, when the described first crucial phrase of unsuccessful coupling in the database, generate the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
In the present embodiment, in a database with the crucial phrase that storage of data structure is made up of orderly keyword, such storage mode can realize mating faster.And, when unsuccessful coupling, the keyword that can also store according to the child node of the node at last keyword place of successful match in crucial phrase generates the second information, this just means that the second information of generation has guided bone, the answer of user can be guided in tree construction in existing keyword class range, thus finally can provide information for user, solve the problem of user.Therefore, the method for information that provides in the present embodiment can make customer service more quickly and effectively.
Fig. 2 is a kind of process flow diagram providing the method for information according to another exemplary embodiment, in this embodiment, comprises the method generating the crucial phrase of storage of data structure.As shown in Figure 2, the method for information is provided to can be used for, in server, comprising the following steps:
In the step s 21: obtain crucial phrase.
The mode analysis capturing customer service chat log can be adopted to draw one or more business that user is concerned about, for each business, extract one and more than one keyword, and the part of speech, sentence element etc. that mark each keyword are (such as: verb, noun, subject, predicate, the adverbial modifier etc.), then form crucial phrase by these keywords.Such as, the crucial phrase A of acquisition is: mobile phone, application, after sale; Crucial phrase B is: mobile phone, how, return goods; Crucial phrase C is: TV, application, the return of goods.
In step S22: obtain the information that each crucial phrase is corresponding.
This information can be available to the self-service business of user, namely answers the answer of customer problem.Such as, the information that above-mentioned crucial phrase " how, application, after sale " is corresponding can be " you are good, and you can log in official website--find you to want to apply for that order of product after sale in my order--clicking order details--selection is applied for a refund/(return goods, exchange goods, keep in repair) after sale.If you cannot apply for, you also can contact artificial customer service and help you to apply for ".
In step S23: set up an empty tree.
The ground floor node of empty tree is root node root.
Then, following steps are performed to each crucial phrase:
In step s 24 which: by the N number of keyword in crucial phrase in the N+1 layer node of tree construction, father node be the node of storage N-1 keyword node store keyword in mate, N is initially 1.
In step s 25: judge whether that the match is successful, if so, step S29 is performed; If not, step S26 is performed.
In step S26: for the newly-built child node of father node is to store N number of keyword.
In step s 27: judge whether N equals the number of the keyword in crucial phrase, if so, then step S28 is performed; If not, repeated execution of steps S24 after N=N+1 is made.
In step S28: information corresponding for crucial phrase is stored into after in newly-built child node and terminates.
In step S29: judge whether N equals the number of the keyword in crucial phrase, if so, then terminates; If not, repeated execution of steps S24 after N=N+1 is made.
Such as, for the crucial phrase A " mobile phone, after sale, return goods " obtained, crucial phrase B " mobile phone, after sale, exchange goods ", crucial phrase C " mobile phone, price ", crucial phrase D " TV, price ", the tree construction of foundation as shown in Figure 3.This structure make use of high-level efficiency and the key to the issue word randomness of Hash table, therefore can the very fast matching keywords group in ground.
Fig. 4 is a kind of process flow diagram providing the method for information according to another exemplary embodiment, in this embodiment, is included in the method for matching keywords group in the database of tree construction.As shown in Figure 4, the method for information is provided to can be used for, in server, comprising the following steps:
In step S41: receive the content that user sends.
In step S42, extract the keyword received in content and form the first crucial phrase.
In step S43, by the N number of keyword in the first crucial phrase in the N+1 layer node of tree construction, father node be the node of storage N-1 keyword node store keyword in mate, wherein, N is initially 1.
In step S44, judge whether that the match is successful, if so, perform step S45; If not, step S48 is performed.
In step S45, judge whether N equals the number of the keyword in crucial phrase, if so, then perform step S46; If not, repeated execution of steps S43 after N=N+1 is made.
In step S46, judge whether the node that the match is successful is a node, if so, perform step S47; If not, step S48 is performed.
In step S47, the information stored in the successful node of output matching.
In step S48, generate the second information according to the keyword that the child node of the node of last keyword that the match is successful stores.
Such as, when the first crucial phrase is " mobile phone, price ", to the 1st keyword " mobile phone ", mate in the 2nd layer of node of tree construction, after the match is successful, to the 2nd keyword " price ", in the 1st node layer of tree construction " mobile phone " node child node in mate, after the match is successful, be that the information output stored in the node " price " of " mobile phone " is supplied to user by father node.
Such as, when the first crucial phrase is " mobile phone, after sale ", after to the 1st keyword " mobile phone " and the 2nd keyword " after sale ", the match is successful, the node that the match is successful is not a node, therefore, the second information is generated according to the child node " return of goods " of " after sale " node and " exchanging goods ".
Wherein, the second information can be the question sentence according to the keyword in the child node of the node at last keyword place of successful match in described first crucial phrase and default inquiry template generation.Such as, according to the clause of natural language, can apply mechanically fixing inquiry template, SVO is determined shape benefit clause and is inquired.Such as, the second information that the child node " return of goods " of above-mentioned basis " after sale " node and " exchanging goods " generate is: " may I ask you needs the return of goods still to exchange goods? " thus user can be guided to carry out next step answer, must think that user provides the information of needs with final.Therefore, due to the mode of the crucial phrase be made up of orderly keyword with storage of data structure taked in the present embodiment, the mode of the enquirement of guiding can be provided to guide user, and, there is incidence relation in the context of the problem of the guiding proposed, similarly be more interpersonal chat, experience hommization more.
In addition, a keyword can have multiple expression way, and such as, " price ", " how much " all give expression to the meaning of inquiry commodity value, are therefore defined as synonym.Defining a word in synonym is synon subject term.Such as, in above-mentioned synonym, price is defined as subject term.In the above-described embodiments, the successful rule of Keywords matching can comprise: as long as two keywords are that synonym is coupling, otherwise for not mate.
Fig. 5 is a kind of process flow diagram providing the method for information according to another exemplary embodiment, in this embodiment, after again receiving the answer of same user after comprising output second information, again carries out the method for crucial phrase coupling.As shown in Figure 5, the method for information is provided to can be used for, in server, comprising the following steps:
In step s 51: receive the content that user sends.
In step S52, extract the keyword received in content and form the first crucial phrase.
In step S53, by the N number of keyword in the first crucial phrase in the N+1 layer node of tree construction, father node be the node of storage N-1 keyword node store keyword in mate, wherein, N is initially 1.
In step S54, judge whether that the match is successful, if so, perform step S55; If not, step S58 is performed.
In step S55, judge whether N equals the number of the keyword in crucial phrase, if so, then perform step S56; If not, repeated execution of steps S53 after N=N+1 is made.
In step S56, judge whether the node that the match is successful is a node, if so, perform step S57; If not, step S58 is performed.
In step S57, terminate after the information stored in the successful node of output matching.
In step S58, generate the second information according to the keyword that the child node of the node of last keyword that the match is successful stores.
In step S59, again receive the content that same user sends.
Wherein, can also limit by setup times, in Preset Time, namely again receive the content that same user sends, then this user humane answers for the second information generated.
In step S510, mate from the child node in step S58 after extracting the keyword again received in content.
In step 511, judge whether that the match is successful, if so, perform step S56; If not, then the keyword again received in content is re-executed step S51 as the new first crucial phrase.
In the present embodiment, when again to receive the content that same user sends after the second information if generate, coupling can be proceeded, thus user can be continued as information is provided.
Fig. 6 is a kind of block diagram providing the device of information according to an exemplary embodiment.With reference to Fig. 6, this device comprises extraction module 601, the first matching module 602, output module 603 and generation module 604.
This extraction module 601 is configured to form the first crucial phrase for extracting the keyword received in content.
This first matching module 602 is configured in the database of the tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase and mates described first crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase.
This output module 603 is configured to, for when in the database described in successful match during the first crucial phrase, export the first information that described first crucial phrase is corresponding.
This generation module 604 is configured to, for when the described first crucial phrase of unsuccessful coupling in the database, generate the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
As shown in Figure 7, described device also comprises:
Acquisition module 605, is configured to for obtaining described crucial phrase and information corresponding to described crucial phrase.
Second matching module 606, be configured to for according to preset matched rule perform first coupling step: by the N number of keyword in described crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, after making N=N+1, repeat described first coupling step; When mating unsuccessful, for the newly-built child node of the node storing N-1 keyword is to store N number of keyword, and after making N=N+1, repeat described first coupling step; Wherein, N is initially 1.
First matching module 602 be configured to for:
According to preset matched rule perform second coupling step: by the N number of keyword in described first crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, described second coupling step is repeated after making N=N+1, until to all keywords in described first crucial phrase, all the match is successful and last node that the match is successful is branch node, then determine the first crucial phrase described in successful match in the database; Otherwise, then the described first crucial phrase of unsuccessful coupling is in the database determined; Wherein, N is initially 1.
The matched rule preset comprises: when two keywords carrying out mating are synonyms, then the match is successful.
As shown in Figure 8, described device also comprises:
3rd matching module 607, is configured to the keyword for mating from described child node in the content that again receives.
Described second information comprises: according to the keyword in the child node of the node at last keyword place of successful match in described first crucial phrase and the question sentence of inquiry template generation preset.
About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.
In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, as shown in Figure 9, such as, comprise the storer 901 of instruction, above-mentioned instruction can perform said method by the processor 902 of device 900.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.
A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is performed by the processor of terminal, make terminal can perform a kind of method providing information, described method comprises:
Extract the keyword received in content and form the first crucial phrase;
Described first crucial phrase is mated in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase;
When in the database described in successful match during the first crucial phrase, export the first information that described first crucial phrase is corresponding;
When the described first crucial phrase of unsuccessful coupling in the database, generate the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
Fig. 9 is a kind of for providing the block diagram of the device 1900 of information according to an exemplary embodiment.Such as, device 1900 may be provided in a server.With reference to Fig. 9, device 1900 comprises processing components 1922, and it comprises one or more processor further, and the memory resource representated by storer 1932, can such as, by the instruction of the execution of processing element 1922, application program for storing.The application program stored in storer 1932 can comprise each module corresponding to one group of instruction one or more.In addition, processing components 1922 is configured to perform instruction, to perform the method for above information: extract the keyword received in content and form the first crucial phrase; Described first crucial phrase is mated in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase; When in the database described in successful match during the first crucial phrase, export the first information that described first crucial phrase is corresponding; When the described first crucial phrase of unsuccessful coupling in the database, generate the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
Device 1900 can also comprise the power management that a power supply module 1926 is configured to actuating unit 1900, and a wired or wireless network interface 1950 is configured to device 1900 to be connected to network, and input and output (I/O) interface 1958.Device 1900 can operate the operating system based on being stored in storer 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
Those skilled in the art, at consideration instructions and after putting into practice invention disclosed herein, will easily expect other embodiment of the present disclosure.The application is intended to contain any modification of the present disclosure, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present disclosure and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present disclosure and spirit are pointed out by claim below.
Should be understood that, the disclosure is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.The scope of the present disclosure is only limited by appended claim.
Claims (13)
1. the method for information is provided, it is characterized in that, comprising:
Extract the keyword received in content and form the first crucial phrase;
Described first crucial phrase is mated in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase;
When in the database described in successful match during the first crucial phrase, export the first information that described first crucial phrase is corresponding;
When the described first crucial phrase of unsuccessful coupling in the database, generate the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
2. method according to claim 1, is characterized in that, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, comprising:
Obtain described crucial phrase and information corresponding to described crucial phrase;
According to preset matched rule perform first coupling step: by the N number of keyword in described crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, after making N=N+1, repeat described first coupling step; When mating unsuccessful, for the newly-built child node of described father node is to store N number of keyword, and after making N=N+1, repeat described first coupling step; Wherein, N is initially 1.
3. method according to claim 1, is characterized in that, describedly in the database of tree construction being previously stored with crucial phrase and information corresponding to crucial phrase, mates described first crucial phrase, comprising:
According to preset matched rule perform second coupling step: by the N number of keyword in described first crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, described second coupling step is repeated after making N=N+1, until to all keywords in described first crucial phrase, all the match is successful and last node that the match is successful is branch node, then determine the first crucial phrase described in successful match in the database; Otherwise, then the described first crucial phrase of unsuccessful coupling is in the database determined; Wherein, N is initially 1.
4. according to the method in claim 2 or 3, it is characterized in that, described default matched rule comprises: when two keywords carrying out mating are synonyms, then the match is successful.
5. method according to claim 1, it is characterized in that, when the described first crucial phrase of unsuccessful coupling in the database, after generating the second information according to the keyword in the child node of the node at last keyword place of successful match in described first crucial phrase, described method also comprises:
The keyword in the content again received is mated from described child node;
When it fails to match, using the keyword that again receives in content as the new first crucial phrase.
6. method according to claim 1, is characterized in that, described second information comprises:
According to the keyword in the child node of the node at last keyword place of successful match in described first crucial phrase and the question sentence of inquiry template generation preset.
7. the device of information is provided, it is characterized in that, comprising:
Extraction module, forms the first crucial phrase for extracting the keyword received in content;
First matching module, for mating described first crucial phrase in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase;
Output module, for when in the database described in successful match during the first crucial phrase, exports the first information that described first crucial phrase is corresponding;
Generation module, for when the described first crucial phrase of unsuccessful coupling in the database, generates the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
8. device according to claim 7, is characterized in that, described device also comprises:
Acquisition module, for obtaining described crucial phrase and information corresponding to described crucial phrase;
Second matching module, for according to preset matched rule perform first coupling step: by the N number of keyword in described crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, after making N=N+1, repeat described first coupling step; When mating unsuccessful, for the newly-built child node of the node storing N-1 keyword is to store N number of keyword, and after making N=N+1, repeat described first coupling step; Wherein, N is initially 1.
9. device according to claim 7, is characterized in that, described first matching module is used for:
According to preset matched rule perform second coupling step: by the N number of keyword in described first crucial phrase in the N+1 layer node of described tree construction, father node be the node of storage N-1 keyword node storage keyword in mate, when the match is successful, described second coupling step is repeated after making N=N+1, until to all keywords in described first crucial phrase, all the match is successful and last node that the match is successful is branch node, then determine the first crucial phrase described in successful match in the database; Otherwise, then the described first crucial phrase of unsuccessful coupling is in the database determined; Wherein, N is initially 1.
10. device according to claim 8 or claim 9, it is characterized in that, described default matched rule comprises: when two keywords carrying out mating are synonyms, then the match is successful.
11. devices according to claim 7, is characterized in that, described device also comprises:
3rd matching module, for mating the keyword in the content that again receives from described child node, when it fails to match, using the keyword that again receives in content as the new first crucial phrase.
12. devices according to claim 7, is characterized in that, described second information comprises:
According to the keyword in the child node of the node at last keyword place of successful match in described first crucial phrase and the question sentence of inquiry template generation preset.
13. 1 kinds of devices, is characterized in that, comprising:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Extract the keyword received in content and form the first crucial phrase;
Described first crucial phrase is mated in the database of tree construction being previously stored with crucial phrase and the first information corresponding to described crucial phrase; Wherein, in described tree construction according to the rale store storing different keywords in the order of keyword in described crucial phrase and the same one-level node of subtree crucial phrase, and in the node at last keyword place of described crucial phrase, store the first information corresponding to described crucial phrase;
When in the database described in successful match during the first crucial phrase, export the first information that described first crucial phrase is corresponding;
When the described first crucial phrase of unsuccessful coupling in the database, generate the second information according to the keyword that the child node of the node at last keyword place of successful match in described first crucial phrase stores.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410569578.9A CN104298762B (en) | 2014-10-22 | 2014-10-22 | The method and apparatus that information is provided |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410569578.9A CN104298762B (en) | 2014-10-22 | 2014-10-22 | The method and apparatus that information is provided |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104298762A true CN104298762A (en) | 2015-01-21 |
CN104298762B CN104298762B (en) | 2018-04-06 |
Family
ID=52318487
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410569578.9A Active CN104298762B (en) | 2014-10-22 | 2014-10-22 | The method and apparatus that information is provided |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104298762B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104794179A (en) * | 2015-04-07 | 2015-07-22 | 无锡天脉聚源传媒科技有限公司 | Video quick indexing method and device based on knowledge tree |
CN105045919A (en) * | 2015-08-24 | 2015-11-11 | 北京云知声信息技术有限公司 | Information output method and apparatus |
CN105939246A (en) * | 2016-04-15 | 2016-09-14 | 北京思特奇信息技术股份有限公司 | Intelligent customer service method and system based on IM |
CN106933818A (en) * | 2015-12-29 | 2017-07-07 | 北京明朝万达科技股份有限公司 | A kind of quick multiple key text matching technique and device |
CN113905247A (en) * | 2021-09-27 | 2022-01-07 | 北京达佳互联信息技术有限公司 | Information interaction method and device, electronic equipment and storage medium |
-
2014
- 2014-10-22 CN CN201410569578.9A patent/CN104298762B/en active Active
Non-Patent Citations (4)
Title |
---|
朱鲲鹏: ""模式匹配技术在自动答疑***中的应用研究"", 《万方学位论文》 * |
杨晓明 等: ""模式匹配在中文问答***中的应用研究"", 《科学技术与工程》 * |
狄方春: ""基于模式匹配的自动答疑***的研究"", 《万方学位论文》 * |
赵赟 等: ""智能答疑***中语义网的研究与应用"", 《微机发展》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104794179A (en) * | 2015-04-07 | 2015-07-22 | 无锡天脉聚源传媒科技有限公司 | Video quick indexing method and device based on knowledge tree |
CN105045919A (en) * | 2015-08-24 | 2015-11-11 | 北京云知声信息技术有限公司 | Information output method and apparatus |
WO2017032084A1 (en) * | 2015-08-24 | 2017-03-02 | 北京云知声信息技术有限公司 | Information output method and apparatus |
CN107077510A (en) * | 2015-08-24 | 2017-08-18 | 北京云知声信息技术有限公司 | A kind of information output method and device |
CN105045919B (en) * | 2015-08-24 | 2019-08-16 | 北京云知声信息技术有限公司 | A kind of information output method and device |
CN106933818A (en) * | 2015-12-29 | 2017-07-07 | 北京明朝万达科技股份有限公司 | A kind of quick multiple key text matching technique and device |
CN106933818B (en) * | 2015-12-29 | 2019-06-11 | 北京明朝万达科技股份有限公司 | A kind of quick multiple key text matching technique and device |
CN105939246A (en) * | 2016-04-15 | 2016-09-14 | 北京思特奇信息技术股份有限公司 | Intelligent customer service method and system based on IM |
CN113905247A (en) * | 2021-09-27 | 2022-01-07 | 北京达佳互联信息技术有限公司 | Information interaction method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN104298762B (en) | 2018-04-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113962315B (en) | Model pre-training method, device, equipment, storage medium and program product | |
US11481562B2 (en) | Method and apparatus for evaluating translation quality | |
US20200342181A1 (en) | Method and system for automatic formality classification | |
US10423665B2 (en) | Method and system for generating a conversational agent by automatic paraphrase generation based on machine translation | |
US9805717B2 (en) | Voice-based input using natural language processing for interfacing with one or more devices | |
US20180336193A1 (en) | Artificial Intelligence Based Method and Apparatus for Generating Article | |
US11756532B2 (en) | Intelligence-driven virtual assistant for automated idea documentation | |
CN104298762A (en) | Information providing method and information providing device | |
US10540585B2 (en) | Training sequence generation neural networks using quality scores | |
CN110727761B (en) | Object information acquisition method and device and electronic equipment | |
CN116127020A (en) | Method for training generated large language model and searching method based on model | |
CN110297897B (en) | Question-answer processing method and related product | |
CN116127046A (en) | Training method for generating large language model and man-machine voice interaction method based on model | |
CN110738056B (en) | Method and device for generating information | |
CN110929007A (en) | Electric power marketing knowledge system platform and application method | |
CN117633196B (en) | Question-answering model construction method and project question-answering method | |
CN112100355A (en) | Intelligent interaction method, device and equipment | |
US20230317058A1 (en) | Spoken language processing method and apparatus, and storage medium | |
CN115994522A (en) | Text processing method, article generating method and text processing model training method | |
CN116049370A (en) | Information query method and training method and device of information generation model | |
CN116362331A (en) | Knowledge point filling method based on man-machine cooperation construction knowledge graph | |
CN114638221A (en) | Business model generation method and device based on business requirements | |
CN114239604A (en) | Online consultation processing method and device and computer equipment | |
CN113515932A (en) | Method, device, equipment and storage medium for processing question and answer information | |
CN112328871A (en) | Reply generation method, device, equipment and storage medium based on RPA module |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |