CN107833088A - Content providing, device and smart machine - Google Patents
Content providing, device and smart machine Download PDFInfo
- Publication number
- CN107833088A CN107833088A CN201710964960.3A CN201710964960A CN107833088A CN 107833088 A CN107833088 A CN 107833088A CN 201710964960 A CN201710964960 A CN 201710964960A CN 107833088 A CN107833088 A CN 107833088A
- Authority
- CN
- China
- Prior art keywords
- end article
- network data
- knowledge
- user
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a kind of content providing, device and smart machine, and wherein method includes：Obtain the search statement of user's input；Carry out intention assessment to search statement, the problem of determining user type and corresponding merchandise classification；From default knowledge of goods storehouse, the knowledge data of end article corresponding with merchandise classification is obtained；According to problem types, search result is built using the knowledge data of end article；Being returned to user includes the search result of end article.This method not only make it that the search result that user gets is more objective and accurate, and with ageing, and human-edited's cost is also saved, user's request is met, improves the popularization rate of commodity.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of content providing, device and smart machine.
Background technology
With the high speed development of Internet technology, network changes the life of people more and more.Such as user can be with
Desired information is obtained by internet and search engine technique.Particularly, information is obtained on question and answer class website.
However, in actual use, when user obtains information by answering class website, the information base that typically gets
All by manually editing in sheet.This can just make it that the information content that user obtains is of poor quality, ageing deficiency unavoidably, very
To stronger personal subjective colo(u)r being present, there is certain one-sidedness, limitation and hysteresis quality, cause using effect bad.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.
Therefore, first purpose of the present invention is to propose a kind of content providing, this method not only causes user to obtain
The search result got is more objective and accurate, and with ageing, and human-edited's cost is also saved, meeting user needs
Ask, improve the popularization rate of commodity.
Second object of the present invention is to propose a kind of content providing device.
Third object of the present invention is to propose a kind of smart machine.
Fourth object of the present invention is to propose a kind of computer-readable recording medium.
For the above-mentioned purpose, first aspect present invention embodiment proposes a kind of content providing, including：
Obtain the search statement of user's input；
Carry out intention assessment to the search statement, the problem of determining the user type and corresponding merchandise classification；
From default knowledge of goods storehouse, the knowledge data of end article corresponding with the merchandise classification is obtained；
According to described problem type, search result is built using the knowledge data of the end article；
Being returned to the user includes the search result of the end article.
In the content providing that the present embodiment provides, by obtaining the search statement of user's input, search statement is entered
Row intention assessment, type and corresponding merchandise classification the problem of to determine user, then from default knowledge of goods storehouse, obtain
The knowledge data of end article corresponding with merchandise classification, and searched according to problem types using the knowledge data structure of end article
Hitch fruit, right rear line return to the search result for including end article.Thus, when user obtains information, not only to use
The search result that family is got is more objective and accurate, and with ageing, and human-edited's cost is also saved, meet use
Family demand, while improve the popularization rate of commodity.
In addition, the content providing that the above embodiment of the present invention proposes can also have technical characteristic additional as follows：
In one embodiment of the invention, the knowledge data for obtaining end article corresponding with the merchandise classification
Before, in addition to：
According to the essential information of the end article, each network data associated with the end article is obtained；
According to each network data, the essential information of the end article and general knowledge data, the knowledge of goods is established
Storehouse.
In another embodiment of the present invention, after each network data that the acquisition associates with the end article,
Also include：
The entity attribute included according to each network data, Screening Treatment is carried out to each network data；
According to the source of each network data, comment information and/or semantic integrity degree, it is determined that each network data after screening
Score.
In another embodiment of the present invention, after each network data that the acquisition associates with the end article,
Also include：
Each network data is parsed, determines problem types corresponding to each network data；
According to described problem type, the relation map of each network data and the end article is established.
In another embodiment of the present invention, it is described according to described problem type, utilize the knowledge of the end article
Data build search result, including：
According to described problem type, target masterplate is determined；
According to the target masterplate, search result is built using the knowledge data of the end article.
For the above-mentioned purpose, second aspect of the present invention embodiment proposes a kind of content providing device, including：
First acquisition module, for obtaining the search statement of user's input；
First determining module, for carrying out intention assessment to the search statement, the problem of determining the user type and
Corresponding merchandise classification；
Second acquisition module, for from default knowledge of goods storehouse, obtaining target business corresponding with the merchandise classification
The knowledge data of product；
Module is built, for according to described problem type, search result to be built using the knowledge data of the end article；
Respond module, the search result of the end article is included for being returned to the user.
In the content providing device that the present embodiment provides, by obtaining the search statement of user's input, search statement is entered
Row intention assessment, type and corresponding merchandise classification the problem of to determine user, then from default knowledge of goods storehouse, obtain
The knowledge data of end article corresponding with merchandise classification, and searched according to problem types using the knowledge data structure of end article
Hitch fruit, right rear line return to the search result for including end article.Thus, when user obtains information, not only to use
The search result that family is got is more objective and accurate, and with ageing, and human-edited's cost is also saved, meet use
Family demand, while improve the popularization rate of commodity.
In addition, the content providing device that the above embodiment of the present invention proposes can also have technical characteristic additional as follows：
In one embodiment of the invention, in addition to：
3rd acquisition module, for the essential information according to the end article, obtain what is associated with the end article
Each network data；
Module is established, for according to each network data, the essential information of the end article and general knowledge data, establishing
The knowledge of goods storehouse.
In another embodiment of the present invention, in addition to：
Screening module, for the entity attribute included according to each network data, each network data is carried out
Screening Treatment；
Grading module, for the source according to each network data, comment information and/or semantic integrity degree, it is determined that after screening
Each network data score.
In another embodiment of the present invention, in addition to：
Second determining module, for parsing each network data, determine to ask corresponding to each network data
Inscribe type；
Second establishes module, for according to described problem type, establishing each network data and the end article
Relation map.
In another embodiment of the present invention, the structure module, is specifically included：
According to described problem type, target masterplate is determined；
According to the target masterplate, search result is built using the knowledge data of the end article.
For the above-mentioned purpose, third aspect present invention embodiment proposes a kind of smart machine, including memory, processor
And storage is on a memory and the computer program that can run on a processor, during the computing device described program, realization
Content providing described in first aspect embodiment.
In the smart machine that the present embodiment provides, by obtaining the search statement of user's input, search statement is anticipated
Figure identification, type and corresponding merchandise classification the problem of to determine user, then from default knowledge of goods storehouse, obtain and business
The knowledge data of the not corresponding end article of category, and the knowledge data structure search knot according to problem types using end article
Fruit, right rear line return to the search result for including end article.Thus, when user obtains information, not only user is obtained
The search result got is more objective and accurate, and with ageing, and human-edited's cost is also saved, meeting user needs
Ask, while improve the popularization rate of commodity.
For the above-mentioned purpose, fourth aspect present invention embodiment proposes a kind of computer-readable recording medium, deposits thereon
Computer program is contained, the program realizes the content providing described in first aspect embodiment when being executed by processor.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
Fig. 1 is the flow chart of the content providing of one embodiment of the invention；
Fig. 2 is the flow chart for establishing knowledge of goods storehouse of one embodiment of the invention；
Fig. 3 is the schematic diagram of the search result of one embodiment of the invention；
Fig. 4 is the flow chart of the content providing of another embodiment of the present invention；
Fig. 5 is the structural representation of the content providing device of one embodiment of the invention；
Fig. 6 is the structural representation of the smart machine of one embodiment of the invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
Present invention is generally directed in the prior art, user is when obtaining information on question and answer class website, the letter of existing acquisition
It is poor to cease content quality, ageing deficiency, or even the information obtained have stronger personal subjective colo(u)r, have necessarily unilateral
Property, limitation and hysteresis quality, the problem of causing using effect bad, propose a kind of content providing.
Content providing proposed by the present invention, the search statement inputted by obtaining user, anticipates to search statement
Figure identification, type and corresponding merchandise classification the problem of to determine user, then from default knowledge of goods storehouse, obtain with
The knowledge data of end article corresponding to merchandise classification, and search is built using the knowledge data of end article according to problem types
As a result, right rear line returns to the search result for including end article.Thus, when user obtains information, user is not only caused
The search result got is more objective and accurate, and with ageing, and human-edited's cost is also saved, meet user
Demand, while improve the popularization rate of commodity.
The content providing proposed below in conjunction with the accompanying drawings to the embodiment of the present invention is described in detail.
Fig. 1 is the flow chart of the content providing of one embodiment of the invention.
It may comprise steps of as shown in figure 1, present disclosure provides method：
Step 101, the search statement of user's input is obtained.
Specifically, the content providing that the present embodiment provides, can be performed with content providing device provided by the present invention,
Said apparatus can be configured in smart machine, and the search operation of user is controlled with realizing.
Wherein, smart machine can be any hardware device with function of search, for example smart mobile phone, individual digital help
Reason, computer etc., the present invention are not especially limited to this.
During specific implementation, multiple input modes that user can be provided by smart machine input search statement to browsing
In the search column of device.For example, can be that search statement is inputted by way of phonetic entry；Or text can also be passed through
The mode of word input inputs search statement；Or search statement etc., this hair can also be inputted by way of handwriting input
It is bright that this is not specifically limited.
Step 102, carry out intention assessment to search statement, the problem of determining user type and corresponding merchandise classification.
Specifically, the present embodiment can determine the problem of user type and corresponding merchandise classification in the following manner, citing
It is described as follows：
The first implementation, intention assessment is carried out to search statement according to default intention assessment algorithm；
Wherein, default intention assessment algorithm can be that the historical search log information to user parses, and extract
Characteristic information, the characteristic information of extraction is then classified what is obtained by grader；
(Support Vector Machine, it is referred to as it should be noted that above-mentioned grader can be SVMs
SVM) grader or decision tree etc., the present invention are not especially limited to this.
Second of implementation, pass through term vector Word Vec, word sequence Word Rank and name Entity recognition (Named
Entity Recognition, abbreviation NER) technology, the composition of search statement is decomposed, then will decompose obtained data
Input disaggregated model, the problem of obtaining user type and corresponding merchandise classification.
Wherein, NER refer to identify text in have certain sense entity, mainly including name, place name, mechanism name, specially
There is noun etc..
The problem of in the present embodiment, classification can include, but are not limited to：General knowledge class, attribute enquiry class, commodity are evaluated class, sought
Ask and recommend class, consulting class etc..
Merchandise classification can include, but are not limited to makeups class, Household appliances, food liquor etc., and the present invention is to this
It is not especially limited.
For example, the search statement of user's input is " eye cream should begin to use in what age bracketThere is any benefit",
The problem of then user can be determined according to intention assessment, classification was consulting class, and corresponding merchandise classification is makeups class.
Step 103, from default knowledge of goods storehouse, the knowledge data of end article corresponding with merchandise classification is obtained.
Specifically, before the knowledge data of end article corresponding with merchandise classification is obtained, the present invention needs first to establish
Knowledge of goods storehouse.
More specifically, as shown in Fig. 2 the present invention establishes knowledge of goods storehouse may comprise steps of：
Step 201, according to the essential information of end article, each network data associated with end article is obtained.
Wherein, end article refers to commodity to be promoted, and the essential information of end article can include type, the name of commodity
Title, effect, production firm etc..
Because in actual application, the network data on commodity is what the essential information based on commodity created, because
This present invention can be according to the essential information of end article, by modes such as Web Spider, web crawlers from different question and answer class nets
The multiple network datas associated with end article are obtained on standing.
For example, the essential information of end article is " eye cream ", then the network data got is " how much just eye cream is typically smeared
Can be with", " eye cream _ Baidupedia ", " benefit of eye cream has some actually " etc..
Step 202, according to each network data, the essential information of end article and general knowledge data, knowledge of goods storehouse is established.
Specifically, by analyzing the relation between each network data, the essential information of end article and general knowledge data, and base
Relation between above-mentioned three establishes knowledge of goods storehouse.
Further, after knowledge of goods storehouse is established, can be obtained corresponding according to the merchandise classification of determination from knowledge base
End article knowledge data.
Illustrate, however, it is determined that the merchandise classification of user's search statement is makeups class, and end article is eye cream, then content
The sub- knowledge of goods storehouse of makeups class can first be determined according to " makeups class " in knowledge of goods storehouse by providing device, then according to target
Commodity " eye cream ", " eye cream " knowledge data corresponding to acquisition in the sub- knowledge of goods storehouse of makeups class.
Step 104, according to problem types, search result is built using the knowledge data of end article.
Step 105, being returned to user includes the search result of end article.
It is continuing with above-mentioned example to illustrate, if type is official communication the problem of the search statement of user's input in the present embodiment
Class is ask, then content providing device obtains the content about seeking advice from class according to consulting class problem in the knowledge data of " eye cream ".So
The content of the consulting class got integrate search answer corresponding to processing generation afterwards, and search result is returned into use
Family, to facilitate user to browse search result, the display of specific search result can be found in shown in Fig. 3.
In the content providing that the present embodiment provides, by obtaining the search statement of user's input, search statement is entered
Row intention assessment, type and corresponding merchandise classification the problem of to determine user, then from default knowledge of goods storehouse, obtain
The knowledge data of end article corresponding with merchandise classification, and searched according to problem types using the knowledge data structure of end article
Hitch fruit, right rear line return to the search result for including end article.Thus, when user obtains information, not only to use
The search result that family is got is more objective and accurate, and with ageing, and human-edited's cost is also saved, meet use
Family demand, while improve the popularization rate of commodity.
By above-mentioned analysis, when obtaining search result, by carrying out intention assessment to search statement, then basis
The merchandise classification of identification obtains corresponding knowledge data, and builds search result corresponding with problem types using knowledge data.
Another of the present invention is realized in scene, in order that the search result that must be got is more accurate, with more ageing, the present invention exists
When establishing knowledge of goods storehouse, also each network data of acquisition is carried out screening score processing, to cause the knowledge of goods storehouse established
In knowledge data more meet user's request, further improve user satisfaction.With reference to Fig. 4, have to the above situation
Body explanation.
Fig. 4 is the flow chart of the content providing of another embodiment of the present invention.
As shown in figure 4, the content providing of the embodiment of the present invention may comprise steps of：
Step 401, the essential information of commodity is obtained, and each network with commodity association is obtained according to the essential information of commodity
Data.
Wherein, the essential information of commodity can not make to have by production firm's active upload, the present invention in the present embodiment
Body limits.
Step 402, the entity attribute included according to each network data, Screening Treatment is carried out to each network data.
Specifically, due to may include plurality of kinds of contents, such as trade name, commodity effect, commodity in the essential information of commodity
Business men etc..Therefore according to the essential information of commodity, obtain also includes in various the present embodiment with each network data of commodity association
Hold, may there is some and commodity and unmatched network data among these.
On the other hand, in order to be rejected above-mentioned with the unmatched network data of commodity, the present embodiment can be to the network data of acquisition
Screening Treatment is carried out, to ensure the network data and the goods matching that obtain.
For example, if content providing device obtains the net of association according to commodity effect for the essential information of " replenishing water and preserving moisture "
Network data, then can get the commodity of all entity attributes with identical effect, such as " eye cream ", " facial mask ", " wash one's face
Milk " " Essence " etc..However, the commodity for being actually subjected to obtain are " eye creams ", now content providing device then needs further root
According to the type of merchandise of commodity, each network data got is screened, it is not all of " eye cream " that will include entity attribute
Network data is rejected, to cause the entity attribute included in each network data got to be and type of merchandise identical " eye
Frost " data.
Step 403, according to the source of each network data after screening, comment information and/or semantic integrity degree, it is determined that screening
The score of each network data afterwards, and knowledge of goods storehouse is established according to score height.
Wherein, the source of each network data can be obtained from different answer class websites, such as, Baidu knows,
Search ask, Baidupedia etc..
Wherein, voice integrity degree can refer to that whether clear and coherent the sentence of acquisition is, complete.
That is, the entity attribute included in each network data by acquisition and the unmatched network number of end article
After rejecting, according to each network data source, comment information and/or the voice integrity degree after screening, to each net after screening
Network data are scored, and are ranked up according to scoring height so that when obtaining each network data of association according to end article,
Scoring height, the preceding network data of sequence can preferentially be got.
It is understood that the present embodiment can pass through each network number when each network data after to screening carries out score
According to source, comment information realize；Or it can also be realized by the source of each network data, voice integrity degree；Or may be used also
To be realized by the source of each network data, comment information and voice integrity degree three, the present invention is not especially limited to this.
In another embodiment of the present invention, the present embodiment can also establish knowledge of goods storehouse in the following manner.
Specifically, being parsed to each network data, problem types corresponding to each network data is determined；
According to problem types, each network data and the relation map of commodity are established.
That is, by analyzing problem types corresponding to each network data, the problem of to be corresponded to according to each network data
Type establishes the relation map with end article.
For example, according to the essential information " replenishing water and preserving moisture " of eye cream, the network data of acquisition is " what use face's moisturizing has ",
" replenishing water and preserving moisture ranking list is set with the relatively good of which plate ", " moisturizing and moisturizing are the same meanings", " the good shield of moisturizing
Skin product are recommended", " teach your skin how replenishing water and preserving moisture " etc., then by analyzing above-mentioned network data, it may be determined that go out
Problem types corresponding to above-mentioned network data difference is " attribute enquiry class ", " seeking to recommend class ", " consulting class ", " commodity evaluation
Class ", " consulting class ".So according to above-mentioned network data, corresponding problem types first carries out problem and returned content providing device respectively
Class, problem types identical network data is classified as one kind, the relation then established according to problem types between " eye cream "
Figure.
Step 404, the search statement of user's input is obtained.
Step 405, carry out intention assessment to search statement, the problem of determining user type and corresponding merchandise classification.
Step 406, from the knowledge of goods storehouse of foundation, the knowledge data of end article corresponding with merchandise classification is obtained.
Step 407, according to problem types, target masterplate is determined.
Step 408, according to target masterplate, search result is built using the knowledge data of end article.
Step 409, being returned to user includes the search result of end article.
Specifically, in order that the search result that must be generated more codes and standards, the present invention can pre-establish problem types and mesh
Mark the mapping table between masterplate.So as to after problem types is determined, directly inquire about and ask in mapping table
Target masterplate corresponding to type is inscribed, so that according to target masterplate, corresponding network data is obtained from the knowledge base of end article, and
Language generation model based on deep learning, the clear and coherent search result of generated statement.
More specifically, if problem types is general knowledge class or consulting class, content providing device is according to general knowledge class or consulting
Class is retrieved in knowledge base, and will be retrieved general knowledge class or seeked advice from the network data of class, the composition as search result
Part.If problem types is attribute enquiry class, content providing device is matched according to attribute enquiry class in knowledge base, with
Whether the content of match attribute inquiry class search is to promote commodity, no if it is using item property situation as search result
Then abandon answering this problem.
If problem types is commodity when evaluating class, content providing device is evaluated class according to commodity and carried out in knowledge base
Match somebody with somebody, whether be marketing commodities to match the commodity of commodity evaluation class search, commodity are if it is evaluated into situation and tied as search
Fruit, otherwise abandon answering this problem.
If problem types is seeks to recommend class, problem and information attribute value are carried out the degree of correlation by content providing device
Match somebody with somebody, and using matching degree highest commodity as search result.
Further, after using the knowledge data of end article structure search result, search result can be returned to
User, checked in order to which user browses.
The content providing that the present embodiment provides, by obtaining each network data with commodity association, and to each network
Data carry out screening scoring and handle to obtain the network data high with commodity association degree, are then based on each network data after screening and build
Vertical knowledge of goods storehouse, then obtained according to the merchandise classification of search statement from knowledge of goods storehouse corresponding to knowledge of goods number
According to, and according to problem types, it is determined that corresponding target masterplate, and according to target masterplate, utilize the knowledge data structure of end article
Search result is built, and search result is returned into user.Thus, the search result that effectively prevent user's acquisition does not meet user
The situation of demand occurs, and can also save human-edited's cost, improves the satisfaction of user, while improve commodity
Popularization rate.
The content providing device of proposition of the embodiment of the present invention is described with reference to the accompanying drawings.
Fig. 5 is the structural representation of the content providing device of one embodiment of the present of invention.
Reference picture 5, present disclosure, which provides device, to be included：First acquisition module 10, the first determining module 11, second are obtained
Modulus block 12, structure module 13 and return module 14.
Wherein, the first acquisition module 10 is used for the search statement for obtaining user's input；
First determining module 11 is used to carry out the search statement intention assessment, the problem of determining the user type and
Corresponding merchandise classification；
Second acquisition module 12 is used for from default knowledge of goods storehouse, obtains target business corresponding with the merchandise classification
The knowledge data of product；
Build module 13 to be used for according to described problem type, utilize the knowledge data structure search knot of the end article
Fruit；
Specifically, structure module 13 of the present invention specifically includes：
According to described problem type, target masterplate is determined；
According to the target masterplate, search result is built using the knowledge data of the end article.
Module 14 is returned to be used to return to the search result for including the end article to the user.
Further, in another embodiment of the present invention, present disclosure provides device and also included：
3rd acquisition module, for the essential information according to the end article, obtain what is associated with the end article
Each network data；
Module is established, for according to each network data, the essential information of the end article and general knowledge data, establishing
The knowledge of goods storehouse.
In another embodiment of the present invention, present disclosure provides device and also included：
Screening module, for the entity attribute included according to each network data, each network data is carried out
Screening Treatment；
Grading module, for the source according to each network data, comment information and/or semantic integrity degree, it is determined that after screening
Each network data score.
In another embodiment of the present invention, present disclosure provides device and also included：
Also include：
Second determining module, for parsing each network data, determine to ask corresponding to each network data
Inscribe type；
Second establishes module, for according to described problem type, establishing each network data and the end article
Relation map.
It should be noted that the implementation process and technical principle of the content providing device of the present embodiment referring to foregoing to content
The explanation of embodiment of the method is provided, here is omitted.
In the content providing device that the present embodiment provides, by obtaining the search statement of user's input, search statement is entered
Row intention assessment, type and corresponding merchandise classification the problem of to determine user, then from default knowledge of goods storehouse, obtain
The knowledge data of end article corresponding with merchandise classification, and searched according to problem types using the knowledge data structure of end article
Hitch fruit, right rear line return to the search result for including end article.Thus, when user obtains information, not only to use
The search result that family is got is more objective and accurate, and with ageing, and human-edited's cost is also saved, meet use
Family demand, while improve the popularization rate of commodity.
To realize above-described embodiment, the present invention also proposes a kind of smart machine.
Fig. 6 is the structural representation of the smart machine of one embodiment of the invention.
As shown in fig. 6, the smart machine of the present invention includes：Memory 20 and processor 21 and it is stored on memory 20 simultaneously
The computer program that can be run on processor 21, when the processor 21 performs described program, realize first aspect embodiment
Described content providing.Wherein, the content providing includes：Obtain the search statement of user's input；Searched to described
Rope sentence carries out intention assessment, the problem of determining the user type and corresponding merchandise classification；From default knowledge of goods storehouse
In, the knowledge data of acquisition end article corresponding with the merchandise classification；According to described problem type, the target business is utilized
The knowledge data structure search result of product；Being returned to the user includes the search result of the end article.
In the smart machine that the present embodiment provides, by obtaining the search statement of user's input, search statement is anticipated
Figure identification, type and corresponding merchandise classification the problem of to determine user, then from default knowledge of goods storehouse, obtain and business
The knowledge data of the not corresponding end article of category, and the knowledge data structure search knot according to problem types using end article
Fruit, right rear line return to the search result for including end article.Thus, when user obtains information, not only user is obtained
The search result got is more objective and accurate, and with ageing, and human-edited's cost is also saved, meeting user needs
Ask, while improve the popularization rate of commodity.
To achieve these goals, the invention also provides a kind of computer-readable recording medium, it is stored thereon with calculating
Machine program, the program realize the content providing described in first aspect embodiment when being executed by processor.Wherein, the content
Offer method includes：Obtain the search statement of user's input；Intention assessment is carried out to the search statement, determines the user's
Problem types and corresponding merchandise classification；From default knowledge of goods storehouse, target business corresponding with the merchandise classification is obtained
The knowledge data of product；According to described problem type, search result is built using the knowledge data of the end article；To the use
Family returns to the search result for including the end article.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or
Implicitly include at least one this feature.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although have been shown and retouch above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (12)
- A kind of 1. content providing, it is characterised in that including：Obtain the search statement of user's input；Carry out intention assessment to the search statement, the problem of determining the user type and corresponding merchandise classification；From default knowledge of goods storehouse, the knowledge data of end article corresponding with the merchandise classification is obtained；According to described problem type, search result is built using the knowledge data of the end article；Being returned to the user includes the search result of the end article.
- 2. the method as described in claim 1, it is characterised in that described to obtain corresponding with merchandise classification end article Before knowledge data, in addition to：According to the essential information of the end article, each network data associated with the end article is obtained；According to each network data, the essential information of the end article and general knowledge data, the knowledge of goods storehouse is established.
- 3. method as claimed in claim 2, it is characterised in that described to obtain each network data associated with the end article Afterwards, in addition to：The entity attribute included according to each network data, Screening Treatment is carried out to each network data；According to the source of each network data, comment information and/or semantic integrity degree, it is determined that each network data after screening Point.
- 4. method as claimed in claim 2, it is characterised in that described to obtain each network data associated with the end article Afterwards, in addition to：Each network data is parsed, determines problem types corresponding to each network data；According to described problem type, the relation map of each network data and the end article is established.
- 5. the method as described in claim 1-4 is any, it is characterised in that it is described according to described problem type, utilize the mesh The knowledge data structure search result of commodity is marked, including：According to described problem type, target masterplate is determined；According to the target masterplate, search result is built using the knowledge data of the end article.
- A kind of 6. content providing device, it is characterised in that including：First acquisition module, for obtaining the search statement of user's input；First determining module, for carrying out intention assessment to the search statement, the problem of determining the user type and correspondingly Merchandise classification；Second acquisition module, for from default knowledge of goods storehouse, obtaining end article corresponding with the merchandise classification Knowledge data；Module is built, for according to described problem type, search result to be built using the knowledge data of the end article；Module is returned, the search result of the end article is included for being returned to the user.
- 7. device as claimed in claim 6, it is characterised in that also include：3rd acquisition module, for the essential information according to the end article, obtain each net associated with the end article Network data；Module is established, for according to each network data, the essential information of the end article and general knowledge data, described in foundation Knowledge of goods storehouse.
- 8. application as claimed in claim 7, it is characterised in that also include：Screening module, for the entity attribute included according to each network data, each network data is screened Processing；Grading module, for the source according to each network data, comment information and/or semantic integrity degree, it is determined that each after screening The score of network data.
- 9. device as claimed in claim 7, it is characterised in that also include：Second determining module, for being parsed to each network data, determine the problem of each network data corresponds to class Type；Second establishes module, for according to described problem type, establishing the relation of each network data and the end article Collection of illustrative plates.
- 10. the device as described in claim 6-9 is any, it is characterised in that the structure module, specifically include：According to described problem type, target masterplate is determined；According to the target masterplate, search result is built using the knowledge data of the end article.
- 11. a kind of smart machine, it is characterised in that including memory, processor and storage on a memory and can be in processor The computer program of upper operation, during the computing device described program, realize that the content as described in claim 1-5 is any carries Supplier's method.
- 12. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The content providing as described in claim 1-5 is any is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710964960.3A CN107833088A (en) | 2017-10-17 | 2017-10-17 | Content providing, device and smart machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710964960.3A CN107833088A (en) | 2017-10-17 | 2017-10-17 | Content providing, device and smart machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107833088A true CN107833088A (en) | 2018-03-23 |
Family
ID=61648349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710964960.3A Pending CN107833088A (en) | 2017-10-17 | 2017-10-17 | Content providing, device and smart machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107833088A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110019755A (en) * | 2019-02-27 | 2019-07-16 | 杭州简简科技有限公司 | Digital people's livelihood system and construction method based on artificial intelligence big data |
| CN110059172A (en) * | 2019-04-19 | 2019-07-26 | 北京百度网讯科技有限公司 | The method and apparatus of recommendation answer based on natural language understanding |
| CN110232137A (en) * | 2019-05-10 | 2019-09-13 | 北京搜狗科技发展有限公司 | A kind of data processing method, device and electronic equipment |
| CN110362662A (en) * | 2018-04-09 | 2019-10-22 | 北京京东尚科信息技术有限公司 | Data processing method, device and computer readable storage medium |
| CN110516051A (en) * | 2019-07-26 | 2019-11-29 | 北京搜狗科技发展有限公司 | A kind of data processing method, device and electronic equipment |
| CN113869336A (en) * | 2020-06-30 | 2021-12-31 | 北京搜狗科技发展有限公司 | Image identification searching method and related device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117467A (en) * | 2011-03-03 | 2011-07-06 | 南通大学 | Question and answer mode online shopping guide method |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
-
2017
- 2017-10-17 CN CN201710964960.3A patent/CN107833088A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117467A (en) * | 2011-03-03 | 2011-07-06 | 南通大学 | Question and answer mode online shopping guide method |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110362662A (en) * | 2018-04-09 | 2019-10-22 | 北京京东尚科信息技术有限公司 | Data processing method, device and computer readable storage medium |
| CN110019755A (en) * | 2019-02-27 | 2019-07-16 | 杭州简简科技有限公司 | Digital people's livelihood system and construction method based on artificial intelligence big data |
| CN110059172A (en) * | 2019-04-19 | 2019-07-26 | 北京百度网讯科技有限公司 | The method and apparatus of recommendation answer based on natural language understanding |
| CN110232137A (en) * | 2019-05-10 | 2019-09-13 | 北京搜狗科技发展有限公司 | A kind of data processing method, device and electronic equipment |
| CN110516051A (en) * | 2019-07-26 | 2019-11-29 | 北京搜狗科技发展有限公司 | A kind of data processing method, device and electronic equipment |
| CN113869336A (en) * | 2020-06-30 | 2021-12-31 | 北京搜狗科技发展有限公司 | Image identification searching method and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107833088A (en) | Content providing, device and smart machine | |
| CN110633373B (en) | Automobile public opinion analysis method based on knowledge graph and deep learning | |
| CN107220094B (en) | Page loading method and device and electronic equipment | |
| CN107748754B (en) | Knowledge graph perfecting method and device | |
| CN108694647B (en) | Method and device for mining merchant recommendation reason and electronic equipment | |
| Bauer et al. | Quantitive evaluation of Web site content and structure | |
| US8977629B2 (en) | Image-based popularity prediction | |
| WO2021262530A1 (en) | Systems and methods for deep learning model based product matching using multi modal data | |
| CN107391493B (en) | Public opinion information extraction method and device, terminal equipment and storage medium | |
| US7783642B1 (en) | System and method of identifying web page semantic structures | |
| US11416565B2 (en) | Techniques to leverage machine learning for search engine optimization | |
| CN108595494A (en) | The acquisition methods and device of reply message | |
| CN111460130A (en) | Information recommendation method, device, equipment and readable storage medium | |
| KR102227552B1 (en) | System for providing context awareness algorithm based restaurant sorting personalized service using review category | |
| CN110059271A (en) | With the searching method and device of label knowledge network | |
| US11887184B2 (en) | Techniques to facilitate online commerce by leveraging user activity | |
| CN105786977A (en) | Mobile search method and device based on artificial intelligence | |
| CN110827797B (en) | Voice response event classification processing method and device | |
| Kaur et al. | Review of artificial intelligence with retailing sector | |
| WO2016114790A1 (en) | Reading difficulty level based resource recommendation | |
| CN109584006A (en) | A kind of cross-platform goods matching method based on depth Matching Model | |
| CN108734159A (en) | The detection method and system of sensitive information in a kind of image | |
| CN113761347A (en) | Commodity recommendation method, commodity recommendation device, storage medium and commodity recommendation system | |
| CN102999576B (en) | For the method and apparatus determining the page-describing information corresponding to target pages | |
| CN117788109A (en) | Method for generating commodity label based on large language model and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180323 |
|
| RJ01 | Rejection of invention patent application after publication |