CN110516051A - A kind of data processing method, device and electronic equipment - Google Patents

A kind of data processing method, device and electronic equipment Download PDF

Info

Publication number
CN110516051A
CN110516051A CN201910684180.2A CN201910684180A CN110516051A CN 110516051 A CN110516051 A CN 110516051A CN 201910684180 A CN201910684180 A CN 201910684180A CN 110516051 A CN110516051 A CN 110516051A
Authority
CN
China
Prior art keywords
merchandise news
answer
described problem
problem sentence
information
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
Application number
CN201910684180.2A
Other languages
Chinese (zh)
Inventor
许嘉明
刘玉璇
杨菲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sogou Technology Development Co Ltd
Original Assignee
Beijing Sogou Technology Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Sogou Technology Development Co Ltd filed Critical Beijing Sogou Technology Development Co Ltd
Priority to CN201910684180.2A priority Critical patent/CN110516051A/en
Publication of CN110516051A publication Critical patent/CN110516051A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/338Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9538Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/955Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0623Item investigation
    • G06Q30/0625Directed, with specific intent or strategy

Abstract

The embodiment of the present application provides a kind of data processing method, device and electronic equipment, wherein the described method includes: receiving question and answer request;When determining that problem sentence corresponding to the question and answer request has demand for commodity, the corresponding answer information of described problem sentence is returned to, the return information includes the corresponding merchandise news of described problem sentence and goods links;So that user can understand commodity by answering the merchandise news in information, and when user needs that further commodity are understood or bought, the goods links that can be clicked directly in the answer information obtain more merchandise newss into third party website.In terms of existing technologies, the embodiment of the present application is not necessarily to scan for from switching to other platforms, easy to operate, improves user and understands and the efficiency of purchase commodity.

Description

A kind of data processing method, device and electronic equipment
Technical field
This application involves technical field of data processing, more particularly to a kind of data processing method, device and electronic equipment.
Background technique
With the continuous development of Internet technology and the development of search engine technique, user can be applied by search Information inquiry is carried out, such as inquires the pronunciation of some word, meaning, some profile, question and answer etc..
Under the scene of question and answer, after user enters the question and answer page, the question and answer page can show corresponding with customer problem A plurality of answer, for user's browsing.Wherein, when user, which proposes, has the problem of demand for commodity, user provides from problem platform It is got in answer after effectively answering, needs to switch on other platforms (such as electric business platform) and scan for, complicated for operation, efficiency It is low.
Summary of the invention
The embodiment of the present application provides a kind of data processing method, understands and buy commodity to improve under question and answer scene Efficiency.
Correspondingly, the embodiment of the present application also provides a kind of data processing equipment and a kind of electronic equipment, on guaranteeing State the realization and application of method.
To solve the above-mentioned problems, the embodiment of the present application discloses a kind of data processing method, specifically includes: receiving question and answer Request;When determining that problem sentence corresponding to the question and answer request has demand for commodity, return described problem sentence corresponding time Information is answered, the return information includes the corresponding merchandise news of described problem sentence and goods links.
Optionally, the method further include: the problem sentence corresponding to question and answer request carries out natural language processing, Obtain the corresponding natural language processing result of described problem sentence;Corresponding natural language processing knot according to described problem sentence Fruit, judges whether described problem sentence has demand for commodity.
Optionally, whether the decision problem sentence has demand for commodity, comprising: judges that described problem sentence is corresponding certainly Whether the intention type for including in right Language Processing result is intention type relevant to commodity.
Optionally, the corresponding answer information of the return described problem sentence, comprising: lookup and institute from Q & A database State the answer information of problem statement matching;Judge in the answer information of described problem statement matching with the presence or absence of merchandise news and quotient Product link;If not depositing merchandise news and goods links in the answer information, the corresponding commodity letter of described problem sentence is obtained Breath and goods links;It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence;It returns The answer information of the merchandise news and goods links is added.
Optionally, after obtaining the corresponding merchandise news of described problem sentence and goods links, it is described be added to it is described Before in the corresponding answer information of problem sentence, the method further include: obtain the user that the question and answer request corresponding user Portrait and/or the behavioral data of historical user;According to user portrait and/or the behavioral data of historical user, to the quotient Product information and goods links are screened.
Optionally, when judging that the judging result in the answer information with the presence or absence of merchandise news and goods links is yes When, further includes: judge whether the merchandise news in the answer information is newest merchandise news;If so, returning to the answer Information;If it is not, then obtaining the corresponding newest merchandise news of described problem sentence and newest goods links, the answer information is updated Middle merchandise news and goods links simultaneously return.
Optionally, the method further include: judge whether the problems in Q & A database sentence has demand for commodity;Needle To having the problem of demand for commodity sentence, the corresponding merchandise news of described problem sentence and goods links are obtained;By the commodity Information and goods links are added in the corresponding answer information of described problem sentence.
Optionally, the corresponding merchandise news of the acquisition described problem sentence and goods links, comprising: be based on described problem The intent information for including in the corresponding natural language processing result of sentence searches the commodity letter collected from third party website in advance Cease library, the determining and matched merchandise news of the intent information;According to matched merchandise news, corresponding goods links are obtained.
Optionally, the method further include: the click for answering the goods links in information in statistics setting duration The frequency;Judge whether the click frequency is lower than the setting frequency;If so, deleting the goods links answered in information With corresponding merchandise news, and lookup and described other merchandise newss for answering information correspondence problem statement matching and other quotient Product link, and be added in the answer information.
The embodiment of the present application also discloses a kind of data processing equipment, specifically includes: receiving module is asked for receiving question and answer It asks;Return module, for returning to described problem language when determining that problem sentence corresponding to the question and answer request has demand for commodity The corresponding answer information of sentence, the answer information includes the corresponding merchandise news of described problem sentence and goods links.
Optionally, the device further include: natural language processing module, for the problem corresponding to question and answer request Sentence carries out natural language processing, obtains the corresponding natural language processing result of described problem sentence;According to described problem sentence Corresponding natural language processing as a result, judging whether described problem sentence has demand for commodity.
Optionally, the natural language processing module, for judging the corresponding natural language processing knot of described problem sentence Whether the intention type for including in fruit is intention type relevant to commodity.
Optionally, the return module, comprising: answer information searching submodule, for from Q & A database search with The answer information of described problem statement matching;Judging submodule is in the answer information for judging described problem statement matching It is no that there are merchandise newss and goods links;Acquisition of information submodule, if for not depositing merchandise news and quotient in the answer information Product link, then obtain the corresponding merchandise news of described problem sentence and goods links;Information adds submodule, is used for the quotient Product information and goods links are added in the corresponding answer information of described problem sentence;Information returns to submodule, for returning Add the answer information of the merchandise news and goods links.
Optionally, the device further include: screening module, for obtaining the corresponding merchandise news of described problem sentence After goods links, it is described be added in the corresponding answer information of described problem sentence before, obtain question and answer request pair Using user's portrait at family and/or the behavioral data of historical user;According to user portrait and/or the behavior number of historical user According to being screened to the merchandise news and goods links.
Optionally, the device further include: the first update module judges to whether there is in the answer information for working as Merchandise news and the judging result of goods links are to judge whether the merchandise news in the answer information is newest commodity when being Information;If so, returning to the answer information;If it is not, then obtaining the corresponding newest merchandise news of described problem sentence and newest Goods links update merchandise news and goods links in the answer information and return.
Optionally, the device further include: pre- adding module, for whether judging the problems in Q & A database sentence With demand for commodity;Sentence aiming at the problem that with demand for commodity obtains the corresponding merchandise news of described problem sentence and commodity Link;It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence.
Optionally, the information adds submodule, is specifically used for being based on the corresponding natural language processing of described problem sentence As a result the intent information for including in searches the commodity information database collected from third party website in advance, the determining and intent information Matched merchandise news;According to matched merchandise news, corresponding goods links are obtained.
Optionally, the device further include: the second update module, for counting in setting duration in the answer information Goods links the click frequency;Judge whether the click frequency is lower than the setting frequency;If so, deleting the answer information In the goods links and corresponding merchandise news, and search with it is described answer information correspondence problem statement matching other Merchandise news and other goods links, and be added in the answer information.
The embodiment of the present application also discloses a kind of readable storage medium storing program for executing, when the instruction in the storage medium is by electronic equipment Processor execute when so that electronic equipment is able to carry out the data processing method as described in the embodiment of the present application is any.
The embodiment of the present application also discloses a kind of electronic equipment, includes memory and one or more than one Program, perhaps more than one program is stored in memory and is configured to by one or more than one processing for one of them It includes the instruction for performing the following operation that device, which executes the one or more programs: receiving question and answer request;Work as determination When problem sentence corresponding to the question and answer request has demand for commodity, the corresponding answer information of described problem sentence is returned, it is described Answer the answer information that information includes the corresponding merchandise news of described problem sentence and goods links.
Optionally, also comprising the instruction for performing the following operation: the problem sentence corresponding to question and answer request carries out Natural language processing obtains the corresponding natural language processing result of described problem sentence;According to the corresponding of described problem sentence Natural language processing is as a result, judge whether described problem sentence has demand for commodity.
Optionally, whether the decision problem sentence has demand for commodity, comprising: judges that described problem sentence is corresponding certainly Whether the intention type for including in right Language Processing result is intention type relevant to commodity.
Optionally, the corresponding answer information of the return described problem sentence, comprising: lookup and institute from Q & A database State the answer information of problem statement matching;Judge in the answer information of described problem statement matching with the presence or absence of merchandise news and quotient Product link;If not depositing merchandise news and goods links in the answer information, the corresponding commodity letter of described problem sentence is obtained Breath and goods links;It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence;It returns The answer information of the merchandise news and goods links is added.
Optionally, after obtaining the corresponding merchandise news of described problem sentence and goods links, it is described be added to it is described Before in the corresponding answer information of problem sentence, also comprising the instruction for performing the following operation: obtaining the question and answer request pair Using user's portrait at family and/or the behavioral data of historical user;According to user portrait and/or the behavior number of historical user According to being screened to the merchandise news and goods links.
Optionally, when judging that the judging result in the answer information with the presence or absence of merchandise news and goods links is yes When, also comprising the instruction for performing the following operation: judging whether the merchandise news in the answer information is newest commodity letter Breath;If so, returning to the answer information;If it is not, then obtaining the corresponding newest merchandise news of described problem sentence and newest quotient Product link updates merchandise news and goods links in the answer information and returns.
Optionally, also comprising the instruction for performing the following operation: judging whether the problems in Q & A database sentence has There is demand for commodity;Sentence aiming at the problem that with demand for commodity obtains the corresponding merchandise news of described problem sentence and commodity chain It connects;It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence.
Optionally, the corresponding merchandise news of the acquisition described problem sentence and goods links, comprising: be based on described problem The intent information for including in the corresponding natural language processing result of sentence searches the commodity letter collected from third party website in advance Cease library, the determining and matched merchandise news of the intent information;According to matched merchandise news, corresponding goods links are obtained.
Optionally, also comprising the instruction for performing the following operation: the quotient answered in information in statistics setting duration The click frequency of product link;Judge whether the click frequency is lower than the setting frequency;If so, deleting in the answer information The goods links and corresponding merchandise news, and search and described other commodity for answering information correspondence problem statement matching Information and other goods links, and be added in the answer information.
The embodiment of the present application includes the following advantages:
In the embodiment of the present application, after receiving question and answer request, when the problem sentence for determining the question and answer request correspondence has When demand for commodity, return described problem sentence is corresponding and has added the answer information of merchandise news and goods links;And then make Commodity can be understood by answering the merchandise news in information by obtaining user, and when user needs further to carry out commodity When understanding or buying, the goods links that can be clicked directly in the answer information obtain more quotient into third party website Product information.In terms of existing technologies, the embodiment of the present application is not necessarily to scan for from switching to other platforms, easy to operate, Improve the efficiency that user understands and buys commodity.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of data processing method embodiment of the application;
Fig. 2 is a kind of step flow chart of data processing method alternative embodiment of the application;
Fig. 3 is the step flow chart of another data processing method alternative embodiment of the application;
Fig. 4 is a kind of structural block diagram of data processing equipment embodiment of the application;
Fig. 5 is a kind of structural block diagram of data processing equipment alternative embodiment of the application;
A kind of Fig. 6 structural block diagram of the electronic equipment for data processing shown according to an exemplary embodiment;
Fig. 7 is a kind of structure for electronic equipment for data processing that the application is shown according to another exemplary embodiment Schematic diagram.
Specific embodiment
In order to make the above objects, features, and advantages of the present application more apparent, with reference to the accompanying drawing and it is specific real Applying mode, the present application will be further described in detail.
Referring to Fig.1, a kind of step flow chart of data processing method embodiment of the application is shown, can specifically include Following steps:
Step 102 receives question and answer request.
Step 104, when determining that problem sentence corresponding to question and answer request has demand for commodity, return to described problem language The corresponding answer information of sentence;It include the corresponding merchandise news of described problem sentence and goods links in the answer information.
In the embodiment of the present application, user directly can carry out enquirement operation in answer platform.For example, user is in answer platform After input has the query statement for puing question to intention and executes search operation, answer platform can receive asking including the query statement Answer request.Under the scene, the query statement of user's input is contained in the question and answer request, at this point, answer platform can be direct The query statement that user inputs, the problem sentence corresponding as question and answer request are obtained from question and answer request.
Certainly, user can also input in the search box of search platform the query statement putd question to and be intended to, and ties in search If including the question and answer search result (from answer platform) to match with the query statement in fruit page, asked when user triggers this When answering search result, answer platform can receive the request of the question and answer including the question and answer search result correspondence problem sentence.This Under scape, include in question and answer request is the problem language corresponding with the question and answer search result that the query statement of user's input matches Sentence, using the problem sentence problem sentence corresponding as question and answer request.
Answer platform analyzes question and answer request, determines problem sentence corresponding to the question and answer request;And foundation The problem sentence obtains corresponding answer information and returns to user.
It, can when determining that problem sentence corresponding to described problem question and answer request has demand for commodity in the embodiment of the present application Directly to return corresponding with described problem sentence and be added with the corresponding merchandise news of described problem sentence and goods links Answer information to user.Wherein, the corresponding merchandise news of described problem sentence and goods links can be and obtain and add in advance It adds in the corresponding answer information of described problem sentence, is also possible to obtaining corresponding answer information according to the problem sentence When, obtain and be added in the answer information, the embodiment of the present application to this with no restriction.Certainly, described problem is being determined When problem sentence corresponding to request does not have demand for commodity, the corresponding answer information of described problem sentence can be directly returned.
Wherein, the merchandise news can be collects from third party website in advance.It is being collected from third party website When the merchandise news of each commodity, the corresponding goods links of each commodity can also be extracted;Then it can establish the corresponding quotient of each commodity Association between product information and corresponding goods link.Wherein, the merchandise news may include information relevant to commodity;Commodity Information may include: information attribute value, such as may include cruising ability, screen size, system configuration etc. for mobile phone; Information on commodity comment, such as favorable comment, difference are commented, pricing information, favor information and sales volume information etc., the embodiment of the present application pair This is with no restriction.Wherein, the goods links can refer to the link in corresponding page comprising merchandise news, such as commodity official website Link and purchase link etc., the embodiment of the present application to this with no restriction.
So that user can by answer information in merchandise news commodity are understood, and when user need into When one step is understood or bought to commodity, the goods links in the answer information can be clicked directly on, into third party's net It stands, obtains more more intuitive merchandise newss.In terms of existing technologies, the embodiment of the present application is without switching to other platforms It scans for, it is easy to operate, improve the efficiency that user understands and buys commodity.
Wherein, the answer platform can be independent platform, and a part being also possible in search platform is also possible to Search platform itself, the embodiment of the present application to this with no restriction.
In the example of the application, answer platform receives question and answer request, if the problem sentence that question and answer request is corresponding Are as follows: " A1 model mobile phone is good or B1 model mobile phone is good ", can determine that the problem sentence has demand for commodity;It therefore can be with Return described problem sentence is corresponding and has added the answer information of merchandise news and goods links.Such as: answering information includes " A1 model mobile phone cost performance is very high, and system optimization is pretty good, but quality is general;The merchandise news of A1 model mobile phone: " continuation of the journey: 7 Hour, screen size: 6.3 inches, system configuration: running memory: 6G, camera: 4800 Wan Chaoqing cameras, price: 1800 "; The goods links of A1 model mobile phone: https: //www.1234.com/A1/.B1 model mobile phone cruise duration is generally than A1 model Mobile phone is long, and quality is secure, and system optimization is slightly weak;B1 model mobile phone merchandise news " continuation of the journey: 10 hours, screen size: 6.5 Inch, system configuration: running memory: 6G, camera: 16,000,000 four take the photograph, price: 2300 ".The goods links of B1 model mobile phone Are as follows: https: //www.14687.com/B1/.".Wherein, the content that underscore marks is the corresponding commodity of described problem sentence Information and goods links.
In conventional method, if some problem sentence has demand for commodity, user passes through the problem sentence corresponding time After answering acquisition of information to effective information, if desired further appreciates that commodity or purchase commodity, then need to switch to other platforms Middle carry out manual search.In the embodiment of the present application, after receiving question and answer request, when the problem language for determining the question and answer request correspondence When sentence has demand for commodity, return described problem sentence is corresponding and has added the answer information of merchandise news and goods links; So that user can understand commodity by answering the merchandise news in information, and when user needs further to quotient When product are understood or bought, the goods links that can be clicked directly in the answer information obtain more into third party website More merchandise news.In terms of existing technologies, the embodiment of the present application is scanned for without switching to other platforms, operation letter Just, the efficiency that user understands and buys commodity is improved.
In a kind of implementation of the application, there can be demand for commodity problem language in Q & A database in advance Sentence, in its corresponding merchandise news and goods links for answering addition corresponding goods in information.And then receipt of subsequent user looks into When the answer information can be matched by asking sentence, the answer information that this can be added with to merchandise news and goods links is returned To user, improving to return has the corresponding efficiency for answering message of demand for commodity problem sentence.
Referring to Fig. 2, a kind of the step of adding merchandise news and goods links embodiment of the method in advance of the application is shown Flow chart can specifically include following steps:
Step 202, the problems in judging Q & A database, whether sentence has demand for commodity.
In the embodiment of the present application, during user carries out question and answer in answer platform, answer platform can collect use The problem of family the sentence and corresponding answer information of problem sentence, and each problem sentence and corresponding answer information are added to and are asked It answers in database;And be each problem sentence and corresponding answer information, generate corresponding question and answer link;Convenient for subsequent user Problem sentence and corresponding answer information can be obtained by the corresponding question and answer page of the question and answer links and accesses.
Wherein, step 202 can refer to following sub-step 22-24:
Sub-step 22 is directed to a problem sentence in the Q & A database, carries out natural language to described problem sentence It handles (Natural Language Processing, NLP), obtains corresponding NLP processing result.
Sub-step 24, the corresponding NLP processing result of foundation described problem sentence, determine whether described problem sentence has quotient Product demand.
In the embodiment of the present application, natural language processing can be carried out, such as will to each problem sentence in question and answer data Rule-based method and method based on deep learning are combined, and are carried out NLP processing to problem sentence, are obtained the problem language The corresponding NLP processing result of sentence.Wherein, rule-based method can include but is not limited to: JSGF (JSpeech Grammar Format, Jspeech syntax format) etc.;Method based on deep learning can include but is not limited to: CNN (Convolutional Neural Networks, convolutional neural networks) etc..
Wherein, the NLP processing result may include intention type and intent information, and the intention type may include more Kind, such as commodity purchasing class, vegetable cook class, wash shield class;The intent information can be the corresponding specific meaning of intention type Figure can refer to which type of commodity specifically bought as commodity purchasing class is intended to corresponding intent information, and vegetable is cooked class and is intended to Corresponding intent information can refer to what vegetable etc. specifically cooked.For example, problem sentence are as follows: " either with or without what 2000 yuan of left side Right, longer mobile phone in cruise duration is recommended ", by carrying out natural language processing, obtained NLP processing result to problem sentence It include: intention type: commodity purchasing class;Intent information: (1) merchandise classification: mobile phone, (2) price demand: 2000 yuan or so, (3) Functional requirement: play game, (4) performance requirement: continuation of the journey is strong.In another example problem sentence is " how Kung Pao chicken is cooked ", by right Problem sentence carries out natural language processing, and obtained NLP processing result includes: intention type: vegetable cooks class;Intent information: Vegetable: Kung Pao chicken.
Then according to the corresponding NLP processing result of described problem sentence, determine whether described problem sentence there are commodity to need It asks.Wherein, a kind of mode can be, judge in the corresponding NLP processing result of described problem sentence intention type whether be and quotient The relevant intention type of product, such as commodity purchasing class, commodity selling class, commodity understand class;If described problem sentence corresponds to NLP Intention type in processing result is intention type relevant to commodity, then can determine that the problem sentence has demand for commodity; If it is not intention type relevant to commodity that described problem sentence, which corresponds to intention type in NLP processing result, this can be determined Problem sentence does not have demand for commodity.
Step 204, have demand for commodity aiming at the problem that sentence, then obtain the corresponding merchandise news of described problem sentence and Goods links.
Wherein, step 204 is referred to following sub-step 42-44:
Sub-step 42 corresponds to the lookup of the intent information in NLP processing result based on described problem sentence in advance from third party The commodity information database collected in website, the determining and matched merchandise news of the intent information.
Sub-step 44, according to matched merchandise news, obtain corresponding goods links.
In the embodiment of the present application, the merchandise news that answer platform can be collected from a third party website, referred to as one Merchandise news can establish the merchandise news of each item and corresponding quotient after collecting a plurality of merchandise news and corresponding goods links Merchandise news, goods links and correlation tag, are then stored in commodity information database by the correlation tag between product link.In turn After determining that problem sentence has demand for commodity, the intent information in NLP processing result is corresponded to according to the problem sentence, from commodity Matched merchandise news is searched in information bank.Wherein it is possible to intent information be matched with each merchandise news respectively, when certain When merchandise news is matched with the every terms of information in intent information, this merchandise news and the intent information can be determined Match.Then corresponding goods links can be determined according to the corresponding correlation tag of matched merchandise news.
Certainly, answer platform, can also be according to the commodity after collecting a plurality of merchandise news and corresponding goods links Information establishes index (wherein it is possible to using wherein at least one as index);Then it establishes between index and merchandise news letter Correlation tag and merchandise news and corresponding goods link between correlation tag, and by index, merchandise news, commodity Link, index with correlation tag and merchandise news between corresponding goods information and corresponding goods link between association mark Label are stored in commodity information database.It, can be corresponding according to the problem sentence and then after determining that problem sentence has demand for commodity Intent information in NLP processing result searches matched index from commodity information database;It is then based on the corresponding association mark of index Label search matched merchandise news, and the correlation tag according to matched merchandise news searches corresponding Commercial goods labels.
In the embodiment of the present application, there is the problem of demand for commodity corresponding merchandise news of sentence may include a variety of, in order to Accurately merchandise news and corresponding goods links are provided for user, it can be corresponding to respectively having the problem of demand for commodity sentence Merchandise news and goods links are screened.Wherein, to having the problem of demand for commodity corresponding merchandise news of sentence and commodity Linking a kind of mode screened can be, and the historical behavior data according to historical user are screened, and be referred to step 206- step 208.
Step 206, the behavioral data for obtaining historical user.
Step 208, according to the behavioral data of the historical user, to the corresponding merchandise news of described problem sentence and commodity Link is screened.
In the embodiment of the present application, the behavioral data of the historical user of acquisition, can be historical user with described problem language Sentence pair answers merchandise news and/or the relevant behavioral data of goods links, may include following implementations:
In the example of the application, a kind of mode of behavioral data obtaining historical user be can be, and is obtained history and is used The inquiry frequency of the corresponding merchandise news of described problem sentence is inquired at family.Wherein it is possible to according to every log pair in search log The content and timestamp answered count in the first set period of time, and historical user inquires commodity letter corresponding with described problem sentence The inquiry frequency of breath;Wherein, first set period of time can be arranged as desired, and such as nearly three months, the embodiment of the present application With no restriction to this.
In another example of the application, the mode of the behavioral data of another historical user be can be, and is obtained history and is used Click the click frequency of the corresponding goods links of described problem sentence in family.Wherein it is possible to according to every log pair in search log The content and timestamp answered count in the second set period of time, and historical user clicks the corresponding goods links of described problem sentence The click frequency;Wherein, second set period of time can be arranged as desired, and such as nearly three months, the embodiment of the present application pair This is with no restriction.
In another example of the application, another mode for obtaining the behavioral data of historical user be can be, and acquisition is gone through Browsing behavior data of the history user in the corresponding goods links corresponding page of described problem sentence.Wherein, the browsing behavior number According to may include following at least one: stay time, duplication, purchase, collection, shopping cart is added etc. in sharing, can also wrap certainly Include other browsing behavior data, the embodiment of the present application to this with no restriction.
Certainly can also include obtain historical user other behavioral datas, such as obtain historical user goods links (with Described problem sentence is corresponding) behavior in the association page of corresponding page, such as return of goods behavior;The embodiment of the present application does not make this Limitation.
In step 208, can according to above-mentioned at least one behavioral data, to the corresponding merchandise news of described problem sentence and Goods links are screened.Such as according to the inquiry frequency, the corresponding merchandise news of described problem sentence and goods links are carried out Screening such as filters out the highest preceding N kind merchandise news of the inquiry frequency and goods links.In another example according to the frequency is clicked, to described The corresponding merchandise news of problem sentence and goods links are screened, and the inquiry highest preceding M kind merchandise news of the frequency is such as filtered out And goods links.Also for example the corresponding merchandise news of described problem sentence and goods links are carried out according to browsing behavior data Screening;Wherein it is possible to calculate the corresponding score value of the browsing behavior data, the highest preceding P kind commodity letter of score value is then filtered out Breath and goods links.Certainly, if according to above-mentioned at least two behavioral data, to the corresponding merchandise news of described problem sentence and quotient When product link is screened, at least two behavioral datas can be weighted, filter out the maximum preceding Q kind of weighted results Merchandise news and goods links.Wherein, N, M, P and Q are positive integer.
In addition, commodity are kept updating, meets the corresponding merchandise news of problem sentence and goods links may also It is to constantly update.Such as constantly there are new, some commodity undercarriages etc. on commodity.Therefore in order to provide accurately commodity chain for user It connects and merchandise news, periodically each merchandise news in commodity information database and corresponding goods link can be updated, with To the merchandise news and corresponding goods links having in the corresponding answer information of the problem of demand for commodity sentence in Q & A database It is updated, to better meet user demand.Wherein, the period of the update can be arranged as desired, and such as 15 days, this Shen Please embodiment to this with no restriction.
Wherein, after having information update in commodity information database, answer platform can be in the answer information to problem data There are merchandise news and goods links to be updated.In addition, when having newly-increased merchandise news and corresponding commodity in commodity information database When link, it can be determined that the newly-increased merchandise news meet whether in Q & A database each problem sentence demand for commodity letter Breath.It, can be with when determining that the newly-increased merchandise news meets the demand for commodity information of some problem sentence in Q & A database Newly-increased merchandise news and corresponding goods links are added in the corresponding answer information of the problem sentence.
When user is lower to goods links number of clicks a certain in answer information, it may illustrate that this goods links can not Meet user demand;Therefore the embodiment of the present application can also count in setting duration and be added to the goods links answered in information The click frequency.If being added to the click frequency for answering the goods links in information lower than the setting frequency, this can be deleted Goods links and corresponding merchandise news.And it can be searched and the answer information correspondence problem sentence from merchandising database Other matched merchandise newss and other goods links;Then other merchandise newss found and other goods links are added Into the answer information.Wherein, the setting duration can be arranged as desired, and such as 3 months, the embodiment of the present application did not made this Limitation.
Step 210, by the merchandise news and goods links after screening, be added to the answer information of described problem sentence In.
In the embodiment of the present application, after the corresponding merchandise news of described problem sentence and goods links screening, it can will select The merchandise news and goods links afterwards, are added in the answer information of described problem sentence.
It certainly, can be getting if described there is the problem of demand for commodity sentence corresponding answer information is not present After stating the answer information of problem sentence (such as after user answers the problem sentence on answer platform, answer platform can To get the corresponding answer information of the problem sentence), then execute above-mentioned steps 204- step 210.
To sum up, in the embodiment of the present application, it can be determined that whether the problems in Q & A database sentence has demand for commodity, needle To having the problem of demand for commodity sentence, then the corresponding merchandise news of available described problem sentence and goods links will The merchandise news and goods links are added in the answer information of described problem sentence;And then it is subsequently received with commodity When the problem sentence that the question and answer of demand are requested and question and answer request is corresponding can match the answer information, this can be added There are merchandise news and the answer information of goods links to return to user, improving to return has demand for commodity problem sentence is corresponding to answer The efficiency of message improves the efficiency for understanding and buying commodity.
It, can be with after determining the corresponding merchandise news of described problem sentence and goods links secondly, in the embodiment of the present application The behavioral data for obtaining historical user believes the corresponding commodity of described problem sentence according to the behavioral data of the historical user Breath and goods links are screened;To provide accurately merchandise news and goods links for user.
Referring to Fig. 3, a kind of step flow chart of data processing method alternative embodiment of the application is shown, it specifically can be with Include the following steps:
Step 302 receives question and answer request.
In the embodiment of the present application, after answer platform receives question and answer request, problem language corresponding to the question and answer request is determined Sentence;On the one hand the answer information of available described problem statement matching, i.e. execution step 304;On the other hand it may determine that and ask Whether topic sentence has demand for commodity, i.e. execution step 306.
Step 304 is searched and the answer information of described problem statement matching from Q & A database.
In the embodiment of the present application, it can be searched from Q & A database and ask going through for correspondence problem statement matching with the question and answer Then history problem sentence obtains the corresponding answer information of matched historical problem sentence;By the matched historical problem sentence pair The answer information answered, the answer information as question and answer request correspondence problem statement matching.
Wherein, it if having carried out NLP processing to matched historical problem sentence described in Q & A database in advance, obtains pair The NLP processing result answered;Then the matched historical problem language can be determined with the predetermined NLP processing result of direct basis Whether sentence has demand for commodity, so that it is determined that whether the problem sentence of question and answer request correspondence has demand for commodity.If in advance NLP processing is not carried out to matched historical problem sentence described in Q & A database, then can execute step 306- step 308.
Step 306, the problem sentence corresponding to question and answer request carry out natural language processing, obtain described problem sentence Corresponding natural language processing result.
Step 308, the corresponding natural language processing of foundation described problem sentence are as a result, judge whether described problem sentence has There is demand for commodity.
Step 306- step 308 is referring to above-mentioned sub-step 22- sub-step 24, and details are not described herein.
When described problem sentence has demand for commodity, step 310 can be executed;When described problem sentence does not have commodity When demand, step 324 can be executed.Above-mentioned steps 104 are referred to step 310- step 326:
Step 310 judges in the answer information of described problem statement matching with the presence or absence of merchandise news and goods links.
When described problem sentence have demand for commodity when, it can be determined that in the answer information of described problem statement matching whether There are merchandise newss and goods links;If merchandise news and commodity chain are not present in the answer information of described problem statement matching It connects, then can execute step 312, if there are merchandise news and goods links in the answer information of described problem statement matching, Step 322 can be executed.
Step 312 obtains the corresponding merchandise news of described problem sentence and goods links.
This step is similar with above-mentioned steps 204, and details are not described herein.
The behavioral data of step 314, the user's portrait for obtaining the corresponding user of question and answer request and/or historical user.
Step 316, according to the user portrait and/or historical user behavioral data, to the merchandise news and commodity Link is screened.
In order to provide accurately merchandise news and corresponding goods links for user, correspondence can be requested to ask the question and answer The merchandise news and goods links for inscribing sentence are screened.Wherein, a kind of commodity to question and answer request correspondence problem sentence The mode that information and goods links are screened may is that obtaining the question and answer requests user's portrait of corresponding user and/or go through The behavioral data of history user, according to user portrait and/or the behavioral data of historical user, to the merchandise news and commodity Link is screened;And then filter out the matched merchandise news of user corresponding with question and answer request and goods links.
Wherein, the question and answer request user's portrait of corresponding user that can request corresponding user's history according to the question and answer Behavioral data determines, such as age, hobby, gender, identity, the embodiment of the present application to this with no restriction.Wherein it is possible to foundation At least one of the behavioral data of user portrait and historical user, to the corresponding merchandise news of described problem sentence and commodity chain Tap into capable screening;For example, the behavioral data according to historical user is to the corresponding merchandise news of described problem sentence and goods links It is screened, the merchandise news such as obtained has 10 kinds, and it is most that purchase volume can be filtered out according to the behavioral data of historical user Preceding 5 kinds of merchandise news and corresponding goods links.In another example drawing a portrait according to user to the corresponding merchandise news of described problem sentence It is screened with goods links, the merchandise news such as obtained has 10 kinds, if user's portrait is student, can filter out cost performance Highest merchandise news and corresponding goods links.Further for example, drawing a portrait according to the behavioral data of historical user and user, to described The corresponding merchandise news of problem sentence and goods links are screened, and the merchandise news such as obtained has 20 kinds, then are used according to history The behavioral data at family selects the most preceding 10 kinds of merchandise news of purchase volume, if user's portrait is game enthusiasts, according to user Portrait selects the highest merchandise news of game performance and corresponding goods links from this 10 kinds of merchandise newss;Etc., this Shen Please embodiment to this with no restriction.
Step 318, by the merchandise news and goods links after screening, be added to the corresponding answer of described problem sentence In information.
Step 320, return have added the answer information of the merchandise news and goods links.
Step 322, decision problem sentence are corresponding to answer whether merchandise news in information is newest merchandise news.
In the embodiment of the present application, when determining that described problem sentence has demand for commodity, described problem sentence corresponding time Answering has merchandise news and goods links in information;In order to provide newest information for user, it can be determined that described problem sentence In corresponding answer information, whether merchandise news is newest merchandise news.If quotient in the corresponding answer information of described problem sentence Product information is newest merchandise news, then can execute step 324, if merchandise news in the corresponding answer information of described problem sentence It is not newest merchandise news, then can executes step 326.
In a kind of implementation of the application, in a kind of corresponding answer information of judgement described problem sentence, merchandise news It whether is that the mode of newest merchandise news may is that and search corresponding with described problem sentence intent information from commodity information database The merchandise news matched and corresponding goods links;By the corresponding merchandise news and commodity chain answered in information of described problem sentence The problem of connecing, be compared with the merchandise news and goods links found from commodity information database, judging matching sentence is corresponding Answer information in merchandise news whether be newest merchandise news.If it is determined that quotient in the corresponding answer information of described problem sentence Product information is not newest merchandise news, then can execute step 326.If commodity are believed in the corresponding answer information of described problem sentence Breath is newest merchandise news, can also obtain the content in goods links, judges the content in the goods links, if with return It is identical to answer the corresponding merchandise news of goods links described in information;If so, 324 are thened follow the steps, if it is not, thening follow the steps 326.
Step 324 returns to the answer information.
In the embodiment of the present application, if by by described problem sentence it is corresponding answer information in merchandise news and commodity chain It connects, is compared with the merchandise news and goods links found from commodity information database, determine the corresponding answer of problem sentence Merchandise news is newest merchandise news in information, and the content in the goods links, commodity corresponding with the goods links Information is identical, then the corresponding answer information of described problem sentence can be returned to user.
Certainly, if described problem sentence does not have demand for commodity, the corresponding answer of problem sentence can directly be returned Information, wherein do not include merchandise news and goods links in the answer information.
Step 326 obtains the corresponding newest merchandise news of described problem sentence and newest goods links, updates the answer It merchandise news and goods links and is returned in information.
In the embodiment of the present application, if by by described problem sentence it is corresponding answer information in merchandise news and commodity chain It connects, is compared with the merchandise news and goods links found from commodity information database, determine that described problem sentence is corresponding Answering merchandise news in information is not newest merchandise news, then can be by the merchandise news and goods links in the answer information It deletes, and adds newest merchandise news and corresponding goods links (i.e. newest goods links) in answering information.If it is determined that institute The content in goods links is stated, merchandise news corresponding with the goods links is not identical, then according in the goods links Content updates the merchandise news answered in information.
To sum up, it in the embodiment of the present application, after receiving question and answer request, can be searched from Q & A database and described problem The answer information of statement matching, and corresponding problem sentence can be requested to carry out natural language processing question and answer, it obtains described The corresponding NLP processing result of problem sentence judges described problem sentence according to the corresponding NLP processing result of described problem sentence Whether there is demand for commodity;If problem sentence corresponding to the question and answer request has demand for commodity, described problem sentence is judged It whether there is merchandise news and goods links in matched answer information, if not depositing in the answer information of described problem statement matching In merchandise news and goods links, then available corresponding merchandise news and goods links, then by the merchandise news and Goods links are added in the answer information of described problem sentence and return;And then it can be in real time by merchandise news and commodity chain It connects to be added to answer and returns to user in information, improve the efficiency for understanding and buying commodity.
Secondly, can sentence if merchandise news and goods links are not present in the answer information of described problem statement matching Disconnected described problem sentence is corresponding to answer whether merchandise news in information is newest merchandise news;If problem sentence is corresponding to answer information Middle merchandise news is newest merchandise news, then directly returns to the answer information;If problem sentence is corresponding to answer commodity in information Information is not newest merchandise news, then obtains the corresponding newest merchandise news of described problem sentence and newest goods links, is updated It merchandise news and goods links and is returned in the answer information;And then newest commodity letter is added in answering information for user Breath and goods links better meet user demand, improve user experience.
It, can be with after obtaining the corresponding merchandise news of described problem sentence and goods links in addition, in the embodiment of the present application The behavioral data and user's portrait for obtaining historical user, draw a portrait according to the behavioral data of the historical user and user, to described The corresponding merchandise news of problem sentence and goods links are screened;To provide accurately merchandise news and commodity chain for user It connects.
In the alternative embodiment of the application, when the problem sentence for determining the question and answer request correspondence has demand for commodity When, it, can be in user if not including the corresponding merchandise news of described problem sentence and goods links in the answer information returned During browsing the corresponding question and answer page of question and answer request, to problem sentence and information progress NLP analysis is answered, is determined corresponding NLP processing result;Then it obtains and is intended to the merchandise news and goods links of information matches in NLP processing result, and be user Recommend, such as recommended in a manner of pop-up, the embodiment of the present application to this with no restriction.
Such as: problem title: is the dandruff control shampoo containing of which brand good in the question and answer page
Question answering: using professional dandruff control shampoo containing, such as: * * * shampoo, * * * include a kind of special zinc, be can be improved 75% chip-removing capacity.To solving the problems, such as that dandruff has very great help;The brand and type of shampoo are not often replaced.Selection It is suitble to hair quality;Too hot water is not used when hair washing, in order to avoid stimulation scalp;Often hair washing keeps scalp health.
It is analyzed by NLP, can determine corresponding NLP processing result are as follows: intention type: commodity purchasing class;Intent information: (1) merchandise classification: shampoo, (2) Brand: * * *.Then the merchandise news and goods links of available * * * shampoo Recommend user.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method It closes, but those skilled in the art should understand that, the embodiment of the present application is not limited by the described action sequence, because according to According to the embodiment of the present application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should Know, the embodiments described in the specification are all preferred embodiments, and related movement not necessarily the application is implemented Necessary to example.
Referring to Fig. 4, show a kind of structural block diagram of data processing equipment embodiment of the application, can specifically include as Lower module:
Receiving module 402, for receiving question and answer request;
Return module 404, for returning to institute when determining that problem sentence corresponding to the question and answer request has demand for commodity The corresponding answer information of problem sentence is stated, the answer information includes the corresponding merchandise news of described problem sentence and commodity chain It connects.
Referring to Fig. 5, a kind of structural block diagram of data processing equipment alternative embodiment of the application is shown.
In the application an optional embodiment, the device further include:
Natural language processing module 406 carries out natural language processing for the problem sentence corresponding to question and answer request, Obtain the corresponding natural language processing result of described problem sentence;Corresponding natural language processing knot according to described problem sentence Fruit, judges whether described problem sentence has demand for commodity.
In the application an optional embodiment, the natural language processing module 406, for judging described problem sentence Whether the intention type for including in corresponding natural language processing result is intention type relevant to commodity.
In the application an optional embodiment, the return module 404, comprising:
Information searching submodule 4042, for searching the answer letter with described problem statement matching from Q & A database Breath;
Judging submodule 4044, in the answer information for judging described problem statement matching with the presence or absence of merchandise news and Goods links;
Acquisition of information submodule 4046, if being obtained for not depositing merchandise news and goods links in the answer information The corresponding merchandise news of described problem sentence and goods links;
Information adds submodule 4048, for being added to described problem sentence pair for the merchandise news and goods links In the answer information answered;
Information returns to submodule 40410, for returning to the answer information for having added the merchandise news and goods links.
In the application an optional embodiment, the device further include:
Screening module 408 is used for after obtaining the corresponding merchandise news of described problem sentence and goods links, described to add Before being added in the corresponding answer information of described problem sentence, obtain the question and answer request corresponding user user's portrait and/or The behavioral data of historical user;According to user portrait and/or the behavioral data of historical user, to the merchandise news and quotient Product link is screened.
In the application an optional embodiment, the device further include:
First update module 410, for when judge to whether there is merchandise news and goods links in the answer information Judging result is to judge whether the merchandise news in the answer information is newest merchandise news when being;If so, described in returning Answer information;If it is not, then obtaining the corresponding newest merchandise news of described problem sentence and newest goods links, the answer is updated It merchandise news and goods links and is returned in information.
In the application an optional embodiment, the device further include:
Pre- adding module 412, for judging whether the problems in Q & A database sentence has demand for commodity;For having The problem of demand for commodity sentence, obtain the corresponding merchandise news of described problem sentence and goods links;By the merchandise news and Goods links are added in the corresponding answer information of described problem sentence.
In the application an optional embodiment,
The information adds submodule 4048, is specifically used for being based on the corresponding natural language processing result of described problem sentence In include intent information search the commodity information database collected from third party website in advance, determination is matched with the intent information Merchandise news;According to matched merchandise news, corresponding goods links are obtained.
In the application an optional embodiment, the device further include:
Second update module 414, for counting the click frequency for answering the goods links in information in setting duration; Judge whether the click frequency is lower than the setting frequency;If so, deleting the goods links and right answered in information The merchandise news answered, and search and described other merchandise newss and other commodity chains for answering information correspondence problem statement matching It connects, and is added in the answer information.
To sum up, in the embodiment of the present application, after receiving question and answer request, when the problem sentence for determining the question and answer request correspondence When with demand for commodity, return described problem sentence is corresponding and has added the answer information of merchandise news and goods links;Into And user is understood by answering the merchandise news in information commodity, and when user needs further to commodity When being understood or being bought, the goods links in the answer information can be clicked directly on, into third party website, are obtained more Merchandise news.In terms of existing technologies, the embodiment of the present application is not necessarily to scan for from switching to other platforms, operation letter Just, the efficiency that user understands and buys commodity is improved.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple Place illustrates referring to the part of embodiment of the method.
Fig. 6 is a kind of structural block diagram of electronic equipment 600 for data processing shown according to an exemplary embodiment. For example, electronic equipment 600 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console put down Panel device, Medical Devices, body-building equipment, personal digital assistant etc..
Referring to Fig. 6, electronic equipment 600 may include following one or more components: processing component 602, memory 604, Electric power assembly 606, multimedia component 608, audio component 610, the interface 612 of input/output (I/O), sensor module 614, And communication component 616.
The integrated operation of the usual controlling electronic devices 600 of processing component 602, such as with display, call, data are logical Letter, camera operation and record operate associated operation.Processing element 602 may include one or more processors 620 to hold Row instruction, to perform all or part of the steps of the methods described above.In addition, processing component 602 may include one or more moulds Block, convenient for the interaction between processing component 602 and other assemblies.For example, processing component 602 may include multi-media module, with Facilitate the interaction between multimedia component 608 and processing component 602.
Memory 604 is configured as storing various types of data to support the operation in equipment 600.These data are shown Example includes the instruction of any application or method for operating on electronic equipment 600, contact data, telephone directory number According to, message, picture, video etc..Memory 604 can by any kind of volatibility or non-volatile memory device or they Combination realize, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable Programmable read only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, quick flashing Memory, disk or CD.
Electric power assembly 606 provides electric power for the various assemblies of electronic equipment 600.Electric power assembly 606 may include power supply pipe Reason system, one or more power supplys and other with for electronic equipment 600 generate, manage, and distribute the associated component of electric power.
Multimedia component 608 includes the screen of one output interface of offer between the electronic equipment 600 and user. In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch surface Plate, screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touches Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, Multimedia component 608 includes a front camera and/or rear camera.When electronic equipment 600 is in operation mode, as clapped When taking the photograph mode or video mode, front camera and/or rear camera can receive external multi-medium data.It is each preposition Camera and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 610 is configured as output and/or input audio signal.For example, audio component 610 includes a Mike Wind (MIC), when electronic equipment 600 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone It is configured as receiving external audio signal.The received audio signal can be further stored in memory 604 or via logical Believe that component 616 is sent.In some embodiments, audio component 610 further includes a loudspeaker, is used for output audio signal.
I/O interface 612 provides interface between processing component 602 and peripheral interface module, and above-mentioned peripheral interface module can To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock Determine button.
Sensor module 614 includes one or more sensors, for providing the state of various aspects for electronic equipment 600 Assessment.For example, sensor module 614 can detecte the state that opens/closes of equipment 600, the relative positioning of component, such as institute The display and keypad that component is electronic equipment 600 are stated, sensor module 614 can also detect electronic equipment 600 or electronics The position change of 600 1 components of equipment, the existence or non-existence that user contacts with electronic equipment 600,600 orientation of electronic equipment Or the temperature change of acceleration/deceleration and electronic equipment 600.Sensor module 614 may include proximity sensor, be configured to It detects the presence of nearby objects without any physical contact.Sensor module 614 can also include optical sensor, such as CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, which can be with Including acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 616 is configured to facilitate the communication of wired or wireless way between electronic equipment 600 and other equipment. Electronic equipment 600 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.Show at one In example property embodiment, communication component 614 receives broadcast singal or broadcast from external broadcasting management system via broadcast channel Relevant information.In one exemplary embodiment, the communication component 614 further includes near-field communication (NFC) module, short to promote Cheng Tongxin.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band can be based in NFC module (UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment 600 can be by one or more application specific integrated circuit (ASIC), number Word signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided It such as include the memory 604 of instruction, above-metioned instruction can be executed by the processor 620 of electronic equipment 600 to complete the above method.Example Such as, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, soft Disk and optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of electronic equipment When device executes, so that electronic equipment is able to carry out a kind of data processing method, which comprises receive question and answer request;When true When problem sentence corresponding to the fixed question and answer request has demand for commodity, the corresponding answer information of described problem sentence, institute are returned Stating return information includes the corresponding merchandise news of described problem sentence and goods links.
Optionally, the method further include: the problem sentence corresponding to question and answer request carries out natural language processing, Obtain the corresponding natural language processing result of described problem sentence;Corresponding natural language processing knot according to described problem sentence Fruit, judges whether described problem sentence has demand for commodity.
Optionally, whether the decision problem sentence has demand for commodity, comprising: judges that described problem sentence is corresponding certainly Whether the intention type for including in right Language Processing result is intention type relevant to commodity.
Optionally, the corresponding answer information of the return described problem sentence, comprising: lookup and institute from Q & A database State the answer information of problem statement matching;Judge in the answer information of described problem statement matching with the presence or absence of merchandise news and quotient Product link;If not depositing merchandise news and goods links in the answer information, the corresponding commodity letter of described problem sentence is obtained Breath and goods links;It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence;It returns The answer information of the merchandise news and goods links is added.
Optionally, after obtaining the corresponding merchandise news of described problem sentence and goods links, it is described be added to it is described Before in the corresponding answer information of problem sentence, the method further include: obtain the user that the question and answer request corresponding user Portrait and/or the behavioral data of historical user;According to user portrait and/or the behavioral data of historical user, to the quotient Product information and goods links are screened.
Optionally, when judging that the judging result in the answer information with the presence or absence of merchandise news and goods links is yes When, further includes: judge whether the merchandise news in the answer information is newest merchandise news;If so, returning to the answer Information;If it is not, then obtaining the corresponding newest merchandise news of described problem sentence and newest goods links, the answer information is updated Middle merchandise news and goods links simultaneously return.
Optionally, the method further include: judge whether the problems in Q & A database sentence has demand for commodity;Needle To having the problem of demand for commodity sentence, the corresponding merchandise news of described problem sentence and goods links are obtained;By the commodity Information and goods links are added in the corresponding answer information of described problem sentence.
Optionally, the corresponding merchandise news of the acquisition described problem sentence and goods links, comprising: be based on described problem The intent information for including in the corresponding natural language processing result of sentence searches the commodity letter collected from third party website in advance Cease library, the determining and matched merchandise news of the intent information;According to matched merchandise news, corresponding goods links are obtained.
Optionally, the method further include: the click for answering the goods links in information in statistics setting duration The frequency;Judge whether the click frequency is lower than the setting frequency;If so, deleting the goods links answered in information With corresponding merchandise news, and lookup and described other merchandise newss for answering information correspondence problem statement matching and other quotient Product link, and be added in the answer information.
Fig. 7 is a kind of electronic equipment 700 for data processing that the application is shown according to another exemplary embodiment Structural schematic diagram.The electronic equipment 700 can be server, which can generate bigger because of configuration or performance difference Difference, may include one or more central processing units (central processing units, CPU) 722 (for example, One or more processors) and memory 732, the storage of one or more storage application programs 742 or data 744 Medium 730 (such as one or more mass memory units).Wherein, memory 732 and storage medium 730 can be of short duration Storage or persistent storage.The program for being stored in storage medium 730 may include one or more modules (diagram does not mark), Each module may include to the series of instructions operation in server.Further, central processing unit 722 can be set to It is communicated with storage medium 730, executes the series of instructions operation in storage medium 730 on the server.
Server can also include one or more power supplys 726, one or more wired or wireless networks connect Mouthfuls 750, one or more input/output interfaces 758, one or more keyboards 756, and/or, one or one with Upper operating system 741, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..
A kind of electronic equipment includes perhaps one of them or one of more than one program of memory and one Procedure above is stored in memory, and is configured to execute one or one by one or more than one processor Procedure above includes the instruction for performing the following operation: receiving question and answer request;When the problem for determining the question and answer request correspondence When sentence has demand for commodity, the corresponding answer information of described problem sentence is returned to, the answer information includes described problem language The answer information of sentence corresponding merchandise news and goods links.
Optionally, also comprising the instruction for performing the following operation: the problem sentence corresponding to question and answer request carries out Natural language processing obtains the corresponding natural language processing result of described problem sentence;According to the corresponding of described problem sentence Natural language processing is as a result, judge whether described problem sentence has demand for commodity.
Optionally, whether the decision problem sentence has demand for commodity, comprising: judges that described problem sentence is corresponding certainly Whether the intention type for including in right Language Processing result is intention type relevant to commodity.
Optionally, the corresponding answer information of the return described problem sentence, comprising: lookup and institute from Q & A database State the answer information of problem statement matching;Judge in the answer information of described problem statement matching with the presence or absence of merchandise news and quotient Product link;If not depositing merchandise news and goods links in the answer information, the corresponding commodity letter of described problem sentence is obtained Breath and goods links;It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence;It returns The answer information of the merchandise news and goods links is added.
Optionally, after obtaining the corresponding merchandise news of described problem sentence and goods links, it is described be added to it is described Before in the corresponding answer information of problem sentence, also comprising the instruction for performing the following operation: obtaining the question and answer request pair Using user's portrait at family and/or the behavioral data of historical user;According to user portrait and/or the behavior number of historical user According to being screened to the merchandise news and goods links.
Optionally, when judging that the judging result in the answer information with the presence or absence of merchandise news and goods links is yes When, also comprising the instruction for performing the following operation: judging whether the merchandise news in the answer information is newest commodity letter Breath;If so, returning to the answer information;If it is not, then obtaining the corresponding newest merchandise news of described problem sentence and newest quotient Product link updates merchandise news and goods links in the answer information and returns.
Optionally, also comprising the instruction for performing the following operation: judging whether the problems in Q & A database sentence has There is demand for commodity;Sentence aiming at the problem that with demand for commodity obtains the corresponding merchandise news of described problem sentence and commodity chain It connects;It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence.
Optionally, the corresponding merchandise news of the acquisition described problem sentence and goods links, comprising: be based on described problem The intent information for including in the corresponding natural language processing result of sentence searches the commodity letter collected from third party website in advance Cease library, the determining and matched merchandise news of the intent information;According to matched merchandise news, corresponding goods links are obtained.
Optionally, also comprising the instruction for performing the following operation: the quotient answered in information in statistics setting duration The click frequency of product link;Judge whether the click frequency is lower than the setting frequency;If so, deleting in the answer information The goods links and corresponding merchandise news, and search and described other commodity for answering information correspondence problem statement matching Information and other goods links, and be added in the answer information.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
The embodiment of the present application is referring to according to the method for the embodiment of the present application, terminal device (system) and computer program The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart And/or in one or more blocks of the block diagram specify function the step of.
Although preferred embodiments of the embodiments of the present application have been described, once a person skilled in the art knows bases This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as Including preferred embodiment and all change and modification within the scope of the embodiments of the present application.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
Above to a kind of data processing method provided herein, a kind of data processing equipment and a kind of electronic equipment, It is described in detail, specific examples are used herein to illustrate the principle and implementation manner of the present application, the above reality The explanation for applying example is merely used to help understand the present processes and its core concept;Meanwhile for the general technology of this field Personnel, according to the thought of the application, there will be changes in the specific implementation manner and application range, in conclusion this theory Bright book content should not be construed as the limitation to the application.

Claims (10)

1. a kind of data processing method characterized by comprising
Receive question and answer request;
When determining that problem sentence corresponding to the question and answer request has demand for commodity, the corresponding answer of described problem sentence is returned Information, the return information include the corresponding merchandise news of described problem sentence and goods links.
2. the method according to claim 1, wherein the method further include:
The problem sentence corresponding to question and answer request carries out natural language processing, obtains the corresponding natural language of described problem sentence Say processing result;
Corresponding natural language processing according to described problem sentence is as a result, judge whether described problem sentence there are commodity to need It asks.
3. according to the method described in claim 2, it is characterized in that, whether the decision problem sentence has demand for commodity, packet It includes:
Judge whether the intention type for including in the corresponding natural language processing result of described problem sentence is relevant to commodity Intention type.
4. method according to claim 1 or 2, which is characterized in that the corresponding answer letter of the return described problem sentence Breath, comprising:
The answer information with described problem statement matching is searched from Q & A database;
Judge in the answer information of described problem statement matching with the presence or absence of merchandise news and goods links;
If not depositing merchandise news and goods links in the answer information, obtain the corresponding merchandise news of described problem sentence and Goods links;
It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence;
Return to the answer information for having added the merchandise news and goods links.
5. according to the method described in claim 4, it is characterized in that, obtaining the corresponding merchandise news of described problem sentence and quotient Product link after, it is described be added in the corresponding answer information of described problem sentence before, the method further include:
It obtains the question and answer and requests user's portrait of corresponding user and/or the behavioral data of historical user;
According to user portrait and/or the behavioral data of historical user, the merchandise news and goods links are screened.
6. according to the method described in claim 4, it is characterized in that, when judging in the answer information with the presence or absence of merchandise news Judging result with goods links is when being, further includes:
Judge whether the merchandise news in the answer information is newest merchandise news;
If so, returning to the answer information;
If it is not, then obtaining the corresponding newest merchandise news of described problem sentence and newest goods links, the answer information is updated Middle merchandise news and goods links simultaneously return.
7. the method according to claim 1, wherein the method further include:
Judge whether the problems in Q & A database sentence has demand for commodity;
Sentence aiming at the problem that with demand for commodity obtains the corresponding merchandise news of described problem sentence and goods links;
It is added to the merchandise news and goods links in the corresponding answer information of described problem sentence.
8. a kind of data processing equipment characterized by comprising
Receiving module, for receiving question and answer request;
Return module, for returning to described problem when determining that problem sentence corresponding to the question and answer request has demand for commodity The corresponding answer information of sentence, the answer information include the corresponding merchandise news of described problem sentence and goods links.
9. a kind of readable storage medium storing program for executing, which is characterized in that when the instruction in the storage medium is held by the processor of electronic equipment When row, so that electronic equipment is able to carry out the data processing method as described in claim to a method 1-7 is any.
10. a kind of electronic equipment, which is characterized in that include memory and one or more than one program, wherein one A perhaps more than one program is stored in memory and is configured to execute described one by one or more than one processor A or more than one program includes the instruction for performing the following operation:
Receive question and answer request;
When determining that problem sentence corresponding to the question and answer request has demand for commodity, the corresponding answer of described problem sentence is returned Information, it is described to answer the answer information that information includes the corresponding merchandise news of described problem sentence and goods links.
CN201910684180.2A 2019-07-26 2019-07-26 A kind of data processing method, device and electronic equipment Pending CN110516051A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910684180.2A CN110516051A (en) 2019-07-26 2019-07-26 A kind of data processing method, device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910684180.2A CN110516051A (en) 2019-07-26 2019-07-26 A kind of data processing method, device and electronic equipment

Publications (1)

Publication Number Publication Date
CN110516051A true CN110516051A (en) 2019-11-29

Family

ID=68623606

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910684180.2A Pending CN110516051A (en) 2019-07-26 2019-07-26 A kind of data processing method, device and electronic equipment

Country Status (1)

Country Link
CN (1) CN110516051A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113763123A (en) * 2021-08-12 2021-12-07 阿里巴巴(中国)有限公司 Commodity recommendation and search method, commodity recommendation and search equipment and storage medium

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102099803A (en) * 2007-10-23 2011-06-15 瑞5优特有限公司 Method and computer system for automatically answering natural language questions
US20120323991A1 (en) * 2011-06-17 2012-12-20 Microsoft Corporation Mobile social interaction
CN104951428A (en) * 2014-03-26 2015-09-30 阿里巴巴集团控股有限公司 User intention recognition method and device
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
CN105573998A (en) * 2014-10-09 2016-05-11 阿里巴巴集团控股有限公司 Page operation information maintenance method and server
CN105654307A (en) * 2014-11-13 2016-06-08 苏宁云商集团股份有限公司 Commodity recommendation method based on user feedback and commodity recommendation system
CN106326984A (en) * 2016-08-09 2017-01-11 北京京东尚科信息技术有限公司 User intention identification method and device and automatic answering system
CN106407198A (en) * 2015-07-28 2017-02-15 百度在线网络技术(北京)有限公司 Question and answer information processing method and device
CN107833088A (en) * 2017-10-17 2018-03-23 北京百度网讯科技有限公司 Content providing, device and smart machine
CN108153876A (en) * 2017-12-26 2018-06-12 爱因互动科技发展(北京)有限公司 Intelligent answer method and system
CN108536852A (en) * 2018-04-16 2018-09-14 上海智臻智能网络科技股份有限公司 Question and answer exchange method and device, computer equipment and computer readable storage medium
CN109636545A (en) * 2018-12-26 2019-04-16 广州市耀锋电子网络科技有限公司 A kind of electric business platform commercial product recommending algorithm
CN110019725A (en) * 2017-12-22 2019-07-16 科沃斯商用机器人有限公司 Man-machine interaction method, system and its electronic equipment

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102099803A (en) * 2007-10-23 2011-06-15 瑞5优特有限公司 Method and computer system for automatically answering natural language questions
US20120323991A1 (en) * 2011-06-17 2012-12-20 Microsoft Corporation Mobile social interaction
CN104951428A (en) * 2014-03-26 2015-09-30 阿里巴巴集团控股有限公司 User intention recognition method and device
CN105573998A (en) * 2014-10-09 2016-05-11 阿里巴巴集团控股有限公司 Page operation information maintenance method and server
CN105654307A (en) * 2014-11-13 2016-06-08 苏宁云商集团股份有限公司 Commodity recommendation method based on user feedback and commodity recommendation system
CN106407198A (en) * 2015-07-28 2017-02-15 百度在线网络技术(北京)有限公司 Question and answer information processing method and device
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
CN106326984A (en) * 2016-08-09 2017-01-11 北京京东尚科信息技术有限公司 User intention identification method and device and automatic answering system
CN107833088A (en) * 2017-10-17 2018-03-23 北京百度网讯科技有限公司 Content providing, device and smart machine
CN110019725A (en) * 2017-12-22 2019-07-16 科沃斯商用机器人有限公司 Man-machine interaction method, system and its electronic equipment
CN108153876A (en) * 2017-12-26 2018-06-12 爱因互动科技发展(北京)有限公司 Intelligent answer method and system
CN108536852A (en) * 2018-04-16 2018-09-14 上海智臻智能网络科技股份有限公司 Question and answer exchange method and device, computer equipment and computer readable storage medium
CN109636545A (en) * 2018-12-26 2019-04-16 广州市耀锋电子网络科技有限公司 A kind of electric business platform commercial product recommending algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
岳芸: "电商客服自动问答系统的商品意图识别", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑(月刊)》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113763123A (en) * 2021-08-12 2021-12-07 阿里巴巴(中国)有限公司 Commodity recommendation and search method, commodity recommendation and search equipment and storage medium

Similar Documents

Publication Publication Date Title
US9530145B2 (en) Providing social impact information associated with identified products or businesses
CN102591911B (en) The real time individual of position related entities is recommended
US11520824B2 (en) Method for displaying information, electronic device and system
CN107526744A (en) A kind of information displaying method and device based on search
CN108345610A (en) It is a kind of to obtain the method and apparatus of data resource, the device for obtaining data resource
CN107305566B (en) A kind of method and device to search for information matches picture
CN108595493A (en) Method for pushing and device, storage medium, the electronic device of media content
CN110322305A (en) Data object information providing method, device and electronic equipment
CN107798011A (en) A kind of searching method and device, a kind of device for being used to search for
CN109308334A (en) Information recommendation method and device, search engine system
CN110232137A (en) A kind of data processing method, device and electronic equipment
CN108241690A (en) A kind of data processing method and device, a kind of device for data processing
CN108460651A (en) Vehicle recommends method and device
CN109101505A (en) A kind of recommended method, recommendation apparatus and the device for recommendation
CN108874827A (en) A kind of searching method and relevant apparatus
CN107506441A (en) A kind of data arrangement method, apparatus, electronic equipment and storage medium
CN106815291A (en) Search result items exhibiting method, device and the device represented for search result items
CN112508612A (en) Method for training advertisement creative generation model and method and related device for generating advertisement creative
CN108717403B (en) Processing method and device for processing
CN110019885A (en) A kind of expression data recommended method and device
CN109308240A (en) Operation processing method and device, storage medium
CN107526740A (en) A kind of method and electronic equipment for showing search result
CN108509406A (en) A kind of language material abstracting method, device and electronic equipment
CN110516051A (en) A kind of data processing method, device and electronic equipment
CN110009437A (en) Recommended method and device, the device for recommendation

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