CN110362662A - Data processing method, device and computer readable storage medium - Google Patents
Data processing method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN110362662A CN110362662A CN201810308511.8A CN201810308511A CN110362662A CN 110362662 A CN110362662 A CN 110362662A CN 201810308511 A CN201810308511 A CN 201810308511A CN 110362662 A CN110362662 A CN 110362662A
- Authority
- CN
- China
- Prior art keywords
- information
- comment
- question
- comment information
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 24
- 238000003860 storage Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims description 31
- 230000002123 temporal effect Effects 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 9
- 238000012552 review Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 230000010365 information processing Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 8
- 244000062793 Sorghum vulgare Species 0.000 description 7
- 235000019713 millet Nutrition 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000008451 emotion Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Human Computer Interaction (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This disclosure relates to which a kind of data processing method, device and computer readable storage medium, are related to big data field.Disclosed method includes: the question information for obtaining user about object;Search the comment information of stored object;According at least one information in the keyword of comment information and question information, syntactic information and semantic information, comment information is matched with question information;Recommend at least one comment information to user according to matching result, the answer putd question to as user.The disclosure is directed to question information of the user about object, and the comment information of the object is matched with question information, chooses at least one comment information as the answer putd question to according to matching result and recommends user.Due to including evaluation of the other users about the object in comment information, it efficiently can recommend answer relevant to problem in time using comment information for quizmaster, improve the efficiency replied in commodity question and answer, promote user experience.
Description
Technical field
This disclosure relates to big data field, in particular to a kind of data processing method, device and computer-readable storage
Medium.
Background technique
E-commerce industry is highly developed by the development of many years, and most e-commerce websites all have perfect quotient
Product, inventory, order and after sale system.But the magnanimity commodity of e-commerce website but cause huge puzzlement to user, make
User is difficult to choose.Commodity question and answer are a kind of newer forms, and the angle that answer can be concerned about from consumer carries out commodity general
It includes, describes the overall picture of commodity, and provide the instruction in some purchases to consumer.
Currently, including quizmaster and answerer in commodity question answering process.Quizmaster: commodity purchasing intention person pays close attention to some
Commodity or category, but still in the user in hesitation, propose oneself concern.Answerer: certain part quotient was for example bought
The user of product provides personal answer to the problem of quizmaster's proposition.Quizmaster can choose whether to purchase according to the answer of answerer
Buy commodity.
Summary of the invention
Inventor's discovery: the user experience heavy dependence of the response rate of problem in the form of above-mentioned commodity question and answer, question and answer returns
The answer that the person of answering provides.And the answer of most of commodity question and answer is difficult to that the whole issue of quizmaster's proposition, response rate is completely covered
It is not high, and turnaround time is longer, causes quizmaster that cannot be replied in time, reduces the experience of quizmaster.
A disclosure technical problem to be solved is: how to improve the efficiency replied in commodity question and answer, promotes user
Experience.
According to some embodiments of the present disclosure, a kind of data processing method for providing, comprising: obtain user about object
Question information;Search the comment information of stored object;According to the keyword of comment information and question information, syntactic information and
At least one information in semantic information, comment information is matched with question information;Recommended according to matching result to user
At least one comment information, the answer putd question to as user.
In some embodiments, comment information match with question information includes: determining each comment information respectively
With the Keywords matching degree, syntactic match degree and semantic matching degree of question information;By the corresponding keyword of same comment information
Matching degree, syntactic match degree and semantic matching degree are weighted, the matching degree as this comment information and question information.
In some embodiments, recommending at least one comment information to user according to matching result includes: to be commented according to each item
By the corresponding user credit grade of information, user's registration information, comment temporal information and at least one information in rate is used, it is right
Matching result is modified;Recommend at least one comment information to user according to revised matching result.
In some embodiments, matching result includes the matching degree of each comment information and question information;To matching result
Be modified includes: by the corresponding user credit grade weight of comment information, user's registration weight, comment time weighting and answer
It is multiplied using at least one matching degree corresponding with the comment information in rate weight, obtained product is as revised matching
As a result;Wherein, user credit higher grade, and user credit grade weight is higher;The user's registration time is more early, and registration weight is got over
It is high;It is smaller to comment on time lead time corresponding with question information, it is higher to comment on time weighting.
In some embodiments, this method further include: obtain comment information, comment information include from object review pages,
The comment information obtained at least one in the question and answer page, community's class page and customer service system;Establish comment information and object information,
The corresponding relationship of user information and temporal information and storage.
In some embodiments, match with comment information by question information according to keyword includes: to question information
It is segmented respectively with comment information;According to the word frequency of each word and comprising the number of training of the word, mention respectively
Ask the keyword of information and comment information;According to the similarity of the keyword of each comment information and question information, each item is determined
The Keywords matching degree of comment information and question information.
In some embodiments, match with comment information by question information according to syntactic information includes: to believe enquirement
Breath and comment information are segmented respectively;According to the part of speech of word each in question information and comment information, determines put question to respectively
The syntactic structure of each sentence in information and comment information;According to the syntactic structure of sentence each in question information and comment information
Similarity, determine the syntactic match degree of each comment information and question information.
In some embodiments, match with comment information by question information according to semantic information includes: to believe enquirement
Breath and comment information are segmented respectively;The term vector of each word in question information and comment information is determined respectively;According to mentioning
It asks the term vector of each word in information and comment information, calculates the semantic matching degree of each comment information and question information.
According to other embodiments of the disclosure, a kind of data processing equipment for providing, comprising: question information obtains mould
Block, for obtaining question information of the user about object;Comment information searching module, for searching the comment of stored object
Information;Matching module, at least one in the keyword, syntactic information and semantic information according to comment information and question information
Item information, comment information is matched with question information;Answer recommending module, for according to matching result to user recommend to
A few comment information, the answer putd question to as user.
In some embodiments, matching module is used to determine the Keywords matching of each comment information and question information respectively
Degree, syntactic match degree and semantic matching degree, by the corresponding Keywords matching degree of same comment information, syntactic match degree and semanteme
Matching degree is weighted, the matching degree as this comment information and question information.
In some embodiments, answer recommending module is used for according to the corresponding user credit grade of each comment information, uses
Family registration information is commented on temporal information and using at least one information in rate, is modified to matching result, after amendment
Matching result to user recommend at least one comment information.
In some embodiments, matching result includes the matching degree of each comment information and question information;Mould is recommended in answer
Block is used to the corresponding user credit grade weight of comment information, user's registration weight, comment time weighting and answer using rate
At least one matching degree corresponding with the comment information in weight is multiplied, and obtained product is as revised matching result;
Wherein, user credit higher grade, and user credit grade weight is higher;The user's registration time is more early, and registration weight is higher;Comment
Time, lead time corresponding with question information was smaller, and comment time weighting is higher.
In some embodiments, device further include: comment information processing module, for obtaining comment information, foundation is commented
By information and object information, the corresponding relationship of user information and temporal information and storage;Wherein, comment information includes commenting from object
By the comment information obtained in the page, the question and answer page, community's class page and customer service system at least one.
In some embodiments, matching module for segmenting question information and comment information respectively, according to each
The word frequency of word and number of training comprising the word extract the keyword of question information and comment information, according to each respectively
The similarity of the keyword of comment information and question information, determines the Keywords matching of each comment information and question information
Degree.
In some embodiments, matching module for segmenting question information and comment information respectively, according to enquirement
The part of speech of each word in information and comment information determines the grammer knot of each sentence in question information and comment information respectively
Structure determines each comment information and puts question to according to the similarity of the syntactic structure of sentence each in question information and comment information
The syntactic match degree of information.
In some embodiments, matching module determines respectively for segmenting respectively to question information and comment information
The term vector of each word in question information and comment information, according to the word of word each in question information and comment information to
Amount calculates the semantic matching degree of each comment information and question information.
According to the other embodiment of the disclosure, a kind of data processing equipment for providing, comprising: memory;And coupling
To the processor of memory, processor is configured as executing such as aforementioned any reality based on the instruction being stored in memory devices
Apply the data processing method of example.
According to the still other embodiments of the disclosure, a kind of computer readable storage medium provided is stored thereon with calculating
Machine program, wherein the program realizes the step of data processing method of aforementioned any embodiment when being executed by processor.
The disclosure is directed to question information of the user about object, by the comment information of the object and question information progress
Match, at least one comment information is chosen as the answer putd question to according to matching result and recommends user.Due to being wrapped in comment information
Evaluation containing other users about the object can efficiently be recommended in time for quizmaster relevant to problem using comment information
Answer improves the efficiency replied in commodity question and answer, promotes user experience.
By the detailed description referring to the drawings to the exemplary embodiment of the disclosure, the other feature of the disclosure and its
Advantage will become apparent.
Detailed description of the invention
In order to illustrate more clearly of the embodiment of the present disclosure or technical solution in the prior art, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Disclosed some embodiments for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 shows the flow diagram of the data processing method of some embodiments of the present disclosure.
Fig. 2 shows the flow diagrams of the data processing method of other embodiments of the disclosure.
Fig. 3 shows the structural schematic diagram of the data processing equipment of some embodiments of the present disclosure.
Fig. 4 shows the structural schematic diagram of the data processing equipment of other embodiments of the disclosure.
Fig. 5 shows the structural schematic diagram of the data processing equipment of the other embodiment of the disclosure.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present disclosure, the technical solution in the embodiment of the present disclosure is carried out clear, complete
Site preparation description, it is clear that described embodiment is only disclosure a part of the embodiment, instead of all the embodiments.Below
Description only actually at least one exemplary embodiment be it is illustrative, never as to the disclosure and its application or making
Any restrictions.Based on the embodiment in the disclosure, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, belong to the disclosure protection range.
The disclosure provides a kind of data processing method, can be used for commodity question and answer scene.The disclosure is described below with reference to Fig. 1
Some embodiments of data processing method.
Fig. 1 is the flow chart of some embodiments of disclosure data processing method.As shown in Figure 1, the method packet of the embodiment
It includes: step S102~S108.
In step S102, question information of the user about object is obtained.
For the scene of commodity question and answer, user can put question in the enquirement area of item detail page, and system then can be with
It is automatic to obtain the targeted object information of question information, such as goods number etc..User can also be in the visitor of e-commerce platform
The positions such as dress system or community forum, which issue, puts question to, can be right in the case where this user does not explicitly point out and puts question to object
It puts question to sentence to carry out processing and extracts object information.For example, enquirement sentence can be segmented, cleaning (such as removal deactivates
Word), each word is compared with the word in dictionary, determines the corresponding object of question information.Its other party can also be taken
Method determines the corresponding object of question information, is not limited to examples cited.Object can be specific commodity, be also possible to category, example
Such as mobile phone, it is also possible to the product of a certain brand, such as millet mobile phone, can determines according to actual needs.
In step S104, the comment information of stored object is searched.
Comment information can be any type of description information about object of user's generation.For example, being commented on from object
The comment information obtained at least one in the page, the question and answer page, community's class page and customer service system.For example, user's commodity in use
After can make comments in review pages, the enquirement of other users can be answered, or deliver survey in the communities such as forum class page
Article is commented, the problem of encountering can also be reflected in use to customer service or requires after-sale service etc..These comment informations can be anti-
The experience that user uses object is reflected, the user for actually delivering comment information uses body about object in answer other users
When the problem of testing, most of answers are similar to comment information.Therefore comment information, which can be used as, puts question to answer feedback to user.
Comment information can store in database, be updated every predetermined period.Comment information is generally directed to specific
Object can directly determine the corresponding object of comment information.Further, it is possible to be believed according to object acquisition object category, brand etc.
Breath.Object information (including category, brand etc.) and comment information can be associated storage.It can for the comment information of acquisition
To be pre-processed, for example, audited automatically to comment information, removal is wherein comprising sensitive word or unrelated with object, no
Belong to the comment information etc. of normal comment information.Automatically the process audited can be using the side of semantics recognition in natural language processing
Method belongs to the prior art, and details are not described herein.
Further, it is possible to which comment information is segmented, (such as removal stop words) is cleaned, extracts keyword, determines sentence
Sub- grammer, the processing such as determine semantic information (such as emotion, attitude etc.).Can be used for it is subsequent matched with question information, specific side
Method will be described subsequent.So far, object information, the keyword of comment information, Sentence Grammar, language be can store in database
The information such as adopted information and word segmentation result.
The object information stored in the corresponding object information of question information and database is compared, can determine about
Put question to the comment information of object.
In step S106, according in the keyword of comment information and question information, syntactic information and semantic information at least
One information matches comment information with question information.
In some embodiments, match with question information by comment information according to keyword can use with lower section
Method: question information and comment information are segmented respectively;According to the word frequency of each word and include the training sample of the word
Number extracts the keyword of question information and comment information respectively;According to the phase of each comment information and the keyword of question information
Like degree, the Keywords matching degree of each comment information and question information is determined.
If participle has been carried out in storage, extracts the processing such as keyword for comment information, the step can be straight
Scoop out use.It can use TF-IDF (Term Frequency-Inverse Document Frequency, term frequency-inverse document frequency
Rate) algorithm extracts the keyword of comment information or question information.Specifically, calculating the word frequency and inverse document frequency of each word
Product obtains the significance level of word, chooses keyword according to significance level.The word frequency of word is, for example, that the word goes out in the text
The ratio of existing number and the total word number of text.The inverse document frequency of word be, for example, training text sum with comprising the word
The logarithm of the ratio of textual data.The extraction of keyword can also take other algorithms, such as RAKE (Rapid Automatic
Keyword Extraction, fast automatic keyword extraction) scheduling algorithm, it is not limited to examples cited.
It can in the case that remaining word quantity is lower than threshold value after segmenting cleaning for comment information or question information
All words as keyword, are not used the algorithm for extracting keyword.Keyword in question information is commented with every
The Keywords matching degree of question information and comment information is determined by the comparison that keyword each in information carries out similarity.Specifically
, keyword can be converted to by term vector using word2vector algorithm, by calculating the keyword in question information and commenting
By the distance of the term vector of the keyword of information, the similarity of the two is determined, by the corresponding phase of keyword each in question information
The Keywords matching degree of available question information and comment information is added like degree.By the above method calculate keyword word to
Amount can increase matched accuracy, for example, in " millet " word in millet mobile phone and edible millet " millet " though a word
It is so same word, but meaning is different, can be distinguished by the way that the similarity of both term vector judgements is very low.
In some embodiments, match with question information by comment information according to syntactic information can use with lower section
Method: question information and comment information are segmented respectively;According to the part of speech of word each in question information and comment information, divide
Not Que Ding in question information and comment information each sentence syntactic structure;According to sentence each in question information and comment information
Syntactic structure similarity, determine the syntactic match degree of each comment information and question information.
If the processing such as participle, the syntactic information for determining each sentence has been carried out in storage for comment information,
The step can be applied directly.Part of speech of word such as noun, verb, adjective etc..According to the sequence and part of speech of each word
It can determine the syntactic structure of sentence.By comparing syntactic structure, the syntactic match of comment information and question information can be determined
Degree.The syntactic match degree of part of speech, syntactic structure and comment information and question information, example can be determined according to existing algorithm
Such as, syntax tree, details are not described herein.Syntactic structure can also include each in sentence in addition to the part of speech and sequence of each word
The features such as word, part of speech and sequence can be matched when word, the i.e. matching degree of comparison sentence.
In some embodiments, match with question information by comment information according to semantic information can use with lower section
Method: question information and comment information are segmented respectively;The word of each word in question information and comment information is determined respectively
Vector;According to the term vector of word each in question information and comment information, the language of each comment information and question information is calculated
Adopted matching degree.
If participle has been carried out in storage in comment information, can directly be applied in this step.Determine the word of word
Vector can use word2vector algorithm, can also use other algorithms, details are not described herein.It can use deep learning
The similarity of the term vector matrix of neural computing question information and comment information.For example, CNN can be used
(Recurrent Neural Networks, is followed by (Convolutional Neural Network, convolutional neural networks) or RNN
Ring neural network) etc. calculate comment information and question information semantic matching degree, details are not described herein.
A kind of application scenarios of above-described embodiment are for example, user wants the Mobile phone of purchase apple, but is intended to understand it
Performance can issue enquirement, for example, whether mobile phone use is smooth, there is what problem, and whether photograph is clear etc..For user
The enquirement of sending, system search for the purchase user to match in the comment under commodity, the assessment in forum, the use in community automatically
Family discusses information and buys the information etc. of user and customer service consulting, chooses and puts question to maximally related several comments to return with user
To user is putd question to, then it can make that user is putd question to understand mobile phone situation in time in the case where nobody answers the question, promote user
Experience.
Key word matching method, syntactic match method and semantic matching method in above-described embodiment can be used alone,
It can also any two or three of combined use.For example, determining the Keywords matching of each comment information and question information respectively
Degree, syntactic match degree and semantic matching degree;By the corresponding Keywords matching degree of same comment information, syntactic match degree and semanteme
Matching degree is weighted, the matching degree as this comment information and question information.It can be matched accurate according to actual test
Different weights is arranged in the result of rate, respectively Keywords matching, syntactic match and semantic matches, and three kinds of matching degrees are added
Power, the matching degree as comment information and question information.
In step S108, at least one comment information is recommended to user according to matching result, the answer putd question to as user.
The user that matching degree recommends enquirement higher than the comment information of threshold value as answer can be chosen.Further, for
The comment information that matching degree is higher than threshold value can also be handled, for example, can match to these comment informations, by content
The comment information selected part that similarity is higher than threshold value recommends user or comment information is grouped recommendation according to meaning
To user.
Specifically, can choose the opposite or opposite comment information grouping of meaning by syntactic match recommends user, language
Method matching refers to previous embodiment.For example, customer problem be millet mobile phone and iPhone which it is more preferable use, some comment informations
More handy than iPhone for millet mobile phone, some comment informations are that iPhone is more handy than millet mobile phone, can by syntactic match
To judge that two word meanings are different, it can be grouped and recommend user respectively, the quantity of every group of comment information may further be counted,
Which make to put question to the more intuitive acquisition of user comment support number more.
Comment information can also be grouped by semantic analysis, for example, by using the method for previous embodiment, be determined
Content similarity is higher than a plurality of comment information of threshold value, they are divided into one group.In another example semantic analysis can believe comment
The emotion or attitude of breath are analyzed.Comment information be can analyze as front or negative emotion etc., existing feelings can be used
Feel analysis method, details are not described herein, is grouped according to the emotion of comment information or attitude, recommends user respectively.
The method of above-described embodiment, the mechanism application that can actively answer the question in conjunction with user, for example, being closed according to object
Credit grade, correlation time, the history of the user of connection (such as purchase commodity) answers efficiency, registration information, answer using in rate
At least one of information, choose user as answerer, answer is pushed into the user and is answered, at the same application above-mentioned implementation
The method of example pushes comment information as answer to enquirement user.Specifically, the credit grade of user is got over when choosing answerer
Height, the then probability for being chosen as answerer are higher;User away from puing question to the time closer, is then chosen as answerer's with object correlation time
Probability is higher;User's history answer efficiency is higher, for example, the average time from puing question to answering a question is shorter, is then chosen as back
The probability for the person of answering is higher;The user's registration time is longer, then the probability for being chosen as answerer is higher;Answer is then chosen as back using rate
The probability for the person of answering is higher.The credit grade of user, correlation time, history can be answered to efficiency, registration information, answer using rate
Different corresponding weights is respectively set in this several information, according to the information definite response person after weighting.
The method of above-described embodiment, the question information for user about object, by the comment information and enquirement of the object
Information is matched, and is chosen at least one comment information as the answer putd question to according to matching result and is recommended user.Due to commenting
By in information include evaluation of the other users about the object, using comment information can in time efficiently for quizmaster recommend with
The relevant answer of problem improves the efficiency replied in commodity question and answer, promotes user experience.
Other embodiments of disclosure data processing method are described below with reference to Fig. 2.
Fig. 2 is the flow chart of other embodiments of disclosure data processing method.As shown in Fig. 2, the method for the embodiment
It include: step S202~S214.
In step S202, comment information is obtained.
In step S204, comment information and object information, the corresponding relationship of user information and temporal information and storage are established.
Object information may include: object identity, object category information, object brand message etc..It is delivered and is commented according to user
It may include userspersonal information and user behavior information etc., user by the available user information of log-on message when information
People's information is for example, user identifier, user's registration time, user credit grade etc., user behavior information such as review record are answered
Put question to record etc..User information can be made comments by user information when log-on message (such as user identifier) looked into from system
Look for acquisition.Temporal information includes: the comment time.
After carrying out the comment information that automatic audit retains normal legal to comment information, comment information can be directly established
Corresponding relationship and storage with object information, user information and temporal information.Comment can also be believed with reference in previous embodiment
After breath is segmented, extracts the processing such as keyword, syntactic information, semantic information, believe with object information, user information and time
The corresponding relationship of breath and storage.Above-mentioned processing is carried out to comment information in advance, can be improved and recommend comment information as answer
Efficiency.
In step S206, question information of the user about object is obtained.
In step S208, the comment information of stored object is searched.
In step S210, according in the keyword of comment information and question information, syntactic information and semantic information at least
One information matches comment information with question information.
Step S206~S210 can refer to the description of the corresponding embodiment of earlier figures 1.
In step S212, according to the corresponding user credit grade of each comment information, user's registration information, comment time letter
It ceases and using at least one information in rate, matching result is modified.
In some embodiments, different user credit grade weights can be set for different user credit grades,
User credit higher grade, and user credit grade weight is higher.Different user's registrations can be set for the user's registration time
Weight, the user's registration time is more early, and registration weight is higher.Different comment time weightings can be set for the comment time, comment
Smaller by time lead time corresponding with question information, comment time weighting is higher.Rate can be used for different answers
Answer is set and uses rate weight, answer uses the higher answer of rate, higher using rate weight.The review record of user can also be directed to
Setting comment effect weight, effective review record is more, and comment effect weight is bigger.It can be chosen for actual demand different
Information is arranged different weights and is modified to matching result.
Further, it is possible to every weight is normalized, by the corresponding user credit grade weight of comment information, user
Registration weight, comment time weighting, comment effect weight and answer use at least one and the comment information pair in rate weight
The matching degree answered is multiplied, and obtained product is as revised matching result.
In step S214, at least one comment information is recommended to user according to revised matching result, is mentioned as user
The answer asked.
Comment information can be ranked up according to revised matching result, choose the comment letter that matching degree is greater than threshold value
Breath, which is recommended, puts question to user.This specific step can refer to the description of the corresponding embodiment of earlier figures 1.
Method through the foregoing embodiment can put question to user for recommending with more the comment information of reference value, into
One step promotes user experience.
The disclosure also provides a kind of data processing equipment, is described below with reference to Fig. 3.
Fig. 3 is the structure chart of some embodiments of disclosure data processing equipment.As shown in figure 3, the device of the embodiment
30 include: that question information obtains module 302, comment information searching module 304, matching module 306, answer recommending module 308.
Question information obtains module 302, for obtaining question information of the user about object.
Comment information searching module 304, for searching the comment information of stored object.
Comment information includes obtaining from least one in object review pages, the question and answer page, community's class page and customer service system
The comment information taken.
Matching module 306, in the keyword, syntactic information and semantic information according to comment information and question information
At least one information, comment information is matched with question information.
In some embodiments, matching module 306 for segmenting question information and comment information respectively, according to each
The word frequency of a word and number of training comprising the word extract the keyword of question information and comment information respectively, according to
The similarity of the keyword of each comment information and question information, determines the Keywords matching of each comment information and question information
Degree.
In some embodiments, matching module 306 is for segmenting question information and comment information respectively, according to mentioning
It asks the part of speech of each word in information and comment information, determines the grammer knot of each sentence in question information and comment information respectively
Structure determines each comment information and puts question to according to the similarity of the syntactic structure of sentence each in question information and comment information
The syntactic match degree of information.
In some embodiments, matching module 306 is true respectively for segmenting respectively to question information and comment information
The term vector for determining each word in question information and comment information, according to the word of word each in question information and comment information to
Amount calculates the semantic matching degree of each comment information and question information.
In some embodiments, matching module 306 is used to determine the keyword of each comment information and question information respectively
Matching degree, syntactic match degree and semantic matching degree, by the corresponding Keywords matching degree of same comment information, syntactic match degree and
Semantic matching degree is weighted, the matching degree as this comment information and question information.
Answer recommending module 308 is mentioned for recommending at least one comment information to user according to matching result as user
The answer asked.
In some embodiments, answer recommending module 308 be used for according to the corresponding user credit grade of each comment information,
User's registration information is commented on temporal information and using at least one information in rate, is modified to matching result, according to amendment
Matching result afterwards recommends at least one comment information to user.
Further, matching result includes the matching degree of each comment information and question information;Answer recommending module 308 is used for
By the corresponding user credit grade weight of comment information, user's registration weight, comment time weighting and answer using in rate weight
At least one of the multiplication of corresponding with comment information matching degree, obtained product is as revised matching result;User's letter
With higher grade, user credit grade weight is higher;The user's registration time is more early, and registration weight is higher;It comments on the time and puts question to
The corresponding lead time of information is smaller, and comment time weighting is higher.
As shown in figure 3, the data processing equipment 30 can also include: comment information processing module in some embodiments
310, for obtaining comment information, establishing the corresponding relationship of comment information and object information, user information and temporal information and depositing
Storage.
Data processing equipment in embodiment of the disclosure can realize respectively by various calculating equipment or computer system, under
Face combines Fig. 4 and Fig. 5 to be described.
Fig. 4 is the structure chart of some embodiments of disclosure data processing equipment.As shown in figure 4, the device of the embodiment
40 include: memory 410 and the processor 420 for being coupled to the memory 410, and processor 420 is configured as being based on being stored in
Instruction in memory 410 executes the data processing method in the disclosure in any some embodiments.
Wherein, memory 410 is such as may include system storage, fixed non-volatile memory medium.System storage
Device is for example stored with operating system, application program, Boot loader (Boot Loader), database and other programs etc..
Fig. 5 is the structure chart of other embodiments of disclosure data processing equipment.As shown in figure 5, the dress of the embodiment
Setting 50 includes: memory 510 and processor 520, similar with memory 410 and processor 420 respectively.It can also include defeated
Enter output interface 530, network interface 540, memory interface 550 etc..These interfaces 530,540,550 and memory 510 and place
It can for example be connected by bus 560 between reason device 520.Wherein, input/output interface 530 is display, mouse, keyboard, touching
It touches the input-output equipment such as screen and connecting interface is provided.Network interface 540 provides connecting interface for various networked devices, such as can be with
It is connected to database server or cloud storage server etc..Memory interface 550 is that the external storages such as SD card, USB flash disk mention
For connecting interface.
Those skilled in the art should be understood that embodiment of the disclosure can provide as method, system or computer journey
Sequence product.Therefore, complete hardware embodiment, complete software embodiment or combining software and hardware aspects can be used in the disclosure
The form of embodiment.Moreover, it wherein includes the calculating of computer usable program code that the disclosure, which can be used in one or more,
Machine can use the meter implemented in non-transient storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of calculation machine program product.
The disclosure is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present disclosure
Figure and/or block diagram describe.It is interpreted as to be realized by computer program instructions each in flowchart and/or the block diagram
The combination of process and/or box in process and/or box and flowchart and/or the block diagram.It can provide these computer journeys
Sequence instruct to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor with
A machine is generated, so that the instruction generation executed by computer or the processor of other programmable data processing devices is used for
Realize the dress for the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram
It sets.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The foregoing is merely the preferred embodiments of the disclosure, not to limit the disclosure, all spirit in the disclosure and
Within principle, any modification, equivalent replacement, improvement and so on be should be included within the protection scope of the disclosure.
Claims (18)
1. a kind of data processing method, comprising:
Obtain question information of the user about object;
Search the comment information of the stored object;
According at least one letter in the keyword of the comment information and the question information, syntactic information and semantic information
Breath, the comment information is matched with the question information;
Recommend at least one comment information to the user according to matching result, the answer putd question to as the user.
2. data processing method according to claim 1, wherein it is described by the comment information and the question information into
Row matches
The Keywords matching degree, syntactic match degree and semantic matching degree of each comment information and the question information are determined respectively;
The corresponding Keywords matching degree of same comment information, syntactic match degree and semantic matching degree are weighted, as this
The matching degree of comment information and the question information.
3. data processing method according to claim 1, wherein described to be recommended at least according to matching result to the user
One comment information includes:
According to the corresponding user credit grade of each comment information, user's registration information, comment temporal information and use in rate
At least one information, is modified the matching result;
Recommend at least one comment information to the user according to revised matching result.
4. data processing method according to claim 3, wherein
The matching result includes the matching degree of each comment information and the question information;
Described be modified to the matching result include:
The corresponding user credit grade weight of comment information, user's registration weight, comment time weighting and answer are weighed using rate
At least one matching degree corresponding with the comment information in weight is multiplied, and obtained product is as revised matching result;
Wherein, user credit higher grade, and the user credit grade weight is higher;The user's registration time is more early, the registration
Weight is higher;The comment time, lead time corresponding with the question information was smaller, and the comment time weighting is higher.
5. data processing method according to claim 1-4, further includes:
Comment information is obtained, the comment information includes from object review pages, the question and answer page, community's class page and customer service system
In the comment information that obtains at least one;
Establish comment information and object information, the corresponding relationship of user information and temporal information and storage.
6. data processing method according to claim 1-4, wherein
It is described the question information match with the comment information according to keyword include:
The question information and the comment information are segmented respectively;
According to the word frequency of each word and comprising the number of training of the word, the question information and the comment are extracted respectively
The keyword of information;
According to the similarity of each comment information and the keyword of the question information, each comment information and the enquirement are determined
The Keywords matching degree of information.
7. data processing method according to claim 1-4, wherein
It is described the question information match with the comment information according to syntactic information include:
The question information and the comment information are segmented respectively;
According to the part of speech of each word in the question information and the comment information, the question information and described is determined respectively
The syntactic structure of each sentence in comment information;
According to the similarity of the syntactic structure of each sentence in the question information and the comment information, each item comment letter is determined
The syntactic match degree of breath and the question information.
8. data processing method according to claim 1-4, wherein
It is described the question information match with the comment information according to semantic information include:
The question information and the comment information are segmented respectively;
The term vector of each word in the question information and the comment information is determined respectively;
According to the term vector of each word in the question information and the comment information, calculates each comment information and mentioned with described
Ask the semantic matching degree of information.
9. a kind of data processing equipment, comprising:
Question information obtains module, for obtaining question information of the user about object;
Comment information searching module, for searching the comment information of the stored object;
Matching module, for according in the keyword of the comment information and the question information, syntactic information and semantic information
At least one of information, the comment information is matched with the question information;
Answer recommending module, for recommending at least one comment information to the user according to matching result, as the user
The answer of enquirement.
10. data processing equipment according to claim 9, wherein
The matching module is used to determine the Keywords matching degree, syntactic match of each comment information Yu the question information respectively
Degree and semantic matching degree carry out the corresponding Keywords matching degree of same comment information, syntactic match degree and semantic matching degree
Weighting, the matching degree as this comment information and the question information.
11. data processing equipment according to claim 9, wherein
The answer recommending module is used for according to the corresponding user credit grade of each comment information, user's registration information, comment
At least one information in temporal information and use rate, is modified the matching result, according to revised matching result
Recommend at least one comment information to the user.
12. data processing equipment according to claim 11, wherein
The matching result includes the matching degree of each comment information and the question information;
When the answer recommending module is used for the corresponding user credit grade weight of comment information, user's registration weight, comment
Between weight and answer using in rate weight at least one of matching degree multiplication corresponding with the comment information, obtained product conduct
Revised matching result;
Wherein, user credit higher grade, and the user credit grade weight is higher;The user's registration time is more early, the registration
Weight is higher;The comment time, lead time corresponding with the question information was smaller, and the comment time weighting is higher.
13. according to the described in any item data processing equipments of claim 9-12, further includes:
Comment information processing module establishes comment information and object information, user information and time is believed for obtaining comment information
The corresponding relationship of breath and storage;
Wherein, the comment information includes at least one from object review pages, the question and answer page, community's class page and customer service system
Locate the comment information obtained.
14. according to the described in any item data processing equipments of claim 9-12, wherein
The matching module for segmenting the question information and the comment information respectively, according to the word of each word
Frequency and the number of training comprising the word, extract the keyword of the question information and the comment information, according to each respectively
The similarity of the keyword of comment information and the question information, determines the key of each comment information and the question information
Word matching degree.
15. according to the described in any item data processing equipments of claim 9-12, wherein
The matching module for segmenting the question information and the comment information respectively, according to the question information
With the part of speech of word each in the comment information, each sentence in the question information and the comment information is determined respectively
Syntactic structure determines each item according to the similarity of the syntactic structure of each sentence in the question information and the comment information
The syntactic match degree of comment information and the question information.
16. according to the described in any item data processing equipments of claim 9-12, wherein
The matching module determines the enquirement for segmenting respectively to the question information and the comment information respectively
The term vector of each word in information and the comment information, according to each word in the question information and the comment information
Term vector, calculate each comment information and the question information semantic matching degree.
17. a kind of data processing equipment, comprising:
Memory;And
It is coupled to the processor of the memory, the processor is configured to based on the finger being stored in the memory devices
It enables, executes such as the described in any item data processing methods of claim 1-8.
18. a kind of computer readable storage medium, is stored thereon with computer program, wherein when the program is executed by processor
The step of realizing any one of claim 1-8 the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810308511.8A CN110362662A (en) | 2018-04-09 | 2018-04-09 | Data processing method, device and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810308511.8A CN110362662A (en) | 2018-04-09 | 2018-04-09 | Data processing method, device and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110362662A true CN110362662A (en) | 2019-10-22 |
Family
ID=68213413
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810308511.8A Pending CN110362662A (en) | 2018-04-09 | 2018-04-09 | Data processing method, device and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110362662A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112801745A (en) * | 2021-02-02 | 2021-05-14 | 李海涛 | Big data platform based online comment validity recommendation method |
CN112989020A (en) * | 2019-12-17 | 2021-06-18 | 北京沃东天骏信息技术有限公司 | Information processing method, apparatus and computer readable storage medium |
CN113051380A (en) * | 2021-03-23 | 2021-06-29 | 北京百度网讯科技有限公司 | Information generation method and device, electronic equipment and storage medium |
CN113610247A (en) * | 2021-07-22 | 2021-11-05 | 北京中交兴路信息科技有限公司 | Fault help seeking method and device for freight vehicle, storage medium and terminal |
CN116226677A (en) * | 2023-05-09 | 2023-06-06 | 北京搜狐新媒体信息技术有限公司 | Parallel corpus construction method and device, storage medium and electronic equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102279894A (en) * | 2011-09-19 | 2011-12-14 | 嘉兴亿言堂信息科技有限公司 | Method for searching, integrating and providing comment information based on semantics and searching system |
CN104536980A (en) * | 2014-12-05 | 2015-04-22 | 百度在线网络技术(北京)有限公司 | To-be-commented item quality information determination method and device |
CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
CN106709007A (en) * | 2016-12-23 | 2017-05-24 | 北京奇虎科技有限公司 | Automobile search result display method and automobile search result display device |
CN106997376A (en) * | 2017-02-28 | 2017-08-01 | 浙江大学 | The problem of one kind is based on multi-stage characteristics and answer sentence similarity calculating method |
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 |
CN107844533A (en) * | 2017-10-19 | 2018-03-27 | 云南大学 | A kind of intelligent Answer System and analysis method |
-
2018
- 2018-04-09 CN CN201810308511.8A patent/CN110362662A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102279894A (en) * | 2011-09-19 | 2011-12-14 | 嘉兴亿言堂信息科技有限公司 | Method for searching, integrating and providing comment information based on semantics and searching system |
CN104536980A (en) * | 2014-12-05 | 2015-04-22 | 百度在线网络技术(北京)有限公司 | To-be-commented item quality information determination method and device |
CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
CN106709007A (en) * | 2016-12-23 | 2017-05-24 | 北京奇虎科技有限公司 | Automobile search result display method and automobile search result display device |
CN106997376A (en) * | 2017-02-28 | 2017-08-01 | 浙江大学 | The problem of one kind is based on multi-stage characteristics and answer sentence similarity calculating method |
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 |
CN107844533A (en) * | 2017-10-19 | 2018-03-27 | 云南大学 | A kind of intelligent Answer System and analysis method |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112989020A (en) * | 2019-12-17 | 2021-06-18 | 北京沃东天骏信息技术有限公司 | Information processing method, apparatus and computer readable storage medium |
CN112801745A (en) * | 2021-02-02 | 2021-05-14 | 李海涛 | Big data platform based online comment validity recommendation method |
CN113051380A (en) * | 2021-03-23 | 2021-06-29 | 北京百度网讯科技有限公司 | Information generation method and device, electronic equipment and storage medium |
CN113051380B (en) * | 2021-03-23 | 2023-07-25 | 北京百度网讯科技有限公司 | Information generation method, device, electronic equipment and storage medium |
CN113610247A (en) * | 2021-07-22 | 2021-11-05 | 北京中交兴路信息科技有限公司 | Fault help seeking method and device for freight vehicle, storage medium and terminal |
CN116226677A (en) * | 2023-05-09 | 2023-06-06 | 北京搜狐新媒体信息技术有限公司 | Parallel corpus construction method and device, storage medium and electronic equipment |
CN116226677B (en) * | 2023-05-09 | 2023-07-14 | 北京搜狐新媒体信息技术有限公司 | Parallel corpus construction method and device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2018383346B2 (en) | Domain-specific natural language understanding of customer intent in self-help | |
CN111177569B (en) | Recommendation processing method, device and equipment based on artificial intelligence | |
CN108536852B (en) | Question-answer interaction method and device, computer equipment and computer readable storage medium | |
CN110362662A (en) | Data processing method, device and computer readable storage medium | |
KR102472572B1 (en) | Method for profiling user's intention and apparatus therefor | |
CN111475729B (en) | Search content recommendation method and device | |
US9251292B2 (en) | Search result ranking using query clustering | |
CN106407280A (en) | Query target matching method and device | |
CN109885773A (en) | A kind of article personalized recommendation method, system, medium and equipment | |
CN110955831B (en) | Article recommendation method and device, computer equipment and storage medium | |
US10002187B2 (en) | Method and system for performing topic creation for social data | |
CN103870538A (en) | Method, user modeling equipment and system for carrying out personalized recommendation for users | |
CN110516033A (en) | A kind of method and apparatus calculating user preference | |
CN107526718A (en) | Method and apparatus for generating text | |
Saia et al. | A semantic approach to remove incoherent items from a user profile and improve the accuracy of a recommender system | |
CN101937432A (en) | System and method for negotiation between two parties according to supply and demand information | |
CN113821588A (en) | Text processing method and device, electronic equipment and storage medium | |
CN113722487A (en) | User emotion analysis method, device and equipment and storage medium | |
CN112182126A (en) | Model training method and device for determining matching degree, electronic equipment and readable storage medium | |
CN111882224A (en) | Method and device for classifying consumption scenes | |
CN111737607A (en) | Data processing method, data processing device, electronic equipment and storage medium | |
Chhabra et al. | Exploring Hugging Face Transformer Library Impact on Sentiment Analysis: A Case Study | |
CN113344674A (en) | Product recommendation method, device, equipment and storage medium based on user purchasing power | |
CN114595377A (en) | Vocabulary recommendation method and device, terminal and readable storage medium | |
CN112989020A (en) | Information processing method, apparatus and computer readable storage medium |
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 |