CN110135694A - Product risks appraisal procedure, device, computer equipment and storage medium - Google Patents
Product risks appraisal procedure, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110135694A CN110135694A CN201910296125.6A CN201910296125A CN110135694A CN 110135694 A CN110135694 A CN 110135694A CN 201910296125 A CN201910296125 A CN 201910296125A CN 110135694 A CN110135694 A CN 110135694A
- Authority
- CN
- China
- Prior art keywords
- product
- assessed
- target text
- data
- text data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application involves big data technical field, a kind of product risks appraisal procedure, device, computer equipment and storage medium are provided.Method includes selecting information according to the product that risk assessment request carries, determine product to be assessed, obtain the corresponding retrieval regular expression of product to be assessed, according to retrieval regular expression, retrieve the associating web pages of product to be assessed, and target text data relevant to product to be assessed in associating web pages are extracted, target text data are inputted into pre-set product risk evaluation model, obtain the risk evaluation result of product to be assessed.Real-time retrieval can be carried out by the associating web pages to product to be assessed, promptly and accurately to the acquisitions of the target text data of product to be assessed, improve the Risk Assessment Quality to product to be assessed.
Description
Technical field
This application involves big data technical fields, set more particularly to a kind of product risks appraisal procedure, device, computer
Standby and storage medium.
Background technique
With the continuous development of Internet technology, e-commerce is developing into a flourishing business model, so more
Add and realize convenient for user to the feedback of product, is equally also easier to the feedback for getting different user to product, client is consuming
Later, the product often just bought delivers their view or comments on corresponding product publishing web page, for gold
Melt product, other consumers often want according to above webpage view and comment carry out risk assessment, decide whether to purchase
Buy the product.
But since the renewal speed for assessing content in webpage is very fast, it is difficult to get in real time update about wanting to know about
All assessment data of product, it is not prompt enough to the acquisition of the risk assessment data of product accurate to cause, and is easy to cause to product
Risk Assessment Quality it is not high.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of product that can be improved product risks quality of evaluation
Methods of risk assessment, device, computer equipment and storage medium.
A kind of product risks appraisal procedure, which comprises
Information is selected according to the product that risk assessment request carries, determines product to be assessed;
Obtain the corresponding retrieval regular expression of the product to be assessed;
According to the retrieval regular expression, the associating web pages of the product to be assessed are retrieved, and extract the association net
Target text data relevant to the product to be assessed in page;
The target text data are inputted into pre-set product risk evaluation model, the risk for obtaining the product to be assessed is commented
Estimate result.
In one of the embodiments, it is described obtain the corresponding retrieval regular expression of the product to be assessed before, and also
Include:
Data are issued according to preset product, determine that publication has multiple associating web pages of the product to be assessed, the pass
Networking page is used to show the assessment data of the product to be assessed of real-time update;
The preset keyword of the product to be assessed is obtained, and obtains the correspondence domain name of the associating web pages;According to described
Preset keyword and domain name construct the corresponding retrieval regular expression of the product to be assessed.
It in one of the embodiments, include the real-time assessment data of the product to be assessed in the associating web pages;Institute
State according to the retrieval regular expression, retrieve the associating web pages of the product to be assessed, and extract in the associating web pages with
The relevant target text data of the product to be assessed include:
According to the domain-name information in the retrieval regular expression, the associating web pages of the product to be assessed are retrieved;
According to the preset keyword that carries in the retrieval regular expression, extract in the associating web pages with it is described to be evaluated
The corresponding real-time assessment data of the yield by estimation product;
Each real-time assessment data are subjected to clustering processing, obtain multiple target text data for carrying cluster labels
Gather, includes the target text data in the target text data acquisition system.
It is described in one of the embodiments, that the target text data are inputted into pre-set product risk evaluation model, it obtains
The risk evaluation result of the product to be assessed includes:
Obtain the corresponding vector of each target text data in each target text data acquisition system;
The vector is inputted into pre-set product risk evaluation model, obtains the corresponding assessment of the target text data acquisition system
Label;
It is carried according to each corresponding assessment tag of target text data acquisition system and the target text data acquisition system
Cluster labels, obtain the risk evaluation result of the product to be assessed.
It is described in one of the embodiments, that the target text data are inputted into pre-set product risk evaluation model, it obtains
Before the risk evaluation result for obtaining the product to be assessed, further includes:
The Product evaluation data for obtaining sample product carry out clustering processing to the Product evaluation data, to the product
It assesses data and carries out clustering processing;
The product category mark carried according to the sample, by the Product evaluation data clusters processing result by cluster dimension
Degree is updated to the product category and identifies corresponding default sample database;
The incidence relation for obtaining the default sample database and initial product risk evaluation model is closed according to the association
System obtains the corresponding Product evaluation data of each initial product risk evaluation model;
According to the Product evaluation data, the initial product risk evaluation model is trained, is obtained described default
Product risks assessment models.
It is described according to the Product evaluation data in one of the embodiments, to the initial product risk assessment mould
Type is trained, and is obtained the pre-set product risk evaluation model and is included:
According to the cluster dimension, the proprietary word in field and emotional characteristics of the Product evaluation data of the cluster dimension are extracted
Word;
According to the neck for passing judgement on part of speech and extract of the feature part of speech of the proprietary word in preset field and emotional characteristics word
The proprietary word in domain and the emotional characteristics word, sort out Product evaluation data described in the cluster dimension;
Vector conversion process is carried out to the Product evaluation data, and is tied according to the corresponding classification of the Product evaluation data
Fruit determines that the Product evaluation data correspond to the assessment tag of vector;
The vector of the assessment tag will be carried in the cluster dimension, input in initial product risk evaluation model with
The corresponding evaluation module of the cluster dimension, sub-module are trained the initial product risk evaluation model, obtain described
Pre-set product risk evaluation model.
The target text data are inputted into pre-set product risk evaluation model in one of the embodiments, obtain institute
The risk evaluation result for stating product to be assessed includes:
The product type mark that the product to be assessed carries is obtained, determines the product category of the product to be assessed, and
Obtain pre-set product risk evaluation model corresponding with the product category;
The target text data are inputted into the pre-set product risk evaluation model, obtain the wind of the product to be assessed
Dangerous assessment result.
A kind of product risks assessment device, described device include:
Product determining module to be assessed, the product for being carried according to risk assessment request select information, determine to be assessed
Product;
It retrieves regular expression and obtains module, for obtaining the corresponding retrieval regular expression of the product to be assessed;
Target text data extraction module, for retrieving the product to be assessed according to the retrieval regular expression
Associating web pages, and extract target text data relevant to the product to be assessed in the associating web pages;
Risk evaluation module, for the target text data to be inputted pre-set product risk evaluation model, described in acquisition
The risk evaluation result of product to be assessed.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Information is selected according to the product that risk assessment request carries, determines product to be assessed;
Obtain the corresponding retrieval regular expression of the product to be assessed;
According to the retrieval regular expression, the associating web pages of the product to be assessed are retrieved, and extract the association net
Target text data relevant to the product to be assessed in page;
The target text data are inputted into pre-set product risk evaluation model, the risk for obtaining the product to be assessed is commented
Estimate result.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Information is selected according to the product that risk assessment request carries, determines product to be assessed;
Obtain the corresponding retrieval regular expression of the product to be assessed;
According to the retrieval regular expression, the associating web pages of the product to be assessed are retrieved, and extract the association net
Target text data relevant to the product to be assessed in page;
The target text data are inputted into pre-set product risk evaluation model, the risk for obtaining the product to be assessed is commented
Estimate result.
The said goods methods of risk assessment, device, computer equipment and storage medium are carried by risk assessment request
Product selects information, determines product to be assessed, and obtain the corresponding retrieval regular expression of product to be assessed, may be implemented to treat
The associating web pages for assessing product carry out real-time retrieval, get the relevant target text data of currently existing product to be assessed,
To utilize pre-set product risk evaluation model, the risk for carrying out product to be assessed to the file destination data obtained in real time is commented
Estimate, obtain the risk evaluation result of product to be assessed, solves the target about product to be assessed that can not obtain update in real time
The problem of text data, promptly and accurately to the acquisitions of the target text data of product to be assessed, to improve to production to be assessed
The Risk Assessment Quality of product.
Detailed description of the invention
Fig. 1 is the application scenario diagram of product risks appraisal procedure in one embodiment;
Fig. 2 is the flow diagram of product risks appraisal procedure in one embodiment;
Fig. 3 is the flow diagram of product risks appraisal procedure in another embodiment;
Fig. 4 is the flow diagram of product risks appraisal procedure in another embodiment;
Fig. 5 is the flow diagram of product risks appraisal procedure in another embodiment;
Fig. 6 is the flow diagram of the sub-step of step S490 in Fig. 5 in one embodiment;
Fig. 7 is the structural block diagram that product risks assess device in one embodiment;
Fig. 8 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Product risks appraisal procedure provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated with server 104 by network.The selection function that user passes through the product selection interface of triggering terminal 102
Key selects the product wanted to know about, and it is corresponding to send the product in real time for the corresponding product of function key that terminal 102 is triggered according to user
Risk assessment request to server 104, server 104 selects information according to the product that risk assessment request carries, determine to
Product is assessed, and obtains the corresponding retrieval regular expression of product to be assessed, server 104 is according to retrieval regular expression, inspection
The associating web pages of rope product to be assessed, and target text data relevant to product to be assessed in associating web pages are extracted, by target
Text data inputs pre-set product risk evaluation model, obtains the risk evaluation result of product to be assessed and by product pair to be assessed
The risk evaluation result answered pushes to terminal 102.Wherein, terminal 102 can be, but not limited to be various personal computers, notebook
Computer, smart phone, tablet computer and portable wearable device, server 104 can be either more with independent server
The server cluster of a server composition is realized.
In one embodiment, as shown in Fig. 2, providing a kind of product risks appraisal procedure, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
Step S200 selects information according to the product that risk assessment request carries, determines product to be assessed.
Risk assessment request refers to that terminal is sent to server, for making server carry out risk to the product that user selects
The request message of assessment.Product selection information refers to that user carries out selection to product by the product selection interface of triggering terminal
As a result the information generated.Product to be assessed refers to that the product for needing to carry out risk assessment of user's selection, product can be divided into not
Same product type, by taking financial products as an example, product type includes finance product, loan product and insurance products etc..With
Family selects the product wanted to know about by the selection function key of the product selection interface of triggering terminal, and terminal is triggered according to user
The corresponding product of function key sends the corresponding risk assessment of the product and requests to server, in real time so that server passes through to choosing
The product selected carries out risk assessment, and the risk evaluation result for feeding back the product provides purchase for user and suggest simultaneously to user
Auxiliary user further appreciates that the total evaluation situation of the product.
Step S300 obtains the corresponding retrieval regular expression of product to be assessed.
Retrieval regular expression is to be retrieved for realizing the webpage of specified type, and extract the correlation in the webpage obtained
The logical formula of specified content.Enterprise can generally be sent out in classification by product in different web pages when issuing financial products
Cloth is consulted convenient for user, buys and deliver assessment, and identical product can sometimes be published on different webpages, but each webpage domain
Name is more similar, and it is identical for having partial bytes in domain name.Retrieving regular expression then includes the association for issuing product to be assessed
The domain name of the same section of selected parts in each domain name of webpage, retrieval regular expression can also include the corresponding pass of product to be assessed
Key word carries out the extraction of target text data for the webpage to retrieval.It can also be set according to demand in retrieval regular expression
Fixed single or multiple indefinite bytes, to be retrieved to obtain multiple webpages according to indefinite byte in retrieval, wherein indefinite word
Section refers to the uncertain byte in domain name with certain value range.In embodiment, a product to be assessed can correspond to
One retrieval regular expression, can also correspond to multiple retrieval regular expressions.
Step S400 retrieves the associating web pages of product to be assessed, and extract in associating web pages according to retrieval regular expression
Target text data relevant to product to be assessed.
Using retrieval regular expression, the associating web pages of to be assessed product of the search comprising corresponding domain name constitute webpage collection
It closes.When it is multiple for retrieving regular expression, according to putting in order for retrieval regular expression, web search is successively carried out, when
Retrieval regular expression searches the default value range of the indefinite byte when including indefinite byte, according to the value range, according to
It is secondary to give the indefinite byte assignment, obtain the associating web pages of product to be assessed.It is carried out according to the keyword in retrieval regular expression
The extraction of target data text, wherein retrieval regular expression includes the requirement of keyword match canonical, such as character types (number
Word or character string), matching number (character number to be matched), matching area (boundary, centre, forward and backward), match pattern it is (complete
Office's matching or part match), capital and small letter limitation (entirely be capitalization or be small letter entirely), number of repetition (frequency of occurrence of same character)
Deng.Keyword refers to that the data information for characterizing product feature, different product are provided with different keywords, such as financing produces
The keyword of product can be name of product, Nian Hua, earning rate, time limit, purchase amount of money etc..Due to being also likely to be present in same webpage
Other garbages, server need to carry out the information associated with product to be assessed in webpage by preset keyword
Screening and extraction, carry out the filtering of data, and the data of extraction are stored.In one embodiment, data filtering can be with
Stop words processing is removed to realize by the target text data to associating web pages, and wherein stop words mainly includes tone pair
Word, auxiliary word, conjunction, the word of the parts of speech such as preposition.
Target text data are inputted pre-set product risk evaluation model, obtain the risk of product to be assessed by step S500
Assessment result.
Preset product analysis model refers to trained in advance for carrying out product according to the target text data of input
The model of risk analysis, target text data may include the data information of multiple dimensions of product to be assessed, by different dimensions
Data information distinguish the grading module divided in input model, the data information of each dimension is assessed respectively, according to every
The model evaluation parameter of the assessment result of dimension information and corresponding dimension calculates the integrated risk assessment of product to be assessed, and
Export risk evaluation result.Risk evaluation result may include comments, and comments refer to the straight of product analysis result
It sees and expresses, such as the finance product risk is low, it is proposed that purchase.Wherein, different product types has different evaluation criterias, example
Such as, the assessment factor of regular class finance product is income, and the assessment factor of the finance product of stock class is risk etc..
The said goods methods of risk assessment selects information by the product that risk assessment request carries, determines the yield by estimation to be evaluated
Product, and the corresponding retrieval regular expression of product to be assessed is obtained, it may be implemented to carry out the associating web pages of product to be assessed real
When retrieve, the relevant target text data of current existing product to be assessed are got, to utilize pre-set product risk assessment
The file destination data obtained in real time are carried out the risk assessment of product to be assessed by model, and the risk for obtaining product to be assessed is commented
Estimate as a result, solving the problems, such as the target text data about product to be assessed that can not obtain update in real time, to production to be assessed
The acquisition of the target text data of product promptly and accurately, to improve the Risk Assessment Quality to product to be assessed.
In one embodiment, as shown in figure 3, step S300, obtains the corresponding retrieval regular expression of product to be assessed
Before, further includes:
Step S270 issues data according to preset product, determines that publication has multiple associating web pages of product to be assessed, closes
Networking page is used to show the assessment data of the product to be assessed of real-time update.
Step S280, obtains the preset keyword of product to be assessed, and obtains the correspondence domain name of associating web pages;
Step S290 constructs the corresponding retrieval regular expression of product to be assessed according to preset keyword and domain name.
Product publication data refer to the data of the publishing web page for record product, and product publishing web page is used for release product
Relevant information, and implement update show product assessment data webpage, identical product publishing web page may include multiple productions
Product, identical product can reside in multiple publishing web pages, and the webpage of the relevant information comprising identical product is the association of the product
Webpage.The preset keyword of product to be assessed refer to with characterization the specific domain feature words of product, a product to be assessed can
To be corresponding with multiple preset keywords, for example, finance product keyword may include name of product, Nian Hua, earning rate, the time limit,
Play purchase amount of money etc..Webpage search range is determined according to the domain name of the associating web pages of product to be assessed, is determined according to preset keyword
Target text data to be extracted in webpage construct the corresponding retrieval canonical of product to be assessed by preset keyword and domain name
Expression formula, can be with the target text data of quick obtaining to real-time update.
It in one embodiment, include the real-time assessment data of product to be assessed in associating web pages;As shown in figure 4, step
S400, according to retrieval regular expression, retrieve the associating web pages of product to be assessed, and extract in associating web pages with product to be assessed
Relevant target text data include:
Step S420 retrieves the associating web pages of product to be assessed according to the domain-name information in retrieval regular expression.
Step S430, according to the preset keyword that carries in retrieval regular expression, extract in associating web pages with it is to be assessed
The corresponding real-time assessment data of product.
Each real-time assessment data are carried out clustering processing by step S440, obtain multiple target texts for carrying cluster labels
Notebook data set includes target text data in target text data acquisition system.
Clustering processing refers to the treatment process that the real-time assessment data of same dimension are carried out to Commonness Analysis and data classification,
Target text data can be obtained by carrying out clustering processing to real-time assessment data.In embodiment, pass through target text number
The preset keyword or domain feature words for including in carry out data screening to real-time assessment data and carry out data classification, will
The preset keyword or domain feature words obtain the target text number for carrying cluster labels as the cluster labels for sorting out data
According to set.
In one embodiment, as shown in figure 4, target text data are inputted pre-set product risk assessment by step S500
Model, the risk evaluation result for obtaining product to be assessed include:
Step S520 obtains the corresponding vector of each target text data in each target text data acquisition system.
Vector is inputted pre-set product risk evaluation model, obtains that target text data acquisition system is corresponding to be commented by step S530
Estimate label.
Step S540 is carried according to the corresponding assessment tag of each target text data acquisition system and target text data acquisition system
Cluster labels, obtain the risk evaluation result of product to be assessed.
By being segmented to target text data, using the continuous bag of words of word2vec by the textual data after participle
According to vector is converted to, participle is characterized as the tool of real number value vector by continuous bag of words, using deep learning training, to text
The processing of this content is reduced to the processing model of the vector operation in vector space.Assessment tag refers to each dimension of product to be assessed
Assessment result constitute data label, for characterizing each dimension assessment result of product to be assessed, cluster labels refer to each mesh
The corresponding data dimensional characteristics label of text data set is marked, it is available by combining cluster labels with assessment tag
The feature and specific assessment result of each dimension of product to be assessed, to obtain the comprehensive risk assessment knot of product to be assessed
Fruit.
In one embodiment, as shown in figure 5, target text data are inputted pre-set product risk assessment by step S500
Model, before the risk evaluation result for obtaining product to be assessed, further includes:
Step S460 obtains the Product evaluation data of sample product, clustering processing is carried out to Product evaluation data, to product
It assesses data and carries out clustering processing.
Step S470 is identified according to the product category that sample carries, by Product evaluation data clusters processing result by cluster
Dimensions updating to product category identifies corresponding default sample database.
Step S480 obtains the incidence relation of default sample database and initial product risk evaluation model, according to association
Relationship obtains the corresponding Product evaluation data of each initial product risk evaluation model.
Step S490 is trained initial product risk evaluation model, obtains pre-set product according to Product evaluation data
Risk evaluation model.
Sample product refers to the product including having assessment result, obtains pre-set product risk evaluation model for training.
Product evaluation data refer to the data, such as the income height of A product, the risk height of B product of evaluation result etc. of characterization product.It produces
Product classification logotype is used to distinguish the product type of product, and the product of different product type corresponds to different product risks assessment moulds
Type, product type include insurance products, finance product and loan product etc., and clustering processing can press same type of product
The classification that each Product evaluation data are carried out according to cluster dimension after classification, can store product analysis data according to cluster dimension
To the sample database to corresponding product type.Initial product risk evaluation model, which refers to, to be used for through trained and parameter regulation,
The model of the risk assessment to goal-based assessment data may be implemented, in embodiment, initial product risk evaluation model can be
Deep neural network model including multiple data evaluation modules, each data processing module are used for the target text to each cluster dimension
Notebook data is assessed.Clustering processing process includes sorting out same type of product, and analyze and obtain identical product
The common denominator data of each Product evaluation data.Has assessment according to what each sample product in common denominator data, and cluster set carried
As a result, determining assessment weight corresponding to each dimension data in common denominator data, and commented assessment weight as initial product risk
Estimate the risk score index parameter of each module of model.
In one embodiment, as shown in fig. 6, step S490, according to Product evaluation data, to initial product risk assessment
Model is trained, and is obtained pre-set product risk evaluation model and is included:
Step S492, according to cluster dimension, the proprietary word in field and the mood for extracting the Product evaluation data of cluster dimension are special
Levy word.
Step S494 passes judgement on part of speech, Yi Jiti according to the feature part of speech of the proprietary word in preset field and emotional characteristics word
The proprietary word in the field taken and emotional characteristics word sort out Product evaluation data in cluster dimension.
Step S496 carries out vector conversion process to Product evaluation data, and according to the corresponding classification of Product evaluation data
As a result, determining that Product evaluation data correspond to the assessment tag of vector.
Step S498 will cluster the vector for carrying assessment tag in dimension, input in initial product risk evaluation model
Evaluation module corresponding with cluster dimension, sub-module are trained initial product risk evaluation model, obtain pre-set product wind
Dangerous assessment models.
The proprietary word in field refers to the proper noun of product fields, as the proprietary word in the field of financial product include income,
Risk, by stages interest rate and amount etc..Emotional characteristics word refers to for expressing relatively semantic passing judgement on property word, such as high and low,
It is long and short etc., but in different contexts, the same emotional characteristics word may express different meanings, such as income height and risk
Height, although all including emotional characteristics word "high", income height is commendatory term, and this kind of evaluation may be defined as favorable comment, but risk is high
It is derogatory term, may be defined as difference and comment, but risk and return relationship between is all the proprietary word in field, it is in embodiment, proprietary by defining field
The part of speech feature of word and emotional characteristics word pass judgement on part of speech, by way of combination, to determine the commendation and derogatory sense in each context,
Successively determine that target text data belong to favorable comment or poor comment.Favorable comment, which refers to, belongs to product to the view of product to be assessed or comment
The text of pole speech has generally comprised commendation expression in favorable comment, such as income is high, the time limit is short etc., and difference is commented then on the contrary, favorable comment and poor
The expression commented is obtained by the proprietary vocabulary of product scope and the combination of emotional characteristics word.The classification that favorable comment and difference are commented refers to favorable comment
The process that Product evaluation data and the assessment data commented of difference distinguish, categorization results include in such data the accounting of favorable comment with
The accounting that difference is commented, accounting data can be the Product evaluation data count that favorable comment information and difference comment information to account for the cluster dimension respectively
Ratio, can be indicated with percentage, categorization results determine the assessment tag of product to be assessed data of all categories, and are added to logical
It crosses in the corresponding vector of Product evaluation data, as the data label of vector, according to the appraisal right of each dimension of Product evaluation data
Weight, the risk score index parameter of initial neural network model, and according to the vector of each dimension of Product evaluation data, it is produced to initial
Product risk evaluation model is trained.Parameter threshold is assessed according to preset model, to the risk score of initial neural network model
Index parameter optimizes, and model evaluation parameter includes accuracy rate and recall rate, and accuracy rate is indicated for given test data
When collection, the ratio between sample number and total number of samples that classifier is correctly classified, that is, loss function are 0-1 losses in test data set
Accuracy rate.It may is that accuracy rate=qualification sample size/all total sample numbers of system with formula expression.Recall rate is covering
The measurement in face, measurement have multiple positive examples to be divided into positive example.It can be expressed as with formula: recall rate=qualification sample size/system
All qualification total sample numbers.When model evaluation parameter meets given threshold range, determine that initial product risk evaluation model is each
The risk score index parameter of module, to obtain pre-set product risk evaluation model.By to initial product risk assessment mould
Type is trained, and is optimized to model parameter, and the precision of analysis of product risks assessment models can be improved.
In one embodiment, as shown in figure 5, target text data are inputted pre-set product risk assessment by step S500
Model, the risk evaluation result for obtaining product to be assessed include:
Step S560 obtains the product type mark that product to be assessed carries, determines the product category of product to be assessed, and
Obtain pre-set product risk evaluation model corresponding with product category.
Target text data are inputted pre-set product risk evaluation model, obtain the risk of product to be assessed by step S570
Assessment result.
The product of different product type carries out risk assessment, Ke Yigen by different pre-set product risk evaluation models
It is accounted for according to the assessment factor of each product type, carries out specific aim assessment, quality of evaluation can be improved.In other embodiments
In, comments corresponding with risk evaluation result can also be generated according to the correspondence assessment factor of different product type, such as
The assessment factor of regular class finance product is income, and corresponding comments can be " income is high, it is proposed that purchase " etc..Server
Risk evaluation result and comments are pushed into terminal, judge whether to be suitble to purchase for carrying out convenient for auxiliary.
It should be understood that although each step in the flow chart of Fig. 2-6 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-6
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in fig. 7, providing a kind of product risks assessment device, comprising:
Product determining module 200 to be assessed, the product for being carried according to risk assessment request select information, determine to be evaluated
The yield by estimation product;
It retrieves regular expression and obtains module 300, for obtaining the corresponding retrieval regular expression of product to be assessed;
Target text data extraction module 400, for retrieving the association net of product to be assessed according to retrieval regular expression
Page, and extract target text data relevant to product to be assessed in associating web pages;
Risk evaluation module 500 obtains to be assessed for target text data to be inputted pre-set product risk evaluation model
The risk evaluation result of product.
In one embodiment, product risks assessment device further includes retrieval regular expression building module, is used for basis
Preset product issues data, determines that publication has multiple associating web pages of product to be assessed, associating web pages are for showing in real time more
The assessment data of new product to be assessed, obtain the preset keyword of product to be assessed, and obtain the correspondence domain name of associating web pages;
According to preset keyword and domain name, the corresponding retrieval regular expression of product to be assessed is constructed.
It in one embodiment, include the real-time assessment data of product to be assessed in associating web pages;Target text data mention
Modulus block 400 is also used to the associating web pages of product to be assessed be retrieved, according to inspection according to the domain-name information in retrieval regular expression
The preset keyword carried in rope regular expression extracts real-time assessment data corresponding with product to be assessed in associating web pages,
Each real-time assessment data are subjected to clustering processing, obtain multiple target text data acquisition systems for carrying cluster labels, target text
It include target text data in notebook data set.
In one embodiment, risk evaluation module 500 are also used to obtain each target in each target text data acquisition system
Vector is inputted pre-set product risk evaluation model, it is corresponding to obtain target text data acquisition system by the corresponding vector of text data
Assessment tag, the cluster mark carried according to the corresponding assessment tag of each target text data acquisition system and target text data acquisition system
Label, obtain the risk evaluation result of product to be assessed.
In one embodiment, product risks assessment device further includes model training module, for obtaining sample product
Product evaluation data are carried out clustering processing by Product evaluation data, are carried out clustering processing to Product evaluation data, are taken according to sample
The product category of band identifies, and Product evaluation data clusters processing result is corresponding to product category mark by cluster dimensions updating
Default sample database obtains the incidence relation of default sample database and initial product risk evaluation model, is closed according to association
System, obtains the corresponding Product evaluation data of each initial product risk evaluation model, according to Product evaluation data, to initial product wind
Dangerous assessment models are trained, and obtain pre-set product risk evaluation model.
In one embodiment, model training module is also used to extract the Product evaluation of cluster dimension according to cluster dimension
The proprietary word in the field of data and emotional characteristics word, according to passing judgement on for the feature part of speech of the proprietary word in preset field and emotional characteristics word
Part of speech and the proprietary word in field and emotional characteristics word extracted are sorted out Product evaluation data in cluster dimension, to product
It assesses data and carries out vector conversion process, and according to the corresponding categorization results of Product evaluation data, determine Product evaluation data pair
The assessment tag for answering vector will cluster the vector for carrying assessment tag in dimension, input in initial product risk evaluation model
Evaluation module corresponding with cluster dimension, sub-module are trained initial product risk evaluation model, obtain pre-set product wind
Dangerous assessment models.
In one embodiment, risk evaluation module 500 are also used to obtain the product type mark that product to be assessed carries
Know, the product category of product to be assessed is determined, and obtain pre-set product risk evaluation model corresponding with product category, by target
Text data inputs pre-set product risk evaluation model, obtains the risk evaluation result of product to be assessed.
The said goods risk assessment device selects information by the product that risk assessment request carries, determines the yield by estimation to be evaluated
Product, and the corresponding retrieval regular expression of product to be assessed is obtained, it may be implemented to carry out the associating web pages of product to be assessed real
When retrieve, the relevant target text data of current existing product to be assessed are got, to utilize pre-set product risk assessment
The file destination data obtained in real time are carried out the risk assessment of product to be assessed by model, and the risk for obtaining product to be assessed is commented
Estimate as a result, solving the problems, such as the target text data about product to be assessed that can not obtain update in real time, to production to be assessed
The acquisition of the target text data of product promptly and accurately, to improve the Risk Assessment Quality to product to be assessed.
Specific about product risks assessment device limits the limit that may refer to above for product risks appraisal procedure
Fixed, details are not described herein.Modules in the said goods risk assessment device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 8.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of product risks appraisal procedure.The display screen of the computer equipment can be liquid crystal display or electric ink is shown
Screen, the input unit of the computer equipment can be the touch layer covered on display screen, be also possible on computer equipment shell
Key, trace ball or the Trackpad of setting can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 8, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of when executing computer program
Information is selected according to the product that risk assessment request carries, determines product to be assessed;
Obtain the corresponding retrieval regular expression of product to be assessed;
According to retrieval regular expression, retrieve the associating web pages of product to be assessed, and extract in associating web pages with it is to be assessed
The relevant target text data of product;
Target text data are inputted into pre-set product risk evaluation model, obtain the risk evaluation result of product to be assessed.
In one embodiment, it is also performed the steps of when processor executes computer program
Data are issued according to preset product, determine that publication there are multiple associating web pages of product to be assessed, associating web pages are used
In the assessment data for the product to be assessed for showing real-time update;
The preset keyword of product to be assessed is obtained, and obtains the correspondence domain name of associating web pages;According to preset keyword and
Domain name constructs the corresponding retrieval regular expression of product to be assessed.
It in one embodiment, include the real-time assessment data of product to be assessed in associating web pages;Processor executes calculating
It is also performed the steps of when machine program
According to the domain-name information in retrieval regular expression, the associating web pages of product to be assessed are retrieved;
According to the preset keyword carried in retrieval regular expression, extract corresponding with product to be assessed in associating web pages
Assessment data in real time;
Each real-time assessment data are subjected to clustering processing, obtain multiple target text data sets for carrying cluster labels
It closes, includes target text data in target text data acquisition system.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain the corresponding vector of each target text data in each target text data acquisition system;
Vector is inputted into pre-set product risk evaluation model, obtains the corresponding assessment tag of target text data acquisition system;
The cluster mark carried according to the corresponding assessment tag of each target text data acquisition system and target text data acquisition system
Label, obtain the risk evaluation result of product to be assessed.
In one embodiment, it is also performed the steps of when processor executes computer program
The Product evaluation data for obtaining sample product carry out clustering processing to Product evaluation data, to Product evaluation data
Carry out clustering processing;
The product category mark carried according to sample, extremely by cluster dimensions updating by Product evaluation data clusters processing result
Product category identifies corresponding default sample database;
The incidence relation for obtaining default sample database and initial product risk evaluation model is obtained according to incidence relation
The corresponding Product evaluation data of each initial product risk evaluation model;
According to Product evaluation data, initial product risk evaluation model is trained, obtains pre-set product risk assessment
Model.
In one embodiment, it is also performed the steps of when processor executes computer program
According to cluster dimension, the proprietary word in field and emotional characteristics word of the Product evaluation data of cluster dimension are extracted;
It is special according to the feature part of speech of the proprietary word in preset field and the field of emotional characteristics word passing judgement on part of speech and extracting
There are word and emotional characteristics word, Product evaluation data in cluster dimension are sorted out;
Vector conversion process is carried out to Product evaluation data, and according to the corresponding categorization results of Product evaluation data, is determined
Product evaluation data correspond to the assessment tag of vector;
To cluster and carry the vector of assessment tag in dimension, input in initial product risk evaluation model with cluster dimension
Corresponding evaluation module, sub-module are trained initial product risk evaluation model, obtain pre-set product risk evaluation model.
In one embodiment, it is also performed the steps of when processor executes computer program
The product type mark that product to be assessed carries is obtained, determines the product category of product to be assessed, and obtain and produce
The not corresponding pre-set product risk evaluation model of category;
Target text data are inputted into pre-set product risk evaluation model, obtain the risk evaluation result of product to be assessed.
The above-mentioned computer equipment for realizing product risks appraisal procedure is selected by the product that risk assessment request carries
Information is selected, determines product to be assessed, and obtains the corresponding retrieval regular expression of product to be assessed, may be implemented to production to be assessed
The associating web pages of product carry out real-time retrieval, the relevant target text data of currently existing product to be assessed are got, thus sharp
With pre-set product risk evaluation model, the file destination data obtained in real time are carried out with the risk assessment of product to be assessed, is obtained
The risk evaluation result of product to be assessed solves the target text data about product to be assessed that can not obtain update in real time
The problem of, promptly and accurately to the acquisitions of the target text data of product to be assessed, to improve the risk to product to be assessed
Quality of evaluation.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Information is selected according to the product that risk assessment request carries, determines product to be assessed;
Obtain the corresponding retrieval regular expression of product to be assessed;
According to retrieval regular expression, retrieve the associating web pages of product to be assessed, and extract in associating web pages with it is to be assessed
The relevant target text data of product;
Target text data are inputted into pre-set product risk evaluation model, obtain the risk evaluation result of product to be assessed.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Data are issued according to preset product, determine that publication there are multiple associating web pages of product to be assessed, associating web pages are used
In the assessment data for the product to be assessed for showing real-time update;
The preset keyword of product to be assessed is obtained, and obtains the correspondence domain name of associating web pages;According to preset keyword and
Domain name constructs the corresponding retrieval regular expression of product to be assessed.
It in one embodiment, include the real-time assessment data of product to be assessed in associating web pages;Computer program is located
Reason device also performs the steps of when executing
According to the domain-name information in retrieval regular expression, the associating web pages of product to be assessed are retrieved;
According to the preset keyword carried in retrieval regular expression, extract corresponding with product to be assessed in associating web pages
Assessment data in real time;
Each real-time assessment data are subjected to clustering processing, obtain multiple target text data sets for carrying cluster labels
It closes, includes target text data in target text data acquisition system.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Obtain the corresponding vector of each target text data in each target text data acquisition system;
Vector is inputted into pre-set product risk evaluation model, obtains the corresponding assessment tag of target text data acquisition system;
The cluster mark carried according to the corresponding assessment tag of each target text data acquisition system and target text data acquisition system
Label, obtain the risk evaluation result of product to be assessed.
In one embodiment, it is also performed the steps of when computer program is executed by processor
The Product evaluation data for obtaining sample product carry out clustering processing to Product evaluation data, to Product evaluation data
Carry out clustering processing;
The product category mark carried according to sample, extremely by cluster dimensions updating by Product evaluation data clusters processing result
Product category identifies corresponding default sample database;
The incidence relation for obtaining default sample database and initial product risk evaluation model is obtained according to incidence relation
The corresponding Product evaluation data of each initial product risk evaluation model;
According to Product evaluation data, initial product risk evaluation model is trained, obtains pre-set product risk assessment
Model.
In one embodiment, it is also performed the steps of when computer program is executed by processor
According to cluster dimension, the proprietary word in field and emotional characteristics word of the Product evaluation data of cluster dimension are extracted;
It is special according to the feature part of speech of the proprietary word in preset field and the field of emotional characteristics word passing judgement on part of speech and extracting
There are word and emotional characteristics word, Product evaluation data in cluster dimension are sorted out;
Vector conversion process is carried out to Product evaluation data, and according to the corresponding categorization results of Product evaluation data, is determined
Product evaluation data correspond to the assessment tag of vector;
To cluster and carry the vector of assessment tag in dimension, input in initial product risk evaluation model with cluster dimension
Corresponding evaluation module, sub-module are trained initial product risk evaluation model, obtain pre-set product risk evaluation model.
In one embodiment, it is also performed the steps of when computer program is executed by processor
The product type mark that product to be assessed carries is obtained, determines the product category of product to be assessed, and obtain and produce
The not corresponding pre-set product risk evaluation model of category;
Target text data are inputted into pre-set product risk evaluation model, obtain the risk evaluation result of product to be assessed.
It is above-mentioned for realizing product risks appraisal procedure and computer readable storage medium, by risk assessment request take
The product of band selects information, determines product to be assessed, and obtain the corresponding retrieval regular expression of product to be assessed, may be implemented
Real-time retrieval is carried out to the associating web pages of product to be assessed, gets the relevant target text number of currently existing product to be assessed
According to so that the file destination data obtained in real time are carried out with the risk of product to be assessed using pre-set product risk evaluation model
Assessment, obtains the risk evaluation result of product to be assessed, solves the mesh about product to be assessed that can not obtain update in real time
The problem of marking text data, promptly and accurately to the acquisitions of the target text data of product to be assessed, to improve to be assessed
The Risk Assessment Quality of product.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Instruct relevant hardware to complete by computer program, computer program to can be stored in a non-volatile computer readable
It takes in storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, this Shen
Please provided by any reference used in each embodiment to memory, storage, database or other media, may each comprise
Non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
Above embodiments only express the several embodiments of the application, and the description thereof is more specific and detailed, but can not
Therefore it is construed as limiting the scope of the patent.It should be pointed out that for those of ordinary skill in the art,
Under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection scope of the application.
Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of product risks appraisal procedure, which comprises
Information is selected according to the product that risk assessment request carries, determines product to be assessed;
Obtain the corresponding retrieval regular expression of the product to be assessed;
According to the retrieval regular expression, the associating web pages of the product to be assessed are retrieved, and are extracted in the associating web pages
Target text data relevant to the product to be assessed;
The target text data are inputted into pre-set product risk evaluation model, obtain the risk assessment knot of the product to be assessed
Fruit.
2. the method according to claim 1, wherein described obtain the corresponding retrieval canonical of the product to be assessed
Before expression formula, further includes:
Data are issued according to preset product, determine that publication has multiple associating web pages of the product to be assessed, the association net
The assessment data of the to be assessed product of the page for showing real-time update;
The preset keyword of the product to be assessed is obtained, and obtains the correspondence domain name of the associating web pages;
According to the preset keyword and domain name, the corresponding retrieval regular expression of the product to be assessed is constructed.
3. method according to claim 1 or 2, which is characterized in that include the product to be assessed in the associating web pages
Real-time assessment data;It is described that the associating web pages of the product to be assessed are retrieved according to the retrieval regular expression, and extract
Target text data relevant to the product to be assessed include: in the associating web pages
According to the domain-name information in the retrieval regular expression, the associating web pages of the product to be assessed are retrieved;
According to the preset keyword that carries in the retrieval regular expression, extract in the associating web pages with described the yield by estimation to be evaluated
The corresponding real-time assessment data of product;
Each real-time assessment data are subjected to clustering processing, obtain multiple target text data sets for carrying cluster labels
It closes, includes the target text data in the target text data acquisition system.
4. according to the method described in claim 3, it is characterized in that, described input pre-set product wind for the target text data
Dangerous assessment models, the risk evaluation result for obtaining the product to be assessed include:
Obtain the corresponding vector of each target text data in each target text data acquisition system;
The vector is inputted into pre-set product risk evaluation model, obtains the corresponding assessment mark of the target text data acquisition system
Label;
It is carried according to each corresponding assessment tag of target text data acquisition system and the target text data acquisition system poly-
Class label obtains the risk evaluation result of the product to be assessed.
5. the method according to claim 1, wherein described input pre-set product wind for the target text data
Dangerous assessment models, before the risk evaluation result for obtaining the product to be assessed, further includes:
The Product evaluation data for obtaining sample product carry out clustering processing to the Product evaluation data;
The product category mark carried according to the sample, more by cluster dimension by the Product evaluation data clusters processing result
The new extremely product category identifies corresponding default sample database;
The incidence relation for obtaining the default sample database and initial product risk evaluation model, according to the incidence relation,
Obtain the corresponding Product evaluation data of each initial product risk evaluation model;
According to the Product evaluation data, the initial product risk evaluation model is trained, the pre-set product is obtained
Risk evaluation model.
6. according to the method described in claim 5, it is characterized in that, described according to the Product evaluation data, to described initial
Product risks assessment models are trained, and are obtained the pre-set product risk evaluation model and are included:
According to the cluster dimension, the proprietary word in field and emotional characteristics word of the Product evaluation data of the cluster dimension are extracted;
It is special according to the feature part of speech of the proprietary word in preset field and the field of emotional characteristics word passing judgement on part of speech and extracting
There are word and the emotional characteristics word, Product evaluation data described in the cluster dimension are sorted out;
Vector conversion process is carried out to the Product evaluation data, and according to the corresponding categorization results of the Product evaluation data,
Determine that the Product evaluation data correspond to the assessment tag of vector;
The vector of the assessment tag will be carried in the cluster dimension, input in initial product risk evaluation model with it is described
The corresponding evaluation module of dimension is clustered, sub-module is trained the initial product risk evaluation model, obtains described default
Product risks assessment models.
7. according to the method described in claim 5, it is characterized in that, target text data input pre-set product risk is commented
Estimate model, the risk evaluation result for obtaining the product to be assessed includes:
The product type mark that the product to be assessed carries is obtained, determines the product category of the product to be assessed, and obtain
Pre-set product risk evaluation model corresponding with the product category;
The target text data are inputted into the pre-set product risk evaluation model, the risk for obtaining the product to be assessed is commented
Estimate result.
8. a kind of product risks assess device, which is characterized in that described device includes:
Product determining module to be assessed, the product for being carried according to risk assessment request select information, determine product to be assessed;
It retrieves regular expression and obtains module, for obtaining the corresponding retrieval regular expression of the product to be assessed;
Target text data extraction module, for retrieving the association of the product to be assessed according to the retrieval regular expression
Webpage, and extract target text data relevant to the product to be assessed in the associating web pages;
Risk evaluation module obtains described to be evaluated for the target text data to be inputted pre-set product risk evaluation model
The risk evaluation result of the yield by estimation product.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910296125.6A CN110135694A (en) | 2019-04-12 | 2019-04-12 | Product risks appraisal procedure, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910296125.6A CN110135694A (en) | 2019-04-12 | 2019-04-12 | Product risks appraisal procedure, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110135694A true CN110135694A (en) | 2019-08-16 |
Family
ID=67569798
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910296125.6A Pending CN110135694A (en) | 2019-04-12 | 2019-04-12 | Product risks appraisal procedure, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110135694A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111125071A (en) * | 2019-11-25 | 2020-05-08 | 珠海格力电器股份有限公司 | Method and device for evaluating real-time data reliability and storage medium |
CN111404721A (en) * | 2020-02-13 | 2020-07-10 | 中国平安人寿保险股份有限公司 | Web-based model training process data visualization processing method, device and equipment |
CN113435759A (en) * | 2021-07-01 | 2021-09-24 | 贵州电网有限责任公司 | Primary equipment risk intelligent evaluation method based on deep learning |
CN113849760A (en) * | 2021-12-02 | 2021-12-28 | 云账户技术(天津)有限公司 | Sensitive information risk assessment method, system and storage medium |
CN116167623A (en) * | 2023-04-21 | 2023-05-26 | 武汉墨仗信息科技股份有限公司 | Electronic purchasing management and control method and system based on Internet |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105844424A (en) * | 2016-05-30 | 2016-08-10 | 中国计量学院 | Product quality problem discovery and risk assessment method based on network comments |
WO2017133456A1 (en) * | 2016-02-01 | 2017-08-10 | 腾讯科技(深圳)有限公司 | Method and device for determining risk evaluation parameter |
CN108711004A (en) * | 2018-05-14 | 2018-10-26 | 北京京东金融科技控股有限公司 | Methods of risk assessment and device and computer readable storage medium |
CN108805444A (en) * | 2018-06-07 | 2018-11-13 | 北京字节跳动网络技术有限公司 | Appraisal procedure, device, equipment and computer readable storage medium |
CN109242352A (en) * | 2018-10-19 | 2019-01-18 | 中国银行股份有限公司 | A kind of financial risks appraisal procedure and device |
CN109345374A (en) * | 2018-09-17 | 2019-02-15 | 平安科技(深圳)有限公司 | Risk control method, device, computer equipment and storage medium |
CN109360105A (en) * | 2018-09-18 | 2019-02-19 | 平安科技(深圳)有限公司 | Product risks method for early warning, device, computer equipment and storage medium |
WO2019061976A1 (en) * | 2017-09-28 | 2019-04-04 | 平安科技(深圳)有限公司 | Fund product recommendation method and apparatus, terminal device, and storage medium |
-
2019
- 2019-04-12 CN CN201910296125.6A patent/CN110135694A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017133456A1 (en) * | 2016-02-01 | 2017-08-10 | 腾讯科技(深圳)有限公司 | Method and device for determining risk evaluation parameter |
CN105844424A (en) * | 2016-05-30 | 2016-08-10 | 中国计量学院 | Product quality problem discovery and risk assessment method based on network comments |
WO2019061976A1 (en) * | 2017-09-28 | 2019-04-04 | 平安科技(深圳)有限公司 | Fund product recommendation method and apparatus, terminal device, and storage medium |
CN108711004A (en) * | 2018-05-14 | 2018-10-26 | 北京京东金融科技控股有限公司 | Methods of risk assessment and device and computer readable storage medium |
CN108805444A (en) * | 2018-06-07 | 2018-11-13 | 北京字节跳动网络技术有限公司 | Appraisal procedure, device, equipment and computer readable storage medium |
CN109345374A (en) * | 2018-09-17 | 2019-02-15 | 平安科技(深圳)有限公司 | Risk control method, device, computer equipment and storage medium |
CN109360105A (en) * | 2018-09-18 | 2019-02-19 | 平安科技(深圳)有限公司 | Product risks method for early warning, device, computer equipment and storage medium |
CN109242352A (en) * | 2018-10-19 | 2019-01-18 | 中国银行股份有限公司 | A kind of financial risks appraisal procedure and device |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111125071A (en) * | 2019-11-25 | 2020-05-08 | 珠海格力电器股份有限公司 | Method and device for evaluating real-time data reliability and storage medium |
CN111404721A (en) * | 2020-02-13 | 2020-07-10 | 中国平安人寿保险股份有限公司 | Web-based model training process data visualization processing method, device and equipment |
CN111404721B (en) * | 2020-02-13 | 2023-07-25 | 中国平安人寿保险股份有限公司 | Visual processing method, device and equipment for model training process data based on web |
CN113435759A (en) * | 2021-07-01 | 2021-09-24 | 贵州电网有限责任公司 | Primary equipment risk intelligent evaluation method based on deep learning |
CN113435759B (en) * | 2021-07-01 | 2023-07-04 | 贵州电网有限责任公司 | Primary equipment risk intelligent assessment method based on deep learning |
CN113849760A (en) * | 2021-12-02 | 2021-12-28 | 云账户技术(天津)有限公司 | Sensitive information risk assessment method, system and storage medium |
CN113849760B (en) * | 2021-12-02 | 2022-07-22 | 云账户技术(天津)有限公司 | Sensitive information risk assessment method, system and storage medium |
CN116167623A (en) * | 2023-04-21 | 2023-05-26 | 武汉墨仗信息科技股份有限公司 | Electronic purchasing management and control method and system based on Internet |
CN116167623B (en) * | 2023-04-21 | 2023-08-01 | 武汉墨仗信息科技股份有限公司 | Electronic purchasing management and control method and system based on Internet |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110135694A (en) | Product risks appraisal procedure, device, computer equipment and storage medium | |
CN111767741B (en) | Text emotion analysis method based on deep learning and TFIDF algorithm | |
CN110444198B (en) | Retrieval method, retrieval device, computer equipment and storage medium | |
Bauer et al. | Quantitive evaluation of Web site content and structure | |
CN110489520A (en) | Event-handling method, device, equipment and the storage medium of knowledge based map | |
CN109829629B (en) | Risk analysis report generation method, apparatus, computer device and storage medium | |
CN109767318A (en) | Loan product recommended method, device, equipment and storage medium | |
CN109740152B (en) | Text category determination method and device, storage medium and computer equipment | |
CN108874992A (en) | The analysis of public opinion method, system, computer equipment and storage medium | |
CN109493199A (en) | Products Show method, apparatus, computer equipment and storage medium | |
CN110569500A (en) | Text semantic recognition method and device, computer equipment and storage medium | |
CN108376131A (en) | Keyword abstraction method based on seq2seq deep neural network models | |
CN108388660B (en) | Improved E-commerce product pain point analysis method | |
CN109360105A (en) | Product risks method for early warning, device, computer equipment and storage medium | |
CN108170859A (en) | Method, apparatus, storage medium and the terminal device of speech polling | |
CN109815333A (en) | Information acquisition method, device, computer equipment and storage medium | |
CN109858010A (en) | Field new word identification method, device, computer equipment and storage medium | |
CN109299094A (en) | Tables of data processing method, device, computer equipment and storage medium | |
CN109271627A (en) | Text analyzing method, apparatus, computer equipment and storage medium | |
CN114971730A (en) | Method for extracting file material, device, equipment, medium and product thereof | |
CN111462752A (en) | Client intention identification method based on attention mechanism, feature embedding and BI-L STM | |
CN109033427A (en) | The screening technique and device of stock, computer equipment and readable storage medium storing program for executing | |
CN115357699A (en) | Text extraction method, device, equipment and storage medium | |
CN110532229A (en) | Instrument of evidence search method, device, computer equipment and storage medium | |
CN112380346B (en) | Financial news emotion analysis method and device, computer equipment and 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 |