CN110097250A - Product risks prediction technique, device, computer equipment and storage medium - Google Patents
Product risks prediction technique, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110097250A CN110097250A CN201910212867.6A CN201910212867A CN110097250A CN 110097250 A CN110097250 A CN 110097250A CN 201910212867 A CN201910212867 A CN 201910212867A CN 110097250 A CN110097250 A CN 110097250A
- Authority
- CN
- China
- Prior art keywords
- product
- label
- supervision
- information
- public sentiment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 230000005540 biological transmission Effects 0.000 claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 27
- 230000008451 emotion Effects 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 abstract 1
- 239000000047 product Substances 0.000 description 181
- 230000008569 process Effects 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 239000006227 byproduct Substances 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 238000011217 control strategy Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves big data analysis, in particular to a kind of product risks prediction technique, device, computer equipment and storage medium.The described method includes: receiving the supervision information of supervision server transmission, judge that supervising information indicates whether supervision tightening；When supervising information indicates supervision tightening, current public feelings information is obtained；Public sentiment label is extracted from public feelings information；Public sentiment label is matched with pre-generated product portrait label；When matching there are product portrait label and public sentiment label, then exporting product corresponding with the product of successful match portrait label, there are risks.Using this method can forecasting risk product, improve product risks control efficiency.
Description
Technical field
This application involves technical field of data processing, more particularly to a kind of product risks prediction technique, device, computer
Equipment and storage medium.
Background technique
With China's rapid development of economy, the product for more and more meeting people's various aspects demand has appeared in society
On, but the listing of product, also along with risk while bringing profit for company, in this interests with risk and the back deposited
Under scape, the risk management of product is just particularly important.
It however, at present to the risk management of product, is researched and developed again for the specific products pair after research and development of products
The risk management and control strategy answered, hence for there are the company of typical products in mass production, research staff need for each product into
The research and development of row risk management and control strategy, inefficiency.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of product risks prediction technique that can be improved efficiency,
Device, computer equipment and storage medium.
A kind of product risks prediction technique, which comprises
The supervision information for receiving supervision server transmission judges that the supervision information indicates whether supervision tightening；
When the supervision information indicates supervision tightening, current public feelings information is obtained；
Public sentiment label is extracted from the public feelings information；
The public sentiment label is matched with pre-generated product portrait label；
When matching there are product portrait label and the public sentiment label, then exports and drawn with the product of successful match
As there are risks for the corresponding product of label.
The generating mode of the product portrait label in one of the embodiments, comprising:
Receive the product attribute index of input；
From preset because choosing the factor corresponding with the ATTRIBUTE INDEX in subsystem；
The product portrait label is established according to the selected factor.
It is described in one of the embodiments, to carry out matching it with pre-generated product portrait label by public sentiment label
Afterwards, further includes:
When matching there is no product portrait label and the public sentiment label, then by the public sentiment label to described pre-
If be updated because of subsystem.
It is described in one of the embodiments, that public sentiment label is extracted from the public feelings information, comprising:
The public feelings information is segmented, and calculates the corresponding word frequency of each participle and emotion score；
Obtain second point that the word frequency is greater than default emotion score greater than the first participle and emotion score of predeterminated frequency
Word；
It regard the first participle and second participle as public sentiment label.
Output product corresponding with the product of successful match portrait label exists in one of the embodiments,
After risk, further includes:
The corresponding subsidiary's server of the product is inquired, and the information of the product and the supervision information are sent
To subsidiary's server.
The judgement supervision information indicates whether supervision tightening in one of the embodiments, comprising:
Corresponding first parameter in the supervision information is obtained by the macro-performance indicator pre-established；
Macroscopical scene early warning index and scene downlink probability are calculated according to first parameter；
The supervision information according to macroscopical scene early warning index and the scene downlink probabilistic determination indicates whether
Supervision tightening；
When macroscopical scene early warning index and the scene downlink probability wherein at least one are greater than preset value, then
The supervision information indicates supervision tightening；
When macroscopical scene early warning index and the scene downlink probability are respectively less than preset value, then the supervision is believed
Breath indicates that supervision is not tightened.
It is described in one of the embodiments, to exist in output product corresponding with the portrait label of product described in successful match
After risk, further includes:
The product portrait label and the corresponding processing scheme of product portrait label of successful match are obtained, and defeated
The processing scheme out；
Receive the parameter adjustment instruction corresponding with the processing scheme of input；
The second parameter in the processing scheme is adjusted according to the parameter adjustment instruction.
A kind of product risks prediction meanss, described device include:
Judgment module, for whether judging the supervision information when receiving the supervision information of supervision server transmission
Indicate supervision tightening；
Module is obtained, for obtaining current public feelings information when the supervision information indicates supervision tightening；
Extraction module, for extracting public sentiment label from the public feelings information；
Matching module, for matching the public sentiment label with pre-generated product portrait label；
Output module, for exporting and the production when matching there are product portrait label and the public sentiment label
Product are drawn a portrait, and there are risks for the corresponding product of label.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes the above method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of above method is realized when row.
The said goods Risk Forecast Method, device, computer equipment and storage medium are sent receiving supervision server
Supervision information when, judge supervise information indicate whether supervision tightening, if supervision information indicate supervision tightening, illustrate there is product
There are risks, then obtain the public feelings information under current supervision tightening state, public sentiment label is extracted from the public feelings information got,
Public sentiment label is matched with pre-generated product portrait label, is matched when there are product portrait labels with public sentiment label
When, explanation is that there are risks for product, then exporting the product, there are risks, improves the efficiency of product risks control.
Detailed description of the invention
Fig. 1 is the application scenario diagram of product risks prediction technique in one embodiment；
Fig. 2 is the flow diagram of product risks prediction technique in one embodiment；
Fig. 3 is the flow diagram of the generation step of product portrait label in one embodiment；
Fig. 4 is the structural block diagram of product risks prediction meanss in one embodiment；
Fig. 5 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 prediction technique provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated by network with supervision server 104.Terminal 102 can receive the supervision of the transmission of supervision server 104
Information judges that supervising information indicates whether supervision tightening, when supervising information indicates supervision tightening, obtains current public feelings information,
Terminal 102 extracts public sentiment label from public feelings information, and public sentiment label is matched with pre-generated product portrait label,
When matching there are product portrait label and public sentiment label, then product corresponding with the product of successful match portrait label is exported
It there are risk, does not need to be researched and developed for each product, but label is drawn a portrait by product to determine whether product is deposited
It is high-efficient in risk.Wherein, it is various personal computers that terminal 102, which can be, but not limited to, laptop, smart phone, is put down
Plate computer and portable wearable device, supervision server 104 can be formed with the either multiple servers of independent server
Server cluster realize.
In one embodiment, as shown in Fig. 2, providing a kind of product risks prediction technique, it is applied to Fig. 1 in this way
In terminal 102 for be illustrated, comprising the following steps:
Step 202, the supervision information that supervision server is sent is received, judges that supervising information indicates whether supervision tightening.
Specifically, terminal is sent after the supervision information for receiving supervision server transmission according to supervision server
Supervision information judgement supervision information indicates whether supervision tightening phenomenon currently occur.Wherein, supervision information can be Securities Regulatory Bureau, religion
The policy information of Yu Budeng government bodies.Optionally, terminal receives the supervision information that supervision server is sent, and can be and sets in advance
Setting period periodically receives, and is also possible to the reception when data fluctuations occurs in market surpervision information, is also possible to above-mentioned two time
Section all receives, and the present embodiment is not limited.
Step 204, when supervising information indicates supervision tightening, current public feelings information is obtained.
Specifically, when terminal determines that supervision information indicates supervision tightening, current public feelings information is obtained, public feelings information obtains
Information can be obtained in the various flow webpages of internet, microblogging by the supervision server of carry out public sentiment monitoring by taking, and calculate letter
Frequency is ceased, gets information of the frequency greater than predeterminated frequency as current public feelings information.In addition, supervision server can also be direct
Go out to directly acquire information frequency in public feelings information net, internet big data monitoring platform, and information frequency is greater than predeterminated frequency
Information as current public feelings information, the present embodiment is not limited.
Step 206, public sentiment label is extracted from public feelings information.
Specifically, after terminal gets public feelings information, public feelings information is analyzed and processed, is extracted and public feelings information phase
Corresponding public sentiment label.Acquisition public sentiment data is analyzed and processed to public feelings information, can be a large amount of public feelings informations of upload
Integration, classification and calculating process, such as after public feelings information is integrated, by public feelings information according to information frequency size,
The modes such as the type of information are classified, then the information frequency in calculating public feelings information, the change rate of information frequency, newly-increased letter
The substantially situation of public sentiment can be obtained in the public sentiment data of acquisition and default value comparison by the information category of breath and frequency etc., than
Such as, the public sentiments situation such as high, amount is low, the minimum refund of mode of repayment 5% that there is currently interest rates.Public sentiment mark corresponding with public sentiment situation
Label rough can show that current public sentiment, such as interest rate height, the objective group of granting, fund amount, payment for goods purposes, application channel etc. are worked as
The essential information of preceding public sentiment.
Step 208, public sentiment label is matched with pre-generated product portrait label.
Specifically, it after terminal extracts public sentiment label, is matched with the portrait label of pre-generated product.Wherein
The process matched can determine the feature tag of successful match by the way of fuzzy matching, and if a product or project institute
The number for having the successful match of label and this feature label is more than the default accounting of all labels, then just thinks that the product is drawn a portrait
Tag match success.For example, such as current public sentiment label includes, interest rate is high, amount is low, the minimum refund of mode of repayment 5%
Deng more than ten, there are more than 70 to include above-mentioned more than ten public sentiment labels, but only one product in the product of certain company or project
Portrait label include wherein the 80% of more than ten public sentiment labels, then public sentiment label is drawn a portrait with the product and is matched.
In addition, product portrait label can be in specific server pre-generate, need in terminal by public sentiment mark
When label are matched with product portrait label, then those pre-generated product portrait labels can be read from server.
Step 210, when matching there are product portrait label and public sentiment label, output and the product of successful match are drawn a portrait
There are risks for the corresponding product of label.
Specifically, when the public sentiment label of terminal and product portrait tag match success, terminal is obtained to be marked with product portrait
Signing the information of corresponding product and output products, there are risks.Product information can only include the title of product, also may include
The information such as title, size, quantity, rate per month, the amount of product, the present embodiment are not limited.
In the said goods Risk Forecast Method, terminal judges to supervise when receiving the supervision information of supervision server transmission
Pipe information indicates whether supervision tightening, then determines that supervision information indicates supervision tightening, illustrates then to obtain with the presence of product risk
Public feelings information under current supervision tightening state, extracts public sentiment label from the public feelings information got, by public sentiment label and in advance
The product portrait label first generated is matched, and when matching there are product portrait label and public sentiment label, explanation is product
There are risks, then export the product there are risk, the rapid positioning of product when realizing supervision tightening, avoid and repeatedly research and develop
Step also saves risk management resource while improving Efficiency of Risk Management.
In one embodiment, as shown in figure 3, the generating mode of product portrait label, may comprise steps of:
Step 302, the product attribute index of input is received.
Specifically, in the presence of having newly-increased product, terminal receives the ATTRIBUTE INDEX of newly-increased product.The ATTRIBUTE INDEX of product
The expression product attribute that can summarize, for example, the institute of newly-increased product can be obtained simultaneously when certain company has newly-increased product
Region (one line/two wires/tri- lines), place industry (finance/manufacture/service/...), amount (20%/40%/60%/
80%/...) etc. indicate that the index of product attribute, above-mentioned ATTRIBUTE INDEX are used to establish product portrait label of the newly-increased product.
Step 304, from preset because choosing the factor corresponding with ATTRIBUTE INDEX in subsystem.
Specifically, after terminal receives the ATTRIBUTE INDEX of newly-increased product, from pre-set product because chosen in subsystem with
The corresponding factor of ATTRIBUTE INDEX of newly-increased product, for example, when the interest rate level of the ATTRIBUTE INDEX of product is 3%, it is right
The factor answered can be low interest rates, and when the amount of the ATTRIBUTE INDEX of product is 60%, the corresponding factor can be amount
It is high.Optionally, when the ATTRIBUTE INDEX of newly-increased product is in the absence of pre-set product is because in subsystem simultaneously, by newly-increased product
ATTRIBUTE INDEX be converted into the corresponding factor, and be updated to because of subsystem.Optionally, because subsystem can be according to product kind
Class selection is corresponding because of subsystem, for example product is retail product, because subsystem may be selected by retail trade system risks and assumptions body
System.
Step 306, product portrait label is established according to the selected factor.
Specifically, after terminal chooses the factor, according to the factor of selection by combinations of factors, the product portrait of the product is established
Label.
In the said goods Risk Forecast Method, product portrait label is established by the ATTRIBUTE INDEX of product, it is ensured that product
The relevance drawn a portrait between label and product.And also can timely to establish product portrait label because of the timely root of subsystem
Update adjustment is made according to public sentiment, ensure that the novelty of data, while also improving the success rate of matching process.
In one embodiment, after public sentiment label being matched with pre-generated product portrait label, further includes:
When matching there is no product portrait label and public sentiment label, then pass through public sentiment label to preset because subsystem carries out more
Newly.
Specifically, when matching there is no product portrait label and public sentiment label, i.e., public sentiment label is in because of subsystem
The object factor can not be matched, illustrates not timely update because subsystem exists, because of the phenomenon that subcategory is out-of-date, then passes through public sentiment
Public sentiment label, because subsystem is updated, is converted into the factor, and be updated to because of subsystem to preset by label.
It is updated in time to because of subsystem in this way, increases the foundation of the product portrait label of product newly convenient for the later period, can also prevent
Only because data cannot timely update, caused by product portrait label the case where not being consistent with product actual conditions.
In one embodiment, terminal judges that the supervision information that supervision server is sent indicates whether supervision tightening, comprising:
Corresponding first parameter in supervision information is obtained by the macro-performance indicator pre-established；Macroscopic field is calculated according to the first parameter
Scape early warning index and scene downlink probability；It is according to macroscopical scene early warning index and scene downlink probabilistic determination supervision information
No expression supervision tightening；When macroscopical scene early warning index and scene downlink probability wherein at least one are greater than preset value, then
Supervising information indicates supervision tightening；When macroscopical scene early warning index and scene downlink probability are respectively less than preset value, then supervise
Information indicates that supervision is not tightened.
Specifically, terminal can pre-establish index and supervise the relationship of the parameter of information, and relationship can be such as: supervision letter
The relationship of the variation of interest rate and macro-performance indicator in breath, the relationship of the variation of amount and macro-performance indicator in supervision information,
The variation of duration and the relationship of macro-performance indicator etc. in information are supervised, these supervision information values is established and macroscopic view passes through
The relation table for index of helping.Secondly terminal calculates macroscopical scene early warning index according to these parameter values and relation table of supervision information
Whether macroeconomy and scene downlink probability supervise information according to macroscopical scene early warning index and scene downlink probabilistic determination
Indicate supervision tightening.Alternatively it is also possible to can judge the numerical value of supervision tightening by other parameters, such as journey is tightened in market
Degree, product sales degree etc., to determine whether there is supervision tightening, all numerical value that can judge supervision tightening is all in this reality
It applies in a protection scope, it is numerous to list herein.Terminal is sentenced after obtaining macroscopical scene early warning index and scene downlink probability
When disconnected current macroscopic scene early warning index and scene downlink probability wherein at least one are greater than preset value, then information expression is supervised
Supervision tightening；When macroscopical scene early warning index and scene downlink probability are respectively less than preset value, then supervising information indicates supervision
It does not tighten.
Multiple parameters acquisition is carried out to supervision information according to the economic indicator of macroscopic view, is then supervised by the parameter acquired
The judgement of pipe tightening can more fully judge that supervision tightening with the presence or absence of supervision tightening, improves the accuracy rate of judging result.
In one embodiment, public sentiment label is extracted from public feelings information, comprising: segment, and count to public feelings information
Calculate the corresponding word frequency of each participle and emotion score；The first participle and emotion score that word frequency is obtained greater than predeterminated frequency are greater than
Second participle of default emotion score；It regard the first participle and the second participle as public sentiment label.
Specifically, after terminal gets public feelings information, participle operation is carried out to public feelings information, wherein the calculating of word frequency
Mode may is that the word frequency and inverse document frequency that calculate each participle to word weight, obtain word weight and be greater than preset value
Word as public sentiment label.For example: terminal is collected into 1000 activity request sentences, and first statement amounts to 10 lists
Word, wherein single quotation marks has 3, and from also has 3.Having 10 sentences in 1000 sentences includes single quotation marks, and 100 include
From, word frequency and inverse document frequency calculate as follows:
Word frequency (TF)=(number that some word occurs in this public feelings information)/(total word number of this public feelings information)
Inverse document frequency (IDF)=log ((total number of this movable public feelings information)/it (include the word in this activity
Public feelings information item number+1))
Word weight (TF-IDF)=word frequency (TF) * inverse document frequency (IDF)
Table 1
| Public feelings information number comprising the word | TF | IDF | TF-IDF | |
| Single quotation marks | 10 | 0.3 | 1.958 | 0.5874 |
| From | 100 | 0.3 | 0.995 | 0.3318 |
Calculated result is as shown in table 1: the TF-IDF=0.3318 of the TF-IDF=0.5874 of single quotation marks, from, single quotation marks
TF-IDF be greater than from TF-IDF.
The calculating of emotion score, which can be, presets emotion score library, by the word in each word emotion score library into
Row matching, if successful match, gets corresponding score, so as to which the emotion score of each participle is calculated.
Public sentiment label is obtained by the word frequency and emotion score of public feelings information, can more accurately, comprehensively be believed from public sentiment
Public sentiment label is extracted in breath, prevents the case where public sentiment label is not inconsistent with current public sentiment.
In one embodiment, product corresponding with the product of successful match portrait label is exported there are after risk, is also wrapped
It includes: the corresponding subsidiary's server of inquiry product, and subsidiary's server is sent by the information of product and supervision information.
Specifically, in terminal output and product corresponding to the product of successful match portrait label there are after risk, in order to
Further inform that risk carrier solves risk product problem, terminal will also inquire the service of subsidiary corresponding to the product
Device, and subsidiary's server is sent by the information of risk product and supervision information.Optionally, terminal can also be by public opinion information
It is sent to subsidiary's server with public opinion label, is referred to for subsidiary risk carrier.
Subsidiary's server is sent by the information of risk product and supervision information, facilitates the subsidiary of risk exposure can
The fact that more timely know current production there are risks, to facilitate subsidiary that can adopt within the shorter time to risk
Take measure.
In one embodiment, it is gone back in output product corresponding with successful match product portrait label there are after risk
It include: to obtain the product portrait label and the corresponding processing scheme of product portrait label of successful match, and export processing scheme；
Receive the parameter adjustment instruction corresponding with processing scheme of input；According to parameter adjustment instruction to the second parameter in processing scheme
It is adjusted.
Specifically, in terminal output and product corresponding to the product of successful match portrait label there are after risk, in order to
Guarantee that risk product problem is resolved, terminal also obtains corresponding issue handling scheme and exports the program, issue handling side
Obtaining for case can be the risk indicator of acquisition current production risk, such as product interest rate is low, amount is excessively high, then detects wind
The risk class (in such as gently, weighing three grades) of dangerous index, according to the tentative programme that risk class, On The Choice solve, is being obtained
After taking tentative programme, the validity of tentative programme is calculated, and inquires the optimal risk indicator that the tentative programme can control, example
The optimal risk indicator that such as can control is to reduce amount, and then the risk indicator of the control according to required for current production risk,
Select permeability solution.
Corresponding issue handling scheme is obtained by risk product, the risk problem targetedly occurred for product, which provides, asks
Processing scheme is inscribed, being conducive to risk problem being capable of more being resolved more efficiently in time.
It should be understood that although each step in the flow chart of Fig. 2~3 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, in Fig. 2~3 at least
A part of step may include that perhaps these sub-steps of multiple stages or stage are not necessarily in same a period of time to multiple sub-steps
Quarter executes completion, but can execute at different times, the execution in these sub-steps or stage be sequentially also not necessarily according to
Secondary progress, but in turn or can replace at least part of the sub-step or stage of other steps or other steps
Ground executes.
In one embodiment, as shown in figure 4, providing a kind of product risks prediction meanss, comprising: judgment module 402,
Obtain module 404, extraction module 406, matching module 408, output module 410, in which:
Judgment module 402, for receive supervision server transmission supervision information when, judge supervise information whether table
Show supervision tightening.
Module 404 is obtained, for obtaining current public feelings information when supervising information indicates supervision tightening.
Extraction module 406, for extracting public sentiment label from public feelings information.
Matching module 408, for matching public sentiment label with pre-generated product portrait label.
Output module 410, for when matching there are product portrait label and public sentiment label, output to be drawn a portrait with product
There are risks for the corresponding product of label.
In one embodiment, the said goods risk profile device can also include:
Receiving module, product attribute index for receiving input.
Module is chosen, is used for from preset because choosing the factor corresponding with ATTRIBUTE INDEX in subsystem.
Portrait label establishes module, for establishing product portrait label according to the selected factor.
In one embodiment, device can also include:
Update module, for when there is no product portrait label and public sentiment label match when, by public sentiment label to pre-
If be updated because of subsystem.
In one embodiment, device can also include:
Word segmentation module for segmenting to public feelings information, and calculates the corresponding word frequency of each participle and emotion score.
Second obtains module, is greater than default emotion greater than the first participle and emotion score of predeterminated frequency for obtaining word frequency
Second participle of score.
Label adding module, for regarding the first participle and second participle as public sentiment label.
In one embodiment, device can also include:
Transmission module is sent out for inquiring the corresponding subsidiary's server of product, and by the information of product and supervision information
It is sent to subsidiary's server.
In one embodiment, device can also include:
Third obtains module, obtains corresponding first ginseng in supervision information for the macro-performance indicator by pre-establishing
Number.
Computing module, for calculating macroscopical scene early warning index and scene downlink probability according to the first parameter.
Second judgment module, for whether supervising information according to macroscopical scene early warning index and scene downlink probabilistic determination
Indicate supervision tightening；When macroscopical scene early warning index and scene downlink probability wherein at least one are greater than preset value, then supervise
Pipe information indicates supervision tightening；When macroscopical scene early warning index and scene downlink probability are respectively less than preset value, then letter is supervised
Breath indicates that supervision is not tightened.
In one embodiment, device can also include:
4th obtains module, for obtaining product portrait label and the corresponding processing of product portrait label of successful match
Scheme, and export processing scheme.
Second receiving module, parameter adjustment instruction corresponding with processing scheme for receiving input.
Module is adjusted, for being adjusted according to parameter adjustment instruction to the second parameter in processing scheme.
Specific about product risks prediction meanss limits the limit that may refer to above for product risks prediction technique
Fixed, details are not described herein.Modules in the said goods risk profile 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 5.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 Work attendance method.The display screen of the computer equipment can be liquid crystal display or electric ink display screen, the meter
The input unit for calculating machine equipment can be the touch layer covered on display screen, be also possible to be arranged on computer equipment shell by
Key, trace ball or Trackpad can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 5, 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 the supervision letter for receiving supervision server transmission when executing computer program
Breath judges that supervising information indicates whether supervision tightening；When supervising information indicates supervision tightening, current public feelings information is obtained；From
Public sentiment label is extracted in public feelings information；Public sentiment label is matched with pre-generated product portrait label；When there are products
When portrait label and public sentiment label match, then exporting product corresponding with the product of successful match portrait label, there are risks.
In one embodiment, the generating mode that processor executes related product portrait label when computer program can
To include: the product attribute index for receiving input；From preset because choosing the factor corresponding with ATTRIBUTE INDEX in subsystem；According to
The selected factor establishes product portrait label.
In one embodiment, processor execute realized when computer program by public sentiment label and pre-generated
It can also include: when matching there is no product portrait label and public sentiment label, then after product portrait label is matched
By public sentiment label to preset because subsystem is updated.
In one embodiment, processor executes the related extraction public sentiment label from public feelings information when computer program
It may include: to be segmented to public feelings information, and calculate the corresponding word frequency of each participle and emotion score；Word frequency is obtained to be greater than
The first participle and emotion score of predeterminated frequency are greater than the second participle of default emotion score；The first participle and second are segmented
As public sentiment label.
In one embodiment, processor executes the product picture in output and successful match realized when computer program
As the corresponding product of label is there are after risk, can also including: the corresponding subsidiary's server of inquiry product, and by product
Information and supervision information are sent to subsidiary's server.
In one embodiment, related judgement supervision information indicates whether to supervise when processor executes computer program
The deterministic process of tightening may include: to obtain corresponding first ginseng in supervision information by the macro-performance indicator pre-established
Number；Macroscopical scene early warning index and scene downlink probability are calculated according to the first parameter；According to macroscopical scene early warning index and
Scene downlink probabilistic determination supervision information indicates whether supervision tightening；When macroscopical scene early warning index and scene downlink probability its
In at least one be greater than preset value when, then supervise information indicate supervision tightening；When macroscopical scene early warning index and scene downlink
When probability is respectively less than preset value, then supervising information indicates that supervision is not tightened.
In one embodiment, that is realized when processor execution computer program draws a portrait in output and successful match product
There are after risk, can also include: the product portrait label and product portrait for obtaining successful match for the corresponding product of label
The corresponding processing scheme of label, and export processing scheme；Receive the parameter adjustment instruction corresponding with processing scheme of input；According to
Parameter adjustment instruction is adjusted the second parameter in processing scheme.
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 the supervision information for receiving supervision server transmission when being executed by processor, judge to supervise information
Indicate whether supervision tightening；When supervising information indicates supervision tightening, current public feelings information is obtained；Carriage is extracted from public feelings information
Feelings label；Public sentiment label is matched with pre-generated product portrait label；When there are product portrait label and public sentiment marks
When label match, then exporting product corresponding with the product of successful match portrait label, there are risks.
In one embodiment, the generating mode of related product portrait label when computer program is executed by processor
It may include: the product attribute index for receiving input；From preset because choosing the factor corresponding with ATTRIBUTE INDEX in subsystem；Root
Product portrait label is established according to the selected factor.
In one embodiment, realized when computer program is executed by processor by public sentiment label and pre-generated
Product portrait label matched after, can also include: when there is no product portrait label and public sentiment label match when,
Then by public sentiment label to preset because subsystem is updated.
In one embodiment, related when computer program is executed by processor that public sentiment mark is extracted from public feelings information
Label may include: to segment to public feelings information, and calculate the corresponding word frequency of each participle and emotion score；It is big to obtain word frequency
It is greater than the second participle of default emotion score in the first participle and emotion score of predeterminated frequency；By the first participle and second point
Word is as public sentiment label.
In one embodiment, the product in output and successful match realized when computer program is executed by processor
The corresponding product of portrait label is there are after risk, can also including: the corresponding subsidiary's server of inquiry product, and by product
Information and supervision information be sent to subsidiary's server.
In one embodiment, related judgement supervision information indicates whether to supervise when computer program is executed by processor
The deterministic process of pipe tightening may include: to obtain corresponding first ginseng in supervision information by the macro-performance indicator pre-established
Number；Macroscopical scene early warning index and scene downlink probability are calculated according to the first parameter；According to macroscopical scene early warning index and
Scene downlink probabilistic determination supervision information indicates whether supervision tightening；When macroscopical scene early warning index and scene downlink probability its
In at least one be greater than preset value when, then supervise information indicate supervision tightening；When macroscopical scene early warning index and scene downlink
When probability is respectively less than preset value, then supervising information indicates that supervision is not tightened.
In one embodiment, that is realized when computer program is executed by processor draws in output and successful match product
As there are after risk, can also include: that the product portrait label for obtaining successful match and product are drawn for the corresponding product of label
As the corresponding processing scheme of label, and export processing scheme；Receive the parameter adjustment instruction corresponding with processing scheme of input；Root
The second parameter in processing scheme is adjusted according to parameter adjustment instruction.
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
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including 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.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of product risks prediction technique, which comprises
The supervision information for receiving supervision server transmission judges that the supervision information indicates whether supervision tightening；
When the supervision information indicates supervision tightening, current public feelings information is obtained；
Public sentiment label is extracted from the public feelings information；
The public sentiment label is matched with pre-generated product portrait label；
When matching there are product portrait label and the public sentiment label, then exports to draw a portrait with the product of successful match and mark
Signing corresponding product, there are risks.
2. the method according to claim 1, wherein the generating mode of product portrait label, comprising:
Receive the product attribute index of input；
From preset because choosing the factor corresponding with the ATTRIBUTE INDEX in subsystem；
The product portrait label is established according to the selected factor.
3. according to the method described in claim 2, it is characterized in that, described public sentiment label and pre-generated product are drawn a portrait is marked
After label are matched, further includes:
When matching there is no product portrait label and the public sentiment label, then by the public sentiment label to described preset
Because subsystem is updated.
4. the method according to claim 1, wherein described extract public sentiment label, packet from the public feelings information
It includes:
The public feelings information is segmented, and calculates the corresponding word frequency of each participle and emotion score；
Obtain the second participle that the word frequency is greater than default emotion score greater than the first participle and emotion score of predeterminated frequency；
It regard the first participle and second participle as public sentiment label.
5. the label the method according to claim 1, wherein the product of the output and successful match is drawn a portrait
There are after risk for corresponding product, further includes:
The corresponding subsidiary's server of the product is inquired, and sends institute for the information of the product and the supervision information
State subsidiary's server.
6. the method according to claim 1, wherein the judgement supervision information indicates whether that supervision is received
Tightly, comprising:
Corresponding first parameter in the supervision information is obtained by the macro-performance indicator pre-established；
Macroscopical scene early warning index and scene downlink probability are calculated according to first parameter；
The supervision information according to macroscopical scene early warning index and the scene downlink probabilistic determination indicates whether to supervise
Tightening；
It is when macroscopical scene early warning index and the scene downlink probability wherein at least one are greater than preset value, then described
Supervising information indicates supervision tightening；
When macroscopical scene early warning index and the scene downlink probability are respectively less than preset value, then the supervision information table
Show that supervision is not tightened.
7. the method according to claim 1, wherein described in output and the portrait label of product described in successful match
There are after risk for corresponding product, further includes:
The product portrait label and the corresponding processing scheme of product portrait label of successful match are obtained, and exports institute
State processing scheme；
Receive the parameter adjustment instruction corresponding with the processing scheme of input；
The second parameter in the processing scheme is adjusted according to the parameter adjustment instruction.
8. a kind of product risks prediction meanss, which is characterized in that described device includes:
Judgment module, for judging that the supervision information is indicated whether when receiving the supervision information of supervision server transmission
Supervision tightening；
Module is obtained, for obtaining current public feelings information when the supervision information indicates supervision tightening；
Extraction module, for extracting public sentiment label from the public feelings information；
Matching module, for matching the public sentiment label with pre-generated product portrait label；
Output module, for when matching there are product portrait label and the public sentiment label, output to be drawn with the product
As there are risks for the corresponding product of label.
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 |
|---|---|---|---|
| CN201910212867.6A CN110097250B (en) | 2019-03-20 | 2019-03-20 | Product risk prediction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910212867.6A CN110097250B (en) | 2019-03-20 | 2019-03-20 | Product risk prediction method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110097250A true CN110097250A (en) | 2019-08-06 |
| CN110097250B CN110097250B (en) | 2024-07-02 |
Family
ID=67443337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910212867.6A Active CN110097250B (en) | 2019-03-20 | 2019-03-20 | Product risk prediction method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097250B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782123A (en) * | 2019-09-18 | 2020-02-11 | 中国平安财产保险股份有限公司 | Matching method and device of decision scheme, computer equipment and storage medium |
| CN114049142A (en) * | 2021-10-27 | 2022-02-15 | 创优数字科技(广东)有限公司 | Commodity quality data processing method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000348118A (en) * | 1999-06-04 | 2000-12-15 | Nippon Steel Corp | Method and system for risk management and recording medium for this method |
| WO2018023981A1 (en) * | 2016-08-03 | 2018-02-08 | 平安科技（深圳）有限公司 | Public opinion analysis method, device, apparatus and computer readable storage medium |
| CN108052586A (en) * | 2017-12-11 | 2018-05-18 | 上海壹账通金融科技有限公司 | The analysis of public opinion method, system, computer equipment and storage medium |
| CN108335006A (en) * | 2017-10-02 | 2018-07-27 | 平安普惠企业管理有限公司 | Air control method, apparatus, equipment, system and storage medium based on products configuration |
| 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 |
-
2019
- 2019-03-20 CN CN201910212867.6A patent/CN110097250B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000348118A (en) * | 1999-06-04 | 2000-12-15 | Nippon Steel Corp | Method and system for risk management and recording medium for this method |
| WO2018023981A1 (en) * | 2016-08-03 | 2018-02-08 | 平安科技（深圳）有限公司 | Public opinion analysis method, device, apparatus and computer readable storage medium |
| CN108335006A (en) * | 2017-10-02 | 2018-07-27 | 平安普惠企业管理有限公司 | Air control method, apparatus, equipment, system and storage medium based on products configuration |
| CN108052586A (en) * | 2017-12-11 | 2018-05-18 | 上海壹账通金融科技有限公司 | The analysis of public opinion method, system, 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 |
Non-Patent Citations (1)
| Title |
|---|
| 瞿志凯 等: "暴恐事件网络舆情风险预警研究", 《情报杂志》, vol. 35, no. 6, 30 June 2016 (2016-06-30), pages 40 - 46 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782123A (en) * | 2019-09-18 | 2020-02-11 | 中国平安财产保险股份有限公司 | Matching method and device of decision scheme, computer equipment and storage medium |
| CN110782123B (en) * | 2019-09-18 | 2024-07-09 | 中国平安财产保险股份有限公司 | Matching method and device of decision scheme, computer equipment and storage medium |
| CN114049142A (en) * | 2021-10-27 | 2022-02-15 | 创优数字科技(广东)有限公司 | Commodity quality data processing method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110097250B (en) | 2024-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109783730A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| WO2020073727A1 (en) | Risk forecast method, device, computer apparatus, and storage medium | |
| CN105488163B (en) | Information-pushing method and device | |
| CN110990529B (en) | Industry detail dividing method and system for enterprises | |
| CN112214508B (en) | Data processing method and device | |
| KR101435096B1 (en) | Apparatus and method for prediction of merchandise demand using social network service data | |
| CN113641828A (en) | Power grid provider portrait imaging method based on knowledge graph and storage device | |
| CN111738506A (en) | Cash center cash stock usage amount prediction method and device, electronic device, and medium | |
| CN110097250A (en) | Product risks prediction technique, device, computer equipment and storage medium | |
| Zhao et al. | Predicting oil prices: an analysis of oil price volatility cycle and financial markets | |
| Zhong et al. | Influence of artificial intelligence applications on total factor productivity of enterprises—evidence from textual analysis of annual reports of Chinese-listed companies | |
| CN113421014A (en) | Target enterprise determination method, device, equipment and storage medium | |
| CN103678322A (en) | System and method for sample data integration | |
| CN116701658A (en) | Business intention determining method and device and computer equipment | |
| CN116664306A (en) | Intelligent recommendation method and device for wind control rules, electronic equipment and medium | |
| CN109783876A (en) | Time series models method for building up, device, computer equipment and storage medium | |
| CN115719270A (en) | Credit evaluation method, device, apparatus, medium, and program product | |
| CN111429257B (en) | Transaction monitoring method and device | |
| CN111930604B (en) | Online transaction performance analysis method and device, electronic equipment and readable storage medium | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN108764981A (en) | Server, the processing method of text data and storage medium | |
| Paulo et al. | Assessment of biomass supply chain design and planning using discrete-event simulation modeling | |
| CN114693428A (en) | Data determination method and device, computer readable storage medium and electronic equipment | |
| CN114139798A (en) | Enterprise risk prediction method and device and electronic equipment | |
| CN112132689A (en) | Recommendation method and device based on time sequence factor event |
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 | ||
| GR01 | Patent grant |