CN109615168A - The appraisal procedure and device of commodity satisfaction, storage medium and electronic equipment - Google Patents
The appraisal procedure and device of commodity satisfaction, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN109615168A CN109615168A CN201811315295.6A CN201811315295A CN109615168A CN 109615168 A CN109615168 A CN 109615168A CN 201811315295 A CN201811315295 A CN 201811315295A CN 109615168 A CN109615168 A CN 109615168A
- Authority
- CN
- China
- Prior art keywords
- commodity
- characteristic information
- relevant
- information
- news
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Purpose of this disclosure is to provide the appraisal procedure and device of a kind of commodity satisfaction, storage medium and electronic equipment, data processing difficulty is larger when solving the problems, such as in the related technology to commodity satisfaction assessment.The described method includes: according to the characteristic information of input, consumer feedback's information of commodity relevant to the characteristic information is obtained, consumer feedback's information includes the calling information of commodity relevant to the characteristic information and/or one or more news of commodity relevant with the characteristic information;Quantification treatment is carried out to consumer feedback's information, obtains the commodity one or more evaluation index with the characteristic information;According to the numerical relationship model between the one or more evaluation index and preset evaluation index and satisfaction, the satisfaction of commodity relevant to the characteristic information is determined.
Description
Technical field
This disclosure relates to technical field of information processing, and in particular, to a kind of appraisal procedure and device of commodity satisfaction,
Storage medium and electronic equipment.
Background technique
With the transition of China's economic, economic growth accelerates to promote transformation from the Rapid Expansion of quantity to quality, with GNP,
The reflections such as GDP are economic " quantitative index " differences, and the state of development for measuring economic consumption not only needs to consider economic development
Scale, it is often more important that consider the quality of economic development.The exactly national industry economy that customer satisfaction index is investigated
" quality index ".The growth that its implementation and publication is intended to guide and help China's Industry to realize matter, improves industry, enterprise and production
Product competitiveness.
Especially, in recent years governments at all levels, China pay much attention to and concern food and drug safety problem, consumer, enterprise and
The risk prevention consciousness of government is continually strengthened, and related functional management department all accordingly increases the supervision of food and drug safety risk
The ability of dynamics, processing burst food and drug safety event is being gradually increased, and early warning system is built to have obtained unprecedented
It is fast-developing.
Supervision department assesses the security level of food and medicine to commodity, and generates relevant assessment data.So
And these assessment data can only embody the safety of food and medicine from single dimension, it is full to the acquisition food and medicine of various dimensions
Meaning degree needs to look for relevant information from mass data, and data processing difficulty is larger.
Summary of the invention
Purpose of this disclosure is to provide the appraisal procedure and device of a kind of commodity satisfaction, storage medium and electronic equipment,
Data processing difficulty is larger when solving the problems, such as in the related technology to commodity satisfaction assessment.
To achieve the goals above, the disclosure provides a kind of appraisal procedure of commodity satisfaction, which comprises
According to the characteristic information of input, obtain commodity relevant to the characteristic information consumer feedback's information and/or
Supervise information;
Quantification treatment is carried out to consumer feedback's information and/or the supervision information, obtains that there is the feature to believe
The commodity one or more evaluation index of breath;
According to the mathematical relationship between the one or more evaluation index and preset evaluation index and satisfaction
Model determines the satisfaction of commodity relevant to the characteristic information.
Optionally, the supervision information of commodity relevant to the characteristic information is obtained, comprising:
Obtain the security level of commodity relevant to the characteristic information;
Quantification treatment is carried out to the supervision information, obtains having the commodity one or more of the characteristic information to evaluate
Index, comprising:
The security level is normalized, the security level for obtaining commodity relevant to the characteristic information is commented
Valence index.
Optionally, the supervision information of commodity relevant to the characteristic information is obtained, comprising:
Obtain the sum to sample the problem of obtaining after the checking of commodity relevant to the characteristic information, Yi Jisuo
State the quantity for the sample disposed in problem sample;
Quantification treatment is carried out to the supervision information, obtains having the commodity one or more of the characteristic information to evaluate
Index, comprising:
Calculate the quotient of the quantity of the sample disposed and the sum of described problem sample, and using the quotient as
Problem sample disposition rate evaluation index.
Optionally, consumer feedback's information of commodity relevant to the characteristic information is obtained, comprising:
Obtain the calling information of relevant to characteristic information commodity, the calling information include: to the feature
The complaint total number of events of the relevant commodity of information, each complaint event finish situation index, and with each complaint event phase
The weight parameter of pass;
Quantification treatment is carried out to consumer feedback's information, obtains the commodity one or more with the characteristic information
Item evaluation index, comprising:
The complaint handling satisfaction evaluation index M of commodity relevant to the characteristic information is obtained by following formula:
Wherein, B finishes situation index for complaint event, and J is the urgency level index of complaint event, and T is to complain the mankind
Type index, Y are whether complaint event is the professional index complained, and JTY is the power relevant to complaint event that quantization obtains
Weight parameter, the complaint total number of events of N commodity relevant to the characteristic information.
Optionally, consumer feedback's information of commodity relevant to the characteristic information is obtained, further includes:
Browser is imitated to the access process of given server by news crawler module, is obtained and the characteristic information phase
One or more news of the commodity of pass;
Quantification treatment is carried out to consumer feedback's information, obtains the commodity one or more with the characteristic information
Item evaluation index, comprising:
News described in each executes following steps:
Word segmentation processing is carried out to the news by stammerer word segmentation module and word2vec module, is obtained new described in each
Multiple participles of the content of news;Emotion score is carried out according to each participle of vocabulary feeling polarities dictionary assessment set in advance,
And the emotion score of the news is obtained by the emotion score of the multiple participles for the content for counting the news;
According to the emotion score and preset emotion of one or more news of commodity relevant to the characteristic information
Analysis model obtains the news public sentiment evaluation index of commodity relevant to the characteristic information.
Optionally, it is described according to the one or more evaluation index and preset evaluation index and satisfaction it
Between numerical relationship model, determine the satisfaction of relevant to characteristic information commodity, comprising:
The multinomial evaluation index if it exists, then the value being weighted and averaged the multinomial evaluation index is as the spy
Reference ceases the satisfaction of relevant commodity.
Optionally, the characteristic information of the commodity of input includes the feature of following one or more dimension:
Region, time, merchandise classification.
The disclosure provides a kind of assessment device of commodity satisfaction, and described device includes:
Module is obtained, for the characteristic information according to input, obtains the consumer of commodity relevant to the characteristic information
Feedback information and/or supervision information;
Processing module is had for carrying out quantification treatment to consumer feedback's information and/or the supervision information
There is the commodity one or more evaluation index of the characteristic information;
Determining module, for according to the one or more evaluation index and preset evaluation index and satisfaction
Between numerical relationship model, determine the satisfaction of relevant to characteristic information commodity.
Optionally, the acquisition module, for obtaining the security level of commodity relevant to the characteristic information;
The processing module obtains related to the characteristic information for the security level to be normalized
Commodity security level evaluation index.
Optionally, the acquisition module, for obtaining to after the checking of commodity relevant to the characteristic information
To the problem of sample sum and described problem sample in the quantity of sample disposed;
The processing module, for calculating the quotient of the quantity of the sample disposed and the sum of described problem sample
Value, and using the quotient as problem sample disposition rate evaluation index.
Optionally, for obtaining the calling information of commodity relevant to the characteristic information, the calling information includes: pair
The complaint total number of events of commodity relevant to the characteristic information, each complaint event finish situation index, and with it is each
The relevant weight parameter of complaint event;
The processing module, the complaint handling for obtaining commodity relevant to the characteristic information by following formula are full
Meaning degree evaluation index M:
Wherein, B finishes situation index for complaint event, and J is the urgency level index of complaint event, and T is to complain the mankind
Type index, Y are whether complaint event is the professional index complained, and JTY is the power relevant to complaint event that quantization obtains
Weight parameter, the complaint total number of events of N commodity relevant to the characteristic information.
Optionally, the acquisition module, for imitating access of the browser to given server by news crawler module
Process obtains one or more news of commodity relevant to the characteristic information;
The processing module executes following steps for news described in each:
Word segmentation processing is carried out to the news by stammerer word segmentation module and word2vec module, is obtained new described in each
Multiple participles of the content of news;Emotion score is carried out according to each participle of vocabulary feeling polarities dictionary assessment set in advance,
And the emotion score of the news is obtained by the emotion score of the multiple participles for the content for counting the news;
It is also used to the emotion score of one or more news according to commodity relevant to the characteristic information, and default
Sentiment analysis model, obtain the news public sentiment evaluation index of commodity relevant to the characteristic information.
Optionally, the determining module, for when there are the multinomial evaluation index, the multinomial evaluation index to be added
Satisfaction of the value that weight average obtains as the relevant commodity of the characteristic information.
Optionally, the characteristic information of the commodity of input includes the feature of following one or more dimension:
Region, time, merchandise classification.
The disclosure provides a kind of computer readable storage medium, is stored thereon with computer program, and the program is by processor
The step of any one the method is realized when execution.
The disclosure provides a kind of electronic equipment, comprising:
Memory is stored thereon with computer program;
Processor, for executing the computer program in the memory, to realize the step of any one the method
Suddenly.
Above-mentioned technical proposal can at least reach following technical effect:
Quantified by consumer feedback's information to commodity relevant to the characteristic information, is obtained further according to quantization
One or more evaluation index and preset evaluation index and satisfaction between numerical relationship model, determining and institute
State the satisfaction of the relevant commodity of characteristic information.In such manner, it is possible to refine the classification of commodity, make the collection of data information and arrange more
Add intelligence, and can reflect the satisfaction of commodity from many levels, thus when reducing commodity satisfaction assessment data processing
Difficulty.
Other feature and advantage of the disclosure will the following detailed description will be given in the detailed implementation section.
Detailed description of the invention
Attached drawing is and to constitute part of specification for providing further understanding of the disclosure, with following tool
Body embodiment is used to explain the disclosure together, but does not constitute the limitation to the disclosure.In the accompanying drawings:
Fig. 1 is a kind of appraisal procedure flow chart of commodity satisfaction shown in one exemplary embodiment of the disclosure.
Fig. 2 is a kind of appraisal procedure flow chart of commodity satisfaction shown in one exemplary embodiment of the disclosure.
Fig. 3 is a kind of appraisal procedure flow chart of commodity satisfaction shown in one exemplary embodiment of the disclosure.
Fig. 4 is a kind of assessment apparatus structure block diagram of commodity satisfaction shown in one exemplary embodiment of the disclosure.
Fig. 5 is a kind of electronic equipment structural block diagram shown in one exemplary embodiment of the disclosure.
Specific embodiment
It is described in detail below in conjunction with specific embodiment of the attached drawing to the disclosure.It should be understood that this place is retouched
The specific embodiment stated is only used for describing and explaining the disclosure, is not limited to the disclosure.
Fig. 1 is a kind of appraisal procedure flow chart of commodity satisfaction shown in one exemplary embodiment of the disclosure, the side
Method includes:
S11 obtains consumer feedback's information of commodity relevant to the characteristic information according to the characteristic information of input,
Consumer feedback's information include commodity relevant to the characteristic information calling information and/or with the characteristic information phase
One or more news of the commodity of pass.
Optionally, the characteristic information of the commodity of the input includes the feature of following one or more dimension: ground
Domain, time, merchandise classification.
For example, the regional feature of input can be located in the area for the subordinate that XX is saved or XX is saved.Further, will
XX save data subdividing be 13 time dimension angle value, respectively " whole, D1, D2, D3, D4, D5, D6, D7, D8, D9, D10,
D11, D12 ", wherein " whole " represents the annual data of xx province, and D represents the value monthly divided for unit.
By taking the foodstuff in commodity as an example, food can be subdivided into 30 major class, in addition the data of " whole " type, altogether
31 values, respectively " whole, grain processing product, ' edible oil, grease and its product ', flavouring, meat products, dairy products, drink
Material, instant food, biscuit, can, frozen, quick-frozen food, potato and dilated food, pan work, tealeaves and related system
Product, drinks, vegetable product, fruit product, parched food and nut product, egg products, cocoa and Baked Coffee product, sugar,
Aquatic product, starch and starch-based product, cake, bean product, bee product, special diet food, dining food, edible agricultural product,
Food additives ".
Specifically, consumer feedback's information and/or supervision information can be transferred from existing database, can also connect
After the characteristic information for receiving input, corresponding content information is searched for from data network using crawlers.
S12, to consumer feedback's information carry out quantification treatment, obtain the commodity one with the characteristic information or
The multinomial evaluation index of person.
Consumer feedback's information may include the calling information to commodity, the calling information may include: to
The complaint total number of events of the relevant commodity of the characteristic information, each complaint event finish situation index, and with each throwing
Tell the relevant weight parameter of event.Specifically, can be thrown according to the urgency level index of the event of complaint, complainant's index of classification
Tell whether event is the professional index complained, the weight parameter relevant to complaint event quantified.
Consumer feedback's information can also include news information related with commodity.The forward direction of these news is negative
To emotion index can reflect consumer to a certain extent for the satisfaction of commodity.
S13, according to the mathematics between the one or more evaluation index and preset evaluation index and satisfaction
Relational model determines the satisfaction of commodity relevant to the characteristic information.
Optionally, it is described according to the one or more evaluation index and preset evaluation index and satisfaction it
Between numerical relationship model, determine the satisfaction of relevant to characteristic information commodity, comprising: the multinomial evaluation if it exists
Index, then the value being weighted and averaged the multinomial evaluation index is as the satisfaction of the relevant commodity of the characteristic information.
Above-mentioned technical proposal can at least reach following technical effect:
Quantified by consumer feedback's information to commodity relevant to the characteristic information, is obtained further according to quantization
One or more evaluation index and preset evaluation index and satisfaction between numerical relationship model, determining and institute
State the satisfaction of the relevant commodity of characteristic information.In such manner, it is possible to refine the classification of commodity, make the collection of data information and arrange more
Add intelligence, and can reflect the satisfaction of commodity from many levels, thus when reducing commodity satisfaction assessment data processing
Difficulty.
Fig. 2 is a kind of appraisal procedure flow chart of commodity satisfaction shown in one exemplary embodiment of the disclosure, the side
Method includes:
S21 receives the characteristic information of input.
By taking food as an example, every analysis result of existing Food Inspection detection data is divided into region, time and food
Three dimensions of major class.
S22 obtains the security level of commodity relevant to the characteristic information.
According to the inspection detection data of relevant departments, the security level of food is divided into 1~5 totally 5 grades, the number of grade
Value is lower, and to represent food safer;Conversely, the numerical value of grade is higher, to represent food more dangerous.
The security level is normalized in S23, obtains safety of commodity relevant to the characteristic information etc.
Grade evaluation index.
Corresponding security level evaluation index is arrived by what 5 food safety grades were normalized.For example, food is pacified
1 grade of congruent grade is most security level, in the food safety satisfaction highest that objective level can reflect, therefore defines the grade
Security level evaluation index is 1.Similar, food safety class 5 grade is least security level, can be reflected in objective level
Food safety satisfaction it is minimum, therefore define the grade security level evaluation index be 0.And so on it is available such as table
Food safety grade shown in 1 and food safety grade evaluation index mapping table.
Table 1
Food safety grade | Food safety grade evaluation index |
1 | 1 |
2 | 0.75 |
3 | 0.5 |
4 | 0.25 |
5 | 0 |
S24 obtains the sum to sample the problem of obtaining after the checking of commodity relevant to the characteristic information, with
And the quantity for the sample disposed in described problem sample.
Supervision department checks the information data storing of the inspection peace pipe in food and medicine in problem sample table, including
Investigate and prosecute to the problem of the classification of sample, disposition state, place region and investigate and prosecute the data such as time.It can from the problem sample table
To filter out commodity relevant to the characteristic information, and the sum of problem sample is obtained according to the selection result and described is asked
The quantity for the sample disposed in topic sample.
S25, calculates the quotient of the quantity of the sample disposed and the sum of described problem sample, and by the quotient
As problem sample disposition rate evaluation index.
That is, problem sample disposition rate evaluation index=quantity/problem sample sum of sample for having disposed.
S26 will be weighted and averaged the security level evaluation index and described problem sample disposition rate evaluation index
Handle satisfaction of the obtained value as commodity relevant to the characteristic information.
It is worth noting that food safety grade evaluation index and problem sample disposition rate evaluation index are all to be located at 0~1
Between value.
Specifically, the satisfaction C of commodity relevant to the characteristic information can be calculated by following formula:
C=(food safety grade evaluation index+problem sample disposition rate evaluation index) * 100/2;
C is the numerical value that a value range is 0~100 as a result,.C value is bigger, and the satisfaction for indicating commodity is higher;Conversely, C
The satisfaction for being worth smaller mark commodity is lower.
In the following, illustrating so that the characteristic information of input is " city xx, in January, 2017, beverage based food " as an example.
Analyzing to the Food Inspection detection data in " city xx, in January, 2017, beverage based food " first, is eaten
Product security level is 1 grade, and further obtaining food safety grade evaluation index is " 1 ".
Next checks that the information data storing of the inspection peace pipe in supervision department's inspection food and medicine in problem sample table, obtains
The quantity for the sample disposed into problem sample is 0, and the sum of problem sample is 0.Program in the specific implementation is set
In fixed, if set the data bulk that filters out as 0, indicate there is no relevant data under this feature information dimension, it is possible to understand that
It is not detected problem sample for the based food, that is to say, that this based food is safe, to objectively reflect
The satisfaction of the based food is higher, for the integrality for guaranteeing subsequent calculating, correspondingly, problem sample disposition rate evaluation index is set
It is set to " 1 ".
Processing will be weighted and averaged to the security level evaluation index and described problem sample disposition rate evaluation index
Satisfaction of the obtained value " 1 " as commodity relevant to the characteristic information.To can be obtained most after satisfaction " 1 " percentage
Whole index value is 100.From examining testing result can be seen that, the city xx in January, 2017 beverage based food is compared with high safety grade
Food, it is also fewer for the inspection data of problem sample, it can be considered that food relevant to this feature information is more pacified
Entirely, consumer is objectively satisfied.
Through the above technical solutions, can quantitative analysis go out commodity relevant to characteristic information satisfaction.With input
Characteristic information change, can also further evaluate the satisfaction of the commodity of same type difference enterprise, with type difference when
The satisfaction of the satisfaction of the commodity of phase and the commodity with type different geographical.
In addition, supervision department can clearly check by the appraisal procedure of above-mentioned commodity satisfaction, comprehensively understand quotient
The relevant enterprise of the lower problem behind of the security postures of product, track articles satisfaction, and then make more scientific, more effective, more
Quick administrative decision.In addition, the manufacturer of commodity can be assisted more by the appraisal procedure of above-mentioned commodity satisfaction
The satisfaction of commodity is solved, Instructing manufacture quotient targetedly works out corresponding market strategy to a certain extent, it is supervised constantly to change
Into product quality, consumption demand is catered to, improves customer satisfaction, the market competitiveness of enterprise is promoted from another side, is increased
The economic benefit of strong enterprise.
Fig. 3 is a kind of appraisal procedure flow chart of commodity satisfaction shown in one exemplary embodiment of the disclosure, the side
Method includes:
S31 receives the characteristic information of input.
By taking food as an example, every analysis result of existing Food Inspection detection data is divided into region, time and food
Three dimensions of major class.
S32 obtains the calling information of commodity relevant to the characteristic information.
Wherein, the calling information includes: the complaint total number of events to commodity relevant to the characteristic information, each throwing
That tells event finishes situation index, and weight parameter relevant to each complaint event.
S33 calculates the complaint handling satisfaction evaluation of commodity relevant to the characteristic information according to the calling information
Index.
Exemplary, specific implementation process can refer to following example.
When corresponding characteristic information is " XX province, Food & Drug ", XX is saved into the original Excel of Food & Drug calling information
The data of file are converted to two SQL file tables, respectively represent the report table of the particular content of complaints and denunciation and complain thing
The handle table for finishing situation of part.
Report table is analyzed by data dictionary, learns that the record of complaints and denunciation in table report includes to complain to lift
The urgency level of report, complainant's type, type of service and whether be the information such as occupation report, and when handle table then includes
Between, region and the information such as disposition to report record, therefore can be from region, time and food to the partial data
Three dimensions of major class are set out, consumer's subjectivity satisfaction that analysis complaints and denunciation are reflected.
Further, it is also possible to do desensitization process to the partial data for being related to sensitive information, our nothings of the attribute value of certain item data
Method utilizes, the value that can be used for calculating to this attribute definition one.For example, urgency level defines " 0~5 " totally 6 grades, most
Inferior grade 0 indicates not urgent, and corresponding urgency level index value is 0.5;Highest level 5 indicates very urgent, corresponding urgent
Level index value is 1.The definition situation of the value of weight parameter involved in calculating and index of correlation is as shown in table 2:
Table 2
Specifically, being referred to by the complaint handling satisfaction evaluation that following formula obtains commodity relevant to the characteristic information
Mark M:
Wherein, B finishes situation index for complaint event, and J is the urgency level index of complaint event, and T is to complain the mankind
Type index, Y are whether complaint event is the professional index complained, and JTY is the power relevant to complaint event that quantization obtains
Weight parameter, the complaint total number of events of N commodity relevant to the characteristic information.
The complaint handling satisfaction evaluation index being calculated is the value between one -1~+1, and the value is bigger, indicates to disappear
The person of expense is more satisfied to the disposition of complaints and denunciation;Conversely, the value is smaller, indicate that consumer gets over the disposition of complaints and denunciation
It is dissatisfied.
S34 imitates browser to the access process of given server by news crawler module, obtains and believe with the feature
Cease one or more news of relevant commodity.
Specifically, news crawler module can be imitated using code and be browsed according to the request module in python language
Then device analyzes according to the result of access webpage the access process of given server, further extract with it is described
One or more news of the relevant commodity of characteristic information.
S35 calculates the emotion score of each news.
Specifically, news described in each executes following steps: passing through stammerer word segmentation module and word2vec module pair
The news carries out word segmentation processing, obtains multiple participles of the content of news described in each;According to the vocabulary emotion set in advance
The each participle of polarity dictionary assessment carries out emotion score, and the emotion of multiple participles of the content by counting the news
Score obtains the emotion score of the news.
When it is implemented, can construct module by sentiment dictionary constructs vocabulary feeling polarities dictionary.Specifically, using Hownet
(Hownet) sentiment dictionary and TaiWan, China university simplified form of Chinese Character feeling polarities dictionary (NTSUSD) are as basic dictionary, and add
Enter some emotion words relevant to food safety theme as the vocabulary feeling polarities dictionary that early period, the analysis of public opinion used.
Further, news crawler module is obtained using stammerer participle technique and word2vec technology by sentiment analysis module
The news taken carries out text-processing, then calculates emotion score using vocabulary feeling polarities dictionary to each participle, will count
All participles score as the emotion score for news item.
S36, according to the emotion score of one or more news of commodity relevant to the characteristic information and preset
Sentiment analysis model obtains the news public sentiment evaluation index of commodity relevant to the characteristic information.
Specifically, the result of the analysis of public opinion is that every news assesses an emotion grade, one shares 0~5 totally 6 emotions
Grade, higher grade, and expression public sentiment is more passive, and the consumer satisfaction degree reflected is lower, and 0 indicates that media opinion is positive
's.In order to facilitate data fusion, the emotion grade that can use news corresponds to emotion and is scored at main process object.
It is handled by news crawler module and sentiment analysis, the emotion score of available every news, this score
Value is possible to be positive, it is also possible to be negative, and not have bound.It is that the emotion score of news is set in order to facilitate data fusion
Threshold value, for example, setting a value as the section of [- 100,100];And to score value carry out specification, with obtain one -1~+1 it
Between value.
When the emotion score to every news processes, the score in this section is mapped as in section [- 1,1]
Emotional value be denoted as Q, if the emotion score of news is lower than -100, the emotional value Q of the score of this news mapping is -1, together
Reason, if emotion score is more than 100, the emotional value Q of score mapping is+1.It follows that after given threshold, every news
Emotion score minimum -100, up to 100.The emotion of news score is converted to emotional value and obtains calculation are as follows:
The emotional value of our available every news by the calculation method, Q value range are -1~+1.Refer in order to obtain
Determine to can reflect consumer under characteristic information to the result of commodity subjective satisfaction, it is also necessary to merge the emotional value of every news,
It is as follows to merge formula:
It is worth noting that corresponding news content or calling information are not got under some characteristic informations,
With regard to news public sentiment evaluation index or problem sample disposition rate evaluation index can not be calculated.The dimension that characteristic information can be increased is drawn
The rugosity of gradation degree can obtain news content or calling information in the larger context in this way, to calculate reasonable
News public sentiment evaluation index or problem sample disposition rate evaluation index.
S37 will be weighted and averaged the complaint handling satisfaction evaluation index and the news public sentiment evaluation index
Handle satisfaction of the obtained value as commodity relevant to the characteristic information.
It is worth noting that complaint handling satisfaction evaluation index and news public sentiment evaluation index are all to be located at -1~+1
Between value.
Specifically, the satisfaction C of commodity relevant to the characteristic information can be calculated by following formula:
Z=(complaint handling satisfaction evaluation index+news public sentiment evaluation index) * 100/2;
Z is the numerical value that a value range is -100~+100 as a result,.If Z value is negative, consumer's subjectivity is defined as to quotient
Product are dissatisfied, and Z value is lower, indicate that consumer is more dissatisfied to commodity;If Z value is positive, consumer's subjectivity is defined as to commodity
It is satisfied, and Z value is higher, indicates that consumer is more satisfied to commodity.
Through the above technical solutions, can quantitative analysis go out commodity relevant to characteristic information satisfaction.With input
Characteristic information change, can also further evaluate the satisfaction of the commodity of same type difference enterprise, with type difference when
The satisfaction of the satisfaction of the commodity of phase and the commodity with type different geographical.
In addition, supervision department can clearly check by the appraisal procedure of above-mentioned commodity satisfaction, comprehensively understand quotient
The relevant enterprise of the lower problem behind of the security postures of product, track articles satisfaction, and then make more scientific, more effective, more
Quick administrative decision.In addition, the manufacturer of commodity can be assisted more by the appraisal procedure of above-mentioned commodity satisfaction
The satisfaction of commodity is solved, Instructing manufacture quotient targetedly works out corresponding market strategy to a certain extent, it is supervised constantly to change
Into product quality, consumption demand is catered to, improves customer satisfaction, the market competitiveness of enterprise is promoted from another side, is increased
The economic benefit of strong enterprise.
It is worth noting that for simple description, therefore, it is stated as a series of dynamic for above method embodiment
It combines, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described.Secondly, this
Field technical staff also should be aware of, and the embodiments described in the specification are all preferred embodiments, and related movement is simultaneously
It is not necessarily necessary to the present invention.In addition, in the absence of conflict, specific implementation can also be the group of above embodiment
It closes, for example, resulting by calculating, complaint handling satisfaction evaluation index, news public sentiment evaluation index, security level evaluation refer to
The number between any evaluation index and preset evaluation index and satisfaction in mark, problem sample disposition rate evaluation index
Relational model is learned, determines the satisfaction of commodity relevant to the characteristic information.
Fig. 4 is a kind of assessment device for commodity satisfaction that disclosure exemplary embodiment provides, and described device includes:
Module 410 is obtained, for the characteristic information according to input, obtains the consumption of commodity relevant to the characteristic information
Person's feedback information and/or supervision information;
Processing module 420 is obtained for carrying out quantification treatment to consumer feedback's information and/or the supervision information
To the commodity one or more evaluation index with the characteristic information;
Determining module 430, for according to the one or more evaluation index and preset evaluation index and satisfaction
Numerical relationship model between degree determines the satisfaction of commodity relevant to the characteristic information.
Optionally, the acquisition module, for obtaining the security level of commodity relevant to the characteristic information;
The processing module obtains related to the characteristic information for the security level to be normalized
Commodity security level evaluation index.
Optionally, the acquisition module, for obtaining to after the checking of commodity relevant to the characteristic information
To the problem of sample sum and described problem sample in the quantity of sample disposed;
The processing module, for calculating the quotient of the quantity of the sample disposed and the sum of described problem sample
Value, and using the quotient as problem sample disposition rate evaluation index.
Optionally, for obtaining the calling information of commodity relevant to the characteristic information, the calling information includes: pair
The complaint total number of events of commodity relevant to the characteristic information, each complaint event finish situation index, and with it is each
The relevant weight parameter of complaint event;
The processing module, the complaint handling for obtaining commodity relevant to the characteristic information by following formula are full
Meaning degree evaluation index M:
Wherein, B finishes situation index for complaint event, and J is the urgency level index of complaint event, and T is to complain the mankind
Type index, Y are whether complaint event is the professional index complained, and JTY is the power relevant to complaint event that quantization obtains
Weight parameter, the complaint total number of events of N commodity relevant to the characteristic information.
Optionally, the acquisition module, for imitating access of the browser to given server by news crawler module
Process obtains one or more news of commodity relevant to the characteristic information;
The processing module executes following steps for news described in each:
Word segmentation processing is carried out to the news by stammerer word segmentation module and word2vec module, is obtained new described in each
Multiple participles of the content of news;Emotion score is carried out according to each participle of vocabulary feeling polarities dictionary assessment set in advance,
And the emotion score of the news is obtained by the emotion score of the multiple participles for the content for counting the news;
It is also used to the emotion score of one or more news according to commodity relevant to the characteristic information, and default
Sentiment analysis model, obtain the news public sentiment evaluation index of commodity relevant to the characteristic information.
Optionally, the determining module, for when there are the multinomial evaluation index, the multinomial evaluation index to be added
Satisfaction of the value that weight average obtains as the relevant commodity of the characteristic information.
Optionally, the characteristic information of the commodity of input includes the feature of following one or more dimension:
Region, time, merchandise classification.
Above-mentioned technical proposal can at least reach following technical effect:
Quantified by consumer feedback's information to commodity relevant to the characteristic information and/or supervision information,
The mathematical relationship between one or more evaluation index and preset evaluation index and satisfaction obtained further according to quantization
Model determines the satisfaction of commodity relevant to the characteristic information.In such manner, it is possible to refine the classification of commodity, make data information
Collection and arrange it is more intelligent, and can from many levels reflect commodity satisfaction, be commented to reduce commodity satisfaction
The processing difficulty of data when estimating.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
The disclosure provides a kind of computer readable storage medium, is stored thereon with computer program, and the program is by processor
The step of assessment of any one commodity satisfaction is realized when execution.
The disclosure provides a kind of electronic equipment, comprising:
Memory is stored thereon with computer program;
Processor, for executing the computer program in the memory, to realize the assessment side of commodity satisfaction
The step of method.
Fig. 5 is the block diagram of a kind of electronic equipment 500 shown according to an exemplary embodiment.The electronic equipment can be one
Kind computer, data processor or mobile terminal are started to write.As shown in figure 5, the electronic equipment 500 may include: processor 501,
Memory 502.The electronic equipment 500 can also include multimedia component 503, input/output (I/O) interface 504, and communication
One or more of component 505.
Wherein, processor 501 is used to control the integrated operation of the electronic equipment 500, to complete above-mentioned commodity satisfaction
Appraisal procedure in all or part of the steps.Memory 502 is for storing various types of data to support to set in the electronics
Standby 500 operation, these data for example may include any application or method for operating on the electronic equipment 500
Instruction and the relevant data of application program, such as complaint handling satisfaction evaluation index, news public sentiment evaluation index, peace
Congruent grade evaluation index, problem sample disposition rate evaluation index or news content, etc..The memory 502 can be by any
The volatibility or non-volatile memory device or their combination of type are realized, such as static random access memory
(Static Random Access Memory, abbreviation SRAM), electrically erasable programmable read-only memory (Electrically
Erasable Programmable Read-Only Memory, abbreviation EEPROM), Erasable Programmable Read Only Memory EPROM
(Erasable Programmable Read-Only Memory, abbreviation EPROM), programmable read only memory
(Programmable Read-Only Memory, abbreviation PROM), and read-only memory (Read-Only Memory, referred to as
ROM), magnetic memory, flash memory, disk or CD.Multimedia component 503 may include screen and audio component.Wherein
Screen for example can be touch screen, and audio component is used for output and/or input audio signal.For example, audio component may include
One microphone, microphone is for receiving external audio signal.The received audio signal can be further stored in storage
Device 502 is sent by communication component 505.Audio component further includes at least one loudspeaker, is used for output audio signal.I/O
Interface 504 provides interface between processor 501 and other interface modules, other above-mentioned interface modules can be keyboard, mouse,
Button etc..These buttons can be virtual push button or entity button.Communication component 505 is for the electronic equipment 500 and other
Wired or wireless communication is carried out between equipment.Wireless communication, such as Wi-Fi, bluetooth, near-field communication (Near Field
Communication, abbreviation NFC), 2G, 3G or 4G or they one or more of combination, therefore corresponding communication
Component 505 may include: Wi-Fi module, bluetooth module, NFC module.
In one exemplary embodiment, electronic equipment 500 can be by one or more application specific integrated circuit
(Application Specific Integrated Circuit, abbreviation ASIC), digital signal processor (Digital
Signal Processor, abbreviation DSP), digital signal processing appts (Digital Signal Processing Device,
Abbreviation DSPD), programmable logic device (Programmable Logic Device, abbreviation PLD), field programmable gate array
(Field Programmable Gate Array, abbreviation FPGA), controller, microcontroller, microprocessor or other electronics member
Part is realized, for executing the appraisal procedure of above-mentioned commodity satisfaction.
In a further exemplary embodiment, a kind of computer readable storage medium including program instruction is additionally provided, it should
The step of appraisal procedure of above-mentioned commodity satisfaction is realized when program instruction is executed by processor.For example, this is computer-readable
Storage medium can be the above-mentioned memory 502 including program instruction, and above procedure instruction can be by the processor of electronic equipment 500
501 execute to complete the appraisal procedure of above-mentioned commodity satisfaction.
The preferred embodiment of the disclosure is described in detail in conjunction with attached drawing above, still, the disclosure is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the disclosure, a variety of letters can be carried out to the technical solution of the disclosure
Monotropic type, these simple variants belong to the protection scope of the disclosure.It is further to note that in above-mentioned specific embodiment
Described in each particular technique feature can be combined in any appropriate way in the case of no contradiction, be
Avoid unnecessary repetition, no further explanation will be given to various combinations of possible ways for the disclosure.
In addition, any combination can also be carried out between a variety of different embodiments of the disclosure, as long as it is without prejudice to originally
Disclosed thought equally should be considered as disclosure disclosure of that.
Claims (12)
1. a kind of analysis method of commodity satisfaction, which is characterized in that the described method includes:
According to the characteristic information of input, consumer feedback's information of commodity relevant to the characteristic information, the consumption are obtained
Person's feedback information includes the calling information and/or commodity relevant with the characteristic information of commodity relevant to the characteristic information
One or more news;
Quantification treatment is carried out to consumer feedback's information, obtains having the commodity one or more of the characteristic information to comment
Valence index;
According to the mathematical relationship mould between the one or more evaluation index and preset evaluation index and satisfaction
Type determines the satisfaction of commodity relevant to the characteristic information.
2. the method according to claim 1, wherein obtaining the consumer of commodity relevant to the characteristic information
Feedback information, comprising:
Obtain the calling information of relevant to characteristic information commodity, the calling information include: to the characteristic information
The complaint total number of events of relevant commodity, each complaint event finish situation index, and relevant to each complaint event
Weight parameter;
Quantification treatment is carried out to consumer feedback's information, obtains having the commodity one or more of the characteristic information to comment
Valence index, comprising:
The complaint handling satisfaction evaluation index M of commodity relevant to the characteristic information is obtained by following formula:
Wherein, B finishes situation index for complaint event, and J is the urgency level index of complaint event, and T is that complainant's type refers to
Mark, Y are whether complaint event is the professional index complained, and JTY is weight relevant to the complaint event ginseng that quantization obtains
Number, the complaint total number of events of N commodity relevant to the characteristic information.
3. method according to claim 1 or 2, which is characterized in that obtain disappearing for commodity relevant to the characteristic information
The person's of expense feedback information, further includes:
Browser is imitated to the access process of given server by news crawler module, is obtained relevant to the characteristic information
One or more news of commodity;
Quantification treatment is carried out to consumer feedback's information, obtains having the commodity one or more of the characteristic information to comment
Valence index, comprising:
Following steps are executed to each news:
Word segmentation processing is carried out to the news by stammerer word segmentation module and word2vec module, obtains the interior of each news
The multiple participles held;Emotion score is carried out according to each participle of vocabulary feeling polarities dictionary assessment set in advance, and is passed through
The emotion score for counting multiple participles of the content of the news obtains the emotion score of the news;
According to the emotion score of one or more news of commodity relevant to the characteristic information and preset sentiment analysis
Model obtains the news public sentiment evaluation index of commodity relevant to the characteristic information.
4. method according to claim 1 or 2, which is characterized in that it is described according to the one or more evaluation index,
And the numerical relationship model between preset evaluation index and satisfaction, determine expiring for commodity relevant to the characteristic information
Meaning degree, comprising:
The multinomial evaluation index if it exists then believes the value that the multinomial evaluation index is weighted and averaged as the feature
Cease the satisfaction of relevant commodity.
5. method according to claim 1 or 2, which is characterized in that the characteristic information of the commodity of input includes following
The feature of one or more dimension:
Region, time, merchandise classification.
6. a kind of assessment device of commodity satisfaction, which is characterized in that described device includes:
Module is obtained, for the characteristic information according to input, obtains the consumer feedback of commodity relevant to the characteristic information
Information, consumer feedback's information include commodity relevant to the characteristic information calling information and/or with the feature
One or more news of the relevant commodity of information;
Processing module obtains the commodity with the characteristic information for carrying out quantification treatment to consumer feedback's information
One or more evaluation index;
Determining module, for according between the one or more evaluation index and preset evaluation index and satisfaction
Numerical relationship model, determine the satisfaction of relevant to characteristic information commodity.
7. device according to claim 6, which is characterized in that the acquisition module, for obtaining and the characteristic information
The calling information of relevant commodity, the calling information include: total to the complaint event of commodity relevant to the characteristic information
Number, each complaint event finish situation index, and weight parameter relevant to each complaint event;
The processing module, for obtaining the complaint handling satisfaction of commodity relevant to the characteristic information by following formula
Evaluation index M:
Wherein, B finishes situation index for complaint event, and J is the urgency level index of complaint event, and T is that complainant's type refers to
Mark, Y are whether complaint event is the professional index complained, and JTY is weight relevant to the complaint event ginseng that quantization obtains
Number, the complaint total number of events of N commodity relevant to the characteristic information.
8. device according to claim 6 or 7, which is characterized in that the acquisition module, for passing through news crawler module
Browser is imitated to the access process of given server, obtain commodity relevant to the characteristic information one or more is new
It hears;
The processing module executes following steps for news described in each:
Word segmentation processing is carried out to the news by stammerer word segmentation module and word2vec module, obtains news described in each
Multiple participles of content;Emotion score is carried out according to each participle of vocabulary feeling polarities dictionary assessment set in advance, and is led to
The emotion score for crossing the multiple participles for the content for counting the news obtains the emotion score of the news;
It is also used to the emotion score and preset feelings of one or more news according to commodity relevant to the characteristic information
Feel analysis model, obtains the news public sentiment evaluation index of commodity relevant to the characteristic information.
9. device according to claim 6 or 7, which is characterized in that the determining module, for there are multinomial institute's commentaries
When valence index, the value that the multinomial evaluation index is weighted and averaged is as the satisfaction of the relevant commodity of the characteristic information
Degree.
10. device according to claim 6 or 7, which is characterized in that the characteristic information of the commodity of input includes following
The feature of one or more dimension:
Region, time, merchandise classification.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The step of any one of claim 1-5 the method is realized when execution.
12. a kind of electronic equipment characterized by comprising
Memory is stored thereon with computer program;
Processor, for executing the computer program in the memory, to realize described in any one of claim 1-5
The step of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811315295.6A CN109615168A (en) | 2018-11-06 | 2018-11-06 | The appraisal procedure and device of commodity satisfaction, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811315295.6A CN109615168A (en) | 2018-11-06 | 2018-11-06 | The appraisal procedure and device of commodity satisfaction, storage medium and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109615168A true CN109615168A (en) | 2019-04-12 |
Family
ID=66003095
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811315295.6A Pending CN109615168A (en) | 2018-11-06 | 2018-11-06 | The appraisal procedure and device of commodity satisfaction, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109615168A (en) |
-
2018
- 2018-11-06 CN CN201811315295.6A patent/CN109615168A/en active Pending
Non-Patent Citations (1)
Title |
---|
马费成: "《信息经济学》", 30 June 2012 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fami et al. | Determinants of household food waste behavior in Tehran city: A structural model | |
Chen et al. | Food environments and obesity: household diet expenditure versus food deserts | |
Whelan et al. | You can’t find healthy food in the bush: poor accessibility, availability and adequacy of food in rural Australia | |
Kirkpatrick et al. | Performance of the Automated Self-Administered 24-hour Recall relative to a measure of true intakes and to an interviewer-administered 24-h recall | |
Cameron et al. | Variation in supermarket exposure to energy-dense snack foods by socio-economic position | |
CN109636440A (en) | The appraisal procedure and device of commodity satisfaction, storage medium and electronic equipment | |
CN107851097A (en) | Data analysis system, data analysing method, data analysis program and storage medium | |
Fami et al. | The relationship between household food waste and food security in Tehran city: The role of urban women in household management | |
Partington et al. | Reduced-item food audits based on the nutrition environment measures surveys | |
Kersten et al. | Peer Reviewed: Small Food Stores and Availability of Nutritious Foods: A Comparison of Database and In-Store Measures, Northern California, 2009 | |
Okumus et al. | Generation Y's dining out behavior | |
Batarseh et al. | Public policymaking for international agricultural trade using association rules and ensemble machine learning | |
Lim et al. | Statistical Process Control for The Food Industry | |
Ho | A new approach to measuring Overall Liking with the Many-Facet Rasch Model | |
Muñoz Torrecillas et al. | Self-control in intertemporal choice and mediterranean dietary pattern | |
González-Vallejo et al. | Analysis of nutrition judgments using the Nutrition Facts Panel | |
Olstad et al. | Prospective associations between diet quality and body mass index in disadvantaged women: the Resilience for Eating and Activity Despite Inequality (READI) study | |
Cavaliere et al. | Exploring the environmental impact associated with the abandonment of the Mediterranean Diet, and how to reduce it with alternative sustainable diets | |
Dunford et al. | Availability, healthiness, and price of packaged and unpackaged foods in India: A cross-sectional study | |
WO2024002216A1 (en) | Service problem attribution method and device | |
CN109615168A (en) | The appraisal procedure and device of commodity satisfaction, storage medium and electronic equipment | |
CN111861546A (en) | Comment quality judgment method, device, equipment and storage medium | |
Wadolowska et al. | Comparing dietary patterns derived by two methods and their associations with obesity in Polish girls aged 13–21 years: The cross-sectional GEBaHealth study | |
Wei | Research on data preprocessing in supermarket customers data mining | |
Manala-O et al. | Food waste behavior of young fast-food consumers in the Philippines |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190412 |