CN113127707A - Product design influence analysis method - Google Patents
Product design influence analysis method Download PDFInfo
- Publication number
- CN113127707A CN113127707A CN202110436736.3A CN202110436736A CN113127707A CN 113127707 A CN113127707 A CN 113127707A CN 202110436736 A CN202110436736 A CN 202110436736A CN 113127707 A CN113127707 A CN 113127707A
- Authority
- CN
- China
- Prior art keywords
- product
- influence
- design
- data
- value
- 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
- 238000013461 design Methods 0.000 title claims abstract description 181
- 238000004458 analytical method Methods 0.000 title claims abstract description 25
- 238000011156 evaluation Methods 0.000 claims abstract description 146
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000012216 screening Methods 0.000 claims abstract description 7
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 238000012163 sequencing technique Methods 0.000 claims abstract description 5
- 230000008859 change Effects 0.000 claims description 17
- 230000004927 fusion Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 239000002131 composite material Substances 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims 1
- 238000011160 research Methods 0.000 abstract description 6
- 239000002699 waste material Substances 0.000 abstract description 2
- 238000000222 aromatherapy Methods 0.000 description 15
- 238000004364 calculation method Methods 0.000 description 10
- 238000011161 development Methods 0.000 description 6
- 238000011835 investigation Methods 0.000 description 4
- 241000222519 Agaricus bisporus Species 0.000 description 2
- 235000001674 Agaricus brunnescens Nutrition 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000012356 Product development Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/027—Frames
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a product design influence analysis method, which comprises the following steps: collecting related product design information data of a target product to form a primary case database; carrying out knowledge unit sequencing on data in the primary case database to form a product design knowledge base; dividing data of a product design knowledge base into user evaluation data and expert evaluation data to form a user evaluation index and an expert evaluation index, and obtaining a comprehensive score of the user evaluation index and the expert evaluation index; obtaining a product design influence numerical value according to the comprehensive scores of the user evaluation indexes and the expert evaluation indexes; the visual map is formed according to the product design influence numerical value, and the method breaks through the bottleneck that the traditional design influence research wastes time and labor, and has the advantages of screening products with high influence and assisting designers in subsequent design aiming at the technical problem of how to quantitatively calculate the product design influence at present.
Description
Technical Field
The invention relates to the technical field of product design, in particular to a product design influence analysis method.
Background
In recent years, influence is a hot topic in the field of product design, and evaluation of influence is a hot research problem in the fields of literature metrology, propaganda, social network relationship and the like. Leaderboards of the most influential product and the like are often used in the industry to summarize excellent, high influential, benchmarked products. The high-influence product is generally accepted by experts to different degrees, so that the wide acceptance of users and markets generates larger social influence and commercial value, and meanwhile, the high-influence product also has influence on the design of other products according to the technical innovation diffusion theory, and the high-influence product is shown in that after a certain new characteristic of the high-influence product is generated in a time sequence, other products follow and imitate the characteristic.
The existing high-influence product acquisition method is generally realized by design investigation, namely questionnaires, observation, structural interview, network data statistics and other methods, and comprises various types such as competitive product investigation, user demand investigation, consumption motivation, life style investigation and the like. The traditional design research is limited by technology and manpower conditions, so that the traditional design research has the limitations of long running period, high cost, limited samples, subjective experience and the like.
Before a designer performs a design activity, the designer usually needs to acquire data related to product development through design research, and acquire reference and guidance information for subsequent design activities after interpretation and analysis, wherein the reference and guidance information includes acquisition of high-impact products in the field.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a product design influence analysis method, breaks through the bottleneck of time and labor waste in traditional design influence research, and has the advantages of screening products with high influence and assisting designers in subsequent design.
In order to solve the technical problem, the invention is solved by the following technical scheme:
a product design influence analysis method comprises the following steps:
collecting related product design information data of a target product to form a primary case database;
carrying out knowledge unit sequencing on data in the primary case database to form a product design knowledge base;
dividing data of a product design knowledge base into user evaluation data and expert evaluation data to form a user evaluation index and an expert evaluation index, and obtaining a comprehensive score of the user evaluation index and the expert evaluation index;
obtaining a product design influence numerical value according to the comprehensive scores of the user evaluation indexes and the expert evaluation indexes;
and forming a visual map according to the product design influence numerical value.
Optionally, collecting related product design information data of the target product to form a primary case database, including the following steps:
according to the target product, product data related to the target product is obtained;
and performing information mining analysis according to the structural characteristics of the product data, and establishing a primary case database.
Optionally, the method for organizing knowledge units in the primary case database to form a product design knowledge base includes the following steps:
removing irrelevant and repeated contents in the primary case information base, and filtering the information of the data in the primary case database;
product-level information fusion is carried out on the primary case database after information filtration, so that collected data of the same product from different data sources point to the same product case;
and performing characteristic-level information fusion on the data subjected to the product-level information fusion, and eliminating repeated cases and cases with inconsistent types, thereby establishing a product design knowledge base.
Optionally, obtaining the user evaluation comprehensive score and the expert evaluation comprehensive score includes the following steps:
standardizing different types of user evaluation indexes in a product design knowledge base;
calculating the proportion of the ith product in the user evaluation index under the jth user evaluation index to obtain the proportion distribution of the jth user evaluation index among the products;
obtaining the entropy value and entropy redundancy of the jth user evaluation index according to the proportion distribution of the jth user evaluation index among the products;
obtaining the weight of each user evaluation index according to the entropy and the entropy redundancy, and obtaining a user evaluation comprehensive score;
standardizing different types of expert evaluation indexes in a product design knowledge base;
calculating the proportion of the ith product in the expert evaluation index under the jth expert evaluation index to obtain the proportion distribution of the jth expert evaluation index among the products;
obtaining the entropy value and entropy redundancy of the jth expert evaluation index according to the proportion distribution of the jth expert evaluation index among the products;
and obtaining the weight of each expert evaluation index according to the entropy and the entropy redundancy, and obtaining the comprehensive score of the expert evaluation.
Optionally, obtaining a product design influence value according to the comprehensive score of the user evaluation index and the expert evaluation index, including the following steps:
setting weight coefficients of user evaluation indexes and expert evaluation indexes, wherein the sum of the weight coefficients is 1;
and obtaining a product design influence value according to the user evaluation comprehensive score and the expert evaluation comprehensive score.
Optionally, forming a visual map according to the product design influence value, including the following steps:
obtaining a high-influence product according to the product design influence value, and forming a high-influence product time sequence map according to the relation between the product design influence value of the high-influence product and time;
obtaining a high-influence product according to the product design influence value, and forming a product design influence change trend map according to the change of the product design influence value of the high-influence product along with time;
obtaining a high-influence product according to the product design influence value, and screening out a replaceable product in a product design knowledge base according to the high-influence product;
and forming a comparison map of the alternative product and the high-influence product according to the comparison of the product design influence numerical values of the alternative product and the high-influence product.
Optionally, a product design influence time series map is formed according to the relation between the product design influence and time, and the method includes the following steps:
calculating the product design influence value one by taking staged time as a unit according to the time sequence;
setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products;
and processing description data of the high-influence product, and visualizing the description data by using a bubble chart.
Optionally, a product design influence change trend map is formed according to the change of the product design influence with time, and the method includes the following steps:
dividing the product into staged sub-units by taking the time from the time of marketing to the time of data acquisition as a total unit according to the time sequence, and calculating the value of the influence of product design one by one;
setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products;
and generating a curve map to form an influence change trend map.
Optionally, a high-influence product is obtained according to the product design influence value, and an alternative product is screened out in a product design knowledge base according to the high-influence product, and the method comprises the following steps:
calculating the product design influence value of the target product one by taking staged time as a unit according to the time sequence;
setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products;
calculating the text similarity of the description information of other products except the high-influence product in the product design knowledge base and the description information of the high-influence product;
and setting a second threshold value, and listing other products with text similarity greater than the second threshold value as replaceable products of high-influence products.
Optionally, a product design influence value comparison between the alternative product and the high influence product is performed to form a comparison map between the alternative product and the high influence product, which includes the following steps:
calculating the product design influence value of the replaceable product;
and obtaining a comparison map of the alternative product and the high-influence product through the force guide map.
Compared with the prior art, the technical scheme provided by the invention has the following beneficial effects:
the high-influence product is obtained by calculating the product design influence value, and the product design influence value of the high-influence product forms a map form for a designer to design and reference, so that the designer is assisted to know the development conditions of related products at the beginning of designing the product, the design development trend of the product is summarized, and more design reference cases are provided for the designer by obtaining a replaceable product.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a method for analyzing influence of product design according to an embodiment of the present invention;
FIG. 2 is a high-impact product time series diagram of a product design impact analysis method according to an embodiment of the present invention;
fig. 3 is a product design influence change trend map of a product design influence analysis method according to an embodiment of the present invention;
FIG. 4 is a comparison graph of an alternative product and a high-impact product of a product design impact analysis method according to an embodiment of the present invention;
fig. 5 is a time-series diagram of a high-influence product, which is an example of a champignon machine, in the product design influence analysis method according to the embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples, which are illustrative of the present invention and are not to be construed as being limited thereto.
As shown in fig. 1, a method for analyzing influence of product design includes the following steps: collecting related product design information data of a target product to form a primary case database; carrying out knowledge unit sequencing on data in the primary case database to form a product design knowledge base; dividing data of a product design knowledge base into user evaluation data and expert evaluation data to form a user evaluation index and an expert evaluation index, and obtaining a comprehensive score of the user evaluation index and the expert evaluation index; obtaining a product design influence numerical value according to the comprehensive scores of the user evaluation indexes and the expert evaluation indexes; and forming a visual map according to the influence value of the product design.
The method comprises the following steps of collecting related product design information data of a target product to form a primary case database: according to the target product, product data related to the target product is obtained, the product data comprises data of multiple sources such as shopping mats, design jackpots, enterprise brands, product designs, product evaluation websites and social platforms, and the related product design information data of the target product to be collected can be adjusted according to the requirements of actual evaluation angles.
Information mining analysis is carried out according to the structural characteristics of product data, and a primary case database is established, wherein the information mining analysis is used for mining the data through two methods respectively, specifically, a Scap open source framework is adopted to extract semi-structured data which is simple in structure and convenient to apply, the data comprises information such as sales volume, selling price, user feedback, product introduction and the like, and the data mainly comes from a shopping e-commerce website, a design jackpot official website, an enterprise brand official website and the like; meanwhile, unstructured data with low product information density and much noise are captured by adopting a Nutch theme information acquisition mode, the data comprise information such as conceptual product introduction, designers, expert comments and the like, mainly come from a product design website and a product evaluation website, and all acquired information such as webpage texts and images are subjected to CTPN (connective Text probable network) character detection algorithm, CRNN (relational recovery Neural network) character recognition algorithm and SSD (Single Shot Multi Box Detector) picture detection algorithm to form a primary case database comprising a corpus, an image library and the like, so that a foundation is laid for further data processing.
The method comprises the following steps of carrying out knowledge unit sequencing on data in a primary case database to form a product design knowledge base: the method includes the steps of removing irrelevant and repeated contents in a primary case information base, and filtering information of data in the primary case information base, wherein about seventy thousand pieces of product information relevant to an aromatherapy machine are collected from a network by taking the aromatherapy machine as an example, and specifically, relevant contents are reserved by Bert (bidirectional Encoder retrieval from transformations) training text classification. And eliminating content irrelevant to the product characteristics in the product network advertising promotion, such as price reduction promotion and other product information of the commodity store. And eliminating low-quality comments such as over-short comments, repeated comments and exclamation word and character information.
Product-level information fusion is carried out on the primary case database after information filtering, so that collected data of the same product from different data sources point to the same product case, specifically, character matching is carried out on the basis of information such as product name and serial number, different data form product-level information, the data are gathered in the product level, and the gathered information points to the same product case.
The method comprises the steps of performing characteristic-level information fusion on data after product-level information fusion, and eliminating repeated cases and cases with inconsistent types, so as to establish a product design knowledge base, namely classifying the data of the same product case, wherein the classification rule is to fuse the data of the same attribute and different data sources, for example, basic information such as product sales volume, product price, prize obtaining condition and the like is relatively simple, respectively establishing fused data, and then screening to eliminate repeated cases, parts, ingredients and the like with inconsistent types, so as to obtain the product design knowledge base of the aromatherapy machine, wherein the number of the product design knowledge base is accumulated to be about 800.
The user evaluation is based on the self demand and preference of the user, the evaluation of the product is integrally obtained by paying attention to the data related to the purchased product on the internet, and the representative data comprises the browsing amount of the product web page in the shopping e-commerce website, the product sales amount, the user evaluation number, the product search amount, the discussion amount taking the product as the subject in the social network site and the like; the expert evaluation is based on the design value ethical orientation and innovation level evaluation, the evaluation of the product in the professional field is obtained through prize evaluation, and representative data such as the number of prizes, the prize level, the professional evaluation number and the like of the product in the design jackpot official website are obtained.
And obtaining a user evaluation comprehensive score and an expert evaluation comprehensive score, comprising the following steps of: standardizing different types of user evaluation indexes in a product design knowledge base, and setting a user evaluation comprehensive score uiExpert evaluation comprehensive score is viWherein the index composition of u is xijThe j-th item of the user evaluation index (i 1, 2 … n; j 1, 2, … m) of the ith product includes: sales, evaluation number, etc. The index composition of the expert evaluation score v is yijThe j-th expert evaluation index value (i 1, 2 … n; j 1, 2, … m) of the ith product includes: the external prize-counting number, prize grade, professional evaluation number and the like in China are standardized, namely the absolute value of the user evaluation index value is converted into a relative value x'ijThe calculation formula is as follows:
calculating the proportion p of the ith product in the user evaluation index under the jth user evaluation indexijTo obtain the specific gravity distribution, p, of the jth user evaluation index among all productsijThe calculation formula of (2) is as follows:
obtaining the entropy e of the jth user evaluation index according to the proportion distribution of the jth user evaluation index among the productsjAnd entropy redundancy djWherein the entropy value ejThe larger the information content contained in the jth user evaluation index is, the more important the user evaluation index is, and the entropy value e of the user evaluation index isjThe smaller, the more weight needs to be given, by assigning the entropy value ejConversion into entropy redundancy djSo that the entropy redundancy djHas positive correlation with index weight, convenient weight calculation and entropy value ejSum entropy redundancy djAre respectively calculated as
dj＝1-ej。
Obtaining the weight w of each user evaluation index according to the entropy and the entropy redundancyjAnd obtaining a user evaluation composite score uiThe weight w of each user evaluation indexjAnd a user evaluation composite score uiThe calculation formulas are respectively as follows:
after the comprehensive evaluation score of the user is obtained, carrying out standardized processing on different types of expert evaluation indexes in a product design knowledge base; calculating the proportion of the ith product in the expert evaluation index under the jth expert evaluation index to obtain the proportion distribution of the jth expert evaluation index among the products; obtaining the entropy value and entropy redundancy of the jth expert evaluation index according to the proportion distribution of the jth expert evaluation index among the products; obtaining the weight of each expert evaluation index according to the entropy and the entropy redundancy, and obtaining the comprehensive score v of the expert evaluationiWherein, the standardization of the expert evaluation index, the proportion of the ith product in the expert evaluation index under the jth expert evaluation index, and the jth expert evaluation indexThe calculation formulas of the entropy value and the entropy redundancy of the evaluation indexes and the weight of each expert evaluation index are the same as the calculation formulas corresponding to the user evaluation indexes.
According to the comprehensive scores of the user evaluation indexes and the expert evaluation indexes, obtaining a product design influence numerical value, comprising the following steps: setting weight coefficients of user evaluation indexes and expert evaluation indexes, wherein the sum of the weight coefficients is 1, namely setting the value of the influence of product design as giThe weighting factor of the user evaluation index is a, the weighting factor of the expert evaluation index is b, and a + b is 1, and a and b are adjusted according to the application scenario.
Obtaining a product design influence numerical value according to the user evaluation comprehensive score and the expert evaluation comprehensive score, wherein the calculation formula is as follows: gi＝aui+bvi。
In the embodiment, the user evaluation indexes selected by the aromatherapy machine are the product sales and the user evaluation number, and the expert evaluation indexes are the design prize number, the prize level and the professional evaluation number. Calculating the product design influence value one by taking the year as a unit, calculating the weighted value of each index according to a formula, and explaining the basic calculation process of the influence value by taking a certain aromatherapy machine as an example as shown in table 1:
the sales volume in the product design knowledge base is 45836, the user comment number is 3170, the number of design prizes is 0, the prize grade is 0, the professional evaluation number is 0, and x' ═ 0.612, 0.875, 0, 0, 0} is obtained by formula calculation; p ═ {0.0053, 0.014, 0, 0, 0 }; 0.00878; and v is 0, the user evaluation index and the expert evaluation index are respectively set to be 0.5, and the total influence score is g is 0.00439.
As shown in fig. 2 to 4, the formation of the visual map according to the product design influence value includes the following steps: obtaining a high-influence product according to the product design influence value, and forming a high-influence product time sequence map according to the relation between the product design influence value of the high-influence product and time; obtaining a high-influence product according to the product design influence value, and forming a product design influence change trend map according to the change of the product design influence value of the high-influence product along with time; obtaining a high-influence product according to the product design influence value, and screening out a replaceable product in a product design knowledge base according to the high-influence product; and forming a comparison map of the alternative product and the high-influence product according to the comparison of the product design influence numerical values of the alternative product and the high-influence product.
As shown in fig. 2, according to the relationship between the product design influence and the time, a product design influence time series map is formed, which includes the following steps: calculating the product design influence value one by taking staged time as a unit according to the time sequence; setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products; and processing description data of the high-influence product, and visualizing the description data by using a bubble chart.
The larger the value of the influence of product design is, the larger the bubbles representing the influence of product design is, and the smaller the bubbles are, otherwise, the relationship among the high-influence products is, through data such as description of the screened high-influence products and the like, the imitative influence of the early-starting products on the later-stage product design is obtained by adopting a mode of commonly generating the same descriptors, and the relationship is established.
As shown in fig. 3, the method for forming a product design influence variation trend map according to the variation of the product design influence with time comprises the following steps: dividing the product into staged sub-units by taking the time from the time of marketing to the time of data acquisition as a total unit according to the time sequence, and calculating the value of the influence of product design one by one; setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products; and generating a curve map to form an influence change trend map.
Obtaining a high-influence product according to the product design influence value, and screening out an alternative product in a product design knowledge base according to the high-influence product, wherein the method comprises the following steps: calculating the product settings of the target products one by taking the staged time as a unit according to the time sequenceMeasuring the influence value; setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products; calculating the text similarity of the description information of other products except the high-influence product and the description information of the high-influence product in a product design knowledge base, wherein the text similarity can be calculated by a Jaccard coefficient method, the larger the Jaccard coefficient value is, the higher the sample similarity is, the calculation method is a numerical value obtained by dividing the intersection of two samples by the union, and the formula is
Specifically, a TF matrix of the text is calculated through a CountVectorizer, then the intersection and union of the text and the TF matrix are calculated by using Numpy, and then the Jacard coefficient is calculated; and setting a second threshold value, and listing other products with text similarity greater than the second threshold value as replaceable products of high-influence products.
As shown in fig. 4, according to the comparison of the product design influence values of the alternative product and the high-influence product, a comparison map of the alternative product and the high-influence product is formed, which includes the following steps: calculating the product design influence value of the replaceable product; obtaining a comparison map of the alternative product and the high-influence product through the force guide map, wherein the larger the text similarity is, the smaller the distance between the alternative product and the high-influence product is, and otherwise, the larger the distance is; the larger the value of the product design influence, the larger the bubbles representing the product design influence, and vice versa.
In the case of the aromatherapy machine, the threshold value one is set to 0.6, that is, the aromatherapy machine with the product design influence value larger than 0.6 is determined as a high-influence product, and the total number of the obtained aromatherapy machine cases is 48.
As shown in fig. 5, data such as product descriptions of 48 screened high-influence products are associated by means of common occurrence of the same descriptors to form a product design influence time sequence graph, key nodes in the evolution process of the aromatherapy machine can be observed, namely, product cases with important influence are generated, the development stage of the aromatherapy machine can be summarized according to the nodes, the development path of the aromatherapy machine can be summarized by observing the association between the early aromatherapy machine and the later-stage products, the design assistance of a designer is to know what high-influence products are, excellent products with industry heading function are screened out, the development condition of specific types of products can be known, important products are known, and the designer is assisted to know the basic condition of the products.
The method comprises the steps of analyzing the change of stage product design influence values from the time of sale of the high-influence aromatherapy machine to the time of data statistics by taking seasons as a unit to form an influence change trend map, observing the change trend of the influence of each high-influence aromatherapy machine according to the map and finding the case still having the influence rising trend, namely finding the aromatherapy machine case relatively having higher rising potential, and analyzing and finding the information such as 'hot door' functional characteristics inherited among high-influence products in the product through the relation among the high-influence products, so as to provide information assistance for the designer in formulating the design direction, provide a valuable reference case for the designer in design and facilitate summarizing the design development trend of a specific product.
Through digging with the similar product of champignon machine product, provide more reference selection for the designer, the design inspiration and the thinking of supplementary excitation designer.
TABLE 1
In addition, it should be noted that the specific embodiments described in the present specification may differ in the shape of the components, the names of the components, and the like. All equivalent or simple changes of the structure, the characteristics and the principle of the invention which are described in the patent conception of the invention are included in the protection scope of the patent of the invention. Various modifications, additions and substitutions for the specific embodiments described may be made by those skilled in the art without departing from the scope of the invention as defined in the accompanying claims.
Claims (10)
1. A product design influence analysis method is characterized by comprising the following steps:
collecting related product design information data of a target product to form a primary case database;
carrying out knowledge unit sequencing on data in the primary case database to form a product design knowledge base;
dividing data of a product design knowledge base into user evaluation data and expert evaluation data to form a user evaluation index and an expert evaluation index, and obtaining a comprehensive score of the user evaluation index and the expert evaluation index;
obtaining a product design influence numerical value according to the comprehensive scores of the user evaluation indexes and the expert evaluation indexes;
and forming a visual map according to the product design influence numerical value.
2. The product design influence analysis method according to claim 1, collecting related product design information data of a target product to form a primary case database, comprising the steps of:
according to the target product, product data related to the target product is obtained;
and performing information mining analysis according to the structural characteristics of the product data, and establishing a primary case database.
3. The product design impact analysis method of claim 1, wherein the data in the primary case database is subjected to knowledge unit sorting to form a product design knowledge base, comprising the steps of:
removing irrelevant and repeated contents in the primary case information base, and filtering the information of the data in the primary case database;
product-level information fusion is carried out on the primary case database after information filtration, so that collected data of the same product from different data sources point to the same product case;
and performing characteristic-level information fusion on the data subjected to the product-level information fusion, and eliminating repeated cases and cases with inconsistent types, thereby establishing a product design knowledge base.
4. The product design influence analysis method according to claim 1, wherein the step of obtaining the user evaluation composite score and the expert evaluation composite score comprises the following steps:
standardizing different types of user evaluation indexes in a product design knowledge base;
calculating the proportion of the ith product in the user evaluation index under the jth user evaluation index to obtain the proportion distribution of the jth user evaluation index among the products;
obtaining the entropy value and entropy redundancy of the jth user evaluation index according to the proportion distribution of the jth user evaluation index among the products;
obtaining the weight of each user evaluation index according to the entropy and the entropy redundancy, and obtaining a user evaluation comprehensive score;
standardizing different types of expert evaluation indexes in a product design knowledge base;
calculating the proportion of the ith product in the expert evaluation index under the jth expert evaluation index to obtain the proportion distribution of the jth expert evaluation index among the products;
obtaining the entropy value and entropy redundancy of the jth expert evaluation index according to the proportion distribution of the jth expert evaluation index among the products;
and obtaining the weight of each expert evaluation index according to the entropy and the entropy redundancy, and obtaining the comprehensive score of the expert evaluation.
5. The product design influence analysis method according to claim 1, wherein a product design influence value is obtained according to the comprehensive score of the user evaluation index and the expert evaluation index, and the method comprises the following steps:
setting weight coefficients of user evaluation indexes and expert evaluation indexes, wherein the sum of the weight coefficients is 1;
and obtaining a product design influence value according to the user evaluation comprehensive score and the expert evaluation comprehensive score.
6. The product design influence analysis method according to claim 1, wherein a visualization map is formed according to the product design influence numerical value, and the method comprises the following steps:
obtaining a high-influence product according to the product design influence value, and forming a high-influence product time sequence map according to the relation between the product design influence value of the high-influence product and time;
obtaining a high-influence product according to the product design influence value, and forming a product design influence change trend map according to the change of the product design influence value of the high-influence product along with time;
obtaining a high-influence product according to the product design influence value, and screening out a replaceable product in a product design knowledge base according to the high-influence product;
and forming a comparison map of the alternative product and the high-influence product according to the comparison of the product design influence numerical values of the alternative product and the high-influence product.
7. The product design influence analysis method according to claim 6, wherein a product design influence time series map is formed according to the relation between the product design influence and time, and the method comprises the following steps:
calculating the product design influence value one by taking staged time as a unit according to the time sequence;
setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products;
and processing description data of the high-influence product, and visualizing the description data by using a bubble chart.
8. The product design influence analysis method according to claim 6, wherein a product design influence change trend map is formed according to the change of the product design influence with time, and the method comprises the following steps:
dividing the product into staged sub-units by taking the time from the time of marketing to the time of data acquisition as a total unit according to the time sequence, and calculating the value of the influence of product design one by one;
setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products;
and generating a curve map to form an influence change trend map.
9. The product design influence analysis method of claim 6, wherein a high influence product is obtained according to the product design influence value, and an alternative product is screened from a product design knowledge base according to the high influence product, comprising the following steps:
calculating the product design influence value of the target product one by taking staged time as a unit according to the time sequence;
setting a first threshold value, and listing products with the product design influence value exceeding the first threshold value as high-influence products;
calculating the text similarity of the description information of other products except the high-influence product in the product design knowledge base and the description information of the high-influence product;
and setting a second threshold value, and listing other products with text similarity greater than the second threshold value as replaceable products of high-influence products.
10. The product design influence analysis method according to claim 9, wherein a comparison map of the alternative product and the high influence product is formed according to the comparison of the product design influence values of the alternative product and the high influence product, and the method comprises the following steps:
calculating the product design influence value of the replaceable product;
and obtaining a comparison map of the alternative product and the high-influence product through the force guide map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110436736.3A CN113127707A (en) | 2021-04-22 | 2021-04-22 | Product design influence analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110436736.3A CN113127707A (en) | 2021-04-22 | 2021-04-22 | Product design influence analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113127707A true CN113127707A (en) | 2021-07-16 |
Family
ID=76779092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110436736.3A Pending CN113127707A (en) | 2021-04-22 | 2021-04-22 | Product design influence analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113127707A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108228874A (en) * | 2018-01-18 | 2018-06-29 | 北京邮电大学 | World knowledge collection of illustrative plates visualization device and method based on artificial intelligence technology |
| CN109508388A (en) * | 2018-11-28 | 2019-03-22 | 交通银行股份有限公司 | A kind of method and apparatus of relational network visualization map |
| CN112187716A (en) * | 2020-08-26 | 2021-01-05 | 中国科学院信息工程研究所 | Knowledge graph display method for malicious codes in network attack |
| CN112468440A (en) * | 2020-10-28 | 2021-03-09 | 北京工业大学 | Knowledge graph-based industrial control system attack clue discovery system |
-
2021
- 2021-04-22 CN CN202110436736.3A patent/CN113127707A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108228874A (en) * | 2018-01-18 | 2018-06-29 | 北京邮电大学 | World knowledge collection of illustrative plates visualization device and method based on artificial intelligence technology |
| CN109508388A (en) * | 2018-11-28 | 2019-03-22 | 交通银行股份有限公司 | A kind of method and apparatus of relational network visualization map |
| CN112187716A (en) * | 2020-08-26 | 2021-01-05 | 中国科学院信息工程研究所 | Knowledge graph display method for malicious codes in network attack |
| CN112468440A (en) * | 2020-10-28 | 2021-03-09 | 北京工业大学 | Knowledge graph-based industrial control system attack clue discovery system |
Non-Patent Citations (1)
| Title |
|---|
| 刘征，王昀: "基于知识计量的产品设计调研方法", 《计算机集成制造系统》, vol. 26, no. 10, 31 October 2020 (2020-10-31), pages 2690 - 2699 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10748164B2 (en) | Analyzing sentiment in product reviews | |
| CN105589948B (en) | A kind of reference citation network visualization and literature recommendation method and system | |
| CN103778214B (en) | A kind of item property clustering method based on user comment | |
| CN103870973B (en) | Information push, searching method and the device of keyword extraction based on electronic information | |
| CN103886074B (en) | Commercial product recommending system based on social media | |
| CN107577759A (en) | User comment auto recommending method | |
| JP4637969B1 (en) | Properly understand the intent of web pages and user preferences, and recommend the best information in real time | |
| CN105512687A (en) | Emotion classification model training and textual emotion polarity analysis method and system | |
| CN109670542A (en) | A kind of false comment detection method based on comment external information | |
| CN109829733B (en) | False comment detection system and method based on shopping behavior sequence data | |
| US20080114800A1 (en) | Method and system for automatically extracting data from web sites | |
| CN106296312A (en) | Online education resource recommendation system based on social media | |
| CN109522562B (en) | Webpage knowledge extraction method based on text image fusion recognition | |
| CN105930469A (en) | Hadoop-based individualized tourism recommendation system and method | |
| CN107315738A (en) | A kind of innovation degree appraisal procedure of text message | |
| CN109345272A (en) | One kind is based on the markovian shop credit risk forecast method of improvement | |
| CN112990973B (en) | Online shop portrait construction method and system | |
| CN111353044B (en) | Comment-based emotion analysis method and system | |
| CN112015721A (en) | E-commerce platform storage database optimization method based on big data | |
| KR20120108095A (en) | System for analyzing social data collected by communication network | |
| Singh et al. | Sentiment analysis of a product based on user reviews using random forests algorithm | |
| Park et al. | An opinion-driven decision-support framework for benchmarking hotel service | |
| CN113901308A (en) | Knowledge graph-based enterprise recommendation method and recommendation device and electronic equipment | |
| CN102915358B (en) | Navigation website implementation method and device | |
| CN109670922B (en) | Online book value discovery method based on mixed features |
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 |
Application publication date: 20210716 |
|
| RJ01 | Rejection of invention patent application after publication |