CN111724196A - Method for improving quality of automobile product based on user experience - Google Patents
Method for improving quality of automobile product based on user experience Download PDFInfo
- Publication number
- CN111724196A CN111724196A CN202010409688.4A CN202010409688A CN111724196A CN 111724196 A CN111724196 A CN 111724196A CN 202010409688 A CN202010409688 A CN 202010409688A CN 111724196 A CN111724196 A CN 111724196A
- Authority
- CN
- China
- Prior art keywords
- user
- function
- node
- automobile
- functions
- 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
Images
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for improving the quality of an automobile product based on user experience, which comprises the following steps: user comments on an automobile website are crawled to serve as a demand data source; analyzing the relation between comment texts based on a demand data source, and formulating a demand decomposition rule; extracting keywords from the comment text through the semantic similarity graph; classifying the functional elements through sentiment scoring and analysis; and correspondingly improving the steer-by-wire system, the counterweight, the size and the hand-held part details of the steering wheel based on the classification result. According to the method, the product requirements are decomposed through the user comment texts on the automobile forum, the target function elements are obtained through matching, the product defects are found, the quality of the automobile products is improved, and the safety of the automobile products is improved.
Description
Technical Field
The invention relates to the field of automobile products, in particular to a method for improving the quality of an automobile product based on user experience.
Background
Following interconnectionDue to the rapid development of the network, users can share more experiences and feelings of using products through the network. In the face of increasing urgency of user demands, enterprises want to obtain competitive advantages in the market and need to guide product iteration and upgrading by analyzing the user demands. "China manufacturing 2025" issued by State Council mentions "promoting the formation of research, development, manufacturing and industry organization modes based on dynamic perception of consumption requirements", so that it is very urgent to establish mapping association between user requirements and product functions, and enterprises begin with the user requirements to analyze the product functions, so that the research and development period of the products can be saved, and the user experience can be improved[1]。
The method for mapping the requirement of the product to the function is very important for improving the product design, and the existing mapping process research is generally to carry out creative analysis according to the acquired user requirement and abstract to obtain the total function of the product[2](ii) a Or using Quality Function Development (QFD)[3]KANO model[4]Fuzzy metric algorithm[5]Theory of extension of qi[6]And the like, to complete the functional mapping from the requirements to the products. However, the existing demand-function mapping methods lack the influence of the experience elements in the user demands, and the functional characteristics obtained after mapping often cannot be accurate, so that the real demands of the users are truly reflected[7-8]。
The prior art has the following disadvantages:
1) the mapping is subject to errors. The mapping process is usually based on experience, the user requirements have the characteristics of fuzziness and subjectivity, and the final mapping result has larger error which is larger than the expected error;
2) there is hysteresis in the mapping. The dynamic change characteristic of the user requirement is not considered, the product requirement obtained by mapping the user requirement is lagged, and the authenticity of the user requirement cannot be reflected.
3) The mapping process is heavy and inefficient. The whole mapping process lacks an effective mechanism for mutual scheduling between user requirements and product functions, so that the analysis process needs to be artificially discriminated, and the mapping efficiency is low.
4) The mapping process lacks the role of taking into account user experience factors. The user experience elements play a key role in the demand analysis, and experience reflects direct feeling of a user after using a product, and relates to ergonomics. The experience elements are not described in the current mapping process, and the whole mapping process is single, so that the mapped product functions cannot reflect the essential requirements of users.
Reference to the literature
[1] Ash associated similarity matching and solving [ J ] computer integrated manufacturing system, 2012(04) 27-34 for populus gorgeous, yaohio, zhuyghiping, et al.
[2]Nazari-Shirkouhi S,Keramati A.Modeling customer satisfaction withnew product design using a flexible fuzzy regression-data envelopmentanalysis algorithm[J].Applied Mathematical Modelling,2017,50(oct.):755-771.
[3] Research on a functional demand acquisition mechanism oriented to concept design in Haiyan, et al, of Single hongbo, Kudzuvine, [ J ]. Chinese mechanical engineering, 2013(12):47-52.
[4] Plum, mahuang, et al.
[5] Thanks to yang development, zhang xian, et al. generalized customer demand analysis based on FCM and IGA and their resource allocation [ J ]. computer integrated manufacturing system, 2015(3): 634-.
[6] Zhang Jianhui, Wanjuan, Daizui, et al, product demand-function mapping method based on extension theory [ J ], scientific technology and engineering, 2017(24), 171-.
[7]Wang Y,Tseng M M.Integrating comprehensive customer requirementsinto product design[J].Cirp Annals Manufacturing Technology,2011,60(1):175-178.
[8]Lemkem T,Stone R B,Arlitt R M.Ontologies to support customerrequirement formulation in aerospace design[C].Cleveland,OH,United states:American Society of Mechanical Engineers(ASME),2017:1-12.
Disclosure of Invention
The invention provides a method for improving the quality of an automobile product based on user experience, which decomposes product requirements through a user comment text on an automobile forum, finds out product defects by matching to obtain target function elements, improves the quality of the automobile product, and improves the safety of the automobile product, and is described in detail in the following:
a method for improving automotive product quality based on user experience, the method comprising:
user comments on an automobile website are crawled to serve as a demand data source;
analyzing the relation between comment texts based on a demand data source, and formulating a demand decomposition rule;
extracting keywords from the comment text through the semantic similarity graph; classifying the functional elements through sentiment scoring and analysis;
and correspondingly improving the steer-by-wire system, the counterweight, the size and the hand-held part details of the steering wheel based on the classification result.
Further, the analyzing the relationship between the comment texts based on the demand data source and formulating the demand decomposition rule specifically include:
abstracting text content into a graph model, and constructing a semantic relation graph triple M<N，E，C>Summarizing the relation between the words, wherein N is a set of nodes, and one node represents a word; e is a set of directed edges, and one edge represents a modification relation among words; c represents the set of text contents after the requirement processing, and WN is used for the nodes i and jiRepresents the weight, WE, of node i(i,j)The weight representing the edge pointing from node i to node j is calculated as follows:
WNinumber of times node i appears in set C
WE(i,j)Number of times node i and node j have a semantic logical relationship
And screening the keywords based on the semantic relation graph, wherein a formula for calculating the K value of the keywords is as follows:
wherein i is one of the nodes, d is a balance factor and satisfies 0<d<1, N isSet of all nodes, s is the number of times i points to the set of other points, n is the number of times i points to the set of other points, the first half of the formula
Representing the importance of the node i to think of itself, the second half
Indicating the importance of other nodes considering node i.
The method specifically comprises the following steps of extracting keywords from the comment text through the semantic similarity graph:
the long text is extracted through the core key words and converted into a short text with similar semanteme.
Further, the classifying the functional elements through sentiment scoring and analyzing specifically comprises:
decomposing the functions of the existing product to obtain the functional elements, and comparing the functional elements with the functional elements obtained by demand analysis to obtain various new functions of the product so as to meet the demands of users;
classifying the functional elements after emotion scoring according to the dictionary, and dividing the functional elements into the following parts according to the satisfaction degree of the user: positive function, negative function, irrelevant function and newly added function.
Wherein the forward function is positively correlated with the user satisfaction, and the emotion score is greater than 0; the negative function is negatively related to the satisfaction degree of the user, and the emotion score is less than 0; filtering the irrelevant functions by a Gooseker and then removing the irrelevant functions; and the newly added function needs to be generated after the set of the positive and negative function elements is removed and compared with the existing function.
Further, the positive functions are reserved, the negative functions are improved, irrelevant functions are removed, the newly added functions are added and supplemented, and finally the set of target function elements is obtained.
The technical scheme provided by the invention has the beneficial effects that:
1. the method can establish a mapping model of requirements and functions aiming at the user comment text data, avoids the defects of fuzziness and subjectivity of the traditional model, forms a system architecture, and can quickly reflect mapping association;
2. the method can quickly process the network text data, and considers the user experience elements, wherein the result after the requirement-function mapping can better reflect the real requirement of the user, thereby meeting the requirement in practical application;
3. according to the method, the public praise data of the automobile network forum is analyzed, the demand result of the user on the product function is obtained, the product defect is found out, the quality of the automobile product is improved, the safety of the automobile product is improved, and the potential safety hazard is reduced.
Drawings
FIG. 1 is a schematic diagram of the optical path of the system;
FIG. 2 is a schematic diagram of a requirement-function mapping process;
FIG. 3 is a function discovery flow diagram;
FIG. 4 is a diagram of a technical case.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in further detail below.
In view of the limitation of the existing demand-function mapping method, the invention hopes that the problems of error, hysteresis and low efficiency of the existing demand-function mapping method can be solved by deeply analyzing the network comment of the automobile product by means of a big data analysis method and considering the key effect of user experience elements in the network comment, and a complete product demand-function mapping model based on user experience is established. The user requirements are extracted through the network comments, the systematic mapping of the requirements to the product functions is completed, the product defects are found out, the quality of the automobile products is improved, the safety of the automobile products is improved, and the potential safety hazards are reduced.
Step 1: and (4) acquiring the demand, and crawling user comments on the automobile website as a demand data source.
1) And (5) data crawling. The data of a public praise block on an automobile forum website is obtained through a Python crawler, and description indexes of the automobile, such as space, power, control, oil consumption, appearance, interior decoration and comfort, are classified and stored in a local database.
2) And (6) data cleaning. In order to ensure the research value of the collected user comment data, useless data needs to be cleaned.
The data for cleansing included:
(ii) repeated review data. The user issues repeated comments for many times, which causes interference of virtual height in the process of data mining and analysis, so that the repeated comment data needs to be deleted, and only one of the repeated comments of the user is reserved as a comment text for access.
② there is missing comment data. The user is influenced by factors such as time, environment and network, the published comment text has large loss and even blank, the data of the part has no value for research, and the data of the part needs to be deleted pertinently to reduce the interference of noise data.
3) Word segmentation and part-of-speech tagging. The comment text still contains some information irrelevant to the automobile product, which can cause noise interference to subsequent analysis, so that the comment text is subjected to fine simplified processing. The Chinese academy ICTCCLAS word segmentation system is adopted to perform word segmentation and stop word removal on user comment data, nouns, adjectives, verbs and adverbs in part-of-speech tagging are mainly concerned with entity words related to automobile products, and the key effect is achieved on subsequent demand analysis.
4) And (5) processing clauses and subjective sentences.
Dividing into sentences. Comment text is typically described in terms of periods, exclamation marks, and question marks as ending symbols for a complete segment of language. Because the online comments made by the users have the characteristics of fuzziness, subjectivity and randomness, and the condition that punctuation marks are lost in the comment texts of the users possibly exists, periods are manually added by taking the punctuation marks as clauses so as to ensure that the comment texts are complete.
② processing the main sentence. Comparing the single sentences after sentence division with HowNet dictionaries one by one, if the single sentences do not contain emotion evaluation words, the sentence is only objectively described, the experience requirements of the user after using the product are not shown, and the requirement analysis is not carried out; if the emotion evaluation words are contained, the sentence is a subjective sentence, and the text is stored for subsequent requirement analysis.
Step 2: and (5) requirement decomposition, namely analyzing the relation between the comment texts and formulating a requirement decomposition rule.
The user comment text language processed by the requirement still has the characteristics of complexity and diversity, and the user requirement is difficult to be directly converted into the functional characteristic. Therefore, the invention provides a method based on semantic similarity graph, which abstracts the text content into one or more keywords, and then directly maps the required keywords into the function indexes to complete the mapping process from the requirement to the function.
The textual content of the requirement description is usually composed of a piece of speech or a sentence, wherein the noun, verb, adjective, adverb usually already carry the subject information of the content. Through the preprocessing of word segmentation, word segmentation and part-of-speech tagging, only verbs, nouns, adjectives and adverbs related to the use of automobile products are reserved, and a semantic relation graph is constructed by utilizing the table 1.
TABLE 1 modified relationships between words and core words
After the requirement processing, abstracting the text content into a graph model, and constructing a semantic relation graph triple M<N，E，C>The relationships between words are summarized. Wherein N (node) is a collection of nodes, one node representing a word; e (edge) is a set of directed edges, and one edge represents a modification relation among words; c (content) represents the set of text content after the requirement processing. For nodes i and j, using WNiRepresents the weight, WE, of node i(i,j)The weight representing the edge pointing from node i to node j is calculated as follows:
WNinumber of occurrences of node i in set C (1)
WE(i,j)Number of times node i and node j have a semantic logical relationship (2)
Then, screening keywords based on the semantic relation graph, wherein a formula for calculating the K value of the keywords is as follows:
in formula (3), i is a node therein, d is a balance factor and satisfies 0<d<1, N is the set of all nodes, s is the set of points to which i points, and N is the number of times i points to the set of points. First half of formula
Representing the importance of the node i to think of itself, the second half
Indicating the importance of other nodes considering node i.
And step 3: and (4) function matching, namely extracting keywords from the comment text through the semantic similarity graph.
After the requirement decomposition in the step 2, the requirement text is extracted into a form of a keyword, for example, "starting and leaving to get the oil supply response ultrafast. The device has the advantages of no time for overtaking, smooth acceleration and no pause and frustration. The road has not run at high speed, is a road in suburbs of cities, is driven to 90 times as fast as possible, does not rotate more than two thousand times, and has more power than the previous thought. Some owners running at high speed in forums still run 140 power quite enough, so the engine in Honda is good. The long text is extracted into a short text form of 'quick starting reaction, no overtaking, smooth acceleration without jerking feeling' through keywords of a semantic similarity graph, and the result after demand-function matching is a functional element of 'large engine power and strong transmission performance'.
The long text is converted into a short text with similar semanteme through the extraction of the core key words, the work processing amount of the text content is essentially reduced through the simplified result, and the subsequent analysis of the data is facilitated.
And 4, step 4: and function discovery, namely classifying the function elements through emotion scoring and analysis.
In the stage of function discovery, the original functions of the automobile product need to be recombined. In the process of user experience, the existing function preferentially meets the user requirement, and when the existing function cannot meet the user requirement, the new function needs to be generated through the existing function, so as to further meet the user requirement, as shown in fig. 2.
The function discovery needs to decompose the functions of the existing product to obtain the function elements thereof, and then compare the function elements with the function elements obtained by the requirement analysis to obtain various new functions of the product so as to meet the requirements of users. Classifying the functional elements after sentiment scoring according to a HowNet dictionary, and dividing the functional elements into the following parts according to user satisfaction: four categories of positive functions, negative functions, irrelevant functions and added functions are classified according to the following table 2.
TABLE 2 functional element Classification basis
After the functional elements are classified, function building is performed, positive functions are reserved, negative functions are improved, irrelevant functions are removed, and newly added functions are added and supplemented, so that a set of target functional elements is finally obtained, as shown in fig. 3.
In the function discovery stage, besides the original seven indexes of space, power, control, oil consumption, appearance, interior and comfort, the function discovery method also discovers two newly added function indexes generated by paying attention to economy and serviceability of a user after analysis. The cost performance of the user on the automobile is more considered, and with the continuous expansion of network communication and service only, the additional service performance of the product derived after the user uses the automobile plays an important role in improving the performance of user experience.
Taking user demand data as an example, the demand expressed by the user through online comment is that steering wheel steering is not smooth enough, and after the mapping of the demand function, the demand is directly reflected by a 'control' index, and the demand is indirectly reflected by a 'service' index and a 'dynamic' index. As shown in fig. 4, the following technical improvement method is proposed for this:
1. optimization and upgrading of a steer-by-wire system of a steering wheel. Wherein a sensor detects movement of the steering wheel and sends information to a microprocessor. The computer then sends commands to actuators on the shaft that turn as directed by the user, and the steer-by-wire system employs a more dedicated communication link, employing a steering sensor to minimize time delays, helping to improve the user's fluency in operating the steering wheel.
2. Improvements in steering wheel weight and size. The heavier the steering wheel is, the more fatigued the driver is, and the lighter the steering wheel is, the more fuzzy the road feel is, the more easily the runway is deviated. Heavy and small steering wheels are suitable for small automobiles, light and large steering wheels are suitable for medium and large automobiles, and the parameter proportional relation between the counterweight and the size needs to establish an inverse functional relation.
3. And (3) improving the details of the hand-held part of the steering wheel. The identification device is hidden under the leather layer of the steering wheel and is used for identifying the gripping force of a user on the steering wheel under different operating environments. The grip force is different often for the user under short time and long-time driving state, and long-time driving, grip force is stronger on the contrary, and identification equipment stimulates the user with the mode of vibrations and relaxs this moment, carries out tired awakening, helps promoting the smoothness nature that the steering wheel controlled.
In the embodiment of the present invention, except for the specific description of the model of each device, the model of other devices is not limited, as long as the device can perform the above functions.
Those skilled in the art will appreciate that the drawings are only schematic illustrations of preferred embodiments, and the above-described embodiments of the present invention are merely provided for description and do not represent the merits of the embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. A method for improving quality of automotive products based on user experience, the method comprising:
user comments on an automobile website are crawled to serve as a demand data source;
analyzing the relation between comment texts based on a demand data source, and formulating a demand decomposition rule;
extracting keywords from the comment text through the semantic similarity graph; classifying the functional elements through sentiment scoring and analysis;
and correspondingly improving the steer-by-wire system, the counterweight, the size and the hand-held part details of the steering wheel based on the classification result.
2. The method for improving the quality of the automobile product based on the user experience of claim 1, wherein the relationship between the comment texts is analyzed based on the demand data source, and the demand decomposition rule is formulated as follows:
abstracting text content into a graph model, and constructing a semantic relation graph triple M<N，E，C>Summarizing the relation between the words, wherein N is a set of nodes, and one node represents a word; e is a set of directed edges, and one edge represents a modification relation among words; c represents the set of text contents after the requirement processing, and WN is used for the nodes i and jiRepresents the weight, WE, of node i(i,j)The weight representing the edge pointing from node i to node j is calculated as follows:
WNinumber of times node i appears in set C
WE(i,j)Number of times node i and node j have a semantic logical relationship
The keywords are screened based on the semantic relation graph, and the formula for calculating the K value of the keywords is as follows
Where i is one of the nodes, d is a balancing factor and satisfies 0< d <1, N is the set of all nodes, s is the set where i points to other points,
n is the number of times i points to the set of other points, the first half of the formula
Representing the importance of the node i to think of itself, the second half
Indicating the importance of other nodes considering node i.
3. The method for improving the quality of automobile products based on user experience according to claim 1, wherein the extracting keywords from the comment text through the semantic similarity map specifically comprises:
the long text is extracted through the core key words and converted into a short text with similar semanteme.
4. The method for improving the quality of automobile products based on user experience according to claim 1, wherein the functional elements are classified by sentiment scoring and analysis, specifically:
decomposing the functions of the existing product to obtain the functional elements, and comparing the functional elements with the functional elements obtained by demand analysis to obtain various new functions of the product so as to meet the demands of users;
classifying the functional elements after emotion scoring according to the dictionary, and dividing the functional elements into the following parts according to the satisfaction degree of the user: positive function, negative function, irrelevant function and newly added function.
5. The method for improving the quality of automobile products based on user experience of claim 4,
the forward function is positively correlated with the user satisfaction, and the emotion score is greater than 0;
the negative function is negatively related to the satisfaction degree of the user, and the emotion score is less than 0;
filtering the irrelevant functions by a Gooseker and then removing the irrelevant functions;
and the newly added function needs to be generated after the set of the positive and negative function elements is removed and compared with the existing function.
6. The method for improving the quality of automobile products based on the user experience as claimed in claim 4 or 5, wherein the positive functions are retained, the negative functions are improved, the irrelevant functions are eliminated, the newly added functions are added and supplemented, and finally the set of target function elements is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010409688.4A CN111724196A (en) | 2020-05-14 | 2020-05-14 | Method for improving quality of automobile product based on user experience |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010409688.4A CN111724196A (en) | 2020-05-14 | 2020-05-14 | Method for improving quality of automobile product based on user experience |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111724196A true CN111724196A (en) | 2020-09-29 |
Family
ID=72564428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010409688.4A Pending CN111724196A (en) | 2020-05-14 | 2020-05-14 | Method for improving quality of automobile product based on user experience |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111724196A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116579633A (en) * | 2023-07-12 | 2023-08-11 | 湖南省计量检测研究院 | Method for realizing quality analysis of service state of wind power equipment based on data driving |
| CN116957633A (en) * | 2023-09-19 | 2023-10-27 | 武汉创知致合科技有限公司 | Product design user experience evaluation method based on intelligent home scene |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107193803A (en) * | 2017-05-26 | 2017-09-22 | 北京东方科诺科技发展有限公司 | A kind of particular task text key word extracting method based on semanteme |
| CN107305539A (en) * | 2016-04-18 | 2017-10-31 | 南京理工大学 | A kind of text tendency analysis method based on Word2Vec network sentiment new word discoveries |
| CN107704503A (en) * | 2017-08-29 | 2018-02-16 | 平安科技（深圳）有限公司 | User's keyword extracting device, method and computer-readable recording medium |
| CN108364199A (en) * | 2018-02-28 | 2018-08-03 | 北京搜狐新媒体信息技术有限公司 | A kind of data analysing method and system based on Internet user's comment |
| CN109408809A (en) * | 2018-09-25 | 2019-03-01 | 天津大学 | A kind of sentiment analysis method for automobile product comment based on term vector |
| CN110442728A (en) * | 2019-06-28 | 2019-11-12 | 天津大学 | Sentiment dictionary construction method based on word2vec automobile product field |
| CN111144929A (en) * | 2019-12-04 | 2020-05-12 | 天津大学 | Comment object and word combined extraction method for automobile industry user generated content |
-
2020
- 2020-05-14 CN CN202010409688.4A patent/CN111724196A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107305539A (en) * | 2016-04-18 | 2017-10-31 | 南京理工大学 | A kind of text tendency analysis method based on Word2Vec network sentiment new word discoveries |
| CN107193803A (en) * | 2017-05-26 | 2017-09-22 | 北京东方科诺科技发展有限公司 | A kind of particular task text key word extracting method based on semanteme |
| CN107704503A (en) * | 2017-08-29 | 2018-02-16 | 平安科技（深圳）有限公司 | User's keyword extracting device, method and computer-readable recording medium |
| CN108364199A (en) * | 2018-02-28 | 2018-08-03 | 北京搜狐新媒体信息技术有限公司 | A kind of data analysing method and system based on Internet user's comment |
| CN109408809A (en) * | 2018-09-25 | 2019-03-01 | 天津大学 | A kind of sentiment analysis method for automobile product comment based on term vector |
| CN110442728A (en) * | 2019-06-28 | 2019-11-12 | 天津大学 | Sentiment dictionary construction method based on word2vec automobile product field |
| CN111144929A (en) * | 2019-12-04 | 2020-05-12 | 天津大学 | Comment object and word combined extraction method for automobile industry user generated content |
Non-Patent Citations (1)
| Title |
|---|
| 王余行: ""基于网络论坛数据的汽车质量问题挖掘研究"", 《中国优秀博硕士学位论文全文数据库（硕士） 工程科技Ⅱ辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116579633A (en) * | 2023-07-12 | 2023-08-11 | 湖南省计量检测研究院 | Method for realizing quality analysis of service state of wind power equipment based on data driving |
| CN116579633B (en) * | 2023-07-12 | 2023-11-17 | 湖南省计量检测研究院 | Method for realizing quality analysis of service state of wind power equipment based on data driving |
| CN116957633A (en) * | 2023-09-19 | 2023-10-27 | 武汉创知致合科技有限公司 | Product design user experience evaluation method based on intelligent home scene |
| CN116957633B (en) * | 2023-09-19 | 2023-12-01 | 武汉创知致合科技有限公司 | Product design user experience evaluation method based on intelligent home scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105740228B (en) | A kind of internet public feelings analysis method and system | |
| Ali et al. | Type-2 fuzzy ontology-based opinion mining and information extraction: A proposal to automate the hotel reservation system | |
| CN109408809A (en) | A kind of sentiment analysis method for automobile product comment based on term vector | |
| CN111724196A (en) | Method for improving quality of automobile product based on user experience | |
| CN103365867A (en) | Method and device for emotion analysis of user evaluation | |
| Du et al. | News text summarization based on multi-feature and fuzzy logic | |
| Singh et al. | Do online consumer reviews help to evaluate the performance of automobile manufacturers? | |
| Seo et al. | Unusual customer response identification and visualization based on text mining and anomaly detection | |
| CN111859962B (en) | Method and device for extracting data required by automobile public praise word cloud | |
| CN109241534A (en) | A kind of examination paper automatic generation method and device based on text AI study | |
| Bryndin | Communicative-associative development of smart artificial intelligence by criteria with the help of ensembles of diversified agents | |
| Cui et al. | Driving event recognition of battery electric taxi based on big data analysis | |
| CN109871486B (en) | Product demand analysis method and system for market-ahead under social media environment | |
| Dwivedi et al. | Sentiment analysis for COVID vaccinations using Twitter: text clustering of positive and negative sentiments | |
| Modoni et al. | A semantic framework for graph-based enterprise search | |
| Buenaño-Fernández et al. | Improvement of massive open online courses by text mining of students' emails: a case study | |
| Katiandhago et al. | Sentiment Analysis of Twitter Cases of Riots at Kanjuruhan Stadium Using the Naive Bayes Method | |
| Guo et al. | Research on user behavior oriented intelligent interactive design of automobile cockpit | |
| CN111611455A (en) | User group division method based on user emotional behavior characteristics under microblog hot topics | |
| Patil et al. | SQL ChatBot–using Context Free Grammar | |
| Sugimoto et al. | Method to assist the building and expression of subjective concepts and its application to design problems | |
| Coatanéa et al. | A prospective analysis of the engineering design discipline evolution based on key influencing trends | |
| Ko et al. | Discovering research areas from patents: A case study in autonomous vehicles industry | |
| Peng et al. | Hybrid collaborative filtering recommendation algorithm for als model based on a big data platform | |
| Yang et al. | Automatic Generation Analysis Method of Automobile Chassis Electronic Control System Based on NLP-intelligent Control Condition |
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: 20200929 |
|
| RJ01 | Rejection of invention patent application after publication |