CN116860969A - Customer comment analysis method, system, equipment and medium - Google Patents
Customer comment analysis method, system, equipment and medium Download PDFInfo
- Publication number
- CN116860969A CN116860969A CN202310812427.0A CN202310812427A CN116860969A CN 116860969 A CN116860969 A CN 116860969A CN 202310812427 A CN202310812427 A CN 202310812427A CN 116860969 A CN116860969 A CN 116860969A
- Authority
- CN
- China
- Prior art keywords
- intermediate data
- emotion
- target
- keywords
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 38
- 230000008451 emotion Effects 0.000 claims abstract description 115
- 238000000605 extraction Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 38
- 239000013598 vector Substances 0.000 claims abstract description 35
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000003860 storage Methods 0.000 claims description 13
- 238000011835 investigation Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 230000002996 emotional effect Effects 0.000 claims 1
- 238000011160 research Methods 0.000 abstract description 3
- 238000012827 research and development Methods 0.000 abstract description 3
- 238000011156 evaluation Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000009849 deactivation Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a method, a system, equipment and a medium for analyzing customer comments, wherein the method comprises the following steps: target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data; extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data; clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters; based on a preset emotion dictionary, performing emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data; and determining the product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster. The research and development personnel can quickly and comprehensively understand the overall evaluation of the customer on the product, can summarize the suggestion and opinion of the customer on the product, and can summarize the trend of the customer on the product demand according to the analyzed emotion characteristics so as to research and develop a new product which meets the requirements of masses.
Description
Technical Field
The application relates to the field of natural language processing, in particular to a method, a system, equipment and a medium for analyzing customer comments.
Background
In recent years, with the development of various software applications, the requirements of users on the content and the functions of the software are higher and higher, and the main way for developers to obtain the comments and suggestions of the users on the products is to feed back the comments of the users. As social media grows explosively on networks (e.g., comments, forum discussions, blogs, microblogs, twitter, comments, and posts on social networking sites), individuals and organizations increasingly use content in these media to make decisions. Today, if one wants to purchase a consumer product, one is no longer limited to soliciting comments from friends and family, because there are many user reviews and discussions about the product on a public forum on the Web, it may no longer be necessary for an organization to conduct questionnaires, polls and focus groups to gather public comments, because there is a large amount of such information available publicly. However, due to the proliferation of various websites, finding and monitoring opinion websites on the web and extracting information therefrom remains a difficult task. Each web site typically contains large points of view, which are not always easily interpreted in lengthy blogs and forum posts. It is difficult for a typical person to identify relevant websites and extract and summarize the views therein. There is therefore a need for an automated emotion analysis system.
However, the research personnel or the client manager reads the feedback of the analysis comments one by one so as to obtain the comments and suggestions of the user, which are too dependent on personal preference and research and development experience and have lower efficiency.
Disclosure of Invention
In order to solve the above problems, the present application proposes a method, apparatus and medium, wherein the method comprises:
target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data; extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data; clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters; based on a preset emotion dictionary, carrying out emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data; and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
In one example, the preprocessing the target comment data to obtain intermediate data and a word vector corresponding to the intermediate data specifically includes: performing word deactivating operation on the target comment data based on a preset stop word list to obtain first intermediate data; deleting the symbol data in the first intermediate data through a regular expression to obtain second intermediate data; the symbol data includes at least one of an error symbol and a network expression; extracting trunk information of the second intermediate data through the expression of a bidirectional encoder based on a transformer, and normalizing the index length; extracting word sequences in the trunk information by using a Bert embedding layer, and converting the word sequences into word vectors.
In one example, the keyword extraction and clustering specifically includes: extracting keywords corresponding to the intermediate data based on a document theme generation model; determining the similarity between the keywords based on the word vectors respectively corresponding to the keywords; and clustering the keywords based on the similarity among the keywords to obtain a first number of keyword extraction clusters.
In one example, the emotion feature analysis specifically includes: determining a preset emotion dictionary, a preset negative word list and a preset degree adverb list; determining emotion scores corresponding to the intermediate data based on emotion words in the intermediate data; determining emotion polarities corresponding to the emotion scores based on negative words and degree adverbs before the emotion words in the intermediate data; and determining emotion characteristic value analysis corresponding to the intermediate data based on the emotion polarity and the emotion score.
In one example, before the emotion feature analysis is performed on the intermediate data based on the preset emotion dictionary, the method further includes: taking the Opinion Lexicon emotion dictionary as an initial emotion dictionary; and expanding the initial emotion dictionary by using an emotion tendency point mutual information algorithm to obtain the preset emotion dictionary.
In one example, the determining the product attribute weight score corresponding to the target product based on the emotion feature value and the keyword extraction cluster specifically includes: determining target keywords corresponding to the target product attributes to extract clusters; determining target keywords contained in the target keyword extraction clusters and target intermediate data containing the target keywords; acquiring emotion characteristic values corresponding to the target intermediate data, and determining cluster weight scores corresponding to the target keyword extraction clusters through the following formula:
wherein R is a cluster weight score, n is the number of target keywords contained in the target keyword extraction cluster, and u i Extracting emotion characteristic values, t, corresponding to the ith target keyword in the cluster for the target keywords i Is u i The corresponding time correction coefficient is related to comment posting time corresponding to the target intermediate data; and weighting the cluster weight scores corresponding to the extraction clusters of the target keywords in the target product attributes respectively to obtain the product attribute weight scores.
In one example, after the determining the product attribute weight score corresponding to the target product, the method further includes: acquiring all target product attributes corresponding to the target product; determining a product investigation report corresponding to the target product based on the product attribute weight scores corresponding to all the target product attributes respectively; and the product investigation report is presented to staff through a report format.
The application also provides a customer comment analysis system, which comprises: the preprocessing module is used for acquiring target comment data and preprocessing the target comment data to obtain intermediate data and word vectors corresponding to the intermediate data; the keyword extraction module is used for extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data; the clustering module clusters the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters; the emotion analysis module is used for carrying out emotion feature analysis on the intermediate data based on a preset emotion dictionary so as to obtain emotion feature values related to each keyword in the intermediate data; and the weight scoring module is used for determining the product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
The application also provides customer comment analysis equipment, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform: target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data; extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data; clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters; based on a preset emotion dictionary, carrying out emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data; and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
The present application also provides a non-volatile computer storage medium storing computer-executable instructions configured to: target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data; extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data; clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters; based on a preset emotion dictionary, carrying out emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data; and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
The method provided by the application has the following beneficial effects: the research and development personnel can quickly and comprehensively understand the overall evaluation of the customer on the product, can summarize the suggestion and opinion of the customer on the product, and can summarize the trend of the customer on the product demand according to the analyzed emotion characteristics so as to research and develop a new product which meets the requirements of masses.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a schematic flow chart of a method for analyzing customer comments in an embodiment of the application;
FIG. 2 is a schematic diagram of a system for analyzing customer comments according to an embodiment of the present application;
fig. 3 is a schematic diagram of a mechanism of a customer comment analysis device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a flow diagram of a method for analyzing customer comments according to one or more embodiments of the present disclosure. The method can be applied to different types of products, such as internet financial products, electronic commerce products, instant messaging products, game products, official products and the like. The process may be performed by a computing device in the corresponding domain (e.g., a wind control server or intelligent mobile terminal corresponding to the payment service, etc.), and certain input parameters or intermediate results in the process allow for manual intervention adjustments to help improve accuracy.
The implementation of the analysis method according to the embodiment of the present application may be a terminal device or a server, which is not particularly limited in the present application. For ease of understanding and description, the following embodiments are described in detail with reference to a server.
It should be noted that the server may be a single device, or may be a system composed of a plurality of devices, that is, a distributed server, which is not particularly limited in the present application.
As shown in fig. 1, an embodiment of the present application provides a method for analyzing customer comments, including:
s101: target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data.
Firstly, target comment data related to a target product is obtained, and the target comment data is preprocessed, so that intermediate data and word vectors corresponding to the intermediate data are obtained. The intermediate data refers to comment data remaining after operations such as cleaning, disabling words, and the like.
In one embodiment, the target comment data may be stored in a storage device of the computer device in advance, and when the comment data of the target product needs to be analyzed, the computer device may select the target comment data from the storage device. Of course, the computer device may also acquire the target comment data from other external devices. For example, the target comment data is stored in the cloud, and when the comment data of the target product is required to be analyzed, the computer device can acquire the target comment data from the cloud, and the acquisition mode of the target comment data is not limited in this embodiment.
In one embodiment, when preprocessing is performed, firstly, a word deactivating operation is required to be performed on target comment data based on a preset deactivation word list so as to obtain first intermediate data, and then symbol data in the first intermediate data can be deleted through a regular expression so as to obtain second intermediate data, wherein the symbol data comprise error symbols, network expression and other symbol data. And extracting trunk information of the second intermediate data through the expression of a bidirectional encoder based on a transformer to obtain intermediate data, normalizing the index length, extracting word sequences in the trunk information by using a Bert embedding layer, and converting the word sequences into word vectors.
S102: and extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data.
S103: and clustering the keywords based on the word vectors corresponding to the keywords to obtain keyword extraction clusters.
In one embodiment, when extracting keywords and clustering, a model may be generated based on a document theme, keywords corresponding to intermediate data are extracted, then similarity between the keywords is determined based on word vectors respectively corresponding to the keywords, and finally clustering operation is performed on the keywords based on the similarity between the keywords, so as to obtain a first number of keyword extraction clusters.
S104: and carrying out emotion feature analysis on the intermediate data based on a preset emotion dictionary so as to obtain emotion feature values related to each keyword in the intermediate data.
In one embodiment, when performing emotion feature value analysis, a preset emotion dictionary, a preset negative word list and a preset degree adverb list are determined first, then emotion scores corresponding to intermediate data are determined based on emotion words in the intermediate data, emotion polarities corresponding to emotion scores are determined based on negative words and degree adverbs before emotion words in the intermediate data, and finally emotion feature value analysis corresponding to the intermediate data is determined based on the emotion polarities and the emotion scores. The final emotion characteristic value has positive and negative scores, and the higher the score is, the more positive the score is, and the lower the score is, the more negative the score is.
In one embodiment, an Opininon Lexicon emotion dictionary is used as an initial emotion dictionary, and the initial emotion dictionary is expanded by using an emotion tendency point mutual information algorithm to obtain a preset emotion dictionary.
S105: and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
In one embodiment, in determining the weight score corresponding to a product attribute, the product attribute to be evaluated is first determined, e.g., the product attribute of the food product may be a packaging attribute, a taste attribute, an appearance attribute, etc. Then determining target keyword extraction clusters corresponding to the target product attributes, wherein the target keyword extraction clusters can correspond to the taste, the sweetness and the like under the taste attributes, and then determining target keywords contained in the target keyword extraction clusters and target intermediate data containing the target keywords. It should be noted that, here, the falling target keyword extraction cluster refers to all keyword extraction clusters corresponding to the target product attribute, the target keyword refers to all keywords in a certain target keyword extraction cluster, and the target intermediate data refers to all intermediate data corresponding to a certain target keyword. And then acquiring emotion characteristic values corresponding to the target intermediate data, and determining a clustering weight score corresponding to the target keyword extraction clustering through the following formula:
wherein R is a cluster weight score, n is the number of target keywords contained in the target keyword extraction cluster, and u i Extracting emotion characteristic values, t, corresponding to the ith target keyword in the cluster for the target keywords i Is u i And the corresponding time correction coefficient is related to comment posting time corresponding to the target intermediate data. It will be appreciated that the closer the comment data is to the current time node, the greater the analysis impact on the target product, and hence the time correction factor is introduced here. And finally, weighting the cluster weight scores corresponding to the extraction clusters of the target keywords in the target product attributes respectively to obtain the product attribute weight scores.
In one embodiment, after the weight scores of all the product attributes of the target product are obtained, in order to facilitate the staff to analyze the product attributes of the target product, an investigation report of the target product can be generated, specifically, all the target product attributes corresponding to the target product need to be obtained first, the product investigation report corresponding to the target product is determined based on the product attribute weight scores corresponding to all the target product attributes respectively, and finally the product investigation report is presented to the staff in a report format.
As shown in fig. 2, the embodiment of the present application further provides a customer comment analysis system, including:
the preprocessing module 201 acquires target comment data, and preprocesses the target comment data to obtain intermediate data and word vectors corresponding to the intermediate data.
The keyword extraction module 202 performs keyword extraction on the intermediate data to obtain keywords corresponding to the intermediate data.
And a clustering module 203, for clustering the keywords based on the word vectors corresponding to the keywords to obtain keyword extraction clusters.
And the emotion analysis module 204 performs emotion feature analysis on the intermediate data based on a preset emotion dictionary to obtain emotion feature values related to each keyword in the intermediate data.
And the weight scoring module 205 is used for determining the product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
As shown in fig. 3, the embodiment of the present application further provides a customer comment analysis device, including:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:
target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data; extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data; clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters; based on a preset emotion dictionary, carrying out emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data; and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
The embodiment of the application also provides a nonvolatile computer storage medium, which stores computer executable instructions, wherein the computer executable instructions are configured to:
target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data; extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data; clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters; based on a preset emotion dictionary, carrying out emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data; and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the apparatus and medium embodiments, the description is relatively simple, as it is substantially similar to the method embodiments, with reference to the section of the method embodiments being relevant.
The devices and media provided in the embodiments of the present application are in one-to-one correspondence with the methods, so that the devices and media also have similar beneficial technical effects as the corresponding methods, and since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media are not repeated here.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (trans itory med i a), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. A method of customer comment analysis, comprising:
target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data;
extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data;
clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters;
based on a preset emotion dictionary, carrying out emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data;
and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
2. The method of claim 1, wherein the preprocessing the target comment data to obtain intermediate data and word vectors corresponding to the intermediate data specifically includes:
performing word deactivating operation on the target comment data based on a preset stop word list to obtain first intermediate data;
deleting the symbol data in the first intermediate data through a regular expression to obtain second intermediate data; the symbol data includes at least one of an error symbol and a network expression;
extracting trunk information of the second intermediate data through the expression of a bidirectional encoder based on a transformer, and normalizing the index length;
extracting word sequences in the trunk information by using a Bert embedding layer, and converting the word sequences into word vectors.
3. The method according to claim 1, wherein the keyword extraction and clustering specifically comprises:
extracting keywords corresponding to the intermediate data based on a document theme generation model;
determining the similarity between the keywords based on the word vectors respectively corresponding to the keywords;
and clustering the keywords based on the similarity among the keywords to obtain a first number of keyword extraction clusters.
4. The method according to claim 1, characterized in that the emotional characteristics analysis specifically comprises:
determining a preset emotion dictionary, a preset negative word list and a preset degree adverb list;
determining emotion scores corresponding to the intermediate data based on emotion words in the intermediate data;
determining emotion polarities corresponding to the emotion scores based on negative words and degree adverbs before the emotion words in the intermediate data;
and determining emotion characteristic value analysis corresponding to the intermediate data based on the emotion polarity and the emotion score.
5. The method of claim 1, wherein prior to emotion feature analysis of the intermediate data based on a preset emotion dictionary, the method further comprises:
taking the Opinion Lexicon emotion dictionary as an initial emotion dictionary;
and expanding the initial emotion dictionary by using an emotion tendency point mutual information algorithm to obtain the preset emotion dictionary.
6. The method according to claim 1, wherein determining a product attribute weight score corresponding to a target product based on the emotion feature value and the keyword extraction cluster specifically comprises:
determining target keywords corresponding to the target product attributes to extract clusters;
determining target keywords contained in the target keyword extraction clusters and target intermediate data containing the target keywords;
acquiring emotion characteristic values corresponding to the target intermediate data, and determining cluster weight scores corresponding to the target keyword extraction clusters through the following formula:
wherein R is a cluster weight score, n is the number of target keywords contained in the target keyword extraction cluster, and u i Extracting emotion characteristic values, t, corresponding to the ith target keyword in the cluster for the target keywords i Is u i The corresponding time correction coefficient is related to comment posting time corresponding to the target intermediate data;
and weighting the cluster weight scores corresponding to the extraction clusters of the target keywords in the target product attributes respectively to obtain the product attribute weight scores.
7. The method of claim 6, wherein after determining the product attribute weight score corresponding to the target product, the method further comprises:
acquiring all target product attributes corresponding to the target product;
determining a product investigation report corresponding to the target product based on the product attribute weight scores corresponding to all the target product attributes respectively;
and the product investigation report is presented to staff through a report format.
8. A customer comment analysis system, comprising:
the preprocessing module is used for acquiring target comment data and preprocessing the target comment data to obtain intermediate data and word vectors corresponding to the intermediate data;
the keyword extraction module is used for extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data;
the clustering module clusters the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters;
the emotion analysis module is used for carrying out emotion feature analysis on the intermediate data based on a preset emotion dictionary so as to obtain emotion feature values related to each keyword in the intermediate data;
and the weight scoring module is used for determining the product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
9. A customer comment analysis apparatus characterized by comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform:
target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data;
extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data;
clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters;
based on a preset emotion dictionary, carrying out emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data;
and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
10. A non-transitory computer storage medium storing computer-executable instructions, the computer-executable instructions configured to:
target comment data are obtained, and preprocessing is carried out on the target comment data so as to obtain intermediate data and word vectors corresponding to the intermediate data;
extracting keywords from the intermediate data to obtain keywords corresponding to the intermediate data;
clustering the keywords based on word vectors corresponding to the keywords to obtain keyword extraction clusters;
based on a preset emotion dictionary, carrying out emotion feature analysis on the intermediate data to obtain emotion feature values related to each keyword in the intermediate data;
and determining a product attribute weight score corresponding to the target product based on the emotion characteristic value and the keyword extraction cluster.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310812427.0A CN116860969A (en) | 2023-07-03 | 2023-07-03 | Customer comment analysis method, system, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310812427.0A CN116860969A (en) | 2023-07-03 | 2023-07-03 | Customer comment analysis method, system, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116860969A true CN116860969A (en) | 2023-10-10 |
Family
ID=88235253
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310812427.0A Pending CN116860969A (en) | 2023-07-03 | 2023-07-03 | Customer comment analysis method, system, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116860969A (en) |
-
2023
- 2023-07-03 CN CN202310812427.0A patent/CN116860969A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9514405B2 (en) | Scoring concept terms using a deep network | |
US9449271B2 (en) | Classifying resources using a deep network | |
US9576075B2 (en) | Context aware query selection | |
CN105989040B (en) | Intelligent question and answer method, device and system | |
US20140172415A1 (en) | Apparatus, system, and method of providing sentiment analysis result based on text | |
US10762150B2 (en) | Searching method and searching apparatus based on neural network and search engine | |
US8719025B2 (en) | Contextual voice query dilation to improve spoken web searching | |
US10073839B2 (en) | Electronically based thesaurus querying documents while leveraging context sensitivity | |
US10706359B2 (en) | Method and system for generating predictive models for scoring and prioritizing leads | |
CN106708871B (en) | Method and device for identifying social service characteristic users | |
CN111143551A (en) | Text preprocessing method, classification method, device and equipment | |
CN112434533B (en) | Entity disambiguation method, entity disambiguation device, electronic device, and computer-readable storage medium | |
CN110795613B (en) | Commodity searching method, device and system and electronic equipment | |
CN110825954A (en) | Keyword recommendation method and device and electronic equipment | |
CN116522912A (en) | Training method, device, medium and equipment for package design language model | |
CN110019702B (en) | Data mining method, device and equipment | |
US11966440B2 (en) | Metadata tag identification | |
CN115795158A (en) | Material sorting and neural network training method, device, equipment and storage medium | |
CN106971306B (en) | Method and system for identifying product problems | |
CN113076450B (en) | Determination method and device for target recommendation list | |
CN116860969A (en) | Customer comment analysis method, system, equipment and medium | |
CN111783453B (en) | Text emotion information processing method and device | |
US10896461B2 (en) | Method and apparatus for data mining based on users' search behavior | |
CN110019771B (en) | Text processing method and device | |
CN112434126A (en) | Information processing method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |