CN115098650B - Comment information analysis method based on historical data model and related device - Google Patents
Comment information analysis method based on historical data model and related device Download PDFInfo
- Publication number
- CN115098650B CN115098650B CN202211028162.7A CN202211028162A CN115098650B CN 115098650 B CN115098650 B CN 115098650B CN 202211028162 A CN202211028162 A CN 202211028162A CN 115098650 B CN115098650 B CN 115098650B
- Authority
- CN
- China
- Prior art keywords
- comment
- entity
- user evaluation
- target
- class
- 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.)
- Active
Links
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Finance (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a comment information analysis method based on a historical data model and a related device, which are used for improving the accuracy of comment information analysis. The method comprises the following steps: acquiring a plurality of historical comment texts of a target commodity class, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; calling an entity extraction model to extract entity information of the standard comment texts to obtain an entity class, and extracting an entity evaluation class from the standard comment texts; inputting the entity class and the entity evaluation class into a comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; extracting a plurality of user evaluation indexes in the user evaluation result, and generating a target commodity value degree according to the plurality of user evaluation indexes; and performing industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a comment information analysis method based on a historical data model and a related device.
Background
With the rapid development of computer technology, the e-commerce industry is also rapidly developed, the e-commerce application program is rapidly developed and intelligent equipment is popularized, and a large number of users share and record own preference information of the users to commodities through a network. The comment data of the user actively shares various information such as own hobbies, moods or opinions to commodities and the like in the e-commerce application program, and the e-commerce application program accurately records browsing tracks and personal interest and hobby information of the user.
According to the existing scheme, personalized services are further provided for the user by analyzing information carried in the comments, a merchant can also know the interest tendency of the user in advance and prepare in advance, but the comment analysis of the existing scheme lacks credibility, namely the accuracy is low.
Disclosure of Invention
The invention provides a comment information analysis method based on a historical data model and a related device, which are used for improving the accuracy of comment information analysis.
The invention provides a comment information analysis method based on a historical data model, which comprises the following steps: receiving a comment information analysis request sent by a terminal, and determining a target commodity type to be analyzed according to the comment information analysis request; acquiring a plurality of historical comment texts of the target commodity category from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting entity evaluation classes corresponding to the entity classes from the standard comment texts; inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing the commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree; and performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining, from a preset e-commerce application program, a plurality of historical comment texts of the target commodity category, and performing standardization and integration processing on the plurality of historical comment texts to obtain a plurality of standard comment texts includes: carrying out cluster processing on comment data in a preset E-commerce application program through a preset cluster algorithm to obtain a comment data set; matching a plurality of historical review texts corresponding to the target commodity category from the review data set; and respectively calculating the relevance of the plurality of historical comment texts and the target commodity category, and deleting the historical comment texts of which the relevance is smaller than a preset threshold value to obtain a plurality of standard comment texts.
Optionally, in a second implementation manner of the first aspect of the present invention, the invoking a preset entity extraction model to extract entity information from the multiple standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting an entity evaluation class corresponding to the entity class from the multiple standard comment texts includes: inputting the plurality of standard comment texts into a preset entity extraction model, wherein the entity extraction model comprises: an encoder and a decoder; performing entity extraction on the plurality of standard comment texts through the encoder to obtain an entity class corresponding to each standard comment text; extracting the relationship of the entity class corresponding to each standard comment text through the decoder to obtain the entity relationship corresponding to each entity class; and extracting an entity evaluation class corresponding to the entity class from the plurality of standard comment texts according to the entity relationship.
Optionally, in a third implementation manner of the first aspect of the present invention, the inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result includes: constructing a user evaluation matrix according to the entity class and the entity evaluation class; inputting the user evaluation matrix into a preset comment information analysis model, and extracting a first interest point corresponding to the user evaluation matrix through the comment information analysis model; searching a second interest point matched with the first interest point through the comment information analysis model; calculating the position information of the first interest point and the second interest point based on a preset user evaluation function, and inquiring a plurality of third interest points corresponding to the first interest point according to the position information; determining weights corresponding to the first interest point, the second interest point and the third interest point according to the user evaluation matrix, and generating a target sequence according to the weights; and comparing the weights in the target sequence, extracting a public interest point from the target sequence, and generating a user evaluation result according to the public interest point.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the extracting multiple user evaluation indexes in the user evaluation result, and performing commodity value degree analysis on the target commodity category according to the multiple user evaluation indexes to obtain a target commodity value degree includes: extracting user evaluation indexes from the user evaluation result to obtain a plurality of user evaluation indexes; carrying out commodity value degree grading on the target commodity category according to the user evaluation indexes to obtain a plurality of value degree grades; and carrying out normalization processing on the multiple value degree scores to generate the value degree of the target commodity corresponding to the target commodity category.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the target commodity value degree to obtain an industry trend prediction result includes: performing industry classification matching on the target commodity category based on a preset industry classification library to obtain a target industry corresponding to the target commodity category; inputting the value degree of the target commodity into a preset trend analysis model, and predicting the interest of the target industry through the trend analysis model to obtain the interest of the target user; and generating an industry trend prediction result corresponding to the target industry according to the target user interest.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the method for analyzing comment information based on a historical data model further includes: commenting and monitoring the target commodity category according to the industry trend prediction result to obtain comment monitoring data; adjusting the prediction result of the industry trend prediction result according to the comment monitoring data to obtain an optimized prediction result; and generating an operation combination scheme corresponding to the target commodity category according to the optimization prediction result.
A second aspect of the present invention provides a comment information analysis apparatus based on a history data model, including: the receiving module is used for receiving a comment information analysis request sent by a terminal and determining a target commodity type to be analyzed according to the comment information analysis request; the acquisition module is used for acquiring a plurality of historical comment texts of the target commodity category from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; the extraction module is used for calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text and extracting an entity evaluation class corresponding to the entity class from the standard comment texts; the analysis module is used for inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; the processing module is used for extracting a plurality of user evaluation indexes in the user evaluation result and analyzing the commodity value degree of the target commodity category according to the user evaluation indexes to obtain the target commodity value degree; and the prediction module is used for carrying out industry classification on the target commodity class to obtain a target industry and carrying out industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result.
Optionally, in a first implementation manner of the second aspect of the present invention, the obtaining module is specifically configured to: carrying out cluster processing on comment data in a preset E-commerce application program through a preset cluster algorithm to obtain a comment data set; matching a plurality of historical review texts corresponding to the target commodity category from the review data set; and respectively calculating the relevance of the plurality of historical comment texts and the target commodity category, and deleting the historical comment texts of which the relevance is smaller than a preset threshold value to obtain a plurality of standard comment texts.
Optionally, in a second implementation manner of the second aspect of the present invention, the extraction module is specifically configured to: inputting the plurality of standard comment texts into a preset entity extraction model, wherein the entity extraction model comprises: an encoder and a decoder; performing entity extraction on the plurality of standard comment texts through the encoder to obtain an entity class corresponding to each standard comment text; extracting the relationship of the entity class corresponding to each standard comment text through the decoder to obtain the entity relationship corresponding to each entity class; and extracting an entity evaluation class corresponding to the entity class from the plurality of standard comment texts according to the entity relationship.
Optionally, in a third implementation manner of the second aspect of the present invention, the analysis module is specifically configured to: constructing a user evaluation matrix according to the entity class and the entity evaluation class; inputting the user evaluation matrix into a preset comment information analysis model, and extracting a first interest point corresponding to the user evaluation matrix through the comment information analysis model; searching a second interest point matched with the first interest point through the comment information analysis model; calculating the position information of the first interest point and the second interest point based on a preset user evaluation function, and inquiring a plurality of third interest points corresponding to the first interest point according to the position information; determining weights corresponding to the first interest point, the second interest point and the third interest point according to the user evaluation matrix, and generating a target sequence according to the weights; and comparing the weights in the target sequence, extracting a public interest point from the target sequence, and generating a user evaluation result according to the public interest point.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the processing module is specifically configured to: extracting user evaluation indexes from the user evaluation result to obtain a plurality of user evaluation indexes; carrying out commodity value degree grading on the target commodity category according to the user evaluation indexes to obtain a plurality of value degree grades; and carrying out normalization processing on the multiple value degree scores to generate the value degree of the target commodity corresponding to the target commodity category.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the prediction module is specifically configured to: performing industry classification matching on the target commodity category based on a preset industry classification library to obtain a target industry corresponding to the target commodity category; inputting the value degree of the target commodity into a preset trend analysis model, and predicting the interest of the target industry through the trend analysis model to obtain the interest of the target user; and generating an industry trend prediction result corresponding to the target industry according to the target user interest.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the comment information analysis apparatus based on a historical data model further includes: the monitoring module is used for commenting and monitoring the target commodity category according to the industry trend prediction result to obtain commenting and monitoring data; adjusting the prediction result of the industry trend prediction result according to the comment monitoring data to obtain an optimized prediction result; and generating an operation combination scheme corresponding to the target commodity category according to the optimization prediction result.
A third aspect of the present invention provides a comment information analyzing apparatus based on a history data model, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the historical data model-based comment information analysis device to perform the historical data model-based comment information analysis method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to execute the above-described comment information analysis method based on a historical data model.
In the technical scheme provided by the invention, a comment information analysis request sent by a terminal is received, and a target commodity class to be analyzed is determined according to the comment information analysis request; acquiring a plurality of historical comment texts of the target commodity category from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting entity evaluation classes corresponding to the entity classes from the standard comment texts; inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing the commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree; and performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result. According to the method, the entity class and the entity evaluation class in the historical comment text are analyzed, the comment viewpoints of the user are extracted and classified through the pre-constructed comment information analysis model, the user evaluation result is obtained, the trend prediction is performed on the industry through the user evaluation result, and the accuracy of comment information analysis is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a comment information analysis method based on a historical data model in the embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a comment information analysis method based on a historical data model in the embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a comment information analysis apparatus based on a historical data model in the embodiment of the present invention;
FIG. 4 is a schematic diagram of another embodiment of a comment information analysis apparatus based on a historical data model in the embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of a comment information analysis device based on a historical data model in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a comment information analysis method based on a historical data model and a related device, which are used for improving the accuracy of comment information analysis. The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a review information analysis method based on a historical data model in an embodiment of the present invention includes:
101. receiving a comment information analysis request sent by a terminal, and determining a target commodity type to be analyzed according to the comment information analysis request;
it is to be understood that the execution subject of the present invention may be a comment information analysis apparatus based on a historical data model, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
It should be noted that the comment information analysis request is sent through a preset information comment terminal, where the information comment terminal may be a terminal such as a mobile phone or a tablet computer, and the server scans the information comment request to determine a corresponding comment identifier, and then the server obtains a corresponding download link from a comment information database according to the information identifier, and then the server obtains corresponding comment information according to the download link, and then the server performs word segmentation processing on the comment information to determine corresponding keyword information, and then the server performs commodity category matching on the keyword information to determine a target commodity category to be analyzed.
102. Acquiring a plurality of historical comment texts of a target commodity class from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts;
specifically, the server collects attribute embedded vectors corresponding to a plurality of commodities in advance, and obtains a plurality of historical comment texts of a target commodity class from a preset e-commerce application program, it needs to be explained that comment data are collected through a preset clustering algorithm, then vector generation processing is performed on the plurality of historical comment texts, a comment embedded vector corresponding to each historical comment text is obtained, then comment embedded vectors corresponding to the target commodity classes corresponding to the plurality of historical comment texts and the commodity attribute embedded vectors are fused and spliced, corresponding commodity embedded vectors are obtained, and then the server standardizes and integrates the plurality of historical comment texts according to the commodity embedded vectors, so that a plurality of standard comment texts are obtained.
103. Calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting an entity evaluation class corresponding to the entity class from the standard comment texts;
specifically, the server performs sentence division processing on the plurality of standard comment texts, removes repeated sentences, and counts relationships or entity categories in the standard comment texts, it needs to be noted that in the embodiment of the present invention, entity information is extracted according to a preset entity extraction model, a subsequent server performs construction of a category mapping dictionary, keywords are category names, and key values are corresponding category IDs.
104. Inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result;
specifically, the server inputs an entity class and an entity evaluation class into a comment information analysis model for viewpoint analysis, wherein the server determines corresponding topic classification according to the entity class and the entity evaluation class, establishes a user evaluation matrix according to the topic classification, accumulatively calculates the weight sum of each topic classification in domain time, calculates interest points according to the user evaluation matrix, generates a target sequence according to the calculated interest points and the weight sum, extracts public interest points through the target sequence, and generates a user evaluation result according to the public interest points.
105. Extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree;
it should be noted that, in order to obtain a more accurate value, evaluation index analysis needs to be performed on a user evaluation result, after a plurality of evaluation indexes corresponding to the user evaluation result are obtained, the server determines a weight value corresponding to each evaluation index according to the plurality of evaluation indexes, determines a corresponding preset configuration table according to each evaluation index, further performs value grading on a target commodity class according to the preset configuration table, determines a plurality of value grades to obtain a plurality of value grades, and finally performs linear conversion on the plurality of value grades to generate a target commodity value corresponding to the target commodity class.
106. And performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result.
Specifically, the server subdivides target commodity categories according to industry categories by using a k-means algorithm, loads commodity sales data of different industries into different data tables respectively to form an industry promotion historical database,
the method comprises the steps of using a data mining algorithm, taking the change percentage ratio of sales volume after sales promotion as a prediction target, respectively establishing trend analysis models for predicting the trend of commodities for different industries, using industry sales promotion data in an industry sales promotion historical database as model training data, inputting the related plan information of commodities to be promoted, including the number of the commodities to be promoted, the expected sales volume promotion of the commodities, the approximate time period of the sales promotion and the like, as input conditions into the prediction model according to the customized requirements of a user, and then carrying out industry trend prediction on the target industry by a server according to the value degree of the target commodities to obtain an industry trend prediction result.
In the embodiment of the invention, a comment information analysis request sent by a terminal is received, and a target commodity class to be analyzed is determined according to the comment information analysis request; acquiring a plurality of historical comment texts of a target commodity class from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting an entity evaluation class corresponding to the entity class from the standard comment texts; inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing the commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree; and performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result. According to the method, the entity class and the entity evaluation class in the historical comment text are analyzed, the comment viewpoints of the user are extracted and classified through the pre-constructed comment information analysis model, the user evaluation result is obtained, the trend prediction is performed on the industry through the user evaluation result, and the accuracy of comment information analysis is improved.
Referring to fig. 2, another embodiment of the review information analysis method based on the historical data model according to the embodiment of the present invention includes:
201. receiving a comment information analysis request sent by a terminal, and determining a target commodity type to be analyzed according to the comment information analysis request;
specifically, in this embodiment, the specific implementation of step 201 is similar to that of step 101, and is not described herein again.
202. Acquiring a plurality of historical comment texts of a target commodity class from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts;
specifically, the server performs clustering processing on comment data in a preset e-commerce application program through a preset clustering algorithm to obtain a comment data set; the server matches a plurality of historical comment texts corresponding to the target commodity category from the comment data set; and the server respectively calculates the relevance of the plurality of historical comment texts and the target commodity category, and deletes the historical comment texts with the relevance smaller than a preset threshold value to obtain a plurality of standard comment texts.
The server is accessed to the e-commerce application program to obtain a large amount of comment data information, and then the server performs cluster processing on the large amount of comment data information, it needs to be stated that a cluster algorithm in the embodiment of the present invention refers to a K-means algorithm, and the K-means algorithm generally refers to a K-means cluster algorithm.
203. Calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting entity evaluation classes corresponding to the entity classes from the standard comment texts;
specifically, the server inputs a plurality of standard comment texts into a preset entity extraction model, wherein the entity extraction model comprises: an encoder and a decoder; the server performs entity extraction on the plurality of standard comment texts through an encoder to obtain an entity class corresponding to each standard comment text; the server extracts the relation of the entity class corresponding to each standard comment text through a decoder to obtain the entity relation corresponding to each entity class; and the server extracts an entity evaluation class corresponding to the entity class from the plurality of standard comment texts according to the entity relationship.
The server converts an entity relationship into a template in a preset form, the template contains semantic information of fine granularity of the entity relationship, the server inserts marks into starting and ending positions, the entity relationship is extracted and converted into a filling-in form, so that a head entity and a tail entity are extracted, a subsequent server copies the relationship template for multiple times to extract the head entity, the relationship and the tail entity, the server performs entity extraction on a plurality of standard comment texts through an encoder to obtain an entity class corresponding to each standard comment text, the entity class comprises commodity entity classes such as a food commodity class and a daily commodity class, the server performs word segmentation processing on a plurality of standard comment texts after sentence segmentation through an entity extraction model to obtain target word segmentation, the marks are inserted into the starting position of a sentence, the positions of the head entity and the tail entity are updated to obtain positions after word segmentation, the server inputs the sentence after word segmentation to an encoder end to obtain corresponding vectors, the output of the encoder is subjected to two neural networks, the obtained result is used for identifying the entity, the other result is used for extracting a decoder corresponding entity class corresponding to obtain a corresponding entity relationship, and each entity comment decoder passes through the corresponding decoder; and the server extracts an entity evaluation class corresponding to the entity class from the plurality of standard comment texts according to the entity relationship.
204. Inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result;
specifically, the server constructs a user evaluation matrix according to the entity class and the entity evaluation class; inputting the user evaluation matrix into a preset comment information analysis model, and extracting a first interest point corresponding to the user evaluation matrix through the comment information analysis model; searching a second interest point matched with the first interest point through the comment information analysis model; calculating the position information of the first interest point and the second interest point based on a preset user evaluation function, and inquiring a plurality of third interest points corresponding to the first interest point according to the position information; determining weights corresponding to the first interest point, the second interest point and the third interest point according to the user evaluation matrix, and generating a target sequence according to the weights; and comparing the weights in the target sequence, extracting a common interest point from the target sequence, and generating a user evaluation result according to the common interest point.
Specifically, the server constructs a user evaluation matrix according to the entity class and the entity evaluation class, and inputs the user evaluation matrix into a preset comment information analysis model, it should be noted that the server acquires and labels training data, converts the training data into a feature vector set, quantifies interest occupation ratio of topic classification, and generates a comment information analysis model, wherein the specific processes of acquiring and labeling the training data are as follows: collecting page data from a data source using a web crawler; extracting text data from the collected page data; setting a plurality of interest categories according to the extracted text data, adding a label to each interest category, and searching a second interest point matched with the first interest point by a subsequent server through a comment information analysis model; calculating the position information of the first interest point and the second interest point based on a preset user evaluation function, and inquiring a plurality of third interest points corresponding to the first interest point according to the position information; determining weights corresponding to the first interest point, the second interest point and the third interest point according to the user evaluation matrix, and generating a target sequence according to the weights; and comparing the weights in the target sequence, extracting a common interest point from the target sequence, and generating a user evaluation result according to the common interest point.
205. Extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing the commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree;
specifically, the server extracts user evaluation indexes from the user evaluation result to obtain a plurality of user evaluation indexes; carrying out commodity value degree grading on the target commodity category according to the plurality of user evaluation indexes to obtain a plurality of value degree grades; and carrying out normalization processing on the multiple value degree scores to generate the value degree of the target commodity corresponding to the target commodity category.
Determining an evaluation index corresponding to each commodity object according to the commodity objects in the user evaluation result; counting label indexes corresponding to all the evaluation indexes, wherein the label indexes comprise core indexes and are statistical values obtained by carrying out weighted statistics on designated access behavior data indexes formed by all the commodity objects with the evaluation indexes at a plurality of historical times; determining the sorting score of each commodity object according to the evaluation index set of each commodity object, and performing commodity value degree grading on a target commodity class according to a plurality of user evaluation indexes to obtain a plurality of value degree grades, wherein the sorting score is the weighted sum of the label indexes corresponding to all the evaluation indexes of the commodity object; and carrying out normalization processing on the multiple value degree scores to generate the value degree of the target commodity corresponding to the target commodity category.
206. Performing industry classification matching on the target commodity category based on a preset industry classification library to obtain a target industry corresponding to the target commodity category;
207. inputting the value degree of the target commodity into a preset trend analysis model, and predicting the interest of a user in a target industry through the trend analysis model to obtain the interest of the target user;
specifically, the characteristic words of a target commodity class are obtained, an initial industry label corresponding to text information to be classified is obtained according to the characteristic words and a pre-established industry characteristic word library, an iterative model is established according to known text information of known industry classifications, the text information to be classified and the corresponding initial industry label, industry label probabilities of the text information to be classified corresponding to each industry label in the initial industry labels are obtained according to the iterative model, and the industry classification corresponding to the text information to be classified is determined from the initial industry labels according to the industry label probabilities. The text information to be classified is classified through iteration, the classification efficiency of the text information is remarkably improved, the server inputs the value degree of the target commodity into a preset trend analysis model, and user interest prediction is carried out on the target industry through the trend analysis model to obtain the target user interest.
208. And generating an industry trend prediction result corresponding to the target industry according to the target user interest.
Specifically, the server carries out comment monitoring on the target commodity category according to the industry trend prediction result to obtain comment monitoring data; adjusting the prediction result of the industry trend prediction result according to the comment monitoring data to obtain an optimized prediction result; and generating an operation combination scheme corresponding to the target commodity class according to the optimized prediction result.
For example, when the user may possibly generate bad comments, the forecast bad comments are transmitted to a comment processing terminal in time, industry trend forecast is performed according to the forecast bad comments to obtain a corresponding industry trend forecast result, the industry trend forecast result is adjusted to obtain an optimized forecast result, and finally the server generates an operation combination scheme corresponding to the target commodity category according to the optimized forecast result.
In the embodiment of the invention, a comment information analysis request sent by a terminal is received, and a target commodity category to be analyzed is determined according to the comment information analysis request; acquiring a plurality of historical comment texts of a target commodity class from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting an entity evaluation class corresponding to the entity class from the standard comment texts; inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing the commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree; and performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result. According to the method, the entity class and the entity evaluation class in the historical comment text are analyzed, the comment viewpoints of the user are extracted and classified through the pre-constructed comment information analysis model, the user evaluation result is obtained, the trend prediction is performed on the industry through the user evaluation result, and the accuracy of comment information analysis is improved.
In the above description of the comment information analysis method based on the historical data model in the embodiment of the present invention, referring to fig. 3, a comment information analysis apparatus based on the historical data model in the embodiment of the present invention is described below, and an embodiment of the comment information analysis apparatus based on the historical data model in the embodiment of the present invention includes:
the receiving module 301 is configured to receive a comment information analysis request sent by a terminal, and determine a target commodity category to be analyzed according to the comment information analysis request;
an obtaining module 302, configured to obtain multiple historical comment texts of the target product category from a preset e-commerce application program, and perform standardization and integration processing on the multiple historical comment texts to obtain multiple standard comment texts;
the extracting module 303 is configured to invoke a preset entity extraction model to extract entity information from the multiple standard comment texts, obtain an entity class corresponding to each standard comment text, and extract an entity evaluation class corresponding to the entity class from the multiple standard comment texts;
the analysis module 304 is configured to input the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis, so as to obtain a user evaluation result;
the processing module 305 is configured to extract a plurality of user evaluation indexes in the user evaluation result, and perform commodity value degree analysis on the target commodity category according to the plurality of user evaluation indexes to obtain a target commodity value degree;
and the prediction module 306 is used for performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the target commodity value degree to obtain an industry trend prediction result.
In the embodiment of the invention, a comment information analysis request sent by a terminal is received, and a target commodity class to be analyzed is determined according to the comment information analysis request; acquiring a plurality of historical comment texts of the target commodity class from a preset e-commerce application program, and carrying out standardization and integration processing on the plurality of historical comment texts to obtain a plurality of standard comment texts; calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting entity evaluation classes corresponding to the entity classes from the standard comment texts; inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing the commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree; and performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result. According to the method, the entity class and the entity evaluation class in the historical comment text are analyzed, the comment viewpoints of the user are extracted and classified through the pre-constructed comment information analysis model, the user evaluation result is obtained, the trend prediction is performed on the industry through the user evaluation result, and the accuracy of comment information analysis is improved.
Referring to fig. 4, another embodiment of the comment information analysis apparatus based on a historical data model according to the embodiment of the present invention includes:
the receiving module 301 is configured to receive a comment information analysis request sent by a terminal, and determine a target commodity category to be analyzed according to the comment information analysis request;
the obtaining module 302 is configured to obtain a plurality of historical comment texts of the target product category from a preset e-commerce application program, and perform standardization and integration processing on the plurality of historical comment texts to obtain a plurality of standard comment texts;
the extracting module 303 is configured to invoke a preset entity extraction model to extract entity information from the multiple standard comment texts, obtain an entity class corresponding to each standard comment text, and extract an entity evaluation class corresponding to the entity class from the multiple standard comment texts;
the analysis module 304 is configured to input the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis, so as to obtain a user evaluation result;
the processing module 305 is configured to extract a plurality of user evaluation indexes in the user evaluation result, and perform commodity value degree analysis on the target commodity category according to the plurality of user evaluation indexes to obtain a target commodity value degree;
and the prediction module 306 is used for performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the target commodity value degree to obtain an industry trend prediction result.
Optionally, the obtaining module 302 is specifically configured to: carrying out cluster processing on comment data in a preset E-commerce application program through a preset cluster algorithm to obtain a comment data set; matching a plurality of historical review texts corresponding to the target commodity category from the review data set; and respectively calculating the relevance of the plurality of historical comment texts and the target commodity category, and deleting the historical comment texts of which the relevance is smaller than a preset threshold value to obtain a plurality of standard comment texts.
Optionally, the extracting module 303 is specifically configured to: inputting the plurality of standard comment texts into a preset entity extraction model, wherein the entity extraction model comprises: an encoder and a decoder; performing entity extraction on the plurality of standard comment texts through the encoder to obtain an entity class corresponding to each standard comment text; extracting the relationship of the entity class corresponding to each standard comment text through the decoder to obtain the entity relationship corresponding to each entity class; and extracting entity evaluation classes corresponding to the entity classes from the plurality of standard comment texts according to the entity relations.
Optionally, the analysis module 304 is specifically configured to: constructing a user evaluation matrix according to the entity class and the entity evaluation class; inputting the user evaluation matrix into a preset comment information analysis model, and extracting a first interest point corresponding to the user evaluation matrix through the comment information analysis model; searching a second interest point matched with the first interest point through the comment information analysis model; calculating the position information of the first interest point and the second interest point based on a preset user evaluation function, and inquiring a plurality of third interest points corresponding to the first interest point according to the position information; determining weights corresponding to the first interest point, the second interest point and the third interest point according to the user evaluation matrix, and generating a target sequence according to the weights; and comparing the weights in the target sequence, extracting a public interest point from the target sequence, and generating a user evaluation result according to the public interest point.
Optionally, the processing module 305 is specifically configured to: extracting user evaluation indexes from the user evaluation result to obtain a plurality of user evaluation indexes; carrying out commodity value degree grading on the target commodity category according to the user evaluation indexes to obtain a plurality of value degree grades; and carrying out normalization processing on the multiple value degree scores to generate the value degree of the target commodity corresponding to the target commodity category.
Optionally, the prediction module 306 is specifically configured to: performing industry classification matching on the target commodity category based on a preset industry classification library to obtain a target industry corresponding to the target commodity category; inputting the value degree of the target commodity into a preset trend analysis model, and predicting the interest of the target industry through the trend analysis model to obtain the interest of the target user; and generating an industry trend prediction result corresponding to the target industry according to the target user interest.
Optionally, the comment information analysis apparatus based on the historical data model further includes: the monitoring module 307 is configured to perform comment monitoring on the target commodity category according to the industry trend prediction result to obtain comment monitoring data; adjusting the prediction result of the industry trend prediction result according to the comment monitoring data to obtain an optimized prediction result; and generating an operation combination scheme corresponding to the target commodity category according to the optimization prediction result.
In the embodiment of the invention, a comment information analysis request sent by a terminal is received, and a target commodity class to be analyzed is determined according to the comment information analysis request; acquiring a plurality of historical comment texts of the target commodity category from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting entity evaluation classes corresponding to the entity classes from the standard comment texts; inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing the commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree; and performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the target commodity value degree to obtain an industry trend prediction result. According to the method, the entity class and the entity evaluation class in the historical comment text are analyzed, the comment viewpoints of the user are extracted and classified through the pre-constructed comment information analysis model, the user evaluation result is obtained, the trend prediction is performed on the industry through the user evaluation result, and the accuracy of comment information analysis is improved.
Fig. 3 and 4 describe the comment information analysis device based on the historical data model in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the comment information analysis device based on the historical data model in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a comment information analyzing apparatus based on a historical data model according to an embodiment of the present invention, where the comment information analyzing apparatus 500 based on a historical data model may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing an application 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations in the comment information analyzing apparatus 500 based on the historical data model. Still further, the processor 510 may be configured to communicate with the storage medium 530, and execute a series of instruction operations in the storage medium 530 on the review information analysis device 500 based on the historical data model.
The review information analysis device 500 based on the historical data model may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, mac OS X, unix, linux, freeBSD, and the like. Those skilled in the art will appreciate that the structure of the comment information analyzing apparatus based on the historical data model shown in fig. 5 does not constitute a limitation of the comment information analyzing apparatus based on the historical data model, and may include more or less components than those shown in the figure, or some components in combination, or a different arrangement of components.
The invention also provides a comment information analysis device based on a historical data model, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the comment information analysis method based on the historical data model in the above embodiments.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and may also be a volatile computer-readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the method for analyzing review information based on a historical data model.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A comment information analysis method based on a historical data model is characterized by comprising the following steps:
receiving a comment information analysis request sent by a terminal, and determining a target commodity type to be analyzed according to the comment information analysis request;
acquiring a plurality of historical comment texts of the target commodity category from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; the method for obtaining the multiple historical comment texts of the target commodity category from the preset e-commerce application program and standardizing and integrating the multiple historical comment texts to obtain multiple standard comment texts comprises the following steps: carrying out cluster processing on comment data in a preset E-commerce application program through a preset cluster algorithm to obtain a comment data set; matching a plurality of historical comment texts corresponding to the target commodity category from the comment data set; respectively calculating the relevance of the plurality of historical comment texts and the target commodity category, and deleting the historical comment texts of which the relevance is smaller than a preset threshold value to obtain a plurality of standard comment texts;
calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting entity evaluation classes corresponding to the entity classes from the standard comment texts;
inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; the method for analyzing the user evaluation viewpoints by inputting the entity classes and the entity evaluation classes into a preset comment information analysis model to obtain user evaluation results includes: constructing a user evaluation matrix according to the entity class and the entity evaluation class; inputting the user evaluation matrix into a preset comment information analysis model, and extracting a first interest point corresponding to the user evaluation matrix through the comment information analysis model; searching a second interest point matched with the first interest point through the comment information analysis model; calculating the position information of the first interest point and the second interest point based on a preset user evaluation function, and inquiring a plurality of third interest points corresponding to the first interest point according to the position information; determining weights corresponding to the first interest point, the second interest point and the third interest point according to the user evaluation matrix, and generating a target sequence according to the weights; comparing the weights in the target sequence, extracting a public interest point from the target sequence, and generating a user evaluation result according to the public interest point;
extracting a plurality of user evaluation indexes in the user evaluation result, and analyzing the commodity value degree of the target commodity class according to the user evaluation indexes to obtain the target commodity value degree;
and performing industry classification on the target commodity category to obtain a target industry, and performing industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result.
2. The method for analyzing comment information based on a historical data model according to claim 1, wherein the step of calling a preset entity extraction model to extract entity information from the plurality of standard comment texts to obtain an entity class corresponding to each standard comment text, and extracting an entity evaluation class corresponding to the entity class from the plurality of standard comment texts comprises:
inputting the plurality of standard comment texts into a preset entity extraction model, wherein the entity extraction model comprises: an encoder and a decoder;
performing entity extraction on the plurality of standard comment texts through the encoder to obtain an entity class corresponding to each standard comment text;
extracting the relationship of the entity class corresponding to each standard comment text through the decoder to obtain the entity relationship corresponding to each entity class;
and extracting an entity evaluation class corresponding to the entity class from the plurality of standard comment texts according to the entity relationship.
3. The method for analyzing comment information based on a historical data model according to claim 1, wherein the extracting a plurality of user evaluation indexes in the user evaluation result and analyzing the commodity value degree of the target commodity category according to the plurality of user evaluation indexes to obtain a target commodity value degree comprises:
extracting user evaluation indexes from the user evaluation result to obtain a plurality of user evaluation indexes;
carrying out commodity value degree grading on the target commodity category according to the user evaluation indexes to obtain a plurality of value degree grades;
and carrying out normalization processing on the multiple value degree scores to generate the value degree of the target commodity corresponding to the target commodity category.
4. The method for analyzing the comment information based on the historical data model according to claim 1, wherein the step of performing industry classification on the target commodity category to obtain a target industry and performing industry trend prediction on the target industry according to the target commodity value degree to obtain an industry trend prediction result comprises the steps of:
performing industry classification matching on the target commodity class based on a preset industry classification library to obtain a target industry corresponding to the target commodity class;
inputting the value degree of the target commodity into a preset trend analysis model, and predicting the interest of the target industry through the trend analysis model to obtain the interest of the target user;
and generating an industry trend prediction result corresponding to the target industry according to the target user interest.
5. The historical data model-based comment information analysis method according to any one of claims 1 to 4, wherein the historical data model-based comment information analysis method further includes:
commenting and monitoring the target commodity category according to the industry trend prediction result to obtain comment monitoring data;
adjusting the prediction result of the industry trend prediction result according to the comment monitoring data to obtain an optimized prediction result;
and generating an operation combination scheme corresponding to the target commodity category according to the optimization prediction result.
6. A comment information analysis apparatus based on a history data model is characterized by comprising:
the receiving module is used for receiving a comment information analysis request sent by a terminal and determining a target commodity class to be analyzed according to the comment information analysis request;
the acquisition module is used for acquiring a plurality of historical comment texts of the target commodity category from a preset e-commerce application program, and standardizing and integrating the plurality of historical comment texts to obtain a plurality of standard comment texts; the method for obtaining the multiple historical comment texts of the target commodity category from the preset e-commerce application program and standardizing and integrating the multiple historical comment texts to obtain the multiple standard comment texts comprises the following steps: carrying out cluster processing on comment data in a preset E-commerce application program through a preset cluster algorithm to obtain a comment data set; matching a plurality of historical review texts corresponding to the target commodity category from the review data set; respectively calculating the relevance of the plurality of historical comment texts and the target commodity category, and deleting the historical comment texts of which the relevance is smaller than a preset threshold value to obtain a plurality of standard comment texts;
the extraction module is used for calling a preset entity extraction model to extract entity information of the standard comment texts to obtain an entity class corresponding to each standard comment text and extracting an entity evaluation class corresponding to the entity class from the standard comment texts;
the analysis module is used for inputting the entity class and the entity evaluation class into a preset comment information analysis model for user evaluation viewpoint analysis to obtain a user evaluation result; the method for analyzing the user evaluation viewpoint by inputting the entity class and the entity evaluation class into a preset comment information analysis model to obtain a user evaluation result includes: constructing a user evaluation matrix according to the entity class and the entity evaluation class; inputting the user evaluation matrix into a preset comment information analysis model, and extracting a first interest point corresponding to the user evaluation matrix through the comment information analysis model; searching a second interest point matched with the first interest point through the comment information analysis model; calculating the position information of the first interest point and the second interest point based on a preset user evaluation function, and inquiring a plurality of third interest points corresponding to the first interest point according to the position information; determining weights corresponding to the first interest point, the second interest point and the third interest point according to the user evaluation matrix, and generating a target sequence according to the weights; comparing the weights in the target sequence, extracting a public interest point from the target sequence, and generating a user evaluation result according to the public interest point;
the processing module is used for extracting a plurality of user evaluation indexes in the user evaluation result and analyzing the commodity value degree of the target commodity category according to the user evaluation indexes to obtain the target commodity value degree;
and the prediction module is used for carrying out industry classification on the target commodity class to obtain a target industry and carrying out industry trend prediction on the target industry according to the value degree of the target commodity to obtain an industry trend prediction result.
7. A comment information analysis apparatus based on a history data model, characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the historical data model-based opinion information analysis device to perform the historical data model-based opinion information analysis method of any of claims 1-5.
8. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the method for historical data model-based review information analysis of any of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211028162.7A CN115098650B (en) | 2022-08-25 | 2022-08-25 | Comment information analysis method based on historical data model and related device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211028162.7A CN115098650B (en) | 2022-08-25 | 2022-08-25 | Comment information analysis method based on historical data model and related device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115098650A CN115098650A (en) | 2022-09-23 |
CN115098650B true CN115098650B (en) | 2022-11-04 |
Family
ID=83300162
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211028162.7A Active CN115098650B (en) | 2022-08-25 | 2022-08-25 | Comment information analysis method based on historical data model and related device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115098650B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115827821B (en) * | 2022-11-11 | 2024-01-09 | 深圳市今古科技有限公司 | Judgment strategy generation method and system based on information |
CN115860783B (en) * | 2022-12-23 | 2023-09-26 | 广东南粤分享汇控股有限公司 | E-commerce platform user feedback analysis method and system based on artificial intelligence |
CN116894684B (en) * | 2023-09-11 | 2023-11-24 | 山东商业职业技术学院 | Big data-based computer data processing method and system |
CN117455059A (en) * | 2023-11-06 | 2024-01-26 | 深圳市乐思软件技术有限公司 | Industry trend evaluation system based on data acquisition |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101498375B1 (en) * | 2013-08-09 | 2015-03-13 | 경희대학교 산학협력단 | Method for estimating content considering user value and user profile |
CN104281890A (en) * | 2014-10-08 | 2015-01-14 | 电子科技大学 | Method and system for predicting fashion products in e-commerce system |
US11295353B2 (en) * | 2015-07-27 | 2022-04-05 | Kayhan Kucukcakar | Collaborative peer review search system and method of use |
CN107220352B (en) * | 2017-05-31 | 2020-12-08 | 北京百度网讯科技有限公司 | Method and device for constructing comment map based on artificial intelligence |
CN108280688A (en) * | 2018-01-29 | 2018-07-13 | 京东方科技集团股份有限公司 | The comment information analysis method of object, apparatus and system |
CN113158670A (en) * | 2021-01-21 | 2021-07-23 | 北京明略昭辉科技有限公司 | E-commerce comment suggestion extraction method based on entity emotion recognition |
CN113627969A (en) * | 2021-06-21 | 2021-11-09 | 杭州盟码科技有限公司 | Product problem analysis method and system based on E-commerce platform user comments |
CN114090880A (en) * | 2021-11-10 | 2022-02-25 | 北京明略软件***有限公司 | Method and device for commodity recommendation, electronic equipment and storage medium |
CN114037485A (en) * | 2021-12-16 | 2022-02-11 | 微评(上海)信息技术有限公司 | Business comment-based service quality evaluation method, device, equipment and medium |
CN114861059A (en) * | 2022-05-18 | 2022-08-05 | 北京百度网讯科技有限公司 | Resource recommendation method and device, electronic equipment and storage medium |
-
2022
- 2022-08-25 CN CN202211028162.7A patent/CN115098650B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN115098650A (en) | 2022-09-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115098650B (en) | Comment information analysis method based on historical data model and related device | |
WO2019214245A1 (en) | Information pushing method and apparatus, and terminal device and storage medium | |
CN110413780B (en) | Text emotion analysis method and electronic equipment | |
CN103914478B (en) | Webpage training method and system, webpage Forecasting Methodology and system | |
CN114238573B (en) | Text countercheck sample-based information pushing method and device | |
CN108027814B (en) | Stop word recognition method and device | |
CN109086265B (en) | Semantic training method and multi-semantic word disambiguation method in short text | |
CN101097570A (en) | Advertisement classification method capable of automatic recognizing classified advertisement type | |
CN111984792A (en) | Website classification method and device, computer equipment and storage medium | |
CN112416778A (en) | Test case recommendation method and device and electronic equipment | |
CN113420018A (en) | User behavior data analysis method, device, equipment and storage medium | |
CN111831810B (en) | Intelligent question-answering method, device, equipment and storage medium | |
CN111241410A (en) | Industry news recommendation method and terminal | |
CN111190946A (en) | Report generation method and device, computer equipment and storage medium | |
CN112669113A (en) | Product recommendation method and device, storage medium and electronic device | |
CN112685635A (en) | Item recommendation method, device, server and storage medium based on classification label | |
CN105677825A (en) | Analysis method for client browsing operation | |
CN114722198A (en) | Method, system and related device for determining product classification code | |
CN112685374A (en) | Log classification method and device and electronic equipment | |
CN113837824A (en) | Information pushing method and system | |
CN114936326B (en) | Information recommendation method, device, equipment and storage medium based on artificial intelligence | |
CN111460114A (en) | Retrieval method, device, equipment and computer readable storage medium | |
Hamad et al. | Sentiment analysis of restaurant reviews in social media using naïve bayes | |
CN113961811B (en) | Event map-based conversation recommendation method, device, equipment and medium | |
CN113806638B (en) | Personalized recommendation method based on user portrait and related equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |