CN114782110A - Demand mining method and system based on logistic regression two-classification and JMTS - Google Patents
Demand mining method and system based on logistic regression two-classification and JMTS Download PDFInfo
- Publication number
- CN114782110A CN114782110A CN202210503754.3A CN202210503754A CN114782110A CN 114782110 A CN114782110 A CN 114782110A CN 202210503754 A CN202210503754 A CN 202210503754A CN 114782110 A CN114782110 A CN 114782110A
- Authority
- CN
- China
- Prior art keywords
- data
- logistic regression
- jmts
- comparison
- target product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a demand mining method and system based on logistic regression binary classification and JMTS, which relate to the field of data processing and can be applied to the financial field and other fields, and the method comprises the following steps: acquiring first analysis data containing target products on a preset social platform, performing secondary classification screening through a logistic regression model according to the first analysis data to obtain comparison text data, and identifying and obtaining competitive product information according to the comparison text data; acquiring second analysis data on a preset social platform according to the target product and the competitive product information, and analyzing through a JMTS theme emotion model according to the second analysis data to obtain positive and negative evaluation keywords of the target product and the competitive product information; and generating demand data of the target product according to the positive and negative evaluation keywords.
Description
Technical Field
The application relates to the field of data processing, can be applied to the financial field and other fields, and particularly relates to a demand mining method and system based on logistic regression two-classification and JMTS.
Background
Most of the traditional demand forecasting methods rely on interviews, questionnaires or user interaction, however, the user demand changes continuously, and the traditional demand forecasting methods have certain delay and cannot acquire the changing demand of the user quickly in real time. With the rapid growth of online software application stores, more and more users will leave a view and feel of downloading and using software in the application stores. The online comment of the user becomes an important basis for the user to select and use the software, the potential demand of the user on the software is hidden in the comment, however, most of the analysis of the potential demand of the user based on the online comment of the user only analyzes one product individually. Social comparison theory shows that competition is ubiquitous, and most markets are competitive except a few ridge-broken markets nowadays. Like most existing software product evaluation methods, measuring software performance without consideration of other competitive alternatives may lead to incomplete or even misleading conclusions. Therefore, there is a need for an efficient and accurate method for mining product demand.
Disclosure of Invention
The application aims to provide a demand mining method and system based on logistic regression two-classification and JMTS, and the improvement demand of a current target product is determined by analyzing the advantages and disadvantages of competitive products relative to the target product; and moreover, based on the combined use of the logistic regression model and the JMTS theme emotion model, the potential requirements of the user are determined by further considering the emotion of the user while the automatic requirement mining of the product is realized.
To achieve the above object, the present application provides a demand mining method based on logistic regression two-classification and JMTS, which specifically includes: obtaining first analysis data containing target products on a preset social platform, performing secondary classification screening through a logistic regression model according to the first analysis data to obtain comparison text data, and identifying and obtaining competitive product information according to the comparison text data; acquiring second analysis data on a preset social platform according to the target product and the competitive product information, and analyzing through a JMTS theme emotion model according to the second analysis data to obtain positive and negative evaluation keywords of the target product and the competitive product information; and generating demand data of the target product according to the positive and negative evaluation keywords.
In the above demand mining method based on logistic regression two-classification and JMTS, optionally, the obtaining of the first analysis data including the target product on the predetermined social platform includes: obtaining a product category and a corresponding feature keyword according to the target product; collecting comment data of corresponding categories on a preset social platform according to the product categories; and screening the comment data through the characteristic keywords to obtain first analysis data.
In the above method for demand mining based on logistic regression two-classification and JMTS, optionally, the method further includes: obtaining comment data in a preset period on a preset social platform, and carrying out classification and calibration according to text categories in the comment data to obtain comparative text data and non-comparative text data; and obtaining a logistic regression model through a logistic regression training preset model according to the comparative text data and the non-comparative text data.
In the above requirement mining method based on logistic regression two-classification and JMTS, optionally, identifying and obtaining the information of the competitive products according to the comparison text data includes: analyzing and obtaining emotion information in the comparison text data through an emotion analysis tool; and extracting competitive product information from the comparison text data according to the comparison result of the emotion information and the preset emotion type.
In the above demand mining method based on logistic regression two-classification and JMTS, optionally, collecting second analysis data on a predetermined social platform according to the target product and the bid information includes: collecting comment data of corresponding categories on a preset social platform according to the characteristic keywords of the competitive product information; and screening the comment data according to the feature keywords of the target product to obtain second analysis data containing the target product and the competitive product information.
In the above method for mining a demand based on logistic regression two-classification and JMTS, optionally, the generating of the demand data of the target product according to the positive and negative evaluation keywords includes: obtaining comparison data between the target product and the competitive product information according to the occurrence frequency of the positive and negative evaluation keywords; and generating demand data of the target product according to the comparison data.
The application also provides a demand mining system based on logistic regression two-classification and JMTS, and the system comprises a competitive product identification module, a keyword extraction module and a user demand mining module; the competitive product identification module is used for acquiring first analysis data of a target product contained on a preset social platform, performing secondary classification screening through a logistic regression model according to the first analysis data to obtain comparison text data, and identifying and acquiring competitive product information according to the comparison text data; the keyword extraction module is used for acquiring second analysis data on a preset social contact platform according to the target product and the competitive product information, and acquiring positive and negative evaluation keywords of the target product and the competitive product information through JMTS theme emotion model analysis according to the second analysis data; and the user demand mining module is used for generating demand data of the target product according to the positive and negative evaluation keywords.
In the above requirement mining system based on logistic regression two-classification and JMTS, optionally, the competitive product identification module includes a first acquisition unit, and the first acquisition unit is configured to obtain a product category and a corresponding feature keyword according to the target product; collecting comment data of corresponding categories on a preset social platform according to the product categories; and screening the comment data through the feature keywords to obtain first analysis data.
In the above demand mining system based on logistic regression two-classification and JMTS, optionally, the system further includes a topic emotion model construction module, where the topic emotion model construction module is configured to obtain comment data in a predetermined period on a predetermined social platform, and perform classification and calibration according to text categories in the comment data to obtain comparative text data and non-comparative text data; and obtaining a logistic regression model through a logistic regression training preset model according to the comparative text data and the non-comparative text data.
In the above requirement mining system based on logistic regression two-classification and JMTS, optionally, the competitive product identification module includes a screening unit, and the screening unit is configured to obtain emotion information in the comparison text data through emotion analysis tool analysis; and extracting competitive product information from the comparison text data according to the comparison result of the emotion information and the preset emotion type.
In the above requirement mining system based on logistic regression two-classification and JMTS, optionally, the keyword extraction module includes a second acquisition unit, and the second acquisition unit is configured to acquire comment data of a corresponding category on a predetermined social platform according to the feature keyword of the contest information; and screening the comment data according to the feature keywords of the target product to obtain second analysis data containing the target product and the competitive product information.
In the above requirement mining system based on logistic regression two-classification and JMTS, optionally, the user requirement mining module includes a statistical unit and a comparison unit; the statistical unit is used for obtaining comparison data between the target product and the competitive product information according to the occurrence frequency of the positive and negative evaluation keywords; the comparison unit is used for generating demand data of the target product according to the comparison data.
The application also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the method.
The present application also provides a computer-readable storage medium storing a computer program for executing the above method.
The present application also provides a computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the above-described method.
The beneficial technical effect of this application lies in: by summarizing the sentiment in the comment text and determining the product aspects that the reviewer is satisfied with or criticized; these were used to obtain positive and negative evaluations of the target product. Meanwhile, a training model based on logistic regression is used for finding out competitive products of target software, positive and negative comments with the same functions are obtained by JMTS modeling, and finally potential demands of users are mined under the condition of using competitive advantages of competitive products for reference.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this application, and are not intended to limit the application. In the drawings:
FIG. 1 is a schematic flow chart of a logistic regression-based two-classification and JMTS demand mining method according to an embodiment of the present application;
FIG. 2 is a schematic diagram provided in accordance with an embodiment of the present application;
FIG. 3 is a schematic diagram provided by an embodiment of the present application;
FIG. 4 is a schematic view provided by an embodiment of the present application;
FIG. 5 is a schematic view provided by an embodiment of the present application;
FIG. 6 is a schematic diagram provided in accordance with an embodiment of the present application;
FIG. 7 is a schematic view provided by an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following detailed description will be provided with reference to the drawings and examples to explain how to apply the technical means to solve the technical problems and to achieve the technical effects. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments in the present application may be combined with each other, and the technical solutions formed are all within the scope of the present application.
Additionally, the steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions and, although a logical order is illustrated in the flow charts, in some cases, the steps illustrated or described may be performed in an order different than here.
Referring to fig. 1, a demand mining method based on logistic regression two-classification and JMTS provided by the present application specifically includes:
s101, first analysis data containing target products on a preset social platform are obtained, second classification screening is carried out through a logistic regression model according to the first analysis data to obtain comparison text data, and competitive product information is obtained through identification according to the comparison text data;
s102, acquiring second analysis data on a preset social platform according to the target product and the competitive product information, and analyzing through a JMTS theme emotion model according to the second analysis data to obtain positive and negative evaluation keywords of the target product and the competitive product information;
s103, generating demand data of the target product according to the positive and negative evaluation keywords.
Therefore, the machine learning method is applied to user demand mining through the embodiment, the theme emotion modeling-based prediction model is established from the perspective of user online comment and the perspective of user emotion, developers of the mobile application software can be effectively helped to clarify user demands, new demands are introduced into the next round of software updating so as to be better adapted to the ideas of users, the usability and competitiveness of the software are further improved, and the satisfaction degree of the users can be effectively improved by introducing competitive product advantages and using the competitive product advantages under the competitive environment.
Referring to fig. 2, in an embodiment of the present application, the obtaining the first analysis data of the target product on the predetermined social platform includes:
s201, obtaining a product category and a corresponding feature keyword according to the target product;
s202, collecting comment data of corresponding categories on a preset social platform according to the product categories;
s203, screening the comment data through the feature keywords to obtain first analysis data.
In practical applications, the product category may be a specific category of a target product, and the feature keyword may be a product name, a nickname or other words capable of representing the product, which may be selected and set by a person skilled in the art according to practical situations.
Referring to fig. 3, in an embodiment of the present application, the method further includes:
s301, comment data in a preset period on a preset social platform are obtained, and classified calibration is carried out according to text categories in the comment data to obtain comparative text data and non-comparative text data;
s302, a logistic regression model is obtained through a logistic regression training preset model according to the comparative text data and the non-comparative text data.
In actual work, the Logistic regression model is Logistic regression, which is a generalized linear regression analysis model and is generally applied to regression, binary classification and multiple classification. When a logistic regression design is used to regress or classify a problem, it will first create a cost function; then, determining the optimal model parameters by an iterative optimization method; finally testing the quality of the model; the implementation of Logistic regression includes three steps: finding a prediction function, constructing a loss function and finding a regression parameter which minimizes the loss function; this process can be implemented by the prior art and will not be described in detail herein.
Referring to fig. 4, in an embodiment of the present application, the identifying and obtaining the information of the competitive products according to the comparison text data includes:
s401, obtaining emotion information in the comparison text data through emotion analysis tool analysis;
s402, extracting competitive product information from the comparison text data according to the comparison result of the emotion information and the preset emotion type.
Specifically, JMTS: a Joint Multi-grain Topic model is a Topic Sentiment model, can solve the problem that LDA is not suitable for extracting topics from online comments, and provides an MG-LDA model and a JMTS model by expanding LDA, wherein the JMTS model expands MG-LDA by constructing an additional Sentiment layer on the premise of generating Sentiment-oriented evaluable aspects in the assumed Topic and Sentiment area distribution. Compared with other models, the online comments can be more effectively modeled by adding the emotion layer, because the relation can be established between the emotion words and the evaluable aspects, the aspect keywords and the keywords with high positive and negative evaluation frequency of the user on the related aspects can be obtained simultaneously, and the potential requirements of the user can be better mined.
Referring to fig. 5, in an embodiment of the present application, the collecting second analysis data on a predetermined social platform according to the target product and the contest information includes:
s501, collecting comment data of corresponding categories on a preset social platform according to the feature keywords of the competitive product information;
s502, screening the comment data according to the feature keywords of the target product to obtain second analysis data containing the target product and the competitive product information.
In actual work, the embodiment aims to determine the comment information related to the competition information through the competition information, and then further screens comments containing target products based on the comment information, so that the difference and the advantages of the comments can be effectively analyzed; the implementation process can adopt the existing text extraction technology and crawler capture technology, and related technicians in the field can select the setting according to actual needs, and the application is not further limited herein.
Referring to fig. 6, in an embodiment of the present application, the generating the demand data of the target product according to the positive and negative evaluation keywords includes:
s601, obtaining comparison data between the target product and the competitive product information according to the occurrence frequency of the positive and negative evaluation keywords;
s602, generating demand data of the target product according to the comparison data.
In particular, as mobile devices have surpassed fixed Internet access, mobile applications and distribution platforms have become increasingly important; the application store enables users to search, purchase and install mobile applications and then give feedback in the form of comments and scores, the comments may contain information about user experiences and opinions, functional requests and error reports on the applications, and therefore the comments are valuable not only for users who wish to know the opinions of others on the applications, but also for developers and software companies interested in customer feedback, and therefore the application can perform demand mining based on the conditions of the comments, wherein the mining mainly comprises obtaining relevant comments based on the logistic regression model and then confirming relevant competitive product information based on the comments; and then, the use feelings of the user on the emotion analysis tool and the user are confirmed through the emotion analysis tool, so that the real tendency of the user is finally confirmed, and a related demand suggestion of a target product is given.
In practical operation, the application flow of the above embodiment is as follows:
1. determining target products to be researched, and collecting related posts from social platform
2. Stop word filtering is performed on the collected posts.
3. In order to determine the competing product of the target software, it is first classified whether the post contains comparative text. To train and test the classifier, a subset of the posts needs to be manually tagged for training and testing data. And finally, selecting the classifier which is trained by logistic regression as a final classifier for comparing text recognition.
4. To analyze the competitive advantage (and disadvantage) of the target product, SentiStrength tool is used to analyze the emotion expressed in the UGC text, selecting the competitive product with competitive advantage.
5. The method comprises the steps of obtaining user online comments of a target product, constructing a theme emotion model by using JMTS, obtaining related subject terms, filtering whether the user online comments of competing products contain the related subject terms or not, selecting the user online comments containing the subject terms of the target product, and modeling by using JMTS to obtain the subject terms of target software and competing products and related positive and negative popular comment terms.
6. And respectively analyzing the subject words and hot words of the target software and the competitive products, analyzing the potential user requirements of the target software, and using the positive hot words of the same subject of the competitive products as the competitive advantages.
Referring to fig. 7, the present application further provides a demand mining system based on logistic regression two-classification and JMTS, the system includes a competitive product identification module, a keyword extraction module, and a user demand mining module; the competitive product identification module is used for acquiring first analysis data containing target products on a preset social platform, performing secondary classification screening through a logistic regression model according to the first analysis data to obtain comparison text data, and identifying and obtaining competitive product information according to the comparison text data; the keyword extraction module is used for acquiring second analysis data on a preset social platform according to the target product and the competitive product information, and acquiring positive and negative evaluation keywords of the target product and the competitive product information through JMTS theme emotion model analysis according to the second analysis data; and the user demand mining module is used for generating demand data of the target product according to the positive and negative evaluation keywords.
The system also comprises a theme emotion model construction module, wherein the theme emotion model construction module is used for acquiring comment data in a preset period on a preset social platform, and classifying and calibrating according to text types in the comment data to acquire comparative text data and non-comparative text data; and obtaining a logistic regression model through a logistic regression training preset model according to the comparative text data and the non-comparative text data. Specifically, in actual work, the competitive product identification module is mainly used for mining competitive products with competitive advantages from posts; the theme emotion model construction module is used for constructing a theme emotion model for a target product, filtering comments, which do not contain subject words of target software, of user comments of competitive products with competitive advantages, which are mined in the module I, and finally respectively constructing the theme emotion model for the filtered user comments; a user requirement mining module: and the analysis module II is used for obtaining the subject terms of each product and the related hot positive and negative keywords, analyzing the potential user requirements of the target product and analyzing the competitive product advantages of the same subject.
In an embodiment of the application, the competitive product identification module includes a first acquisition unit, and the first acquisition unit is configured to obtain a product category and a corresponding feature keyword according to the target product; collecting comment data of corresponding categories on a preset social platform according to the product categories; and screening the comment data through the feature keywords to obtain first analysis data. Furthermore, the competitive product identification module can also comprise a screening unit, and the screening unit is used for obtaining emotion information in the comparison text data through emotion analysis tool analysis; and extracting the competitive product information from the comparison text data according to the comparison result of the emotion information and the preset emotion type.
In another embodiment of the application, the keyword extraction module comprises a second acquisition unit, and the second acquisition unit is used for acquiring comment data of a corresponding category on a predetermined social platform according to the feature keywords of the competitive product information; and screening the comment data according to the feature keywords of the target product to obtain second analysis data containing the target product and the competitive product information.
In actual work, the application flow of each component is as follows:
1. mining posts of target software from social software;
2. marking whether a part of the posts acquired in the step 1 contain comparative contents or not, and finishing secondary classification by using a trained logistic regression model;
3. performing keyword recognition on the posts containing the comparison content in the step 2, and mining potential competitive products;
4. judging the sentiment values of the posts of the potential competitive products obtained in the step 3 according to different products, and selecting competitive products with more positive comments;
5. collecting user comments of target software to perform JMTS theme emotion modeling, respectively collecting the user comments of competitive products and filtering out the comments without the subject words of the target software;
6. respectively constructing JMTS theme emotion models for the user comments of the competitive products obtained in the step 5 to obtain subject words and related positive and negative comment keywords;
7. and (5) completing user requirement mining by using the subject words and the related keywords obtained in the step (6).
In an embodiment of the application, the user requirement mining module comprises a statistical unit and a comparison unit; the statistical unit is used for obtaining comparison data between the target product and the competitive product information according to the occurrence frequency of the positive and negative evaluation keywords; the comparison unit is used for generating the demand data of the target product according to the comparison data. Specifically, in actual work, the process of generating the demand data may include: classifying the comments of the target software and the competitive products according to the types of the subjects in the keywords, and then sorting according to the ASO and ASS (optimized rating) of the target software, namely sorting according to the satisfactory and unsatisfactory levels of the target software; finally, based on the sequencing results, a proposal for improving the targeted demand is provided for the target software; of course, the specific implementation manner can be selected according to actual needs, and persons skilled in the art can also use other manners given by requirements, and the application is not further limited herein.
The beneficial technical effect of this application lies in: by summarizing the sentiment in the comment text and determining the product aspects that the reviewer is satisfied with or criticized; these were used to obtain positive and negative evaluations of the target product. Meanwhile, a training model based on logistic regression is used for finding out competitive products of target software, positive and negative comments with the same functions are obtained by JMTS modeling, and finally potential requirements of users are mined under the condition of referencing the competitive advantages of the competitive products.
The application also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the method.
The present application also provides a computer-readable storage medium storing a computer program for executing the above method.
The present application also provides a computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the above-described method.
As shown in fig. 8, the electronic device 600 may further include: communication module 110, input unit 120, audio processing unit 130, display 160, power supply 170. It is noted that the electronic device 600 does not necessarily include all of the components shown in FIG. 8; furthermore, the electronic device 600 may also comprise components not shown in fig. 8, which may be referred to in the prior art.
As shown in fig. 8, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the cpu 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides an input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, but is not limited to, an LCD display.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes referred to as an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142 for storing application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.
The memory 140 may also include a data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for a communication function and/or for performing other functions of the electronic device (e.g., a messaging application, a directory application, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, etc., may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and to receive audio input from the microphone 132 to implement general telecommunication functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 130 is also coupled to the central processor 100, enabling recording locally through a microphone 132, and enabling locally stored sound to be played through a speaker 131.
As will be appreciated by one skilled in the art, 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 flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
The above-mentioned embodiments are further described in detail for the purpose of illustrating the invention, and it should be understood that the above-mentioned embodiments are only illustrative of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (15)
1. A demand mining method based on logistic regression two-classification and JMTS, which is characterized by comprising the following steps:
obtaining first analysis data containing target products on a preset social platform, performing secondary classification screening through a logistic regression model according to the first analysis data to obtain comparison text data, and identifying and obtaining competitive product information according to the comparison text data;
acquiring second analysis data on a preset social contact platform according to the target product and the competitive product information, and analyzing through a JMTS theme emotion model according to the second analysis data to obtain positive and negative evaluation keywords of the target product and the competitive product information;
and generating demand data of the target product according to the positive and negative evaluation keywords.
2. The logistic regression two-classification and JMTS based demand mining method of claim 1, wherein obtaining the first analysis data on the predetermined social platform including the target product comprises:
obtaining a product category and a corresponding feature keyword according to the target product;
collecting comment data of corresponding categories on a preset social platform according to the product categories;
and screening the comment data through the characteristic keywords to obtain first analysis data.
3. The logistic regression two-classification and JMTS based demand mining method of claim 1, further comprising:
obtaining comment data in a preset period on a preset social platform, and carrying out classification and calibration according to text categories in the comment data to obtain comparative text data and non-comparative text data;
and obtaining a logistic regression model through a logistic regression training preset model according to the comparative text data and the non-comparative text data.
4. The method of claim 1, wherein identifying and obtaining bid information based on the comparison textual data comprises:
obtaining emotion information in the comparison text data through emotion analysis tool analysis;
and extracting competitive product information from the comparison text data according to the comparison result of the emotion information and the preset emotion type.
5. The logistic regression two-classification and JMTS based demand mining method of claim 1, wherein collecting second analysis data on a predetermined social platform based on the target product and the bid product information comprises:
collecting comment data of corresponding categories on a preset social platform according to the characteristic keywords of the competitive product information;
and screening the comment data according to the feature keywords of the target product to obtain second analysis data containing the target product and the competitive product information.
6. The logistic regression two-classification and JMTS based demand mining method of claim 1, wherein generating demand data for the target product based on the positive and negative evaluation keywords comprises:
obtaining comparison data between the target product and the competitive product information according to the occurrence frequency of the positive and negative evaluation keywords;
and generating demand data of the target product according to the comparison data.
7. A demand mining system based on logistic regression two-classification and JMTS is characterized by comprising a competitive product identification module, a keyword extraction module and a user demand mining module;
the competitive product identification module is used for acquiring first analysis data containing target products on a preset social platform, performing secondary classification screening through a logistic regression model according to the first analysis data to obtain comparison text data, and identifying and obtaining competitive product information according to the comparison text data;
the keyword extraction module is used for acquiring second analysis data on a preset social platform according to the target product and the competitive product information, and acquiring positive and negative evaluation keywords of the target product and the competitive product information through JMTS theme emotion model analysis according to the second analysis data;
and the user demand mining module is used for generating demand data of the target product according to the positive and negative evaluation keywords.
8. The logistic regression two-classification and JMTS based demand mining system of claim 7, wherein the competitive product identification module comprises a first collecting unit for obtaining product categories and corresponding feature keywords according to the target products; collecting comment data of corresponding categories on a preset social platform according to the product categories; and screening the comment data through the feature keywords to obtain first analysis data.
9. The logistic regression two-classification and JMTS-based demand mining system according to claim 7, further comprising a topic emotion model construction module, wherein the topic emotion model construction module is configured to obtain comment data on a predetermined social platform in a predetermined period, and perform classification and calibration according to text categories in the comment data to obtain comparison text data and non-comparison text data; and obtaining a logistic regression model through a logistic regression training preset model according to the comparative text data and the non-comparative text data.
10. The logistic regression two-classification and JMTS based demand mining system of claim 7, wherein the competitive product identification module comprises a screening unit for obtaining emotion information in the comparison text data through emotion analysis tool analysis; and extracting the competitive product information from the comparison text data according to the comparison result of the emotion information and the preset emotion type.
11. The system of claim 7, wherein the keyword extraction module comprises a second collection unit, and the second collection unit is configured to collect comment data of a corresponding category on a predetermined social platform according to the feature keywords of the contest information; and screening the comment data according to the feature keywords of the target product to obtain second analysis data containing the target product and the competitive product information.
12. The logistic regression two-classification and JMTS-based demand mining system of claim 7, wherein the user demand mining module comprises a statistical unit and a comparison unit;
the statistical unit is used for obtaining comparison data between the target product and the competitive product information according to the occurrence frequency of the positive and negative evaluation keywords;
the comparison unit is used for generating demand data of the target product according to the comparison data.
13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 6 when executing the computer program.
14. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 6 by a computer.
15. A computer program product comprising computer program/instructions, characterized in that the computer program/instructions, when executed by a processor, implement the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210503754.3A CN114782110A (en) | 2022-05-10 | 2022-05-10 | Demand mining method and system based on logistic regression two-classification and JMTS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210503754.3A CN114782110A (en) | 2022-05-10 | 2022-05-10 | Demand mining method and system based on logistic regression two-classification and JMTS |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114782110A true CN114782110A (en) | 2022-07-22 |
Family
ID=82436461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210503754.3A Pending CN114782110A (en) | 2022-05-10 | 2022-05-10 | Demand mining method and system based on logistic regression two-classification and JMTS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114782110A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236527A (en) * | 2023-11-13 | 2023-12-15 | 宁德市天铭新能源汽车配件有限公司 | Automobile part demand prediction method and system based on ensemble learning |
-
2022
- 2022-05-10 CN CN202210503754.3A patent/CN114782110A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236527A (en) * | 2023-11-13 | 2023-12-15 | 宁德市天铭新能源汽车配件有限公司 | Automobile part demand prediction method and system based on ensemble learning |
| CN117236527B (en) * | 2023-11-13 | 2024-02-06 | 宁德市天铭新能源汽车配件有限公司 | Automobile part demand prediction method and system based on ensemble learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6799574B2 (en) | Method and device for determining satisfaction with voice dialogue | |
| CN108121795B (en) | User behavior prediction method and device | |
| US20200143265A1 (en) | Systems and methods for automated conversations with feedback systems, tuning and context driven training | |
| US11544135B2 (en) | Systems and methods for the analysis of user experience testing with AI acceleration | |
| CN113688326B (en) | Recommendation method, device, equipment and computer readable storage medium | |
| CN110335596A (en) | Products Show method, apparatus, equipment and storage medium based on speech recognition | |
| Hastie | Metrics and evaluation of spoken dialogue systems | |
| US11909100B2 (en) | Systems and methods for the analysis of user experience testing with AI acceleration | |
| CN103455411A (en) | Log classification model building and action log classifying method and device | |
| CN112926471A (en) | Method and device for identifying image content of business document | |
| CN114782110A (en) | Demand mining method and system based on logistic regression two-classification and JMTS | |
| Zhang et al. | Adaptation behaviour in using one-stop smart governance apps: an exploratory study between digital immigrants and digital natives | |
| Karanam et al. | Design for social sharing: The case of mobile apps | |
| CN111444930A (en) | Method and device for determining prediction effect of two-classification model | |
| CN112734142B (en) | Resource learning path planning method and device based on deep learning | |
| CN115562960A (en) | Application optimization method and system of intelligent equipment | |
| CN115292167A (en) | Life cycle prediction model construction method, device, equipment and readable storage medium | |
| CN113971581A (en) | Robot control method and device, terminal equipment and storage medium | |
| EP4014115A1 (en) | Systems and methods for the analysis of user experience testing with ai acceleration | |
| CN113191821A (en) | Data processing method and device | |
| CN111768306A (en) | Risk identification method and system based on intelligent data analysis | |
| CN111026991A (en) | Data display method and device and computer equipment | |
| CN112948251B (en) | Automatic software testing method and device | |
| EP4375912A1 (en) | Systems and methods for improved user experience results analysis | |
| CN116012128A (en) | User experience analysis method and device for bank counter business product |
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 |