CN112395855A - Comment-based evaluation method and device - Google Patents
Comment-based evaluation method and device Download PDFInfo
- Publication number
- CN112395855A CN112395855A CN202011394831.3A CN202011394831A CN112395855A CN 112395855 A CN112395855 A CN 112395855A CN 202011394831 A CN202011394831 A CN 202011394831A CN 112395855 A CN112395855 A CN 112395855A
- Authority
- CN
- China
- Prior art keywords
- data
- comment
- text
- applying
- determining
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000003066 decision tree Methods 0.000 claims abstract description 41
- 238000003058 natural language processing Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 26
- 238000012795 verification Methods 0.000 claims description 19
- 238000012552 review Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 19
- 238000013461 design Methods 0.000 description 18
- 238000004891 communication Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000003796 beauty Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Finance (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a comment-based evaluation method and device, and the comment-based evaluation method provided by the embodiment comprises the following steps: acquiring a first comment text issued by a user aiming at a target object and first grading data corresponding to the first comment text; according to the first comment text, applying a natural language processing method for preprocessing to determine a second comment text; according to the second comment text, applying a word frequency inverse text frequency algorithm to carry out vectorization processing, and determining first comment data; and determining an evaluation result by applying a decision tree regression model according to the first comment data and the first score data. By the comment-based evaluation method provided by the embodiment of the invention, the targeted evaluation of customers on the hotel is accurately obtained, so that the operation of the hotel is effectively improved, and the service quality is accurately improved.
Description
Technical Field
The invention relates to the field of big data processing, in particular to a comment-based evaluation method and device.
Background
With the development of the internet and the popularization of online payment technology, more and more people are used to book a hotel in an online mode through a mobile phone APP, a website and the like, evaluation of the hotel is reserved after the people check in the hotel, the evaluation comprises text comments and grading data, and the hotel acquires the attention points of customers through feedback of the evaluation, so that the operation of the hotel is improved, and the service quality is improved.
In the prior art, evaluation is mainly processed by presetting evaluation keywords and corresponding evaluation items, and after online evaluation by a customer, a system background collects and analyzes the score of each keyword to obtain the evaluation, and the evaluation keywords in the processing mode are few, such as only giving out 'sanitation', 'environment', 'service' and 'facility', and allowing the customer to evaluate; meanwhile, the corresponding scoring items are not many, such as "very satisfactory", "general" and "unsatisfactory" are given. Due to the fact that the preset comment keywords and the corresponding grading items are too simple and insufficient in precision, the pertinence evaluation of the customers on the hotel cannot be accurately obtained, and therefore operation of the hotel cannot be effectively improved, and service quality cannot be accurately improved.
Therefore, how to accurately acquire the targeted evaluation of the customer on the hotel so as to effectively improve the operation of the hotel and accurately improve the service quality is an urgent problem to be solved.
Disclosure of Invention
The invention provides a comment-based evaluation method, which can accurately acquire the pertinence evaluation of customers on a hotel so as to effectively improve the operation of the hotel and accurately improve the service quality.
In a first aspect, the present invention provides a comment-based evaluation method, including:
acquiring a first comment text issued by a user aiming at a target object and first grading data corresponding to the first comment text;
according to the first comment text, applying a natural language processing method for preprocessing to determine a second comment text;
according to the second comment text, applying a word frequency inverse text frequency algorithm to carry out vectorization processing, and determining first comment data;
and determining an evaluation result by applying a decision tree regression model according to the first comment data and the first score data, wherein the first comment data corresponds to the first score data.
In one possible design, determining the evaluation result by applying a decision tree regression model according to the first comment data and the first score data includes:
determining comment data and score data of all users according to the first comment data and the first score data;
dividing and classifying the comment data and the score data into a training data set and a verification data set according to a preset proportion X, wherein the training data set comprises the comment data with the proportion of X and the score data corresponding to the proportion of X; the verification data set comprises comment data with the proportion of 1-X and score data corresponding to the proportion of 1-X, wherein X is a decimal number larger than 0 and smaller than 1;
according to the training data set, training by applying a decision tree regression model to determine a first model parameter;
according to the verification data set and the first model parameters, performing parameter optimization by using a decision tree regression model to determine second model parameters;
and determining an evaluation result by applying a decision tree regression model according to the comment data, the grading data and the second model parameter.
In one possible design, applying a decision tree regression model to determine the evaluation result based on the review data, the scoring data, and the second model parameter includes:
determining the importance of the comment data by applying a decision tree regression model according to the comment data, the score data and the second model parameter;
and arranging the comment data in a descending order according to the importance degree, and determining an evaluation result.
In one possible design, the natural language processing method includes: punctuation removal, participle removal, stop word removal, and stem extraction.
In one possible design, after acquiring a first comment text posted by a user for a target object and first score data corresponding to the first comment text, the method further includes:
establishing a first corresponding relation between the first comment text and the first scoring data;
the first correspondence is stored in a database of the server.
In one possible design, before determining the evaluation result by applying a decision tree regression model according to the first comment data and the first score data, the method further includes:
establishing a second corresponding relation between the first comment data and the first grading data according to the first corresponding relation, the first comment data and the first grading data;
the second correspondence is stored in a database.
In one possible design, the target object is a hotel.
In a second aspect, the present invention also provides a comment-based evaluation apparatus, including:
the acquisition module is used for acquiring a first comment text issued by a user aiming at a target object and first grading data corresponding to the first comment text;
the first determining module is used for applying a natural language processing method to carry out preprocessing according to the first comment text and determining a second comment text; according to the second comment text, applying a word frequency inverse text frequency algorithm to carry out vectorization processing, and determining first comment data;
and the second determining module is used for applying a decision tree regression model according to the first comment data and the first grading data to determine an evaluation result, wherein the first comment data corresponds to the first grading data.
In one possible design, the second determining module is configured to:
determining comment data and score data of all users according to the first comment data and the first score data;
dividing and classifying the comment data and the score data into a training data set and a verification data set according to a preset proportion X, wherein the training data set comprises the comment data with the proportion of X and the score data corresponding to the proportion of X; the verification data set comprises comment data with the proportion of 1-X and score data corresponding to the proportion of 1-X, wherein X is a decimal number larger than 0 and smaller than 1;
according to the training data set, training by applying a decision tree regression model to determine a first model parameter;
according to the verification data set and the first model parameters, performing parameter optimization by using a decision tree regression model to determine second model parameters;
and determining an evaluation result by applying a decision tree regression model according to the comment data, the grading data and the second model parameter.
In one possible design, the second determining module is specifically configured to:
determining the importance of the comment data by applying a decision tree regression model according to the comment data, the score data and the second model parameter;
and arranging the comment data in a descending order according to the importance degree, and determining an evaluation result.
In one possible design, the natural language processing method includes: punctuation removal, participle removal, stop word removal, and stem extraction.
In one possible design, the obtaining module is further configured to:
establishing a first corresponding relation between the first comment text and the first scoring data;
the first correspondence is stored in a database of the server.
In one possible design, the second determining module is further configured to:
establishing a second corresponding relation between the first comment data and the first grading data according to the first corresponding relation, the first comment data and the first grading data;
the second correspondence is stored in a database.
In one possible design, the target object is a hotel.
In a third aspect, the present invention further provides an evaluation system, including:
a processor; and the number of the first and second groups,
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform any of the comment based rating methods of the first aspect via execution of executable instructions.
In a fourth aspect, an embodiment of the present invention further provides a storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements any one of the comment-based evaluation methods in the first aspect.
The invention provides a comment-based evaluation method and device, wherein a first comment text issued by a user for a target object and first grading data corresponding to the first comment text are obtained; according to the first comment text, applying a natural language processing method for preprocessing to determine a second comment text; according to the second comment text, applying a word frequency inverse text frequency algorithm to carry out vectorization processing, and determining first comment data; and determining an evaluation result by applying a decision tree regression model according to the first comment data and the first grading data, so that the targeted evaluation of the customer on the hotel is accurately obtained, the operation of the hotel is effectively improved, and the service quality is accurately improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a diagram illustrating an application scenario for a comment-based rating method in accordance with an exemplary embodiment of the present invention;
FIG. 2 is a flow diagram illustrating a review-based rating method in accordance with an exemplary embodiment of the present invention;
FIG. 3 is a corresponding diagram of comment text and score data for a comment-based rating method shown in accordance with an exemplary embodiment of the present invention;
FIG. 4 is a diagram illustrating comment text preprocessing for a comment-based rating method in accordance with an exemplary embodiment of the present invention;
FIG. 5 is a data vectorization diagram illustrating a comment-based rating method of the present invention in accordance with an exemplary embodiment;
FIG. 6 is a diagram illustrating an evaluation result of a review-based evaluation methodology in accordance with an exemplary embodiment of the present invention;
FIG. 7 is a schematic overall flow diagram of a comment-based evaluation method according to an exemplary embodiment of the present invention;
FIG. 8 is a schematic diagram illustrating the structure of a review-based review appliance in accordance with an exemplary embodiment of the present invention;
fig. 9 is a schematic structural diagram of an evaluation system according to an exemplary embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
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 is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, 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.
The following describes the technical solutions of the present invention and how to solve the above technical problems with specific embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 1 is a diagram illustrating an application scenario of a comment-based evaluation method according to an exemplary embodiment of the present invention, as shown in fig. 1, including obtaining information 101, text processing 102, decision tree regression model 103, and evaluation result 104; specifically, the information acquisition 101 includes that comment texts and score data are acquired on a system platform, the text processing 102 includes text preprocessing and data vectorization, after the comment texts and the score data are acquired, a natural language processing method is applied to the comment texts to perform preprocessing including punctuation removal, word segmentation, word stop removal and word stem extraction, a plurality of preprocessed texts are obtained, a word frequency inverse text frequency algorithm is applied to the plurality of texts to perform vectorization operation, and the plurality of preprocessed texts are converted into vector data which can be recognized by a computer and express text semantics; and training and verifying by applying a decision tree regression model according to the vector data and the grading data to obtain an evaluation result. By the processing mode, the real value of the comment is mined, and the targeted evaluation of the customer on the hotel is accurately obtained so as to effectively improve the operation of the hotel and accurately improve the service quality.
FIG. 2 is a flow diagram illustrating a review-based rating method in accordance with an exemplary embodiment of the present invention; as shown in fig. 2, the comment-based evaluation method provided in this embodiment includes:
step 201, acquiring a first comment text issued by a user aiming at a target object and first scoring data corresponding to the first comment text;
specifically, for example, fig. 3 is a schematic diagram illustrating correspondence between comment texts and score data of a comment-based evaluation method according to an exemplary embodiment of the present invention, as shown in fig. 3, a first customer comment "only parks outside a hotel are beautiful; i are very angry, so that I can publish the posts on all possible websites when planning a journey, so that nobody can make a mistake to book the place, and the like, wherein the corresponding customer score of the comment is 2.9.
Further specifically, a first corresponding relation between the first comment text and the first scoring data is established; the first correspondence is stored in a database of the server. For example, as shown in FIG. 3, the first customer review and corresponding customer score is 2.9 points; the second customer review and corresponding customer score were 7.5 points; the third customer comment and the corresponding customer score are 7.1 points; the fourth customer comment and the corresponding customer score are 3.8 points; the fifth customer comment and the corresponding customer score are 6.7 points; the sixth customer comment and the corresponding customer score are 6.7 points; and the customer comments correspond to the corresponding customer scores one by one, establish a corresponding relation and store the corresponding relation in a database of the server.
More specifically, the target object is a hotel. Here, the scenario in which the first comment text posted for the target object and the first score data corresponding to the first comment text are applicable includes: 1) hotels, shopping malls, museums and other places where people interact with each other; 2) the effect of product, service, etc. experience; the embodiment of the invention takes a hotel as an example, and other situations are not described again.
specifically, the natural language processing method includes: removing punctuation marks, word segmentation, stop words and stem extraction; for example, fig. 4 is a schematic diagram illustrating a review text preprocessing of a review-based evaluation method according to an exemplary embodiment of the present invention, and as shown in fig. 4, a natural language processing method is applied to the first customer review in fig. 3 for preprocessing, and a second review text determined to include words such as "park, outside, hotel, beauty, and vitality" is obtained.
The second comment text obtained through the processing of step 201 and step 202 can completely and accurately represent all the contents of the customer comment. Since the description mode of the second comment text is a language mode of characters, in order to better combine the language mode with the data scored by the customer for model training, the second comment text needs to be converted in advance, and the text data is converted into vector data capable of being recognized and expressing text semantics by a computer, and the specific processing procedure is as follows.
specifically, a word frequency inverse text frequency algorithm is applied to carry out vectorization operation on the second comment text; fig. 5 is a schematic data vectorization diagram of the comment-based evaluation method according to an exemplary embodiment of the present invention, and as shown in fig. 5, each word in the second comment text is vectorized to obtain a string of vector data in a digital form, so as to facilitate model training in combination with the customer rating data.
And 204, determining an evaluation result by applying a decision tree regression model according to the first comment data and the first score data, wherein the first comment data corresponds to the first score data.
Specifically, according to the first comment data and the first score data, comment data and score data of all users are determined; dividing and classifying the comment data and the score data into a training data set and a verification data set according to a preset proportion X, wherein the training data set comprises the comment data with the proportion of X and the score data corresponding to the proportion of X; the verification data set comprises comment data with the proportion of 1-X and score data corresponding to the proportion of 1-X, wherein X is a decimal number larger than 0 and smaller than 1;
according to the training data set, training by applying a decision tree regression model to determine a first model parameter; according to the verification data set and the first model parameters, performing parameter optimization by using a decision tree regression model to determine second model parameters; and determining an evaluation result by applying a decision tree regression model according to the comment data, the grading data and the second model parameter.
For example, according to the method of step 201 and 203, the comment texts and the score data of all users are converted into the correspondence between the comment data and the score data; classifying comment data and scoring data of 60% of all users into a training data set according to a preset proportion X, wherein the value of X is 60%; the remaining 40% of the user's review data and rating data were categorized as verification data sets. Training the training data set by applying a decision tree regression model to determine a first model parameter; inputting the comment data and the score data of the verification data set into a decision tree regression model for verification according to the first model parameter, optimizing the model parameter and determining a second model parameter, wherein when the verification data set runs in the trained decision tree regression model, a Mean Squared Error (MSE) is generated, and the MSE represents a Mean square value of the difference between a predicted value and a true value, and the smaller the Mean square value is, the better the difference is; and verifying the accuracy of the decision tree regression model through the mean square error, continuously optimizing parameters, and determining final second model parameters.
Further specifically, a second corresponding relation between the first comment data and the first score data is established according to the first corresponding relation, the first comment data and the first score data; the second correspondence is stored in a database. For example, there are corresponding relations between comment texts and rating data of all users, and these corresponding relations are stored in the database of the server; after the comment texts of all users are converted into comment data, in order to accurately correspond to the rating data, the correspondence between the comment data and the rating data needs to be established according to the stored correspondence between the comment texts and the rating data, the comment data after the comment texts are converted, and the rating data, and stored in the database.
Further specifically, a decision tree regression model is applied according to the comment data, the score data and the second model parameter to determine the importance of the comment data; and arranging the comment data in a descending order according to the importance degree, and determining an evaluation result.
For example, after determining the second model parameter, inputting comment data and score data of all users into the decision tree regression model, and the importance of the obtained comment data is as shown in fig. 6, where fig. 6 is a schematic diagram of an evaluation result of the comment-based evaluation method according to an exemplary embodiment of the present invention, and the comment data arranged in descending order according to the importance in the diagram are: dirty, rough, staff, small, noisy, old, none, and the like, and words which are useless for evaluation are removed: staff, none, room, the most important 5 evaluations to the hotel are: dirty, rough, small, noisy, old.
The evaluation result of the customer on the hotel obtained by the method of the step 201-204 is processed, fig. 7 is an overall flow diagram of the evaluation method based on the comment shown in the exemplary embodiment of the present invention, and as shown in fig. 7, the evaluation result obtained by the processing method can truly reflect the value of the comment, and accurately obtain the targeted attention point of the customer on the hotel so as to effectively improve the operation of the hotel and accurately improve the service quality.
Fig. 8 is a schematic structural diagram of a comment-based evaluation apparatus according to an exemplary embodiment of the present invention. As shown in fig. 8, the comment-based evaluation apparatus 80 according to the present embodiment includes:
an obtaining module 801, configured to obtain a first comment text issued by a user for a target object and first score data corresponding to the first comment text;
a first determining module 802, configured to apply a natural language processing method to perform preprocessing according to the first comment text, and determine a second comment text; according to the second comment text, applying a word frequency inverse text frequency algorithm to carry out vectorization processing, and determining first comment data;
the second determining module 803 is configured to apply a decision tree regression model according to the first comment data and the first score data, and determine an evaluation result, where the first comment data corresponds to the first score data.
In one possible design, the second determining module 803 is configured to:
determining comment data and score data of all users according to the first comment data and the first score data;
dividing and classifying the comment data and the score data into a training data set and a verification data set according to a preset proportion X, wherein the training data set comprises the comment data with the proportion of X and the score data corresponding to the proportion of X; the verification data set comprises comment data with the proportion of 1-X and score data corresponding to the proportion of 1-X, wherein X is a decimal number larger than 0 and smaller than 1;
according to the training data set, training by applying a decision tree regression model to determine a first model parameter;
according to the verification data set and the first model parameters, performing parameter optimization by using a decision tree regression model to determine second model parameters;
and determining an evaluation result by applying a decision tree regression model according to the comment data, the grading data and the second model parameter.
In one possible design, the second determining module 803 is specifically configured to:
determining the importance of the comment data by applying a decision tree regression model according to the comment data, the score data and the second model parameter;
and arranging the comment data in a descending order according to the importance degree, and determining an evaluation result.
In one possible design, the natural language processing method includes: punctuation removal, participle removal, stop word removal, and stem extraction.
In one possible design, the obtaining module 801 is further configured to:
establishing a first corresponding relation between the first comment text and the first scoring data;
the first correspondence is stored in a database of the server.
In one possible design, the second determining module 802 is further configured to:
establishing a second corresponding relation between the first comment data and the first grading data according to the first corresponding relation, the first comment data and the first grading data;
the second correspondence is stored in a database.
In one possible design, the target object is a hotel.
Fig. 9 is a schematic structural diagram of an evaluation system according to an exemplary embodiment of the present invention. As shown in fig. 9, the present embodiment provides an evaluation system 90, including:
a processor 901; and the number of the first and second groups,
a memory 902 for storing executable instructions of the processor, which may also be a flash (flash memory);
wherein the processor 901 is configured to perform the respective steps of the above-described method via execution of executable instructions. Reference may be made in particular to the description relating to the preceding method embodiment.
Alternatively, the memory 902 may be separate or integrated with the processor 901.
When the memory 902 is a device independent from the processor 901, the database 90 may further include:
a bus 903 for connecting the processor 901 and the memory 902.
In addition, embodiments of the present application further provide a computer-readable storage medium, in which computer-executable instructions are stored, and when at least one processor of the user equipment executes the computer-executable instructions, the user equipment performs the above-mentioned various possible methods.
Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. Additionally, the ASIC may reside in user equipment. Of course, the processor and the storage medium may reside as discrete components in a communication device.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A review-based evaluation method, comprising:
acquiring a first comment text issued by a user aiming at a target object and first scoring data corresponding to the first comment text;
according to the first comment text, applying a natural language processing method for preprocessing to determine a second comment text;
according to the second comment text, applying a word frequency inverse text frequency algorithm to carry out vectorization processing, and determining first comment data;
and determining an evaluation result by applying a decision tree regression model according to the first comment data and the first score data, wherein the first comment data correspond to the first score data.
2. The method of claim 1, wherein determining an evaluation result by applying a decision tree regression model based on the first opinion data and the first scoring data comprises:
determining comment data and score data of all users according to the first comment data and the first score data;
dividing and classifying the comment data and the score data into a training data set and a verification data set according to a preset proportion X, wherein the training data set comprises the comment data with the proportion of X and the score data corresponding to the proportion of X; the verification data set comprises comment data with the proportion of 1-X and score data corresponding to the proportion of 1-X, wherein X is a decimal number larger than 0 and smaller than 1;
according to the training data set, applying the decision tree regression model for training to determine a first model parameter;
according to the verification data set and the first model parameters, applying the decision tree regression model to carry out parameter optimization and determining second model parameters;
and applying the decision tree regression model according to the comment data, the grading data and the second model parameter to determine the evaluation result.
3. The method of claim 2, wherein said applying the decision tree regression model based on the opinion data, the scoring data, and the second model parameters to determine the evaluation results comprises:
applying the decision tree regression model according to the comment data, the score data and the second model parameter to determine the importance of the comment data;
and sorting the comment data in a descending order according to the importance degree, and determining the evaluation result.
4. The method of claim 1, wherein the natural language processing method comprises: punctuation removal, participle removal, stop word removal, and stem extraction.
5. The method of claim 1, wherein after obtaining the first comment text posted by the user for the target object and the first score data corresponding to the first comment text, further comprising:
establishing a first corresponding relation between the first comment text and the first scoring data;
storing the first corresponding relation in a database of a server.
6. The method of claim 5, wherein before applying a decision tree regression model based on the first opinion data and the first scoring data to determine an evaluation result, further comprising:
establishing a second corresponding relation between the first comment data and the first score data according to the first corresponding relation, the first comment data and the first score data;
storing the second correspondence in the database.
7. The method of any one of claims 1-6, wherein the target object is a hotel.
8. A review-based review device, comprising:
the acquisition module is used for acquiring a first comment text issued by a user aiming at a target object and first grading data corresponding to the first comment text;
the first determining module is used for applying a natural language processing method to carry out preprocessing according to the first comment text and determining a second comment text; according to the second comment text, applying a word frequency inverse text frequency algorithm to carry out vectorization processing, and determining first comment data;
and the second determining module is used for applying a decision tree regression model according to the first comment data and the first score data to determine an evaluation result, wherein the first comment data corresponds to the first score data.
9. An evaluation system, comprising:
a processor; and the number of the first and second groups,
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the comment based rating method of any one of claims 1 to 7 via execution of the executable instructions.
10. A storage medium on which a computer program is stored, which program, when executed by a processor, implements the comment-based evaluation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011394831.3A CN112395855A (en) | 2020-12-03 | 2020-12-03 | Comment-based evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011394831.3A CN112395855A (en) | 2020-12-03 | 2020-12-03 | Comment-based evaluation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112395855A true CN112395855A (en) | 2021-02-23 |
Family
ID=74605026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011394831.3A Pending CN112395855A (en) | 2020-12-03 | 2020-12-03 | Comment-based evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112395855A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094855A (en) * | 2023-08-24 | 2023-11-21 | 哈尔滨工业大学 | Prediction method of non-native language customer satisfaction based on hotel service language |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090127A (en) * | 2017-11-15 | 2018-05-29 | 北京百度网讯科技有限公司 | Question and answer text evaluation model is established with evaluating the method, apparatus of question and answer text |
| CN109829155A (en) * | 2019-01-18 | 2019-05-31 | 平安科技（深圳）有限公司 | Determination method, automatic scoring method, apparatus, equipment and the medium of keyword |
| CN109977225A (en) * | 2019-03-13 | 2019-07-05 | 咪咕文化科技有限公司 | The analysis of public opinion method and device |
| CN110119770A (en) * | 2019-04-28 | 2019-08-13 | 平安科技（深圳）有限公司 | Decision-tree model construction method, device, electronic equipment and medium |
-
2020
- 2020-12-03 CN CN202011394831.3A patent/CN112395855A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090127A (en) * | 2017-11-15 | 2018-05-29 | 北京百度网讯科技有限公司 | Question and answer text evaluation model is established with evaluating the method, apparatus of question and answer text |
| CN109829155A (en) * | 2019-01-18 | 2019-05-31 | 平安科技（深圳）有限公司 | Determination method, automatic scoring method, apparatus, equipment and the medium of keyword |
| CN109977225A (en) * | 2019-03-13 | 2019-07-05 | 咪咕文化科技有限公司 | The analysis of public opinion method and device |
| CN110119770A (en) * | 2019-04-28 | 2019-08-13 | 平安科技（深圳）有限公司 | Decision-tree model construction method, device, electronic equipment and medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094855A (en) * | 2023-08-24 | 2023-11-21 | 哈尔滨工业大学 | Prediction method of non-native language customer satisfaction based on hotel service language |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522556B (en) | Intention recognition method and device | |
| CN108304526B (en) | Data processing method and device and server | |
| CN108108426B (en) | Understanding method and device for natural language question and electronic equipment | |
| US20140351228A1 (en) | Dialog system, redundant message removal method and redundant message removal program | |
| CN107944911B (en) | Recommendation method of recommendation system based on text analysis | |
| CN112163553B (en) | Material price accounting method, device, storage medium and computer equipment | |
| CN111309887B (en) | Method and system for training text key content extraction model | |
| CN112416778A (en) | Test case recommendation method and device and electronic equipment | |
| CN114722839A (en) | Man-machine collaborative dialogue interaction system and method | |
| CN114783421A (en) | Intelligent recommendation method and device, equipment and medium | |
| CN111324698A (en) | Deep learning method, evaluation viewpoint extraction method, device and system | |
| CN114037545A (en) | Client recommendation method, device, equipment and storage medium | |
| CN114255096A (en) | Data requirement matching method and device, electronic equipment and storage medium | |
| JP6757840B2 (en) | Sentence extraction system, sentence extraction method, and program | |
| CN110968664A (en) | Document retrieval method, device, equipment and medium | |
| CN111368066B (en) | Method, apparatus and computer readable storage medium for obtaining dialogue abstract | |
| CN108984777B (en) | Customer service method, apparatus and computer-readable storage medium | |
| CN103886869B (en) | A kind of information feedback method based on speech emotion recognition and system | |
| CN112395855A (en) | Comment-based evaluation method and device | |
| CN109241993B (en) | Evaluation object emotion classification method and device integrating user and overall evaluation information | |
| CN116842263A (en) | Training processing method and device for intelligent question-answering financial advisor model | |
| KR101754124B1 (en) | The restaurant recommending system and the recommending method thereof | |
| CN114141236B (en) | Language model updating method and device, electronic equipment and storage medium | |
| CN112328812B (en) | Domain knowledge extraction method and system based on self-adjusting parameters and electronic equipment | |
| CN115080864A (en) | Artificial intelligence based product recommendation method and device, computer equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210223 |
|
| RJ01 | Rejection of invention patent application after publication |