CN110766439A - Hotel network public praise evaluation method and system and electronic equipment - Google Patents
Hotel network public praise evaluation method and system and electronic equipment Download PDFInfo
- Publication number
- CN110766439A CN110766439A CN201910813805.0A CN201910813805A CN110766439A CN 110766439 A CN110766439 A CN 110766439A CN 201910813805 A CN201910813805 A CN 201910813805A CN 110766439 A CN110766439 A CN 110766439A
- Authority
- CN
- China
- Prior art keywords
- public praise
- training
- classified
- data
- dimension classification
- 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 98
- 238000012549 training Methods 0.000 claims abstract description 82
- 238000013145 classification model Methods 0.000 claims abstract description 41
- 238000004458 analytical method Methods 0.000 claims abstract description 36
- 230000008451 emotion Effects 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 230000015654 memory Effects 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 7
- 230000008676 import Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000006403 short-term memory Effects 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 12
- 230000011218 segmentation Effects 0.000 description 4
- 230000004308 accommodation Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
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
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a hotel network public praise evaluation method, a hotel network public praise evaluation system and electronic equipment, wherein the hotel network public praise evaluation method comprises the following steps: preprocessing public praise comment data to be analyzed to obtain a training set and a data set to be classified; training a network model by using the training set to obtain a dimension classification model; inputting the data set to be classified into the dimension classification model to obtain a dimension classification result; and taking the dimension classification result as the input of emotion analysis to obtain a public praise evaluation. The invention not only can provide the overall evaluation of the hotel, but also can obtain the public praise evaluation of each service aspect of the hotel.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a hotel network public praise evaluation method, a hotel network public praise evaluation system and electronic equipment.
Background
The hotel provides a lodging experience, and the catering product consumption is a typical experience type product. Consumers are unable to make an accurate assessment of the content and quality of the service prior to purchase consumption. Often referring to the opinion of others before purchasing to reduce decision risk. When a consumer searches for hotel information at a travel website or a search engine, a comparison is made of the information of only the specific address, telephone number, website of the hotel and prices of various predetermined channels. Consumers are not satisfied with this basic information. The real experience is more helpful for them to make effective and accurate judgments. Network evaluation is in progress. The network evaluation has the characteristics of wide propagation range, large information quantity, anonymity, super-space-time characteristics and the like. It is not an easy matter for consumers to manually summarize the public praise of each type of service in a hotel from a large number of network evaluations. Thus, network public praise evaluation systems of various large tourism platforms are produced.
In the prior art, the hotel network public praise evaluation method only has overall evaluation and cannot obtain public praise evaluation of each service aspect of the hotel, so that a consumer cannot effectively make a decision.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide a hotel network public praise evaluation method, system and electronic device, which are used to solve the problem that the hotel network public praise evaluation method in the prior art only has overall evaluation and cannot obtain public praise evaluation in each service aspect of a hotel, so that a consumer cannot make a decision effectively.
In order to achieve the above objects and other related objects, the present invention provides a hotel network public praise evaluation method, including:
preprocessing public praise comment data to be analyzed to obtain a training set and a data set to be classified;
training a network model by using the training set to obtain a dimension classification model;
inputting the data set to be classified into the dimension classification model to obtain a dimension classification result;
and taking the dimension classification result as the input of emotion analysis to obtain a public praise evaluation.
In an embodiment of the present invention, the step of preprocessing the public praise comment data to be analyzed to obtain a training set and a data set to be classified includes:
segmenting the sentences of the public praise comment data to be analyzed to obtain segmented sentences;
labeling the segmented sentences to obtain a label set;
obtaining a first vector and a characteristic value vector according to the label set;
and obtaining the training set and the data set to be classified according to the first vector and the characteristic value vector.
In an embodiment of the present invention, the hotel network public praise evaluation method further includes: and acquiring the to-be-analyzed public praise comment data.
In an embodiment of the present invention, the step of training the network model by using the training set to obtain the dimension classification model includes:
initializing parameters of the network model;
inputting the training set into the data set to be classified to obtain the data set to be classified input into the training set;
importing the data set to be classified input into the training set into the network model to obtain a training result set and a label set;
carrying out error analysis on the training result set and the label set to obtain an error analysis result;
judging whether the error analysis result converges to a set threshold value, and if so, obtaining a dimension classification model; and if the data set is not converged to the set threshold, inputting the training set into the data set to be classified again.
In an embodiment of the present invention, the parameters of the network model include a weight and an offset.
In one embodiment of the invention, the network model comprises a long-short term memory network model.
In order to achieve the above object, the present invention further provides a hotel network public praise evaluation system, including:
the preprocessor is used for preprocessing the public praise comment data to be analyzed to obtain a training set and a data set to be classified;
a dimension classification model acquirer for training the network model by using the training set to obtain a dimension classification model;
the dimension classification result acquirer is used for inputting the data set to be classified into the dimension classification model to obtain a dimension classification result;
and the public praise evaluation acquirer is used for taking the dimension classification result as the input of the emotion analysis to obtain the public praise evaluation.
In an embodiment of the present invention, the hotel network public praise evaluation system further includes a public praise comment data acquirer, where the public praise comment data acquirer is configured to acquire the public praise comment data to be analyzed.
In an embodiment of the present invention, the dimension classification model obtainer includes:
a model initialization processor for initializing parameters of the network model;
a to-be-classified data set acquirer, configured to input the training set into the to-be-classified data set to obtain the to-be-classified data set input into the training set;
a training result set and label set acquirer, configured to import the to-be-classified data set input to the training set into the network model to obtain a training result set and a label set;
an error analysis result acquirer, configured to perform error analysis on the training result set and the label set to obtain an error analysis result;
the judger is used for judging whether the error analysis result converges to a set threshold value or not, and if so, a dimension classification model is obtained; and if the data set is not converged to the set threshold, inputting the training set into the data set to be classified again.
In order to achieve the above object, the present invention further provides an electronic device, which includes a data processor and a memory, where the memory stores program instructions, and the data processor executes the program instructions to implement the hotel network public praise evaluation method.
As described above, the hotel network public praise evaluation method, system and electronic device of the present invention have the following beneficial effects:
the invention discloses a hotel network public praise evaluation method which comprises the steps of preprocessing public praise comment data to be analyzed to obtain a training set and a data set to be classified; training a network model by using the training set to obtain a dimension classification model; inputting the data set to be classified into the dimension classification model to obtain a dimension classification result; and finally, taking the dimension classification result as the input of emotion analysis to obtain word-of-mouth evaluation. The invention not only can provide the overall evaluation of the hotel, but also can obtain the public praise evaluation of each service aspect of the hotel, for example, how the public praise of the accommodation environment is, how the public praise of the catering is, and can enable consumers to make decisions more effectively and accurately.
The hotel network public praise evaluation method greatly reduces the calculation amount and complexity when high-dimensional data processing is carried out. The invention greatly improves the data processing efficiency and is beneficial to processing the user evaluation.
The hotel network public praise evaluation method comprises a preprocessor, a dimension classification model acquirer, a dimension classification result acquirer and a public praise evaluation acquirer. The public praise evaluation system not only can evaluate the integrity of the hotel, but also can obtain public praise evaluation of each service aspect of the hotel.
Drawings
Fig. 1 is a flowchart illustrating a method for evaluating a public praise of a hotel network according to an embodiment of the present disclosure.
Fig. 2 is a flowchart illustrating a hotel network public praise evaluation method according to another embodiment of the present application.
Fig. 3 is a flowchart illustrating a step S1 of the hotel network public praise evaluation method in fig. 1 according to an embodiment of the present application.
Fig. 4 is a flowchart illustrating a working procedure of step S2 of the hotel network public praise evaluation method in fig. 1 according to an embodiment of the present application.
Fig. 5 is a block diagram illustrating a hotel network public praise evaluation system according to an embodiment of the present application.
Fig. 6 is a block diagram illustrating a hotel network public praise evaluation system according to another embodiment of the present application.
Fig. 7 is a block diagram illustrating a structure of a dimension classification model acquirer of a hotel network public praise evaluation system according to an embodiment of the present application.
Fig. 8 is a hardware structure diagram of an implementation of a hotel network public praise evaluation system according to an embodiment of the present application.
Fig. 9 is a hardware configuration diagram of an implementation of a hotel network public praise evaluation system according to another embodiment of the present application.
Fig. 10 is a block diagram of an electronic device according to an embodiment of the present application.
Description of the element reference numerals
1 processor
2 memory
10 preprocessor
20-dimensional classification model acquirer
21 model initial processor
22 to-be-classified data set acquirer
23 training result set and label set acquirer
24 error analysis result obtainer
25 judger
30-dimension classification result acquirer
40-mouth stele evaluation acquirer
50 public praise comment data acquirer
S0-S4
S11-S14
S21-S26
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Referring to fig. 1, fig. 1 is a flowchart illustrating a hotel network public praise evaluation method according to an embodiment of the present application. A hotel network public praise evaluation method comprises the following steps: and S1, preprocessing the public praise comment data to be analyzed to obtain a training set and a data set to be classified. And S2, training the network model by using the training set to obtain a dimension classification model. And S3, inputting the data set to be classified into the dimension classification model to obtain a dimension classification result. And S4, taking the dimension classification result as the input of emotion analysis to obtain a public praise evaluation. Referring to fig. 2, fig. 2 is a flowchart illustrating a hotel network public praise evaluation method according to another embodiment of the present application. Before the step S1, the method for evaluating the public praise of the hotel network further includes a step S0, where the step S0 is to obtain the public praise comment data to be analyzed. Means for obtaining the public praise comment data to be analyzed include, but are not limited to, crawling a lot of evaluation information from a travel website by using a crawler technology. Specifically, step S1 may be, but is not limited to, preprocessing the tombstone comment data to be analyzed using a Hidden Markov Model (HMM). Specifically, step S4 uses the dimension classification result as an input of emotion analysis to obtain a public praise evaluation. And the obtained dimension classification result is used as the input of a naive Bayesian model (NaiveBayesian model, NBM) emotion analysis to obtain the final service type public praise evaluation. The nature of the hidden Markov model is derived from observed parametersImplicit parameter information is taken and there will be some dependency on features between contexts. In the aspect of word segmentation, the method is to know the Chinese sentence sequence O ═ O1,O2,O3......OnFinding out the best possible word segmentation sequence S ═ S1,S2,S3......SN}. The hidden markov model includes five tuples: and (3) state set: q ═ Q1,Q2,Q3....QNN is the number of possible states. And (3) observation set: v ═ V1,V2,V3....VMAnd M is the possible observation number. Transition probability: a ═ aij]Wherein a isijRepresenting the transition probability from state i to state j. Observing a probability matrix: b ═ Bj(k)]Wherein b isj(k) V representing the Generation of an Observation in the case of State jKThe probability of (c). And an initial state distribution pi. The state set is set to Q ═ B, E, M, S }. Respectively, indicating the beginning, end, middle, and character of a word as independent words. For example: "weather is good today", and the state sequence that can be solved by the hidden markov model is "BEBEBE". The segmentation result is today/weather/ok. For sentence sequence O ═ O1,O2,O3......OnThe word segmentation sequence S that maximizes P (S |0) { S ═ S1,S2,S3......SN}. The method is obtained by using a Bayesian formula: p (S | O) ═ P (O | S) × P (S). Two assumptions are needed to simplify the above equation: the limited historical assumption: suppose SiOnly by Si-1And (6) determining. Namely P (S)i|Si-1,Si-2......S1)=P(Si|Si-1). The independent output assumption is that: received signal O at i-th timeiBy transmitting signals S onlyiAnd (6) determining. According to the above two hypotheses P (O)1,O2,O3....|S1,S2,S3...)=P(O1|S1)*P(O2|S2)*P(O3|S3) .., solving the maximum value of the simplified formula to obtain the most basic sequence. The optimal path of the turntable sequence meets the characteristics that: the sub-paths of the optimal path must also be optimal. Defining the state at time tThe maximum value of the probability of i is δt(i) Then there is a recurrence formula deltat+1(i)=max[δt(j)aji]bi(0t+1). Specifically, the network model in step S2 includes, but is not limited to, a Long short term memory network model (Long short term memory). The long-short term memory network model avoids the problem of gradient disappearance caused by long-time sequence dependency of the traditional neural network, and the basic idea of the long-short term memory network model is as follows: judgment information is added into the traditional RNN algorithm to judge whether a useful processor exists. The problem of long-order dependence in the traditional RNN model is solved. The traditional neural network is fully connected from an input layer to a hidden layer to an output layer. There is no connection laterally between the layers in the time series. The RNN is called a recurrent neural network because the current output of a sequence is related to not only the current input, but also the input at the previous point in time. I.e. there is no connection between nodes of the hidden layer but a connection. The input of the hidden layer includes not only the input of the current input layer but also the output of the hidden layer at the last point in time. Bayesian classification is a generic term for a class of classification algorithms, which are based on Bayesian theorem. Naive bayesian classification is the most common and simplest class of classification algorithms among bayesian classification algorithms. Naive Bayes is applied to emotion analysis, specifically, a class which maximizes a P (class | feature) value is found according to features. Let A be the signature sequence (A ═ A)1,A2,A3...AN}), C is a category. Then there are:the na iotave bayes formula makes conditional independence assumptions on the conditional probabilities. The above formula is simplified according to the assumption of conditional independence.
Referring to fig. 3, fig. 3 is a flowchart illustrating a working procedure of step S1 of the hotel network public praise evaluation method in fig. 1 according to an embodiment of the present application. The step of preprocessing the public praise comment data to be analyzed in the step S1 to obtain a training set and a data set to be classified includes: and S11, segmenting the sentence of the public praise comment data to be analyzed to obtain a segmented sentence. And S12, labeling the segmented sentences to obtain a label set. And S13, obtaining a first vector and a characteristic value vector according to the label set. And S14, obtaining the training set and the data set to be classified according to the first vector and the characteristic value vector. Referring to fig. 4, fig. 4 is a flowchart illustrating a step S2 of the hotel network public praise evaluation method in fig. 1 according to an embodiment of the present application. The step of training the network model by using the training set in the step 2 to obtain a dimension classification model includes: and S21, initializing parameters of the network model. And S22, inputting the training set into the data set to be classified to obtain the data set to be classified input into the training set. And S23, importing the data set to be classified input into the training set into the network model to obtain a training result set and a label set. And S24, carrying out error analysis on the training result set and the label set to obtain an error analysis result. And S25, judging whether the error analysis result converges to a set threshold, if so, performing the operation of S26, and if not, performing the operation of S22, and inputting the training set into the data set to be classified again. And S26, obtaining a dimension classification model. The first vector may be, but is not limited to, a one _ hot vector, and the label in step S12 is divided into two parts: the first part is the type of service (accommodation/dining/customer service, etc.) and the second part is the evaluation of the type of service. For example: "traffic is inconvenient". The labels of this sentence should be: external traffic-negative. For example: the term "service week to week" results in "service/week to week", the service relates to the management level, week to week does not relate to any service type. When the sentence is converted into a vector, the service corresponds to a feature value, which is assumed to be "1", and the service corresponds to "0". The service week to corresponding vector is "01". And the tag set corresponds to a one _ hot vector. Taking the above sentence as an example, assuming five service types are involved, the corresponding tag set is "01000" in the service week, and "1" therein corresponds to "management level". The sentence vector and the label set vector are combined to form a data set. The data set is divided into two parts, a training set: training the model; and a dataset to be classified.
Referring to fig. 5, fig. 6, and fig. 7, fig. 5 is a block diagram illustrating a hotel network public praise evaluation system according to an embodiment of the present application. Fig. 6 is a block diagram illustrating a hotel network public praise evaluation system according to another embodiment of the present application. Fig. 7 is a block diagram illustrating a structure of a dimension classification model acquirer of a hotel network public praise evaluation system according to an embodiment of the present application. Similar to the principle of the hotel network public praise evaluation method of the present invention, the present invention further provides a hotel network public praise evaluation system, the whole hotel network public praise evaluation system can be implemented in a computer system or a server system, and the computer system or the server system includes but is not limited to: the system comprises a preprocessor 10, a dimension classification model acquirer 20, a dimension classification result acquirer 30, a public praise evaluation acquirer 40 and a public praise comment data acquirer 50. The hotel network public praise evaluation system comprises: preprocessor 10, dimension classification model acquirer 20, dimension classification result acquirer 30, and word-of-mouth evaluation acquirer 40. The preprocessor 10, the dimension classification model acquirer 20, the dimension classification result acquirer 30 and the public praise evaluation acquirer 40 are connected in sequence. The preprocessor 10 is configured to preprocess the public praise comment data to be analyzed to obtain a training set and a data set to be classified. The dimension classification model obtainer 20 is configured to train a network model using the training set to obtain a dimension classification model. The dimension classification result obtainer 30 is configured to input the to-be-classified data set to the dimension classification model to obtain a dimension classification result. The public praise evaluation acquirer 40 is used for taking the dimension classification result as an input of emotion analysis to obtain public praise evaluation. The hotel network public praise evaluation system further comprises a public praise comment data acquirer 50, wherein the public praise comment data acquirer 50 is used for acquiring the public praise comment data to be analyzed. The public praise comment data acquirer 50 is connected with the preprocessor 10. The dimension classification model obtainer 20 includes: a model initial processor 21, a to-be-classified data set acquirer 22, a training result set and label set acquirer 23, an error analysis result acquirer 24, and a judger 25. The model initial processor 21, the dataset to be classified acquirer 22, the training result set acquirer 23, the error analysis result acquirer 24 and the judger 25 are connected in sequence. The model initialization processor 21 is used to initialize the parameters of the network model. The to-be-classified data set obtainer 22 is configured to input the training set into the to-be-classified data set to obtain the to-be-classified data set input into the training set. The training result set and label set obtainer 23 is configured to import the to-be-classified data set input into the training set into the network model, so as to obtain a training result set and a label set. The error analysis result obtainer 24 is configured to perform error analysis on the training result set and the label set to obtain an error analysis result. The judger 25 is configured to judge whether the error analysis result converges to a set threshold, and if so, obtain a dimension classification model; and if the data set is not converged to the set threshold, inputting the training set into the data set to be classified again.
Referring to fig. 8 and 9, fig. 8 is a hardware structure diagram of an implementation of a hotel network public praise evaluation system according to an embodiment of the present application. Fig. 9 is a hardware configuration diagram of an implementation of a hotel network public praise evaluation system according to another embodiment of the present application. The hotel network public praise evaluation system can be implemented on a notebook computer or a desktop computer or a server, but is not limited to the implementation, and the preprocessor 10, the dimension classification model acquirer 20, the dimension classification result acquirer 30, the public praise evaluation acquirer 40 and the public praise comment data acquirer 50 in the hotel network public praise evaluation system can be implemented on a notebook computer or a desktop computer or a server. Referring to fig. 10, fig. 10 is a block diagram of an electronic device according to an embodiment of the present disclosure. The invention also provides electronic equipment which comprises a processor 1 and a memory 2, wherein the memory 2 stores program instructions, and the processor 1 runs the program instructions to realize the hotel network public praise evaluation method.
The invention discloses a hotel network public praise evaluation method, which comprises the following steps: firstly, S1, pre-processing the public praise comment data to be analyzed to obtain a training set and a data set to be classified. And S2, training the network model by utilizing the training set to obtain a dimension classification model. And S3, inputting the data set to be classified into the dimension classification model to obtain a dimension classification result. And S4, finally, taking the dimension classification result as the input of emotion analysis to obtain a public praise evaluation. The invention not only can provide the overall evaluation of the hotel, but also can obtain the public praise evaluation of each service aspect of the hotel, for example, how the public praise of the accommodation environment is, how the public praise of the catering is, and can enable consumers to make decisions more effectively and accurately.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A hotel network public praise evaluation method is characterized by comprising the following steps:
preprocessing public praise comment data to be analyzed to obtain a training set and a data set to be classified;
training a network model by using the training set to obtain a dimension classification model;
inputting the data set to be classified into the dimension classification model to obtain a dimension classification result;
and taking the dimension classification result as the input of emotion analysis to obtain a public praise evaluation.
2. The hotel network public praise evaluation method according to claim 1, wherein the step of preprocessing the public praise comment data to be analyzed to obtain a training set and a data set to be classified comprises:
segmenting the sentences of the public praise comment data to be analyzed to obtain segmented sentences;
labeling the segmented sentences to obtain a label set;
obtaining a first vector and a characteristic value vector according to the label set;
and obtaining the training set and the data set to be classified according to the first vector and the characteristic value vector.
3. The hotel network public praise evaluation method according to claim 1, further comprising: and acquiring the to-be-analyzed public praise comment data.
4. The method of claim 1, wherein the step of training the network model with the training set to obtain the dimension classification model comprises:
initializing parameters of the network model;
inputting the training set into the data set to be classified to obtain the data set to be classified input into the training set;
importing the data set to be classified input into the training set into the network model to obtain a training result set and a label set;
carrying out error analysis on the training result set and the label set to obtain an error analysis result;
judging whether the error analysis result converges to a set threshold value, and if so, obtaining a dimension classification model; and if the data set is not converged to the set threshold, inputting the training set into the data set to be classified again.
5. The hotel network public praise evaluation method according to claim 4, wherein the evaluation method comprises the following steps: the parameters of the network model include weight and offset.
6. The hotel network public praise evaluation method according to claim 4, wherein the evaluation method comprises the following steps: the network model comprises a long-term and short-term memory network model.
7. A hotel network public praise evaluation system, characterized in that the hotel network public praise evaluation system comprises:
the preprocessor is used for preprocessing the public praise comment data to be analyzed to obtain a training set and a data set to be classified;
a dimension classification model acquirer for training the network model by using the training set to obtain a dimension classification model;
the dimension classification result acquirer is used for inputting the data set to be classified into the dimension classification model to obtain a dimension classification result;
and the public praise evaluation acquirer is used for taking the dimension classification result as the input of the emotion analysis to obtain the public praise evaluation.
8. The hotel network public praise evaluation system according to claim 7, wherein: the hotel network public praise evaluation system further comprises a public praise comment data acquirer, and the public praise comment data acquirer is used for acquiring the public praise comment data to be analyzed.
9. The hotel network public praise evaluation system according to claim 7, wherein the dimension classification model obtainer comprises:
a model initialization processor for initializing parameters of the network model;
a to-be-classified data set acquirer, configured to input the training set into the to-be-classified data set to obtain the to-be-classified data set input into the training set;
a training result set and label set acquirer, configured to import the to-be-classified data set input to the training set into the network model to obtain a training result set and a label set;
an error analysis result acquirer, configured to perform error analysis on the training result set and the label set to obtain an error analysis result;
the judger is used for judging whether the error analysis result converges to a set threshold value or not, and if so, a dimension classification model is obtained; and if the data set is not converged to the set threshold, inputting the training set into the data set to be classified again.
10. An electronic device comprising a data processor and a memory, the memory storing program instructions, characterized in that: the data processor executes program instructions to implement the hotel network public praise evaluation method of any of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910813805.0A CN110766439A (en) | 2019-08-30 | 2019-08-30 | Hotel network public praise evaluation method and system and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910813805.0A CN110766439A (en) | 2019-08-30 | 2019-08-30 | Hotel network public praise evaluation method and system and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110766439A true CN110766439A (en) | 2020-02-07 |
Family
ID=69329310
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910813805.0A Pending CN110766439A (en) | 2019-08-30 | 2019-08-30 | Hotel network public praise evaluation method and system and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110766439A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112528183A (en) * | 2020-12-16 | 2021-03-19 | 平安银行股份有限公司 | Webpage component layout method and device based on big data, electronic equipment and medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107025284A (en) * | 2017-04-06 | 2017-08-08 | 中南大学 | The recognition methods of network comment text emotion tendency and convolutional neural networks model |
CN107862343A (en) * | 2017-11-28 | 2018-03-30 | 南京理工大学 | The rule-based and comment on commodity property level sensibility classification method of neutral net |
CN109284506A (en) * | 2018-11-29 | 2019-01-29 | 重庆邮电大学 | A kind of user comment sentiment analysis system and method based on attention convolutional neural networks |
CN109408809A (en) * | 2018-09-25 | 2019-03-01 | 天津大学 | A kind of sentiment analysis method for automobile product comment based on term vector |
CN110059191A (en) * | 2019-05-07 | 2019-07-26 | 山东师范大学 | A kind of text sentiment classification method and device |
CN110059922A (en) * | 2019-03-11 | 2019-07-26 | 北京比速信息科技有限公司 | Satisfaction evaluation method on the line of data is commented on based on internet tourist |
CN110134947A (en) * | 2019-04-17 | 2019-08-16 | 中国科学院计算技术研究所 | A kind of sensibility classification method and system based on uneven multi-source data |
-
2019
- 2019-08-30 CN CN201910813805.0A patent/CN110766439A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107025284A (en) * | 2017-04-06 | 2017-08-08 | 中南大学 | The recognition methods of network comment text emotion tendency and convolutional neural networks model |
CN107862343A (en) * | 2017-11-28 | 2018-03-30 | 南京理工大学 | The rule-based and comment on commodity property level sensibility classification method of neutral net |
CN109408809A (en) * | 2018-09-25 | 2019-03-01 | 天津大学 | A kind of sentiment analysis method for automobile product comment based on term vector |
CN109284506A (en) * | 2018-11-29 | 2019-01-29 | 重庆邮电大学 | A kind of user comment sentiment analysis system and method based on attention convolutional neural networks |
CN110059922A (en) * | 2019-03-11 | 2019-07-26 | 北京比速信息科技有限公司 | Satisfaction evaluation method on the line of data is commented on based on internet tourist |
CN110134947A (en) * | 2019-04-17 | 2019-08-16 | 中国科学院计算技术研究所 | A kind of sensibility classification method and system based on uneven multi-source data |
CN110059191A (en) * | 2019-05-07 | 2019-07-26 | 山东师范大学 | A kind of text sentiment classification method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112528183A (en) * | 2020-12-16 | 2021-03-19 | 平安银行股份有限公司 | Webpage component layout method and device based on big data, electronic equipment and medium |
CN112528183B (en) * | 2020-12-16 | 2023-08-18 | 平安银行股份有限公司 | Webpage component layout method and device based on big data, electronic equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109376222B (en) | Question-answer matching degree calculation method, question-answer automatic matching method and device | |
JP7360497B2 (en) | Cross-modal feature extraction method, extraction device, and program | |
CN112164391A (en) | Statement processing method and device, electronic equipment and storage medium | |
CN111199474B (en) | Risk prediction method and device based on network map data of two parties and electronic equipment | |
CN111177402B (en) | Evaluation method, device, computer equipment and storage medium based on word segmentation processing | |
CN111767366A (en) | Question and answer resource mining method and device, computer equipment and storage medium | |
CN111783903B (en) | Text processing method, text model processing method and device and computer equipment | |
CN109359180B (en) | User portrait generation method and device, electronic equipment and computer readable medium | |
CN109783812B (en) | Chinese named entity recognition method, system and device based on self-attention mechanism | |
US20190080352A1 (en) | Segment Extension Based on Lookalike Selection | |
CN112905897B (en) | Similar user determination method, vector conversion model, device, medium and equipment | |
CN110598869B (en) | Classification method and device based on sequence model and electronic equipment | |
KR20220002065A (en) | method, apparatus, computer equipment, computer readable storage medium and computer program for visual qustion answering | |
CN111274822A (en) | Semantic matching method, device, equipment and storage medium | |
CN111666766A (en) | Data processing method, device and equipment | |
CN110717090A (en) | Network public praise evaluation method and system for scenic spots and electronic equipment | |
CN113779225A (en) | Entity link model training method, entity link method and device | |
CN112131345A (en) | Text quality identification method, device, equipment and storage medium | |
CN113657087B (en) | Information matching method and device | |
CN113076758B (en) | Task-oriented dialog-oriented multi-domain request type intention identification method | |
CN109977292A (en) | Searching method, calculates equipment and computer readable storage medium at device | |
CN113535949A (en) | Multi-mode combined event detection method based on pictures and sentences | |
CN110766439A (en) | Hotel network public praise evaluation method and system and electronic equipment | |
Mankolli et al. | A hybrid machine learning method for text analysis to determine job titles similarity | |
CN113468311B (en) | Knowledge graph-based complex question and answer method, device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200422 Address after: 215300 room 1602-1605, 1699 South Road, Zu Chong Chong, Kunshan, Suzhou, Jiangsu. Applicant after: YIWO ARTIFICIAL INTELLIGENCE TECHNOLOGY (JIANGSU) Co.,Ltd. Address before: Room 401, No. 1699 Zuchong South Road, Kunshan City, Suzhou City, Jiangsu Province Applicant before: Kunshan Quantum Kunci Quantum Technology Co., Ltd. |