CN116385029B - Hotel bill detection method, system, electronic equipment and storage medium - Google Patents
Hotel bill detection method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116385029B CN116385029B CN202310428022.7A CN202310428022A CN116385029B CN 116385029 B CN116385029 B CN 116385029B CN 202310428022 A CN202310428022 A CN 202310428022A CN 116385029 B CN116385029 B CN 116385029B
- Authority
- CN
- China
- Prior art keywords
- information
- hotel
- preset
- order data
- bill
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 73
- 230000008451 emotion Effects 0.000 claims abstract description 195
- 238000011156 evaluation Methods 0.000 claims abstract description 56
- 230000009471 action Effects 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims description 30
- 238000002372 labelling Methods 0.000 claims description 24
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 20
- 230000011218 segmentation Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 18
- 238000003064 k means clustering Methods 0.000 claims description 13
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 description 21
- 230000001680 brushing effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000004308 accommodation Effects 0.000 description 3
- 230000002996 emotional effect Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a hotel bill detection method, a hotel bill detection system, electronic equipment and a storage medium, wherein the hotel bill detection method comprises the following steps: acquiring all order data of a target hotel in a preset time period; detecting client information, preset room information and after-sales information by using preset client rules, preset room rules and preset after-sales rules, and judging whether a target hotel has a bill swiping action or not; if the target hotel is judged to have no ordering behavior, extracting evaluation information in each order data; acquiring the final emotion polarity of each order data according to the first emotion polarity of the text information and the second emotion polarity of the image information; and judging whether the target hotel has a bill-refreshing action or not according to the final emotion polarity of each order data and the grading information of each order data. The invention uses the customer rule, the room rule and the after-sale rule to carry out primary detection, and carries out secondary detection under the condition that whether the bill-refreshing behavior exists can not be determined, so that whether the hotel has the bill-refreshing behavior can be effectively detected.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a hotel bill detection method, a hotel bill detection system, an electronic device, and a storage medium.
Background
The hotel bill-brushing behavior refers to the behavior that a hotel or staff thereof falsifies an order through false means so as to obtain higher sales or improve the purposes such as performance assessment. Such behavior typically involves false subscriptions, false evaluations, false traffic, and the like.
Hotel brush lists can have negative impact on both consumers and industries. For consumers, they may mislead the choices due to false evaluations, resulting in poor quality of service hotels getting an improper appreciation and thus affecting the accommodation experience; for the industry, hotel brush lines are a way to break the competitive order, making it difficult for a hotel that complies with the regulations to survive and develop, ultimately leading to unhealthy development throughout the industry.
The transaction platform needs to detect whether a hotel has a bill of sale, so a hotel bill of sale detection method is needed.
Disclosure of Invention
The invention provides a hotel bill detection method, a hotel bill detection system, electronic equipment and a storage medium, and mainly aims to provide a hotel bill detection method for a transaction platform and effectively improve the detection efficiency of a hotel bill.
In a first aspect, an embodiment of the present invention provides a hotel bill detection method, including:
acquiring all order data of a target hotel in a preset time period, wherein the order data comprises client information, preset room information, evaluation information and after-sale information;
detecting the client information, the preset room information and the after-sales information respectively by using preset client rules, preset room rules and preset after-sales rules, and judging whether the target hotel has a bill swiping action or not;
if the target hotel does not have the action of the bill, extracting evaluation information in each order data, wherein the evaluation information comprises text information, image information and grading information;
acquiring a first emotion polarity of text information according to the text information in each order data, and acquiring a second emotion polarity of image information according to the image information in each order data;
acquiring the final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity;
and judging whether the target hotel has a bill swiping action or not according to the final emotion polarity of each order data and the grading information of each order data.
Further, the determining whether the target hotel has a billing action according to the final emotion polarity of each order data and the grading information of each order data includes:
acquiring a preset hotel portrait of the target hotel, wherein the preset hotel portrait comprises actual emotion polarities and actual scores of the target hotel;
classifying the final emotion polarity of each order data and the grading information of each order data by combining the preset hotel portraits and a K-means clustering algorithm to obtain classification categories;
and judging whether the target hotel has a bill-refreshing action according to the distance between the classification category and the preset hotel portrait.
Further, the step of classifying the final emotion polarity of each order data and the grading information of each order data by combining the preset hotel portrait and the K-means clustering algorithm to obtain classification categories includes:
and taking the actual emotion polarity and the actual score as an initial clustering center of a K-means clustering algorithm, classifying the final emotion polarity of each order data and the score information of each order data, and obtaining the classification category.
Further, the detecting the customer information, the predetermined room information, and the after-sales information by using a predetermined customer rule, a predetermined room rule, and a predetermined after-sales rule, respectively, to determine whether the target hotel has a bill swiping action includes:
Judging whether the target hotel has a bill refreshing action or not by utilizing the preset client rule according to the client account number, the client IP address, the browser type, the browser version and the screen resolution in the client information;
judging whether the target hotel has a bill-refreshing action or not by utilizing the preset room rule according to the room price and the preset time in the preset room information;
judging whether the target hotel has a bill swiping action or not by utilizing the preset after-sale rule according to the order completion degree information and the evaluation operation information in the after-sale information;
if the judgment result of at least N times is that the target hotel has a single action, judging that the target hotel has a single action, otherwise, judging that the target hotel does not have a single action, wherein N is a positive integer, and N is not more than 3.
Further, the obtaining the first emotion polarity of the text information according to the text information in each order data includes:
removing stop words, word segmentation and part of speech tagging of the text information to obtain target word segmentation and target part of speech;
and carrying out context emotion analysis according to the target word segmentation and the part of speech of the target word segmentation to obtain a first emotion polarity of the text information.
Further, the obtaining the second emotion polarity of the image information according to the image information in each order data includes:
acquiring a labeling signal;
if the marking signal is a preset marking indication signal, marking the image information in each order data by a manual marking method to obtain the second emotion polarity;
otherwise, labeling the image information in each order data through an emotion labeling neural network model, and obtaining the second emotion polarity, wherein the emotion labeling neural network model is obtained through training of an image sample and emotion polarities of the image sample.
Further, the obtaining the final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity includes:
and carrying out weighted summation on the first emotion polarity and the second emotion polarity to obtain the final emotion polarity of each order data.
In a second aspect, an embodiment of the present invention provides a hotel bill detection system, including:
the order module is used for acquiring order data of a target hotel in a preset time period, wherein the order data comprises client information, preset room information, evaluation information and after-sale information;
The primary judgment module is used for respectively detecting the client information, the preset room information and the after-sales information by using preset client rules, preset room rules and preset after-sales rules and judging whether the target hotel has a bill swiping action or not;
the evaluation module is used for extracting evaluation information in each order data if judging that the target hotel does not have the action of refreshing, wherein the evaluation information comprises text information, image information and scoring information;
the emotion module is used for acquiring a first emotion polarity of the text information according to the text information in each order data and acquiring a second emotion polarity of the image information according to the image information in each order data;
the comprehensive module is used for acquiring the final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity;
and the final judging module is used for judging whether the target hotel has a bill swiping action or not according to the final emotion polarity of each order data and the grading information of each order data.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the steps of the foregoing hotel bill detection method are implemented when the processor executes the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium storing a computer program, where the computer program when executed by a processor implements the steps of the hotel bill detection method.
According to the hotel bill detection method, the system, the electronic equipment and the storage medium, customer information, preset room information, evaluation information and after-sales information of order data are firstly extracted, and the hotel bill is detected according to the outstanding characteristics in the hotel bill detection method, so that the efficiency of the detection method is improved; in addition, the primary judgment result is usually determined by combining the judgment results of the three detection methods, the accuracy of the primary judgment result can be improved by combining the three methods, the detection of orders with obvious bill brushing behaviors by using a follow-up complex algorithm is avoided, and the bill brushing detection efficiency is improved; finally, judging whether the target hotel has a bill-refreshing action or not through the first emotion polarity of the text information and the second emotion polarity of the image information, and finally improving the accuracy of the bill-refreshing detection method through the combination of primary judgment and secondary judgment.
Drawings
Fig. 1 is a flowchart of a hotel bill detection method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a hotel brush list detection system according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
In order to better understand the solution of the present application, the following description will make clear and complete descriptions of the technical solution of the embodiment of the present application with reference to the accompanying drawings in the embodiment of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In the embodiment of the application, at least one refers to one or more; plural means two or more. In the description of this application, the words "first," "second," and the like are used solely for the purpose of distinguishing between descriptions and not necessarily for the purpose of indicating or implying a relative importance or order.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, the terms "comprising," "including," "having," and variations thereof herein mean "including but not limited to," unless expressly specified otherwise.
The hotel bill detection method provided by the embodiment of the invention is mainly applied to a transaction platform, in actual life, the transaction platform can be an intermediary website or APP providing a hotel reservation function, hotel merchants display information of various aspects of hotels, such as positions, grades, prices, rooms, services and the like, and users log in the intermediary website or APP to check the information of each hotel and then select the hotels meeting own requirements for reservation.
In order to improve search ranking and evaluation on an intermediary website or APP, some hotels can perform a bill-swiping operation, which seriously affects the normal market environment, and in order to solve the problem, fig. 1 is a flowchart of a hotel bill-swiping detection method provided by an embodiment of the invention, as shown in fig. 1, the method includes:
s110, acquiring all order data of a target hotel in a preset time period, wherein the order data comprises client information, preset room information, evaluation information and after-sale information;
firstly, all order data of a target hotel in a preset time period are acquired, wherein the preset time period can be within one month, one week or a few days, and the order data can be specifically determined according to actual conditions, and the embodiment of the invention is not particularly limited to the specific steps. The target hotel is a hotel which needs to be subjected to bill swiping detection, and under normal conditions, the transaction platform can sequentially carry out bill swiping detection on each hotel on the website.
When all order data of a target hotel are acquired, the order data refer to all data related to generating an order, wherein the order can be an order with accommodation completed or an order with reservation and cancellation, and the client information, reservation room information, evaluation information and after-sale information related in the process belong to the category of the order data.
It is readily understood that when a hotel is to be booked, to avoid being discovered, the hotel is booked as typically involving a large number of new account numbers and new IP addresses; and in order to reduce the cost of the bill, a large number of special or low-priced rooms are usually reserved, and after reservation is completed, the operation of canceling the order is accompanied, and a great deal of deliberate acceptance is made for the target hotel.
Aiming at the characteristics of hotel bill detection, the embodiment of the invention firstly acquires the client information, the preset room information, the evaluation information and the after-sale information in the order data, and firstly detects whether the target hotel is bill-printed by using a general rule so as to improve the hotel bill-printing detection efficiency.
It should be noted that, in this embodiment, the client information refers to client related information for hotel reservation, such as ID account number, IP address, phone number, browser type, browser version, screen resolution, etc. of the client; the predetermined room information refers to room information predetermined by the client, such as a number of a resident room, a time of a predetermined room, a time of leaving a room, a price of a room, and the like; the evaluation information refers to evaluation of accommodation experience of the target hotel after the customer completes the order or cancels the order, and generally comprises star rating and image-text evaluation; after-market information refers to whether the target hotel is rated or scored after the customer completes or cancels the order.
In this embodiment, customer information, predetermined room information, evaluation information and after-sales information of order data are extracted first, and hotel management behavior is detected according to the characteristics that are more prominent in the hotel management method, so as to improve the efficiency of the detection method.
S120, detecting the client information, the preset room information and the after-sales information respectively by using preset client rules, preset room rules and preset after-sales rules, and judging whether the target hotel has a bill swiping action or not;
in this embodiment, the preset customer rule is used to perform the bill-refreshing detection on the customer information, the preset room rule is used to perform the bill-refreshing detection on the preset room information, the preset after-sales rule is used to detect the after-sales information, and whether the target hotel has the bill-refreshing action is judged according to the detection results of the three aspects.
It should be noted that, the preset client rule may be that a large number of new account numbers and sex IPs appear suddenly in the order data, or the order data originate from the same computer (i.e. all orders are operated on the computer in the hotel), and through these outstanding characteristics, it can be determined that the target hotel obviously has a billing behavior.
The preset room rule can be that a large number of orders are suddenly appeared in the order data in the same time period, or a large number of orders of special price rooms or low price rooms exist in the order data, and the obvious ordering behavior of the target hotel can be judged through the outstanding characteristics.
The preset after-sales rules can be that most of order canceling operations exist in order data, or the evaluation is very high in the order canceling operations, or the evaluation content is mostly repeated or very high in similarity, or the given score is very high, and the obvious ordering behavior of the target hotel can be judged through the outstanding characteristics.
The above three modes can be combined with each other to perform preliminary bill detection, or can be performed separately to perform preliminary bill detection, specifically, can be determined according to actual conditions, and the embodiment is not limited in detail.
In the three-time bill detection judgment, if the first judgment result is that the target hotel has a bill, the first judgment result is that the target hotel has a bill; as another implementation method, in the three-time bill detection and judgment, if at least two judgment results are that the target hotel exists and the first judgment result is that the target hotel exists. The implementation may be determined according to actual situations, which is not specifically limited in this embodiment.
In this embodiment, by combining the characteristics of hotel bill detection, the hotel bill is detected from the three aspects of the customer characteristics, the room characteristics and the after-sales characteristics, when the order data has obvious bill behavior, the hotel bill can be judged in the initial bill detection, and the subsequent judgment in a more complex mode is avoided, so that the efficiency of the method can be improved.
In some embodiments, the detecting the customer information, the predetermined room information, and the after-market information using a preset customer rule, a preset room rule, and a preset after-market rule, respectively, to determine whether the target hotel has a billing action includes:
judging whether the target hotel has a bill refreshing action or not by utilizing the preset client rule according to the client account number, the client IP address, the browser type, the browser version and the screen resolution in the client information;
judging whether the target hotel has a bill-refreshing action or not by utilizing the preset room rule according to the room price and the preset time in the preset room information;
judging whether the target hotel has a bill swiping action or not by utilizing the preset after-sale rule according to the order completion degree information and the evaluation operation information in the after-sale information;
if the judgment result of at least N times is that the target hotel has a single action, judging that the target hotel has a single action, otherwise, judging that the target hotel does not have a single action, wherein N is a positive integer, and N is not more than 3.
In this embodiment, the preset client rule may be as follows:
If a new account number exceeding a certain proportion exists in the customer account number in the order data, wherein the new account number refers to an account number registered in an intermediary website for the first time, other operations such as taking out sales, buying group buying tickets and the like are not performed on the intermediary website, and the registration time of the new account number is close to the time of a reserved hotel, the target hotel is considered to have a refreshing behavior; if a large number of same IP addresses exist in the order data and the orders with the same IP addresses exceed a certain proportion, a large number of the order data can be determined to come from the same computer, or the browser type, browser version and screen resolution in the order data are the same and the number of the orders with the same part exceeds a certain proportion, a large number of the order data can be determined to come from the same computer, and the two types can determine that the target hotel has a swiping behavior. The judging methods can be used singly or in combination, and are determined according to actual conditions.
When the client information is judged by using the preset client rule, the judgment can be performed according to the method, and a judgment result is obtained.
The preset room rules may be as follows:
if a large number of low-price rooms or special-price rooms are reserved in the same time period in order data, the higher the room price is, the higher the ordering cost is, so that the low-price rooms are reserved in ordering, and whether the ordering behavior exists can be judged according to the number of the low-price rooms. And if the number of the low-price rooms in the order data reaches a certain ratio, judging that the target hotel has a swiping behavior.
When the customer information is judged by using the preset room rule, the judgment can be performed according to the method, and a judgment result is obtained.
The preset after-market rules may be as follows:
if there is a proportion of cancel order operations in the order data, or if the proportion of evaluate operations in the order data is too high, or if the number of good comments in the evaluation increases sharply, it may be determined that the target hotel has a stock of play. The judging methods can be used singly or in combination, and are determined according to actual conditions.
When the customer information is judged by using the preset after-sales rule, the judgment can be performed according to the method, and the judgment result is obtained.
In this embodiment, the primary judgment result is determined by combining the judgment results of the three detection methods, and by combining the three methods, the accuracy of the primary judgment result can be improved, and the detection of an order with obvious form-swiping behavior by using a subsequent complex algorithm is avoided, so that the form-swiping detection efficiency is improved.
S130, if the target hotel does not have the action of a bill, extracting evaluation information in each order data, wherein the evaluation information comprises text information, image information and grading information;
If the primary judgment result is that the target hotel has a single brushing effect, the subsequent judgment is not needed, and the judgment result is directly sent to related management staff so as to perform related processing on the target hotel; if the primary judgment result shows that the target hotel does not have the action of ordering, judging again according to the evaluation information in each order data in order to avoid omission.
In this embodiment, the evaluation information in each order data is extracted, and the specific extraction method may extract the evaluation information in the website through a crawler technology. The evaluation information includes text information, image information and scoring information, the text information is written in an evaluation box, the image information is an image inserted during evaluation, the scoring information is scoring four aspects of hotel position, service, facility and sanitation, and the scoring information can be determined according to actual conditions, and the embodiment is not particularly limited to this.
S140, acquiring a first emotion polarity of the text information according to the text information in each order data, and acquiring a second emotion polarity of the image information according to the image information in each order data;
and then extracting text information in each order data, and identifying emotion characteristics in the text information according to the extracted text information to obtain a first emotion polarity expressed by the text information.
Generally, when extracting emotion features in evaluation information in the background technology, since the evaluation of uploading pictures is small in all the evaluations, only text information is focused, and emotion polarities contained in the picture information are ignored.
Therefore, in order to improve the detection accuracy, if the order data comprises image information, the emotion characteristics in the image information are identified according to the extracted image information, so that the second emotion polarity expressed by the text information is obtained.
It should be noted that, the first emotion polarity and the second emotion polarity may include two types of positive evaluation and negative evaluation, or may be classified into five different degrees, that is, poor, general, better, and good, and may be specifically determined according to actual situations, which is not specifically limited in this embodiment. For ease of illustration, the present embodiment distinguishes between the five degrees of difference, worse, generally, better, and better.
In the embodiment, when the emotion polarity is calculated, the second emotion polarity in the image information is combined, and compared with the background technology, the calculated final emotion polarity can be more accurate.
In some embodiments, the obtaining the first emotion polarity of the text information according to the text information in each order data includes:
Removing stop words, word segmentation and part of speech tagging of the text information to obtain target word segmentation and target part of speech;
and carrying out context emotion analysis according to the target word segmentation and the part of speech of the target word segmentation to obtain a first emotion polarity of the text information.
Common emotion analysis methods are: the emotion analysis method based on the emotion dictionary and the emotion analysis method based on machine learning are simple and common emotion analysis methods, the emotion words in the text are counted based on the emotion dictionary, and emotion polarities of the text are classified according to the information such as the part of speech and the strength of the emotion words. The method has the advantages of simplicity, easiness in use and high calculation speed, and can well process some common emotion expressions; the method based on machine learning is a more advanced and fine emotion analysis method, and utilizes a machine learning algorithm to extract and classify the characteristics of the text so as to identify the emotion polarity of the text. However, it has the disadvantage of requiring a large amount of training data and computational resources, which may not work well for small-scale data sets.
As the evaluation information of each hotel is generally hundreds or thousands, the data set is less, and if a machine learning method is adopted, the phenomenon of fitting is easy to occur; in addition, considering implementation cost, emotion analysis is performed by adopting an emotion analysis method based on an emotion dictionary in the embodiment, and the contextual emotion analysis method is one of emotion dictionary analysis methods.
And extracting the first emotion polarity of the text information by a context emotion analysis method according to the text information in each order data. Specifically, preprocessing is carried out on the text information, and after stop words are removed, word segmentation and part of speech tagging are carried out on the text information, so that target word segmentation and target word part of speech are obtained.
Since for an ambiguous or ambiguous word, its emotional polarity needs to be judged according to the context. For example, the "big" word in "big room" and "big room problem much" one indicates positive emotion and one indicates negative emotion, and in emotion analysis, context needs to be considered to associate emotion polarity with specific context.
In this embodiment, by means of part-of-speech tagging, for an ambiguous word or ambiguous word, the emotion polarity of the ambiguous word needs to be determined according to the part-of-speech. For example, "good" may represent positive emotion, or may represent a degree adverb. During emotion analysis, emotion words can be classified according to part-of-speech tagging information, so that misjudgment of ambiguous words and ambiguous words is avoided.
After the target word segmentation and the part of speech of the target word segmentation are obtained, context emotion analysis is carried out, and the first emotion polarity of the text information is calculated according to emotion polarity words in the text information.
In the embodiment, the emotion polarity is calculated by adopting a context analysis method against the condition of fewer hotel evaluation data sets; and through part-of-speech tagging, emotion words can be classified according to part-of-speech tagging information during emotion analysis, so that misjudgment of ambiguous words and ambiguous words is avoided, and the accuracy of emotion polarity judgment is improved.
In some embodiments, the obtaining the second emotion polarity of the image information according to the image information in each order data includes:
acquiring a labeling signal;
if the marking signal is a preset marking indication signal, marking the image information in each order data by a manual marking method to obtain the second emotion polarity;
otherwise, labeling the image information in each order data through an emotion labeling neural network model, and obtaining the second emotion polarity, wherein the emotion labeling neural network model is obtained through training of an image sample and emotion polarities of the image sample.
When the second emotion polarity of the image information is extracted, firstly, a labeling signal is acquired, the labeling signal can be input by a manager, and when the manager is idle in time, the labeling signal is set to be a preset labeling indicating signal.
In order to be objective and fair, the condition of human intervention is reduced, the value of a labeling signal can be modified, all image information is input into an emotion labeling neural network model, images are labeled through a neural network method, a second emotion polarity is obtained, the neural network is obtained through training of an image sample and a sample label, and the sample label is the emotion polarity.
The default value of the marking signal is a preset marking indication signal.
In this embodiment, a second emotion polarity calculation mode of the image information may be selected according to actual situations, and when the image information in the comment is relatively less, and hardware cost needs to be reduced, and calculation efficiency is improved, a manual labeling method is adopted to obtain the second emotion polarity; when the full-automatic detection method is needed to be realized, the specific value of the labeling signal can be modified, and the image information is detected by an artificial intelligence method to obtain the second emotion polarity. The method expands the applicable scene of the hotel detection method.
S150, acquiring the final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity;
after the first emotion polarity and the second emotion polarity are calculated, the first emotion polarity and the second emotion polarity are synthesized according to the first emotion polarity and the second emotion polarity, and the final emotion polarity is obtained.
In some embodiments, the obtaining the final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity includes:
and carrying out weighted summation on the first emotion polarity and the second emotion polarity to obtain the final emotion polarity of each order data.
In this embodiment, the final emotion polarity of each order data is obtained by weighted summation of the first emotion polarity and the second emotion polarity.
It should be noted that, if no image information exists in the order data, the weight corresponding to the second emotion polarity is set to 0, and the weight corresponding to the first emotion polarity is set to 1; if image information exists in the order data, the weight of the first emotion polarity is set to be a first preset weight, the weight of the second emotion polarity is set to be a second preset weight, the first preset weight and the second preset weight can be determined according to actual conditions, in the embodiment, the first preset weight is set to be 0.8, and the second preset weight is set to be 0.6.
And S160, judging whether the target hotel has a bill swiping action or not according to the final emotion polarity of each order data and the grading information of each order data.
Typically, for a true comment, the final emotional polarity score should be distributed between the positive and negative faces, while a comment on a bill will typically have a significant deviation in emotional polarity score. According to the final emotion polarity of each order data and the grading information of each order data, whether the target hotel has a behavior of a refreshing action is judged, if so, the target hotel is considered to have the behavior of the refreshing action, otherwise, the target hotel is considered to have no behavior of the refreshing action.
In some embodiments, the determining whether the target hotel has a billing action according to the final emotion polarity of each order data and the scoring information of each order data includes:
acquiring a preset hotel portrait of the target hotel, wherein the preset hotel portrait comprises actual emotion polarities and actual scores of the target hotel;
classifying the final emotion polarity of each order data and the grading information of each order data by combining the preset hotel portraits and a K-means clustering algorithm to obtain classification categories;
And judging whether the target hotel has a bill-refreshing action according to the distance between the classification category and the preset hotel portrait.
In this embodiment, a preset hotel portrait of a target hotel is first obtained, the preset hotel portrait is formulated according to industry standards, the preset hotel portrait includes an actual emotion polarity and an actual score of the target hotel, and it is to be noted that the actual emotion polarity refers to an objective emotion evaluation of the target hotel, whether the emotion evaluation belongs to positive or negative, whether the emotion evaluation is general or better, and the like; the actual score refers to the objective score for the target hotel.
And then combining the preset hotel portraits with a K-means clustering algorithm, and classifying the final emotion polarity of each order data and the grading information of each order data to obtain all classification categories. The K-means clustering algorithm (K-means algorithm) is an iterative solution clustering analysis algorithm, which needs to determine the position of an initial clustering center in the calculation process, and the accuracy of the final classification category is seriously affected because the initial clustering center has a great influence on clustering.
In the embodiment, the final emotion polarity of each order data and the grading information of the order data are classified through a K-means clustering algorithm, so that all classification categories are obtained.
As an implementation manner, the classifying the final emotion polarity of each order data and the grading information of each order data by combining the preset hotel portrait and the K-means clustering algorithm to obtain classification categories includes:
and taking the actual emotion polarity and the actual score as an initial clustering center of a K-means clustering algorithm, classifying the final emotion polarity of each order data and the score information of each order data, and obtaining the classification category.
In this embodiment, since the actual emotion polarity and the actual score in the preset hotel image are both represented most objectively, the actual emotion polarity and the actual score are used as the initial clustering center of the K-means algorithm, so that the characteristics of the preset hotel image and the K-means algorithm can be effectively combined, and the clustering precision and accuracy can be improved.
After each classification category is obtained, according to the distance between each classification category and the preset hotel image, if the distance deviation is larger, the specific deviation can be determined according to the actual situation, the existence of the target hotel is considered to be a behavior of the bill, otherwise, the target hotel is considered to be the absence of the behavior of the bill.
The embodiment provides a hotel bill detection method, which comprises the steps of firstly extracting client information, preset room information, evaluation information and after-sale information of order data, and detecting hotel bill behavior according to the more prominent characteristics in the hotel bill detection method so as to improve the efficiency of the detection method; in addition, the primary judgment result is usually determined by combining the judgment results of the three detection methods, the accuracy of the primary judgment result can be improved by combining the three methods, the detection of orders with obvious bill brushing behaviors by using a follow-up complex algorithm is avoided, and the bill brushing detection efficiency is improved; finally, judging whether the target hotel has a bill-refreshing action or not through the first emotion polarity of the text information and the second emotion polarity of the image information, and finally improving the accuracy of the bill-refreshing detection method through the combination of primary judgment and secondary judgment.
Fig. 2 is a schematic structural diagram of a hotel bill detection system according to an embodiment of the present invention, as shown in fig. 2, the system includes an order module 210, a primary judgment module 220, an evaluation module 230, an emotion module 240, a synthesis module 250 and a final judgment module 260, wherein:
the order module 210 is configured to obtain order data of a target hotel in a preset time period, where the order data includes customer information, preset room information, evaluation information, and after-sale information;
the primary judging module 220 is configured to detect the client information, the predetermined room information, and the after-sales information respectively by using a preset client rule, a preset room rule, and a preset after-sales rule, and judge whether the target hotel has a bill swiping action;
the evaluation module 230 is configured to extract evaluation information in each order data if it is determined that the target hotel does not have a billing action, where the evaluation information includes text information, image information, and scoring information;
the emotion module 240 is configured to obtain a first emotion polarity of text information according to the text information in each order data, and obtain a second emotion polarity of image information according to the image information in each order data;
The synthesis module 250 is configured to obtain a final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity;
the final judging module 260 is configured to judge whether the target hotel has a billing action according to the final emotion polarity of each order data and the grading information of each order data.
The embodiment is a system embodiment corresponding to the above method embodiment, and the specific implementation process is the same as that of the above method embodiment, and the details refer to the above method embodiment, and the system embodiment is not limited in particular.
The modules in the hotel bill detection system can be realized in whole or in part by software, hardware and a combination thereof. The above modules may be embedded in hardware or independent of a processor in the electronic device, or may be stored in software in a memory in the electronic device, so that the processor may call and execute operations corresponding to the above modules.
Fig. 3 is a schematic structural diagram of an electronic device, which may be a server, according to an embodiment of the present invention, and an internal structure diagram of the electronic device may be as shown in fig. 3. The electronic device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a computer storage medium, an internal memory. The computer storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the computer storage media. The database of the electronic device is used for storing data generated or acquired in the process of executing a hotel bill detection method, such as a preset time period and order data. The network interface of the electronic device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a hotel bill detection method.
In one embodiment, an electronic device is provided that includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of a hotel bill detection method in the above embodiments when the computer program is executed by the processor. Alternatively, the processor, when executing the computer program, performs the functions of the modules/units in this embodiment of a hotel bill detection system.
In one embodiment, a computer storage medium is provided, and a computer program is stored on the computer storage medium, where the computer program is executed by a processor to implement the steps of a hotel bill detection method in the above embodiment. Alternatively, the computer program, when executed by the processor, performs the functions of the modules/units in the embodiment of a hotel bill detection system described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (7)
1. The hotel bill detection method is characterized by comprising the following steps of:
acquiring all order data of a target hotel in a preset time period, wherein the order data comprises client information, preset room information, evaluation information and after-sale information, the client information comprises an ID account number, an IP address, a telephone number, a browser type, a browser version and screen resolution of a client, the preset room information comprises a check-in room number, preset room time, room leaving time and room price, and the after-sale information comprises whether the client evaluates or scores the target hotel after finishing an order or canceling the order;
Detecting the client information, the preset room information and the after-sales information respectively by using preset client rules, preset room rules and preset after-sales rules, and judging whether the target hotel has a bill swiping action or not;
in the three-time bill detection judgment, if at least one judgment result is that the target hotel has a bill, judging that the target hotel has a bill;
if the target hotel does not have the action of the bill, extracting evaluation information in each order data, wherein the evaluation information comprises text information, image information and grading information;
acquiring a first emotion polarity of text information according to the text information in each order data, and acquiring a second emotion polarity of image information according to the image information in each order data;
acquiring the final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity;
acquiring a preset hotel portrait of the target hotel, wherein the preset hotel portrait comprises actual emotion polarities and actual scores of the target hotel;
classifying the final emotion polarity of each order data and the grading information of each order data by combining the preset hotel portraits and a K-means clustering algorithm to obtain classification categories;
Judging whether the target hotel has a bill-refreshing action according to the distance between the classification category and the preset hotel portrait;
the step of obtaining the first emotion polarity of the text information according to the text information in each order data comprises the following steps:
removing stop words, word segmentation and part of speech tagging of the text information to obtain target word segmentation and target part of speech;
performing context emotion analysis according to the target word segmentation and the part of speech of the target word segmentation to obtain a first emotion polarity of the text information;
the step of obtaining the second emotion polarity of the image information according to the image information in each order data comprises the following steps:
acquiring a labeling signal;
if the marking signal is a preset marking indication signal, marking the image information in each order data by a manual marking method to obtain the second emotion polarity;
otherwise, labeling the image information in each order data through an emotion labeling neural network model, and obtaining the second emotion polarity, wherein the emotion labeling neural network model is obtained through training of an image sample and emotion polarities of the image sample.
2. The hotel bill detection method according to claim 1, wherein the step of classifying the final emotion polarity of each order data and the scoring information of each order data by combining the preset hotel portraits and a K-means clustering algorithm to obtain classification categories comprises:
and taking the actual emotion polarity and the actual score as an initial clustering center of a K-means clustering algorithm, classifying the final emotion polarity of each order data and the score information of each order data, and obtaining the classification category.
3. The hotel bill detection method according to claim 1, wherein the detecting the customer information, the predetermined room information, and the after-market information using a predetermined customer rule, a predetermined room rule, and a predetermined after-market rule, respectively, to determine whether the target hotel has a bill-swiping action comprises:
judging whether the target hotel has a bill refreshing action or not by utilizing the preset client rule according to the client account number, the client IP address, the browser type, the browser version and the screen resolution in the client information;
judging whether the target hotel has a bill-refreshing action or not by utilizing the preset room rule according to the room price and the preset time in the preset room information;
Judging whether the target hotel has a bill swiping action or not by utilizing the preset after-sale rule according to the order completion degree information and the evaluation operation information in the after-sale information;
if the judgment result of at least N times is that the target hotel has a single action, judging that the target hotel has a single action, otherwise, judging that the target hotel does not have a single action, wherein N is a positive integer, and N is not more than 3.
4. The hotel bill detection method according to any one of claims 1 to 3, wherein the obtaining the final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity comprises:
and carrying out weighted summation on the first emotion polarity and the second emotion polarity to obtain the final emotion polarity of each order data.
5. A hotel bill detection system, comprising:
the order module is used for acquiring order data of a target hotel in a preset time period, wherein the order data comprises client information, preset room information, evaluation information and after-sale information, the client information comprises an ID account number, an IP address, a telephone number, a browser type, a browser version and screen resolution of a client, the preset room information comprises a room number, time of preset rooms, time of leaving rooms and room price, and the after-sale information comprises whether the target hotel is evaluated or scored after the client completes or cancels the order;
The primary judgment module is used for respectively detecting the client information, the preset room information and the after-sales information by using preset client rules, preset room rules and preset after-sales rules and judging whether the target hotel has a bill swiping action, and in the three bill swiping detection judgment, if at least one judgment result is that the target hotel has a bill swiping action, judging that the target hotel has a bill swiping action;
the evaluation module is used for extracting evaluation information in each order data if judging that the target hotel does not have the action of refreshing, wherein the evaluation information comprises text information, image information and scoring information;
the emotion module is used for acquiring a first emotion polarity of the text information according to the text information in each order data and acquiring a second emotion polarity of the image information according to the image information in each order data;
the step of obtaining the first emotion polarity of the text information according to the text information in each order data comprises the following steps:
removing stop words, word segmentation and part of speech tagging of the text information to obtain target word segmentation and target part of speech;
performing context emotion analysis according to the target word segmentation and the part of speech of the target word segmentation to obtain a first emotion polarity of the text information;
The step of obtaining the second emotion polarity of the image information according to the image information in each order data comprises the following steps:
acquiring a labeling signal;
if the marking signal is a preset marking indication signal, marking the image information in each order data by a manual marking method to obtain the second emotion polarity;
otherwise, labeling the image information in each order data through an emotion labeling neural network model, and obtaining the second emotion polarity, wherein the emotion labeling neural network model is obtained through training of an image sample and emotion polarities of the image sample;
the comprehensive module is used for acquiring the final emotion polarity of each order data according to the first emotion polarity and the second emotion polarity;
the final judging module is used for acquiring preset hotel portraits of the target hotel, wherein the preset hotel portraits comprise actual emotion polarities and actual scores of the target hotel, classifying the final emotion polarities of each order data and the scoring information of each order data by combining the preset hotel portraits and a K-means clustering algorithm, acquiring classification categories, and judging whether the target hotel has a bill swiping action according to the distance between the classification categories and the preset hotel portraits.
6. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the hotel sheet detection method of any of claims 1 to 4 when the computer program is executed.
7. A computer storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the hotel bill detection method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310428022.7A CN116385029B (en) | 2023-04-20 | 2023-04-20 | Hotel bill detection method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310428022.7A CN116385029B (en) | 2023-04-20 | 2023-04-20 | Hotel bill detection method, system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116385029A CN116385029A (en) | 2023-07-04 |
| CN116385029B true CN116385029B (en) | 2024-01-30 |
Family
ID=86963318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310428022.7A Active CN116385029B (en) | 2023-04-20 | 2023-04-20 | Hotel bill detection method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116385029B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818173A (en) * | 2017-11-15 | 2018-03-20 | 电子科技大学 | A kind of false comment filter method of Chinese based on vector space model |
| CN108038696A (en) * | 2017-12-01 | 2018-05-15 | 杭州呯嘭智能技术有限公司 | Brush list detection method and system based on equipment mark code and social group information |
| CN108345587A (en) * | 2018-02-14 | 2018-07-31 | 广州大学 | A kind of the authenticity detection method and system of comment |
| CN108733653A (en) * | 2018-05-18 | 2018-11-02 | 华中科技大学 | A kind of sentiment analysis method of the Skip-gram models based on fusion part of speech and semantic information |
| CN109829166A (en) * | 2019-02-15 | 2019-05-31 | 重庆师范大学 | People place customer input method for digging based on character level convolutional neural networks |
| CN110602184A (en) * | 2019-08-29 | 2019-12-20 | 微梦创科网络科技（中国）有限公司 | Method and device for monitoring and processing cheating behaviors in website |
| WO2020076179A1 (en) * | 2018-10-11 | 2020-04-16 | Общество С Ограниченной Ответственностью "Глобус Медиа" | Method for determining tags for hotels and device for the implementation thereof |
| CN111445271A (en) * | 2020-03-31 | 2020-07-24 | 携程计算机技术（上海）有限公司 | Model generation method, and prediction method, system, device and medium for cheating hotel |
| CN111783875A (en) * | 2020-06-29 | 2020-10-16 | 中国平安财产保险股份有限公司 | Abnormal user detection method, device, equipment and medium based on cluster analysis |
| CN112395556A (en) * | 2020-09-30 | 2021-02-23 | 广州市百果园网络科技有限公司 | Abnormal user detection model training method, abnormal user auditing method and device |
| CN112712127A (en) * | 2021-01-07 | 2021-04-27 | 北京工业大学 | Image emotion polarity classification method combined with graph convolution neural network |
| CN112905739A (en) * | 2021-02-05 | 2021-06-04 | 北京邮电大学 | False comment detection model training method, detection method and electronic equipment |
| CN112989056A (en) * | 2021-04-30 | 2021-06-18 | 中国人民解放军国防科技大学 | False comment identification method and device based on aspect features |
| CN113469789A (en) * | 2021-07-01 | 2021-10-01 | 易纳购科技(北京)有限公司 | Abnormal order detection method and device and computer equipment |
| CN114331592A (en) * | 2021-12-10 | 2022-04-12 | 北京互金新融科技有限公司 | Method for identifying malicious order-swiping behavior |
| CN114443735A (en) * | 2022-01-27 | 2022-05-06 | 深圳市天下房仓科技有限公司 | Hotel data mapping rule generation method, device, equipment and storage medium |
| CN114492423A (en) * | 2021-12-28 | 2022-05-13 | 广州大学 | False comment detection method, system and medium based on feature fusion and screening |
| CN115526166A (en) * | 2022-09-01 | 2022-12-27 | 江西中业智能科技有限公司 | Image-text emotion inference method, system, storage medium and equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170200205A1 (en) * | 2016-01-11 | 2017-07-13 | Medallia, Inc. | Method and system for analyzing user reviews |
-
2023
- 2023-04-20 CN CN202310428022.7A patent/CN116385029B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818173A (en) * | 2017-11-15 | 2018-03-20 | 电子科技大学 | A kind of false comment filter method of Chinese based on vector space model |
| CN108038696A (en) * | 2017-12-01 | 2018-05-15 | 杭州呯嘭智能技术有限公司 | Brush list detection method and system based on equipment mark code and social group information |
| CN108345587A (en) * | 2018-02-14 | 2018-07-31 | 广州大学 | A kind of the authenticity detection method and system of comment |
| CN108733653A (en) * | 2018-05-18 | 2018-11-02 | 华中科技大学 | A kind of sentiment analysis method of the Skip-gram models based on fusion part of speech and semantic information |
| WO2020076179A1 (en) * | 2018-10-11 | 2020-04-16 | Общество С Ограниченной Ответственностью "Глобус Медиа" | Method for determining tags for hotels and device for the implementation thereof |
| CN109829166A (en) * | 2019-02-15 | 2019-05-31 | 重庆师范大学 | People place customer input method for digging based on character level convolutional neural networks |
| CN110602184A (en) * | 2019-08-29 | 2019-12-20 | 微梦创科网络科技（中国）有限公司 | Method and device for monitoring and processing cheating behaviors in website |
| CN111445271A (en) * | 2020-03-31 | 2020-07-24 | 携程计算机技术（上海）有限公司 | Model generation method, and prediction method, system, device and medium for cheating hotel |
| CN111783875A (en) * | 2020-06-29 | 2020-10-16 | 中国平安财产保险股份有限公司 | Abnormal user detection method, device, equipment and medium based on cluster analysis |
| CN112395556A (en) * | 2020-09-30 | 2021-02-23 | 广州市百果园网络科技有限公司 | Abnormal user detection model training method, abnormal user auditing method and device |
| CN112712127A (en) * | 2021-01-07 | 2021-04-27 | 北京工业大学 | Image emotion polarity classification method combined with graph convolution neural network |
| CN112905739A (en) * | 2021-02-05 | 2021-06-04 | 北京邮电大学 | False comment detection model training method, detection method and electronic equipment |
| CN112989056A (en) * | 2021-04-30 | 2021-06-18 | 中国人民解放军国防科技大学 | False comment identification method and device based on aspect features |
| CN113469789A (en) * | 2021-07-01 | 2021-10-01 | 易纳购科技(北京)有限公司 | Abnormal order detection method and device and computer equipment |
| CN114331592A (en) * | 2021-12-10 | 2022-04-12 | 北京互金新融科技有限公司 | Method for identifying malicious order-swiping behavior |
| CN114492423A (en) * | 2021-12-28 | 2022-05-13 | 广州大学 | False comment detection method, system and medium based on feature fusion and screening |
| CN114443735A (en) * | 2022-01-27 | 2022-05-06 | 深圳市天下房仓科技有限公司 | Hotel data mapping rule generation method, device, equipment and storage medium |
| CN115526166A (en) * | 2022-09-01 | 2022-12-27 | 江西中业智能科技有限公司 | Image-text emotion inference method, system, storage medium and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 融合内容及行为的虚假评论检测方法研究;宋海霞;《中国优秀硕士学位论文全文数据库 信息科技辑(月刊)，2015年第01期》;9-38 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116385029A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784170B (en) | Vehicle risk assessment method, device, equipment and storage medium based on image recognition | |
| CN108133013B (en) | Information processing method, information processing device, computer equipment and storage medium | |
| US11321784B2 (en) | Methods and systems for automatically detecting fraud and compliance issues in expense reports and invoices | |
| US10255550B1 (en) | Machine learning using multiple input data types | |
| CN110826006B (en) | Abnormal collection behavior identification method and device based on privacy data protection | |
| CN109949154B (en) | Customer information classification method, apparatus, computer device and storage medium | |
| CN108550065B (en) | Comment data processing method, device and equipment | |
| CN107807941A (en) | Information processing method and device | |
| Zhang et al. | How much is an image worth? An empirical analysis of property’s image aesthetic quality on demand at Airbnb | |
| CN111476653A (en) | Risk information identification, determination and model training method and device | |
| CN112184143B (en) | Model training method, device and equipment in compliance audit rule | |
| CN112102049A (en) | Model training method, business processing method, device and equipment | |
| US20240112236A1 (en) | Information processing device, information processing method, and computer-readable storage medium storing program | |
| CN116385029B (en) | Hotel bill detection method, system, electronic equipment and storage medium | |
| CN110334936B (en) | Method, device and equipment for constructing credit qualification scoring model | |
| CN116342141A (en) | Method, device and equipment for identifying empty shell enterprises | |
| CN113902553A (en) | Risk identification method and device based on knowledge graph, computer equipment and medium | |
| CN111754245B (en) | Method, device and equipment for authenticating business scene | |
| CN117271713A (en) | Associated object recognition method, associated object recognition device, electronic equipment and storage medium | |
| CN113449506A (en) | Data detection method, device and equipment and readable storage medium | |
| CN113283979A (en) | Loan credit evaluation method and device for loan applicant and storage medium | |
| CN110570301A (en) | Risk identification method, device, equipment and medium | |
| CN112258315B (en) | Method and device for checking vehicle credit pre-credit data based on identity tag | |
| US11710328B2 (en) | Systems and methods for identifying a presence of a completed document | |
| CN115171048B (en) | Asset classification method, system, terminal and storage medium based on image recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |