Hotel guest room reservation system based on sentiment analysis demand

Through the hotel room reservation system combining sentiment analysis and user browsing history, the problem of users' long time to screen hotels is solved, the reservation experience and guest satisfaction are improved, and the effect of quickly matching the user's target hotel is achieved.

CN119067239APending Publication Date: 2024-12-03SUZHOU LANGJIETONG INTELLIGENT TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411194721.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Users need to screen a large number of comments during hotel room reservation, resulting in increased time costs, poor reservation experience, and poor guest satisfaction.

Method used

Design a hotel room reservation system based on sentiment analysis needs, including information collection module, preprocessing module, analysis module, search module and reservation module. By crawling hotel review information, use the K nearest neighbor regression algorithm for sentiment analysis, combined with users Browse history and click history, filter and rank hotels, and push hotels that best meet user needs.

Benefits of technology

It effectively shortens the time for users to screen hotels, improves reservation experience, improves guest satisfaction, and quickly matches user target hotels through sentiment analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067239A_ABST
    Figure CN119067239A_ABST
Patent Text Reader

Abstract

The invention discloses a hotel guest room reservation system based on an emotion analysis demand, and the system comprises an information collection module which is used for obtaining data information on a website, and the data information comprises hotel brief introduction and hotel comment information; the preprocessing module is used for splitting the hotel brief introduction and the hotel comment information and screening out comments containing the sentiment aspect word set and comments not containing the sentiment aspect word set; the analysis module is used for performing lexical analysis and grammatical analysis on the comments containing the sentiment aspect word set by utilizing a K nearest neighbor regression algorithm to obtain a first sentiment analysis assignment score corresponding to the comments containing the sentiment aspect word set; and the retrieval module is used for acquiring the browsing history of the user. According to the invention, the problems of time cost increase, poor reservation experience and poor guest satisfaction caused by long hotel screening time of the user according to the comments can be solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a hotel room reservation system based on sentiment analysis requirements. Background Art

[0002] With the development of science and technology, the scale of personnel flow has expanded, and the intelligentization of hotel room systems has become more and more widespread. At present, most hotels use a three-percent-structured room reservation system based on browser-Web server-backend database to book hotel rooms. The reservation method is to log in, check the room, book a room, check out, and perform a series of operations in the browser. The customer information and room information are transmitted to the database for background management, and then the database information is transmitted to the display page via the Web server to give customers a choice. It is used to achieve the purpose of customer information entry, room reservation, and real-time feedback of room information, so as to facilitate customer check-in. However, this system has certain limitations. During the room reservation process, customers need to constantly check the room style and other guests' comments to determine the comfort of the room, compare their own needs for the room, and make room reservations. Because everyone's thinking is different, and the comments are different, it is easy to waste time during the room information screening process, resulting in increased time costs, poor reservation experience, and poor guest satisfaction. Summary of the invention

[0003] The purpose of the present invention is to propose a hotel room reservation system based on sentiment analysis needs in order to solve the problem that it takes a long time for users to screen hotels based on reviews, resulting in increased time costs, poor booking experience and low guest satisfaction.

[0004] In order to achieve the above object, the present invention adopts the following technical solution: a hotel room reservation system based on sentiment analysis requirements, comprising:

[0005] An information collection module, wherein the information collection module is used to obtain data information on the website, wherein the data information includes hotel profiles and hotel review information;

[0006] A preprocessing module, wherein the preprocessing module is used to split the hotel profile and the hotel review information, and filter out the reviews containing the sentiment word set and the reviews not containing the sentiment word set;

[0007] An analysis module, the analysis module is used to perform lexical analysis and grammatical analysis on the comments containing the sentiment word set by using a K-nearest neighbor regression algorithm to obtain a first sentiment analysis assignment score corresponding to the comments containing the sentiment word set;

[0008] A retrieval module is used to obtain the user's browsing history, extract the user's stay time and jump order on each web page, record the anchor text information clicked by the user during the jump process, perform subject hotel analysis on the browsed web pages, and obtain the second sentiment analysis assignment score of the browsed web page comment data;

[0009] The booking module is used to compare the second sentiment analysis assigned score with the first sentiment analysis assigned score, and if the difference is within a preset threshold range, the corresponding hotel is pushed to the user.

[0010] As a further description of the above technical solution:

[0011] The hotel review information includes the user's operation records, browsing records, search records, click records and review information.

[0012] As a further description of the above technical solution:

[0013] The comment information includes images, videos, audios and texts.

[0014] As a further description of the above technical solution:

[0015] The pre-processing module includes an image processing sub-module, a video processing sub-module, an audio processing sub-module and a text processing sub-module;

[0016] The image processing submodule is used to extract information from the image and convert it into corresponding text description;

[0017] The video processing submodule is used to extract information from the video and convert it into corresponding text descriptions;

[0018] The audio processing submodule is used to extract information from the audio and convert it into corresponding text description;

[0019] The text processing submodule is used to split the text information and filter out the comments containing the sentiment word set and the comments not containing the sentiment word set.

[0020] As a further description of the above technical solution:

[0021] The processing steps of the text processing submodule are:

[0022] Split the text information into several sentences;

[0023] The sentence is split to obtain a number of words, and then the words are tagged with parts of speech.

[0024] As a further description of the above technical solution:

[0025] It also includes a preference prediction module, which performs classification statistics based on the hotels browsed by users within a period of time and calculates the hotel preference ranking.

[0026] As a further description of the above technical solution:

[0027] The reservation module includes a comparison submodule, a ranking submodule and a push submodule;

[0028] The comparison submodule is used to compare the second sentiment analysis assigned score with the first sentiment analysis assigned score to obtain difference data;

[0029] The ranking submodule ranks the hotels according to the difference data;

[0030] The push submodule pushes hotels to users based on their rankings from high to low.

[0031] As a further description of the above technical solution:

[0032] The information collection module crawls hotel review information from different platforms using crawler technology and performs deduplication processing on the hotel review information.

[0033] In summary, due to the adoption of the above-mentioned technical scheme, the beneficial effects of the present invention are: by collecting hotel information reviews through the information collection module, the user's target hotel can be selected according to the evaluation information; through the preprocessing module, the emotional information in the hotel review information can be screened out, and the quality of the hotel can be judged according to the emotional information, and the user's target hotel can be matched; through the analysis module and the retrieval module, the information closest to the user's purpose can be found according to the information browsed by the user, and the hotel can be pushed to the user, thereby solving the problem that it takes a long time for users to screen hotels according to reviews, resulting in increased time cost, poor booking experience and poor guest satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 The present invention is a flowchart of a method for transmitting information in a communication network in an offline state. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] See also Figure 1 The present invention provides a technical solution: a hotel room reservation system based on sentiment analysis requirements, comprising:

[0038] An information collection module, wherein the information collection module is used to obtain data information on the website, wherein the data information includes hotel profiles and hotel review information;

[0039] A preprocessing module, wherein the preprocessing module is used to split the hotel profile and the hotel review information, and filter out the reviews containing the sentiment word set and the reviews not containing the sentiment word set;

[0040] An analysis module, the analysis module is used to perform lexical analysis and grammatical analysis on the comments containing the sentiment word set by using a K-nearest neighbor regression algorithm to obtain a first sentiment analysis assignment score corresponding to the comments containing the sentiment word set;

[0041] A retrieval module is used to obtain the user's browsing history, extract the user's stay time and jump order on each web page, record the anchor text information clicked by the user during the jump process, perform subject hotel analysis on the browsed web pages, and obtain the second sentiment analysis assignment score of the browsed web page comment data;

[0042] The booking module is used to compare the second sentiment analysis assigned score with the first sentiment analysis assigned score, and if the difference is within a preset threshold range, the corresponding hotel is pushed to the user.

[0043] The hotel review information includes the user's operation records, browsing records, search records, click records and review information.

[0044] The comment information includes images, videos, audios and texts.

[0045] The pre-processing module includes an image processing sub-module, a video processing sub-module, an audio processing sub-module and a text processing sub-module;

[0046] The image processing submodule is used to extract information from the image and convert it into corresponding text description;

[0047] The video processing submodule is used to extract information from the video and convert it into corresponding text descriptions;

[0048] The audio processing submodule is used to extract information from the audio and convert it into corresponding text description;

[0049] The text processing submodule is used to split the text information and filter out the comments containing the sentiment word set and the comments not containing the sentiment word set.

[0050] For image processing, first extract the image data from the comments, delete the images whose clarity is lower than the set threshold, use the Brenner gradient function to calculate the image clarity, and delete the images below the threshold according to the set threshold. The Brenner gradient function calculates the square of the grayscale difference between two adjacent pixels;

[0051] The video data is preprocessed. The specific steps are: use the VideoCapture class in 0penCV and the Python video editing library MoviePy for cropping, splicing, title insertion, video synthesis, video processing and custom effects, and use opencv to obtain the audio data of the video;

[0052] Preprocess the audio data. The specific steps are as follows: Use the speechrecognition module of the Python video editing library to convert speech into text. The speechrecognition module not only includes IBM's speech recognition API, but also Microsoft's and Google's speech recognition APIs. Use this module to call the corresponding API to convert speech into text. After converting to text, use Jieba word segmentation to segment the sentences and words, and pre-process the converted text;

[0053] For the collected text information, Jieba word segmentation is used to segment sentences and words. Jieba word segmentation is a Chinese word segmentation tool in Python. For a long paragraph of text, its word segmentation principle can be roughly divided into three steps: first, use regular expressions to roughly divide the Chinese paragraph into sentences; then construct each sentence into a directed acyclic graph (DAG), and then find the best segmentation scheme; finally, for continuous single words, use the hidden Markov model (HMM model) to divide them again.

[0054] The processing steps of the text processing submodule are:

[0055] Split the text information into several sentences;

[0056] The sentence is split to obtain a number of words, and then the words are tagged with parts of speech.

[0057] This can accurately extract useful information and improve the efficiency of information processing.

[0058] It also includes a preference prediction module, which classifies and counts the hotels browsed by users within a period of time and calculates the hotel preference ranking. In this way, the corresponding hotels can be pushed in time as the user's preferences change, avoiding pushing wrong hotel information and leaving a bad user experience. The period of time can be one month or half a month.

[0059] The reservation module includes a comparison submodule, a ranking submodule and a push submodule;

[0060] The comparison submodule is used to compare the second sentiment analysis assigned score with the first sentiment analysis assigned score to obtain difference data;

[0061] The ranking submodule ranks the hotels according to the difference data;

[0062] The push submodule pushes hotels to users based on their rankings from high to low.

[0063] The difference data is the absolute value of the second sentiment analysis assigned score minus the first sentiment analysis assigned score. In this way, the hotels can be ranked according to the difference data. The smaller the difference, the higher the hotel ranking and the closer it is to the user's target hotel, so that the user can quickly find the target hotel.

[0064] The information collection module crawls hotel review information from different platforms through crawler technology and performs deduplication processing on the hotel review information, which can quickly filter out useful information from the hotel review information and improve the information processing efficiency.

[0065] Working principle: By collecting hotel information reviews through the information collection module, the user's target hotel can be selected based on the evaluation information; through the pre-processing module, the emotional information in the hotel review information can be filtered out, and the quality of the hotel can be judged based on the emotional information, and the user's target hotel can be matched; through the analysis module and the retrieval module, the information closest to the user's purpose can be found based on the information browsed by the user, and the hotel can be pushed to the user, thus solving the problem that users spend a long time screening hotels based on reviews, resulting in increased time costs, poor booking experience and poor guest satisfaction.

[0066] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A hotel room reservation system based on sentiment analysis needs, characterized in that: include: An information collection module, wherein the information collection module is used to obtain data information on the website, wherein the data information includes hotel profiles and hotel review information; A preprocessing module, wherein the preprocessing module is used to split the hotel profile and the hotel review information, and filter out the reviews containing the sentiment word set and the reviews not containing the sentiment word set; An analysis module, the analysis module is used to perform lexical analysis and grammatical analysis on the comments containing the sentiment word set by using a K-nearest neighbor regression algorithm to obtain a first sentiment analysis assignment score corresponding to the comments containing the sentiment word set; A retrieval module is used to obtain the user's browsing history, extract the user's stay time and jump order on each web page, record the anchor text information clicked by the user during the jump process, perform subject hotel analysis on the browsed web pages, and obtain the second sentiment analysis assignment score of the browsed web page comment data; The booking module is used to compare the second sentiment analysis assigned score with the first sentiment analysis assigned score, and if the difference is within a preset threshold range, the corresponding hotel is pushed to the user.

2. A hotel room reservation system based on sentiment analysis requirements according to claim 1, characterized in that: The hotel review information includes the user's operation records, browsing records, search records, click records and review information.

3. A hotel room reservation system based on sentiment analysis requirements according to claim 2, characterized in that: The comment information includes images, videos, audios and texts.

4. A hotel room reservation system based on sentiment analysis requirements according to claim 1, characterized in that: The pre-processing module includes an image processing sub-module, a video processing sub-module, an audio processing sub-module and a text processing sub-module; The image processing submodule is used to extract information from the image and convert it into corresponding text description; The video processing submodule is used to extract information from the video and convert it into corresponding text descriptions; The audio processing submodule is used to extract information from the audio and convert it into corresponding text description; The text processing submodule is used to split the text information and filter out the comments containing the sentiment word set and the comments not containing the sentiment word set.

5. A hotel room reservation system based on sentiment analysis requirements according to claim 4, characterized in that: The processing steps of the text processing submodule are: Split the text information into several sentences; The sentence is split to obtain a number of words, and then the words are tagged with parts of speech.

6. A hotel room reservation system based on sentiment analysis requirements according to claim 1, characterized in that: It also includes a preference prediction module, which performs classification statistics based on the hotels browsed by users within a period of time and calculates the hotel preference ranking.

7. A hotel room reservation system based on sentiment analysis requirements according to claim 1, characterized in that: The reservation module includes a comparison submodule, a ranking submodule and a push submodule; The comparison submodule is used to compare the second sentiment analysis assigned score with the first sentiment analysis assigned score to obtain difference data; The ranking submodule ranks the hotels according to the difference data; The push submodule pushes hotels to users based on their rankings from high to low.

8. A hotel room reservation system based on sentiment analysis requirements according to claim 1, characterized in that: The information collection module crawls hotel review information from different platforms using crawler technology and performs deduplication processing on the hotel review information.