CN110807091A - Hotel intelligent question-answer recommendation and decision support analysis method and system - Google Patents
Hotel intelligent question-answer recommendation and decision support analysis method and system Download PDFInfo
- Publication number
- CN110807091A CN110807091A CN201910154681.XA CN201910154681A CN110807091A CN 110807091 A CN110807091 A CN 110807091A CN 201910154681 A CN201910154681 A CN 201910154681A CN 110807091 A CN110807091 A CN 110807091A
- Authority
- CN
- China
- Prior art keywords
- hotel
- customer
- database
- question
- decision support
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 54
- 238000003058 natural language processing Methods 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 15
- 238000012163 sequencing technique Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 230000008451 emotion Effects 0.000 claims description 54
- 238000000034 method Methods 0.000 claims description 30
- 238000010801 machine learning Methods 0.000 claims description 16
- 230000009193 crawling Effects 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 10
- 238000012552 review Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000002996 emotional effect Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 241001123248 Arma Species 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000000638 solvent extraction Methods 0.000 abstract 1
- 235000021167 banquet Nutrition 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 229910052711 selenium Inorganic materials 0.000 description 3
- 239000011669 selenium Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004308 accommodation Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (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 relates to a hotel intelligent question-answer recommendation and decision support analysis method and a system, which are used for realizing the following steps: the crawler is utilized to crawl mass data of a plurality of tourism websites quickly and efficiently, and the mass data are updated in real time; extracting comment information hotel attribute keywords by using an algorithm, carrying out sentiment analysis on each keyword, and partitioning; arranging a related entity database, an attribute database and a customer-hotel relation database, and constructing a knowledge graph; the knowledge map tool and the query language are used to compile a question-answer template, and the natural language processing technology and the entity recognition technology are used to recognize the left message and automatically answer the question of the system user. The invention has the beneficial effects that: learning customer preferences, intelligently recommending that a hotel automatically replies to customer comment information for the customer according to the customer personality, and realizing oriented sending of hotel advertisement consultation in a mail or message form; the system is continuously optimized by self, question and answer templates are enriched, intelligent sequencing is achieved, and the system is more suitable for people.
Description
Technical Field
The invention relates to a hotel intelligent question-answer recommendation and decision support analysis method and system, and belongs to the field of computers.
Background
With the increasing proportion of social media networks in the decision-making of customers, various travel modes such as commercial travel, family travel, academic travel, medical travel and country travel are deeply enjoyed, and travel subsidiary consumer goods such as air tickets, civil accommodations, hotels and entrance tickets ordered through a travel website become a mainstream for travel product sales. The online and offline sales mode enables tourism to become more convenient and faster. The method has the advantages that the comment information of the tourist website plays a great role in the process of purchasing commodities by customers, how to effectively mine the comment information, arranging the disordered comment information of the customers into a searchable and structured database, arranging the useful information of the social media network into a structured knowledge network, providing real and reliable purchasing recommendation for the customers, providing effective decision support analysis for merchants, and realizing intelligent interaction among the comment information knowledge base, the customers and the merchants, and is the main purpose and key point of the method. For this reason, the advent of artificial intelligence technology provides the present invention with technological possibilities for this purpose. The invention realizes intelligent response, intelligent hotel recommendation and decision support analysis of the hotel based on the knowledge map, self-recognition language processing and emotion analysis artificial intelligence technology based on the diversity, authenticity, real-time property and huge amount of the tourism website information, thereby saving the time for browsing each merchant comment information for the customer, providing real-time decision support for the merchant, and effectively promoting the merchant to realize customer relationship management, customer satisfaction and loyalty evaluation, effectively orienting personality promotion dynamic information and the like.
The number of the tourism websites existing in the world is large, with the rise of travel enthusiasm going abroad, hotels where the tourism websites are located are all over places of a management ball, and in order to comprehensively dig available information of each website and quickly establish a relatively complete real-time knowledge map, a crawler is established on the basis of 'multi-process + multi-thread', and useful information of different websites on different hotels is quickly crawled and updated in real time.
Disclosure of Invention
The invention provides an intelligent hotel question-answer recommendation and decision support analysis method and system, wherein the system adopts Python programming language, and adopts related program packages such as datetime, pymongo, pysql, download, mongb _ queue, downloading, multiprocessing, bs, re, and selenium to construct a main module on a Pycharm IDE platform. The invention firstly constructs a multithreading and multiprocessing high-speed crawler to crawl hotel social media network customers, hotel attribute information and hotel and customer relationship information, such as reviewer ID, check-in time, type of living room, travel type, place of birth, hotel star level, affiliated group, comment information, scoring information and the like. And then, using public Word banks such as Jieba, Google and the like to cut words and remove stop words, using related Python databases such as genesis, Word2Vec, sklern, numpy, collections, math and the like to generate a Word vector matrix, using a decision tree (keyword: prediction type 1, non-keyword: prediction type 2) not limited to TextRank, LDA, TF-IDF, TPR and random forest bureau to extract keywords (prediction type 1), using "" as a separator to generate a short sentence, and using the short sentence as a unit to calculate emotion scores of the keywords (emotion scores are continuously distributed in [0,1], "1" as a positive emotion score and "0" as a negative emotion score). Then the invention classifies and arranges the database into an entity database containing attributes and an entity relation database. Then, the invention takes the entity data as nodes and the relationship data as node relationships, based on but not limited to a Neo4J knowledge graph construction tool and a Python programming language, a knowledge graph is established by using py2Neo, and a problem template is designed aiming at the three aspects of the entity, the attribute and the relationship, so that the invention is used for the convenient entity, attribute and relationship query of the system user. In addition, the invention designs a question input box, and uses natural language processing technology to identify the condition sentence and the query sentence, and identify the entity node, attribute and mutual relation of the condition sentence and the query sentence, thereby realizing the scene constructed by the system user, understanding the question background and the question content, and answering the question provided by the user according to the constructed knowledge graph. Meanwhile, according to customers carrying different attributes, the top three hotels with highest emotional average scores of the concerned hotel attributes are recommended based on the hotel attributes concerned by the customers. In addition, the system automatically identifies the comment content of the customer by using a natural language processing technology, edits and sets an automatic reply, performs natural language processing on the advertisement consultation content issued by the hotel, identifies the entity and the related attributes thereof, and automatically sends and recommends different customers in the forms of mail, automatic reply of messages and the like.
The technical scheme of the invention comprises a hotel intelligent question-answer recommendation and decision support analysis method, which is characterized by comprising the following steps: s100, compiling and using a crawler to crawl relationship data between a hotel and a customer from a hotel social media network; s200, extracting hotel attribute keywords from the comment information, and performing sentiment analysis and scoring on each attribute keyword; s300, creating and arranging an entity database, a hotel attribute database, a customer attribute database and an entity relationship database, and outputting results; s400, integrating the results output in the S300, taking the integrated results as knowledge graph input data, and establishing a knowledge graph of the customer and the hotel; s500, establishing an intelligent question-answer template for the frequently-used question answers of the hotel and the customer according to the database obtained in the S300; s600, creating a recommendation module for attributes of the hotel and the customer according to the database obtained in the S300; s700, compiling decision support analysis modules for attributes of the hotel and the customer according to the database obtained in the S300; and S800, optimizing the condition record of the system use generated in the S500 by using machine learning.
According to the hotel intelligent question-answer recommendation and decision support analysis method, S100 specifically comprises the following steps: compiling and using a high-speed crawler to crawl customers, hotels and customer-hotel relationship data from a hotel social media network; wherein, the customer data includes but is not limited to comment ID, check-in time, house type, travel type, place of birth; the information of the hotel includes but is not limited to the star level of the hotel and the affiliated group; hotel and customer relationship data includes but is not limited to review information and scoring information; the crawled information includes structural, semi-structural and non-structural data.
According to the hotel intelligent question-answer recommendation and decision support analysis method, S200 specifically comprises the following steps: s201, importing a hotel special word database, cutting words of the crawled comment data by using related corpora such as Jieba and Google English corpora and removing stop words; s202, generating a Word vector matrix by using but not limited to algorithms such as TextRank, LDA, TF-IDF, TPR and the like, and Python databases of genim, Word2Vec, sklern, numpy, categories and math, extracting keywords by using but not limited to a random forest office decision tree, calculating accuracy and recall rate, calculating an average value, and outputting the keywords in sequence; the accuracy rate refers to the percentage of the predicted keywords in the predicted 1, the recall rate refers to the percentage of the predicted keywords in the predicted 1, the predicted category of the keywords in the predicted 1 and the predicted category of the non-keywords in the predicted 2; s203, positioning word vectors around each keyword, dividing the word vectors into a plurality of short sentences by using a 'divider', identifying and counting emotion words around the keywords by using the short sentences as units, marking positive emotion words as 1 and negative emotion words as 0, solving the average emotion scores of the whole comment on different keywords, finally solving the average emotion score of each customer on the hotel, dividing the emotion scores into percentages to serve as recommendation indexes of the customers on the hotel, dispersing the scores in intervals of [0,0.5 ] and [0.5,1], and marking the relationship results as not recommending 0 and recommending 1.
According to the hotel intelligent question-answer recommendation and decision support analysis method, S300 specifically comprises the following steps: s301, arranging an entity database containing attributes, wherein the entity database comprises: the hotel property database comprises but is not limited to attributes such as hotel star levels, affiliated groups and the like, and the customer property database comprises but is not limited to customer comment IDs, ages, sexes, places of birth, travel types, house types and concerned hotel property keywords; s302, arranging an entity relation database, wherein the entity relation database comprises: the method comprises the steps of obtaining relations among customers, relations among hotels and relations among the customers and the hotels, wherein the relations among the customers comprise but are not limited to keywords of attributes of a certain hotel, such as same age, same sex, same house type, same country and the same mention, and the hotel relation data comprise but are not limited to keywords of same star level and the same group; the relationship between the customer and the hotel comprises whether the customer recommends the hotel or not and a recommendation index.
According to the hotel intelligent question-answer recommendation and decision support analysis method, S400 specifically comprises the following steps: taking entity data as nodes and relationship data as node relationships, including but not limited to building a knowledge graph using a Neo4J knowledge graph building tool, a Python programming language, and py2 Neo.
According to the hotel intelligent question-answer recommendation and decision support analysis method, S500 specifically comprises the following steps: s501, setting a question template according to the database obtained in S300, establishing an attribute, entity and relationship synonym library by using a py2neo and other related Python libraries, writing common questions into SPARQL and Cypher query sentences, establishing a common question-answer template, selecting a question-answer form, answering the common questions, wherein the questions comprise but are not limited to hotel customer number series conforming to attributes or relationships, relationship query among entities and the like, and intelligently sequencing the template through query records of a machine learning system user; s502, providing a question input box for inputting a message, wherein the message comprises but is not limited to hotel experience, expected expectation of a customer on a hotel and inquiry of a hotel manager for a hotel special message push target object, identifying an input question by using natural language processing, identifying a condition sentence and an inquiry sentence, respectively identifying entity nodes, attributes and interrelation of the condition sentence and the inquiry sentence, and outputting inquiry content according to the inquiry sentence of S501; s503, based on neural network deep learning related models such as LSTM and RNN, named entity recognition is carried out by using, but not limited to, CRF + +, NeuroNER and the like, entity nodes, attributes and mutual relations are labeled, questions are converted into a mode of 'condition input-result inquiry', the common questions in the mode are written into SPARQL and Cypher query sentences, question answers are established and results are output, and meanwhile, a message information 'condition input-result inquiry' mode is added into a system user record for machine learning, template optimization and intelligent sequencing.
According to the hotel intelligent question-answer recommendation and decision support analysis method, S600 specifically comprises the following steps: s601, recommending the first three hotels with highest emotional average score of attributes of the hotels in a specific area based on attributes of the hotels concerned by customers according to the customers with different attributes; s602, automatically identifying the comment content of the customer by using a natural language processing technology, editing and setting automatic reply, carrying out natural language processing on the advertisement consultation content issued by the hotel, identifying entities and relevant attributes thereof, and automatically sending and recommending different customers in the forms of e-mail, automatic reply of left messages and the like.
According to the hotel intelligent question-answer recommendation and decision support analysis method, S700 specifically comprises the following steps: and performing word cloud display on the keywords, performing descriptive analysis and information mining and graphic visualization on emotion analysis results, predicting the emotion scores of the attributes of the hotels by using but not limited to LSTM and ARMA algorithms, performing relevance exploration on the emotion scores by using but not limited to Apriori and Xgboost, and providing decision support data for different hotels.
According to the hotel intelligent question-answer recommendation and decision support analysis method, S800 specifically comprises the following steps: and S801, performing machine learning on the system use condition records generated in S500, continuously enriching templates and reordering, so that the system is more intelligent and easier to operate, namely performing machine learning on the system use record database generated in S500 and optimizing intelligent template sequencing.
The technical scheme of the invention also comprises a hotel intelligent question-answering recommendation and decision support analysis system which is used for executing any method, and the system comprises the following steps: the data acquisition module is used for compiling and using a crawler to crawl relationship data between the hotel and the customer from a hotel social media network; the keyword extraction and emotion analysis module is used for extracting hotel attribute keywords from the comment information, carrying out emotion analysis on each attribute keyword and scoring; the knowledge map database preparation module is used for creating and arranging an entity database, a hotel attribute database, a customer attribute database and an entity relationship database and outputting results; the knowledge graph establishing module is used for integrating the results output by the knowledge graph database preparation module, taking the integrated results as knowledge graph input data and establishing a knowledge graph of a customer and a hotel; the intelligent question-answering module is used for intelligently answering common problems and complex problems of the customer and the hotel manager; the intelligent recommendation module is used for recommending related hotels and realizing the pushing and automatic reply of the hotel to the individual advertisement consultation of the customers; the decision support analysis module is used for providing decision support and data analysis; and the system optimization module is used for optimizing the hotel intelligent question-answer recommendation and decision support analysis system based on the knowledge graph, the natural language processing and the emotion analysis.
The invention has the beneficial effects that: the method comprises the following steps of (1) quickly and efficiently crawling mass data of a plurality of travel websites by using a multithreading and multiprocessing crawler, and updating in real time; extracting comment information hotel attribute keywords by using an algorithm, carrying out sentiment analysis on each keyword, and distributing scores in an interval of [0,1 ]; arranging a related entity database, an attribute database and a 'customer-hotel' relation database, and constructing a 'customer-hotel' knowledge map; writing a question-answering template by using a knowledge map tool and a query language, and identifying a left message and automatically answering the question of a system user by using a natural language processing technology and an entity identification technology; learning customer preferences through an artificial intelligence technology, recommending a hotel to the customer in an individual intelligent manner, automatically replying the customer comment information and the hotel advertisement consultation information only by using a natural language processing technology and an entity identification technology, and realizing oriented sending of the hotel advertisement consultation in a mail or message form; meanwhile, the system continuously optimizes the system by self through the learning processing of the database of the system use records, enriches the question and answer templates and the intelligent sequencing, and makes the system more suitable for the citizens.
Drawings
FIG. 1 is a general flow diagram of a method according to an embodiment of the invention;
FIG. 2 is a block diagram illustrating a system architecture according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a "multi-thread + multi-process" travel website high-speed crawler according to an embodiment of the invention;
FIG. 4 is a schematic view of a one-stop crawler according to an embodiment of the present invention;
fig. 5 is a schematic flow chart of an intelligent question answering module method according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention provides a hotel intelligent question-answering recommendation and decision support analysis method and system, which relate to the technologies of web crawlers, parallel computing, machine learning, knowledge maps, database management, recommendation models, prediction models, data mining and the like, and the conception, the specific structure and the generated technical effect of the invention are clearly and completely described by combining embodiments and drawings so as to fully understand the purpose, the scheme and the effect of the invention.
It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature or indirectly fixed or connected to the other feature. Furthermore, the descriptions of upper, lower, left, right, etc. used in the present disclosure are only relative to the mutual positional relationship of the constituent parts of the present disclosure in the drawings. As used in this disclosure, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any combination of one or more of the associated listed items.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element of the same type from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure. The use of any and all examples, or exemplary language ("e.g.," such as "or the like") provided herein, is intended merely to better illuminate embodiments of the invention and does not pose a limitation on the scope of the invention unless otherwise claimed.
FIG. 1 shows a general flow diagram of a method according to an embodiment of the invention. The method comprises the following specific steps:
(1) data acquisition of the tourism website: the method comprises the steps of designing and constructing a general high-speed crawler of a multi-thread and multi-process tourism website by using related program packages such as datetime, pymongo, pysql, download, mongodb _ queue, reading, multiprocessing, bs, re and selenium of a Python programming language, and crawling related customers, hotels and customer-hotel relationship data from a plurality of platforms of a social media network. Customer data includes, but is not limited to, review ID, check-in time, type of dwelling, type of travel, place of birth, etc.; the information of the hotel comprises but is not limited to the star level of the hotel, the affiliated group and the like; hotel and customer relationship data includes, but is not limited to, review information, scoring information, and the like. The crawling information comprises structural data, semi-structural data and unstructured data. For example: crawling Chinese and English data of 20 hotels, which are ranked the most front in 2017 years in a certain city, of three travel websites, namely a travel website 1, a travel website 2 and a travel website 3, running processes on the cpu3 different cores respectively by the travel website 1, the travel website 2 and the travel website 3, wherein in each process, the websites are stored in a 'to-be-crawled website queue', 'crawling website queue' and 'crawled website queue', and crawl information of a reviewer ID, a reviewer place of birth, a reviewer age, a reviewer house type, a review time, a review title, review content, a hotel star level, a hotel group and the like.
Fig. 3 is a schematic diagram of a high-speed crawler of a multi-thread and multi-process tourism website, and fig. four is a schematic diagram of a one-stop crawler flow: the method comprises the steps of arranging a hotel list to be crawled, inputting hotel names into different tourism websites, constructing a url list, taking each tourism website as one process, arranging a website queue to be crawled, a website queue to be crawled and a website queue to be crawled by using a queue ordering mode in each process, setting reasonable Timeout as a threshold value, placing websites with processing time exceeding the set Timeout in the website queue to be crawled, and placing websites which have been crawled successfully in the website queue to be crawled. And (4) taking the process of crawling target data as a daemon thread, and finally storing the crawled data into a database. In this regard, different processes may run on different cores of the cup, and different computer online or cloud crawling may be implemented. For models adopted in different thread crawling processes, a one-stop model of simulating a browser, acquiring webpage codes, crawling required data, simulating clicking on the next page, closing the browser and storing the crawling data can be used for crawling.
(2) Extracting key words and analyzing emotion: importing a hotel special word database, and using related corpora such as Jieba and Google English corpora to cut words of the crawled comment data and remove stop words; the method comprises the steps of using algorithms such as but not limited to TextRank, LDA, TF-IDF, TPR and the like, using related Python databases such as genesis, Word2Vec, sklern, numpy, collections, math and the like to generate a Word vector matrix, extracting keywords (prediction type 1) by using a random forest local decision tree (keywords: prediction type 1 and non-keywords: prediction type 2), calculating accuracy and recall, calculating an average value, and outputting the average value in sequence. Wherein the accuracy rate refers to the percentage of the predicted 1 keywords in the predicted keywords, and the recall rate refers to the percentage of the predicted 1 keywords in the original keywords. Positioning word vectors around each keyword, dividing the word vectors into a plurality of short sentences by using a 'separator', identifying and counting emotion words around the keywords by using the short sentences as units, marking positive emotion words as 1 and negative emotion words as 0, solving the average emotion scores of the whole comment on different keywords, finally solving the average emotion score of each customer on the hotel, dividing the emotion scores into percentages to serve as the recommendation index of the customer on the hotel, dispersing the scores in the intervals of 0,0.5) and 0.5,1, and marking the relationship results as 'not recommended 0, recommended 1'. For example, "banquet hall" and "restaurant" are two hotel attribute keywords, and "banquet hall in a certain city is decorated very bright, and a restaurant is available, and the banquet hall is out of service", and the attention of the customer is "banquet hall" and "restaurant", and the emotion scores of both are "(1 +0)/2 ═ 0.5" and "1", respectively.
(3) And (3) sorting and establishing an entity, an attribute and a relational database: and (3) arranging an entity database containing attributes: the entity database comprises a hotel attribute database and a customer attribute database, wherein the hotel attribute database comprises attributes such as hotel star levels, affiliated groups and the like, and the customer attribute database comprises attributes such as customer review ID, age, gender, places of birth, travel types, house types, concerned hotel attribute keywords (the attribute keywords are mentioned as 1 in the review, and the attribute keywords are not mentioned as 0); sorting the entity relational database: the entity relationship database comprises relationships among customers, relationships among hotels and relationships among customers and hotels, wherein relationship data among customers comprise but are not limited to keywords (the relationships are specific to a single age group, sex, house type, place of birth, attribute keywords and the like) of attributes of a hotel, and the data include but are not limited to keywords (the relationships are specific to a star level, a group name and the like) of attributes of a hotel; the relationship between the customer and the hotel comprises whether the customer recommends the hotel or not and a recommendation index. For example: the customer attribute database is: a, customer: mini, birth date: china, house type: large bed room, injection point: "service"; ivanka, birth place: china, house type: no haze room, note point: "service" and "room". Hotel property database: crown holiday hotel in a certain city: star level: 5, group: intercontinental, "service" emotion averages: 0.8, "room" emotion average score: 0.9; crown holiday hotel in certain city in certain place: star rating: 5, group: intercontinental, "service" emotion averages: 0.7, "room" emotion average score: 0.6. a relational database: the birth places of the customers A and B are both China, and both concern service; the crown holiday hotel in a certain city and the crown holiday hotel in a certain city belong to the intercontinental group and are 5-star-level hotels.
(4) Establishing a knowledge graph of 'customer-hotel', establishing a common problem template of the customer and the hotel and intelligently processing question and answer search by natural language: taking entity data as nodes and relational data as node relations, and establishing a knowledge graph by using py2Neo based on but not limited to a Neo4J knowledge graph construction tool and a Python programming language; the problem template may be: 1. what are the best hotels in a certain city to "serve"? 2. Where do customers focus on "price"? 3. ____ (where number (1) service is filled, (2) room, (3) banquet hall, (4) facilities, etc., can be filled which are a number of) are there the recommended hotels? 4. What percentage of customers are at ____ (where fill out numbers (1) for service, (2) room, (3) banquet hall, (4) facilities, etc., can fill out more)? Etc. of
FIG. 4 is a flow chart of a one-stop crawler according to an embodiment of the present invention.
Fig. 5 is a schematic flow chart of an intelligent question answering module method according to an embodiment of the present invention: s501, setting a question template according to the database obtained in S300, establishing an attribute, entity and relationship synonym library by using a py2neo and other related Python libraries, writing common questions into SPARQL and Cypher query sentences, establishing a common question-answer template, selecting a question-answer form, answering the common questions, wherein the questions comprise but are not limited to hotel customer number series conforming to attributes or relationships, relationship query among entities and the like, and meanwhile, intelligently sequencing the templates through query records of users of a machine learning system; providing a question input box, inputting a long message, wherein the message is rich in information and can be the experience of the hotel, the expectation of a customer on the hotel is met, a hotel manager uses natural language processing to identify the input question aiming at the inquiry of a hotel special message push target object and the like, a condition sentence and an inquiry sentence are identified, the entity nodes, the attributes and the mutual relations of the condition sentence and the inquiry sentence are respectively identified, and the inquiry content is output by combining an S501 inquiry sentence; based on neural network deep learning related models such as LSTM and RNN, named entity recognition is carried out by using, but not limited to, CRF + +, NeuroNER and the like, entity nodes, attributes and mutual relations are labeled, the problems are converted into a mode of 'condition input-result inquiry', the common problems in the mode are compiled into SPARQL and Cypher query sentences, questions and answers are built and results are output, and meanwhile, a message information 'condition input-result inquiry' mode is added into a system user record for machine learning, template optimization and intelligent sequencing. The problem template may be: 1. what are the best hotels in a certain city to "serve"? 2. Where do customers focus on "price"? 3. ____ (where number (1) service is filled, (2) room, (3) banquet hall, (4) facilities, etc., can be filled which are a number of) are there the recommended hotels? 4. What percentage of customers are at ____ (where fill out numbers (1) for service, (2) room, (3) banquet hall, (4) facilities, etc., can fill out more)? And the like.
(5) According to the hotel attribute emotion score and the customer attention attribute, realizing individual recommendation, automatic hotel reply and advertisement consultation push: recommending the first three hotels with the highest emotional average score of attributes of the hotels in a specific area according to the attributes of the hotels concerned by customers with different attributes; the method comprises the steps of automatically identifying comment contents of customers by using a natural language processing technology, editing and setting automatic reply, carrying out natural language processing on advertisement consultation contents issued by a hotel, identifying entities and relevant attributes thereof, and automatically sending and recommending different customers in the forms of e-mails, automatic reply of messages and the like. For example: a certain comment, when I come out of a toilet today, the floor is very smooth, I just fall a foot at a bad place, and the heart is filled. "entity word: the emotion scores of a toilet, a floor, a missing emotion word and the floor are 0, and the total emotion score is 0, then the system automatically replies: "get a sorry you unsatisfied with our floor, we will deal with it immediately, hope you have happy recall next time"; the latest marketing consultation of crown holidays in a certain place is that the entity words of the consultation are western-style restaurant and price, namely that the western-style restaurant sells 99-generation 200-generation cash voucher during the current spring festival, and the message is sent to customers paying attention to the western-style restaurant and the price.
(6) And (3) performing time series prediction and correlation analysis on the attribute emotion analysis scores, and providing decision support for a decider: performing word cloud display on the keywords, performing descriptive analysis and information mining and graphic visualization on emotion analysis results, predicting the emotion scores of attributes of the hotels by using but not limited to LSTM and ARMA algorithms, performing relevance exploration on the emotion scores by using but not limited to Apriori and Xgboost, and providing decision support data for different hotels;
(7) the machine learning system uses the record, realizes system optimization: and (3) performing machine learning on the system use condition records generated in the step (S500), continuously enriching templates and reordering, so that the system is more intelligent and easier to operate, namely performing machine learning on the system use record database generated in the step (S500) and optimizing intelligent template sequencing.
The technical scheme of the invention specifically discloses a more detailed implementation scheme, which specifically comprises the following steps:
(1) the embodiment designs and writes a multithreading and multiprocessing tourism website high-speed crawler to crawl comments and customer information of 28 hotel hotels in a certain city from 8 months 8 to 2018 months 8, a tourism website 1, a tourism website 2 and the local network by using a Python programming language, datetime, pymongo, pysql, download, MongoDB _ queue, reading, multiprocessing, bs, re, selenium and other related packages, wherein the Pycharm IDE compiler is used for crawling 49702 comment information as a basic data storage unit and using a 4-core processor computer Ethernet as a crawling environment for 3 hours and 42 minutes.
(2) The method uses a Jieba and Google English corpus, adopts Python to compile, uses related Python databases such as genim, Word2Vec, sklern, numpy, collections, math and the like, removes stop words, adopts a TF-ITF algorithm to extract the first 600 entity keywords, obtains 25 hotel attribute keywords in total through synonym replacement, and uses an emotion analysis model to carry out emotion scoring on the 25 attributes of the 28 hotels.
(3) The databases are arranged into a customer-attribute database, a hotel-attribute database and a relational database, wherein 43055 customers with no repeated comment ID are provided, 4 customer attributes are respectively 'place of birth', 'house type', 'tour mode', 'comment date/stay-in date', 29 hotel attributes are provided, and respectively are 25 attribute emotion average scores, total emotion average scores, star grades, regions and groups.
(4) 43055 customers and 28 hotels serve as entity nodes, customer attributes and hotel attributes serve as related attribute features, a Neo4J knowledge graph construction tool and a Python programming language are used, and a py2Neo is imported to establish a knowledge graph model.
(5) Setting a problem template: 1. what are the best hotels in a certain city to "serve"? 2. Where do customers focus on "price"? 3. ____ (where number (1) service is filled, (2) room, (3) banquet hall, (4) facilities, etc., can be filled which are a number of) are there the recommended hotels? 4. What percentage of customers are at ____ (where fill out numbers (1) for service, (2) room, (3) banquet hall, (4) facilities, etc., can fill out more)? The method comprises the steps of establishing an attribute, entity and relationship synonym library by using a py2neo and other related Python libraries, writing common questions into SPARQL query sentences, establishing a common question-answer template, selecting a question-answer form, answering the common questions, realizing hotel customer number series of attributes or relationships, querying relationships among entities and the like.
(6) Based on an RNN neural network deep learning related model, named entity recognition is carried out by using NeuroNER, label labeling is carried out on entity nodes, attributes and mutual relations, a problem is converted into a mode of 'conditional input-result query', common problems of the mode are written into SPARQL query sentences, question answers are established, and results are output.
(7) The system usage record (5) is formulated as a mode of "conditional input-result query", for example: a system user enters in an input box: "a hotel in a certain city has good service under intercontinental flag, and generally has more customers" the system converts it into: conditions are as follows: hotel address: in a certain city, the emotion analysis score > of "service" is 0.5, and the hotel group: intercontinental regions; inquiring: is the customer born? ", put it into the system usage record database and add it to the template, cluster the system usage record data and reorder it, place the class selected to contain the query at the top of the user question template. Thereby achieving the optimization of the whole system.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.
Claims (10)
1. A hotel intelligent question-answer recommendation and decision support analysis method is characterized by comprising the following steps:
s100, crawling relationship data between the hotel and the customer from a hotel social media network by using a crawler;
s200, extracting hotel attribute keywords from the comment information, and performing sentiment analysis and scoring on each attribute keyword;
s300, creating and arranging an entity database, a hotel attribute database, a customer attribute database and an entity relationship database, and outputting results;
s400, integrating the results output in the S300, taking the integrated results as knowledge graph input data, and establishing a knowledge graph of the customer and the hotel;
s500, establishing an intelligent question-answer template for the frequently-used question answers of the hotel and the customer according to the database obtained in the S300;
s600, creating a recommendation module for attributes of the hotel and the customer according to the database obtained in the S300;
s700, compiling decision support analysis modules for attributes of the hotel and the customer according to the database obtained in the S300;
and S800, optimizing the condition record of the system use generated in the S500 by using machine learning.
2. The hotel intelligent question-answer recommendation and decision support analysis method according to claim 1, wherein the S100 specifically comprises:
compiling and using a high-speed crawler to crawl customers, hotels and customer-hotel relationship data from a hotel social media network;
wherein, the customer data includes but is not limited to comment ID, check-in time, house type, travel type, place of birth;
the information of the hotel includes but is not limited to the star level of the hotel and the affiliated group;
hotel and customer relationship data includes but is not limited to review information and scoring information;
the crawled information includes structural, semi-structural and non-structural data.
3. The hotel intelligent question-answer recommendation and decision support analysis method according to claim 1, wherein the S200 specifically comprises:
s201, importing a hotel special word database, cutting words of the crawled comment data by using related corpora such as Jieba and Google English corpora and removing stop words;
s202, generating a Word vector matrix by using but not limited to algorithms such as TextRank, LDA, TF-IDF, TPR and the like, and Python databases of genim, Word2Vec, sklern, numpy, categories and math, extracting keywords by using but not limited to a random forest office decision tree, calculating accuracy and recall rate, calculating an average value, and outputting the keywords in sequence;
the accuracy rate refers to the percentage of the predicted keywords in the predicted 1, the recall rate refers to the percentage of the predicted keywords in the predicted 1, the predicted category of the keywords in the predicted 1 and the predicted category of the non-keywords in the predicted 2;
s203, positioning word vectors around each keyword, dividing the word vectors into a plurality of short sentences by using a 'divider', identifying and counting emotion words around the keywords by using the short sentences as units, marking positive emotion words as 1 and negative emotion words as 0, solving the average emotion scores of the whole comment on different keywords, finally solving the average emotion score of each customer on the hotel, dividing the emotion scores into percentages to serve as recommendation indexes of the customers on the hotel, dispersing the scores in intervals of [0,0.5 ] and [0.5,1], and marking the relationship results as not recommending 0 and recommending 1.
4. The hotel intelligent question-answer recommendation and decision support analysis method according to claim 1, wherein the S300 specifically comprises:
s301, arranging an entity database containing attributes, wherein the entity database comprises:
the hotel property database comprises but is not limited to attributes such as hotel star levels, affiliated groups and the like, and the customer property database comprises but is not limited to customer comment IDs, ages, sexes, places of birth, travel types, house types and concerned hotel property keywords;
s302, arranging an entity relation database, wherein the entity relation database comprises:
the method comprises the steps of obtaining relations among customers, relations among hotels and relations among the customers and the hotels, wherein the relations among the customers comprise but are not limited to keywords of attributes of a certain hotel, such as same age, same sex, same house type, same country and the same mention, and the hotel relation data comprise but are not limited to keywords of same star level and the same group;
the relationship between the customer and the hotel comprises whether the customer recommends the hotel or not and a recommendation index.
5. The hotel intelligent question-answer recommendation and decision support analysis method according to claim 1, wherein the S400 specifically comprises:
taking entity data as nodes and relationship data as node relationships, including but not limited to building a knowledge graph using a Neo4J knowledge graph building tool, a Python programming language, and py2 Neo.
6. The hotel intelligent question-answer recommendation and decision support analysis method according to claim 1, wherein the S500 specifically comprises:
s501, setting a question template according to the database obtained in S300, establishing an attribute, entity and relationship synonym library by using a py2neo and other related Python libraries, writing common questions into SPARQL and Cypher query sentences, establishing a common question-answer template, selecting a question-answer form, answering the common questions, wherein the questions comprise but are not limited to hotel customer number series conforming to attributes or relationships, relationship query among entities and the like, and intelligently sequencing the template through query records of a machine learning system user;
s502, providing a question input box for inputting a message, wherein the message comprises but is not limited to hotel experience, expected expectation of a customer on a hotel and inquiry of a hotel manager for a hotel special message push target object, identifying an input question by using natural language processing, identifying a condition sentence and an inquiry sentence, respectively identifying entity nodes, attributes and interrelation of the condition sentence and the inquiry sentence, and outputting inquiry content according to the inquiry sentence of S501;
s503, based on neural network deep learning related models such as LSTM and RNN, named entity recognition is carried out by using, but not limited to, CRF + +, NeuroNER, label marking is carried out on entity nodes, attributes and mutual relations, the problems are converted into a mode of 'condition input-result inquiry', the common problems in the mode are compiled into SPARQL and Cypher query sentences, questions and answers are built and results are output, meanwhile, a message leaving information 'condition input-result inquiry' mode is added into a system user record, machine learning is carried out, templates are optimized, and intelligent sequencing is carried out.
7. The hotel intelligent question-answer recommendation and decision support analysis method according to claim 1, wherein the S600 specifically comprises:
s601, recommending the first three hotels with highest emotional average score of attributes of the hotels in a specific area based on attributes of the hotels concerned by customers according to the customers with different attributes;
s602, automatically identifying the comment content of the customer by using a natural language processing technology, editing and setting automatic reply, carrying out natural language processing on the advertisement consultation content issued by the hotel, identifying entities and relevant attributes thereof, and automatically sending and recommending different customers in the forms of e-mail, automatic reply of left messages and the like.
8. The hotel intelligent question-answer recommendation and decision support analysis method according to claim 1, wherein the S700 specifically comprises:
and performing word cloud display on the keywords, performing descriptive analysis and information mining and graphic visualization on emotion analysis results, predicting the emotion scores of the attributes of the hotels by using but not limited to LSTM and ARMA algorithms, performing relevance exploration on the emotion scores by using but not limited to Apriori and Xgboost, and providing decision support data for different hotels.
9. The hotel intelligent question-answer recommendation and decision support analysis method according to claim 1, wherein the S800 specifically comprises:
and S801, performing machine learning on the system use condition records generated in S500, continuously enriching templates and reordering, so that the system is more intelligent and easier to operate, namely performing machine learning on the system use record database generated in S500 and optimizing intelligent template sequencing.
10. A hotel intelligent question-answering recommendation and decision support analysis system for performing the method of any of claims 1-9, the system comprising:
the data acquisition module is used for compiling and using a crawler to crawl relationship data between the hotel and the customer from a hotel social media network;
the key word extraction and emotion analysis module is used for extracting hotel attribute key words from the comment information, carrying out emotion analysis on each attribute key word and scoring;
the knowledge map database preparation module is used for creating and arranging an entity database, a hotel attribute database, a customer attribute database and an entity relationship database and outputting results;
the knowledge graph establishing module is used for integrating the results output by the knowledge graph database preparation module, taking the integrated results as knowledge graph input data and establishing a knowledge graph of a customer and a hotel;
the intelligent question-answering module is used for intelligently answering common problems and complex problems of the customer and the hotel manager;
the intelligent recommendation module is used for recommending related hotels and realizing the pushing and automatic reply of the hotel to the individual advertisement consultation of the customers;
the decision support analysis module is used for providing decision support and data analysis;
and the system optimization module is used for optimizing the hotel intelligent question-answer recommendation and decision support analysis system based on the knowledge graph, the natural language processing and the emotion analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910154681.XA CN110807091B (en) | 2019-03-01 | 2019-03-01 | Hotel intelligent question-answer recommendation and decision support analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910154681.XA CN110807091B (en) | 2019-03-01 | 2019-03-01 | Hotel intelligent question-answer recommendation and decision support analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110807091A true CN110807091A (en) | 2020-02-18 |
| CN110807091B CN110807091B (en) | 2023-08-18 |
Family
ID=69487332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910154681.XA Active CN110807091B (en) | 2019-03-01 | 2019-03-01 | Hotel intelligent question-answer recommendation and decision support analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110807091B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339269A (en) * | 2020-02-20 | 2020-06-26 | 来康科技有限责任公司 | Knowledge graph question-answer training and application service system with automatically generated template |
| CN111341456A (en) * | 2020-02-21 | 2020-06-26 | 中南大学湘雅医院 | Method and device for generating diabetic foot knowledge map and readable storage medium |
| CN111831880A (en) * | 2020-02-21 | 2020-10-27 | 桂林电子科技大学 | Intelligent question and answer method based on micro hotel platform |
| CN112199484A (en) * | 2020-10-12 | 2021-01-08 | 上海伊巢网络科技有限公司 | Artificial intelligence customer service reply system for hotel residents |
| CN112256852A (en) * | 2020-10-28 | 2021-01-22 | 北京软通智慧城市科技有限公司 | Scenic spot comment data processing method and device, electronic equipment and storage medium |
| CN113158082A (en) * | 2021-05-13 | 2021-07-23 | 聂佼颖 | Artificial intelligence-based media content reality degree analysis method |
| CN113190664A (en) * | 2021-04-25 | 2021-07-30 | 内蒙古工业大学 | Dynamic decision-making method for replying emotion in multi-turn conversation |
| WO2021179455A1 (en) * | 2020-03-10 | 2021-09-16 | 深圳市华侨城创新研究院有限公司 | Scientometric method for measuring happiness indexes of tourist attractions |
| CN113641798A (en) * | 2021-10-12 | 2021-11-12 | 成都晓多科技有限公司 | Identification method and system for disruptive comments of merchants |
| US11222358B2 (en) | 2020-05-29 | 2022-01-11 | At&T Intellectual Property I, L.P. | Facilitation of artificial intelligence predictions of telecommunications customers |
| CN116823321A (en) * | 2023-07-06 | 2023-09-29 | 青岛酒店管理职业技术学院 | Method and system for analyzing economic management data of electric business |
| CN117522533A (en) * | 2024-01-08 | 2024-02-06 | 江西求是高等研究院 | Hotel intelligent searching method and system |
| CN118013390A (en) * | 2024-04-10 | 2024-05-10 | 北京铁力山科技股份有限公司 | Intelligent workbench control method and system based on big data analysis |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117467A (en) * | 2011-03-03 | 2011-07-06 | 南通大学 | Question and answer mode online shopping guide method |
| CN103246677A (en) * | 2012-02-13 | 2013-08-14 | 广州淘信互联网科技有限公司 | Search method and search system on basis of social intercourse |
| US20140129493A1 (en) * | 2012-10-11 | 2014-05-08 | Orboros, Inc. | Method and System for Visualizing Complex Data via a Multi-Agent Query Engine |
| WO2017010652A1 (en) * | 2015-07-15 | 2017-01-19 | 포항공과대학교 산학협력단 | Automatic question and answer method and device therefor |
| US20170132676A1 (en) * | 2015-11-09 | 2017-05-11 | Anupam Madiratta | System and method for hotel discovery and generating generalized reviews |
| US20170193086A1 (en) * | 2015-12-31 | 2017-07-06 | Shanghai Xiaoi Robot Technology Co., Ltd. | Methods, devices, and systems for constructing intelligent knowledge base |
| CN107633084A (en) * | 2017-09-28 | 2018-01-26 | 武汉虹旭信息技术有限责任公司 | Based on the public sentiment managing and control system and its method from media |
| CN107958091A (en) * | 2017-12-28 | 2018-04-24 | 北京贝塔智投科技有限公司 | A kind of NLP artificial intelligence approaches and interactive system based on financial vertical knowledge mapping |
| WO2018072563A1 (en) * | 2016-10-18 | 2018-04-26 | 中兴通讯股份有限公司 | Knowledge graph creation method, device, and system |
| CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
| CN108182262A (en) * | 2018-01-04 | 2018-06-19 | 华侨大学 | Intelligent Answer System construction method and system based on deep learning and knowledge mapping |
| CN109145102A (en) * | 2018-09-06 | 2019-01-04 | 杭州安恒信息技术股份有限公司 | Intelligent answer method and its knowledge mapping system constituting method, device, equipment |
| CN109388748A (en) * | 2018-09-26 | 2019-02-26 | 深圳壹账通智能科技有限公司 | A kind of answering method of comment information, storage medium and server |
-
2019
- 2019-03-01 CN CN201910154681.XA patent/CN110807091B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117467A (en) * | 2011-03-03 | 2011-07-06 | 南通大学 | Question and answer mode online shopping guide method |
| CN103246677A (en) * | 2012-02-13 | 2013-08-14 | 广州淘信互联网科技有限公司 | Search method and search system on basis of social intercourse |
| US20140129493A1 (en) * | 2012-10-11 | 2014-05-08 | Orboros, Inc. | Method and System for Visualizing Complex Data via a Multi-Agent Query Engine |
| WO2017010652A1 (en) * | 2015-07-15 | 2017-01-19 | 포항공과대학교 산학협력단 | Automatic question and answer method and device therefor |
| US20170132676A1 (en) * | 2015-11-09 | 2017-05-11 | Anupam Madiratta | System and method for hotel discovery and generating generalized reviews |
| US20170193086A1 (en) * | 2015-12-31 | 2017-07-06 | Shanghai Xiaoi Robot Technology Co., Ltd. | Methods, devices, and systems for constructing intelligent knowledge base |
| WO2018072563A1 (en) * | 2016-10-18 | 2018-04-26 | 中兴通讯股份有限公司 | Knowledge graph creation method, device, and system |
| CN107633084A (en) * | 2017-09-28 | 2018-01-26 | 武汉虹旭信息技术有限责任公司 | Based on the public sentiment managing and control system and its method from media |
| CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
| CN107958091A (en) * | 2017-12-28 | 2018-04-24 | 北京贝塔智投科技有限公司 | A kind of NLP artificial intelligence approaches and interactive system based on financial vertical knowledge mapping |
| CN108182262A (en) * | 2018-01-04 | 2018-06-19 | 华侨大学 | Intelligent Answer System construction method and system based on deep learning and knowledge mapping |
| CN109145102A (en) * | 2018-09-06 | 2019-01-04 | 杭州安恒信息技术股份有限公司 | Intelligent answer method and its knowledge mapping system constituting method, device, equipment |
| CN109388748A (en) * | 2018-09-26 | 2019-02-26 | 深圳壹账通智能科技有限公司 | A kind of answering method of comment information, storage medium and server |
Non-Patent Citations (2)
| Title |
|---|
| 时雨;古天龙;宾辰忠;孙彦鹏;: "基于知识图谱的旅游景点问答系统" * |
| 王晓燕;丁鑫;: "酒店预订类APP评论界面优化及顾客关注焦点研究" * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339269A (en) * | 2020-02-20 | 2020-06-26 | 来康科技有限责任公司 | Knowledge graph question-answer training and application service system with automatically generated template |
| CN111339269B (en) * | 2020-02-20 | 2023-09-26 | 来康科技有限责任公司 | Knowledge graph question-answering training and application service system capable of automatically generating templates |
| CN111341456B (en) * | 2020-02-21 | 2024-02-23 | 中南大学湘雅医院 | Method and device for generating diabetic foot knowledge graph and readable storage medium |
| CN111341456A (en) * | 2020-02-21 | 2020-06-26 | 中南大学湘雅医院 | Method and device for generating diabetic foot knowledge map and readable storage medium |
| CN111831880A (en) * | 2020-02-21 | 2020-10-27 | 桂林电子科技大学 | Intelligent question and answer method based on micro hotel platform |
| WO2021179455A1 (en) * | 2020-03-10 | 2021-09-16 | 深圳市华侨城创新研究院有限公司 | Scientometric method for measuring happiness indexes of tourist attractions |
| US11222358B2 (en) | 2020-05-29 | 2022-01-11 | At&T Intellectual Property I, L.P. | Facilitation of artificial intelligence predictions of telecommunications customers |
| CN112199484A (en) * | 2020-10-12 | 2021-01-08 | 上海伊巢网络科技有限公司 | Artificial intelligence customer service reply system for hotel residents |
| CN112256852A (en) * | 2020-10-28 | 2021-01-22 | 北京软通智慧城市科技有限公司 | Scenic spot comment data processing method and device, electronic equipment and storage medium |
| CN113190664A (en) * | 2021-04-25 | 2021-07-30 | 内蒙古工业大学 | Dynamic decision-making method for replying emotion in multi-turn conversation |
| CN113190664B (en) * | 2021-04-25 | 2022-06-10 | 内蒙古工业大学 | Dynamic decision-making method for replying emotion in multi-turn conversation |
| CN113158082A (en) * | 2021-05-13 | 2021-07-23 | 聂佼颖 | Artificial intelligence-based media content reality degree analysis method |
| CN113641798A (en) * | 2021-10-12 | 2021-11-12 | 成都晓多科技有限公司 | Identification method and system for disruptive comments of merchants |
| CN116823321B (en) * | 2023-07-06 | 2024-02-06 | 青岛酒店管理职业技术学院 | Method and system for analyzing economic management data of electric business |
| CN116823321A (en) * | 2023-07-06 | 2023-09-29 | 青岛酒店管理职业技术学院 | Method and system for analyzing economic management data of electric business |
| CN117522533A (en) * | 2024-01-08 | 2024-02-06 | 江西求是高等研究院 | Hotel intelligent searching method and system |
| CN118013390A (en) * | 2024-04-10 | 2024-05-10 | 北京铁力山科技股份有限公司 | Intelligent workbench control method and system based on big data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110807091B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807091A (en) | Hotel intelligent question-answer recommendation and decision support analysis method and system | |
| CN111737495B (en) | Middle-high-end talent intelligent recommendation system and method based on domain self-classification | |
| Nirala et al. | A survey on providing customer and public administration based services using AI: chatbot | |
| Huyen | Designing machine learning systems | |
| Mehmann et al. | Crowd logistics− a literature review and maturity model | |
| CN105843781B (en) | For improving the method and system of the matrix sort of buffer efficiency | |
| CN105183869B (en) | Building knowledge mapping database and its construction method | |
| Liu et al. | Analyzing changes in hotel customers’ expectations by trip mode | |
| CN107257970A (en) | The problem of being carried out from structuring and unstructured data sources answer | |
| CN106663125A (en) | Question sentence generation device and computer program | |
| CN103679462A (en) | Comment data processing method and device and searching method and system | |
| CN106970991B (en) | Similar application identification method and device, application search recommendation method and server | |
| CN103917968A (en) | System and method for managing opinion networks with interactive opinion flows | |
| CN110442728A (en) | Sentiment dictionary construction method based on word2vec automobile product field | |
| KR102121901B1 (en) | System for online public fund investment management assessment service | |
| Nguyen et al. | Analysing online customer experience in hotel sector using dynamic topic modelling and net promoter score | |
| Pinto et al. | An ontology for modeling cultural heritage knowledge in urban tourism | |
| CN115860283B (en) | Contribution degree prediction method and device based on knowledge worker portrait | |
| Fuchs et al. | Business intelligence for destinations: Creating knowledge from social media | |
| Karpagam et al. | A mobile based intelligent question answering system for education domain | |
| Rao et al. | Friendly Interfaces Between Humans and Machines | |
| Simanjuntak et al. | Weighted Hybrid Recommendation System for Toba Tourism Based on Google Review Data | |
| Jiang et al. | Seize market opportunities: market segmentation, profile and monitoring through user-generated content | |
| Dixon et al. | Occupational models from 42 million unstructured job postings | |
| Amalina | Sentiresearch: Lexicon-Based Web Application For Indonesian Sentiment Analysis |
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 |