WO2021261987A1

WO2021261987A1 - System and method for providing destination recommendation to travelers

Info

Publication number: WO2021261987A1
Application number: PCT/MY2020/050186
Authority: WO
Inventors: Rabe'atuladawiyah SAMSER; Ma. Stella Tabora DOMINGO; Duc Nghia PHAM
Original assignee: Mimos Berhad
Priority date: 2020-06-22
Filing date: 2020-12-02
Publication date: 2021-12-30

Abstract

The present invention discloses a system and a method for providing a recommendation of tourist destinations. The system comprises a data collection unit, a data analysis unit and a recommendation unit. The data collection unit is configured for accessing world wide web to fetch world wide web data associated with a target destination. The data analysis unit is configured for processing the world wide web data received from the data collection unit. The data analysis unit comprises a sentence segmentation module, an entity analytic module, a sentence categorization module and a rating module. The recommendation unit is configured for providing a tourist destination recommendation in response to an initiator, comprising a list of suggested tourist destinations ordered based on a destination ranking list, accompanied with estimated costs of living and currency associated thereto, and trip-related products.

Description

SYSTEM AND METHOD FOR PROVIDING DESTINATION RECOMMENDATION TO TRAVELERS

FIELD OF THE INVENTION

The present invention generally relates to tourism activities and travel planning. More particularly, the present invention relates to a system and a method for providing a recommendation of destinations in an ordered rank for travelers.

BACKGROUND OF THE INVENTION

Almost all people are fond of traveling. They love exploring new places for recreation or as a passion. They travel to learn a lot about people's traditions, to enjoy picturesque places and to try different foods. The advent of technology has helped people explore new options and come across places which they may not have heard of. It also enables internet users to quickly find relevant information about travel destination, and to select, compare and make decisions almost instantly.

The enormous growth of webs has become sources for a large amount of information available online. This information may be helpful for users, to suggest items or services as per their traveling preferences. However, these data have increased so dramatically that is exceedingly difficult for the consumers to find what they are looking for. This has led to a problem of plenty where people have lots to choose from, which may create a problem of singling out a destination. Picking a tourist destination from the massive information available is one of the most intricate tasks for tourists or travelers when making travel plans, both before and during their travel. Even worse, the online information may contain erroneous text passages, machine-translated texts, outdated contents and sentences that were not proofread properly.

Also, people are mostly unaware of local or domestic safety and security at the destination of choice. Risks are originating in the human and institutional environment such as common delinquency and terrorism, the tourism and related sectors such as transport, sports and retail trade, and the individual travelers such as health conditions and criminal activity. The physical and environmental risks may manifest if the travelers, for example, are not prepared from the medical viewpoint and are exposed to emergencies such as natural disasters and epidemics.

The information retrieval for travel destination has become commonplace through, for instance, a recommender system. Recommender system plays the role of generating suggestions by collecting user information such as preferences, interests, and locations, and by narrowing down the data and provide appropriate recommendations to the users. Many kinds of research focus on travel destination recommendation using personalized information based on user preferences and social media data as well as historical data, using tourist destination as input and basis.

By way of background, United States Patent 9,798,978 B2 discloses a data architecture for use within a travel industry cognitive information processing system environment. The architecture, according to the ‘978 patent, comprises a plurality of data sources comprising a public data source comprising publicly available travel information and a private data source comprising privately managed, company specific travel information, and a cognitive data management module for accessing information from the plurality of data sources and providing the information to an inference and learning system.

It would, therefore, be advantageous to provide a solution that would overcome the deficiencies and shortcomings of prior art by way of providing a system and a method for providing a recommendation of destinations in an ordered rank with, among others, costing assessment, exchanging currency prediction, safety input and sentiment. Although there are systems and methods for the same in the prior art, for many practical purposes, there is still considerable room for improvement.

SUMMARY OF THE INVENTION

The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the invention. Its sole purpose is to present some concepts of the invention in a simplified form as a prelude to the more detailed description that is presented later. Accordingly, the present invention provides a system for providing a recommendation of tourist destinations.

The system of the present invention comprises a data collection unit configured for accessing world wide web to fetch world wide web data associated with a target destination, wherein the data collection unit comprises a text modification module for replacing an irregular data word found in the said world wide web data with an equivalent regular data word that is determined by a word embedding model through a neural network. The system further comprises a data analysis unit configured for processing the world wide web data received from the data collection unit, comprising a sentence segmentation module for segmenting text of the world wide web data into one or more sentences and an entity analytic module for analyzing the said one or more sentences to identify an entity word, thereby determining a destination location associated thereof. The data analysis unit further comprises a sentence categorization module for parsing the said one or more sentences to identify a category-trigger word, thereby assigning a word category to the same; and a rating module for analyzing the said one or more sentences to provide, in relation to the target destination, a sentiment feedback and an intent feedback by way of a return positivity value, and a safety feedback by way of a safety positivity value or safety status. The system further comprises a recommendation unit connected to the data analysis unit configured for providing a tourist destination recommendation in response to an initiator, comprising a ranking module for generating a destination ranking list by way of processing the return positivity value and the safety positivity value or safety status using a ranking model by means of natural language processing, wherein the tourist destination recommendation comprises a list of suggested tourist destinations ordered based on the said destination ranking list.

Preferably, the word embedding model is selected from a group comprising a frequency-based word embedding model and a prediction-based word embedding model.

Preferably, the data analysis unit comprises a syntactic analysis module for facilitating the determination of destination location for the entity word which remains undetermined by the said entity analytic module. Preferably, the syntactic analysis module recognizes, based on sentence dependency, the destination location for the said undetermined entity word as the destination location of the entity word of the one or more sentences previously determined.

Preferably, the syntactic analysis module facilitates the assignment of word category to the category-trigger word which remains unassigned by the said sentence categorization module.

Preferably, the syntactic analysis module recognizes, based on sentence dependency, the word category for the said unassigned category-trigger word as the word category of the category-trigger word of the one or more sentences previously assigned.

Preferably, the return positivity value is determined by a sentiment positivity value derivable from the said sentiment feedback and an intensity value derivable from the said intent feedback.

Preferably, the initiator includes a destination input provided by a user through a user system interface.

Preferably, the recommendation unit comprises a cost assessment and prediction engine for determining the costs of living and currency thereof by way of retrieving associated cost data from a periodically updated cost database.

Preferably, the list of suggested tourist destinations is rendered along with estimated costs of living and currency associated thereto, and trip-related products.

In accordance with another aspect of the present invention, there is provided a method for providing a recommendation of tourist destinations.

The method of the present invention comprises the steps of accessing world wide web to fetch world wide web data associated with a target destination, including replacing an irregular data word found in the said world wide web data with an equivalent regular data word that is determined by a word embedding model through a neural network; processing the world wide web data, comprising segmenting text of the world wide web data into one or more sentences; analyzing the said one or more sentences for identifying an entity word, thereby determining a destination location associated thereof; parsing the said one or more sentences for identifying a category-trigger word, thereby assigning a word category to the same; and analyzing the said one or more sentences for providing, in relation to the target destination, a sentiment feedback and an intent feedback by way of a return positivity value, and a safety feedback by way of a safety positivity value or safety status; and providing a tourist destination recommendation in response to an initiator, comprising generating a destination ranking list by way of processing the return positivity value and the safety positivity value or safety status using a ranking model by means of natural language processing, wherein the tourist destination recommendation comprises a list of suggested tourist destinations ordered based on the said destination ranking list.

Advantageously, the present invention enables users such as travelers, travel planners, coordinators or potential travelers to choose and plan their holiday trips based on the tourist destination recommendation which contains the list of suggested tourist destinations in an ordered rank, i.e. the destination ranking list in a highly specific, cost-effective, quick and simple manner, without the necessity of complicated and sophisticated components. The tourist destination recommendation also provides holiday trip costing assessment based on currency exchange rate prediction for the following few months and destination cost of living, destination safety ranking based on social media sentiment and popularity.

Further advantages of the present invention include that the system and the method enhance tourist decision-making, reduce users’ efforts and preserve their privacy, increase recommendation performance, and improve user satisfaction.

The foregoing and other objects, features, aspects and advantages of the present invention will become better understood from a careful reading of a detailed description provided herein below with appropriate reference to the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

A more complete appreciation of the invention and many of the attendant advantages thereof will be readily as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein:

Figure 1 is a schematic diagram of a system for providing a recommendation of tourist destinations according to one embodiment of the present invention;

Figure 2 is a flow diagram of a method for providing a recommendation of tourist destinations according to one embodiment of the present invention;

Figure 3 is a flow diagram of an entity analytic module representing a step of analyzing the one or more sentences for identifying an entity word as stated in the method of Figure 2 according to one embodiment of the present invention;

Figure 4 is a flow diagram of a sentence categorization module representing the step of parsing the said one or more sentences for identifying a category-trigger word as stated in the method of Figure 2 according to one embodiment of the present invention;

Figure 5 is a flow diagram of a rating module representing the step of analyzing the said one or more sentences for providing, in relation to the target destination, a sentiment feedback and an intent feedback by way of a return positivity value, and a safety feedback by way of a safety positivity value or safety status as stated in the method of Figure 2 according to one embodiment of the present invention; and

Figure 6 is a flow diagram of a recommendation unit representing the step of providing a tourist destination recommendation in response to an initiator as stated in the method of Figure 2 according to one embodiment of the present invention.

It is noted that the drawings may not be to scale. The drawings are intended to depict only typical aspects of the invention, and therefore should not be considered as limiting the scope of the invention. DETAILED DESCRIPTION OF THE INVENTION

The present invention discloses a system and a method for providing recommendation of tourist destinations to a user which primarily includes, but not limited to, a traveler or delegated co-worker inputting travel data, a system user, a trip or travel planner, a trip or travel coordinator and the like. The present invention provides travelers a platform to choose and plan their holiday trip based on destination recommendation. The present invention provides holiday trip costing assessment based on currency exchange rate prediction for the upcoming months and destination’s cost of living. The present invention provides a destination safety ranking based on social media sentiment. The present invention also provides tourism (e.g. places of interest, attractions, and activities) ranking and information based on social media sentiment and popularity.

According to one preferred embodiment, the system of the present invention preferably comprises a data collection unit 100, a data analysis unit 200 and a recommendation unit 300 as schematically shown in Figure 1.

The data collection unit 100 is preferably configured for accessing world wide web of various sources in order to fetch world wide web data associated with a target destination. The target destination is preferably a geographic destination or location available on a map. The geographic destination or location includes a country's regions, cities, states, tourist sites, and other sites of interest located therein.

The world wide web data includes, but not limited to articles published in peer-review journals, newspapers, magazines, blogs, individual blog or forum entry, music, art, Twitter entries, Facebook entries, Linkedln entries, and other social media entries. The world wide web data published may come from professional journalists, citizen journalists, publications, observers, researchers, editors, and institutions. In certain embodiments, articles and information are obtained from specific people with expertise on a topic or people located in particular regions.

The sources of the world wide web may include all webpages without much consideration for the type of content that is being indexed, for example, blogs, forums, e-commerce sites, newspapers, and other online data sources. The world wide web data also may include electronic, electronically transformed and stored books, texts, stories, publications, magazines, journals, news and the like. Those data can be selectively searched, manipulated, hyperlinked, marked, noted, highlighted, cut, copied, pasted, edited and merged into one resultant set of information may also be included.

The data collection unit 100 preferable comprises a text modification module 101. The text modification module 101 may be configured for identifying or finding an irregular data word in the said world wide web data. Any irregular data word found thereof will be subsequently subject to replacement or replaced with the respective equivalent regular data word. The equivalent regular data word is preferably determined by a word embedding model through a neural network. The word embedding model is selected from a group comprising a frequency-based word embedding model and a prediction -based word embedding model. An example of the word embedding model includes a data analysis tool or program such as Word2Vec. This unsupervised machine learning tool and the like can be employed to analyze a text input, i.e. the irregular data word, and to generate a vector representation of said irregular data word. The resulting model may then be used to identify how closely related are an arbitrary input set of words. In one embodiment, the data collection unit 100 generates processed world wide web data that is further transmitted to the data analysis unit 200 for data segmentation, characterization, classification, and analysis.

The data analysis unit 200 is directly connected to the data collection unit 100. The data analysis unit 200 is preferably configured for processing the world wide web data received from the data collection unit 100. The data analysis unit 200 preferably comprises a sentence segmentation module 201 , an entity analytic module 202, a sentence categorization module 203, a rating module 204, and a syntactic analysis module 205.

The sentence segmentation module 201 is configured for performing sentence segmentation. The sentence segmentation module 201 preferably segment text of the world wide web data into one or more sentences (or known as sentence-by-data). In one embodiment, the sentence segmentation may refer to the process of determining text passages consisting of one or more words and likewise identifying sentence boundaries between words in different sentences. Those of skill in the art will be aware that most written languages have punctuation marks which occur at sentence boundaries. In the sentence segmentation, the sentence segmentation module 201 carries out sentence boundary detection, sentence boundary disambiguation, and sentence boundary recognition to determine divisional of a corpus of text into sentences for further processing.

The entity analytic module 202 is configured for analyzing said one or more sentences to identify an entity word therefrom. Following the identification, the entity analytic module 202 determines a destination location associated with the entity word identified thereof.

In one embodiment, the entity word is a word contained in a document and refers to one or more focused named entities in the world wide web data. For each sentence segmented out of the world wide web data, one or more entity words may be identified. Examples of the named entities include, but not limited to, spatial entities, social entities, business entities, government entities, public entities, political entities, national entities, legal entities, human entities, corporate entities and other entity words that have association relationship with the preceding entities that reference a same concerned object. For instance, “Malaysia” which is the name of the country in Asia may be regarded as an entity word. Likewise, “National Zoo” may be regarded as an entity word of a landmark. The entity analytic module 202 may also recognize any entity words in languages other than English. For example, “Taman Tema ” (in Bahasa) may be identified as a public entity that is classified as an entity word of “Theme Park”.

The entity analytic module 202 may employ a suitable recognition or extraction tool such as focused named entity recognition (FNER) technology to identify the entity word in said one or more sentences.

The sentence categorization module 203 is preferably configured for parsing said one or more sentences to identify a category-trigger word. The category-trigger word is a word that initiates, compels or drives importation or reference of a predefined list of word categories.

Upon detection and extraction, it is preferred that the sentence categorization module 203 assigns a word category to the category-trigger word identified thereof, facilitated by a category knowledge database which also stores the predefined list of word categories. The predefined list of word categories includes, but not limited to, food, attraction place, accommodation, weather, activity, history, safety, event, religion and recognition. For instance, “historic metropolis” may be identified as a category-trigger word for a word category of history. In another example, “asam pedas” (a local dish in Bahasa) may be recognized as a category-trigger word for the food word category.

The rating module 204 comprises a sentiment analysis module 204a, an intent identification module 204b and a safety analysis module 204c. The rating module 204 is preferably configured for analyzing said one or more sentences to provide, in relation to the target destination, a sentiment feedback, an intent feedback, and a safety feedback. Preferably, the sentiment feedback is generated by the sentiment analysis module 204a, the intent feedback is generated by the intent identification module 204b, and the safety feedback is generated by the safety analysis module 204c.

According to one preferred embodiment, the sentiment feedback and the intent feedback provided by, respectively, the sentiment analysis module 204a and the intent identification module 204b to the rating module 204 are preferably by way of a return positivity value. The return positivity value is determined by a sentiment positivity value derivable from the sentiment feedback and an intensity value derivable from the intent feedback.

The safety feedback provided by the safety analysis module 204c to the rating module 204 is preferably by way of a safety positivity value or safety status.

The syntactic analysis module 205 is preferably configured for facilitating the determination of destination location for the entity word which remains undetermined by the entity analytic module 202. In this regard, the syntactic analysis module 205 recognizes, based on sentence dependency, the destination location for the undetermined entity word as the destination location of the entity word of the one or more sentences previously determined.

In another embodiment, the syntactic analysis module 205 is preferably configured for facilitating the assignment of word category to the category-trigger word, which remains unassigned by the sentence categorization module 203. In this regard, the syntactic analysis module 205 recognizes, based on sentence dependency, the word category for the unassigned category-trigger word as the word category of the category-trigger word of the one or more sentences previously assigned.

The recommendation unit 300 connected to the data analysis unit 200 is preferably configured for providing a tourist destination recommendation in response to an initiator. The initiator includes, but not limited to, a destination input provided by a user through a user system interface provided at a traveler assistant linked thereto. The recommendation unit 300 generally plays the role of generating suggestions by collecting user information such as locations.

The recommendation unit 300 preferably comprises a ranking module 301 and a cost assessment and prediction engine 302. The ranking module 301 is configured for generating a destination ranking list by way of processing the return positivity value and the safety positivity value or safety status. The destination ranking list is preferably produced by using a ranking model by means of natural language processing (NLP). An example of the ranking model includes a natural language parse ranker of an NLP system that employs a function to rank the possible suggested destinations (such as by category and entity). The cost assessment and prediction engine 302 is configured for determining estimated costs of living and exchanging currency thereof for the present month and onwards, or for the duration of stay or travel period specified thereof. The estimated costs of living and predicted exchanging currency are finalized by referencing to associated cost data retrieved from a periodically updated cost database. The periodically updated cost database comprises a currency prediction database and a cost of living database.

The tourist destination recommendation generated by the recommendation unit 300 preferably comprises a list of suggested tourist destinations ordered based on the destination ranking list. The list of suggested tourist destinations is preferably accompanied by the estimated costs of living and the currency associated thereto, and trip or travel-related products or services. The trip or travel-related products may include, but not limited to, airlines, car rental, hotel, train, bus, limousines, and any other travel-related product or service.

In an embodiment of the recommendation unit 300, the user system interface of the traveler assistant assists in exploring potential destinations with tourism and safety ranking list and costing assessment leveraging on the ranking data analytics. The user system interface allows a user to enter data as the initiator, e.g. destination inputs. The user system interface may receive a user's input via a text input field, using voice input/recognition technologies, and many more. Similarly, the user system interface may display or otherwise share received data in textual or audio form. The traveler assistant facilitates displaying the list of suggested tourist destinations with the information of the cost of living and exchanging currency. The traveler assistant further provides, through the user system interface, a means for redirection to a registered third-party platform such as travel, flight and hotel booking platforms that are external to the system of the present invention.

Concerning the method of the present invention, Figure 2 provides a summarized flow diagram depicting the steps involved, as explained in the preceding paragraphs in connection with the system thereof. For purposes of clarity in explanation and understanding, the method of the present invention is described in the following section.

The method preferably begins with step 400 of accessing, by the data collection unit 100, the world wide web to fetch the world wide web data associated with a target destination. Step 400 includes step 401 of replacing an irregular data word found in the world wide web data with an equivalent regular data word that is determined by a word embedding model through a neural network.

It is subsequently followed by step 500 of processing the world wide web data. Step 500 preferably comprises the following steps:

501 - segmenting text of the world wide web data into one or more sentences;

502 - analyzing said one or more sentences for identifying an entity word, thereby determining a destination location associated thereof;

503 - parsing said one or more sentences for identifying a category-trigger word, thereby assigning a word category to the same; and

504 - analyzing said one or more sentences for providing, in relation to the target destination, a sentiment feedback and an intent feedback by way of a return positivity value, and a safety feedback by way of a safety positivity value or safety status.

Following that, the method initiates step 600 of providing a tourist destination recommendation in response to an initiator. The step 600 preferably comprises step 601 of generating a destination ranking list by way of processing the return positivity value and the safety positivity value or safety status using a ranking model by means of natural language processing. The tourist destination recommendation comprises a list of suggested tourist destinations ordered based on the destination ranking list, accompanied with estimated costs of living and currency associated thereto, and trip-related products or services.

Figures 3, 4, 5, and 6 provide the self-explanatory flow diagrams which illustrate step 502, step 503, step 504 and step 600, respectively.

According to Figure 3, with reference to the entity analytic module 202, step 502 preferably includes the steps of: a) analyzing the one or more sentences segmented from the world wide web data thereof; b) identifying an entity word from said one or more sentences; c) checking if any entity word has been identified, if no entity word identified, then checks sentence dependency by the syntactic analysis module 205, if the sentence is related to the previous sentence, then assigns the destination location for the undetermined entity word as the destination location of the entity word of the sentence previously determined, if there are more unprocessed sentences, then starts analyzing the same, if there is no more unprocessed sentence, then ceases at end block, if the sentence is not related to the previous sentence, then checks any unprocessed sentences, if there are more unprocessed sentences, then starts analyzing the same, if there is no more unprocessed sentence, then ceases at end block, if entity word identified, then determines a destination location associated with the entity word thereof, if there are more unprocessed sentences, then starts analyzing the same, if there is no more unprocessed sentence, then ceases at end block.

According to Figure 4, with reference to the sentence categorization module, step 503 preferably includes the steps of: a) parsing the one or more sentences thereof; b) identifying a category-trigger word from said one or more sentences; d) checking if a word category for the category-trigger word has been identified, if no word category identified, then checks sentence dependency by the syntactic analysis module 205, if the sentence is related to the previous sentence, then assigns the word category for the unassigned category- trigger word as the word category of the category-trigger word of the sentence previously assigned, and stores in a system database, if there are more unprocessed sentences, then starts analyzing the same, if there is no more unprocessed sentence, then ceases at end block, if the sentence is not related to the previous sentence, then ceases at end block, if word category identified, then assigns a word category to the category-trigger word thereof, if there are more unprocessed sentences, then starts analyzing the same, if there is no more unprocessed sentence, then ceases at end block. According to Figure 5, with reference to the rating module 204, step 504 preferably includes the steps of: a) analyzing each sentence by category and entity; b) checking if word category for safety and/or weather exists, if word category for safety and/or weather exists, then conducts a safety feedback using a safety model, and checks if safety feedback is positive, if safety feedback is positive, then obtains a safety positivity value (SPval), and assigns safety status as “Safe”, and ceases at end block, if safety feedback is not positive, then checks on month and duration of occurrence of non-safety incident or situation, if the month and duration of incident or situation is equal or more than the current month, then assigns safety status as “Safe for Current X Month”, and ceases at end block, if the month and duration of incident or situation is less than the current month, then assigns safety status as “Not Safe for Current X Month”, and ceases at end block, if word category for safety and/or weather does not exist, then provides a sentiment feedback and an intent feedback to compute a return positivity value and ceases at end block.

According to Figure 6, with reference to the recommendation unit 300, step 600 preferably includes the steps of: a) receiving an initiator such as destination input from a user; b) conducting, for each initiator, a search in a destination rating database; c) checking if the initiator exists, if the initiator exist, then generates a destination ranking list by processing the return positivity value and the safety positivity value or safety status using a ranking model by means of NLP (step 601); provides a tourist destination recommendation comprising a list of suggested tourist destinations ordered based on the destination ranking list; and provides estimated costs of living and currency associated thereto, and trip-related products, if the user chooses to redirect to a registered third- party platform, then proceed to the registered third-party platform, if the user chooses not to redirect to a registered third- party platform, then if there are any further initiator received, then starts analyzing the same, if there is no further initiator, then displays search results on the user system interface, and ceases at end block. if the initiator does not exist, then assigns as “No Result

Found”, if there are any further initiator received, then starts analyzing the same, if there is no further initiator, then displays search results on the user system interface, and ceases at end block.

The present invention will now be specifically described by the following examples, but it should be understood that the invention is not limited in any way to these examples.

Example 1

Data Collection Unit

World wide web data fetched from world wide web was considered below.

Sentence Segmentation Module (201)

• Sentence 1 “Located on the southwest coast of Malaysia, Melaka City is arguably the country’s most historic metropolis”

• Sentence 2 “Its central historical zone, a crumbling set of colonial-era buildings in and around Chinatown, gained Unesco World Heritage listing in 2008, and the benefits are now spreading to the Sungai Melaka”

• Sentence 3 “It even chugs past small stands of mangroves until it reaches its northern terminus, the Taman Rempah jetty”

• Sentence 4 “The 45-minute cruise passes blood-red Dutch-era buildings at the foot of Bukit St Paul (St Paul Hill), going beyond the remodelled godowns (old warehouses) of Chinatown and to the gaily-painted traditional wooden houses of Kampung Morten”

• Sentence 7 “Asam Pedas is very Famous in Melaka”

• Sentence 8 “It is a good place to recommend to those who love this food.” Entity Analytic Module (202) & Sentence Categorization Module (203)

Rating Module (204)

Although an overview of the inventive subject matter has been described with reference to specific example embodiments, various modifications and changes may be made to these embodiments without departing from the broader scope of embodiments of the present disclosure. Such embodiments of the inventive subject matter may be referred to herein, individually or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any single disclosure or inventive concept if more than one is, in fact, disclosed.

The embodiments illustrated herein are described in sufficient detail to enable those skilled in the art to practice the teachings disclosed. Other embodiments may be used and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. The Detailed Description, therefore, is not to be taken in a limiting sense, and the scope of various embodiments is defined only by the appended claims, along with the full range of equivalents to which such claims are entitled.

As used herein, the term “or” may be construed in either an inclusive or exclusive sense. Moreover, plural instances may be provided for resources, operations, or structures described herein as a single instance. Additionally, boundaries between various resources, operations, modules, engines, and data stores are somewhat arbitrary, and particular operations are illustrated in a context of specific illustrative configurations. Other allocations of functionality are envisioned and may fall within a scope of various embodiments of the present disclosure. In general, structures and functionality presented as separate resources in the example configurations may be implemented as a combined structure or resource. Similarly, structures and functionality presented as a single resource may be implemented as separate resources. These and other variations, modifications, additions, and improvements fall within a scope of embodiments of the present disclosure as represented by the appended claims. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

The foregoing description, for the purpose of explanation, has been described with reference to specific example embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the possible example embodiments to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The example embodiments were chosen and described in order to best explain the principles involved and their practical applications, to thereby enable others skilled in the art to best utilize the various example embodiments with various modifications as are suited to the particular use contemplated.

It will also be understood that, although the terms “first,” “second,” and so forth 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 from another. For example, a first contact could be termed a second contact, and, similarly, a second contact could be termed a first contact, without departing from the scope of the present example embodiments. The first contact and the second contact are both contacts, but they are not the same contact. The terminology used in the description of the example embodiments herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used in the description of the example embodiments and the appended examples, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

As used herein, the term “if” may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” may be construed to mean “upon determining” or “in response to determining” or “upon detecting [the stated condition or event]” or “in response to detecting [the stated condition or event],” depending on the context.

Claims

1. A system for providing a recommendation of tourist destinations, characterized in that, the system comprising: a data collection unit (100) configured for accessing world wide web to fetch world wide web data associated with a target destination, wherein the data collection unit (100) comprises a text modification module (101) for replacing an irregular data word found in the world wide web data with an equivalent regular data word that is determined by a word embedding model through a neural network; a data analysis unit (200) configured for processing the world wide web data received from the data collection unit (100), comprising: a sentence segmentation module (201 ) for segmenting text of the world wide web data into one or more sentences; an entity analytic module (202) for analyzing the one or more sentences to identify an entity word, thereby determining a destination location associated thereof; a sentence categorization module (203) for parsing the one or more sentences to identify a category-trigger word, thereby assigning a word category to the same; and a rating module (204) for analyzing the one or more sentences to provide, in relation to the target destination, a sentiment feedback and an intent feedback by way of a return positivity value, and a safety feedback by way of a safety positivity value or safety status; and a recommendation unit (300) connected to the data analysis unit (200) configured for providing a tourist destination recommendation in response to an initiator, comprising: a ranking module (301) for generating a destination ranking list by way of processing the return positivity value and the safety positivity value or safety status using a ranking model by means of natural language processing, wherein the tourist destination recommendation comprises a list of suggested tourist destinations ordered based on the destination ranking list.

2. The system according to Claim 1 , wherein the word embedding model is selected from a group comprising a frequency-based word embedding model and a prediction-based word embedding model.

3. The system according to Claim 1 , wherein the data analysis unit (200) further comprises a syntactic analysis module (205) for facilitating the determination of destination location for the entity word which remains undetermined by the entity analytic module (202).

4. The system according to Claim 3, wherein the syntactic analysis module (205) recognizes, based on sentence dependency, the destination location for the undetermined entity word as the destination location of the entity word of the one or more sentences previously determined.

5. The system according to Claim 3, wherein the syntactic analysis module (205) facilitates the assignment of word category to the category-trigger word which remains unassigned by the sentence categorization module (203).

6. The system according to Claim 5, wherein the syntactic analysis module (205) recognizes, based on sentence dependency, the word category for the unassigned category-trigger word as the word category of the category-trigger word of the one or more sentences previously assigned.

7. The system according to Claim 1 , wherein the return positivity value is determined by a sentiment positivity value derivable from the sentiment feedback and an intensity value derivable from the intent feedback.

8. The system according to Claim 1 , wherein the initiator includes a destination input provided by a user through a user system interface.

9. The system according to Claim 1 , wherein the recommendation unit (300) further comprises a cost assessment and prediction engine (302) for determining the costs of living and currency thereof by way of retrieving associated cost data from a periodically updated cost database.

10. The system according to Claim 1 , wherein the list of suggested tourist destinations is rendered along with estimated costs of living and currency associated thereto, and trip-related products.

1 . A method for providing a recommendation of tourist destinations, characterized in that, the method comprising the steps of: accessing world wide web to fetch world wide web data associated with a target destination (400), including: replacing an irregular data word found in the world wide web data with an equivalent regular data word that is determined by a word embedding model through a neural network (401); processing the world wide web data (500), comprising: segmenting text of the world wide web data into one or more sentences (501); analyzing the one or more sentences for identifying an entity word, thereby determining a destination location associated thereof (502); parsing the one or more sentences for identifying a category-trigger word, thereby assigning a word category to the same (503); and analyzing the one or more sentences for providing, in relation to the target destination, a sentiment feedback and an intent feedback by way of a return positivity value, and a safety feedback by way of a safety positivity value or safety status (504); and providing a tourist destination recommendation in response to an initiator (600), comprising: generating a destination ranking list by way of processing the return positivity value and the safety positivity value or safety status using a ranking model by means of natural language processing (601), wherein the tourist destination recommendation comprises a list of suggested tourist destinations ordered based on the destination ranking list.