KR20180091492A - Method, system and non-transitory computer-readable recording medium for analyzing sentiment based on position related document - Google Patents

Abstract

According to an aspect of the invention, provided is a method for analyzing emotion based on a position related document. The method includes: a step of generating a position related document with reference to content collected from at least one user terminal device or at least one server and position information associated with the content; a step of calculating a subject-emotion score for each topic at a position associated with the generated position related document; and a step of determining a preference that a user located at a first position is expected to have for at least one topic, with reference to the subject-emotion score for each topic at the first position.

Description

[0001] METHOD, SYSTEM AND NON-TRANSITORY COMPUTER READABLE RECORDING MEDIUM FOR ANALYZING SENTIMENT BASED ON POSITION RELATED DOCUMENT [0002] FIELD OF THE INVENTION [0003]

The present invention relates to a method, system and non-temporal computer-readable recording medium for analyzing emotion based on location-related documents.

In recent years, various location-based services using GPS, cellular network, etc. have been introduced. Typical examples of the location-based service include a service for providing information related to a place where the user is currently located (for example, information on a map, a shop, etc.), a navigation service for guiding a route from the current location to the destination, And a service for tagging the location information with respect to the user.

However, the conventional location-based service only considers the primary or direct association with the user's location in determining the service to be provided to the user. Thus, according to the prior art, there is a limitation that it is difficult to provide a service that has a complex or indirect relationship with the location of the user, but which may be very useful to the user.

SUMMARY OF THE INVENTION The present invention has been made to solve all the problems of the prior art described above.

The present invention relates to a method and apparatus for generating a location-related document by referring to content collected from a user terminal or a server and positional information associated with the content, By calculating the emotion score and determining a preference that the user at the first position with respect to the topic-subject-emotion score at the first position is expected to have for at least one topic, And to generate quantified information about emotions that a user can feel.

In order to accomplish the above object, a representative structure of the present invention is as follows.

According to an aspect of the present invention there is provided a method for analyzing emotion based on a position related document, the method comprising: receiving content from at least one user terminal device or at least one server; Calculating a topic-emotion score for each topic at a location associated with the generated location-related document, and calculating a topic-emotion score for each topic at the first location, By way of reference, a method is provided that includes determining a preference that a user located at the first location is expected to have for at least one topic.

According to another aspect of the present invention there is provided a system for analyzing emotions based on a position related document, the system comprising: means for receiving content collected from at least one user terminal device or at least one server and location information associated with the content A location-related document management unit for generating a location-related document by referring to the generated location-related document, and calculating a target-emotion score for each topic at a position associated with the generated location-related document, There is provided a system including an emotional analysis section that, with reference to a score, determines a preference that a user located at the first position is expected to have for at least one topic.

In addition, there is provided another method, system, and non-transitory computer readable recording medium for recording a computer program for carrying out the method for implementing the present invention.

According to the present invention, it is possible to achieve a target-emotion score for each topic on a significant position on the map.

Further, according to the present invention, it is possible to generate quantified information on emotions that a user located at a specific place can feel.

1 is a diagram showing a schematic configuration of an overall system for analyzing emotion according to an embodiment of the present invention.
2 is a diagram illustrating an exemplary internal configuration of an emotion analysis system according to an embodiment of the present invention.
FIG. 3 is a diagram illustrating a process of generating a location-related document according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating a process of calculating a subject-emotion score and a preference degree according to an embodiment of the present invention.

The following detailed description of the invention refers to the accompanying drawings, which illustrate, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different, but need not be mutually exclusive. For example, certain features, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in connection with an embodiment. It is also to be understood that the position or arrangement of the individual components within each disclosed embodiment may be varied without departing from the spirit and scope of the invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is to be limited only by the appended claims, along with the full scope of equivalents to which such claims are entitled, if properly explained. In the drawings, like reference numerals refer to the same or similar functions throughout the several views.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, so that those skilled in the art can easily carry out the present invention.

Configuration of the entire system

1 is a diagram showing a schematic configuration of an overall system for analyzing emotion according to an embodiment of the present invention.

1, an overall system according to an exemplary embodiment of the present invention may include a communication network 100, an emotion analysis system 200, a user terminal 300, and a server 400. [

First, the communication network 100 according to an embodiment of the present invention can be configured without regard to communication modes such as wired communication and wireless communication. The communication network 100 can be a local area network (LAN), a metropolitan area network ), A wide area network (WAN), and the like. Preferably, the communication network 100 referred to herein may be the well-known Internet or World Wide Web (WWW). However, the communication network 100 may include, at least in part, a known wire / wireless data communication network, a known telephone network, or a known wire / wireless television communication network, without being limited thereto.

Next, the emotion analysis system 200 according to an embodiment of the present invention generates a location-related document with reference to content collected from the user terminal 300 or the server 400 and position information associated with the content , A target-emotion score for each topic at a location associated with the generated location-related document is calculated, and a user located at the first location with reference to the topic-specific subject-emotion score at the first location It is possible to perform the function of generating the quantified information on the emotion that the user located at the predetermined position can feel by determining the degree of preference that is expected to have for one topic.

The configuration and function of the emotion analysis system 200 according to the present invention will be described in detail through the following detailed description.

Next, in accordance with an embodiment of the present invention, the user terminal device 300 is a digital device including a function that allows a user to access the emotion analysis system 200 and then communicate with the user terminal device 300, such as a smart phone, a tablet, Any number of digital devices having memory means such as a computer, a notebook computer, a workstation, a PDA, a web pad, a mobile phone, etc. and equipped with a microprocessor and capable of computing can be employed as the user terminal device 300 according to the present invention. have.

In particular, the user terminal device 300 may include an application (not shown) that enables a user to receive a service from the emotion analysis system 200. Such an application may be downloaded from the emotion analysis system 200 or a known web server (not shown).

Next, in accordance with an embodiment of the present invention, the server 400 may perform the function of providing the content related to the location to the emotion analysis system 200 or the user terminal device 300. [ Specifically, the server 400 according to an exemplary embodiment of the present invention may include a social network such as Twitter, Facebook, Instagram, etc., And may be a server operated by the entity providing the service (SNS).

Structure of Emotion Analysis System

Hereinafter, the internal structure of the emotional analysis system that performs an important function for the implementation of the present invention and the functions of the respective components will be described.

2 is a diagram illustrating an exemplary internal configuration of an emotion analysis system according to an embodiment of the present invention.

2, the emotion analyzing system 200 according to an embodiment of the present invention includes a location-related document managing unit 210, an emotion analyzing unit 220, a service providing unit 230, a communication unit 240, (250). According to an exemplary embodiment of the present invention, at least a part of the location-related document management unit 210, the emotion analyzing unit 220, the service providing unit 230, the communication unit 240, Lt; / RTI > shown in FIG. These program modules may be included in the emotion analysis system 200 in the form of an operating system, an application program module, and other program modules, and may be physically stored on various known storage devices. These program modules may also be stored in a remote storage device capable of communicating with the emotion analysis system 200. [ These program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types as described below in accordance with the present invention.

First, according to one embodiment of the present invention, the location-related document management unit 210 collects various contents collected from at least one user terminal device 300 or at least one server 400 and location information associated with the contents can do.

In particular, according to an embodiment of the present invention, the above content and location information may be collected from social media. For example, posts containing location information, such as geo-tagged tweets, and articles containing place information, such as reviews of restaurants, may be collected.

Also, according to an embodiment of the present invention, location information associated with the content may be specified on a two-dimensional coordinate system defined by latitude and longitude. Thus, according to one embodiment of the present invention, a large number of content collected from social media may be mapped onto a two-dimensional coordinate system according to the location information associated therewith.

FIG. 3 is a diagram illustrating a process of generating a location-related document according to an embodiment of the present invention.

Referring to FIG. 3, it is said that "strawberry smoothie was so sad because it was soothing in the smile from the coffee of Gangnam Station # Mali" associated with the two-dimensional coordinate (37.497857, 127.027492) Various contents 311, 312, and 313 can be collected, such as " OK, you can comfort my heart ".

In addition, according to one embodiment of the present invention, the location-related document management unit 210 may generate at least one location-related document with reference to the content and location information collected as described above.

Specifically, according to an embodiment of the present invention, the location-related document may include words included in the content associated with the location information and information on the number of times the word appears.

In this regard, referring to FIG. 3, the position related document generated in association with the position (37.497857, 127.027492) is "(37.497857, 127.027492) -> [(mind, 3), (Americano, 10), (strawberry smoothie, 2), ...] "(320).

In addition, according to an embodiment of the present invention, the location-related document management unit 210 performs a smoothing process on two or more location-related documents commonly belonging to a predetermined range based on the location or generation time, It is possible to perform the function of integrating two or more of the above-mentioned location-related documents. This makes it possible to integrate a plurality of location-related documents, which may be regarded as being substantially at the same location or at the same place, with slight differences, into one location-related document.

According to an embodiment of the present invention, a known smoothing algorithm may be used to perform smoothing processing on the position-associated document.

As an example of the smoothing algorithm, the location-related document management unit 210 according to an embodiment of the present invention may include a location- The smaller the difference between the time and the position or the generation time of the second position related document is, the higher the weight given to the second position related document can be.

Hereinafter, an example in which a smoothing algorithm for weighting based on distances among the above smoothing algorithms is used will be described in more detail.

(x, y), which is generated in association with a second position, Dx, y, which is a first position-related document generated in association with a first position, (x, y) Can be assumed to be integrated (i.e., absorbed). In this case, the location-related-document managing unit 210 according to an embodiment of the present invention searches for a word not included in Dx, y among the words included in Dx ', y' (X, y) and (x (y, y)) for the word already contained in Dx, y among the words included in Dx ', y' ', y') can be added to the number of occurrences in Dx, y.

It should be noted that the smoothing algorithm used in the present invention is not necessarily limited to those listed above, but may be changed within a range that can achieve the object of the present invention.

In this regard, referring to FIG. 3, the combined position-related document obtained by smoothing the plurality of position related documents generated in association with the position (37.497857, 127.027492) and its surroundings is "(37.497857, 127.027492) Can be generated (330) as [(mind, 15.33), (Americano, 32.17), (strawberry smoothie, 5.81), ...].

Next, according to an embodiment of the present invention, the emotion analyzing unit 220 may calculate a target-emotion score for each topic at a position associated with the position-related document generated as described above.

Specifically, according to one embodiment of the present invention, a topic can be defined based on words included in the position-related document described above, and can be generated by a known natural language processing algorithm or artificial intelligence algorithm. It should be noted that the natural language processing algorithm or artificial intelligence algorithm used for generating a topic in the present invention can be changed within a range that can achieve the object of the present invention.

FIG. 4 is a diagram illustrating a process of calculating a subject-emotion score and a preference degree according to an embodiment of the present invention.

Referring to Figure 4 (a), the topics T1, T2, and T3 may be generated based on the words contained in the various location-related documents generated in association with each of the various locations. Here, the topic T1 is specified by "work, office worker, boredom, ...", the topic T2 is specified by "beer, wine, cocktail, mochi, ..." and topic T3 is " Person, wait, ... "(410).

Also, according to one embodiment of the present invention, the subject-emotion score indicates which emotion is expressed for a particular topic in a large number of contents generated in association with a specific position, for example, A high score is calculated when it is analyzed as being negative, and a low score is calculated when negative emotion is analyzed as being expressed.

The object-emotion score as described above can be calculated by a known emotion analysis algorithm. An example of such emotion analysis algorithm is described in Yohan, Jo and Alice H. Oh., And Proceedings of the Fourth ACM International Conference on Web search and data mining. The emotion analysis algorithm described in the paper entitled " Aspect and sentiment unification model for online review analysis ", published in ACM, 2011, can be used. However, it should be noted that the emotion analysis algorithm used in the present invention is not necessarily limited to those listed above, and can be changed within a range that can achieve the object of the present invention.

Referring to FIG. 4 (a), the object-emotion score at the position (37.497857, 127.027492) (indicating Gangnam station) is calculated as [T1: -5 points, T2: 4 points, T3: -3 points] (420). From the target-emotion score, it can be judged that there is a high tendency that negative emotions tend to be expressed with respect to the topics T1 and T3 in the content generated in association with the Gangnam station, and a positive emotion is not expressed with respect to the topic T2.

In addition, according to an embodiment of the present invention, the emotion analyzing unit 220 refers to the subject-emotion score of each topic at a specific position, and determines that a user located at a specific position is expected to have at least one topic It is possible to perform the function of determining the preference.

Referring to FIG. 4B, it can be assumed that a user is located in Yeoksam, Itaewon and Gangnam in weekday day, weekday evening, and weekend, respectively. In this case, the emotion analyzing unit 220 according to an embodiment of the present invention may be configured such that, with reference to the object-emotion score calculated for Yeoksam, Itaewon, and Gangnam above, The preference for the topic T2 is high and the preference for the topic T2 is high on the weekday evening when the user is located at Itaewon and the preference for the topic T2 is high on the weekends when the user is located in Gangnam 430).

Specifically, according to an embodiment of the present invention, the emotion analyzing unit 220 may correct the preference determined as described above based on the actual copper line of the user. For example, if the user frequently visits a restaurant belonging to the topic T1 even though the user is expected to have a low preference for the topic T1, the emotion analyzing unit 220 according to an embodiment of the present invention Corresponding to this, it is possible to perform correction for increasing the preference for the topic T1 of the user.

Next, in accordance with an embodiment of the present invention, the service provider 230 refers to the user's preference for each topic determined as described above, and transmits information (e.g., location, Food, performances, schedule recommendation, and the like).

Meanwhile, the communication unit 240 according to an embodiment of the present invention performs a function of allowing the emotion analysis system 200 to communicate with an external device such as the user terminal 300. [

The control unit 250 controls the flow of data between the location-related document management unit 210, the emotion analyzing unit 220, the service providing unit 230, and the communication unit 240 . That is, the control unit 250 controls the flow of data between the components of the emotion analyzing system 200, from the outside, thereby generating the location-related document managing unit 210, the emotion analyzing unit 220, the service providing unit 230, And the communication unit 240, respectively.

The embodiments of the present invention described above can be implemented in the form of program instructions that can be executed through various computer components and recorded in a non-transitory computer readable recording medium. The non-transitory computer readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the non-transitory computer-readable recording medium may be those specially designed and constructed for the present invention or may be those known to those skilled in the computer software arts. Examples of non-transitory computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs, DVDs, magneto-optical media such as floppy disks magneto-optical media), and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules for performing the processing according to the present invention, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, Those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims.

Therefore, the spirit of the present invention should not be construed as being limited to the above-described embodiments, and all of the equivalents or equivalents of the claims, as well as the following claims, I will say.

100: Network
200: Emotional Analysis System
210: Position related document management unit
220: Emotion analysis section
230: Service Offering
240:
250:
300: User terminal device

Claims (14)

A method for analyzing emotion based on a position related document,
Generating a location-related document with reference to content collected from at least one user terminal device or at least one server and location information associated with the content,
Calculating a subject-emotion score for each topic at a location associated with the generated location-related document, and
Determining a likelihood that a user located at the first location is expected to have for at least one topic, with reference to the topic-specific per-topic-emotion score at the first location
Lt; / RTI >
Wherein the topic is defined based on at least one word included in the generated location-related document. The method according to claim 1,
Wherein the content and the location information are collected from a social media. The method according to claim 1,
Wherein the location information is specified by latitude and longitude. The method according to claim 1,
Wherein the location-related document includes information about a word appearing in association with the location information and the number of times the word appears. The method according to claim 1,
In the location-related document generation step,
Related document by performing a smoothing process on two or more position-related documents belonging in common within a predetermined range based on position or generation time of the position-related document. 6. The method of claim 5,
In the location-related document generation step,
The method of claim 1, wherein the step of merging the second location-related document into the first location-related document further comprises: determining a location of the first location- A method in which the weight assigned to an associated document is increased. The method according to claim 1,
Wherein the determined preference is corrected based on an actual copper line of the user. The method according to claim 1,
Further comprising the step of determining information to be recommended to a user located at said first location with reference to said determined preference. A non-transitory computer readable recording medium having recorded thereon a computer program for carrying out the method according to any one of claims 1 to 6, 7 and 8. A system for analyzing emotions based on a position related document,
A location-related document management unit for generating a location-related document with reference to content collected from at least one user terminal device or at least one server and location information associated with the content, and
Calculating a subject-emotion score for each topic at a location associated with the generated location-related document, and referring to the topic-subject-emotion score at the first location, And an emotion analyzing section for determining a preference that is expected to have for one topic,
Wherein the topic is defined based on at least one word included in the generated location-related document. 11. The method of claim 10,
Wherein the content and the location information are collected from a social media. 11. The method of claim 10,
Wherein the location-related document includes information about a word appearing in association with the location information and the number of times the word appears. 11. The method of claim 10,
Wherein the location-related document management unit performs smoothing processing on two or more location-related documents belonging in common within a predetermined range based on a location or a generation time, thereby integrating the two or more location-related documents. 11. The method of claim 10,
And a service providing unit configured to determine information to be recommended to a user located at the first location with reference to the determined preference.

Images