KR20200125507A - Method for recommending item using degree of association between unit of language and using breakdown - Google Patents

Abstract

The present invention relates to an item recommendation method using a degree of association between a language unit and a use item for recommending similar items with high purchase possibility by using a vector model-based inference method based on a degree of association between words, not by simply using a matching method expressed by keywords, by conceiving a new cognitive system through research on people′s emotions and tastes, T.P.O (Time, Place, Occasion), and characteristics of various lists (color, texture, etc.) based on language units and user preferences, experience and/or purchase history, based on the languages spoken by the user in daily life, and then applying machine learning technology and natural language understanding technology.

Description

Item recommendation method using the association between language units and usage history {METHOD FOR RECOMMENDING ITEM USING DEGREE OF ASSOCIATION BETWEEN UNIT OF LANGUAGE AND USING BREAKDOWN}

The present invention relates to an item recommendation method using a degree of association between a language unit and a usage history, and more particularly, based on the language unit and the languages used by the user in daily life based on the user's preference, experience and/or purchase history. As a result, a new recognition system was devised through research on human emotions and tastes, TPO (Time, Place, Occasion) and various list-specific characteristics (color, texture, etc.), and implemented by applying machine learning technology and natural language understanding technology. , Not just a matching method expressed by keywords, but using a vector model-based inference method based on the degree of association between language units, using the degree of association between language units and usage details to recommend similar items with high purchase potential. It is about how to recommend items.

In general, modern information users (web users, hereinafter collectively referred to as "users") must select the information they want in an environment in which a large amount and various types of information are simultaneously provided. In addition, since the information required by the user has a variety of formats according to the source of the information, a more intelligent and automated system is required for comprehensive analysis and utilization.

In order to satisfy these requirements, a system that analyzes and recommends users' search patterns was used.

A typical application for research on users' search patterns is to analyze session data of users who access their server from the server side and use them for advertisements or user-customized web pages.

This analysis result is recognized as one of the most important management strategies for companies that have users as their main customers along with collaborative filtering technology. In other words, users' search results (eg, search page, search time, search order, transaction trend, etc.) recorded in the server are used as one of the main sources of value-added. The analyzed data is used to infer a web page to be visited later by the user or to infer a product of interest, and as a result, the application is being made in the direction of recommending a product with high purchase potential suitable for the user's characteristics. In addition, there are many attempts to analyze the user's search pattern on the client side in the form of a proxy server or plug-in, which has the advantage of utilizing more various information than the analysis on the server side.

However, there is a problem in that the existing user preference analysis system and recommendation service cannot use various information and cannot overcome the limitations of using only the information given in their respective domains.

Therefore, there is a need to recommend similar items with high purchase potential using a vector model-based inference method based on the degree of association between language units based on the user's preference or experience and/or purchase history. Became.

1. Korean Utility Model Publication No. 20-0426027, "User-defined information retrieval system" (announced on September 18, 2006)

An object of the present invention was devised to solve the above-described problem, and uses a vector model-based inference method based on the degree of association between language units based on user preference, experience, and/or purchase history. Therefore, it is intended to provide an item recommendation method using the degree of association between language units and usage details to recommend similar items with high purchase possibility.

An item recommendation method using a degree of association between a language unit and a usage history according to the present invention is an item recommendation method using a degree of association between a language unit performed by an item recommendation device and a usage item, and is performed by a control unit of the item recommendation device. -Setting a degree of association between use items; Obtaining an experience item list including user experience items by a control unit of the item recommendation device; Acquiring a language unit-relevance pair in a language unit based on a threshold value in association with each experience item in the experience item list by a control unit of the item recommendation device; Obtaining, by a control unit of the item recommendation device, a language unit-user association between a user and each language unit based on a language unit-relevance pair between all language units corresponding to the experience item list; And generating a user recommendation item list based on a language unit-user association degree by a control unit of the item recommendation device.

The item recommendation method using the degree of association between language units and usage details according to the present invention uses a vector model-based inference method based on the degree of association between language units based on user preference or experience and/or purchase history. Therefore, there is an advantage of being able to recommend similar items with high purchase possibility.

In addition, there is an advantage of being able to adjust some of the recommended items to be recommended to users of a specific pattern.

In addition, there is an advantage in that it is possible to provide recommended items to users according to the ranking of recommendations.

In addition, there is an advantage that it is possible to adjust some of the recommended items to be provided to users of a specific pattern.

It also has the advantage of being vectorized by processing keywords with word2vec or other similar vectorization techniques.

In addition, there is an advantage in that it is possible to add and delete language units displayed in the language unit adjustment interface corresponding to the clicked category by clicking on the web chart or the one chart.

1 is a schematic overall block diagram of an item recommendation system using a degree of association between language units and usage details according to the present invention.
FIG. 2 is a block diagram showing the configuration of the terminal shown in FIG. 1;
A configuration block diagram of the item recommendation device shown in FIG. 1 of FIG. 3.
4A to 4C are flowcharts of an item recommendation process through an item recommendation interface according to an embodiment of the present invention.
5 is a flowchart of an item recommendation process according to an embodiment of the present invention.
6 is a detailed flowchart of some of the steps of FIG. 5;
7 is a detailed flowchart of some of the steps of FIG. 6.
Figure 8 is a detailed flow chart of some other steps of Figure 6;
9 is a flowchart of an item recommendation process according to another embodiment of the present invention.
10 is an exemplary diagram of a stored object-keyword association according to an embodiment of the present invention.
11 is an exemplary diagram of a basic language unit-keyword association according to an embodiment of the present invention.
12 is a detailed flowchart of some other steps of FIG. 5.
13 is a flowchart of an item recommendation process according to another embodiment of the present invention.
14 is a flowchart of an item recommendation process according to another embodiment of the present invention.
15 is a detailed flowchart of some of the steps of FIG. 13 according to an embodiment of the present invention.
16 is a detailed flowchart of some of the steps of FIG. 13 according to another embodiment of the present invention.
Figure 17 is a detailed flow chart of some of the steps of Figure 13 according to another embodiment of the present invention.
18 is a diagram showing a term hierarchy according to an embodiment of the present invention.
19 is an exemplary view showing main language units for each language unit list based on a language unit associated with a selected item according to an embodiment of the present invention.
20 is an exemplary diagram illustrating main language units for each language unit list based on a language unit associated with a selected item according to another embodiment of the present invention.
21 and 22 are exemplary views showing an average correlation criterion of major language units for each list according to an embodiment of the present invention.
23 is an exemplary view showing an average degree of association criteria of major language units for each list according to another embodiment of the present invention.
24 and 25 are exemplary views showing keywords and keyword categories in main language units for each list according to an embodiment of the present invention.
26 is an exemplary view showing keywords and keyword categories in main language units for each list according to another embodiment of the present invention.
27 is an exemplary view showing a language unit adjustment interface corresponding to a clicked list according to an embodiment of the present invention.
28 is an exemplary view showing an interface for adjusting all language units corresponding to a clicked list according to an embodiment of the present invention.
29 is an exemplary view showing an interface for adjusting a language unit corresponding to a clicked list according to another embodiment of the present invention.
30 is an exemplary view showing an interface for adjusting all language units corresponding to a clicked list according to another embodiment of the present invention.
31 is a diagram illustrating an example of a recommendation item recommended by an item recommendation system using a degree of association between a language unit and a use item according to the present invention.

Hereinafter, a method and apparatus for recommending items using a degree of association between a language unit and a used item according to the present invention will be described in more detail through detailed description of embodiments with reference to the drawings. In describing the present invention, if it is determined that a detailed description of a related known technology or configuration may unnecessarily obscure the subject matter of the present invention, a detailed description thereof will be omitted. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a client, an operator, or a user. Therefore, the definition should be made based on the overall contents of the present invention.

The same reference numerals refer to the same elements throughout the drawings.

Hereinafter, in the present application, the language unit may be, for example, a single word/word, such as “lovely”, “remembering of home meal,” or a series of several words/words.

1 is a schematic overall block diagram of an item recommendation system using a degree of association between language units and usage details according to the present invention.

Referring to FIG. 1, an item recommendation system using a degree of association between a language unit and a usage history according to the present invention may include a communication network 150, a terminal 200, and an item recommendation device 300.

Here, the terminal 200 is, for example, a smart phone, PDA, tablet PC, notebook computer, laptop computer, personal computer, and other electronic devices or similar devices capable of performing communication, receiving user input, and outputting a screen. Can be implemented.

In addition, the item recommendation device 300 may be implemented as, for example, a workstation, a server, a general computer, an electronic device capable of performing other communication, or a similar device.

In addition, the terminal 200 and the item recommendation device 300 are connected through the communication network 150 and communicate with each other through the communication network 150.

In addition, the communication network 150 is, for example, LTE (Long Term Evolution), LTE-A (LTE-Advanced), WI-FI, LAN (Local Area Network), WAN (Wide Area Network), CDMA (Code Division Multiple Access). ), Time Division Multiple Access (TDMA), Wireless Broadband (WiBro), Global System for Mobile Communications (GSM), and others. It may be implemented using at least some of the communication methods developed in the past, present, or available in the future. Hereinafter, for convenience, it will be described as if the terminal 200 and the item recommendation device 300 directly communicate with each other without referring to the communication network 150.

Detailed operations and configurations of the terminal 200 and the item recommendation device 300 will be described later with reference to FIGS. 2 to 8.

2 is a block diagram showing the configuration of the terminal shown in FIG. 1.

Referring to FIG. 2, the terminal 200 may include an input unit 210, a display unit 220, a communication unit 230, a storage unit 240, and a control unit 250.

Here, the input unit 210 converts a user's input operation into an input signal and transmits it to the control unit 250. The input unit 210 may be implemented as, for example, a keyboard, a mouse, a touch sensor on a touch screen, a touch pad, a keypad, a voice input, and other input processing devices that are possible in the present, in the past, or in the future. The input unit 210 may receive, for example, a user's item recommendation request input and transmit it to the control unit 250.

In addition, the display unit 220 outputs a screen according to the control of the controller 250. The display unit 220 may be implemented as, for example, an LCD (liquid crystal display), an LED (light emitting diode), an OLED (organic light emitting diode), a projector, and other display devices that are possible in the present, in the past, or in the future. The display unit 220 may display, for example, an interface page for item recommendation or an item recommendation result page.

In addition, depending on the embodiment, instead of the screen output, a component using a different method for transmitting information to the user such as voice output or vibration may be used instead of the display unit 220.

In addition, the communication unit 230 exchanges data with the item recommendation device 300 and/or other external devices. The communication unit 230 transmits the data received from the item recommendation device 300 to the control unit 250. In addition, the communication unit 230 transmits data to the item recommendation device 300 under the control of the controller 250. The communication technology used by the communication unit 230 may vary depending on the type of communication network 150 or other circumstances.

Also, the storage unit 240 stores data under the control of the controller 250 and transmits the requested data to the controller 250.

In addition, the controller 250 controls the overall operation of the terminal 200 and each component. The control unit 250 transmits an item recommendation request and other data to the item recommendation device 300 according to the information input from the input unit 210 as described later, and according to the page information received from the item recommendation device 300 The result page and/or the interface page are displayed through the display unit 220. The operation performed by the control unit 250 may be distributedly processed by several physically separated computing devices. Some of the operations performed by the controller 250 are performed by the first server and other operations are performed by the second server. In this case, the control unit 250 may be implemented as a total number of physically separated computing devices.

Here, the storage unit 240 may be implemented as a total of physically separated storage devices.

In addition, when the controller 250 or the storage unit 240 is implemented as a total of several devices that are physically separated, communication between several devices may be required. Here, for the sake of simplicity, description will be made on the assumption that the storage unit 240 or the control unit 250 is implemented as one object.

In addition, when the terminal 200 transmits and receives data, it may be expressed that the communication unit 230 transmits and receives data according to the control of the controller 250 according to the viewpoint, and the controller 250 controls the communication unit 230 to transmit data. It can also be expressed as sending and receiving.

Specific operations of each component of the terminal 200 will be described later with reference to FIGS. 4A to 8.

3 is a block diagram showing the configuration of the item recommendation device shown in FIG. 1.

Referring to FIG. 3, the item recommendation device 300 may include a communication unit 310, a control unit 320, and a storage unit 330.

Here, the communication unit 310 exchanges data with the terminal 200. The communication unit 310 transmits the data received from the terminal 200 to the control unit 320. In addition, the communication unit 310 transmits data to the terminal 200 under the control of the controller 320. The communication technology used by the communication unit 310 may vary depending on the type of communication network 150 or other circumstances.

In addition, the storage unit 330 stores data under the control of the controller 320 and transmits the data requested from the controller 320 to the controller 320.

In addition, the controller 320 controls the overall operation of the item recommendation device 300 and each component. When receiving an interface page request, an item recommendation result page request, and other data through the communication unit 310, the control unit 320 loads necessary data from the storage unit 330 and generates page information. The page information is transmitted to the terminal 200 through the communication unit 310.

Here, when the item recommendation device 300 transmits and receives data, it may be expressed that the communication unit 310 transmits and receives data according to the control of the controller 320 according to the viewpoint, or the controller 320 controls the communication unit 310 It can also be expressed as transmitting and receiving data. In addition, according to an embodiment, data for providing information may be transmitted and received by voice or other methods instead of a page for visually providing information.

Detailed operations of each component of the item recommendation device 300 will be described later with reference to FIGS. 4A to 8.

4A to 4C are flowcharts illustrating an item recommendation process through an item recommendation interface according to an embodiment of the present invention.

4A to 4C, an item recommendation process through the item recommendation interface is as follows.

First, in step S401, a degree of association between language units and items is set by the control unit 320 of the item recommendation device 300. This process may be performed by a method described later with reference to FIGS. 5 to 9, may be set by an administrator, or may be set in another method.

Thereafter, in step S402, an experience item list including the user's experience item is obtained by the control unit 320 of the item recommendation device 300. Here, the experience item is, for example, a purchase of the product, a preference mark (e.g., like), a visit record (e.g., a photo held by the terminal, a photo uploaded by the user, or location information of the terminal) Analysis, etc.), items with selection/inquiry records, and can be limited according to item categories (travel destinations/movies/broadcast programs). In addition, the experience item may be limited to a period within a certain period from the present to the past according to an embodiment.

Steps S403 to S407 below may be omitted when servicing only one item category.

Thereafter, in S403, the control unit 320 of the item recommendation device 300 generates item category selection interface page information including a language unit list together with an experience item. Here, the item category selection interface page information is information necessary to generate an item category selection interface page. In addition, the item category selection interface page is a page for inducing a user's input, receiving the user's input, and transmitting it to the item recommendation device 300. For example, the item category selection interface page information may be in the form of an HTML document or other markup language document. In addition, according to an embodiment, the terminal 200 has the form information of the item category selection interface page in advance, and only items corresponding to the content may be transmitted from the item recommendation device 300 to the terminal 200. Hereinafter, for convenience, it is assumed that interface page information or other page information is delivered in an HTML document format. However, it is not intended to limit the present invention to this.

Thereafter, in step S404, the item category selection interface page information is transmitted to the terminal 200 by the communication unit 310 of the item recommendation device 300.

Thereafter, in step S405, the control unit 250 of the terminal 200 constructs an item category selection interface page using the item category selection interface page information, and the display unit 220 of the terminal provides the user 400 with the item category selection interface page. Is displayed. Here, the item category selection interface page may include, for example, an interface through which the user 400 requests item recommendation, inputs and/or selects a keyword for item recommendation, and sets for other item recommendation. .

Thereafter, in step S406, the input unit 210 of the terminal 200 receives the item category selection input of the user 400 inputted through the item category selection interface page and transmits it to the controller 250. Here, the virtual user's experience is selected.

Thereafter, in step S407, the communication unit 230 of the terminal 200 transmits item category selection input information for identifying the user's item category selection input to the item recommendation device 300 under the control of the controller 250. .

Thereafter, in step S408, the control unit 320 of the item recommendation device 300 obtains a language unit/relevance pair corresponding to the user's experience item list. Here, the language unit/relevance pair is associated with each experience item in the experience item list including the user's experience item acquired in step S402, and is obtained based on a threshold value. In addition, the threshold value may be, for example, a maximum number or a minimum degree of association.

For example, according to an embodiment in which the threshold value is the maximum number, the control unit 320 selects the maximum number of language units (for example, 10) among language units for which a degree of association is set for a specific experience item in the experience item list. The degree of relevance (the degree of relevance to the relevant experience item) can be selected in the order of high, and acquired/stored as a language unit-relevance pair.

This process can be performed for all experience items included in the experience item list. If i1 to i10 are included in the experience item list, and the language unit-related degree pair corresponding to i1 is p1_1 to p1_10, p2_1 to p1_10 .... p10_1 to p10_10 may be acquired/stored through the same process. The language unit-relationship pair obtained in this way may be used to obtain a language unit-user association in step S431.

For example, according to an embodiment in which the threshold is the maximum number, the control unit 320 has the minimum degree of association (the degree of relevance to the corresponding experience item) among language units in which a degree of relevance is set for a specific experience item in the experience item list. For language units with a degree of association or higher, a language unit-association degree pair can be obtained/saved. This process can be performed for all experience items included in the experience item list.

The processes of steps S410 to S430 may be provided when additional management is required by the administrator or may be omitted. In addition, in the processes of S410 to S430, an interface may be provided to the service manager, not the user.

Thereafter, in step S410, the control unit 320 of the item recommendation device 300 generates a "main language unit for each language unit list" screen, a web chart, and a scattered chart for each language unit list.

Thereafter, in step S411, the communication unit 310 of the item recommendation device 300 transmits a screen, a web chart, and a distributed chart to the terminal 200 under the control of the controller 320. Deliver.

Thereafter, in step S412, the display unit 220 of the terminal 200 displays a "main language unit for each language unit list" screen, a web chart, and a distributed chart to the user 400.

Thereafter, in step S413, the input unit 210 of the terminal 200 receives the enlarged input of the user 400 in the scatter chart.

Thereafter, in step S414, the communication unit 230 of the terminal 200 transmits the enlarged similar language unit information according to the enlarged input of the user 400 to the item recommendation device 300 under the control of the control unit 250.

After that, in step S415, the interface page information in units of similar languages is generated by the control unit 320 of the item recommendation device 300.

Thereafter, in step S416, the interface page information in units of similar languages is transmitted to the terminal 200 by the communication unit 310 of the item recommendation device 300.

Thereafter, in step S417, the control unit 250 of the terminal 200 constructs a similar language unit interface page using the similar language unit interface page information, and the display unit 220 of the terminal provides the user 400 with the similar language unit interface page. Is displayed.

Thereafter, in step S418, the input unit 210 of the terminal 200 receives the edit input for the list of specific language units of the user 400 and transmits the input to the control unit 250.

Thereafter, in step S419, the communication unit 230 of the terminal 200 enters an edit input for a specific language unit list capable of identifying an edit input for a specific language unit list of the user 400 under the control of the control unit 250 The information is transmitted to the item recommendation device 300.

Thereafter, in step S420, interface page information for adding/deleting a language unit corresponding to a specific language unit list is generated by the control unit 320 of the item recommendation device 300.

Thereafter, in step S421, interface page information for adding/deleting language units corresponding to the specific language unit list is transmitted to the terminal 200 by the communication unit 310 of the item recommendation device 300 under the control of the controller 320. Deliver.

Thereafter, in step S422, the control unit 250 of the terminal 200 configures an interface page for adding/deleting language units by using the interface page information for adding/deleting language units, and the display unit 220 sends to the user 400. Displays the interface page for adding/deleting language units corresponding to the specific language unit list.

Thereafter, in step S423, the input unit 210 of the terminal 200 adds a language unit corresponding to the specific language unit list requested to be added/deleted through the interface page for adding/deleting the language unit corresponding to the specific language unit list. /Delete.

Thereafter, in step S424, the input unit 210 of the terminal 200 receives an input of “selecting a language unit” from the user 400 and transmits it to the control unit 250.

Thereafter, in step S425, the communication unit 230 of the terminal 200 transmits input information of “selecting a language unit” to identify an input of “selecting a language unit” according to the control of the controller 250. ).

Thereafter, in step S426, the control unit 320 of the item recommendation device 300 generates the addition/deletion interface page information for the entire language unit.

Thereafter, in step S427, the communication unit 310 of the item recommendation device 300 transmits the addition/deletion interface page information for the entire language unit to the terminal 200 under the control of the controller 320.

Thereafter, in step S428, the control unit 250 of the terminal 200 configures the add/delete interface page using the add/delete interface page information, and the display unit 220 adds/deletes the entire language unit to the user 400. Display the interface page. Here, language units are grouped and displayed according to a list.

Thereafter, in step S429, the input unit 210 of the terminal 200 receives the add/delete input for the entire language unit of the user 400 and transmits the input to the control unit 250.

Thereafter, in step S430, the communication unit 230 of the terminal 200 recommends the addition/deletion input information for the entire language unit to identify the addition/deletion input for the entire language unit under the control of the controller 250. To the device 300.

Thereafter, in step S431, a language unit between the user and each language unit based on a language unit-relevance pair between all language units corresponding to the experience item list by the control unit 320 of the item recommendation device 300 -Acquire user relevance. According to some embodiments, the controller 320 includes a cumulative value of a degree of association corresponding to a specific language unit with respect to the entire language unit-relevance degree pair corresponding to the experience item list and a language unit between the user and the specific language unit. Language unit-user association can be set so that the user association has a positive correlation. For example, the experience item list includes item 1, item 2, item 3, ... item k, and the set of language unit-relevance pairs corresponding to item n is {(T1, W1_n), (T2, Assuming that W2_n), ..., (Tj, Wj_n)}, the cumulative value of the degree of association corresponding to the specific language unit Tm may be ∑ _n=1...k (Wm_n). Where Wm_n is the degree of association between item n and a specific language unit Tm. According to some embodiments, when the correlation between item n and a specific language unit Tm is 0 or less than a specific reference value, the (Tm, Wm_n) pair may be omitted without being stored. The controller 320 may not store information corresponding to the language unit-relationship pair (Tm, Wm_n) when the association of item n and the specific language unit Tm is 0 or less than a specific reference value. Thereafter, if information corresponding to the language unit-relationship pair (Tm, Wm_n) is not stored, the controller 320 may treat the item n as having a degree of association of 0 corresponding to the specific language unit Tm.

According to some embodiments, the controller 320 determines that the cumulative value of the degree of association corresponding to the specific language unit with respect to the entire language unit-relevance pair corresponding to the experience item list is a language unit between the user and the specific language unit- The language unit-user association may be set so that the degree of user association or the cumulative value of the association degree corresponding to the specific language unit is proportional to the language unit-user association between the user and the specific language unit.

Thereafter, in step S432, the control unit 320 of the item recommendation device 300 generates user recommendation item list information based on a language unit-user association.

For example, the control unit 320 is a value obtained by accumulating individual values having a positive correlation to the language unit-user association degree for a specific language unit and the language unit-item association degree for the specific language unit for all language units Item-user association can be set to have a positive correlation with.

In a specific embodiment, the controller 320 multiplies a language unit-user association degree for a specific language unit and a language unit-item association degree for a specific language unit, and a positive correlation with a value accumulated for all language units. Item-user association can be set to have a relationship.

In a specific embodiment, the controller 320 is a value obtained by multiplying a language unit-user association degree for a specific language unit and a language unit-item association degree for the specific language unit as a value accumulated for all language units. You can set the degree of association.

For example, if the language unit-user association between a specific language unit i and the user is U _i and the language unit-item association between a specific item I _j and the language unit i is R _ij, then the specific item I _j and the user -User relevance can be expressed as ∑ _i=0...k-1 f(R _ij , U _i ). Here, k is the number of language units having a non-zero language unit-item association in relation to a specific item I _j . Here, f(x, y) may be, for example, a value obtained by multiplying x and y, or may be another operation in which x and y and f(x, y) have a positive correlation. In the modified example, the item-user association and the cumulative value of ∑ _i=0...k-1 f(R _ij , U _i ) are positively correlated, rather than a simple accumulation (∑ _i=0...k-1 ). Other equations, including proportional operations, logarithmic operations, etc., can be used to find the item-user association.

The controller 320 may generate a user recommended item list according to the item-user association.

Thereafter, in step S433, the communication unit 310 of the item recommendation device 300 transmits the user recommendation item list information to the terminal 200 under the control of the controller 320.

Thereafter, in step S434, the control unit 250 of the terminal 200 constructs a user recommendation item using the user recommendation item list information, and the display unit 220 displays the user recommendation item to the user 400.

In the embodiments of FIGS. 4A to 4C, it is assumed that a page in a visual form is provided to the user, but it is also possible to provide an interface or result information through voice. In this case, an audio output unit may be used instead of the display unit 220. Instead of the visual/audible method, another type of interface method that is currently possible or will be possible in the future may be used in the relationship with the user 400. In this case, the item recommendation device 300 may provide the terminal 200 with information converted in a different manner instead of page information to fit the interface method.

In the embodiment after FIG. 5, the user 400 wants to be provided with information on an object of a specific field of interest that the user 400 is interested in. However, it is not intended to limit the present invention to this.

Here, the field of interest may be, for example, an object type. For example, if the field of interest is'celebrity', the object corresponding to this field of interest may include'Yoo Si O','Yoo Jae O', and'Taylor Sw O'. For example, if the field of interest is'movie', objects corresponding to this field of interest may include'Dunkir O','Spider O Homeker O','Super Boat O 3', and the like. For example, if the field of interest is'broadcasting program', objects corresponding to this field of interest may include'Infinite OO','American AOO','OO of the Throne', and the like.

In the following embodiments, a document is collected to evaluate the relationship (relevance/weight, etc.) between keywords. Collected documents may all be evaluated as having equal value, or newer documents may be evaluated as having higher value. That is, the association between the age of the document at the time of evaluation and the keywords appearing in the document may have a negative correlation.

Even in the process after FIG. 5 to be described later, the value may be evaluated differently according to the freshness of the document. For example, a case where two keywords appear together in a document 1 day after the evaluation point can be evaluated with a 10 times higher association than a case where two keywords appear together in a document 10 days after the evaluation point. The age of a document may be evaluated in units of seconds/minutes/hours, or in units of days/months/years. For the document evaluated before the age of the document is reflected, the control unit 320 divides the partial relevance value by the age of the document to extract a partial relevance reflecting the document age, and accumulates the partial relevance to two keywords You can extract the degree of association between them.

The creation time of a document to check the age of a document can be determined using, for example, the posting time and/or metadata included in the document, or through periodic crawling, when a new document not found in the previous crawl is found. In this case, it may be determined that a new document was added at the time of a new crawl.

5 is a flowchart of an item recommendation process according to an embodiment of the present invention.

In step S510, the object-keyword association corresponding to the object item and the representative attribute keyword pair is stored in the storage unit 330 by the control unit 320. The process of step S510 may be performed according to, for example, some of the embodiments of FIGS. 6 to 8, a process similar thereto, or a process corresponding thereto. Depending on the embodiment, the process of step S510 may be performed as an input of an administrator or may be performed by receiving an object-keyword association degree determined in an external system through a network or a storage medium.

Meanwhile, the stored object-keyword association diagram is as shown in FIG. 10 showing an example of the stored object-keyword association diagram according to an embodiment of the present invention. In the embodiment of FIG. 10, there are m number of object items (i ₁ to i _m ) and n number of representative attribute keywords (k ₁ to k _n ). For example, the object-keyword association of the object item i ₅ and the representative attribute keyword k ₃ is w _5,3 .

In addition, step S510 is as follows with reference to FIG. 6 showing a detailed procedure of step S510 of FIG. 5.

6, in step S610, a representative attribute keyword candidate set is extracted from the first set of documents by the controller 320. In this case, the controller 320 may collect, for example, keywords frequently appearing in documents corresponding to the field of interest among the first set of documents as a representative attribute keyword candidate set.

In addition, step S610 is as follows with reference to FIG. 7 showing a detailed procedure of step S610 of FIG. 6.

Referring to FIG. 7, the control unit 320 selects keywords appearing in a document, such as object keywords indicating object items belonging to a specific interest field, and keywords appearing in documents, such as field keywords indicating specific interest fields, as first attribute keywords. It can be set as a candidate set and a second attribute keyword candidate set.

For example, if the field of interest to provide the item recommendation service is a celebrity, the field keyword may include'celebrity','celebrity','movie actor','star','celebrity','celeb', and the like. The field keyword may be set by an administrator or recommended/set by the controller 320. After acquiring some field keywords, the controller 320 may recommend/set a similar keyword, which has been analyzed to have a degree of association with the field keywords or higher, as an additional field keyword.

In addition, if the field of interest for providing the item recommendation service is a celebrity, the object keyword may be an individual person belonging to the field of interest. For example, "Yoo Jae O", "Taylor Swew OO", and "Stephan OO" may be object keywords corresponding to celebrities in the field of interest.

Here, to describe the relationship between the field keyword and the object keyword, for example, the field keyword may correspond to the attribute or type of the object keyword. If the field keyword indicates a set, the object keyword may indicate elements belonging to the set.

Also, the object keyword may be set by the administrator or may be selected in a similar manner to the field keyword. Depending on the embodiment, the controller 320 may analyze the context of the collected documents and select keywords that are determined to be elements belonging to the set indicated by the field keywords as object keywords.

Also, popular object keywords and non-popular object keywords may be classified according to the amount of search/collection of the corresponding object keywords. The controller 320 may search/collect a document including each object keyword, set an object keyword whose collection amount is greater than or equal to a specific threshold value as a popular object keyword, and set the remaining object keywords as an unpopular object keyword.

Also, keywords in popular fields and keywords in unpopular fields may be classified according to the amount of search/collection of keywords in the field. The controller 320 may search/collect a document including each field keyword, set a field keyword whose collection amount is greater than or equal to a specific threshold value as a popular field keyword, and set the remaining field keywords as an unpopular field keyword. However, a threshold value for distinguishing a popular object keyword from a non-popular object keyword and a threshold value for distinguishing a popular field keyword and a non-popular field keyword may be different. Hereinafter, for convenience, the popular object keywords and popular field keywords are collectively referred to as popular field object keywords. In addition. For convenience, unpopular object keywords and unpopular field keywords are collectively referred to as unpopular field object keywords.

In addition, in a modified embodiment, only a popular field keyword or a popular object keyword may be used instead of the popular field object keyword. In a modified embodiment, only the unpopular field keyword or the unpopular object keyword may be used instead of the unpopular field object keyword.

In step S710, the controller 320 sets keywords that appear together in the same document as the popular field object keyword as a first attribute keyword candidate set.

Here, the controller 320 may search/collect documents including popular field object keywords, and set keywords included in the collected documents as a first attribute keyword candidate set.

According to another embodiment, the controller 320 may exclude a field keyword and an object keyword from among keywords included in the collected document from the first attribute keyword candidate set. In addition, the controller 320 may exclude a preset meaningless keyword, for example, a survey/article, etc. from the first attribute keyword candidate set. According to another embodiment, the controller 320 may include a keyword registered in a preset dictionary among keywords included in the collected document in the first attribute keyword candidate set.

According to another embodiment, the control unit 320 includes a popular field object keyword.

Search/collect documents, and find popular field object keywords or keywords in the collected documents.

Keywords arranged within a preset distance from the included sentence may be included in the first attribute keyword candidate set. According to another embodiment, the control unit 320 searches for/collects a document containing a keyword of a popular field object, analyzes a context, and selects keywords used for formulating/descripting a keyword of a popular field object as a first attribute keyword candidate. It can also be included in the set.

In addition, the distance between keywords or the distance between a keyword and a sentence is, for example, the number of two keywords or sentences positioned between a keyword and a sentence, the number of two keywords or words positioned between a keyword and a sentence, two keywords or keywords and sentences. It may be determined based on one or more of the number of words positioned between, two keywords, or the number of characters between a keyword and a sentence. The controller 320 may first perform morpheme analysis for keyword analysis.

In step S720, keywords appearing in the same document as non-popular field object keywords are set by the controller 320 as the second attribute keyword candidate set.

Here, the controller 320 may search/collect a document including an unpopular field object keyword, and set keywords included in the collected document as a second attribute keyword candidate set.

According to another embodiment, the controller 320 may exclude a field keyword and an object keyword from among keywords included in the collected document from the second attribute keyword candidate set. In addition, the controller 320 may exclude preset meaningless keywords, for example, survey/article, etc. from the second attribute keyword candidate set. According to another embodiment, the controller 320 may include a keyword registered in a preset dictionary among keywords included in the collected document in the second attribute keyword candidate set.

According to another embodiment, the controller 320 searches/collects a document containing an unpopular field object keyword, and retrieves keywords arranged within a preset distance from the unpopular field object keyword or a sentence containing the keyword in the collected document. It may be included in the second attribute keyword candidate set. According to another embodiment, the control unit 320 searches for/collects a document containing an unpopular field object keyword, analyzes the context, and selects keywords used for formulating/descripting the unpopular field object keyword as a second attribute keyword candidate. It can also be included in the set.

In addition, the distance between keywords or the distance between a keyword and a sentence is, for example, the number of two keywords or sentences positioned between a keyword and a sentence, the number of two keywords or words positioned between a keyword and a sentence, two keywords or keywords and sentences It may be determined based on one or more of the number of words positioned between, two keywords, or the number of characters between a keyword and a sentence. The controller 320 may first perform morpheme analysis for keyword analysis.

In step S730, keywords belonging to both the first attribute keyword candidate set and the second attribute keyword candidate set may be set as the representative attribute keyword candidate set by the controller 320. That is, keywords that are used as expressions for modifying popular field object keywords and also as expressions for non-popular field object keywords may be collected as a representative attribute keyword candidate set.

According to another embodiment, in step S610, the controller 320 may include keywords that appear together with object keywords and/or field keywords in the representative attribute keyword candidate set regardless of whether they are popular or unpopular.

Returning to FIG. 6, in step S620, two or more sub-keywords associated with each representative attribute keyword included in the representative attribute keyword candidate set are extracted from the second set of documents by the control unit 320.

The second set document used for extracting the lower keyword in step S620 and the first set document used for extracting the representative attribute keyword candidate set in step S610 may be different document sets or may be the same document set. For example, the first set of documents may be a set including all collectable documents, and the second set of documents may be a set including only documents in which a specific field of interest to provide an item recommendation service is used as a main keyword. . The controller 320 may analyze collectible documents and analyze whether each document is a document used as a main keyword in a specific field of interest for which the item recommendation service is to be provided, based on keywords that appear frequently.

According to another embodiment, both the first set of documents and the second set of documents may be a set including all collectable related documents. According to another embodiment, the first set of documents may be a set including all of the collectable related documents, and the second set of documents may be a set including only documents related to a specific field of interest for which an item recommendation service is to be provided.

According to another embodiment, the second set of documents may be a set including all of the collectable related documents, and the first set of documents may be a set including only documents related to a specific field of interest for which an item recommendation service is to be provided.

For step S620, the control unit 320, for example, in order to generate a set including only documents related to a specific field of interest for which the item recommendation service is to be provided, documents including a field keyword indicating the field of interest itself and/ Alternatively, a set including only documents related to a specific interest may be generated by collecting documents including object keywords belonging to a corresponding interest field, and extracting documents in which the weight of the field keyword/object keyword is greater than or equal to a preset value. The weight of the field keyword/object keyword can be determined based on the frequency, location, and context of the field keyword/object keyword. For example, a document in which a field keyword/object keyword frequently appears, a field keyword/object keyword is used as the title of the document, or is displayed in large letters or fonts for emphasis may be classified as documents related to a specific field of interest. .

In step S620, the control unit 320 analyzes at least a portion of the second set of documents, extracts a preset number of sub-keywords having the highest correlation with each representative attribute keyword, and extracts two or more sub-keywords associated with each representative attribute keyword. Can be extracted.

Here, the controller 320 may determine a degree of association between the representative attribute keyword and the lower keyword in consideration of the frequency at which the lower keyword appears in the same or similar context as the representative attribute keyword, for example. For example, it can be seen that words appearing around keyword A in a specific sentence may appear around words related to keyword A in other documents.

"I went on a trip with a big heart, but because it was July, the weather was too hot and I suffered."

"I went on a trip with a big heart, but because it was July, the weather was too humid, so I suffered."

Looking at the above two sentences, the word "because it's hot" has been replaced by the word "because it's wet" in the same context. The controller 320 may infer that “hot” and “wet” are words related to each other.

"I went on a trip with a big heart, but because it was July, the weather was too hot and I suffered."

"I went on vacation with a big heart, but because it was July, it was too hot and I suffered."

Similarly, the control unit 320 may infer that “travel” and “vacation” are related words through the above two sentences.

"I went on a trip with a big heart, but because it was July, the weather was too hot and I suffered."

"I went on a trip with a big heart, but because it was August, the weather was too hot and I suffered."

Similarly, the controller 320 may infer that “July” and “August” are related words through the above two sentences.

Therefore, the control unit 320 is the words "hot" and "wet" are related to each other through the previously collected documents, "July" and "August" are related words, and "travel" and "vacation" are related to each other. It can be stored as a word. It is assumed that the following sentences are collected.

"I went on vacation with a big heart, but because it was July, the weather was too humid, so I suffered."

"I went on a trip with a big heart, but it was hard because the weather was too hot because it was August."

The above two sentences are not the same context, but if you know that "hot" and "wet" are related words, "July" and "August" are related words, and "travel" and "vacation" are related words, the control unit (320) will be able to learn that "I suffered" and "I was difficult" are also related words through the above sentence.

Keyword pairs with a high frequency appearing in the same/similar context may be determined to have a high correlation with each other. In addition, the higher the similarity between the context in which the two keywords appear, the higher the correlation between the two keywords can be determined. The control unit 320 performs learning using the collected documents to set the degree of association between keywords, and sets the degree of relevance of keywords appearing in the sentence by using the relationship between the set keywords and the context of the sentence. The accuracy of judging the relationship between liver can also be improved.

In a similar learning method, NNLM (Neural Net Language Model),

RNNLM (Recurrent Neural Net Language Model), word2vec, skipgram, and CBOW (Continuous Bag-of-Words) methods are known. In particular, when word2vec is used, word2vec learns using documents and associates each keyword with a vector, and the similarity between the two keywords can be determined by calculating the cosine similarity of the two vectors.

In this manner or a similar manner, the controller 320 may analyze at least a part of the second set of documents and extract sub-keywords having the highest correlation with each representative attribute keyword by a preset number.

In step S630, the controller 320 may extract an association weight corresponding to each representative attribute keyword and lower keyword pair in the representative attribute keyword candidate set from the second set of documents.

In addition, step S630 is as follows with reference to FIG. 8 showing a detailed sequence of step S630 of FIG. 6.

Referring to FIG. 8, in step S810, at least a part of the second set of documents may be analyzed by the controller 320 to extract a degree of correlation between lower keywords. For example, it is assumed that those collected as related sub-keywords for the representative attribute keyword A1 are 50 sub-keywords of B1 ₁ to B1 ₅₀ . In this case, the controller 320 may extract a degree of correlation between the two sub-keywords by using the frequency at which the two sub-keywords appear together in the same document for these 50 sub-keywords. B1 is also interconnected between the _first B1 and B1 ₂ and B1 is determined in accordance with the _first frequency to the _second appearing in the same document. According to another embodiment, in addition to the frequency in which B1 ₁ and B1 ₂ appear in the same document affects the degree of correlation, when B1 ₁ and B1 ₂ appear in the same document, the distance between two keywords B1 ₁ and B1 ₂ The closer (or the distance between sentences in which two keywords appear), the higher the degree of correlation can be recognized. In a similar way, the degree of correlation between sub-keywords can be extracted. The distance between keywords or between a keyword and a sentence is, for example, the number of two keywords or sentences placed between a keyword and a sentence, the number of words placed between two keywords or a keyword and a sentence, between two keywords or a keyword and a sentence. It may be determined based on one or more of the number of positioned words, two keywords, or the number of characters between a keyword and a sentence.

In step S820, the control unit 320 may extract a correlation weight between each representative attribute keyword and the lower keyword based on the degree of correlation between the lower keywords.

Here, the control unit 320, for example, with respect to a sub-keyword set corresponding to each representative attribute keyword, a correlation between a specific sub-keyword in the sub-keyword set and another sub-keyword in the sub-keyword set, and a specific sub-keyword and representative attribute An association weight between a specific lower keyword and a representative attribute keyword may be set so that the association weight between keywords has a positive correlation with each other.

For example, as the correlation between the sub-keyword B1 ₁ of the representative attribute keyword A1 and other sub-keywords B1 ₂ to B1 ₅₀ of A1 is higher, the association weight between A1 and B1 ₁ may be set higher. For example, an arithmetic mean (or sum) of correlations between B1 ₁ and other sub-keywords B1 ₂ to B1 ₅₀ of A1 may be an association weight between B1 ₁ and A1. Instead of a simple arithmetic mean, a geometric mean/harmonized mean may be used. A cutting average that is averaged out of the correlations between the sub-keywords B1 ₁ and other sub-keywords of A1 (B1 ₂ to B1 ₅₀ ) may be used, excluding the two highest (example) and two lowest (example). have. A median may be used instead of the arithmetic mean of the correlation.

According to some embodiments, the sentence "B1 ₁ and frequency B1 of ₂ appears on the same document" is simply (or, such that appeared as a B1 ₁ and B1 ₂ is used to calculate the associated weight of B1 ₁ for A1 varies, not according to the number of which, or close to the appearance appearance) document, B1 ₁ and B1 ₂ is to appear (or that appear in the same sentence, or close to that) that B1 ₁ appeared the number of documents emerge as It can be obtained by dividing the number of documents and/or the number of documents in which B1 ₂ appears. "B1 ₁ and B1 ₂ on the frequency of appearance in such documents" in a manner similar to the B1 ₁ and B1 ₂ is an appearance number of the document and the amount of correlation (or, or close-up appearance which by appearing in the same sentence) that, as It may be set to have a negative correlation with the number of documents in which B1 ₁ appears and/or the number of documents in which B1 ₂ appears. It is simply a kind of normalization to prevent commonly used words from having a high association weight on the representative attribute keyword A1.

Returning to FIG. 6, in step S640, a lower association degree between the object item and the lower keyword may be extracted from the first set of documents by the controller 320.

Here, among the first set of documents, a document such as an object keyword indicating an object item (for example, "Taylor Swivel"), or sub-keywords frequently appearing in the same sentence or adjacent sentence may be determined to be related to the object item. .

In addition, the controller 320 may collect documents in which the object keyword of the corresponding object item appears, and extract a lower correlation between the lower keyword and the object keyword according to the frequency of appearing together in the documents. In particular, when the lower keyword appears in the same sentence as the object keyword, the control unit 320 may set the association between the lower keyword and the object item to be higher than when the lower keyword appears in a sentence different from the object keyword.

Also, as the sentence in which the lower keyword appears is closer to the sentence in which the object keyword appears, the controller 320 may set a higher degree of association between the lower keyword and the object item of the corresponding object keyword. The proximity of two sentences is, for example, the number of sentences between two sentences, the number of words between two sentences, the number of words between two sentences, and the number of letters between two sentences. It may be determined based on more than one.

In addition, the controller 320 may set the association between the lower keyword and the object item of the corresponding object keyword to be higher as the position where the lower keyword appears is closer to the position where the object keyword appears. The proximity between the sub-keyword and the object keyword is, for example, the number of sentences between the sub-keyword and the object keyword, the number of words between the sub-keyword and the object keyword, and the words between the sub-keyword and the object keyword. It may be determined based on one or more of the number of and the number of characters positioned between the lower keyword and the object keyword.

In step S650, an object-keyword association degree between the object item and each representative attribute keyword may be extracted by using the association weight in step S630 and the sub-relationship degree in step S640 by the controller 320.

For example, the object-keyword association between the object item C and the representative attribute keyword A1 is the sub-relationship between the sub-keywords of C and A1 (for example, B1 ₁ to B1 ₅₀ ) and the association weight of each sub-keyword. It can be extracted using. For example, the object-keyword association degree between the object item C and the representative attribute keyword A1 may be set higher as the lower degree of association between the object item C and B1 ₁ to B1 ₅₀ is higher.

In addition, in the relationship with A1, if the sub-keyword with a higher association weight has a higher sub-relationship with the object item C, the sub-keyword with a lower association weight has a higher sub-relationship with the object C and the representative attribute keyword A1. The object-keyword association between them may be set higher. For example, in the case of Table ₁ , the sub-relationship of the one with higher association weight (B1 ₁ ) than in the case of Table 2 is higher, so that in the case of Table 1, the object between object C and the representative attribute keyword A1- Keyword relevance may be set high.

Associated weight with A1 Degree of association with C B1 ₁ 0.5 0.5 B1 ₂ 0.2 0.2

Associated weight with A1 Degree of association with C B1 ₁ 0.2 0.5 B1 ₂ 0.5 0.2

According to an embodiment, the object-keyword association degree between the object C and the representative attribute keyword A1 may be obtained as a sum (or using the sum) multiplied by the association weight corresponding to each sub-keyword and the sub-relationship. In the case of Table 1, 0.5×0.5+0.2×0.2=0.29, and in the case of Table 2, 0.2×0.5+0.5×0.2=0.20, so the case of Table 1 is between the object C and the representative attribute keyword A1 than the case of Table 2. The object-keyword association degree of may be set to be high. The above-described method of calculating the object-keyword association is only an example, and if the association weight with A1 in step S630 and the sub-relationship with C in step S640 are positively correlated with the object-keyword association between C and A1. Other methods may be used.

Thereafter, when the communication unit 310 receives a request for recommending an item related to a specific representative attribute keyword, the control unit 320 may provide a result item through the communication unit 310 based on the object-keyword association degree extracted in step S650. . For example, when receiving an item recommendation request including one of the representative attribute keywords, the controller 320 may provide information on the object items in the order of the highest object-keyword association in the relationship with the corresponding representative attribute keyword. have.

In another embodiment, when receiving an item recommendation request including two or more representative attribute keywords and weights corresponding thereto, the controller 320 associates object-keywords with representative attribute keywords included in the item recommendation request for each object item. Information on object items may be provided in the order of the highest sum (or average) of values multiplied by weights (or similarly weighted) to degrees.

9 is a flowchart of an item recommendation process according to another embodiment of the present invention.

The embodiment of FIG. 9 further includes two steps S623 and S626 between steps S620 and S630 in addition to the same processes as the embodiment of FIG. 6. Here, redundant description is avoided, and only steps S623 and S626 are described.

In step S623, the controller 320 determines whether each of the sub-keywords extracted in step S620 corresponds to an emotion language (emotional language). To this end, the storage unit 330 or an external server may have a dictionary of appraisal words. The appraised word dictionary is a tool for determining whether a certain word (keyword) is an appraised word, and may hold a list of appraised words, for example. A keyword included in the list of appraised words may be regarded as an appraised word, and a keyword not included in the appraised word list may be determined to be not an appraised word. However, this judgment is based on dictionary meaning, and may not reflect the popular use of words that change with the times. Therefore, the control unit 320 does not determine whether the representative attribute keyword itself is an appraised word, but determines whether to use the representative attribute keyword based on whether the subkeywords related to the representative attribute keyword are appraised words.

In another embodiment, the controller 320 may add another word registered as an appraised word in the appraised word dictionary and learned to have a high correlation (with a pre-set value or more) with a predetermined number or more of words to the appraised word dictionary.

In step S626, only a preset number of representative attribute keywords may remain in the representative attribute keyword candidate set in the order in which the emotional language ratio (or number) of the lower keyword associated by the control unit 320 is high, and the rest may be removed. Through this process, it is possible to prevent keywords far from emotional language from being treated like emotional language.

Returning to FIG. 5, in step S520, the control unit 320 stores a basic language unit-keyword association corresponding to the language unit and the representative attribute keyword pair in the storage unit 330.

Here, the language unit may include expressions that can be expressed by weights of representative attribute keywords. For example, "bored" can be a language unit, and "pretty" can be a language unit.

For the language unit "boring", the representative attribute keywords with high basic language unit-keyword association include representative attribute keywords that can solve a boring situation, such as "interesting", "interesting", "for getting time". I can.

For the language unit "pretty", the representative attribute keywords with high basic language unit-keyword association are similar to "pretty" or describe "pretty" such as "beautiful", "cute", "eye-catching", for example. Representative attribute keywords may be included.

The process of step S520 may be performed, for example, as an input of an administrator or may be performed by receiving a basic language unit-keyword association degree determined in an external system through a network or a storage medium.

According to another embodiment, the process of step S520 may be performed in a manner similar to the process of FIGS. 6 to 9 by analyzing collectible documents such as the Internet, SNS, and news.

In addition, the process of step S520 may include a process of reflecting the user's feedback, as described later.

The process of step S520 may be performed in a manner described later with reference to any one of FIGS. 15 to 17.

11 is an example of a basic language unit-keyword association diagram according to an embodiment of the present invention.

In the embodiment of FIG. 11, all of the language units are q (C ₁ to C _q ), and all of the representative attribute keywords are n (k ₁ to k _n ).

For example, the basic language unit-keyword association of the language unit C ₅ and the representative attribute keyword k ₃ is v _3,5 .

In step S530, the communication unit 310 receives and obtains a received language unit from the terminal 200, and transmits the obtained language unit to the controller 320. Here, the reception language unit is a language unit received by the terminal 200 from a user. The terminal 200 may convert a voice input into an electrical signal (voice signal) and transmit it to the item recommendation device 300. The control unit 320 of the item recommendation device 300 may analyze the voice signal, convert it into text, and match the converted text to a language unit. The controller 320 may also analyze the voice signal to analyze the intonation, pitch, speed, breathing state, etc. of the voice and use it as context information.

According to another embodiment, the terminal 200 may convert a voice input into text and transmit the converted text to the item recommendation device 300. The terminal 200 may analyze the intonation, height, speed, breathing state, etc. of the received voice input and transmit the analysis information to the item recommendation device 300. The item recommendation device 300 may utilize the analysis information as a kind of context information.

In step S540, the control unit 320 obtains a language unit-object correlation corresponding to the target language unit and each object item pair using the object-keyword association degree and the basic language unit-keyword association degree.

12 is a detailed flowchart of step S540 according to an embodiment of the present invention.

Referring to FIG. 12, in step S1210, the control unit 320 obtains a coordinated object-keyword association corresponding to each object item and a representative attribute keyword pair for a reception language unit.

According to an embodiment, the controller 320 includes a receiving language unit and a basic language unit corresponding to the representative attribute keyword pair in the object-keyword association degree corresponding to the object item and the representative attribute keyword pair for each object item and representative attribute keyword pair. -By applying the keyword association degree, the coordinated object-keyword association degree corresponding to each object item and representative attribute keyword pair for the receiving language unit may be obtained.

In particular, for each object item and representative attribute keyword pair, the control unit 320 includes an object-keyword association degree corresponding to an object item and representative attribute keyword pair, and a basic language unit-keyword association degree corresponding to the receiving language unit and the representative attribute keyword pair. The coordinated object-keyword association corresponding to each object item and a representative attribute keyword pair for the target language unit may be obtained by using the multiplied value of.

In addition, the controller 320 has a positive correlation with an object-keyword association and a positive correlation corresponding to the object item and the representative attribute keyword pair for each object item and the representative attribute keyword pair, and the basic attribute corresponding to the reception language unit and the representative attribute keyword pair. It is also possible to set the coordinated object-keyword association corresponding to each object item and representative attribute keyword pair for the receiving language unit so as to have a positive correlation with the language unit-keyword association.

In the present invention, values representing object-keyword association, basic language unit-keyword association, coordinated object-keyword association, basic language unit-sub-keyword association, and other association relationships are all values that are more closely related. Assumed. In other embodiments, when the association value is small, the association is tighter, and for other association values, when the association value is larger, the association is tight, so that the positive correlation-negative correlation is appropriate. It could be used instead.

For example, when the receiving language unit is C ₂ , the control unit 320 may obtain the coordinated object-keyword association corresponding to the object item i ₄ and the representative attribute keyword k ₃ pair, and the object item i ₄ and the representative attribute keyword k ₃ corresponding to a pair of objects - more even the primary language units corresponding to the received language unit of C ₂ and k ₃ represent attribute keywords in pairs w _4,3-keyword association be applied to adjust the object v _3,4 - obtaining the keyword associated can do.

In particular, the method of applying the degree of association may be a method of multiplying the degree of object-relatedness and basic language unit-keyword association. For example, in order to obtain the coordinated object-keyword association corresponding to the object item i ₄ and the representative attribute keyword k ₃ pair when the reception language unit is C ₂ , the control unit 320 may use the object item i ₄ and the representative attribute keyword k _The object-relationship w _4,3 corresponding to ₃ pairs is multiplied by the base language unit-keyword association v _3,2 corresponding to the destination language unit C ₂ and representative attribute keyword k3 pair (w _4,3 Хv _{3, 2} ) can be used to obtain the coordinated object-keyword association. In another embodiment, instead of multiplying, the controller 320 uses a function f(w _4,3) to which a different calculation/use method is applied so that the coordinated object-keyword association has a positive correlation with w _4,3 and v _3,2. , v _3,2 ) can also be used to obtain the coordinated object-keyword association. In addition, (w _4,3 Хv _3,2 ) is used as a coordinated object-keyword association, and correction based on other factors is applied to (w _4,3 Хv _3,2 ) and used as a coordinated object-keyword association. Both methods can be used.

를 이용하여 획득될 수 있다. f(w_4,j,v_j,2)는 객체 항목 i₄ 및 수신 언어 단위 C₂, 키워드 k_j에 대응하는 조정 객체-키워드 연관도이다.In step S1220, a language unit-object association may be obtained by using a value obtained by accumulating the coordinated object-keyword association for a specific object item by the controller 320. For example, the control unit 320 may set a receiving language unit and a language unit-object correlation corresponding to a specific object item pair so as to have a positive correlation with the accumulated value of the coordinated object-keyword association degree for a specific object item. have. The language unit-object association corresponding to the object item i ₄ and the destination language unit C ₂ pair is, for example,

It can be obtained using f(w _4,j ,v _j,2 ) is the coordinated object-keyword association corresponding to the object item i ₄ , the target language unit C ₂ , and the keyword k _j .

이 될 수 있다. 다른 예에서 객체 항목 i₄ 및 수신 언어 단위 C₂ 쌍에 대응하는 언어 단위-객체 연관도는

에 대해 기타 요인에 의한 보정을 가한 값이 될 수 있다.For example, the language unit-object association corresponding to the pair of object item i ₄ and destination language unit C ₂ is

Can be In another example, the language unit-object association corresponding to the pair of object item i ₄ and destination language unit C ₂ is

It may be a value that has been corrected by other factors.

Returning to FIG. 5, in step S550, an object item to be recommended may be provided by the control unit 320 according to a language unit-object relationship corresponding to the received language unit. For example, if the language unit-object correlation corresponding to the reception language unit C ₂ is as shown in Table 3 below, the controller 320 may provide object items to be recommended in the order of Table 4.

Object item Language unit-object association with the receiving language unit i ₁ 0.23 i ₂ 0.33 i ₃ 0.99 i ₄ 0.84

order Object item Language unit-object association with the receiving language unit One i ₁ 0.99 2 i ₂ 0.84 3 i ₃ 0.33 4 i ₄ 0.23

That is, the control unit 320 may provide object items to be recommended in the order of a language unit-object association corresponding to a reception language unit in a high order. The terminal 200 receiving the object item may provide information on the object item i ₃ to the user through the display unit 220. The terminal 200 may also provide information on other object items in a lower order as necessary. The terminal 200 may provide information on the object item i ₃ to a user through a voice through a speaker instead of the display unit 220.

13 is a flowchart of an item recommendation process according to another embodiment of the present invention.

The processes of FIGS. 13 to 17 may be performed by partially using the processes of FIGS. 5 to 12 or partially changing the processes of FIGS. 5 to 12. While describing the process of FIGS. 13 to 17, descriptions of FIGS. 5 to 12 may be used if necessary.

Referring to FIG. 13, in step S1310, a representative attribute keyword candidate set is extracted from the first set of documents by the control unit 320. The controller 320 may collect, for example, keywords frequently appearing in documents corresponding to the field of interest among the first set of documents as a representative attribute keyword candidate set. The process of step S1310 may be the same or similar to the process of step S610 of FIG. 6, for example. The process of step S1310 may be performed through the same or similar process as that of FIG. 7. The description of the process of FIG. 7 is not repeated again.

In step S1320, a language unit set is set by the controller 320. For example, a set of language units can be set by input from the administrator. According to a modified example, the control unit 320 may provide an interface for setting words/phrases suitable for each language unit as language unit candidates, and setting one or more of the language unit candidates as language units.

In step S1330, an object-keyword association diagram corresponding to an object item and a representative attribute keyword pair is stored by the control unit 320.

The process of step S1330 may be performed according to, for example, some of the embodiments of FIGS. 6 to 8, a process similar thereto, or a process corresponding thereto. According to another embodiment, the process of step S1330 may be performed as an input of an administrator or may be performed by receiving an object-keyword association degree determined in an external system through a network or a storage medium.

Since the embodiments of FIGS. 6 to 8 have been described above, repeated descriptions are omitted. However, the process performed in step S610 of FIGS. 6 and 8 is substantially the same as the process of step S1310 of FIG. 13. Therefore, in performing the process of step S1330, even if the embodiments of FIGS. 6 to 8 are used, the process of step S610 is not performed again and the result of step S1310 may be recycled.

In step S1340, the control unit 320 uses the association weight corresponding to the representative attribute keyword and the lower keyword pair, and the base language unit-subkeyword association degree corresponding to the language unit and the lower keyword pair. The corresponding basic language unit-keyword association is stored in the storage unit 330. The process of step S1340 may be performed, for example, as an input from an administrator, or may be performed according to one or more embodiments of FIGS. 15 to 17.

Prior to the process of step S1340 or during the process of step S1340, the lower keyword is determined, the association weight corresponding to the representative attribute keyword and the lower keyword pair is determined, and the basic language unit corresponding to the language unit and the lower keyword pair-sub keyword The degree of association must be determined.

The lower keyword used in the process of step S1340 may be determined while step S620 is performed during the process of step S1330. In this case, the lower keyword of step S620 may be used in step S1340. When the lower keyword is not determined in step S1330, the lower keyword may be determined through the same or similar process as in step S620 of FIG. 6 and the previous process.

The association weight used in the process of step S1340 may be determined while step S630 is performed during the process of step S1330. In this case, the association weight of step S630 may be used in step S1340. When the association weight is not determined in step S1330, the association weight may be determined through the same or similar process as in step S630 of FIG. 6 and the previous process.

The degree of association between the basic language unit and the sub-keyword may be calculated in consideration of the frequency in which the language unit and the sub-keyword appear in the same or similar context.

Hereinafter, in the description of FIGS. 15 to 17, an example of obtaining a basic language unit-keyword association v ₃ and ₂ between the language unit C ₂ and the representative attribute keyword k ₃ will be described. For example, it is assumed that the lower keywords of the representative attribute keyword k ₃ are B ₃₁ to B ₃₅₀ . For the language unit, the representative attribute keyword, and the basic language unit-keyword association, refer to the example described above with reference to FIG. 11. Language unit default language units corresponding to C _j and sub-keyword pair Bg _h-bottom keyword association degree is expressed as x _{j, h.} The association weight corresponding to the pair of the lower keyword Bg _h and the representative attribute keyword k _g is expressed as y _g,h . Language unit C _j, k _g represent attribute keywords and keyword sub Bg _h combination adjust language units corresponding to-be sub-keyword association degree is expressed as x _{j, g, h.}

15 is a detailed flowchart of step S1340 of FIG. 13 according to an embodiment of the present invention.

Referring to FIG. 15, in step S1510, the control unit 320 applies the association weight to the basic language unit-sub-keyword association degree to obtain an adjusted language unit-sub-keyword association degree.

In step S1510, for each language unit and sub-keyword pair, the control unit 320 applies a correlation weight corresponding to the sub-keyword and the representative attribute keyword pair to the basic language unit-sub-keyword correlation degree corresponding to the language unit and sub-keyword pair. Accordingly, an adjustment language unit-sub-keyword association corresponding to each language unit and sub-keyword pair for the representative attribute keyword may be obtained.

For example, when the language unit is C ₂ , the control unit 320 controls the language unit C to obtain a degree of association between the lower keyword B ₃₄ and the representative attribute keyword k ₃ corresponding to the pair of C ₂ to B _{3 4} . ₂ and sub-keyword B3 ₄ pairs of basic language units-sub-keyword relevance x _2,4 , sub-keyword B3 ₄ and representative attribute keyword k ₃ corresponding to the pair of association weight y _3,4 applied to the adjustment language unit- It is possible to obtain sub-keyword correlation x _2,3,4 .

In particular, the method of applying the association weight may be a method of multiplying the basic language unit-sub-keyword association degree x _2,4 by the association weight y _3,4 corresponding to the pair of sub-keyword B3 ₄ and representative attribute keyword k ₃ . For example, when the language unit is C ₂ , the control unit 320 adjusts the language unit-sub-keyword correlation x _2,3,4 between C ₂ -B3 ₄ corresponding to the lower keyword B3 ₄ and the representative attribute keyword k ₃ pair. In order to obtain the base language unit-sub-keyword association x _2,4 corresponding to the language unit C ₂ and the sub-keyword B3 ₄ pair, the association weight y _3,4 corresponding to the sub-keyword B3 ₄ and the representative attribute keyword k ₃ pair is assigned. Using the multiplied value of (x _2,4 Хy _3,4 ), the coordinated language unit-sub-keyword association x _2,3,4 may be obtained. In another embodiment, instead of multiplying, the control unit 320 uses another operation/use method such that the degree of association of the adjusted language unit- _subkeyword x _2,3,4 has a positive correlation with x _2,4 and y _3,4 . It is also possible to obtain the coordinated language unit-sub-keyword association x _2,3,4 using the applied function f(x _2,4 ,y _3,4 ). In addition, (x _2,4 Хy _3,4 ) is used as the adjustment language unit-sub-keyword association x _2,3,4, and (x _2,4 Хy _3,4 ) is adjusted by applying corrections based on other factors. Language unit-sub-keyword association x _{2,3,4, and} both methods can be utilized.

가 될 수 있다. 즉, 하위 키워드 B₃₁ 내지 B₃₅₀에 대해 언어 단위 C₂와의 기본 언어 단위-하위 키워드 연관도 x_2,f를 구한 뒤 각각에 대해 해당 하위 키워드에 대한 연관 가중치 y_3,f를 반영하여 x_2,3,f를 구하고 x_2,3,f를 누적하여 언어 단위 C₂ 및 대표 속성 키워드 k₃ 간의 기본 언어 단위-키워드 연관도를 구할 수 있다. 다른 실시예에 따르면, 언어 단위 C₂ 및 대표 속성 키워드 k₃ 간의 기본 언어 단위-키워드 연관도는

에 기타 요인에 의한 보정을 가한 값이 될 수 있다. 다른 실시예에 따르면, 언어 단위 C₂ 및 대표 속성 키워드 k₃ 간의 기본 언어 단위-키워드 연관도는

과 양의 상관 관계를 가지는 값이 될 수 있다. 여기서는 하나의 대표 속성 키워드에 연결돼 있는 하위 키워드가 50개인 것으로 가정하였으나, 대표 속성 키워드에 연결돼 있는 하위 키워드의 개수가 달라지면 수식에서 f의 누적 범위가 50이 아닌 다른 값이 될 수 있을 것이다.In step S1520, a basic language unit-keyword association degree between the language unit C ₂ and the representative attribute keyword k ₃ is set by using the accumulative value of the adjusted language unit-sub-keyword association x _2,3,f by the controller 320. I can. That is, the basic language unit-keyword association between the language unit C ₂ and the representative attribute keyword k ₃ is

Can be. That is, for the sub-keywords B ₃₁ to B ₃₅₀ , the basic language unit-sub-keyword association x _2,f with the language unit C ₂ is calculated, and for each, x ₂ by reflecting the association weight y _3,f for the sub-keyword. By obtaining _,3,f and accumulating x _2,3,f , the basic language unit-keyword association between the language unit C ₂ and the representative attribute keyword k ₃ can be obtained. According to another embodiment, the basic language unit-keyword association between the language unit C ₂ and the representative attribute keyword k ₃ is

It may be a value that has been corrected by other factors. According to another embodiment, the basic language unit-keyword association between the language unit C ₂ and the representative attribute keyword k ₃ is

It can be a value that has a positive correlation with. Here, it is assumed that there are 50 subkeywords connected to one representative attribute keyword, but if the number of subkeywords connected to the representative attribute keyword is different, the cumulative range of f in the formula may be a value other than 50.

16 is a detailed flowchart of step S1340 of FIG. 13 according to another embodiment of the present invention.

The processes of steps S1510 and S1520 of FIG. 16 are the same as those described above with reference to FIG. 15, and thus are not repeated.

Referring to FIG. 16, in step S1530, among the representative keywords corresponding to a specific language unit, among the representative keywords corresponding to a specific language unit, the basic language unit-keyword association degree of the representative keyword pair corresponding to the language unit is less than or equal to the reference basic language unit-keyword association. The basic language unit-keyword association degree for the representative keyword may be deleted. Representative keywords corresponding to a specific language unit refer to keywords for which a basic language unit-keyword association degree is set in relation to a specific language unit. The reference basic language unit-keyword association may be preset. According to another embodiment, the reference basic language unit-keyword association degree is set using the average value of the basic language unit-keyword association corresponding to a specific language unit, or the basic language unit-keyword association corresponding to a specific language unit is ordered in magnitude. When arranged in a row, it can be set using the basic language unit-keyword association of a specific ranking. A specific value having a positive correlation with the basic language unit-keyword associations corresponding to other specific language units may be the reference basic language unit-keyword association. The reference basic language unit-keyword association degree may be set differently depending on the language unit, or may be set identically for all language units. When the basic language unit-keyword association is deleted, there is no association between the language unit and the representative keyword. The control unit may set the degree of association to 0, or the basic language unit-keyword association degree of the representative keyword pair corresponding to the language unit in a list (which can be replaced by an array or other data structure) representing the basic language unit-keyword association degree. The basic language unit-keyword association can also be deleted by deleting information about Other basic language unit-keyword associations have been deleted (or associations have been deleted).

After the process of step S1530, the basic language unit-keyword association, which has a relatively fine degree of association, is deleted (i.e., it is set as no association), so that an excessively complex operation is performed or an association that has no practical meaning to the user/administrator. Can be suppressed.

17 is a detailed flowchart of step S1340 of FIG. 13 according to another embodiment of the present invention.

Since the processes of steps S1510 and S1520 of FIG. 17 are the same as those described above with reference to FIG. 15, the description will not be repeated. The process of step S1530 of FIG. 17 is the same as the process described above with reference to FIG. 16, so the description will not be repeated.

In step S1540, a basic language unit-keyword association that has not been deleted by the controller 320 may be normalized. For example, in order to include the average value of the basic language unit-keyword associations stored connected to a specific representative attribute keyword in a specific range, the basic language unit-keyword associations stored connected to a specific representative attribute keyword are multiplied by a certain coefficient to increase. Can be reduced or reduced. For another example, in order to include the total of the basic language unit-keyword associations stored connected to a specific representative attribute keyword in a specific range, a constant coefficient is applied to the basic language unit-keyword associations stored connected to a specific representative attribute keyword. It can be increased or decreased by multiplying. In other words, a high value basic language unit-keyword association is concentrated on a certain representative attribute keyword, so even if a certain language unit is selected, only that specific representative attribute keyword is recommended/used or a specific representative attribute keyword is rarely used. Adequate adjustments can be made to do so.

According to another embodiment, instead of multiplying the basic language unit-keyword association by a predetermined coefficient by the control unit 320 in step S1540, normalization may be performed by adding a predetermined coefficient or combining operations such as logarithm and square. According to another embodiment, normalization may be performed by partially reducing only the basic language unit-keyword associations equal to or higher than a specific reference value or partially increasing the basic language unit-keyword associations equal to or lower than a specific reference value.

According to another embodiment, in step S1540, normalization may be performed so that the average value (or sum) of the basic language unit-keyword associations stored by being connected to a specific language unit by the controller 320 is included in a specific range.

In the process of FIG. 17, step S1530 is omitted, and a modified example in which the basic language unit-keyword association normalization process is performed is also possible.

In step S1350, a reception language unit is received from the terminal 200 by the communication unit 310, and the obtained reception language unit is transmitted to the controller 320.

The reception language unit is a language unit received by the terminal 200 from a user. The terminal 200 may convert a voice input into an electrical signal (voice signal) and transmit it to the item recommendation device 300. The control unit 320 of the item recommendation device 300 may analyze the voice signal, convert it into text, and match the converted text to a language unit. The controller 320 may also analyze the voice signal to analyze the intonation, pitch, speed, breathing state, etc. of the voice and use it as context information.

According to another embodiment, the terminal 200 may convert a voice input into text and transmit the converted text to the item recommendation device 300. The terminal 200 may analyze the intonation, height, speed, breathing state, etc. of the received voice input and transmit the analysis information to the item recommendation device 300. The item recommendation device 300 may utilize the analysis information as a kind of context information.

In step S1360, the control unit 320 obtains a language unit-object association corresponding to the target language unit and each object item pair using the object-keyword association degree and the basic language unit-keyword association degree. The process of step S1360 may be performed according to the method of step S540 of FIG. 5 or the method of FIG. 12. Description of the same content will be omitted.

In step S1370, the control unit 320 may provide an object item to be recommended according to a language unit-object relationship corresponding to the received language unit. The process of step S1370 may be performed in the same manner as the process of step S550. The same description is omitted.

14 is a flowchart of an item recommendation process according to another embodiment of the present invention.

Steps S1310, S1320, S1330, S1340, S1350, S1360, and S1370 of FIG. 14 are the same as steps S1310, S1320, S1330, S1340, S1350, S1360, and S1370 of FIG. 13, so the same description will not be repeated.

Step S1333 added in FIG. 14 may be performed at any time after the representative attribute keyword and the lower keyword are determined. For example, step S1333 may be performed simultaneously/in parallel with step S1330, or the process of step S1333 may be performed during step S1330.

In step S1333, an association weight between the representative attribute keyword and the lower keyword is stored by the controller 320. If the process of setting the association weight is not performed in step S1330, the association weight between the representative attribute keyword and the sub-keyword may be set through a process similar to that of step S630 of FIG. 6. According to another embodiment, the association weight between the representative attribute keyword and the lower keyword may be stored in a manner in which the association weight set in step S1330 is called by the controller 320.

In step S1337, the control unit 320 obtains a basic language unit-lower keyword association between the lower keyword and the language unit.

The controller 320 may determine, for example, a degree of association between the language unit and the lower keyword in consideration of the frequency at which the lower keyword appears in the same or similar context as the language unit.

For example, it can be seen that words appearing around keyword A in a specific sentence may appear around words related to keyword A in other documents.

"I went on a trip with a big heart, but because it was July, the weather was too hot and I suffered."

"I went on a trip with a big heart, but because it was July, the weather was too humid, so I suffered."

Looking at the above two sentences, the word "because it's hot" has been replaced by the word "because it's wet" in the same context. The controller 320 may infer that “hot” and “wet” are words related to each other.

"I went on a trip with a big heart, but because it was July, the weather was too hot and I suffered."

"I went on vacation with a big heart, but because it was July, it was too hot and I suffered."

Similarly, the control unit 320 may infer that “travel” and “vacation” are related words through the above two sentences.

"I went on a trip with a big heart, but because it was July, the weather was too hot and I suffered."

"I went on a trip with a big heart, but because it was August, the weather was too hot and I suffered."

Similarly, the controller 320 may infer that “July” and “August” are related words through the above two sentences.

The control unit 320 indicates that "hot" and "wet" are related words, "July" and "August" are related words, and "travel" and "vacation" are related words through the previously collected documents. It can be saved. Assume that the following sentences are collected.

"I went on vacation with a big heart, but because it was July, the weather was too humid, so I suffered."

"I went on a trip with a big heart, but it was hard because the weather was too hot because it was August."

If the two sentences are not the same context, but know that hot" and "wet" are related words, "July" and "August" are related words, and "travel" and "vacation" are related words, the controller 320 ) Through the above sentence, you can learn that "I suffered" and "I had a hard time" are also related words.

Keyword pairs with a high frequency appearing in the same/similar context may be determined to have a high correlation with each other. In addition, the higher the similarity between the context in which the two keywords appear, the higher the correlation between the two keywords can be determined. The control unit 320 performs learning using the collected documents to set the degree of association between keywords, and sets the degree of relevance of keywords appearing in the sentence by using the relationship between the set keywords and the context of the sentence. The accuracy of judging the relationship between liver can also be improved.

In a similar learning method, NNLM (Neural Net Language Model),

RNNLM (Recurrent Neural Net Language Model), word2vec, skipgram, and

CBOW (Continuous Bag-of-Words) method is known. In particular, when word2vec is used, word2vec learns using documents and associates each keyword with a vector, and the similarity between the two keywords can be determined by calculating the cosine similarity of the two vectors.

18 is a diagram showing a term hierarchy according to an embodiment of the present invention.

When the process of FIG. 13 or 14 is completed, language units C ₁ to C _q and representative attribute keywords

A hierarchical relationship between the s (k ₁ to k _n ) and the lower keywords (BX ₁ to BX _n ) is established.

A basic language unit-keyword association degree is set between the language unit and the representative attribute keyword, and an association weight is set between the representative attribute keyword and the lower keyword. Using this hierarchical relationship, the controller 320 may perform an operation such as recommending an appropriate object according to the language unit or selecting a new language unit candidate. In addition, the hierarchical relationship of FIG. 20 may be modified or supplemented through learning while repeating the process of FIGS. 13 and 14 by reflecting new data.

19 is an exemplary view showing main language units for each language unit list based on a language unit associated with a selected item according to an embodiment of the present invention.

Referring to FIG. 19, the main language units for each language unit list are analyzed with word2vec based on the language unit associated with the selected item, and the analyzed result is mapped in two dimensions using a dimension reduction method. For each language unit list (for example, user response/atmosphere/genre characteristics) on the basis of language units, the average correlation with the selected items is arranged and displayed in the order of the highest.

As shown in FIG. 19, for example, in the'user response' language unit list, the average association with the items selected for "want to eat" is the highest, followed by "getting hungry", followed by "reporting" It is the order of "I want to."

In addition, in the'mood' language unit list, "cute" has the highest average correlation with the selected items, followed by "remembering", followed by "normal".

In addition, in the'genre characteristic' language unit list, "complex" has the highest average association with the selected items, followed by "fire", followed by "clean".

20 is an exemplary diagram illustrating main language units for each language unit list based on a language unit associated with a selected item according to another embodiment of the present invention.

Referring to FIG. 20, the main language units for each language unit list are analyzed with word2vec based on the language unit associated with the selected item, and the analyzed result is mapped in two dimensions using a dimension reduction method. For each language unit list (for example, performer/atmosphere/user reaction/genre characteristics) on the basis of language units, the average correlation with the selected items is arranged-displayed in the order of the highest.

As shown in FIG. 20, for example, in the list of'performers' language units, the average correlation with the items selected with "cute" is the highest, followed by "cute", and then "clearly" It is the order of "smile".

In addition, in the'atmosphere' language unit list, "memory" has the highest average correlation with the selected items, followed by "cute", followed by "exciting".

In addition, in the'user response' language unit list, the average correlation with the items selected for "want to see" is the highest, followed by "thank you", followed by "crazy".

In addition, in the'genre characteristic' language unit list, the average association with the items selected for "suffering" is highest, followed by "complex", followed by "quality".

21 and 22 are exemplary diagrams showing an average correlation criterion of major language units for each list according to an embodiment of the present invention.

21 and 22, charts are prepared based on an average degree of association corresponding to a list of each language unit. That is, the average degree of association of the major language units for each list is analyzed with word2vec, and the analyzed result is mapped in two dimensions using the dimension reduction method. Here, a circle with a darker color or a larger color is a keyword having a higher relevance to the selected item, and keywords having similar positions are keywords having a high similarity (the positions of vectors are similar).

In FIGS. 21 and 22, the upper charts are web charts showing the degree of relevance of language units with high relevance, but are not limited thereto and need not necessarily be web charts. Also, the charts below are scatter charts, a kind of one chart.

FIG. 23 is an exemplary diagram showing an average degree of association of major language units for each list according to another embodiment of the present invention.

Referring to FIG. 23, charts are prepared based on an average degree of association corresponding to a list of language units. That is, the average degree of association of the major language units for each list is analyzed with word2vec, and the analyzed result is mapped in two dimensions using the dimension reduction method. Here, a circle with a darker color or a larger color is a keyword having a higher relevance to the selected item, and keywords having similar positions are keywords having a high similarity (the positions of vectors are similar).

In FIG. 23, the upper chart is a web chart showing the degree of relevance of language units with a high degree of relevance as a graph, but is not limited thereto and does not necessarily need to be a web chart. Also, the chart below is a scatter chart, which is a kind of one chart.

24 and 25 are exemplary diagrams showing keywords and keyword lists in main language units for each list according to an embodiment of the present invention.

24 and 25, the chart is a scatter chart, which is a kind of one chart, and zoom-in and zoom-out are possible. Regardless of the zoom-in state/zoom-out state, when the mouse is turned on (otherwise, a corresponding method) on each circle, the keyword + A list of keywords is displayed. FIG. 25 is an enlarged exemplary view in the vicinity of "normal" in FIG. 24; Here, a circle with a darker color or a larger color is a keyword having a higher relevance to the selected item, and keywords having similar positions are keywords having a high similarity (the positions of vectors are similar).

26 is an exemplary view showing keywords and keyword lists in main language units for each list according to another embodiment of the present invention.

In FIG. 26, the chart is a scatter chart that is a kind of one chart, and zoom-in and zoom-out are possible. Regardless of the zoom-in/zoom-out state, when the mouse is turned on (otherwise, a corresponding method) on each circle, a corresponding keyword + keyword list Is displayed. Here, a circle with a darker color or a larger color is a keyword having a higher relevance to the selected item, and keywords having similar positions are keywords having a high similarity (the positions of vectors are similar).

Here, when the above-described web chart or one chart is clicked, as shown in FIGS. 27 and 28 to be described later, a language unit adjustment interface corresponding to the clicked list is displayed.

FIG. 27 is an example of displaying a language unit adjustment interface corresponding to a clicked list according to an embodiment of the present invention, and FIG. 28 is a diagram illustrating an entire language unit adjustment interface corresponding to a clicked list according to an embodiment of the present invention. It is an exemplary diagram shown.

27 and 28, in the initial language unit selection, n language units having a high average correlation with the corresponding items are selected based on the selected items based on a predetermined threshold value. Here, the threshold value may be the maximum number or the minimum degree of association.

In addition, as illustrated, the language units that have already been selected are dark purple, and as the degree of association decreases, the background color becomes blurred, and are arranged in the order of the higher degree of association. In addition to the hue and shading method, it is also possible to display a lower degree of relevance by using another method, for example, brightness/saturation/color/shape.

Also, by clicking "Select language unit" in FIG. 28, individual addition/deletion of the entire language unit is possible.

FIG. 29 is an exemplary view showing a language unit adjustment interface corresponding to a clicked list according to another embodiment of the present invention, and FIG. 30 is an entire language unit adjustment interface corresponding to a clicked list according to another embodiment of the present invention. Is an exemplary diagram showing.

In FIGS. 29 and 30, in the initial language unit selection, n language units having a high average correlation with the corresponding items are selected based on the selected items based on a predetermined threshold value. Here, the threshold value may be the maximum number or the minimum degree of association.

In addition, as illustrated, the language units that have already been selected are dark purple, and as the degree of association decreases, the background color becomes blurred, and the units are arranged in the order of higher association. In addition to the hue and shading method, it is also possible to display a lower degree of relevance by using another method, for example, brightness/saturation/color/shape.

In addition, by clicking "Select language unit" in FIG. 30, it is possible to add/delete all language units.

The recommended items recommended by the item recommendation system using the degree of association between the language unit and the items used according to the present invention are as illustrated in FIG. 31.

In the method and apparatus for recommending items using a degree of association between a language unit and an item to be used according to the present invention as described above, it can be understood that combinations of each block of the flowchart diagrams and the flowchart diagrams can be performed by computer program instructions. There will be. Since these computer program instructions can be mounted on the processor of a general purpose computer, special purpose computer or other programmable data processing equipment, the instructions executed by the processor of the computer or other programmable data processing equipment are described in the flowchart block(s). It creates a means to perform functions. These computer program instructions can also be stored in computer-usable or computer-readable memory that can be directed to a computer or other programmable data processing equipment to implement a function in a particular way, so that the computer-usable or computer-readable memory It is also possible to produce an article of manufacture containing instruction means for performing the functions described in the flowchart block(s). Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so that a series of operating steps are performed on a computer or other programmable data processing equipment to create a computer-executable process to create a computer or other programmable data processing equipment. It is also possible for instructions to perform processing equipment to provide steps for executing the functions described in the flowchart block(s).

In addition, each block may represent a module, segment, or part of code that contains one or more executable instructions for executing the specified logical function(s). In addition, it should be noted that in some alternative execution examples, functions mentioned in blocks may occur out of order. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order depending on the corresponding function.

In this case, the term'~ unit' used in the present embodiment refers to software or hardware components such as FPGA or ASIC, and'~ unit' performs certain roles. However,'~ part' is not limited to software or hardware. The'~ unit' may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors. Thus, as an example,'~ unit' refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, and procedures. , Subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, database, data structures, tables, arrays, and variables. The components and functions provided in the'~ units' may be combined into a smaller number of elements and'~ units', or may be further divided into additional elements and'~ units'. In addition, components and'~ units' may be implemented to play one or more CPUs in a device or a security multimedia card.

As described above, the item recommendation method and apparatus using the degree of association between the language unit and the item to be used according to the present invention is based on the degree of association between words and words based on the user's preference or experience and/or purchase history. Similar items with high purchase potential can be recommended using a vector model-based reasoning method. In addition, some of the recommended items to be provided to users of a specific pattern can be adjusted. In addition, recommended items may be provided to users according to the ranking of recommendations. In addition, some of the recommended items to be provided to users of a specific pattern can be adjusted. You can also vectorize keywords by processing them with word2vec or other similar vectorization techniques. In addition, when a web chart or a one chart is clicked, it may be possible to add and delete a language unit to display the language unit adjustment interface corresponding to the clicked list.

As described above, the present invention has been described based on preferred embodiments, but these embodiments are intended to illustrate, not limit, the present invention, so those skilled in the art to which the present invention pertains without departing from the spirit of the present invention. Various changes, changes or adjustments to the example will be possible. Therefore, the scope of protection of the present invention should be construed as including all examples of changes, examples of changes or adjustments belonging to the gist of the present invention.

150: communication network 200: terminal
210: input unit 220: display unit
230, 310: communication unit 240, 330: storage unit
250, 320: control unit 300: item recommendation device

Claims (8)

An item recommendation method using a degree of association between a language unit performed by an item recommendation device and a used item,
Setting a degree of association between a language unit and a used item by a control unit of the item recommendation device;
Obtaining an experience item list including user experience items by a control unit of the item recommendation device;
Acquiring a language unit-relevance pair in a language unit based on a threshold value in association with each experience item in the experience item list by a control unit of the item recommendation device;
Obtaining, by a control unit of the item recommendation device, a language unit-user association between a user and each language unit based on a language unit-relevance pair between all language units corresponding to the experience item list; And
An item recommendation method using a degree of association between a language unit and a usage history, comprising the step of generating a user recommendation item list based on a language unit-user association degree by a control unit of the item recommendation device.
The method of claim 1,
The step of obtaining a language unit-user association degree between the user and each language unit based on the entire language unit-relevance pair corresponding to the experience item list by the control unit of the item recommendation device,
A cumulative value of a degree of association corresponding to a specific language unit for all language unit-relevance pairs corresponding to the experience item list by the control unit of the item recommendation device and a language unit-user association between the user and the specific language unit An item recommendation method using a degree of association between a language unit and a usage history, comprising the step of setting a language unit-user association so that the degree has a positive correlation.
The method of claim 1,
The step of obtaining a language unit-user association degree between the user and each language unit based on the entire language unit-relevance pair corresponding to the experience item list by the control unit of the item recommendation device,
Language unit-user association between the user and the specific language unit by the control unit of the item recommendation device to determine the cumulative value of the association degree corresponding to a specific language unit for all language unit-relevance pairs corresponding to the experience item list Item recommendation method using a degree of association between language units and usage details including the step of setting a road.
The method of claim 1,
In relation to each experience item in the experience item list by the control unit of the item recommendation device, obtaining a language unit-relevance pair based on a threshold value,
Association between language units and usage details, including the step of acquiring a maximum number of language unit-relevance pairs in the order of high relevance by being associated with each experience item in the experience item list by the control unit of the item recommendation device How to recommend items using degrees.
The method of claim 1,
In relation to each experience item in the experience item list by the control unit of the item recommendation device, obtaining a language unit-relevance pair based on a threshold value,
Item recommendation method using a degree of association between a language unit and a usage history, comprising the step of acquiring a language unit-relevance pair that is equal to or greater than a minimum degree of association by being associated with each experience item in the experience item list by the control unit of the item recommendation device .
The method of claim 1,
Generating a user recommendation item list based on a language unit-user association degree by the control unit of the item recommendation device,
Individual values having a positive correlation to the language unit-user association for a specific language unit and the language unit-item association for the specific language unit have a positive correlation with the accumulated value for all language units Establishing an item-user association; And
An item recommendation method using a degree of association between a language unit and a usage history, including the step of generating a user recommendation item list according to the item-user association degree.
The method of claim 6,
Individual values having a positive correlation to the language unit-user association for a specific language unit and the language unit-item association for the specific language unit have a positive correlation with the accumulated value for all language units The step of setting the item-user association is:
Item-user correlation to have a positive correlation with the accumulated value for the entire language unit by multiplying the language unit-user association for a specific language unit and the language unit-item association for the specific language unit Item recommendation method using a degree of association between a language unit and a usage history comprising the step of setting a.
The method of claim 6,
Individual values having a positive correlation to the language unit-user association for a specific language unit and the language unit-item association for the specific language unit have a positive correlation with the accumulated value for all language units The step of setting the item-user association is:
Setting an item-user association degree as a value obtained by multiplying a language unit-user association degree for a specific language unit and a language unit-item association degree for the specific language unit as a value accumulated for all language units Item recommendation method using the degree of association between language units and usage history.

Images