Method, apparatus and recording medium storing commands for providing item information and visual information corresponding to scenario

Abstract

This invention provides an apparatus for recommending items corresponding to a script and providing visual information about the script. One embodiment of the invention involves a method implemented in an apparatus comprising one or more processors and one or more memories storing commands to be executed by the processors. The method may include the following steps: the processors receive user input for a virtual script; determine one or more items corresponding to the script; generate first visual information indicating the usage of the one or more items in the script; and transmit the first visual information to the user's terminal.

Description

[Technical Field]

[0001] This invention relates to a technology for providing item information and visual information corresponding to a script. [Previous Technology]

[0002] E-commerce services provide customers with a variety of items, and in the process, strive to recommend customized items to customers. E-commerce services may recommend individual items to customers, and may recommend appropriate items to customers based on their individual requests. [Summary of the Invention]

[0003] [Problem to be Solved by the Invention] At least one embodiment of the present invention provides a technique for recommending various items needed for different situations to a user at one time.

[0004] At least one embodiment of the present invention provides a technique that enables users to more effectively and efficiently convey their requirements for item recommendations to e-commerce service providers.

[0005] At least one embodiment of the present invention can provide a technique for identifying the situation in which a user wants to purchase items and recommending a combination of items suitable for that situation.

[0006] At least one embodiment of the present invention can provide a technique that helps a user predict the combined effect of a plurality of recommended items provided to the user.

[0007] At least one embodiment of the present invention can provide a technique for recommending item combinations to a user and providing visual information of the recommended item combinations, thereby enabling the user to effectively predict the overall effect of the item combinations.

[0008] The technical subject matter of this invention is not limited to the technical subject matter mentioned above. Those skilled in the art will clearly understand other technical subject matter not mentioned based on the following description. [Technical Means for Solving the Problem]

[0009] The present invention provides an apparatus for recommending items corresponding to a script and providing visual information about the script. One embodiment of the present invention is implemented in an apparatus comprising one or more processors and one or more memories storing commands to be executed by the one or more processors. The method may include the following steps: the one or more processors receive user input for a virtual script; determine one or more items corresponding to the script; generate first visual information indicating the usage of the one or more items in the script; and transmit the first visual information to the user's user terminal.

[0010] In one embodiment, the step of receiving the input of the script may include the following steps: receiving a first input of the script from the user terminal; analyzing the first input; generating query information corresponding to the first input based on the analysis of the first input; transmitting the query information to the user terminal; and receiving a second input of the script from the user terminal, the second input being the one corresponding to the query information; and the step of determining one or more items corresponding to the script may include the following steps: determining one or more items corresponding to the script based on the first input and the second input.

[0011] In one embodiment, the step of generating the above-mentioned query information may include the following steps: confirming the total number of inputs of the above-mentioned script received from the above-mentioned user terminal; and generating the above-mentioned query information as soon as the total number of inputs is determined to be below a preset number.

[0012] In one embodiment, the step of analyzing the first input may include the following steps: extracting one or more keywords included in the first input; calculating a score corresponding to the first input based on the one or more keywords; and calculating a score corresponding to the first input based on the score corresponding to the first input; and the step of generating query information corresponding to the first input may include the following steps: determining whether to generate the query information based on the score corresponding to the first input and a preset threshold score.

[0013] In one embodiment, the step of analyzing the first input may include the following steps: confirming one or more script attributes corresponding to each of the one or more keywords included in the first input; calculating the score of each of the one or more evaluation items based on the one or more script attributes corresponding to each of the one or more keywords; and calculating the score corresponding to the first input based on the score of each of the one or more evaluation items.

[0014] In one embodiment, the step of calculating the score corresponding to the first input based on the scores of the above-mentioned one or more evaluation items may include the following steps: assigning a preset weighting value according to the above-mentioned evaluation items to the scores of the above-mentioned evaluation items based on the preset weighting value information of the above-mentioned one or more evaluation items, thereby calculating the score corresponding to the first input.

[0015] In one embodiment, the input of the above script may include voice input.

[0016] In one embodiment, the input of the above script may include image input.

[0017] In one embodiment, the above method may further include the following steps: receiving condition information related to the purchase of items from the user terminal; and the step of determining one or more items corresponding to the script may include the following steps: determining one or more items corresponding to the script based on the input of the script and the condition information.

[0018] In one embodiment, the above-mentioned condition information may include the user's budget for purchasing items.

[0019] In one embodiment, the step of determining the above-mentioned one or more items may include determining the above-mentioned one or more items by the amount by which the total price corresponding to the above-mentioned one or more items exceeds the range of the user's pre-specified budget, wherein the above-mentioned one or more items are those corresponding to the above-mentioned script.

[0020] In one embodiment, when the total price corresponding to the determined one or more items exceeds the user's budget, the step of generating the first visual information may include generating the first visual information in the following manner: the first visual information further includes guidance information and advertising information, the guidance information indicating that the total price corresponding to the one or more items exceeds the user's budget, and the advertising information indicating the advertising content of at least one of the one or more items.

[0021] In one embodiment, the step of determining one or more items corresponding to the above script may include the following steps: determining one or more items corresponding to the above script based on the result of inputting the information of the above script into the item determination model and outputting from the item determination model; the item determination model may be a model learned in the following manner: determining one or more items corresponding to the script based on item information, user information and script input.

[0022] In one embodiment, the step of generating the first visual information may include the following steps: generating a first image corresponding to the script; obtaining one or more second images corresponding to the determined one or more items; and generating the first visual information based on the first image and the one or more second images.

[0023] In one embodiment, the step of generating the first visual information based on the first image and the second image may include the following steps: identifying one or more regions in the first image that correspond to each of the one or more items; and placing the one or more second images in each of the one or more regions.

[0024] In one embodiment, the above method may further include the following steps: receiving feedback input from the user terminal corresponding to the first visual information; and generating second visual information obtained from the change of the first visual information based on the feedback input.

[0025] In one embodiment, the above method may further include the following steps: receiving feedback input from the user terminal corresponding to the first visual information; changing at least one of the determined items based on the feedback input; and generating second visual information obtained from the change of the first visual information as the at least one item changes.

[0026] An apparatus according to one embodiment of the present invention includes: a communication circuit; one or more processors; and one or more memory, which store commands executed by the one or more processors; and the apparatus can be configured such that, when executing the one or more commands, the one or more processors perform the following: receive input from a user terminal for a virtual script via the communication circuit; determine one or more items corresponding to the script; generate first visual information, which indicates the usage of the one or more items in the script; and transmit the first visual information to the user terminal via the communication circuit.

[0027] The non-transitory computer-readable recording medium of the present invention records commands that can be executed by one or more processors. These commands can be configured such that, when executing the commands, the one or more processors perform the following: receive user input for a virtual script from a user terminal via a communication circuit; determine one or more items corresponding to the script; generate first visual information indicating the usage of the one or more items in the script; and transmit the first visual information to the user's user terminal via the communication circuit. [Effects of the Invention]

[0028] According to at least one embodiment of the present invention, a combination of various items for each condition a can be recommended to the user at one time.

[0029] According to at least one embodiment of the present invention, during the process of a user inputting requirements for item recommendations, even with minimal user input, the user's desired items can be recommended, and the user's input convenience can be improved.

[0030] According to at least one embodiment of the present invention, items that a user needs but is unaware of can be recommended to the user, thereby improving the user experience of e-commerce services.

[0031] According to at least one embodiment of the present invention, users obtain recommendations for comprehensive combinations of items for various situations, thereby improving the user experience of e-commerce services and expecting to increase sales for e-commerce service providers.

[0032] According to at least one embodiment of the present invention, users can obtain comprehensive recommendations for combinations of items, and can more easily identify the overall effect of such combinations of items.

Implementation Method

[0034] The various embodiments described herein are illustrative of the technical concept of the present invention and are not intended to limit them to specific implementation methods. The technical concept of the present invention includes various modifications, equivalents, alternatives, and embodiments obtained by selectively combining all or part of the embodiments described herein. Furthermore, the scope of the technical concept of the present invention is not limited to the various embodiments presented below or their specific descriptions.

[0035] Unless otherwise defined, the terms used herein, including technical or scientific terms, shall have the meaning commonly understood by one of common sense in the technical field to which this invention pertains.

[0036] The expressions used herein, such as "including," "may include," "possibly possess," "may possess," "have," and "may have," imply the presence of object features (e.g., functions, actions, or constituent elements), and do not exclude the presence of other additional features. That is, the expressions described above should be understood as open-ended terms that have the possibility of including other embodiments.

[0037] Unless otherwise stated in the context, the singular expressions used herein may also have the meaning of the plural expressions, and this also applies to the singular expressions described in the technical solutions.

[0038] Unless otherwise stated in the context, the terms “first,” “second,” “first,” “second,” etc., used herein are used to distinguish one object from others when referring to multiple objects of the same kind, and are not intended to limit the order or importance of such objects.

[0039] As used herein, “A, B, and C,” “A, B, or C,” “A, B, and / or C,” or “at least one of A, B, and C,” “at least one of A, B, or C,” “at least one of A, B, and / or C,” “at least one of A, B, and C,” “at least one of A, B, or C,” “at least one of A, B, and / or C,” etc., may refer to each of the listed items or all possible combinations of the listed items. For example, “at least one of A and B” may refer to (1) A, (2) at least one of A, (3) B, (4) at least one of B, (5) at least one of A and at least one of B, (6) at least one of A and B, (7) at least one of B and A, (8) A and B.

[0040] The expression “based on or according to” as used herein is used to describe one or more factors that affect the determination or judgment of an action or behavior described in the statement or article that includes the expression, and the expression does not exclude additional factors that affect the determination or judgment of the action or behavior.

[0041] The expression used herein to describe a constituent element (e.g., the first constituent element) as “connected” or “linked” to another constituent element (e.g., the second constituent element) may refer not only to the first constituent element being directly connected to or linked to the other constituent element, but also to the first constituent element being connected to or linked to the other constituent element through a medium of another new constituent element (e.g., the third constituent element).

[0042] Depending on the context, the expression "configured to" as used herein may mean "configured in a specific manner," "possessing the capability to perform specific actions," "modified in a specific manner," "made in a specific manner," or "capable of performing specific actions." This expression is not limited to the meaning of "specially designed in hardware." For example, a processor configured to perform a specific action may refer to a special purpose computer constructed through programming to perform that specific action.

[0043] Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings. In the drawings and descriptions, the same or substantially equivalent constituent elements are given the same reference numerals. Furthermore, in the following descriptions of various embodiments, repeated descriptions of the same or corresponding constituent elements may be omitted, but this does not mean that the constituent element is not included in the corresponding embodiment.

[0044] Figure 1 is a diagram illustrating the operation of a device 100 according to one embodiment of the present invention. The device 100 of one embodiment of the present invention can provide visual information 190 to a user 112. For this purpose, the device 100 can send and receive various information with the user terminal 110 of the user 112. In the present invention, the device 100 can be a device of a service provider offering e-commerce services. For example, the device 100 can be a device used by the service provider (e.g., a server). In the present invention, the service provider can be one or more entities providing corresponding e-commerce services. In the present invention, the user 112 can be a user utilizing e-commerce services. The user 112 is not limited to a natural person and can be a collection of natural persons, a company, or various other forms. In the present invention, the user terminal 110 can be the device of the user 112 (e.g., a smartphone).

[0045] User 112 can connect to the e-commerce service of the service provider through user terminal 110. In order to obtain recommendations for more than one item needed by user 112 in various situations, user input 120 can be entered into user terminal 110.

[0046] In this invention, the concept of an article is as follows: it refers to all things that can be the object of a transaction, and includes services in addition to products.

[0047] In this invention, user input 120 may include at least a portion of script input 130 and condition information 140.

[0048] The script input 130 may include input of a virtual script assumed by the user 112. In this invention, the virtual script assumed by the user 112 may refer to a specific situation that the user 112 has experienced, expects to experience, or desires. The virtual script may be a concept centered on when, how, and in what environment the user 112 uses an item, and may generally include problems or needs that the user 112 may encounter, and the experiences that are expected or anticipated. For example, the user 112 may be about to go camping or wish to experience camping. In this case, the camping experience assumed by the user 112 can be understood as a virtual script. The user terminal 110 may transmit the script input 130 to the device 100 based on the user input 120.

[0049] In this invention, user input 120 may refer to the display of user 112's intention to request recommended items in any form, such as the specific environment or situation in which user 112 uses one or more items provided in e-commerce services. The user input includes the script input 130 provided by user 112 to obtain item recommendations.

[0050] User terminal 110 can transmit script input 130 to device 100 based on user input 120. In one embodiment, user input 120 may include voice input from user 112. User 112 may input voice input of the script to user terminal 110. In one embodiment, script input 130 may be the voice input of user 112 received by user terminal 110 itself, or it may be text information generated by user terminal 110 analyzing user 112's voice input. For example, user terminal 110 may recognize user 112's voice input and convert user input 120 into text information. In one embodiment, script input 130 may include information obtained by user terminal 110 through natural language processing of user 112's voice input. For example, script input 130 may include information of one or more keywords, which are extracted by user terminal 110 based on user 112's voice input through morpheme analysis, sentence structure analysis, semantic analysis, etc. In this case, one or more keywords may include keywords for each script attribute. For example, one or more keywords included in a script may refer to a keyword corresponding to any of the following attributes: one or more script attributes related to an occasion, and one or more script attributes related to an item. Script attributes related to a situation may include, for example, the following: time, including the year, season, date, period, and time of occurrence of the situation corresponding to the script; location, including the position of the situation corresponding to the script; entity, which is the person or individual who takes, participates in, or leads the action in the situation corresponding to the script; object, which is the object or thing that the entity interacts with in the situation corresponding to the script; action, which is related to the action or event performed by the entity in the situation corresponding to the script; context (e.g., weather, a friend's birthday, a business meeting, an informal occasion), including the external environment or background, social background, and cultural background that constitute a specific situation; purpose, which is the intention or reason for the entity to perform the action; emotion, including the emotion or emotional state experienced or desired by the entity or object; result, including the result or impact of a specific action or event; the identity the entity will have in the corresponding script (e.g., a wedding guest); and the sensations the entity may feel (e.g., cold or hot). Furthermore, one or more script attributes related to an item may include the following script attributes: item type, brand, price, specific technical specifications or attributes, purpose, design, quality, reviews, inventory, distribution, and additional services. In this case, the script attribute related to distribution may be the following script attribute: corresponding to a script that should receive delivery and use the recommended item more quickly, used when identifying items that can be delivered more quickly.Furthermore, the additional service script attributes may be related to the user 112's requirements regarding the warranty period or after-sales service of the item. In one embodiment, the device 100 may extract from the script input 130 one or more keywords corresponding to at least one of the aforementioned script attributes.

[0051] The script input 130 may include information describing a hypothetical script assumed by the user 112. For example, the user 112 may assume a camping trip and input the following hypothetical script input 130 into the user terminal 110 in the form of voice: "I want to go camping at a campsite in the mountains. I want to cook something to eat while camping, and I also want to sit and rest comfortably." In one embodiment, the recognition or analysis of the voice input has been described as being performed by the user terminal 110, but it can also be performed by the device 100. The device 100 may generate the script input 130 based on the analysis of the voice input 120 received from the user terminal 110.

[0052] User terminal 110 can transmit script input 130 to device 100 based on user input 120. In one embodiment, user input 120 may include text input from user 112. User 112 may input text script input to user terminal 110. In one embodiment, script input 130 may be the text input from user 112 received by user terminal 110 itself, or it may be analysis information generated by user terminal 110 analyzing user 112's text input. For example, user terminal 110 may recognize user 112's text input and convert user input 120 into script input 130. In one embodiment, script input 130 may include information obtained by user terminal 110 through natural language processing of user 112's text input. For example, script input 130 may include information of one or more keywords, which are extracted by user terminal 110 based on user 112's text input through morpheme analysis, sentence structure analysis, semantic analysis, etc. The script input 130 may include information describing a hypothetical script assumed by the user 112. For example, the user 112 may assume a camping trip and input the following hypothetical script input 130 as text into the user terminal 110: "I want to go camping at a campsite in the mountains. I want to cook something to eat while camping, and I also want to sit and rest comfortably." In one embodiment, the recognition or analysis of the text input has been described as being performed by the user terminal 110, but it can also be performed by the device 100. The device 100 may generate the script input 130 based on the analysis of the text input 120 received from the user terminal 110. In one embodiment, the device 100 may extract one or more keywords corresponding to at least one of the aforementioned script attributes based on the script text input 130.

[0053] In one embodiment, user input 120 may include image input from user 112. User 112 may input image input of a script to user terminal 110. In one embodiment, script input 130 may be the image input of user 112 received by user terminal 110 itself, or it may be text information generated by user terminal 110 after analyzing the image input of user 112. For example, user terminal 110 may recognize the image input of user 112 and convert user input 120 into text information. In one embodiment, script input 130 may include information about one or more objects, which are included in the image input of user 112 recognized by user terminal 110. Script input 130 may include an exemplary image of a virtual script assumed by user 112. For example, user 112 may assume a camping trip and input the following image as script input 130 into user terminal 110: an image of people setting up tents, preparing food, and resting on camping chairs at a campsite. In one embodiment, the recognition or analysis of the user's image input has been described as being performed by user terminal 110, but it can also be performed by device 100. Device 100 may generate script input 130 based on the analysis of image input 120 received from user terminal 110. In one embodiment, device 100 may extract one or more keywords corresponding to at least one of the aforementioned script attributes based on the image input 130 of the script.

[0054] The device 100 may receive condition information 140 included in user input 120 from the user terminal 110. The condition information 140 may include conditions for determining one or more items corresponding to the script. In one embodiment, the condition information 140 may include at least a portion of budget information set by the user 112 and information for excluding specific items. For example, the user 112 may expect to purchase one or more items required under the conditions corresponding to the virtual script within a pre-set budget. Furthermore, there may be situations where the user 112, due to already possessing a specific item or not desiring it, wishes to exclude specific items from the recommendations for one or more items corresponding to the script. Similarly, the user 112 may input the condition information 140 by including the conditions for items that must be included.

[0055] In one embodiment, condition information 140 may also be included in user input 120. User 112 may include one or more conditions desired by user 112 along with script input 130 in user input 120. For example, user 112 may include the following condition information 140 in user input 120 while describing a virtual script of camping conditions: "I want to go camping at a campsite in the mountains. I want to cook something to eat while camping and also want to sit and rest comfortably. I don't need a tent, but I must have a backpack. In particular, the backpack should preferably be red." In this case, device 100 may analyze the user's voice input and distinguish between script input 130 and condition information 140 in the voice input. In the example, condition information 140 may include the following information: "tent" is an excluded item, "backpack" is a required item; and may include the following condition: "backpack" should be "red". In other words, condition information 140 may include the condition of the item in user input 120 used to obtain recommendations for items that meet the conditions. In one embodiment, the condition information 140 may include information entered based on a preset user interface such as check boxes or icons.

[0056] The device 100 may determine one or more items corresponding to a script based on the script input 130 received from the user terminal 110. The one or more items may be included in the item set 170. In one embodiment, the device 100 may analyze the script input 130 to determine one or more items corresponding to the script. In this case, the one or more items corresponding to the script may refer to recommended items needed or potentially needed under the circumstances corresponding to the virtual script assumed by the user 112. In one embodiment, the device 100 may analyze the script input 130 to extract one or more keywords of at least one script attribute. For example, one or more keywords included in the script may refer to keywords corresponding to any of the following attributes: one or more script attributes related to an occasion, and one or more script attributes related to an item. Script attributes related to a situation may include, for example, the following: the time when the situation corresponding to the script occurs; the location where the situation corresponding to the script occurs; the entity that takes, participates in, or leads the behavior in the situation corresponding to the script; the object that the entity interacts with in the situation corresponding to the script; the action performed by the entity in the situation corresponding to the script; the context that constitutes the specific situation; the purpose of the entity's behavior; the emotions of the entity or object; and the result or impact of the specific behavior or event. Furthermore, one or more script attributes related to an item may include the following: type, brand, price, specific technical specifications or attributes, purpose, design, quality, reviews, inventory, distribution, and additional services. In one embodiment, device 100 may extract one or more keywords from script input 130 that correspond to at least one of the above-mentioned script attributes. Device 100 may identify one or more items as corresponding to a script based on one or more keywords, wherein the one or more items are related to the keywords and the script attributes corresponding to each keyword.

[0057] In one embodiment, the device 100 may determine one or more items based on a model learned in such a way as to determine one or more items corresponding to the script based on information from the script.

[0058] In one embodiment, the device 100 may determine one or more items corresponding to the script based on condition information 140 received from the user terminal 110.

[0059] In one embodiment, the device 100 may determine one or more items corresponding to a script based on item information 160. In this invention, item information 160 may include information on one or more items provided in an e-commerce service. The device 100 may store information on one or more items processed in the e-commerce service and may determine one or more items corresponding to a script based on the stored item information. In one embodiment, item information 160 may include tag information corresponding to each item. Tag information may include various metadata related to the item. For example, tag information may be assigned to a specific item and may include information on the type of script that frequently matches the corresponding specific item. For example, an item of the "football boots" category may include keywords such as "football" or "sports match" as tag information, or the tag information of the item may include information indicating that it frequently matches or has a high probability of matching scripts under the assumption that the situation is related to "football" or "sports match".

[0060] In one embodiment, the device 100 may determine one or more items corresponding to a script based on user information. User information may include the user's membership level, gender, age, item preference, purchase history, and item preference derived from the purchase history. The device 100 may pre-store user information and may determine one or more items corresponding to a script based on the user information.

[0061] In one embodiment, the device 100 may determine one or more items corresponding to the script, i.e., item set 170, based on at least a portion of the script input 130, condition information 140, item information 160, and user information.

[0062] Device 100 may generate query information 180 based on script input 130. Query information 180 may be information generated by device 100 to receive additional input from user 112 when script input 130 is insufficient to determine the item set 130, or when script input 130 is not specific enough. For example, if user 112 simply inputs "Sunday" as script input 130, it may be difficult to ascertain what situation the user experiences on Sunday, what places they go, and what items they need. Device 100 may generate query information 180 to ensure the specificity of script input 130 and calculate a more reliable item set 170.

[0063] In one embodiment, the device 100 may receive script input 130 (e.g., a first input) and generate query information corresponding to the first input based on analysis of the first input. For example, the device 100 may generate query information 180 related to the first input based on analysis of the first input, such as "Are you planning to travel on Sunday?". In one embodiment, the query information 180 can be generated in a manner that includes guidance on script attributes corresponding to keywords included in the first input and keywords corresponding to different script attributes. For example, if the first input "Sunday" is a keyword corresponding to the script attribute of time, the device 100 may generate query information 180 that guides keywords for places different from the keyword of time based on analysis of the first input, such as "Where are you planning to go on Sunday?". In one embodiment, device 100 may also use natural language processing to construct interactive query information 180 from the keywords included in the first input and the keywords corresponding to different script attributes into a sentence format. In one embodiment, device 100 may generate query information 180 that includes content for asking questions about the keywords in the first input based on script attributes that do not include the keywords in the first input. For example, device 100 may analyze the first input, which includes keywords corresponding to time, and generate query information 180 that guides keywords in script attributes not included in the first input, such as "If the location, product, user, context, purpose, etc. are specifically provided, it will be easier to recommend items." In this case, device 100 may assign priorities among the script attributes and generate query information 180 that guides keywords in script attributes corresponding to higher priorities.

[0064] In one embodiment, device 100 may transmit query information 180 to user terminal 110. Device 100 may transmit signals including commands to control user terminal 110 to expose query information 180 to user 112. In one embodiment, device 100 may receive script input 130 (e.g., a second input) from user terminal 110 based on user input 120 corresponding to query information 180. Device 100 may determine an itemset 170 including one or more items corresponding to a script based on previously received script input (e.g., a first input) and script input received corresponding to query information 180 (e.g., a second input).

[0065] In one embodiment, the device 100 can generate query information 180 based on one or more keywords included in the script input 130 and the script attributes corresponding to each keyword. For example, when the first input includes multiple keywords belonging to the same script attribute, the device 100 can generate query information 180 to guide the second input based on determining that the multiple keywords conflict with each other. For example, when multiple keywords corresponding to the same script attribute, namely "time," are extracted from the first input, and the multiple keywords are "summer" and "winter," the multiple keywords conflict with each other. Therefore, the device 100 can generate query information 180 such as "Are you looking for items suitable for summer? Are you looking for items suitable for winter?" In this case, the device 100 can also generate or modify the query information 180 based on the time when the user makes the input, user information, etc. For example, if the first input occurs in August, even if both the keywords "summer" and "winter" are included, the script that inputs "summer" is more likely to be selected. Therefore, device 100 can generate query information 180 based on the time of input, such as "Looking for items suitable for summer?".

[0066] In one embodiment, when the device 100 receives multiple script inputs 130 (e.g., receiving a first input and a second input), it can generate query information 180 based on the first input and the second input. In one embodiment, when there are contradictions among multiple script inputs 130, the device 100 can generate query information 180 to eliminate the contradictions.

[0067] In one embodiment, the device 100 may generate query information 180 based on the cumulative number of script inputs 130. The device 100 may confirm the total number of script inputs 130 received from the user terminal 110, and generate query information 180 when the total number is determined to be below a preset number. In this way, the device 100 may limit the number of interactions with the user by taking into account user fatigue and computing resources.

[0068] In one embodiment, the device 100 can calculate the score of the script input 130 and generate query information 180 for additional input based on the calculated score. The device 100 can generate query information 180 when the score of the script input (e.g., the first input) is lower than a predetermined threshold.

[0069] In one embodiment, the device 100 can calculate a score corresponding to the input based on one or more keywords included in the script input 130. The score corresponding to the input can be calculated based on evaluation items 150. Evaluation items 150 can correspond to various script attributes and keywords included in each script attribute. For example, the first evaluation item 150 can be an evaluation item such as: whether there is a keyword corresponding to "location" in the script attribute. The second evaluation item 150 can be an evaluation item such as: how many keywords correspond to "item type" in the script attribute. The scores for each evaluation item 150 can be different, and the criteria can also be different. For example, based on the first evaluation item, the score can be calculated solely based on whether there is a keyword corresponding to a specific script attribute; based on the second evaluation item, the score can be calculated based on the number of keywords corresponding to a specific script attribute. In one embodiment, the device 100 calculates scores based on the number of keywords. The more keywords corresponding to a specific script attribute, the higher the score can be assigned to the corresponding evaluation item. Alternatively, if the number of keywords corresponding to a specific script attribute exceeds a specified number, a score can be deducted from the corresponding evaluation item. In one embodiment, the device 100 assigns weighted values ​​to each evaluation item 150. The device 100 calculates the score corresponding to the first input by summing the scores calculated according to each evaluation item 150 based on the weighted values. If the score of the first input is below a preset score, query information 180 is generated. In one embodiment, the device 100 sets different weighted values ​​for the first input and the second input according to each evaluation item 150. For example, if the score of the first evaluation item calculated in the first input is lower than the score of the second evaluation item, the weighting value of the first evaluation item in the second input can be set to be greater than the weighting value of the second evaluation item. Therefore, if the device 100 obtains, for example, keywords of script attributes that are not satisfied in the first input through the second input, it can stop generating query information 180 and perform the action of determining the item set 170 corresponding to the script. Conversely, if the device 100 analyzes the second input and obtains only keywords of script attributes that are satisfied in the first input, but cannot obtain keywords of script attributes that are not satisfied in the first input, it can calculate a relatively low score for the second input by setting a weighting value and generate query information 180 requiring a third input corresponding to the second input.

[0070] Device 100 can generate visual information 190 based on script input 130, item information 160, and an item set 170 corresponding to the script. Visual information 190 may include image information indicating the usage of one or more items included in item set 170 within the script. For example, corresponding to a camping-related script, the following image may be generated as visual information 190: a user using a tent, backpack, stove, and camping chair to enjoy camping. In one embodiment, device 100 can generate visual information 190 corresponding to the script based on an image generation model. In one embodiment, device 100 can generate a first image corresponding to the script, obtain a second image corresponding to item set 170 based on item information 160, and combine the first and second images to generate visual information 190. In one embodiment, visual information 190 may be video. Device 100 can generate a plurality of images corresponding to a script and can generate video based on a plurality of images. The device 100 can transmit the generated visual information 190 to the user terminal 110.

[0071] According to the present invention, multiple items required by a customer in a specific situation can be directly combined to reduce the difficulty of purchasing. For example, when a customer is not aware of the items they need, the device 100 can provide information on the combination of items required for that situation based solely on the specific situation input by the customer.

[0072] Furthermore, customers who need multiple items for a specific event may find it difficult to predict whether the combination of multiple items selected by the customer personally or through the device 100 is harmoniously constituted. However, according to the present invention, the device 100 can provide information in the form of visual information about the simultaneous use of multiple selected items, and make it easier for customers to grasp whether the selected multiple items are a matching combination.

[0073] Figure 2 is a block diagram of a device 100 according to one embodiment of the present invention. The device 100 may include one or more processors 210 and / or one or more memory units 220. In one embodiment, at least one of the elements of the device 100 may be omitted, or other elements may be added to the device 100. In one embodiment, some elements may be additionally or alternatively integrated to achieve, or implemented as a single or multiple entities. In the present invention, one or more processors 210 may be referred to as processor 210. Unless explicitly stated otherwise in the context, the term processor 210 may refer to a collection of one or more processors. In the present invention, one or more memory units 220 may be referred to as memory units 220. Unless explicitly stated otherwise in the context, the term memory units 220 may refer to a collection of one or more memory units. In one embodiment, at least some of the internal / external components of the device 100 can be interconnected via buses, GPIO (general purpose input / output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface) to send and receive information (data, signals, etc.).

[0074] The processor 210 can execute commands (e.g., programs) to control at least one component of the device 100 connected to the processor 210. Furthermore, the processor 210 can perform various operations related to the present invention, such as calculations, processing, data generation, and manipulation. Also, the processor 210 can load information from the memory 220 or store information in the memory 220.

[0075] Memory 220 can store various types of information. The information stored in memory 220, as data obtained, processed, or used by at least one component of device 100, may include commands (e.g., programs). Memory 220 may include volatile and / or non-volatile memory. In this invention, commands, as software stored in memory 220, may include an operating system, applications, and / or middleware for controlling the resources of device 100, which provides various functions to the application to enable the application to utilize the resources of device 100. In one embodiment, memory 220 may store commands that, when executed by processor 210, cause processor 210 to perform calculations.

[0076] In one embodiment, device 100 may further include a communication circuit 230. According to an embodiment, the communication circuit 230 may be omitted from device 100. The communication circuit 230 can enable wireless or wired communication between device 100 and other devices (e.g., servers, databases, sensors, input devices, output devices, etc.). For example, the communication circuit 230 can implement wireless communication in the following ways: eMBB (enhanced Mobile Broadband), URLLC (Ultra Reliable Low-Latency Communications), MMTC (Massive Machine Type Communications), LTE (Long-Term Evolution), LTE-A (LTE Advance), NR (New Radio), UMTS (Universal Mobile Telecommunications System), GSM (Global System for Mobile communications), CDMA (Code Division Multiple Access), WCDMA (Wideband CDMA), WiBro (Wireless Broadband), WiFi (Wireless Fidelity), Bluetooth, NFC (Near Field Communication), GPS (Global Positioning System), or GNSS (Global Navigation Satellite System). For example, the communication circuit 230 can implement wired communication in the following ways: USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), RS-232 (Recommended Standard-232), or POTS (Plain Old Telephone Service).In one embodiment, the processor 210 may control the communication circuit 230 to communicate with the user terminal 110 and / or other devices (e.g., a database). During this process, information can be obtained and stored in memory 220. In one embodiment, the device 100 may also be integrated with other devices (e.g., a database). In this case, the communication circuit 230 may function as a connection circuit or interface connecting the device 100 to corresponding other devices.

[0077] In one embodiment, the device 100 may be a device of various forms. For example, the device 100 may be a computer device, a back-end server, a front-end server, a portable communication device, a portable multimedia device, a device composed of the above devices, or a chip, board, circuit, etc. within the above devices. However, the device 100 of the present invention is not limited to the above devices.

[0078] In one embodiment, the user terminal 110 may be a device of various forms. For example, the user terminal 110 may be a portable communication device (e.g., a smartphone), a computer device (e.g., a tablet computer, a laptop computer), a portable multimedia device, a wearable device, a device combining the above devices, or a chip, board, circuit, etc. within the above devices. However, the user terminal 110 is not limited to the above devices. The user terminal 110 may include one or more processors and / or one or more memory. The one or more memory may store commands that, when executed by one or more processors, cause one or more processors to perform calculations. One or more processors of the user terminal 110 may perform actions corresponding to the actions of the device 100 according to the item recommendation and visual information provision technology of the present invention. In one embodiment, the user terminal 110 may further include an input device and / or an output device. The input device, as a device for obtaining information from the user 112, may include, for example, a touch screen, a keyboard, buttons, a microphone, etc. Output devices are devices that provide various information to users, such as touch screens, displays, etc.

[0079] Figure 3 is a diagram illustrating one or more recommended items corresponding to a virtual script in one embodiment of the present invention, and the generated visual information. The device 100 can use the first page 300 for recommending items to display to the user, in the form of visual information, the usage of the recommended item set in the script, and display information about the recommended item set.

[0080] Page 1 300 may include: a visual information area 310, which includes visual information; and an item information area 320, which displays information about one or more items corresponding to the script.

[0081] In one embodiment, the visual information area 310 may display a first image corresponding to a script, and may display a second image of one or more items corresponding to the script in a portion of the area of ​​the first image. The device 100 may generate a first image corresponding to the script, identify areas corresponding to each item in the first image, and place the second image in each area. For example, the first image may include the shape of a tent, a camping chair, and a person sitting on a camping chair, and the device 100 may present an image (second image) of a recommended item corresponding to the camping chair in the camping chair area, and an image (second image) of a recommended item including a tent in the area including the tent, thereby placing the second image in each area of ​​the first image.

[0082] In one embodiment, each of the second images may be a user interface for requesting detailed information about the corresponding item, or for receiving requests from the user to change the corresponding item or modify the second image. For example, in the visual information area 310, the second image corresponding to the tent may be a user interface for requesting a detailed page of the tent item, or for the device 100 to receive various inputs from the user regarding the tent item, such as a request to change the tent to another tent, a request to change the tent's color scheme, or a request to obtain recommendations for tents at different price points. As described above, the visual information area 310 may include a user interface for requesting changes to the visual information displayed in the visual information area 310 according to the corresponding item, or for revealing detailed information about such items. As described above, requests to change visual information can be understood as user feedback. For example, user feedback may include user input to change or remove an image, or to modify a portion of an image. User feedback may include inputs that reveal visual information when making partial changes to an entered script, such as "showing what it looks like when the weather is colder." In other examples, feedback may include inputs to delete a specific item from the visual information, to change the position of a specific item, or to change the color of a specific item. Device 100 may receive feedback through one or more user interfaces in the visual information area 310.

[0083] In one embodiment, the item information area 320 may display information about one or more items, which are included in an item set determined according to a script. The item information area 320 may include a user interface for receiving user input for each item. In one embodiment, input for changing at least a portion of the recommended item set may be understood as user feedback. For example, feedback input may include inputs such as: changing a specific item to another item; changing a specific item to the same type of item at a different price; or replacing a specific item with another type of item. The device 100 may receive feedback input through one or more user interfaces included in the item information area 320.

[0084] Figure 4 is a diagram of a method for displaying more than one recommended item using the apparatus of the present invention. In one embodiment, the item information area 320 for displaying recommended items may include an item catalog 410 and an item purchase interface 420, as shown in Figure 4.

[0085] The item catalog 410 may include a user interface for receiving inputs such as determining the quantity of each item, deleting an item, or selecting an item.

[0086] The item purchase interface 420 can accept user input for purchasing one or more recommended items. Furthermore, the item purchase interface 420 may include price information, etc.

[0087] Figure 5 is a diagram illustrating the advertising information of the present invention. In one embodiment, the visual information displayed in the visual information area 310 may include markers indicating that an image of a specific item is an advertisement for that item. The device 100 may provide visual information and item information of a portion of one or more items included in the item set 170 as advertising information 510 based on condition information 140.

[0088] In one embodiment, the device 100 can generate visual information including at least one of advertising information 510 and guidance information ("AD"). The advertising information is provided in the form of an advertisement when the total price of one or more items included in the item set 170 exceeds the user's budget. The guidance information indicates the fact that the total price exceeds the user's budget or indicates that the corresponding item image is an advertisement. In one embodiment, when the total price of the item set 170 is determined to exceed the user's budget, the device 100 can determine to provide information on at least one of the items included in the item set 170 in the form of an advertisement. For example, when the price of a specific item is deducted, the total price of the item set 170 becomes below the user's budget, or information on a lower priority item included in the item set 170 can be provided in the form of advertising information 510.

[0089] In one embodiment, the device 100 can also determine one or more items to be included in the item set by the amount by which the total price of the item set exceeds a preset range of the user's budget. For example, the device 100 can determine one or more items corresponding to the script by exceeding the user's budget by a specified percentage or by exceeding a specified amount, and provide at least one of the items in the form of advertising information 510.

[0090] Figure 6 is a diagram illustrating a learning model of one embodiment of the present invention, which learns in the following manner: determining one or more items based on a script corresponding to user input and generating visual information.

[0091] In this invention, the "learning model" can be designed to realize the structure of the human brain in a computer, and can include a plurality of network nodes that simulate neurons of a human neural network and have weighted values. The plurality of network nodes can simulate the synaptic activity of neurons that send and receive signals through synapses, and have interconnections with each other. In the learning model, the plurality of network nodes are located at different depths and can send and receive data according to convolutional connections. For example, the learning model can be an artificial neural network model, a time series analysis model, etc. Here, the time series analysis model, as a model for analyzing time series data, can be an RNN (recurrent neural network) model, an LSTM (long short-term memory) model, or an ARIMA (Autoregressive Integrated Moving Average) model. On the other hand, the present invention is not limited thereto, and various types of models for analyzing data can also be used.

[0092] In this invention, the "learning process" can refer to the following process: the process by which the learning model repeatedly extracts and analyzes the features (patterns) of the input and output data pairs of the learning data to derive the correlation between the input and output data, thereby gradually optimizing the parameters of the learning model based on the correlation between the input and output data.

[0093] In this invention, the "inference process" can refer to the following process: the learning model applies the previously learned pattern to new input data, thereby producing output data as the result of predicting or classifying the input data.

[0094] Figure 6 is a diagram illustrating the process of determining an item set 170 using a learning model 600 learned in the manner described in one embodiment of the present invention: determining one or more items corresponding to a script. Also, Figure 6 is a diagram illustrating the process of generating visual information using a learning model 600 learned in the manner described in one embodiment of the present invention: generating visual information 190 corresponding to a script based on script input.

[0095] In one embodiment, the learning model 600 may be the following model: during the learning process, learning data 610 using different scripts, item attributes, user information, etc. is used to select one or more items corresponding to the script. During the inference process, output data 630 corresponding to one or more items is generated from the input data 620 of the script.

[0096] In one embodiment, the learning model 600 may be the following model: during the learning process, learning data 610, such as different scripts, images of different scripts, and images of more than one item, is used to generate visual information corresponding to the script; during the inference process, visual information output data 630 is generated from the input data 620 of the script.

[0097] Figure 7 is a flowchart illustrating the operation of a device according to one embodiment of the present invention. The device 100 can receive user input for a virtual script (S710). In one embodiment, the device 100 can receive user input for a virtual script, which includes at least a portion of user voice input, image input, and text input.

[0098] Device 100 can determine one or more items corresponding to the script (S720). In one embodiment, device 100 can input user input to the script into a learning model that learns by outputting items that conform to the script, and obtain information about one or more items as its output. In one embodiment, device 100 can analyze user input to the script and determine one or more items corresponding to the script based on the analysis results.

[0099] The device 100 can generate visual information representing the usage of one or more items in the script (S730). In one embodiment, the device 100 can generate a first image corresponding to the script, obtain a second image of each of the one or more items corresponding to the script, and generate visual information based on the first image and the second image. In one embodiment, the device 100 can input the script information into a learning model and obtain a first image corresponding to the script as its output. The learning model can be a model that learns in such a way that it outputs a first image in the form of an image representing the state of the script based on the script input.

[0100] The device 100 can transmit visual information to the user terminal (S740). In one embodiment, the device 100 can transmit information about one or more items that are identified as corresponding to a script, along with the visual information, to the user terminal.

[0101] Figure 8 is a flowchart illustrating the operation of a device according to one embodiment of the present invention. The device 100 can receive a first input of a script (S810). The device 100 can analyze the first input (S820). In one embodiment, the device 100 can input the first input into a natural language processing model and obtain the results of analyzing the first input from the natural language processing model. In one embodiment, the device 100 can extract one or more keywords included in the first input and confirm the script attributes corresponding to each keyword. In one embodiment, the device 100 can analyze the first input and calculate a score for the first input.

[0102] The device 100 may generate query information corresponding to the first input based on the analysis of the first input (S830). In one embodiment, the device 100 may generate query information based on the score of the first input. In one embodiment, the device 100 may generate query information based on the total number of script inputs, the script inputs including the first input.

[0103] Device 100 may receive a second input corresponding to the query information (S840). In one embodiment, device 100 may transmit the query information to user terminal 110. In one embodiment, device 100 may receive a second input from user terminal 110 corresponding to the query information.

[0104] The method of the present invention can be implemented by a computer. The computer may include, for example, a processing device 100. In this invention, the steps of the methods are illustrated and explained in a specific order, but in addition to being performed sequentially, the steps may also be performed in any combination of orders according to the present invention. In one embodiment, at least some steps may be performed in parallel, repeatedly, or heuristically. The present invention does not preclude variations or modifications to these methods. In one embodiment, at least some steps may be omitted, or other steps may be added.

[0105] Various embodiments of the present invention can be implemented in the form of recorded software on a machine-readable recording medium. The software can be software used to implement the various embodiments of the present invention described above. Programmers in the art to which this invention pertains can deduce the software based on the various embodiments of the present invention. For example, the software can be machine-readable commands (e.g., code or code segments) or programs. The machine is a device that can act according to commands called from the recording medium, such as a computer. In one embodiment, the machine can be device 100 of an embodiment of the present invention. In one embodiment, the processor of the machine executes the called commands, thereby enabling the components of the machine to perform functions corresponding to those commands. In one embodiment, the processor can be processor 210 of an embodiment of the present invention. The recording medium can refer to all kinds of recording media capable of being read and stored by a machine. Recording media may include, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. In one embodiment, the recording medium can be memory 220. In one embodiment, the recording medium can also be implemented in the form of being distributed across computer systems connected to a network. Software can be distributed across computer systems and executed. The recording medium can be a non-transitory recording medium. A non-transitory recording medium refers to a tangible medium that exists without regard to semi-permanent or temporary data storage, and does not include transiently transmitted signals.

[0106] The technical concept of the present invention has been described above according to various embodiments. However, the technical concept of the present invention includes various substitutions, variations, and modifications that can be understood by those skilled in the art to which the present invention pertains. Furthermore, it should be understood that such substitutions, variations, and modifications may be included within the scope of the appended patent applications. Embodiments of the present invention can be combined with each other. The embodiments can be combined in various ways depending on the circumstances, and the combined embodiments also fall within the scope of the present invention. [Simplified Explanation of the Diagram]

[0033] Figure 1 is a diagram illustrating the operation process of the device according to one embodiment of the present invention. Figure 2 is a block diagram of the device according to one embodiment of the present invention. Figure 3 is a diagram illustrating one or more recommended items corresponding to a virtual script and the generated visual information according to one embodiment of the present invention. Figure 4 is a diagram illustrating a method of displaying one or more recommended items using the device of the present invention. Figure 5 is a diagram illustrating advertising information according to the present invention. Figure 6 is a diagram illustrating a learning model according to one embodiment of the present invention that learns in the following manner: determining one or more items based on a user-input script and generating visual information. Figure 7 is a flowchart illustrating the operation of the device according to one embodiment of the present invention. Figure 8 is a flowchart illustrating the operation of the device according to one embodiment of the present invention.

Claims

1. A method for providing item information and visual information corresponding to a script, implemented in a device including one or more processors and one or more memories storing commands to be executed by the one or more processors, the method comprising the steps of the one or more processors as follows: receiving input from a user for a virtual script, wherein the script is a specific situation expected or anticipated by the user; identifying one or more items corresponding to the script; generating first visual information indicating the utilization of the one or more items in the script; and transmitting the first visual information to the user's user terminal.

2. The method of claim 1, wherein the step of receiving input to the script includes the following steps: receiving a first input to the script from the user terminal; analyzing the first input; generating query information corresponding to the first input based on the analysis of the first input; transmitting the query information to the user terminal; and receiving a second input to the script from the user terminal, the second input corresponding to the query information; and the step of determining one or more items corresponding to the script includes the following steps: determining one or more items corresponding to the script based on the first input and the second input.

3. The method of request item 2, wherein the step of generating the above query information includes the following steps: confirming the total number of inputs of the above script received from the above user terminal; and generating the above query information as soon as the total number of inputs is determined to be below a preset number.

4. The method of claim 2, wherein the step of analyzing the first input includes the following steps: extracting one or more keywords included in the first input; calculating a score corresponding to the first input based on the one or more keywords; and calculating a score corresponding to the first input based on the score corresponding to the first input; and the step of generating query information corresponding to the first input includes the following steps: determining whether to generate the query information based on the score corresponding to the first input and a preset threshold score.

5. The method of claim 4, wherein the step of analyzing the first input includes the following steps: confirming one or more script attributes corresponding to each of the keywords included in the first input; calculating the score of each of the evaluation items based on the one or more script attributes corresponding to each of the keywords; and calculating the score corresponding to the first input based on the score of each of the one or more evaluation items.

6. The method of claim 5, wherein the step of calculating the score corresponding to the first input based on the scores of the above-mentioned one or more evaluation items includes the following steps: Based on the preset weighting information of the above-mentioned one or more evaluation items, assigning a preset weighting value according to the above-mentioned evaluation items to the scores of the above-mentioned evaluation items, thereby calculating the score corresponding to the first input.

7. As in request item 1, wherein the input to the above script includes voice input.

8. As in request item 1, wherein the input of the above script includes image input.

9. The method of request item 1 further includes the following steps: receiving condition information related to the purchase of an item from the user terminal; and determining one or more items corresponding to the script includes the following steps: determining one or more items corresponding to the script based on the input of the script and the condition information.

10. As in request item 9, wherein the aforementioned condition information includes information about the user's budget for purchasing items.

11. The method of request item 10, wherein the step of determining the more than one item includes determining the more than one item by the following: the amount by which the total price corresponding to the more than one item exceeds the range of the user's pre-specified budget, wherein the more than one item corresponds to the script.

12. The method of claim 1, wherein when the total price corresponding to the determined one or more items exceeds the user's budget, the step of generating the first visual information includes generating the first visual information in such a way that the first visual information further includes guidance information and advertising information, the guidance information indicating that the total price corresponding to the one or more items exceeds the user's budget, and the advertising information indicating the advertising content of at least one of the one or more items.

13. The method of Request 1, wherein the step of determining one or more items corresponding to the above script includes the following steps: determining one or more items corresponding to the above script based on the result output by inputting the information of the above script into the item determination model; the above item determination model is a model learned in the following manner: determining one or more items corresponding to the script based on item information, user information and script input.

14. The method of claim 1, wherein the step of generating the first visual information includes the following steps: generating a first image corresponding to the script; obtaining one or more second images corresponding to the determined one or more items; and generating the first visual information based on the first image and the one or more second images.

15. The method of claim 14, wherein the step of generating the first visual information based on the first image and the second image includes the following steps: identifying one or more regions in the first image that correspond to each of the one or more items; and placing the one or more second images in each of the one or more regions.

16. The method of claim 1 further includes the steps of: receiving input from the user terminal corresponding to the feedback of the first visual information; and generating second visual information obtained from the change of the first visual information based on the feedback input.

17. The method of claim 1 further includes the steps of: receiving input from the user terminal corresponding to the feedback of the first visual information; changing at least one of the determined items based on the feedback input; and generating second visual information obtained from the change of the first visual information as the at least one item changes.

18. An apparatus for providing item information and visual information corresponding to a script, comprising: The device comprises: a communication circuit; one or more processors; and one or more memory units storing commands to be executed by the one or more processors; and the device is configured such that, when executing the one or more commands, the one or more processors perform the following: receiving input from a user terminal via the communication circuit for a virtual script, wherein the script is a specific situation expected or anticipated by the user; identifying one or more items corresponding to the script; generating first visual information indicating the usage of the one or more items in the script; and transmitting the first visual information to the user terminal via the communication circuit.

19. A recording medium that records non-transitory computer-readable recording media for executing commands by one or more processors, wherein the commands are configured such that, when executing the commands, the one or more processors: receive input from a user terminal via a communication circuit for a virtual script, wherein the script is a specific situation desired or anticipated by the user; identify one or more items corresponding to the script; generate first visual information indicating the utilization of the one or more items in the script; and transmit the first visual information to the user terminal via the communication circuit.

Images