Apparatus, method and program for providing content search service
The server system enhances content search accuracy by determining final search information based on user input and updating the search model, addressing the limitations of existing systems by providing reliable and personalized search results.
Patent Information
- Application Number
- KR1020240149051
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-10-28
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2044-10-28
AI Technical Summary
Existing content search systems fail to provide optimal search results with high accuracy and reliability due to the lack of utilization of final search information determined based on additional user information.
A server system that acquires search information from an electronic device, generates additional necessary information, and determines final search information based on user input, utilizing a pre-trained search model that is updated and retrained based on user selections to refine search results.
Provides optimal search results with high accuracy and reliability by incorporating additional user information and updating the search model, ensuring that user preferences are accounted for in the search outcomes.
Smart Images

Figure R1020240149051_ABST
Abstract
Description
Technology Field
[0001] The present invention relates to a device, method, and program for providing a content search service capable of providing optimal search results to a user requesting a content search. Background Technology
[0002] With the rapid increase in online and mobile video consumption driven by high-speed mobile communication and the widespread adoption of smartphones, Over-The-Top (OTT) services—online streaming platforms on the web and mobile—are expanding beyond traditional TV-based broadcasting platforms such as terrestrial, cable, satellite, and IPTV.
[0003] The OTT market size is growing every year, and as mobile communication technology advances, the demand for OTT services is expected to increase even further.
[0004] Accordingly, OTT services are developing services that were not provided by existing broadcasting platforms, or services that can provide enjoyment to users while consuming content. Prior art literature
[65535] Published Patent Application No. 10-2022-0004278 (January 11, 2022) Registered Patent Application No. 10-2654884 (April 3, 2024) The problem to be solved
[0005] We aim to provide optimal search results with high accuracy and reliability to users requesting content search by utilizing final search information determined based on additional user information.
[0006] We aim to provide optimal search results to users by retraining and updating the content search model based on the content finally selected by the user from the search results and the final search information used in the search results. means of solving the problem
[0007] According to one aspect, a server is provided comprising a communication unit connected to an electronic device, a database storing search information for content search by category, and a processor providing search results in response to a content search request from the electronic device, wherein the processor acquires search information for searching at least one piece of content from the electronic device, generates additional necessary information based on the search information and requests it from the electronic device, and when it acquires additional user information corresponding to the additional necessary information from the electronic device, determines final search information based on the additional information and provides search results to the electronic device based on the final search information.
[0008] According to one embodiment, when the processor obtains the search information, if a content search request is received from the electronic device, the processor obtains search request data input to the electronic device in response to the content search request, and can extract and obtain search information from the search request data.
[0009] According to one embodiment, when the processor requests the additional necessary information, it performs a content search based on the search information to provide an initial search result to the electronic device, generates additional necessary information to specify the final search information based on the initial search result, and may request the additional necessary information from the electronic device.
[0010] According to one embodiment, the processor can identify a content genre corresponding to the initial search result after providing the initial search result, select a search category for classifying the content genre, and generate additional necessary information based on the selected search category.
[0011] According to one embodiment, if the additional required information is a search category, the processor can request the additional required information by creating the search category in the form of a main search icon and providing the main search icon to the electronic device so that the main search icon corresponding to the search category is displayed on the initial search result.
[0012] According to one embodiment, when a user input selecting a main search icon corresponding to the search category is received from the electronic device, the processor checks whether a subcategory corresponding to the selected search icon exists, and if the subcategory exists, generates a sub search icon corresponding to the subcategory and provides the sub search icon to the electronic device so that the sub search icon is matched to the main search icon and displayed, thereby requesting the additional necessary information.
[0013] According to one embodiment, when a user input selecting the sub-search icon is received from the electronic device, the processor generates a user search weight input field for each item included in the sub-category of the selected sub-search icon, provides the items included in the sub-category and the user search weight input field for each item to the electronic device, and may request additional necessary information including the user search weight entered through the search weight input field.
[0014] According to one embodiment, if the additional required information is a search category, the processor can create the search category in the form of a speech bubble and request additional required information by providing the speech bubble to the electronic device so that a speech bubble corresponding to the search category is displayed on the initial search result.
[0015] According to one embodiment, when the processor provides a search result based on the final search information, it inputs the final search information into a pre-trained search model to obtain a search result containing content that the user wishes to search for, and provides the search result to the electronic device.
[0016] According to one embodiment, when training the search model, the processor acquires content information classified by category, acquires metadata of the content corresponding to the content information and stores it in the database, trains the search model based on the content and metadata to obtain a training result, and retrains the search model based on the training result to update the search model.
[0017] According to one embodiment, when the processor receives user input selecting specific content from the search results from the electronic device, it can analyze the relationship between the configuration of the selected content and the final search information, and update the search model by retraining the search model based on the relationship.
[0018] According to another aspect, a method for providing a content search service of a server is provided, characterized by comprising the steps of: obtaining search information for searching at least one content from the electronic device; generating additional necessary information based on the search information and requesting it from the electronic device; obtaining additional user information corresponding to the additional necessary information from the electronic device; determining final search information based on the additional information; and providing a search result to the electronic device based on the final search information.
[0019] According to another aspect, a computer program is provided that is combined with a computer, which is hardware, and is stored on a medium to provide a method for providing a content search service.
[0020] According to one aspect, an electronic device is provided comprising a communication unit connected to a server, a display unit for displaying content search results provided from the server, and a control unit for controlling the communication unit and the display unit, wherein the control unit controls the communication unit to transmit a content search request including search request data to the server when search request data for a content search request is input, controls the display unit to display a user response input window corresponding to the additional necessary information request when a request for additional necessary information is received from the server, controls the communication unit to transmit additional user information input through the user response input window to the server, and controls the display unit to display a final search result for the content search when a final search result corresponding to the additional information is received from the server.
[0021] According to another aspect, a method for displaying a content search service of an electronic device is provided, characterized by comprising the steps of: receiving search request data for a content search request; transmitting a content search request including said search request data to said server; receiving a request for additional necessary information from said server; displaying a user response input window corresponding to said request for additional necessary information; transmitting additional user information entered through said user response input window to said server; receiving a final search result corresponding to said additional information from said server; and displaying a final search result for said content search.
[0022] According to another aspect, a computer program is provided that is combined with a computer, which is hardware, and provides a content search service display method stored on a medium to perform a content search service display method. Effects of the invention
[0023] By utilizing final search information determined based on additional user information, optimal search results with high accuracy and reliability can be provided to users requesting content search.
[0024] The content search model can be retrained and updated based on the content finally selected by the user from the search results and the final search information used in the search results to provide the user with optimal search results. Brief explanation of the drawing
[0025] The present disclosure can be easily understood from the combination of the following detailed description and the accompanying drawings, where reference numerals denote structural elements. FIG. 1 is a drawing for explaining a content search service providing system according to one embodiment. FIG. 2 is a drawing for explaining a server according to one embodiment. FIG. 3 is a drawing for explaining an electronic device that communicates with a server according to one embodiment. FIG. 4 is a diagram illustrating a database of a server according to one embodiment. FIG. 5 is a diagram illustrating the process of providing a content search service according to one embodiment. FIGS. 6a to 6c are drawings for explaining the process of obtaining additional information to determine final search information according to one embodiment. FIG. 7 is a diagram illustrating the process of obtaining additional information to determine final search information according to another embodiment. FIG. 8 is a diagram illustrating the process of generating search results using a search model according to one embodiment. FIGS. 9 and FIGS. 10 are drawings for illustrating the search model retraining and update process according to one embodiment. FIG. 11 is a drawing for explaining the process of displaying search results according to one embodiment. FIG. 12 is a flowchart illustrating a method for providing a content search service of a server according to one embodiment. FIG. 13 is a flowchart illustrating a method for displaying a content search service of an electronic device that communicates with a server, according to one embodiment. Specific details for implementing the invention
[0026] Various embodiments are described in detail below with reference to the drawings. The embodiments described below may be implemented in various different forms. In order to explain the features of the embodiments more clearly, detailed descriptions of matters widely known to those skilled in the art to which the following embodiments belong are omitted.
[0027] Meanwhile, when a configuration is described in this specification as being "connected" to another configuration, this includes not only cases where they are "directly connected," but also cases where they are "connected with another configuration in between." Furthermore, when a configuration is described as "including" another configuration, this means that, unless specifically stated otherwise, it does not exclude other configurations but may include additional configurations.
[0028] Additionally, terms including ordinal numbers, such as 'first' or 'second' as used herein, may be used to describe various components, but said components should not be limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another.
[0029] In this specification, the "server" determines final search information based on additional information from the user and can generate and provide optimal content search results with high accuracy and reliability to a user requesting content search using the determined final search information.
[0030] In this specification, "electronic device" may be, but is not limited to, a smartphone, tablet PC, PC, TV, smart TV, mobile phone, PDA (personal digital assistant), laptop, or non-mobile computing device. An application providing a content search service may be distributed and installed on the electronic device. The electronic device may execute the application providing the content search service and receive and display optimal content search results to a user who has requested a content search through the application.
[0031] In this specification, "content" may refer to information or materials provided via the Internet or computer communication, etc. Content may refer to information or materials that are produced, processed, or distributed digitally, such as characters, symbols, voice, sound, images, video, etc. For example, content provided through a server may be video material.
[0032] FIG. 1 is a drawing for explaining a content search service providing system according to one embodiment.
[0033] As illustrated in FIG. 1, a content search service providing system may include a server (100) that provides search results in response to a content search request of an electronic device (200), and an electronic device (200) that is communicationally connected to the server (100) and receives a final search result corresponding to additional information from the server (100) and displays a final search result for content search.
[0034] For example, the electronic device (200) may include both a standing device such as a PC (Personal Computer), Network TV, HBBTV (Hybrid Broadcast Broadband TV), Smart TV, and IPTV (Internet Protocol TV), and a mobile device or handheld device such as a smartphone, Tablet PC, Notebook, and PDA (Personal Digital Assistant).
[0035] And, the network connecting the electronic device (200) and the server (100) includes both wired and wireless networks, and is a general term for a communication network that supports various communication standards or protocols for pairing or / and data transmission and reception between the electronic device (200) and the server (100).
[0036] These wired and wireless networks include all communication networks currently or to be supported in the future by standards, and can support all one or more communication protocols for them.
[0037] Wired / wireless networks can be formed by networks for wired connections such as USB (Universal Serial Bus), CVBS (Composite Video Banking Sync), Component, S-Video (analog), DVI (Digital Visual Interface), HDMI (High Definition Multimedia Interface), RGB, and D-SUB, and communication standards or protocols for them, and networks for wireless connections such as Bluetooth, RFID (Radio Frequency Identification), infrared communication (IrDA: infrared Data Association), UWB (Ultra Wideband), ZigBee, DLNA (Digital Living Network Alliance), WLAN (Wireless LAN) (Wi-Fi), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), LTE / LTE-A (Long Term Evolution / LTE-Advanced), and Wi-Fi Direct, and communication standards or protocols for them.
[0038] Meanwhile, the server (100) obtains search information for searching at least one piece of content from the electronic device (200), generates additional necessary information based on the search information and requests it from the electronic device (200), and when it obtains additional information from the electronic device (200) that corresponds to the additional necessary information, it determines final search information based on the additional information and provides search results to the electronic device (200) based on the final search information.
[0039] Here, when the server (100) obtains search information, when a content search request is received from the electronic device (200), it obtains search request data input to the electronic device (200) in correspondence with the content search request, and can obtain search information by extracting it from the search request data.
[0040] Additionally, when requesting additional necessary information, the server (100) performs a content search based on search information to provide an initial search result to the electronic device (200), generates additional necessary information to specify final search information based on the initial search result, and can request additional necessary information from the electronic device (200).
[0041] Here, the server (100) identifies a content genre corresponding to the initial search result, selects a search category for classifying at least one of the content genre, actors, and synopsis, and can generate additional necessary information based on the selected search category.
[0042] Additionally, when the server (100) provides search results based on final search information, it inputs the final search information into a pre-trained search model to obtain search results containing content that the user wants to search for, and can provide the search results to an electronic device (200).
[0043] Here, when training a search model, the server (100) obtains content information classified by category, obtains metadata of the content corresponding to the content information, trains the search model based on the content and metadata to obtain a training result, and can update the search model by retraining the search model based on the training result.
[0044] In some cases, when the server (100) receives user input selecting specific content from search results from the electronic device (200), it may analyze the relationship between the composition of the selected content and the final search information, and update the search model by retraining the search model based on the relationship.
[0045] In this way, a device providing a content search service can provide optimal search results with high accuracy and reliability to a user requesting a content search by utilizing final search information determined based on additional user information.
[0046] In addition, a device providing a content search service can provide optimal search results to the user by retraining and updating a content search model based on the content finally selected by the user from the search results and the final search information used in the search results.
[0047] FIG. 2 is a drawing for explaining a server according to one embodiment.
[0048] As illustrated in FIG. 2, the server (100) may include a communication unit (110) that is connected to an electronic device, a database (120) that stores search information for content search by category, and a processor (130) that provides search results in response to a content search request from the electronic device.
[0049] Here, the processor (130) of the server (100) may be composed of one or more cores and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device.
[0050] In addition, the communication unit (110) of the server (100) may include a wireless internet module, a short-range communication module, a location information module, etc.
[0051] A wireless internet module refers to a module for wireless internet access, configured to transmit and receive wireless signals in a communication network based on wireless internet technologies.
[0052] Wireless internet technologies include, for example, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), etc., and the above wireless internet module transmits and receives data according to at least one wireless internet technology within a range that includes internet technologies not listed above.
[0053] From the perspective that wireless internet access via WiBro, HSDPA, HSUPA, GSM, CDMA, WCDMA, LTE, LTE-A, etc. is achieved through a mobile communication network, a wireless internet module that performs wireless internet access through a mobile communication network may be understood as a type of mobile communication module.
[0054] A short-range communication module is for short-range communication and can support short-range communication by using at least one of the following technologies: Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus).
[0055] A location information module is a module for obtaining the server's location (or current location), and representative examples include the GPS (Global Positioning System) module or the WiFi (Wireless Fidelity) module.
[0056] And, the database (120) of the server (100) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk.
[0057] Additionally, the server (100) may operate in conjunction with web storage that performs the storage function of the database (120) on the internet. The description of the database described above is merely an example and is not limited thereto.
[0058] For example, the database (120) includes multiple sub-databases that store search information for content search by top category, and each sub-database may include multiple sub-categories included in the top category.
[0059] Meanwhile, the processor (130) can obtain search information for searching at least one content from an electronic device, generate additional necessary information based on the search information and request it from the electronic device, and when it obtains additional information of a user corresponding to the additional necessary information from the electronic device, determine final search information based on the additional information of the user and provide a search result to the electronic device based on the final search information.
[0060] Here, when the processor (130) obtains search information, when a content search request is received from an electronic device, it obtains search request data input to the electronic device in response to the content search request, and can obtain search information by extracting it from the search request data.
[0061] For example, the processor (130) can extract a search term from the text if the search request data input to the electronic device is text, and obtain search information corresponding to the search term.
[0062] As another example, the processor (130) can extract text from the image and obtain search information from the text if the search request data input to the electronic device is an image.
[0063] Here, the processor (130) can estimate the similarity between the extracted texts and the objects included in the image among the multiple texts, select the text with the highest similarity, and obtain search information from the selected text.
[0064] As another example, the processor (130) can convert the sound or voice into text if the search request data input to the electronic device is sound or voice, extract a search term from the text, and obtain search information corresponding to the search term.
[0065] Additionally, when requesting additional necessary information, the processor (130) performs a content search based on search information to provide an initial search result to the electronic device, generates additional necessary information to specify final search information based on the initial search result, and can request additional necessary information from the electronic device.
[0066] For example, after providing an initial search result, the processor (130) checks whether the amount of content information corresponding to the initial search result is greater than or equal to a preset standard amount of information, and if the amount of content information corresponding to the initial search result is greater than or equal to the standard amount of information, it can generate additional necessary information. The reason for this is that if the amount of content information corresponding to the initial search result is too large, inaccurate content information may also be included, so additional necessary information for the search is generated to extract only content information with high reliability and accuracy.
[0067] Here, the processor (130) may not generate additional necessary information if the amount of content information corresponding to the initial search result is less than the standard amount of information.
[0068] Additionally, the processor (130) can identify at least one of a content genre, an actor, and a synopsis corresponding to the initial search result after providing the initial search result, select a search category for classifying the content genre, and generate additional necessary information based on the selected search category.
[0069] Here, when selecting a search category, the processor (130) can extract the user's search history for at least one of the content genre, actor, and synopsis corresponding to the initial search result, and select a search category for classifying at least one of the content genre, actor, and synopsis based on the user's search history.
[0070] In some cases, when selecting a search category, the processor (130) checks whether a corresponding subcategory exists if the selected search category is a top category, and if a subcategory exists, it can select a search category including the top category and its subcategory.
[0071] Additionally, the processor (130) can request additional necessary information by creating a search category in the form of a main search icon if the additional necessary information is a search category, and providing a main search icon to an electronic device so that the main search icon corresponding to the search category is displayed on the initial search result.
[0072] Here, when a user input selecting a main search icon corresponding to a search category is received from an electronic device, the processor (130) checks whether there is a subcategory corresponding to the selected search icon, and if there is a subcategory, creates a sub search icon corresponding to the subcategory and provides the sub search icon to the electronic device so that the sub search icon is displayed by matching it to the main search icon, thereby requesting additional necessary information.
[0073] In some cases, when a user input selecting a sub-search icon is received from an electronic device, the processor (130) creates a user search weight input field for each item included in the sub-category of the selected sub-search icon, provides the items included in the sub-category and the user search weight input field for each item to the electronic device, and may request additional necessary information including the user search weight entered through the search weight input field.
[0074] For example, the processor (130) may recognize that if the user’s search weight entered through the search weight input field is at a high level, the accuracy known by the user for items in a subcategory corresponding to the high level is at a high level; if the user’s search weight is at a middle level, the accuracy known by the user for items in a subcategory corresponding to the middle level is at a middle level; and if the user’s search weight is at a low level, the accuracy known by the user for items in a subcategory corresponding to the low level is at a low level.
[0075] Additionally, the processor (130) can request additional necessary information by creating a search category in the form of a speech bubble if the additional necessary information is a search category, and providing the speech bubble to an electronic device so that a speech bubble corresponding to the search category is displayed on the initial search result.
[0076] Here, when a user's response regarding additional necessary information is received from an electronic device, the processor (130) performs a content search based on the user's response to generate a search result, and if the final search information is not determined based on the search result, it can generate additional necessary information in the form of a speech bubble to determine the final search information and provide it to the electronic device.
[0077] For example, the processor (130) may determine the final search information if the amount of information for the search result is greater than or equal to a preset reference amount of information, and determine the final search information if the amount of information for the search result is less than a preset reference amount of information.
[0078] And, when determining the final search information, the processor (130) performs a content search based on the user's additional information to generate a search result, and if the amount of information for the search result is greater than or equal to a preset standard amount of information, it generates additional necessary information based on the search result and requests more from the electronic device, and if it obtains additional information from the electronic device that corresponds to the additional necessary information, it can determine the final search information based on the additional information.
[0079] For example, when the processor (130) provides search results based on final search information, it may include at least one of the main information for the final searched content, a thumbnail of the final searched content, a replay video, and a preview video.
[0080] Additionally, when providing search results based on final search information, the processor (130) inputs the final search information into a pre-trained search model to obtain search results containing content that the user wants to search for, and can provide the search results to an electronic device.
[0081] Here, the processor (130) can obtain content information classified by category when training a search model, obtain metadata of the content corresponding to the content information and store it in a database (120), train the search model based on the content and metadata to obtain a training result, and retrain the search model based on the training result to update the search model.
[0082] In some cases, when a user input selecting specific content from search results is received from an electronic device, the processor (130) can analyze the relationship between the composition of the selected content and the final search information, and update the search model by retraining the search model based on the relationship.
[0083] Here, the processor (130), when analyzing the relationship between the composition of the selected content and the final search information, can obtain at least one search category corresponding to the selected content, obtain at least one search term included in the final search information, match the search category of the content with the search term of the final search information, and analyze the relationship between the composition of the selected content and the final search information based on the matching result.
[0084] In addition, a search model including the aforementioned neural network model may be a deep neural network. Throughout this specification, neural network, network function, and neural network may be used interchangeably. A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. Using a deep neural network allows for the identification of latent structures of data. That is, it is possible to identify the latent structures of photos, text, videos, voice, and music (e.g., what objects are in a photo, what the content and emotions of the text are, what the content and emotions of the voice are, etc.). A deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, and the like.
[0085] Convolutional Neural Networks (CNNs) are a type of deep neural network that includes neural networks containing convolutional layers. Convolutional Neural Networks are a type of multilayer perceptron designed to use minimal preprocessing. A CNN can consist of one or more convolutional layers and artificial neural network layers combined with them. CNNs can additionally utilize weights and pooling layers. Thanks to this structure, CNNs can fully utilize input data with a two-dimensional structure. Convolutional Neural Networks can be used to recognize objects in images. Convolutional Neural Networks can process image data by representing it as a matrix with dimensions. For example, in the case of RGB (red-green-blue) encoded image data, it can be represented as a two-dimensional matrix for each of the R, G, and B colors (e.g., in the case of a two-dimensional image). That is, the color value of each pixel in the image data can be an element of the matrix, and the size of the matrix can be equal to the size of the image. Therefore, image data can be represented as three 2-dimensional matrices (a 3-dimensional data array).
[0086] In a convolutional neural network, the convolutional process (input / output of the convolutional layer) can be performed by moving the convolutional filter and multiplying the matrix components of the convolutional filter at each location in the image. The convolutional filter can be composed of an n*n matrix. Generally, the convolutional filter can be composed of a fixed-size filter smaller than the total number of pixels in the image. That is, when an m*m image is input into a convolutional layer (for example, a convolutional layer with an n*n size convolutional filter), a matrix representing n*n pixels containing each pixel of the image can be multiplied by the convolutional filter and its components (i.e., multiplying the matrix components). Through this multiplication with the convolutional filter, components matching the convolutional filter can be extracted from the image. For example, a 3x3 convolutional filter for extracting vertical linear components from an image can be constructed as [[0,1,0], [0,1,0], [0,1,0]]. When a 3x3 convolutional filter for extracting vertical linear components is applied to an input image, vertical linear components matching the convolutional filter can be extracted and output from the image. A convolutional layer can apply the convolutional filter to each matrix for each channel representing the image (i.e., R, G, B colors in the case of an R, G, B coded image). A convolutional layer can extract features matching the convolutional filter from the input image by applying the convolutional filter to the input image. The filter values of the convolutional filter (i.e., the values of each component of the matrix) can be updated by backpropagation during the training process of the convolutional neural network.
[0087] A subsampling layer may be connected to the output of a convolutional layer to simplify the output of the convolutional layer, thereby reducing memory usage and computational load. For example, when the output of a convolutional layer is input to a pooling layer having a 2x2 max pooling filter, the image can be compressed by outputting the maximum value contained in each patch for every 2x2 patch from each pixel of the image. The aforementioned pooling may be a method of outputting the minimum value from a patch or the average value of a patch, and any pooling method may be included in the present invention.
[0088] A convolutional neural network may include one or more convolutional layers and subsampling layers. A convolutional neural network can extract features from an image by repeatedly performing convolutional processes and subsampling processes (e.g., the aforementioned max pooling). Through repeated convolutional and subsampling processes, the neural network can extract global features of the image.
[0089] The output of a convolutional layer or a subsampling layer can be input to a fully connected layer. A fully connected layer is a layer where every neuron in one layer is connected to every neuron in an adjacent layer. In a neural network, a fully connected layer can refer to a structure where every node in each layer is connected to every node in another layer.
[0090] FIG. 3 is a drawing for explaining an electronic device that communicates with a server according to one embodiment.
[0091] As illustrated in FIG. 3, the electronic device (200) may include a communication unit (210) that communicates with a server, a display unit (220) that displays search results for content provided from the server, and a control unit (230) that controls the communication unit (210) and the display unit (220).
[0092] Here, the communication unit (210) may include a wireless internet module, a short-range communication module, a location information module, etc.
[0093] And, the display unit (220) can output information of any form generated or determined by the control unit (230) and information of any form received by the communication unit (210).
[0094] For example, the display unit (220) may include at least one of a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, and a 3D display. Some of these display modules may be configured to be transparent or light-transmitting so that the outside can be seen through them. This may be referred to as a transparent display module, and representative examples of transparent display modules include TOLED (Transparent OLED).
[0095] Additionally, an input unit for receiving user input may be further included, and the input unit may have keys and / or buttons on a user interface for receiving user input, or physical keys and / or buttons. A computer program according to embodiments of the present disclosure may be executed in accordance with user input through the input unit.
[0096] In addition, the input unit may receive a signal by detecting the user's button operation or touch input, or receive the voice or movements of the user, etc., through a camera or microphone and convert them into an input signal. For this purpose, speech recognition technology or motion recognition technology may be used.
[0097] Additionally, the input unit may be implemented as an external input device connected to an electronic device. For example, the input device may be at least one of a touch pad, a touch pen, a keyboard, or a mouse for receiving user input, but this is merely an example and is not limited thereto.
[0098] For example, the input unit may recognize user touch input. In some cases, the input unit may have the same configuration as the output unit. The input unit may be composed of a touch screen implemented to receive user selection input. The touch screen may use any one of the following methods: contact capacitance method, infrared light detection method, surface ultrasonic (SAW) method, piezoelectric method, or resistive method. The detailed description of the touch screen described above is merely an example according to one embodiment of the present disclosure, and various touch screen panels may be employed in the platform server (100). The input unit composed of a touch screen may include a touch sensor. The touch sensor may be configured to convert changes such as pressure applied to a specific part of the input unit or capacitance occurring in a specific part of the input unit into an electrical input signal. The touch sensor may be configured to detect not only the location and area of the touch but also the pressure at the time of touch. When there is a touch input to the touch sensor, the corresponding signal(s) are sent to a touch controller. The touch controller may process the signal(s) and then transmit the corresponding data to a processor. Thus, the processor can recognize whether or not a specific area of the input part has been touched.
[0099] Meanwhile, the control unit (230) may be composed of one or more cores and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU) of a computing device.
[0100] Here, the control unit (230) controls the communication unit (210) to transmit a content search request including search request data to the server when search request data for a content search request is input, controls the display unit (220) to display a user response input window corresponding to the additional necessary information request when an additional necessary information request is received from the server, controls the communication unit (210) to transmit additional user information input through the user response input window to the server, and controls the display unit (220) to display the final search result for the content search when a final search result corresponding to the additional information is received from the server.
[0101] The control unit (230) can control the communication unit (210) to transmit the content search request along with the search request data to the server when user input is received in which the search request data and the content search request are input.
[0102] For example, search request data may be at least one of text, image, sound, and voice.
[0103] And the control unit (230) can control the display unit (220) to display the first search result when it receives the first search result corresponding to the search request data from the server.
[0104] Next, the control unit (230) can control the display unit (220) to display a user response input window corresponding to the additional required information request when it receives an additional required information request from the server.
[0105] Here, the user response input window may include a main search icon corresponding to the search category above the initial search result if additional required information is a search category.
[0106] At this time, when the control unit (230) receives user input selecting a main search icon corresponding to a search category, it checks whether there is a sub-category corresponding to the selected search icon, and if there is a sub-category, it can control the display unit (220) so that a sub-search icon corresponding to the sub-category is matched to the main search icon and displayed.
[0107] Additionally, the control unit (230) can control the display unit (220) to display the user's search weight input field for each item included in the sub-category of the selected sub-search icon when a user input selecting a sub-search icon is received.
[0108] Here, the control unit (230) can control the communication unit (210) to transmit the user's search weight to the server when user input is received in the search weight input field.
[0109] For example, the control unit (230) can transmit the user's search weight entered at the upper level to the server when the user enters an upper level in the search weight input field, transmit the user's search weight entered at the middle level to the server when the user enters a middle level in the search weight input field, and transmit the user's search weight entered at the lower level to the server when the user enters a lower level in the search weight input field.
[0110] In some cases, the user response input window may include a speech bubble corresponding to the search category above the initial search result if additional information required is a search category.
[0111] At this time, the control unit (230) can control the display unit (220) to display a speech bubble containing text requesting additional necessary information corresponding to the search category.
[0112] Next, the control unit (230) can control the display unit (220) to display a speech bubble containing text for the user's response when a user's response corresponding to a speech bubble containing text requesting additional necessary information is input, and can control the communication unit (210) to transmit text data for the user's response to a server.
[0113] Next, the control unit (230) can control the display unit (220) to display a search result including at least one of the main information for the final searched content, a thumbnail of the final searched content, a replay video, and a preview video when it receives a search result from the server.
[0114] FIG. 4 is a diagram illustrating a database of a server according to one embodiment.
[0115] As illustrated in FIG. 4, the database (120) of the server can store search information for content search by category.
[0116] For example, the database (120) may include multiple sub-databases that store search information for content search by top category.
[0117] Here, each sub-database may include multiple sub-categories included in the parent category.
[0118] For example, the first sub-database (122) is a database containing poster-related search categories and may include sub-categories including poster background colors, backgrounds, text, etc.
[0119] The second sub-database (124) is a database that includes search categories related to BGM (Back Ground Music), and may include sub-categories such as music genre, instrument sound, vocal gender, tempo, etc.
[0120] The third sub-database (126) is a database containing person-related search categories and may include sub-categories including race, skin color, eye color, hair color, language used, accessories worn, and other characteristics.
[0121] The fourth sub-database (128) is a database containing synopsis-related search categories and may include sub-categories such as character names, actor names, regions, eras, plots, etc.
[0122] The fifth sub-database (129) is a database containing scene-related search categories and may include sub-categories such as mountains, water, deserts, seas, lakes, cities, etc.
[0123] The above sub-database is merely an example, and the server may request additional necessary information required for the final search information from an electronic device based on various search categories stored in the database.
[0124] FIG. 5 is a diagram illustrating the process of providing a content search service according to one embodiment.
[0125] As illustrated in FIG. 5, when a user’s search information (300) including text, images, sounds, and voice, etc., and a content search request are input, the electronic device (200) can transmit the content search request along with the search information (300) to the server (100).
[0126] And the server (100) can perform a content search by extracting a search term from the text if the search information (300) received from the electronic device (100) is text, perform a content search by extracting text from the image if the search information (300) is an image, and perform a content search by converting the sound or voice into text if the search information (300) is sound or voice.
[0127] For example, the server (100) can extract a search term from the text if the search request data input to the electronic device (200) is text, and obtain search information corresponding to the search term.
[0128] As another example, the server (100) can extract text from the image and obtain search information from the text if the search request data input to the electronic device (200) is an image.
[0129] Here, if there are multiple extracted texts, the server (100) estimates the similarity between the multiple texts and the objects included in the image, selects the text with the highest similarity, and obtains search information from the selected text.
[0130] As another example, the server (100) can convert the sound or voice into text if the search request data input to the electronic device (200) is sound or voice, extract a search term from the text, and obtain search information corresponding to the search term.
[0131] Next, the server (100) performs a content search based on search information and provides the initial search result to the electronic device (200), generates additional necessary information to determine the final search information based on the initial search result, and can request the additional necessary information from the electronic device (200).
[0132] Next, when the electronic device (200) receives a request for additional necessary information from the server (100), it can display a user response input window corresponding to the request for additional necessary information.
[0133] Here, the user response input window may include a main search icon corresponding to the search category above the initial search result if additional required information is a search category.
[0134] In some cases, the user response input window may include a speech bubble corresponding to the search category above the initial search result if additional information required is a search category.
[0135] And, the electronic device (200) can transmit additional information about the user's response to the server when the user's response corresponding to additional required information is input.
[0136] Next, the server (100) performs a content search based on additional user information to generate a search result, and if the amount of information in the search result is greater than or equal to a preset standard amount of information, it generates additional necessary information based on the search result and requests it from the electronic device (200), and if it obtains additional user information corresponding to the additional necessary information from the electronic device (200), it can determine the final search information based on the additional information.
[0137] Next, when the electronic device (200) receives a search result from the server (100), it can display final search information including main information about the final searched content and at least one of a thumbnail, a replay video, and a preview video of the final searched content.
[0138] FIGS. 6a to 6c are drawings for explaining the process of obtaining additional information to determine final search information according to one embodiment.
[0139] As illustrated in FIG. 6a, when a server receives a content search request from an electronic device, it acquires search request data (410) that is entered into an input field of the display screen (400) of the electronic device in response to the content search request, extracts search information from the search request data (410), and performs a content search based on the search information to provide an initial search result (420) to the electronic device.
[0140] For example, if there are multiple search details, the server can search for content classified into search categories related to the multiple details and provide information on the multiple related content.
[0141] Next, the server can generate additional necessary information to determine the final search information based on the initial search result (420) and request additional necessary information from the electronic device.
[0142] For example, after providing the initial search result (420), the server checks whether the amount of content information corresponding to the initial search result (420) is greater than or equal to a preset standard amount of information, and if the amount of content information corresponding to the initial search result (420) is greater than or equal to the standard amount of information, it can generate additional necessary information.
[0143] The reason for this is that if the amount of content information corresponding to the initial search results is too large, inaccurate content information may be included; therefore, the purpose is to generate additional necessary information for the search to extract only content information with high reliability and accuracy.
[0144] Here, the server may not generate additional necessary information if the amount of content information corresponding to the initial search result (420) is less than the standard amount of information.
[0145] After providing the initial search result (420), the server can identify the content genre corresponding to the initial search result (420), select a search category for classifying the content genre, and generate additional necessary information based on the selected search category.
[0146] Here, when selecting a search category, the server can extract the user's search history for content genres corresponding to the initial search result and select a search category to classify content genres based on the user's search history.
[0147] In some cases, when selecting a search category, the server checks whether a corresponding subcategory exists if the selected search category is a parent category, and if a subcategory exists, it can select a search category including the parent category and its subcategories.
[0148] As illustrated in FIG. 6b, the server can request additional necessary information by creating a search category in the form of a main search icon if the additional necessary information is a search category, and providing the main search icon (430) to an electronic device so that the main search icon (430) corresponding to the search category is displayed on the initial search result (420).
[0149] Here, when a user input selecting a main search icon (430) corresponding to a search category is received from an electronic device, the server checks whether there is a subcategory corresponding to the selected main search icon (430), and if there is a subcategory, generates a sub search icon (440) corresponding to the subcategory and provides the sub search icon (440) to the electronic device so that the sub search icon (440) is displayed by matching it to the main search icon (430), thereby requesting additional necessary information.
[0150] Next, as illustrated in FIG. 6c, when a user input selecting a sub-search icon (440) is received from an electronic device, the server creates a user search weight input field (460) for each item (450) included in the sub-category of the selected sub-search icon (440), provides the items (450) included in the sub-category and the user search weight input field (460) for each item (450) to the electronic device, and may request additional necessary information including the user search weight entered through the search weight input field (460).
[0151] For example, the server may recognize that if the user’s search weight entered through the search weight input field (460) is at a high level, the accuracy known by the user for the subcategory item (450) corresponding to the high level is at a high level; if the user’s search weight is at a middle level, the accuracy known by the user for the subcategory item (450) corresponding to the middle level is at a middle level; and if the user’s search weight is at a low level, the accuracy known by the user for the subcategory item (450) corresponding to the low level is at a low level.
[0152] For example, referring to Fig. 6c, if search weights are set such that AAA is at the upper level and BBB is at the middle level in the subcategories of characters, the server can provide search results with priority given to content featuring AAA over content featuring BBB. Since user feedback information is reflected in the search weights, the server can provide search results that match the user's intent.
[0153] FIG. 7 is a diagram illustrating the process of obtaining additional information to determine final search information according to another embodiment.
[0154] As illustrated in FIG. 7, when a server receives a content search request from an electronic device, it acquires search request data (410) that is entered into an input field of the display screen (400) of the electronic device in response to the content search request, extracts search information from the search request data (410), and performs a content search based on the search information to provide the initial search result to the electronic device.
[0155] Next, if the additional required information is a search category, the server can create a search category in the form of a speech bubble and request additional required information by providing the speech bubble (510) to an electronic device so that a speech bubble (510) corresponding to the search category is displayed on the initial search result.
[0156] Here, when the server receives a user's response (520) regarding additional necessary information from the electronic device, it performs a content search based on the user's response (520) to generate a search result, and if the final search information is not determined based on the search result, it can generate additional necessary information in the form of a speech bubble to determine the final search information and provide it to the electronic device.
[0157] For example, if the amount of information regarding the search results is greater than or equal to a preset threshold amount of information, the final search information may not be determined, and if the amount of information regarding the search results is less than a preset threshold amount of information, the final search information may be determined.
[0158] And, when determining the final search information, the server performs a content search based on the user's additional information to generate a search result (530), and if the amount of information for the search result (530) is greater than or equal to a preset standard amount of information, it generates additional necessary information based on the search result (530) and requests more from the electronic device, and if it obtains additional user information corresponding to the additional necessary information from the electronic device, it can determine the final search information based on the additional information.
[0159] Above, the server has described the request for additional necessary information in the form of a speech bubble (510), but it is not limited to this and can request additional necessary information in various interactive forms.
[0160] FIG. 8 is a diagram illustrating the process of generating search results using a search model according to one embodiment.
[0161] As illustrated in Fig. 8, the server can pre-train a neural network model for content retrieval and store it in a database.
[0162] Here, when the server determines the final search information, it inputs the final search information into a pre-trained search model (700) to obtain a search result containing the content that the user wants to search for.
[0163] The server can acquire metadata of content selected by the user, train a search model based on the content metadata to obtain training results, and retrain the search model based on the training results to update the search model.
[0164] In addition, the server may update the search model by retraining it based on the association between specific content selected by the user from the provided search results and the final search information.
[0165] FIGS. 9 and FIGS. 10 are drawings for illustrating the search model retraining and update process according to one embodiment.
[0166] As illustrated in FIG. 9, first, the server can obtain content (612) classified by category (614) (620).
[0167] Next, the server can obtain metadata of the content corresponding to the content (612) and store it in the database (630).
[0168] Next, the server can obtain a learning result by training a search model based on content and metadata (640).
[0169] And, the server can update the search model by retraining the search model based on the learning results (650).
[0170] Meanwhile, as illustrated in FIG. 10, the server can receive user input from an electronic device to select specific content (612) from the search results.
[0171] Next, the server can analyze the configuration of the search category (614) of the specific content (612).
[0172] Next, the server can analyze the composition of the search terms (665) of the final search information (660).
[0173] And, the server can analyze the relationship between the category (614) configuration of specific content (612) and the search term (665) of the final search information (660), and update the search model (700) by retraining the search model based on the relationship.
[0174] For example, the server may obtain at least one search category (614) corresponding to the specific content (612) finally selected by the user, obtain at least one search term (665) included in the final search information (660), match the search category (614) of the specific content (612) with the search term (665) of the final search information (660), and analyze the relationship between the composition of the selected specific content (612) and the final search information based on the matching result.
[0175] FIG. 11 is a drawing for explaining the process of displaying search results according to one embodiment.
[0176] As illustrated in FIG. 11, when the electronic device receives a search result from a server, it can display on a display screen the final search information (800) which includes at least one of the main information for the final searched content, a thumbnail (810) of the final searched content, a replay video, and a preview video.
[0177] In some cases, the server may display final search information (800) that further includes the user's search request information (660) on the display screen.
[0178] FIG. 12 is a flowchart illustrating a method for providing a content search service of a server according to one embodiment.
[0179] As illustrated in FIG. 12, the server can obtain search information for searching at least one content from an electronic device (S110).
[0180] Here, when a content search request is received from an electronic device, the server obtains search request data input into the electronic device in response to the content search request, and can extract and obtain search information from the search request data.
[0181] Next, the server can generate additional necessary information based on the search information and request it from the electronic device (S120).
[0182] Here, the server performs a content search based on search information and provides the initial search result to the electronic device, generates additional necessary information to determine the final search information based on the initial search result, and may request the additional necessary information from the electronic device.
[0183] At this time, after providing the initial search result, the server identifies at least one of the content genre, actor, and synopsis corresponding to the initial search result, selects a search category for classifying at least one of the content genre, actor, and synopsis, and can generate additional necessary information based on the selected search category.
[0184] Next, the server can obtain additional user information corresponding to additional required information from the electronic device (S130).
[0185] And, the server can determine the final search information based on additional information (S140).
[0186] Next, the server can provide search results to an electronic device based on the final search information (S150).
[0187] Here, the server inputs the final search information into a pre-trained search model to obtain a search result containing the content that the user wants to search for, and can provide the search result to an electronic device.
[0188] In this way, the server can provide optimal search results with high accuracy and reliability to a user requesting a content search by utilizing final search information determined based on additional user information.
[0189] In addition, the server can provide optimal search results to the user by retraining and updating the content search model based on the content finally selected by the user from the search results and the final search information used in the search results.
[0190] FIG. 13 is a flowchart illustrating a method for displaying a content search service of an electronic device that communicates with a server, according to one embodiment.
[0191] As illustrated in FIG. 13, the electronic device can receive search request data for a content search request from a user (S210).
[0192] Next, the electronic device can transmit a content search request containing search request data to a server (S220).
[0193] Here, when the electronic device receives user input in which search request data and a content search request are entered, it can transmit the content search request along with the search request data to the server.
[0194] For example, search request data may be at least one of text, image, sound, and voice.
[0195] Next, the electronic device receives a request for additional necessary information from the server and can display a user response input window corresponding to the request for additional necessary information (S230).
[0196] Next, the electronic device can transmit additional user information entered through the user response input window to the server (S240).
[0197] Here, the electronic device can display the initial search result when it receives the initial search result corresponding to the search request data from the server, and can display a user response input window corresponding to the additional necessary information request when it receives a request for additional necessary information from the server.
[0198] For example, if additional information is needed in a search category, the user response input window may include a main search icon corresponding to the search category above the initial search result.
[0199] At this time, when the electronic device receives user input selecting a main search icon corresponding to a search category, it checks whether a subcategory corresponding to the selected search icon exists, and if a subcategory exists, it can display a sub-search icon corresponding to the subcategory by matching it to the main search icon.
[0200] Additionally, when the electronic device receives user input selecting a sub-search icon, it can display a user search weight input field for each item included in the sub-category of the selected sub-search icon.
[0201] Here, the electronic device can transmit the user's search weight to the server when user input is received in the search weight input field.
[0202] For example, an electronic device can transmit the user's search weight entered at the upper level to the server when the user enters an upper level in the search weight input field, transmit the user's search weight entered at the middle level to the server when the user enters a middle level in the search weight input field, and transmit the user's search weight entered at the lower level to the server when the user enters a lower level in the search weight input field.
[0203] In some cases, the user response input window may include a speech bubble corresponding to the search category above the initial search result if additional information required is a search category.
[0204] At this time, the electronic device may display a speech bubble containing text requesting additional necessary information corresponding to the search category.
[0205] Subsequently, when a user's response corresponding to a speech bubble containing text requesting additional necessary information is entered, the electronic device can display a speech bubble containing text regarding the user's response and transmit text data regarding the user's response to a server.
[0206] Next, the electronic device can receive a final search result corresponding to additional information from the server (S250).
[0207] And, the electronic device can display the final search result for the content search (S260).
[0208] Here, when the electronic device receives search results from a server, it may display search results including main information about the final searched content and at least one of a thumbnail, a replay video, and a preview video of the final searched content.
[0209] In this way, the present disclosure can provide optimal search results with high accuracy and reliability to a user requesting a content search by utilizing final search information determined based on additional user information.
[0210] The content search model can be retrained and updated based on the content finally selected by the user from the search results and the final search information used in the search results to provide the user with optimal search results.
[0211] The electronic device and server described in the present disclosure may be implemented as hardware components, software components, and / or a combination of hardware components and software components. Additionally, the present disclosure may be provided in the form of a computer program stored on a computer-readable storage medium to perform a method of operating the electronic device and server. Additionally, the present disclosure may be written as a program executable on a computer and may be implemented on a general-purpose digital computer that operates such a program using a computer-readable storage medium.
[0212] Such computer-readable storage media may be read-only memory (ROM), random-access memory (RAM), flash memory, CD-ROMs, CD-Rs, CD+Rs, CD-RWs, CD+RWs, DVD-ROMs, DVD-Rs, DVD+Rs, DVD-RWs, DVD+RWs, DVD-RAMs, BD-ROMs, BD-Rs, BD-R LTHs, BD-REs, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state disk (SSD), and may be any device capable of storing instructions or software, related data, data files, and data structures, and providing instructions or software, related data, data files, and data structures to a processor or computer so that the processor or computer can execute instructions.
[0213] Although the embodiments have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention as defined in the following claims also fall within the scope of the present invention.
Claims
Claim 1 A server comprising: a communication unit that performs communication with an electronic device; a database that stores search information for content search by category; and a processor that provides search results in response to a content search request from the electronic device, wherein the processor acquires search information for searching at least one content from the electronic device, performs a content search based on the search information and provides an initial search result to the electronic device, and if it is determined to generate additional necessary information to specify final search information based on the initial search result based on the amount of content information corresponding to the initial search result, generates the additional necessary information and requests it from the electronic device, and if additional user information corresponding to the additional necessary information is acquired from the electronic device, determines the final search information based on the additional information, and provides the final search result to the electronic device based on the final search information. Claim 2 A server according to claim 1, wherein the processor, when acquiring the search information, acquires search request data input to the electronic device in correspondence with the content search request when a content search request is received from the electronic device, and extracts and acquires search information from the search request data. Claim 3 A server according to claim 2, wherein the processor extracts a search term from the text and obtains search information corresponding to the search term if the search request data input to the electronic device is text. Claim 4 In claim 2, the processor is characterized by extracting text from an image and obtaining search information from the text if the search request data input to the electronic device is an image. Claim 5 A server according to claim 4, wherein the processor estimates the similarity with objects included in the image among the multiple texts when the extracted texts are multiple, selects the text with the highest similarity, and obtains search information from the selected text. Claim 6 A server according to claim 2, wherein the processor converts the sound or voice into text if the search request data input to the electronic device is sound or voice, extracts a search term from the text, and obtains search information corresponding to the search term. Claim 7 delete Claim 8 A server according to claim 1, wherein the processor, after providing the initial search result, checks whether the amount of content information corresponding to the initial search result is greater than or equal to a preset standard amount of information, and if the amount of content information corresponding to the initial search result is greater than or equal to the standard amount of information, generates the additional necessary information. Claim 9 In claim 8, the server is characterized in that the processor does not generate additional necessary information if the amount of content information corresponding to the initial search result is less than the amount of reference information. Claim 10 A server according to claim 1, wherein the processor identifies at least one of a content genre, an actor, and a synopsis corresponding to the initial search result, selects a search category for classifying at least one of the content genre, an actor, and a synopsis, and generates additional necessary information based on the selected search category. Claim 11 A server according to claim 10, wherein the processor, when selecting the search category, extracts a user's search history for at least one of a content genre, actor, and synopsis corresponding to the initial search result, and selects a search category for classifying at least one of the content genre, actor, and synopsis based on the user's search history. Claim 12 A server according to claim 10, wherein the processor, when selecting the search category, checks whether a corresponding subcategory exists if the selected search category is a higher category, and if the subcategory exists, selects the search category including the higher category and its subcategory. Claim 13 A server according to claim 1, wherein the processor requests the additional necessary information by creating the search category in the form of a main search icon if the additional necessary information is a search category, and providing the main search icon to the electronic device so that the main search icon corresponding to the search category is displayed on the initial search result. Claim 14 A server according to claim 13, wherein the processor, upon receiving user input from the electronic device selecting a main search icon corresponding to the search category, checks whether a subcategory corresponding to the selected search icon exists, and if the subcategory exists, generates a sub search icon corresponding to the subcategory and provides the sub search icon to the electronic device so that the sub search icon is displayed by matching it to the main search icon, thereby requesting the additional necessary information. Claim 15 A server according to claim 14, wherein the processor, when a user input selecting the sub-search icon is received from the electronic device, generates a user search weight input field for each item included in the sub-category of the selected sub-search icon, provides the items included in the sub-category and the user search weight input field for each item to the electronic device to request additional necessary information, and obtains the user search weight input through the search weight input field as additional information of the user. Claim 16 A server according to claim 1, wherein the processor creates the search category in the form of a speech bubble if the additional required information is a search category, and requests the additional required information by providing the speech bubble to the electronic device so that the speech bubble corresponding to the search category is displayed on the initial search result. Claim 17 A server according to claim 16, wherein the processor, when a user’s response regarding additional necessary information is received from the electronic device, performs a content search based on the user’s response to generate a search result, and if the final search information is not determined based on the search result, further generates additional necessary information to determine the final search information in the form of a speech bubble and provides it to the electronic device. Claim 18 A server according to claim 1, wherein the processor, when determining the final search information, performs a content search based on the additional information to generate a search result, and if the amount of information regarding the search result is greater than or equal to a preset standard amount of information, generates additional necessary information based on the search result and requests it further from the electronic device, and if additional user information corresponding to the additional necessary information is obtained from the electronic device, determines the final search information based on the additional information. Claim 19 A server according to claim 1, wherein the processor, when providing search results based on the final search information, includes at least one of main information regarding the final searched content and a thumbnail, a replay video, and a preview video of the final searched content. Claim 20 A server according to claim 1, wherein the processor, when providing a search result based on the final search information, inputs the final search information into a pre-trained search model to obtain a search result including content that the user wishes to search for, and provides the search result to the electronic device. Claim 21 A server according to claim 20, wherein the processor, when training the search model, acquires content information classified by category, acquires metadata of the content corresponding to the content information and stores it in the database, trains the search model based on the content and metadata to obtain a training result, and retrains the search model based on the training result to update the search model. Claim 22 A server according to claim 20, wherein the processor analyzes the relationship between the configuration of the selected content and the final search information when a user input selecting specific content from the search results is received from the electronic device, and updates the search model by retraining the search model based on the relationship. Claim 23 A server according to claim 22, wherein the processor, when analyzing the association between the configuration of the selected content and the final search information, obtains at least one search category corresponding to the selected content, obtains at least one search term included in the final search information, matches the search category of the content with the search term of the final search information, and analyzes the association between the configuration of the selected content and the final search information based on the matching result. Claim 24 A method for providing a content search service of a server, comprising: a step of obtaining search information for searching at least one content from an electronic device; a step of performing a content search based on the search information and providing an initial search result to the electronic device, and, if it is determined to generate additional necessary information to specify a final search information based on the initial search result based on the amount of content information corresponding to the initial search result, generating the additional necessary information and requesting it from the electronic device; a step of obtaining additional user information corresponding to the additional necessary information from the electronic device; a step of determining the final search information based on the additional information; and a step of providing a final search result to the electronic device based on the final search information. Claim 25 A computer program that provides a content search service provision method, which is combined with a computer as hardware and is stored in a medium to perform a content search service provision method of a server, wherein the content search service provision method comprises: a step of obtaining search information for searching at least one content from an electronic device; a step of performing a content search based on the search information and providing an initial search result to the electronic device, and, if it is determined to generate additional necessary information to specify a final search information based on the initial search result based on the amount of content information corresponding to the initial search result, generating the additional necessary information and requesting it from the electronic device; a step of obtaining additional user information corresponding to the additional necessary information from the electronic device; a step of determining the final search information based on the additional information; and a step of providing a final search result to the electronic device based on the final search information. Claim 26 An electronic device comprising: a communication unit that performs communication with a server; a display unit that displays content search results provided by the server; and a control unit that controls the communication unit and the display unit, wherein the control unit controls the communication unit to transmit a content search request including the search request data to the server when search request data for a content search request is input, controls the display unit to display the initial search result when an initial search result corresponding to the content search request is received from the server, and controls the display unit to display a user response input window corresponding to the additional necessary information request when an additional necessary information request is received from the server, wherein the additional necessary information request is a request for additional necessary information to specify final search information based on the initial search result, the generation status of which is determined based on the amount of content information corresponding to the initial search result, and the control unit controls the communication unit to transmit additional user information input through the user response input window to the server, and controls the display unit to display the final search result for the content search when a final search result corresponding to the final search information determined based on the additional information is received from the server. Claim 27 A method for displaying a content search service of an electronic device comprises: receiving search request data for a content search request; transmitting a content search request including the search request data to a server; receiving an initial search result corresponding to the content search request from the server and displaying the initial search result; receiving a request for additional necessary information from the server; displaying a user response input window corresponding to the request for additional necessary information; transmitting additional information of a user entered through the user response input window to the server; receiving a final search result corresponding to final search information determined based on the additional information from the server; and displaying a final search result for the content search, wherein the request for additional necessary information is a request for additional necessary information for specifying final search information based on the initial search result, the generation of which is determined based on the amount of content information corresponding to the initial search result. Claim 28 A computer program that provides a content search service display method, which is combined with a computer as hardware and stored in a medium to perform a content search service display method of an electronic device, wherein the content search service display method comprises: a step of receiving search request data for a content search request; a step of transmitting a content search request including the search request data to a server; a step of receiving an initial search result corresponding to the content search request from the server and displaying the initial search result; a step of receiving a request for additional necessary information from the server; a step of displaying a user response input window corresponding to the request for additional necessary information; a step of transmitting additional information of a user entered through the user response input window to the server; a step of receiving a final search result corresponding to a final search information determined based on the additional information from the server; and a step of displaying a final search result for the content search, wherein the request for additional necessary information is a request for additional necessary information for specifying the final search information based on the initial search result, the generation of which is determined based on the amount of content information corresponding to the initial search result.
Citation Information
Patent Citations
Retrieval system and voice recognition method thereof
KR1020210077573A
Method for providing search service and system for the same
KR1020220004278A
Constructability document search system and method for shipbuilding
KR1020220015228A
Method for providing interactive information service and apparatus therefor
KR102654884B1
