Search keyword recommendation server and method based on artificial intelligence big data analysis

Abstract

This invention provides a search keyword recommendation server utilizing artificial intelligence based on big data analysis. It includes at least one processor and a memory, the memory storing instructions to instruct the at least one processor to perform multiple operations. The multiple operations may include: receiving search keywords from a user terminal; receiving search information from the user terminal or an external server; classifying the received search keywords into at least one category; calculating a search keyword score by combining search keywords classified into at least one category; classifying the received search information into at least one category; calculating a search information score by combining search information classified into at least one category; calculating a learning performance score based on a weighted sum of the calculated search keyword score and the search information score; and adjusting the learner's average learning difficulty as the learner continues learning and feedback is collected based on the calculated learning performance score, thereby calculating an adjusted problem difficulty.

Description

Technical Field

[0001] This invention relates to a search keyword recommendation server and method based on artificial intelligence big data analysis. Specifically, it relates to a search keyword recommendation server and method based on artificial intelligence big data analysis, which analyzes the attributes and information of each search keyword, provides search keywords, and provides the optimal search results based on the search keywords. Background Technology

[0002] In modern society, the accelerated pace of digitalization and the explosive growth of information have led to a rapid increase in demand for technologies that enable users to quickly and accurately find the information they want. The development of the internet and mobile technologies, in particular, has not only made daily life more convenient but has also further emphasized the importance of information retrieval in various fields such as business, education, and research. Therefore, search engine technology has become a key technology connecting users with massive amounts of data.

[0003] However, existing search engines require user input. They provide search results based solely on simple keywords and established algorithms, resulting in results that do not fully match the user's actual intent or prevent users from effectively searching for the information they want.

[0004] For example, existing search engines fail to adequately reflect user behavior patterns, specific job requirements, and the contextual meaning of specific keywords, leading to inefficient information retrieval processes. This not only reduces the accuracy of search results but also negatively impacts the user's search experience. Furthermore, today's users have diverse search needs, ranging from rapidly changing trends and real-time information on specific topics to historical data.

[0005] Therefore, depending on the nature of the information a user wants to obtain through searching, sometimes short-term data is needed, while other times long-term data is required. If existing search engines treat this uniformly, search efficiency will suffer due to their inability to accurately identify user intent.

[0006] To address these issues, the demand for search keyword recommendation systems that combine big data and artificial intelligence (AI) technologies is increasing. Big data encompasses a variety of information, including user behavior data, keywords of interest, search patterns, and social trends, which can be used to more accurately analyze the attributes and meanings of specific keywords. Furthermore, AI technology can analyze and learn from this big data in real time to more accurately predict user intent and provide personalized search keywords and results. In this way, users can receive recommendations for potentially relevant keywords they haven't entered, thereby expanding their search scope and the relevance of their search results.

[0007] Therefore, it is necessary to study search keyword recommendation servers and methods based on artificial intelligence and big data analysis to overcome the limitations of existing search engines and provide a user-centric search experience.

[0008] Existing technical documents

[0009] Patent documents

[0010] Patent Document 1: Domestic Patent Publication No. 10-2024-0162361 Summary of the Invention

[0011] The problem that the invention aims to solve

[0012] The purpose of this invention is to solve the above problems and provide a search keyword recommendation server and method based on artificial intelligence big data analysis.

[0013] Methods for solving problems

[0014] To achieve the above objectives, one aspect of the present invention provides a search keyword recommendation server that utilizes artificial intelligence based on big data analysis.

[0015] A search keyword recommendation server based on artificial intelligence big data analysis includes at least one processor, and the at least one processor includes multiple memory, which may include instructions for storing operations to be performed.

[0016] The multiple operations may include: receiving search keywords from a user terminal; receiving search information from an external server; classifying the received search keywords into at least one category; calculating search keyword scores by combining search keywords classified into at least one category; classifying the received search information into at least one category; calculating search information scores by combining search information classified into at least one category; calculating a recommended search keyword score based on a weighted sum of the calculated search keyword scores and the search information scores; and calculating a reference recommendation score based on the sum of the average and standard deviation of the calculated recommended search keyword scores, and selecting only search keywords with a reference recommendation score or higher to provide as recommended keywords.

[0017] Invention Effects

[0018] When using the search keyword recommendation server and method based on artificial intelligence big data analysis of the present invention, in addition to simple keyword search, search results optimized according to needs and intentions can be easily obtained.

[0019] In addition, another advantage of the present invention is that it can innovatively improve the user experience while enhancing the accuracy and efficiency of information retrieval.

[0020] The effects obtained by the present invention are not limited to those described above. Other effects not mentioned will be clearly understood by those skilled in the art from the following description. Attached Figure Description

[0021] The above and other aspects, features and advantages of certain preferred embodiments of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings.

[0022] Figure 1 This is an example diagram illustrating the operating environment of a search keyword recommendation server based on artificial intelligence big data analysis, as provided in an embodiment of the present invention.

[0023] It should be noted that in the above figures, the same reference numerals are used to denote the same or similar elements, features and structures. Detailed Implementation

[0024] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0025] Descriptions of technical content that is well-known in the field of this invention and not directly related to it will be omitted. This is to more clearly convey the spirit of the invention without making it obscure by omitting unnecessary explanations.

[0026] For the same reason, some parts in the accompanying drawings are exaggerated, omitted, or depicted schematically. Furthermore, the dimensions of each component do not perfectly reflect its actual size. In each drawing, identical or corresponding parts are given the same reference numerals.

[0027] The advantages and features of the present invention, as well as methods of implementing them, will become more apparent from the embodiments described in detail below with reference to the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but can be implemented in various different forms, and these embodiments are provided merely to complete the disclosure of the present invention and to enable those skilled in the art to fully understand the scope of the invention, which is defined only by the scope of the claims. Throughout the specification, the same reference numerals denote the same parts.

[0028] At this point, the individual blocks of the flowchart, and the combinations thereof, form a computer program. It will be understood that it can be executed according to instructions. These computer program instructions can be loaded onto the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus for execution by that processor. The instructions create methods for performing the functions described in the flowchart blocks. These computer program instructions can also be stored in computer-usable or computer-readable memory that instructs the computer or other programmable data processing apparatus to implement the functions in a particular manner, such that the instructions stored in computer-usable or computer-readable memory also produce an article of art including instruction means for performing the functions described in the flowchart blocks. The computer program instructions can also be mounted on a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable data processing apparatus to form a computer-executable process, and instructions to cause the computer or other programmable data processing apparatus to perform that process. Steps for performing the functions described in the flowchart blocks can also be provided.

[0029] Furthermore, each block contains one or more executable files to perform a specific logical function. It may represent a module, segment, or section of code containing instructions. Additionally, in some alternative execution examples, it's important to note that the aforementioned functions may be out of order within the blocks. For example, two consecutively displayed blocks may actually execute substantially simultaneously, or sometimes in reverse order, depending on the functions they perform.

[0030] In this embodiment, the term '~component' refers to a software or hardware component such as an FPGA (Field-Programmable Gate Array) or ASIC (Application-Specific Integrated Circuit), and the '~component' plays a specific role. However, the meaning of '~bu' is not limited to software or hardware. A '~bu' can be configured to reside on an addressable storage medium and can be configured to allow one or more processors to play it. Therefore, as an example, '~bu' refers to components such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within components and 'subcomponents' can be combined into a smaller number of components and 'subcomponents', or further separated into additional components and 'subcomponents'. Furthermore, components and 'components' can be implemented to regenerate one or more CPUs within a device or secure multimedia card.

[0031] In the embodiments of the present invention, examples of specific systems will be used as the main subject. However, the key points claimed in this specification can be applied to other communication systems and services with similar technical backgrounds without significantly departing from the scope disclosed in this specification, and this can be determined by those skilled in the art.

[0032] Figure 1 This is an example diagram of the operating environment of a search keyword recommendation server based on artificial intelligence big data analysis, provided for embodiments of the present invention.

[0033] refer to Figure 1 The search keyword recommendation server (300) based on artificial intelligence big data analysis (hereinafter referred to as 'server (300)') can receive learning performance information through user terminal (30).

[0034] The server (300) can receive and analyze search keywords from the user terminal (30). In addition, the server (300) can receive and analyze search information from external servers, and the external servers can receive search information from at least one external cloud server connected to the server (300) via a wired or wireless network.

[0035] At this time, the user terminal (30) is a desktop computer, laptop, notebook, mobile phone, tablet computer, mobile phone, smart watch, smart glasses, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital recorder, digital audio player, digital video recorder, digital video player, it can be PDA (personal digital assistant), etc.

[0036] Furthermore, wired and wireless network methods can include various communication methods such as Bluetooth, BLE (Bluetooth Low Energy), Near Field Communication (NFC), WLAN, Zigbee, Infrared Data Association (IrDA), WFD (Wi-Fi Direct), UWB (Ultra-Wideband), Ant+, Wi-Fi, and RFID (Radio Frequency Identification). They are not limited to these.

[0037] Here, search keywords can include keyword relevance score, keyword trend index, related keyword generation time, keyword similarity score, recommended keyword click-through rate, keyword usage frequency, search intent prediction accuracy, recommended keyword provision speed, personalized keyword application rate, search keyword range diversity, user recommended keyword selection response time, keyword accuracy score, multilingual keyword support rate, and the number of additional recommended keywords relative to the input keywords.

[0038] Here, search information may include the accuracy of search result data periodic adjustment, the proportion of qualitative / quantitative data in search results, the relevance score within search results, the response speed of data visualization, the accuracy of trend data, the data deduplication rate, the response speed of time-based search results, the response rate of user preference data, the accuracy of personalized data recommendations, the analysis rate based on the region of search data, the user satisfaction score by age group, the response speed of search results, the matching rate with user click data, and the scope of multidimensional data provision, etc.

[0039] Next, the server (300) can calculate the search keyword score by combining the search keywords categorized in each category.

[0040] Next, the server (300) can combine the feedback information categorized into each category to generate a search information score.

[0041] The server (300) can calculate the search keyword recommendation score based on the calculated search keyword score and search information score.

[0042] The reference recommendation score is calculated by summing the mean and standard deviation of the search terms, and only search keywords with a reference recommendation score higher than the calculated reference recommendation score are selected as recommended keywords.

[0043] The method of this invention can be implemented in the form of program commands, which can be executed by various computer means and recorded on a computer-readable medium. The computer-readable medium may contain program instructions, data files, and may contain data structures, etc., alone or in combination. The program instructions recorded on the computer-readable medium may be program instructions specifically designed and configured for this invention, or program instructions known and available to those skilled in the art of computer software.

[0044] Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions may include machine language code (e.g., code generated by a compiler) and high-level language code that can be executed by a computer using an interpreter. The aforementioned hardware device may be configured to operate together with at least one software module to perform the operations of the present invention, and vice versa.

[0045] Furthermore, the above-described methods or apparatus can be implemented individually by combining all or part of their configurations or functions.

[0046] The invention has been described above with reference to its preferred embodiments; however, those skilled in the art should understand that various modifications and variations can be made to the invention without departing from the spirit and scope of the invention as set forth in the following claims.

Claims

1. A search keyword recommendation server based on artificial intelligence big data analysis, wherein, include: At least one processor; and A memory-store instruction that instructs at least one processor to perform multiple operations. The above actions are: The action of receiving search keywords input by the user terminal; The act of receiving search information from an external server; The action of classifying received search keywords into at least one category; The operation involves combining search keywords categorized into at least one of the above categories and calculating the search keyword score; The action of classifying received search information into at least one category; The operation of combining search information classified into at least one of the above categories to obtain a search information score; The operation of calculating the weighted sum of the search keyword score and the search information score to calculate the search keyword recommendation score; and A reference recommendation score is calculated by summing the average and standard deviation of the calculated search keyword recommendation scores. Only search keywords with a reference recommendation score higher than the calculated reference recommendation score are selected and used as recommended keywords.

Images