A search method and system based on artificial intelligence

Abstract

The present invention discloses a retrieval method and system based on artificial intelligence, which specifically relates to the technical field of book retrieval, and is used to solve the problem that the retrieval of popular books is relatively cumbersome. The system comprises a display search bar, a processing comparison module, a borrowing module, and a retrieval module. The borrowing module is used to collect user borrowing book information and send it to the processing comparison module and the feedback module. The borrowing module also divides the books by name, establishes a hotspot coefficient through the user borrowing book information and the user retrieval book information received by the processing comparison module, and then divides the books into popular books and ordinary books according to the comparison of the hotspot coefficient and the hotspot threshold, and then analyzes the ranking of the popular books according to the size of the hotspot coefficient of the popular books, and sends the ranking information of the popular books to the hotspot section of the display search bar, so that the popular books are prominently displayed, thereby alleviating the lack of prominent display of the popular books.

Description

Technical Field

[0001] The present invention relates to the technical field of book retrieval, and more specifically, to a retrieval method and system based on artificial intelligence. Background Art

[0002] With the development of computer network technology, the transmission efficiency of information has been improved. The way of obtaining information through retrieval has long become the mainstream, and it is used in various web pages, APPs, AI Q&A, etc. At the same time, it is also gradually widely used on school websites. The main retrieval information includes school enrollment reports, event news, and book borrowing from school libraries. Through artificial intelligence-based retrieval, better services are provided for school teachers and students.

[0003] The existing artificial intelligence-based search retrieves the corresponding books by comparing the book title, classification number and author name with the school book database. However, popular books within the school still need to be searched, which is cumbersome and affects the user's search efficiency. Therefore, a search method and system based on artificial intelligence are proposed. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a retrieval method and system based on artificial intelligence, which solves the problems raised in the above-mentioned background technology by screening and displaying popular books.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an artificial intelligence-based retrieval system, comprising a display search bar, a processing and comparison module, a borrowing module, and a retrieval module;

[0006] The borrowing module is used to collect information about books borrowed by users and send it to the processing and comparison module and the feedback module. The borrowing module also divides the books by name and sends the name information of each book to the book database;

[0007] The retrieval module is used to collect the user's searched book information and send it to the processing comparison module and the feedback module;

[0008] The processing and comparison module calculates the hotspot coefficient according to the user's borrowing book information and the user's search book information, and obtains the popular books and ordinary books according to the comparison of the hotspot coefficient and the hotspot threshold, and sorts the popular books according to the hotspot coefficient and sends them to the display search bar. The processing and comparison module also sends the name of each ordinary book to the feedback module;

[0009] The display search bar includes two sections: a hotspot section and a search bar. The hotspot section is used to receive the ranking information of popular book names. The search bar sends the characters input by the user to the feedback module and displays the ranking information of ordinary and hot books according to the characters input by the user.

[0010] The borrowing module divides the books into m by title, and marks each book title as n, where m is a positive integer, and n={1, 2, 3, ... m}. The processing and comparison module normalizes the user's search book information and the user's borrowed book information to establish a hotspot coefficient, which is expressed as:

[0011] ;

[0012] In the formula, is the hot spot coefficient, , and They are the ratio of book borrowing times to total borrowing times, the ratio of book search times to total search times, and the return rate within the specified time. , and are the ratio of book borrowing times to total borrowing times, the ratio of book search times to total search times, and the weight factor coefficient of return rate within the specified time, and .

[0013] In a preferred embodiment, the processing and comparison module is provided with a hotspot threshold value of the hotspot coefficient, and the hotspot coefficient is compared with the hotspot threshold value. When the hotspot coefficient is greater than or equal to the hotspot threshold value, the processing and comparison module marks it as a popular book, and sorts the hotspot coefficient values ​​of the popular books, and sends the book names with the highest hotspot ranking to the display search bar. When the hotspot coefficient is less than the hotspot threshold value, the processing and comparison module marks it as an ordinary book, and sends the collection of the ordinary book names to the feedback module.

[0014] In a preferred embodiment, the book database is used to receive the titles of various books, and integrate them into a set of titles of various books, and collect a character set of each book title, and send the set of each book title and the character set of each book title to the feedback module; wherein the set of each book title is marked as ZS, and the character set of each book title is marked as SN;

[0015] The feedback module is used to receive the characters input by the user in the display search bar, the set of book titles, the character set of each book title, the set of common book names, the user searched book information and the user borrowed book information, and establish the correlation coefficient between the characters input by the user and the character set of each book title according to the Jaccard similarity formula; the expression is:

[0016] ;

[0017] In the formula, TS is the correlation coefficient, ZF is the character set input by the user, SN is the character set of each book title, It represents the size of the intersection of ZF and SN. It represents the size of the union of ZF and SN;

[0018] The feedback module receives the user search book information and the user borrow book information and obtains the user search common book information and the user borrow common book information according to the set of common book names;

[0019] The feedback module establishes the ranking coefficient of ordinary books based on the information of ordinary books retrieved by users, the information of ordinary books borrowed by users and the relevance coefficient. The expression is: ;

[0020] In the formula, is the ranking coefficient of ordinary books, is the collection of common book titles, and is the number of borrowing and searching of common books per unit time, is the return rate of ordinary books within the specified time, , , and They are the correlation coefficient, the ratio of the number of ordinary book borrowing times to the total number of borrowing times, the ratio of the number of ordinary book searches to the total number of searches, and the weight factor coefficient of the ordinary book return rate within the specified time, and ;

[0021] The feedback module then obtains the ranking coefficient of popular books based on the correlation coefficient, and the expression is:

[0022] ;

[0023] In the formula, is the ranking coefficient of popular books, is the weight factor coefficient of the correlation coefficient, A collection of book titles.

[0024] In a preferred embodiment, the feedback module also sorts the numerical values ​​of the common book ranking coefficients and the popular book ranking coefficients respectively, first putting the common book names at the front, and then sorting the popular book names, and sending the common and popular book names to the display search bar according to the user input characters.

[0025] In a preferred embodiment, the retrieval method comprises the following steps:

[0026] Step S1: Collect user borrowing book information and user search information, send to the processing and comparison module, and obtain the hotspot coefficient;

[0027] Step S2: The processing and comparison module obtains popular books and common books according to the comparison between the hotspot coefficient and the hotspot threshold, first sorts the popular books according to the hotspot coefficient values ​​and sends them to the hotspot section in the display search bar, and then sends the collection of common book names to the feedback module;

[0028] Step S3: the book database collects a set of book titles and a character set of each book title and sends them to the feedback module;

[0029] Step S4: the feedback module obtains a correlation coefficient based on the characters input by the user and the character set of each book title, and then obtains the user searched common book information and the user borrowed common book information by combining the user borrowing information, the user searched information and the set of common book titles;

[0030] Step S5: The feedback module obtains the ranking coefficient of common books and the ranking coefficient of popular books through the correlation coefficient and the information of common books retrieved by users and the information of common books borrowed by users;

[0031] Step S6: The feedback module obtains the ranking of the two types of books according to the numerical values ​​of the common book ranking coefficient and the popular book ranking coefficient, and sends them to the search box in the displayed search bar according to the characters input by the user.

[0032] Technical effects and advantages of the present invention:

[0033] 1. The present invention processes the user borrowing book information and the user searching book information received by the comparison module, establishes a hotspot coefficient, and then divides the hotspot coefficient into hot books and ordinary books according to the comparison between the hotspot coefficient and the hotspot threshold, and then analyzes the ranking of the hot books according to the hotspot coefficient of the hot books, and sends the ranking information of the hot books to the display search bar, so that the hot books are prominently displayed, thereby alleviating the lack of prominent display of the hot books;

[0034] 2. The present invention receives the characters input by the user through the feedback module, the set of book titles, the set of characters of book titles, the set of common book titles, the user searched book information and the user borrowed book information, analyzes and obtains the correlation coefficient, and obtains two types of sorting coefficients through the correlation coefficient and the set of book titles, the set of common book titles, the user searched book information and the user borrowed book information, and integrates the sorting information obtained according to the size of each type of sorting coefficient with the characters input by the user and sends them to the display search bar. Compared with the previous search that sorted the search results by a single hotspot, this has more diversified search results, makes it more convenient for users to search for books, and thus improves the search efficiency of the school library search system. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The module diagram of an artificial intelligence-based retrieval method and system of the present invention is shown in FIG.

[0036] Figure 2 The present invention is a method flow chart of an artificial intelligence-based retrieval method and system. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Example 1 Please refer to Figure 1 As shown, an artificial intelligence-based retrieval system includes a display search bar, a feedback module, a processing and comparison module, a borrowing module, and a retrieval module;

[0039] The borrowing module is used to collect user borrowing book information and send it to the processing comparison module and the feedback module. The user borrowing book information includes the number of book borrowings per unit time, the total number of borrowings per unit time, and the return rate within the specified time, and it is marked as , and ;

[0040] The borrowing module divides the books into m by name, and marks the title of each book as n, where m is a positive integer, and n={1, 2, 3, ...m}. The borrowing module also sends the name information of each book to the book database;

[0041] It should be noted that the unit time can represent a time length of 1 hour, 1 day, 48 hours or a week. There is no limitation on the division of this unit time, but the corresponding unit time is made according to the actual situation. The number of times a book is borrowed indicates the number of times the book is borrowed. The more times a book is borrowed, the more popular the book is in the current unit time. On the contrary, the less popular the book is in the current unit time, the less attractive it is. The total number of borrowings indicates the number of times all books are borrowed. The more total number of borrowings, the better the overall reading environment of the school in the current unit time.

[0042] It should be noted that the specified time refers to the borrowing time set by the user before borrowing, and the return rate within the specified time refers to the ratio of the number of times the user returns the book within the borrowing time set before borrowing to the total number of borrowing times. The greater the return rate within the specified time, the better the management effect of the book. The management effect refers to the probability that the book can be borrowed after retrieval. The better the management effect, the lower the loss rate of the book.

[0043] The retrieval module is used to collect user retrieval book information and send it to the processing comparison module and the feedback module. The user retrieval book information includes the number of book retrievals per unit time and the total number of retrievals, which are marked as and ;

[0044] It should be noted that the unit time is consistent with the unit time of the book borrowing times per unit time collected by the above-mentioned borrowing module. The book search times may indicate the number of times the book has been searched. The more the book search times are, the more popular the book is in the current unit time. The total search times may indicate the number of times all books have been searched. The more the total search times are, the more the school's overall search quantity is in the current unit time.

[0045] The processing and comparison module is used to receive the user borrowing book information collected by the borrowing module and the user searching book information collected by the searching module, analyze and process to obtain the popular book names, and send the popular book names to the display search bar;

[0046] The display search bar includes two sections: a hotspot section and a search box. The hotspot section is used to receive the popular book names sent by the display search bar receiving processing comparison module, so that the current popular books can be clearly focused on during the search. The search box is used to send the characters input by the user to the feedback module. The feedback module then obtains the ranking coefficients of ordinary books and popular books according to the collection of the book titles and the collection of characters of the book titles and the various types of information received, and sends them to the search box.

[0047] It should be noted that both the hotspot section and the search box can be indicated in the display area below, above or next to the search bar, mainly showing popular books and search results, so as to achieve the effect of attracting attention and quick retrieval. There is no limitation on the setting and layout of the hotspot section and the search box, but the corresponding hotspot section and search box are made according to the actual situation;

[0048] The processing and comparison module simultaneously receives the user borrowing book information collected by the borrowing module and the user searching book information collected by the searching module, and performs normalization processing to establish the hotspot coefficient, which is expressed as:

[0049] ;

[0050] In the formula, is the hot spot coefficient, , and are the ratio of book borrowing times to total borrowing times, the ratio of book search times to total search times, and the weight factor coefficient of return rate within the specified time, and , weight factor coefficient , and The specific value of is set by those skilled in the art according to the specific records of actual operation and is not limited here;

[0051] It should be noted that when the hotspot coefficient is larger, it means that the proportion of the number of searches for the book in the total number of searches is larger, the proportion of the number of borrowings of the book in the total number of borrowings is larger, and the return rate within the specified time is also larger, then the book is more popular within the school group and the hotspot is larger;

[0052] The book with a hotspot coefficient greater than or equal to a set threshold is marked as a hot book and sent to a display search bar, including the following steps:

[0053] Get hot spot coefficient After that, the hotspot coefficient is compared with the hotspot threshold set by the processing comparison module. If the hotspot coefficient is greater than or equal to the hotspot threshold, the processing comparison module will mark it as a hot book. If it is smaller than the hotspot threshold, the processing and comparison module will mark it as a normal book;

[0054] It should be noted that popular books refer to books with a high number of borrowing and retrieval times and a high return rate within the school within a unit of time, while ordinary books refer to books with a low number of borrowing and retrieval times and a low return rate within the school within a unit of time.

[0055] The processing comparison module calculates the hotspot coefficient that is greater than or equal to the hotspot threshold For each book, hotspot sorting is performed according to the value of the hotspot coefficient, the books with the highest hotspot sorting are sorted, and the names of the books with the highest hotspot sorting are sent to the display search bar;

[0056] The processing comparison module will also calculate the hotspot coefficient that is less than the hotspot threshold The set of common book titles is labeled as FR and sent to the feedback module;

[0057] It should be noted that the hotspot threshold refers to the hotspot threshold obtained by a series of parameters related to the length of the hotspot section. The range of this hotspot threshold is not limited, but the corresponding hotspot threshold is made according to the actual situation;

[0058] It should be noted that the hotspot ranking refers to the books ranked at the top, which can be the top five or top ten, or the popular books are ranked and then the top ranked books are displayed in the hotspot section. There is no limitation on the hotspot ranking, but the corresponding hotspot ranking is made according to the actual situation;

[0059] It should be noted that after a unit of time, the borrowing module and the retrieval module will collect the user's borrowing book information and the user's retrieval book information again, and send it to the processing and comparison module for hot spot coefficient analysis. According to the hot spot coefficient size, the hot spot ranking is obtained, and the top ranked books are sorted again and sent to the display search bar, thereby replacing the content of the previous version of the hot spot section;

[0060] Embodiment 2 There are still technical problems in the above embodiment 1. When the user enters characters in the displayed search bar, there is still a problem of sorting according to hot spots. There is some irrelevant information fed back, which will also reduce the retrieval efficiency. The following solution is now proposed:

[0061] The book database is used to receive the titles of various books, and integrate them into a set of titles of various books, and collect the character set of the titles of various books, and send the set of titles of various books and the character set of the titles of various books to the feedback module, and mark them as ZS and SN;

[0062] It should be noted that the set of book titles represents the book titles of the books, and the character set of book titles represents the characters contained in the book titles of the books.

[0063] The feedback module is used to receive in real time the characters input by the user in the display search bar, the set of each book title, the character set of each book title, the set of each common book title of the processing and analysis module, and the user searched book information of the retrieval module and the user borrowed book information of the borrowing module, and calculate the correlation coefficient according to the characters input by the user and the character set of each book title, and obtain the user searched common book information and the user borrowed common book information according to the set of each common book title, the user searched book information and the user borrowed book information, and send the common book ranking information and the popular book ranking information obtained by the correlation coefficient, the set of each book title, the user searched common book information and the user borrowed common book information to the search box of the display search bar;

[0064] According to the Jaccard similarity formula, the correlation between the characters input by the user and the character set of each book title is obtained, and the correlation coefficient is established. The expression is:

[0065] ;

[0066] In the formula, TS is the correlation coefficient, ZF is the character set input by the user, It represents the size of the intersection of ZF and SN. It represents the size of the union of ZF and SN;

[0067] It should be noted that in the text similarity calculation, the symbol Represents the intersection operation of sets, symbol Representing the union operation of sets, the character set input by the user and the character set of the book titles in the book database can be represented as vectors in the bag-of-words model, and then the Jaccard similarity score between them is calculated using the above formula. The larger the correlation coefficient TS value is, the more similar the two sets are, and vice versa.

[0068] The feedback module obtains user searched common book information and user borrowed common book information according to the set of common book names received from the processing and analysis module, the user search information from the search module, and the user borrowed information from the borrowing module;

[0069] It should be noted that the information of ordinary book retrieval by users indicates the number of ordinary book retrievals and the total number of retrievals per unit time, and the information of ordinary book borrowing by users indicates the number of ordinary book borrowings and the total number of borrowings per unit time and the return rate of ordinary books within a specified time;

[0070] It should be noted that the feedback module compares the set of common book names with the number of book searches per unit time, the number of book borrowings, and the return rate within a specified time, and selects the number of common book searches per unit time, the number of common book borrowings, and the return rate within a specified time;

[0071] The unit time, the specified time, the total number of borrowing times and the total number of searching times have been introduced in Example 1 and are not limited here.

[0072] The feedback module normalizes the information of common books retrieved by users, the information of common books borrowed by users, and the relevance coefficient, and establishes the common book ranking coefficient, which is expressed as:

[0073] ;

[0074] In the formula, is the ranking coefficient of ordinary books, is the number of ordinary book borrowings per unit time, is the number of ordinary book searches per unit time, is the return rate of ordinary books within the specified time, , , and They are the correlation coefficient, the ratio of the number of ordinary book borrowing times to the total number of borrowing times, the ratio of the number of ordinary book searches to the total number of searches, and the weight factor coefficient of the ordinary book return rate within the specified time, and , weight factor coefficient , , and The specific value of is set by those skilled in the art according to the specific records of actual operation and is not limited here;

[0075] It should be noted that the ranking coefficient of ordinary books It means that after the user inputs characters, the ranking is obtained based on the relevance of the characters with the book title characters in the book database and the popularity of ordinary books. The higher the ranking coefficient of ordinary books, the higher the relevance and popularity of the ordinary books.

[0076] The feedback module then obtains the ranking coefficient of popular books based on the correlation coefficient, and the expression is:

[0077] ;

[0078] In the formula, is the ranking coefficient of popular books, is the weight factor coefficient of the correlation coefficient, the weight factor coefficient The specific value of is set by those skilled in the art according to the specific records of actual operation and is not limited here;

[0079] Among them, TS has been introduced and will not be limited here;

[0080] It should be noted that the titles of popular books are obtained by filtering out the collection of common book titles from the collection of book titles collected from the book database. It can be seen that the collection of book titles includes two categories of books: the collection of popular book titles and the collection of common book titles.

[0081] The feedback module will sort the book names according to the numerical values ​​of the common book sorting coefficients, and send them to the search box of the display search bar according to the characters entered by the user;

[0082] The feedback module also sorts the book names of popular books according to the numerical values ​​of the ranking coefficients and sends them to the search box of the display search bar according to the characters input by the user;

[0083] It should be noted that the feedback module first ranks the names of ordinary books at the front, and then ranks the names of popular books at the back of ordinary book names. This means that even if the ranking coefficient of a popular book is greater than the ranking coefficient of an ordinary book, the popular book name is still ranked after the ordinary book name. For example, if the popular book in the current unit time is "The Three-Body Problem", when the user enters "three", the search box will display ordinary books first and then popular books.

[0084] Romance of the Three Kingdoms

[0085] Sanmao's Wanderings

[0086] The Three Musketeers

[0087] The Three-Body Problem

[0088] "The Three-Body Problem: The Dark Forest"......

[0089] It is possible that the popular book ranking coefficient of "The Three-Body Problem" is greater than the common book ranking coefficient of "The Three Musketeers", but "The Three-Body Problem" is still ranked after "The Three Musketeers";

[0090] Example 3, please refer to Figure 2 As shown, this embodiment provides a search method based on artificial intelligence, and the method includes the following steps:

[0091] Collect user borrowing book information and user search information, send them to the processing and comparison module, and obtain the hotspot coefficient;

[0092] The processing and comparison module obtains popular books and ordinary books according to the comparison between the hotspot coefficient and the hotspot threshold, first sorts the popular books according to the hotspot coefficient values ​​and sends them to the hotspot section in the display search bar, and then sends the collection of the names of ordinary books to the feedback module;

[0093] The book database collects a set of book titles and a character set of book titles and sends them to the feedback module;

[0094] The feedback module obtains a correlation coefficient based on the characters input by the user and the character set of each book title, and then obtains the user searched common book information and the user borrowed common book information by combining the user borrowing information, the user searched information and the set of each common book title;

[0095] The feedback module then obtains the ranking coefficients of ordinary books and popular books through the correlation coefficient and the information of ordinary books retrieved by users and the information of ordinary books borrowed by users;

[0096] The feedback module obtains the ranking of the two types of books according to the numerical values ​​of the ranking coefficients of ordinary books and popular books, and sends the ranking to the search box in the display search bar according to the characters input by the user;

[0097] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0098] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0099] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0100] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0101] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0102] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0104] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0107] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0108] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A search system based on artificial intelligence, characterized in that: Including displaying search bar, processing comparison module, borrowing module, and retrieval module; The borrowing module is used to collect information about books borrowed by users and send it to the processing and comparison module and the feedback module. The borrowing module also divides the books by name and sends the name information of each book to the book database; The retrieval module is used to collect the user's searched book information and send it to the processing comparison module and the feedback module; The processing and comparison module calculates the hotspot coefficient according to the user's borrowing book information and the user's search book information, and obtains the popular books and ordinary books according to the comparison of the hotspot coefficient and the hotspot threshold, and sorts the popular books according to the hotspot coefficient and sends them to the display search bar. The processing and comparison module also sends the name of each ordinary book to the feedback module; The display search bar includes two sections: a hotspot section and a search bar. The hotspot section is used to receive the ranking information of popular book names. The search bar sends the characters input by the user to the feedback module and displays the ranking information of ordinary and hot books according to the characters input by the user. The borrowing module divides the books into m by title, and marks each book title as n, where m is a positive integer, and n={1, 2, 3, ... m}. The processing and comparison module normalizes the user's search book information and the user's borrowed book information to establish a hotspot coefficient, which is expressed as: ； In the formula, is the hot spot coefficient, , , They are the ratio of book borrowing times to total borrowing times, the ratio of book search times to total search times, and the return rate within the specified time. , and are the ratio of book borrowing times to total borrowing times, the ratio of book search times to total search times, and the weight factor coefficient of return rate within the specified time, and .

2. The artificial intelligence-based retrieval system according to claim 1, characterized in that: The processing and comparison module is provided with a hotspot threshold value of the hotspot coefficient, and compares the hotspot coefficient with the hotspot threshold value. When the hotspot coefficient is greater than or equal to the hotspot threshold value, the processing and comparison module marks it as a popular book, and sorts the hotspot coefficient values ​​of the popular books, and sends the names of the books with the highest hotspot ranking to the display search bar. When the hotspot coefficient is less than the hotspot threshold value, the processing and comparison module marks it as an ordinary book, and sends the collection of the names of the ordinary books to the feedback module.

3. The artificial intelligence-based retrieval system according to claim 1, characterized in that: The book database is used to receive the titles of various books, and integrate them into a set of titles of various books, and collect the character set of the titles of various books, and send the set of titles of various books and the character set of the titles of various books to the feedback module; wherein the set of titles of various books is marked as ZS, and the character set of titles of various books is marked as SN; The feedback module is used to receive the characters input by the user in the display search bar, the set of book titles, the character set of each book title, the set of common book names, the user searched book information and the user borrowed book information, and establish the correlation coefficient between the characters input by the user and the character set of each book title according to the Jaccard similarity formula; the expression is: ； In the formula, TS is the correlation coefficient, ZF is the character set input by the user, SN is the character set of each book title, It represents the size of the intersection of ZF and SN. It represents the size of the union of ZF and SN; The feedback module receives the user search book information and the user borrow book information and obtains the user search common book information and the user borrow common book information according to the set of common book names; The feedback module establishes the ranking coefficient of ordinary books based on the information of ordinary books retrieved by users, the information of ordinary books borrowed by users and the relevance coefficient. The expression is: ； In the formula, is the ranking coefficient of common books, FR is the set of common book names, and is the number of borrowing and searching of common books per unit time, is the return rate of ordinary books within the specified time, , , and They are the correlation coefficient, the ratio of the number of ordinary book borrowing times to the total number of borrowing times, the ratio of the number of ordinary book searches to the total number of searches, and the weight factor coefficient of the ordinary book return rate within the specified time, and ; The feedback module then obtains the ranking coefficient of popular books based on the correlation coefficient, and the expression is: ； In the formula, is the ranking coefficient of popular books, is the weight factor coefficient of the correlation coefficient, and ZS is the set of book titles.

4. The artificial intelligence-based retrieval system according to claim 3, characterized in that: The feedback module also sorts the numerical values ​​of the common book ranking coefficients and the popular book ranking coefficients respectively, first putting the common book names at the front, and then sorting the popular book names, and sending the common and popular book names to the display search bar according to the user input characters.

5. A search method based on artificial intelligence, used to implement the search system based on artificial intelligence according to any one of claims 1 to 4, characterized in that: The search method includes the following steps: Step S1: Collect user borrowing book information and user search information, send to the processing and comparison module, and obtain the hotspot coefficient; Step S2: The processing and comparison module obtains popular books and common books according to the comparison between the hotspot coefficient and the hotspot threshold, first sorts the popular books according to the hotspot coefficient values ​​and sends them to the hotspot section in the display search bar, and then sends the collection of common book names to the feedback module; Step S3: the book database collects a set of book titles and a character set of each book title and sends them to the feedback module; Step S4: the feedback module obtains a correlation coefficient based on the characters input by the user and the character set of each book title, and then obtains the user searched common book information and the user borrowed common book information by combining the user borrowing information, the user searched information and the set of common book titles; Step S5: The feedback module obtains the ranking coefficient of common books and the ranking coefficient of popular books through the correlation coefficient and the information of common books retrieved by users and the information of common books borrowed by users; Step S6: The feedback module obtains the ranking of the two types of books according to the numerical values ​​of the common book ranking coefficient and the popular book ranking coefficient, and sends them to the search box in the displayed search bar according to the characters input by the user.

Images