Big data analysis-based publication royalty prepaid abnormity monitoring method

Abstract

The invention relates to a publication royalty prepaid anomaly monitoring method based on big data analysis, and relates to the field of data processing specially used for administrative, commercial, financial, management, supervision or prediction purposes. The method comprises the steps that an intelligent prediction model is adopted to intelligently predict a prediction numerical value of the total selling number of the set books after issuing according to single associated information corresponding to the set books, the total selling number of all the books issued by an author of the set books within a set time interval before the current moment and all associated information corresponding to all the books; determining whether the publication royalty prepaid provided by the copyright agency is abnormal or not based on the predicted numerical value and a set prepaid percentage range; through the method and the device, aiming at the technical problem that the issuing number of the unissued books is difficult to predict so that the published royalty prepaid is easy to be subjected to false price uplifting, the issuing number of the unissued books can be intelligently predicted by adopting the artificial intelligence model on the basis of big data analysis, so that the technical problem is solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing dedicated to administrative, commercial, financial, management, supervisory or forecasting purposes, and in particular to a method for monitoring abnormalities of publishing royalty advances based on big data analysis. Background Art

[0002] Publishing royalty advance refers to a certain amount of money that the publisher pays to the author of the book as part of the copyright fee before the book is officially published. Publishing royalty advance is an important part of the publishing process. Before publishing a book, the publisher often needs to trade copyrights with the author. In order to ensure the smooth progress of the transaction, the publisher will pay a part of the royalties to the author in advance as a recognition and encouragement of the author's creation. The amount of publishing royalty advance is usually negotiated and determined by both parties based on factors such as the expected value of the book, the author's popularity, and market forecasts. The advantage of doing so is that it can ensure that the author obtains a certain amount of financial security before the book is published, thereby motivating the author to complete the creation better. At the same time, publishing royalty advances also help publishers gain an advantageous position in the fiercely competitive market and attract more outstanding authors to join. Therefore, the publishing royalty advance system is a win-win cooperation relationship for authors and publishers.

[0003] The calculation method of publishing royalty advances may vary depending on factors such as the type of book and the author's popularity. For example, the publisher will assess the value of the book based on market conditions, and then negotiate with the author to determine the amount of the publishing royalty advance. After the book is officially published, the publisher will pay the author the remaining royalties again based on sales and the percentage of royalty distribution agreed upon by both parties. However, it is more common that book authors provide copyrights to copyright agencies for operation due to lack of professionalism or in order to obtain more benefits. In this way, when multiple publishing houses compete for the publishing rights of the same book, it is impossible to accurately determine the sales volume and sales amount after the book is released, and thus it is impossible to determine the specific numerical range of the publishing royalty advance, so there is a possibility that the copyright agency will falsely raise the amount.

[0004] For example, the Chinese invention patent with publication number CN108537595A proposes a music copyright royalty calculation method and calculation system, the method includes a designated track mode and a collective distribution mode, and judges whether the income music copyright track is a designated track; when the income music copyright track is a designated track, it enters the designated track mode, and directly calculates the publishing tax according to the right type; when the income music copyright track is not a designated track, it enters the collective distribution mode, and is included in the collective distribution royalty pool, and all music copyright tracks in the collective distribution royalty pool are rated according to their track attributes, and the collective royalty amount is distributed according to the rating, so as to obtain the royalty of each music copyright track. The royalty calculation method of music copyright can efficiently and objectively calculate the royalty of music copyright. The present invention also provides a music copyright royalty calculation system.

[0005] For example, the Chinese invention patent with publication number CN1292896A proposes a method and system for collecting royalties for the use of copyrighted digital materials on the Internet. In one embodiment, the method for managing the use of digital files begins by establishing a count value for the number of times the digital file is allowed to be copied. In response to a given protocol, a copy of the digital file is then selectively transmitted from the source to the target. Therefore, the source and the target can be set in the same computer, the source is a disk storage device and the target is a reproduction device. Whenever a digital file is transmitted from the source to the target reproduction device, the method records an indication and decrements the count value at each transmission. When the count value reaches a given value, the file is destroyed or otherwise prevented from being transmitted from the source device, and the recorded indication is transmitted to the management server to facilitate the payment of royalties to the content provider.

[0006] It can be seen that the above-mentioned prior art only provides a method for calculating the royalties of various works, but does not provide a method for calculating the advance payment of publishing royalties as part of the royalties of books. Naturally, it is impossible to monitor abnormalities in the malicious quotation behavior of falsely inflated advance payments of publishing royalties provided by copyright agencies that represent books. As a result, current publishers may think that other publishers have already provided higher advance payments of publishing royalties, and they may be easily disrupted and decide to give up the copyright competition for books, or have to provide higher advance payments of publishing royalties, which may cause publishing failure or generate considerable economic losses. Summary of the invention

[0007] In order to solve the technical problems in the related fields, the present invention provides a method for monitoring the abnormalities of publishing royalty advances based on big data analysis. When a current publishing house receives the publishing royalty advances quoted by a competing publishing house for a set published book provided by the copyright agency that represents the set book, on the basis of big data analysis, an artificial intelligence model is used to intelligently predict the total number of sales of the set published book after its release based on the relevant information of the set published book and the distribution data of the author's past books, and a reliable numerical range of publishing royalty advances is calculated, thereby identifying the false and excessively high publishing royalty advances given by the copyright agency, and avoiding the rhythm of competing book copyrights being disrupted by the copyright agency.

[0008] According to the present invention, a method for monitoring abnormalities of publishing royalty advance payments based on big data analysis is provided, the method comprising:

[0009] Receiving the advance payment of publishing royalties for the book set to be published, which is provided by the copyright agency acting as the agent for the book set to the current publisher, from a competing publisher, where the book set is a book that has not yet been published;

[0010] Obtain the number of published pages, price, word count, number of chapters, area of ​​a single page of printed paper, and thickness of a set book as the single copy associated information corresponding to the set book;

[0011] Analyze the total number of copies sold of each book published by the author of the set book within a set time interval before the current moment and the associated information of each book;

[0012] Performing a preset number of multiple learning operations on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, wherein the preset number is positively correlated with the writing years of the author of the set book;

[0013] The intelligent prediction model is used to intelligently predict the predicted value of the total number of sales of the set book after it is released according to the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of sales of each copy corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy associated information corresponding to each book;

[0014] Determine whether the publishing royalty advance provided by the copyright agency to the current publisher is abnormal based on a set book pricing amount, a set predicted value of the total number of book sales after publication, and a set advance percentage range.

[0015] It can be seen that the present invention has at least the following five outstanding substantive features:

[0016] Substantive Feature A: To monitor whether the publishing royalty advances quoted by competing publishers for the set books provided by the copyright agency of the set books to the current publisher are false price increases, and to make intelligent predictions on the total number of sales of the set books after they are released, thereby providing key basic data for monitoring the above-mentioned false price increases;

[0017] Substantive Feature B: A customized intelligent prediction model is used to intelligently predict the total number of sales of a set book after its release. The intelligent prediction model is a deep neural network that has completed multiple learning operations, and the number of learning operations completed by the deep neural network is positively correlated with the writing years of the author of the set book, thereby ensuring the effectiveness and stability of the intelligent prediction results;

[0018] Substantive Feature C: Provides sufficient and comprehensive basic information for intelligent prediction of the total number of sales of a set book after its release, including the number of published pages, price, number of words in a single book, number of chapters, single page area of ​​printed paper, and thickness of the set book as the single-copy related information corresponding to the set book, as well as the total number of sales and the related information corresponding to each book published by the author of the set book within a set time interval before the current moment obtained by using big data analysis nodes, so as to further ensure the effectiveness and stability of the intelligent prediction results;

[0019] Substantive feature D: In each learning operation performed on the deep neural network, the total number of copies sold of a known book by a certain author after its release is used as the output content of the deep neural network, the duration of a set time interval positively associated with the writing years of the certain author, the single copy associated information corresponding to the certain book, the total number of copies sold of each book published by the certain author within a set time interval before the release time of the certain book, and the copy associated information corresponding to each book are used as the input content of the deep neural network to complete this learning operation, thereby ensuring the learning effect of each learning operation performed on the deep neural network;

[0020] Substantive Feature E: Determine whether the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal based on the set book pricing amount, the predicted total number of sales of the set book after release, and the set advance payment percentage range. Specifically, multiply the set book pricing amount by the predicted total number of sales of the set book after release to obtain the predicted sales amount of the set book after release, and multiply the predicted sales amount of the set book after release by the upper limit percentage value and the lower limit percentage value of the set advance payment percentage range to obtain the upper limit advance payment value and the lower limit advance payment value that limit the publishing royalty advance payment value range. When the publishing royalty advance provided by the copyright agency to the current publishing house is outside the publishing royalty advance payment value range, determine that the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal, thereby completing the targeted monitoring of whether the publishing royalty advance quoted by the copyright agency for the set book is a false price increase amount. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0022] Figure 1 The present invention is a technical flow chart of a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis.

[0023] Figure 2 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a first embodiment of the present invention.

[0024] Figure 3 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a second embodiment of the present invention.

[0025] Figure 4 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a third embodiment of the present invention.

[0026] Figure 5 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a fourth embodiment of the present invention.

[0027] Figure 6 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a fifth embodiment of the present invention. DETAILED DESCRIPTION

[0028] like Figure 1 As shown, a technical flow chart of a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to the present invention is given.

[0029] like Figure 1 As shown, each step of the present invention is executed on the current publisher side, and the specific technical process of the present invention is as follows:

[0030] Step 1: The current publishing house receives the publishing royalty advance payment provided by the copyright agency of the book set by the monitoring agent, and the publishing royalty advance payment is the publishing royalty advance payment provided by the copyright agency and given by other publishing houses for the set publishing book;

[0031] Obviously, since the advance payment for publishing royalties is provided by the copyright agency, the current publisher does not know the advance payment for publishing royalties given by other publishers as competitors. The authenticity of this advance payment for publishing royalties is questionable, because the copyright agency has the motive to deliberately raise the advance payment for publishing royalties.

[0032] Therefore, it is necessary to adopt a subsequent intelligent prediction mechanism to predict the total number of books that can be sold after the release. Once the total number of sales can be determined, since the upper and lower percentage values ​​of the set advance payment percentage range are the numerical ranges determined by the industry, the sales amount can be determined based on the total number of sales, and then the reliable numerical range of the publishing royalty advance for the set book can be calculated based on the sales amount and the set advance payment percentage range, so as to verify the authenticity of the publishing royalty advance given by the copyright agency;

[0033] Step 2: Design a customized intelligent prediction model to intelligently predict the total number of sales of a given book after it is released;

[0034] Specifically, the structure customization of the intelligent prediction model lies in the following aspects:

[0035] First: the intelligent prediction model is a deep neural network after completing multiple learning operations, and the deep neural network includes a single input layer, a single output layer and multiple hidden layers;

[0036] Second: the number of times the deep neural network completes learning operations is positively correlated with the writing years of the author of the set book;

[0037] Third: In each learning operation performed on the deep neural network, the total number of copies sold of a certain book known by a certain author after its release is used as the output content of the deep neural network, the duration of a set time interval positively associated with the writing years of the certain author, the single copy associated information corresponding to the certain book, the total number of copies sold corresponding to each book published by the certain author within a set time interval before the release time of the certain book, and the copy associated information corresponding to each book are used as the input content of the deep neural network to complete this learning operation, thereby ensuring the learning effect of each learning operation performed on the deep neural network;

[0038] In this way, the effectiveness and stability of the intelligent prediction results are guaranteed through the multi-layer design of the customized structure of the above intelligent prediction model;

[0039] Step 3: Introduce sufficient and comprehensive basic data to set the intelligent prediction of the total number of books sold after publication;

[0040] For example, the multiple pieces of basic data are the number of published pages, the price, the number of words in a single book, the number of chapters, the area of ​​a single page of printed paper, and the thickness of the set book as the single copy related information corresponding to the set book, and the total number of copies sold corresponding to each book published by the author of the set book within a set time interval before the current moment and the related information corresponding to each book obtained by analyzing the big data analysis node;

[0041] It can be seen that the sufficiency and comprehensiveness of the above-mentioned basic data further ensure the effectiveness and stability of the intelligent prediction results;

[0042] Step 4: The intelligent prediction model customized in the second step is used to intelligently predict the total number of sales of the set book after its release based on the multiple basic data selected in the third step;

[0043] Step 5: Use the total number of sales of the set book obtained by the intelligent prediction in step 4 after its release to determine whether the advance payment of publishing royalties provided by the copyright agency to the current publisher is abnormal;

[0044] Specifically, determining whether the publishing royalty advance provided by the copyright agency to the current publisher is abnormal based on the set book pricing amount, the set predicted value of the total number of sales of the book after publication, and the set advance percentage range;

[0045] More specifically, the set book pricing amount is multiplied by the predicted value of the total number of sales of the set book after issuance to obtain the predicted value of the sales amount of the set book after issuance, and the predicted value of the sales amount of the set book after issuance is respectively multiplied by the upper limit percentage value and the lower limit percentage value of the set advance payment percentage range to obtain the upper limit advance payment value and the lower limit advance payment value that define the publishing royalty advance payment value range. When the publishing royalty advance payment provided by the copyright agency to the current publishing house is outside the publishing royalty advance payment value range, it is determined that the publishing royalty advance payment provided by the copyright agency to the current publishing house is abnormal; when the publishing royalty advance payment provided by the copyright agency to the current publishing house is within the publishing royalty advance payment value range, it is determined that the publishing royalty advance payment provided by the copyright agency to the current publishing house is normal.

[0046] In this way, based on big data analysis, artificial intelligence models are used to conduct targeted monitoring of whether the publishing royalty advances quoted by copyright agencies for set books are false price increases, thereby preventing publishers from being maliciously quoted by copyright agencies and disrupting the rhythm of competition for copyrights.

[0047] The key points of the present invention are: determining whether the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal based on the set book pricing amount, the set predicted value of the total number of book sales after publication, and the set advance payment percentage range, executing an artificial intelligence model with a customized structure for intelligent prediction of the total number of book sales after publication, and targeted screening of multiple basic data that are sufficient and comprehensive for intelligent prediction of the total number of book sales after publication.

[0048] Next, a method for monitoring abnormalities of publishing royalty advance payments based on big data analysis of the present invention will be specifically described in the form of an embodiment.

[0049] First embodiment

[0050] Figure 2 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a first embodiment of the present invention.

[0051] like Figure 2 As shown, the method for monitoring abnormalities of publishing royalty advance payments based on big data analysis includes the following steps:

[0052] Step S21: receiving the publishing royalty advance for the set book provided by the copyright agency of the set book to the current publisher, which is quoted by a competing publisher for the set book, where the set book is a book that has not yet been published;

[0053] For example, the competing publisher is a publisher different from the current publisher, and competes with the current publisher for the publishing rights of the set book. Generally, the publishing royalty advances given by the competing publisher and the current publisher are key information for competing copyrights, which are only held by the copyright agency. The current publisher only knows the bid of the competing publisher, but does not know the specific bid amount of the competing publisher. This creates space for the copyright agency to deliberately raise the publishing royalty advance of the other publisher.

[0054] Step S22: Obtain the number of published pages, price, word count, number of chapters, area of ​​a single page of printed paper, and thickness of the set book as the single copy associated information corresponding to the set book;

[0055] Specifically, different information collection components can be used to respectively obtain the number of published pages, the price, the number of words in a single book, the number of chapters, the area of ​​a single page of printed paper, and the thickness of the book;

[0056] Step S23: analyzing the total number of copies sold of each book published by the author of the set book within the set time interval before the current time and the associated information of each book;

[0057] For example, the total number of copies sold of each book published by the author of the set book within the set time interval before the current moment and the associated information of each copy of each book include: the current moment is 0:00 on December 1, 2024, and the set time interval before the current moment is a time interval from 0:00 on December 1, 2004 to 0:00 on December 1, 2024, which lasts for 20 years;

[0058] Step S24: performing a preset number of multiple learning operations on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, wherein the preset number is positively correlated with the writing years of the author of the set book;

[0059] For example, the preset number is positively correlated with the writing years of the author of the set book, including: the writing years of the author of the set book is 30 years, the preset number is 300 times, the writing years of the author of the set book is 25 years, the preset number is 200 times, the writing years of the author of the set book is 20 years, the preset number is 150 times, and so on;

[0060] Step S25: using the intelligent prediction model to intelligently predict the predicted value of the total number of sales of the set book after it is released according to the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of sales of each copy corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy associated information corresponding to each book;

[0061] Specifically, a programmable logic device may be selected to implement a data processing process of using the intelligent prediction model to intelligently predict the predicted value of the total number of sales of the set book after it is released based on the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of copies sold corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy associated information corresponding to each book;

[0062] Step S26: determining whether the advance payment of publishing royalties provided by the copyright agency to the current publisher is abnormal based on the set book price, the set predicted value of the total number of sales of the book after publication, and the set advance payment percentage range;

[0063] The analyzing the total number of copies sold and the associated information of each book respectively corresponding to each book published by the author of the set book within the set time interval before the current moment includes: using a big data analysis node to analyze the total number of copies sold and the associated information of each book respectively corresponding to each book published by the author of the set book within the set time interval before the current moment;

[0064] Wherein, determining whether the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal based on the set book pricing amount, the predicted value of the total number of sales of the set book after issuance, and the set advance payment percentage range includes: multiplying the set book pricing amount by the predicted value of the total number of sales of the set book after issuance to obtain the predicted value of the sales amount of the set book after issuance, multiplying the predicted value of the sales amount of the set book after issuance by the upper limit percentage value and the lower limit percentage value of the set advance payment percentage range to obtain the upper limit advance payment value and the lower limit advance payment value that limit the publishing royalty advance payment value range, and determining that the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal when the publishing royalty advance provided by the copyright agency to the current publishing house is outside the publishing royalty advance payment value range;

[0065] For example, if a book is printed with 5,000 copies, the price is 30, and the agreed royalty rate is 10%, that is, the royalty is 15,000 yuan, and the publishing royalty advance is generally set at 30% to 100% of the royalty. In other words, for this book, a reliable publishing royalty advance accounts for 3%-10% of the total sales of the book, that is, 4,500-15,000 yuan. Publishing royalty advances beyond this range can be regarded as false quotations of publishing royalty advances given by other publishing houses to the current publishing house by the copyright agency. Once abnormal publishing royalty advances with false quotations are monitored, they can be immediately fed back to the current publishing house to assist the current publishing house in making subsequent quotations to avoid being disrupted by false quotations;

[0066] The intelligent prediction model is used to intelligently predict the predicted value of the total number of sales of the set book after it is released according to the duration of the set time interval, the single copy association information corresponding to the set book, the total number of sales of each copy corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy association information corresponding to each book. The duration of the set time interval is positively correlated with the writing years of the author of the set book;

[0067] And wherein, a preset number of multiple learning operations are performed on the deep neural network to obtain the deep neural network after completing the multiple learning operations, and the deep neural network after completing the multiple learning operations is output as an intelligent prediction model, and the preset number is positively correlated with the writing years of the author of the set book, and also includes: in each learning operation performed on the deep neural network, the total number of sales of a certain book known by a certain author after its release is used as the output content of the deep neural network, and the duration length of the set time interval positively correlated with the writing years of the certain author, the single copy association information corresponding to the certain book, the total number of copies of each copy sold corresponding to each book published by the certain author within the set time interval before the release time of the certain book, and the copy association information corresponding to each book are used as the input content of the deep neural network to complete this learning operation.

[0068] Second embodiment

[0069] Figure 3 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a second embodiment of the present invention.

[0070] like Figure 3 As shown, compared with Figure 2 After determining whether the advance payment of publishing royalties provided by the copyright agency to the current publisher is abnormal based on the set book price, the set predicted value of the total number of sales of the book after publication, and the set advance payment percentage range, that is, after step S26, the method further includes:

[0071] Step S31: when it is determined that the advance payment of publishing royalties provided by the copyright agency to the current publishing house is abnormal, wirelessly sending to the big data server of the current publishing house a network data packet including the advance payment of publishing royalties quoted by the competing publishing house for the set book provided by the copyright agency of the set book to the current publishing house and information on the abnormality of the advance payment of publishing royalties;

[0072] For example, when it is determined that the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal, a network data packet including the publishing royalty advance quoted by a competing publishing house for the set book provided by the copyright agency for the set book to the current publishing house and the abnormal information on the publishing royalty advance is wirelessly sent to the big data server of the current publishing house, including: the network data packet is an IP data packet.

[0073] Third embodiment

[0074] Figure 4 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a third embodiment of the present invention.

[0075] like Figure 4 As shown, compared with Figure 2 After determining whether the advance payment of publishing royalties provided by the copyright agency to the current publisher is abnormal based on the set book price, the set predicted value of the total number of sales of the book after publication, and the set advance payment percentage range, that is, after step S26, the method further includes:

[0076] Step S41: when it is determined that the advance payment of publishing royalties provided by the copyright agency to the current publishing house is normal, wirelessly sending to the big data server of the current publishing house a network data packet including the advance payment of publishing royalties quoted by the competing publishing house for the set book provided by the copyright agency acting as the agent to the current publishing house and normal information of the advance payment of publishing royalties;

[0077] For example, when it is determined that the publishing royalty advance provided by the copyright agency to the current publishing house is normal, a network data packet including the publishing royalty advance quoted by a competing publishing house for the set book provided by the copyright agency for the set book to the current publishing house and normal publishing royalty advance information is wirelessly sent to the big data server of the current publishing house, including: the wireless transmission is based on a time division duplex communication link or a frequency division duplex communication link.

[0078] Fourth embodiment

[0079] Figure 5The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a fourth embodiment of the present invention.

[0080] like Figure 5 As shown, compared with Figure 2 After performing a preset number of multiple learning operations on the deep neural network to obtain the deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as the intelligent prediction model, the preset number is positively correlated with the writing years of the author of the set book, that is, after step S24, the method further includes:

[0081] Step S51: using a data storage chip to store various model parameters of the intelligent prediction model to implement model storage of the intelligent prediction model;

[0082] Specifically, the use of a data storage chip to store various model parameters of the intelligent prediction model to implement model storage of the intelligent prediction model includes: the data storage chip is a TF storage device or a FLASH storage device.

[0083] Fifth embodiment

[0084] Figure 6 The present invention is a flowchart showing a method for monitoring abnormalities in publishing royalty advance payments based on big data analysis according to a fifth embodiment of the present invention.

[0085] like Figure 6 As shown, compared with Figure 2 Before receiving the advance payment of publishing royalties for the set book provided by the copyright agency of the set book to the current publisher, and the set book is a book that has not yet been published, that is, before step S21, the method further includes:

[0086] Step S61: the big data server of the current publisher sends a bidding request related to the set book to the big data management node of the copyright agency that acts as the agent for the set book;

[0087] For example, the big data server of the current publishing house sends a bidding request related to the set and published book to the big data management node of the copyright agency that acts as the agent for setting the book, including: different publishing houses have their own big data servers, which perform information interaction with the big data management node of the copyright agency that acts as the agent for setting the book through a wireless network connection.

[0088] Next, various embodiments of the present invention will be further described.

[0089] In each of the above embodiments, optionally, in the method for monitoring abnormalities of publishing royalty advance payments based on big data analysis:

[0090] Receiving the advance payment of publishing royalties for the book set to be published, which is provided by the copyright agency of the book set to the current publisher, from the competing publisher, where the book set is a book that has not yet been published, and includes: the competing publisher and the current publisher are two different publishers that are in competition for the publishing rights of the book set;

[0091] Wherein, determining whether the advance payment of publishing royalties provided by the copyright agency to the current publishing house is abnormal based on the set book pricing amount, the set predicted value of the total number of sales of the book after publication, and the set advance payment percentage range also includes: when the advance payment of publishing royalties provided by the copyright agency to the current publishing house is within the numerical range of the advance payment of publishing royalties, determining that the advance payment of publishing royalties provided by the copyright agency to the current publishing house is normal;

[0092] For example, if a book is printed with 5,000 copies, the price is 30, and the agreed royalty rate is 10%, that is, the royalty is 15,000 yuan, and the publishing royalty advance is generally set at 30% to 100% of the royalty. In other words, for this book, a reliable publishing royalty advance accounts for 3%-10% of the total sales of the book, that is, 4,500-15,000 yuan. The publishing royalty advance that does not exceed this range can be regarded as a normal quotation of publishing royalty advance given by the copyright agency to other publishing houses of the current publishing house;

[0093] Among them, the intelligent prediction model is used to intelligently predict the total number of copies of the set book after release based on the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of copies sold corresponding to each book published by the author of the set book within the set time interval before the current moment, and the each copy associated information corresponding to each book. The predicted value also includes: in the each copy associated information corresponding to each book, the single copy associated information corresponding to each book is the number of published pages, pricing amount, number of words in a single book, number of chapters, single page area of ​​printing paper for the book, and thickness of the book.

[0094] In each of the above embodiments, optionally, in the method for monitoring abnormalities of publishing royalty advance payments based on big data analysis:

[0095] Using the intelligent prediction model to intelligently predict the predicted value of the total number of sales of the set book after it is released according to the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of sales of each book corresponding to each book published by the author of the set book within the set time interval before the current moment, and the associated information of each book also includes: inputting the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of sales of each book corresponding to each book published by the author of the set book within the set time interval before the current moment, and the associated information of each book into the intelligent prediction model in parallel;

[0096] Specifically, a parallel communication mechanism may be selected to complete the parallel input of the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of copies sold corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy associated information corresponding to each book to the intelligent prediction model;

[0097] Among them, using the intelligent prediction model to intelligently predict the predicted value of the total number of sales of the set book after its release based on the duration of the set time interval, the single-copy associated information corresponding to the set book, the total number of copies sold corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy-associated information corresponding to each book also includes: running the intelligent prediction model to obtain the predicted value of the total number of sales of the set book after its release output by the intelligent prediction model.

[0098] And in each of the above embodiments, optionally, in the method for monitoring abnormalities of publishing royalty advance payments based on big data analysis:

[0099] Performing a preset number of multiple learning operations on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, wherein the preset number is positively correlated with the writing years of the author of the set book, further comprising: using a numerical conversion function to represent a numerical conversion relationship of the positive correlation between the preset number and the writing years of the author of the set book;

[0100] The method further comprises: performing a preset number of multiple learning operations on the deep neural network to obtain the deep neural network after the multiple learning operations are completed, and outputting the deep neural network after the multiple learning operations as the intelligent prediction model, wherein the preset number is positively correlated with the writing years of the author of the set book, and further comprising: in the numerical conversion function, setting the writing years of the author of the book as the input value of the numerical conversion function;

[0101] wherein performing a preset number of multiple learning operations on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, and the preset number is positively correlated with the writing years of the author of the set book, further comprising: in the numerical conversion function, the preset number corresponding to the writing years of the author of the set book is the output value of the numerical conversion function;

[0102] The set book pricing amount is multiplied by the predicted value of the total number of sales of the set book after issuance to obtain the predicted value of the sales amount of the set book after issuance, and the predicted value of the sales amount of the set book after issuance is multiplied by the upper limit percentage value and the lower limit percentage value of the set advance payment percentage range to obtain the upper limit advance payment value and the lower limit advance payment value of the limited publishing royalty advance payment value range. When the publishing royalty advance payment provided by the copyright agency to the current publishing house is outside the publishing royalty advance payment value range, it is determined that the publishing royalty advance payment provided by the copyright agency to the current publishing house is abnormal, including: the upper limit percentage value and the lower limit percentage value of the set advance payment percentage range are 10% and 3% respectively;

[0103] Specifically, for example, the agreed royalty rate for printing a book is 10%, and the publishing royalty advance is generally set at 30% to 100% of the royalties. In this way, a reliable publishing royalty advance accounts for 3%-10% of the total sales of the book.

[0104] In addition, in a method for monitoring abnormalities of publishing royalty advances based on big data analysis according to the present invention, there are several technical features as follows to highlight the essential features of the present invention:

[0105] Performing a preset number of multiple learning operations on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, wherein the preset number is positively correlated with the writing years of the author of the set book, including: the deep neural network includes multiple hidden layers, a single output layer and a single input layer, and the multiple hidden layers are between the single output layer and the single input layer;

[0106] And wherein, a preset number of multiple learning operations are performed on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and the deep neural network after completing the multiple learning operations is output as an intelligent prediction model, and the preset number is positively correlated with the writing years of the author of the set book, including: the number of hidden layers of the deep neural network is positively correlated with the number of books published by the author of the set book within a set time interval before the current moment;

[0107] For example, the number of hidden layers of the deep neural network is positively correlated with the number of books published by the author of the set book within a set time interval before the current moment, including: setting the number of books published by the author of the book within the set time interval before the current moment to 5, the number of hidden layers of the deep neural network is 3, setting the number of books published by the author of the book within the set time interval before the current moment to 7, the number of hidden layers of the deep neural network is 5, and setting the number of books published by the author of the book within the set time interval before the current moment to 10, the number of hidden layers of the deep neural network is 7, and so on.

[0108] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms under the guidance of the present invention, all of which are within the protection of the present invention.

Claims

1. A method for monitoring abnormalities of publishing royalty advance payments based on big data analysis, characterized in that: The method comprises: Receiving the advance payment of publishing royalties for the book set to be published, which is provided by the copyright agency acting as the agent for the book set to the current publisher, from a competing publisher, where the book set is a book that has not yet been published; Obtain the number of published pages, price, word count, number of chapters, area of ​​a single page of printed paper, and thickness of a set book as the single copy associated information corresponding to the set book; Analyze the total number of copies sold of each book published by the author of the set book within a set time interval before the current moment and the associated information of each book; Performing a preset number of multiple learning operations on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, wherein the preset number is positively correlated with the writing years of the author of the set book; The intelligent prediction model is used to intelligently predict the predicted value of the total number of sales of the set book after it is released according to the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of sales of each copy corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy associated information corresponding to each book; Determine whether the publishing royalty advance provided by the copyright agency to the current publisher is abnormal based on a set book pricing amount, a set predicted value of the total number of book sales after publication, and a set advance percentage range.

2. The method for monitoring abnormalities of publishing royalty advance payments based on big data analysis according to claim 1, characterized in that: Analyzing the total number of copies sold and the associated information of each book respectively corresponding to each book published by the author of the set book within a set time interval before the current moment includes: using a big data analysis node to analyze the total number of copies sold and the associated information of each book respectively corresponding to each book published by the author of the set book within a set time interval before the current moment; Wherein, determining whether the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal based on the set book pricing amount, the predicted value of the total number of sales of the set book after issuance, and the set advance payment percentage range includes: multiplying the set book pricing amount by the predicted value of the total number of sales of the set book after issuance to obtain the predicted value of the sales amount of the set book after issuance, multiplying the predicted value of the sales amount of the set book after issuance by the upper limit percentage value and the lower limit percentage value of the set advance payment percentage range to obtain the upper limit advance payment value and the lower limit advance payment value that limit the publishing royalty advance payment value range, and determining that the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal when the publishing royalty advance provided by the copyright agency to the current publishing house is outside the publishing royalty advance payment value range; Among them, the intelligent prediction model is used to intelligently predict the total number of sales of the set book after its release based on the duration length of the set time interval, the single copy related information corresponding to the set book, the total number of copies sold corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy related information corresponding to each book. The predicted value includes: the duration length of the set time interval is positively correlated with the writing years of the author of the set book.

3. A method for monitoring abnormalities of publishing royalty advance payments based on big data analysis as claimed in claim 2, characterized in that: A preset number of multiple learning operations are performed on the deep neural network to obtain the deep neural network after the multiple learning operations are completed, and the deep neural network after the multiple learning operations is output as an intelligent prediction model. The preset number is positively correlated with the writing years of the author of the set book and also includes: in each learning operation performed on the deep neural network, the total number of sales of a certain book known by a certain author after its release is used as the output content of the deep neural network, and the duration length of the set time interval positively correlated with the writing years of the certain author, the single copy association information corresponding to the certain book, the total number of copies of each copy sold corresponding to each book published by the certain author within the set time interval before the release time of the certain book, and the copy association information corresponding to each book are used as the input content of the deep neural network to complete this learning operation.

4. A method for monitoring abnormalities of publishing royalty advance payments based on big data analysis as claimed in claim 3, characterized in that: After determining whether the publishing royalty advance provided by the copyright agency to the current publisher is abnormal based on the set book price, the set predicted value of the total number of sales of the book after publication, and the set advance percentage range, the method further includes: When it is determined that the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal, a network data packet including the publishing royalty advance quoted by a competing publishing house for the set book provided by the copyright agency to the current publishing house and information on the abnormal publishing royalty advance is wirelessly sent to the big data server of the current publishing house.

5. The method for monitoring abnormalities of publishing royalty advance payments based on big data analysis as claimed in claim 3, characterized in that: After determining whether the publishing royalty advance provided by the copyright agency to the current publisher is abnormal based on the set book price, the set predicted value of the total number of sales of the book after publication, and the set advance percentage range, the method further includes: When it is determined that the publishing royalty advance provided by the copyright agency to the current publishing house is normal, a network data packet including the publishing royalty advance quoted by a competing publishing house for the set book provided by the copyright agency for the set book to the current publishing house and normal publishing royalty advance information is wirelessly sent to the big data server of the current publishing house.

6. A method for monitoring abnormalities of publishing royalty advance payments based on big data analysis as claimed in claim 3, characterized in that: After performing a preset number of multiple learning operations on the deep neural network to obtain the deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, and the preset number is positively correlated with the writing years of the author of the set book, the method further includes: A data storage chip is used to store various model parameters of the intelligent prediction model to achieve model storage of the intelligent prediction model.

7. A method for monitoring abnormalities of publishing royalty advance payments based on big data analysis as claimed in claim 3, characterized in that: Before receiving the publishing royalty advance for the book to be published, provided by the copyright agency of the book to be published, the competing publisher offers the book to be published, and the book to be published is not yet published, the method further includes: The big data server of the current publishing house sends a bidding request related to the set publishing book to the big data management node of the copyright agency that acts as the agent for the set book.

8. A method for monitoring abnormalities of publishing royalty advance payments based on big data analysis as described in any one of claims 3 to 7, characterized in that: Receiving the advance payment of publishing royalties for the book set to be published, which is provided by the copyright agency of the book set to the current publisher, from the competing publisher, where the book set is a book that has not yet been published, and includes: the competing publisher and the current publisher are two different publishers that are in competition for the publishing rights of the book set; Wherein, determining whether the advance payment of publishing royalties provided by the copyright agency to the current publishing house is abnormal based on the set book pricing amount, the set predicted value of the total number of sales of the book after publication, and the set advance payment percentage range also includes: when the advance payment of publishing royalties provided by the copyright agency to the current publishing house is within the numerical range of the advance payment of publishing royalties, determining that the advance payment of publishing royalties provided by the copyright agency to the current publishing house is normal; Among them, the intelligent prediction model is used to intelligently predict the total number of copies of the set book after release based on the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of copies sold corresponding to each book published by the author of the set book within the set time interval before the current moment, and the each copy associated information corresponding to each book. The predicted value also includes: in the each copy associated information corresponding to each book, the single copy associated information corresponding to each book is the number of published pages, pricing amount, number of words in a single book, number of chapters, single page area of ​​printing paper for the book, and thickness of the book.

9. A method for monitoring abnormalities of publishing royalty advance payments based on big data analysis as described in any one of claims 3 to 7, characterized in that: Using the intelligent prediction model to intelligently predict the predicted value of the total number of sales of the set book after it is released according to the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of sales of each book corresponding to each book published by the author of the set book within the set time interval before the current moment, and the associated information of each book also includes: inputting the duration of the set time interval, the single copy associated information corresponding to the set book, the total number of sales of each book corresponding to each book published by the author of the set book within the set time interval before the current moment, and the associated information of each book into the intelligent prediction model in parallel; Among them, using the intelligent prediction model to intelligently predict the predicted value of the total number of sales of the set book after its release based on the duration of the set time interval, the single-copy associated information corresponding to the set book, the total number of copies sold corresponding to each book published by the author of the set book within the set time interval before the current moment, and the copy-associated information corresponding to each book also includes: running the intelligent prediction model to obtain the predicted value of the total number of sales of the set book after its release output by the intelligent prediction model.

10. A method for monitoring abnormalities of publishing royalty advance payments based on big data analysis as claimed in any one of claims 3 to 7, characterized in that: Performing a preset number of multiple learning operations on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, wherein the preset number is positively correlated with the writing years of the author of the set book, further comprising: using a numerical conversion function to represent a numerical conversion relationship of the positive correlation between the preset number and the writing years of the author of the set book; The method further comprises: performing a preset number of multiple learning operations on the deep neural network to obtain the deep neural network after the multiple learning operations are completed, and outputting the deep neural network after the multiple learning operations as the intelligent prediction model, wherein the preset number is positively correlated with the writing age of the author of the set book, and further comprising: in the numerical conversion function, setting the writing age of the author of the book as the input value of the numerical conversion function; wherein performing a preset number of multiple learning operations on the deep neural network to obtain a deep neural network after completing the multiple learning operations, and outputting the deep neural network after completing the multiple learning operations as an intelligent prediction model, and the preset number is positively correlated with the writing years of the author of the set book, further comprising: in the numerical conversion function, the preset number corresponding to the writing years of the author of the set book is the output value of the numerical conversion function; Among them, the set book pricing amount is multiplied by the predicted value of the total number of sales of the set book after publication to obtain the predicted value of the sales amount of the set book after publication, and the predicted value of the sales amount of the set book after publication is multiplied by the upper limit percentage value and the lower limit percentage value of the set advance payment percentage range to obtain the upper limit advance payment value and the lower limit advance payment value of the limited publishing royalty advance payment value range. When the publishing royalty advance provided by the copyright agency to the current publishing house is outside the publishing royalty advance payment value range, it is determined that the publishing royalty advance provided by the copyright agency to the current publishing house is abnormal, including: the upper limit percentage value and the lower limit percentage value of the set advance payment percentage range are 10% and 3% respectively.

Images