Method for digital collection management and directional sharing

By establishing a digital collection storage model and user browsing and analysis, the problem of low recommendation efficiency of digital collection platforms has been solved, and fast and accurate digital collection recommendations have been achieved, improving user experience and transaction efficiency.

CN118917911APending Publication Date: 2024-11-08CHONGQING TOURISM CLOUD INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410947563.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing digital collection platform lacks a systematic recommendation system, which makes users inefficient in finding intended digital collections, making it difficult to find products similar to existing digital collections.

Method used

Establish a digital collection storage model, classify digital collections by extracting feature points, combining user browsing history and marking point analysis, set the intention recommendation index, conduct accurate push, and adjust the recommendation plan through approximation analysis and real-time monitoring.

Benefits of technology

It realizes the rapid and accurate recommendation of digital collections for users' intentions, improves the user experience, and improves the efficiency and recommendation quality of digital collection transactions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917911A_ABST
    Figure CN118917911A_ABST
Patent Text Reader

Abstract

The invention relates to the field of digital collection management and pushing, and discloses a method for digital collection management and directional sharing, which comprises the following steps: establishing a digital collection storage model, uploading digital collections by a user, extracting feature points, and classifying the digital collections into digital collection feature families; recording a digital collection browsing condition of the user; setting an intention recommendation index for the digital collection; accurately pushing the digital collection feature family to the user according to the intention recommendation index; a calibration object is selected for approximation analysis, and the sharing number is regulated and controlled; detecting changes of the digital collections in real time, and establishing a directional sharing scheme of the digital collections; according to the method and the system, the problems that the current digital collections do not have a digital collection recommendation system, the efficiency of searching the intentional digital collections by the user is low, the user is difficult to search the digital collections similar to the purchased digital collections, and the digital collections are not accurately pushed in the current market are solved, and the method and the system are suitable for systematically managing the digital collections and accurately pushing the digital collections to the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of digital collection management and sharing, and in particular to a method for digital collection management and targeted sharing. Background Art

[0002] Digital collections refer to unique digital certificates generated for specific works or artworks using blockchain technology. On the basis of protecting their digital copyrights, they enable authentic digital distribution, purchase, collection and use. Digital collections are rich in categories, including but not limited to digital pictures, music, videos, 3D models, electronic tickets, digital souvenirs and other forms.

[0003] As digital collections become more and more popular, transactions of digital collections are becoming more and more frequent. However, since digital collections are unique and virtual, when people browse digital collection platforms, the platforms lack a systematic digital collection recommendation system and are unable to recommend users' intended digital collections in a timely manner. As a result, users often have to search for a very long time on digital collection trading platforms before they can find the digital collections they intend to purchase. Summary of the invention

[0004] The present invention is intended to provide a method for digital collection management and targeted sharing, so as to solve the problems that there is currently no digital collection recommendation system for digital collections, users are inefficient in searching for intended digital collections, it is difficult for users to find digital collections similar to those they have purchased, and there is currently no accurate push of digital collections on the market.

[0005] In order to achieve the above object, the present invention provides the following method:

[0006] A method for digital collection management and targeted sharing provided by the present invention is:

[0007] S1: Establish a digital collection storage model according to the type of digital collection, and the user uploads the digital collection according to the digital storage model;

[0008] S2: extracting feature points from the digital collection in the digital collection storage model, and classifying the digital collection into a plurality of digital collection feature groups according to the feature points;

[0009] S3: recommending corresponding digital collection feature families to the user based on the historical records of digital collections browsed by the user, and recording the browsing status of the digital collections of the user;

[0010] S4: according to the user's browsing situation of the digital collection, four digital collection states are set for the digital collection, which correspond to the intention recommendation index of the digital collection respectively;

[0011] S5: accurately push the digital collection feature group to the user according to the digital collection status information;

[0012] S6: Select a calibration object from the digital collection, associate it with the digital collection storage model, perform approximation analysis, and obtain an approximate digital collection family;

[0013] S7: By recording the browsing conditions of visitors in the similar digital collection family, the sharing quantity of the similar digital collection family is regulated;

[0014] S8: Detect the changes of the user's digital collections in real time, and establish a targeted sharing plan for the user's digital collections according to the digital collection families to which they belong.

[0015] Preferably, a digital collection storage model is established according to the types of digital collections, and the user performs the step of uploading digital collections according to the digital storage model, including: the types of digital collections include: digital pictures, music, videos, 3D models, electronic certificates, digital souvenirs; digital collection information includes: historical browsing records of digital collections, historical transfer records of digital collections, historical price fluctuation records of digital collections; the digital collection storage model is a binary tree model, in which the digital collections are bifurcated into the types of digital collections and then each digital collection type is bifurcated into different types of digital collection bifurcation categories, and the structure of each bifurcation part of the bifurcation category is a non-binary bifurcation path, that is, a two-choice bifurcation method; the digital collection storage model has a multi-layer structure, with a maximum of seven layers of bifurcation structure, and the number of digital collections stored in the branches from the top-level bifurcation structure to the bottom-level bifurcation structure is getting smaller and smaller, and the number of restrictions is getting more and more.

[0016] Preferably, the step of extracting feature points from the digital collections in the digital collection storage model and classifying the digital collections into multiple digital collection feature families according to the feature points includes: firstly extracting type feature points according to the types of the digital collections in the digital collection storage model, and extracting one obvious feature point and two inconspicuous feature points according to the types of the digital collections; extracting one feature point from each branch according to the seven-layer bifurcation structure of the digital collection storage model, which is a hierarchical feature point; if the obvious feature points of the types of the digital collections are the same, the digital collections are classified into a large digital collection feature family; if the two inconspicuous feature points of the types of the digital collections are the same, the digital collections are classified into a direct digital collection feature family; if at least one of the two inconspicuous feature points of the types of the digital collections is different, the digital collections are classified into a collateral digital collection feature family; and according to the number of identical hierarchical feature points of the digital collections, the digital collections are accumulated into corresponding hierarchical recommendation association indexes.

[0017] Preferably, the step of recommending a corresponding digital collection feature family to the user based on the historical records of digital collections browsed by the user, and recording the user's browsing of the digital collections, includes: marking any pixel point of the digital collection to obtain a digital collection marking point; binding a duration recording tag and a track recording tag to the digital collection marking point; the duration recording tag records when the user starts browsing the digital collection, and cuts off the recording when the digital collection is switched to obtain the user browsing duration; the track recording tag records when the user starts browsing the digital collection, and the digital collection marking point is restored to the original state to cut off the recording to obtain the user browsing trajectory; if the user browsing duration is greater than or equal to the average browsing duration of the user, the digital collection is marked as the user's first intended digital collection; if the user browsing trajectory is greater than or equal to the digital collection trajectory / average browsing trajectory of the user, the digital collection is marked as the user's second intended digital collection; if the user browsing duration is less than or equal to the average browsing duration of the user and the user browsing trajectory is less than or equal to the digital collection trajectory / average browsing trajectory of the user, the digital collection is marked as a digital collection that the user is not interested in.

[0018] Preferably, the step of setting four digital collection states for digital collections corresponding to the intended recommendation index of the digital collections according to the user's digital collection browsing situation includes: if the digital collection has the first intended digital collection mark and the second intended digital collection mark, setting the digital collection to the first recommended state; if the digital collection has the first intended digital collection mark or the second intended digital collection mark and the number of collections in the direct family of the digital collection to which the digital collection belongs>the number of collections in the characteristic family of the digital collection to which the digital collection belongs*50%, setting the digital collection to the second recommended state; if the digital collection has the first intended digital collection mark or the second intended digital collection mark and the number of collections in the direct family of the digital collection to which the digital collection belongs<=the number of collections in the characteristic family of the digital collection to which the digital collection belongs*50%, setting the digital collection to the third recommended state; if the digital collection has the digital collection label that the user is not interested in, setting the digital collection to the fourth recommended state.

[0019] Preferably, the step of accurately pushing the digital collection feature family to the user according to the digital collection status information includes: pushing the digital collection to the user in a ratio of the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status = 5:2:2:1 to obtain a first pushed digital collection; if the user browsing time and the user browsing trajectory recorded in the digital collection collection mark point of the first pushed digital collection are greater than the historical browsing record of the digital collection, then pushing the digital collection in a ratio of the digital collection feature direct family of the first pushed digital collection: the digital collection feature collateral family of the first pushed digital collection = 5:2 to obtain a second pushed digital collection; if the user browsing time and the user browsing trajectory recorded in the digital collection collection mark point of the first pushed digital collection are <= the historical browsing record of the digital collection, then according to the hierarchical recommendation association index, sharing the secondary associated digital collection with the user in a targeted manner to obtain a third pushed digital collection.

[0020] Preferably, if the user browsing time and the user browsing trajectory recorded by the digital collection collection mark point of the first pushed digital collection are <= the historical browsing record of the digital collection, then according to the hierarchical recommendation association index, the secondary related digital collection is shared with the user in a targeted manner to obtain the third pushed digital collection step, including: if the hierarchical association index is >= 4, the digital collection is pushed to the user in a ratio of the first recommended status: the second recommended status: the third recommended status: the fourth recommended status = 4:3:3:2 to obtain the third pushed digital collection; if the hierarchical association index is >= 2, the digital collection is pushed to the user in a ratio of the first recommended status: the second recommended status: the third recommended status: the fourth recommended status = 3:3:3:2 to obtain the third pushed digital collection; if the hierarchical association index is <2, the digital collection is pushed to the user in a ratio of the first recommended status: the second recommended status: the third recommended status: the fourth recommended status = 3:3:3:3 to obtain the third pushed digital collection.

[0021] Preferably, the step of selecting a calibration object from the digital collection, associating it with the digital collection storage model, performing a similarity analysis, and obtaining an approximate digital collection family includes: randomly selecting a color from the digital collection owned by the user as the calibration color, and then randomly selecting a graphic line outline as the calibration outline when the calibration color is selected; searching for the same color for the calibration color in the direct family of digital collection characteristics to which the digital collection belongs, and after finding the same color, recording the graphic line outline of the digital collection where the color is located; comparing the recorded graphic outline with the calibration outline for overlap, and if the overlap exceeds 80%, adding a user-intended approximate digital collection family label to the digital collection.

[0022] Preferably, the step of regulating the sharing quantity of the approximate digital collection family by recording the browsing conditions of visitors in the approximate digital collection family includes: regularly recording the digital collection mark points of the approximate digital collection family to record the browsing time of the approximate digital collection family and the direct family of digital collections to which the approximate digital collection belongs; if the browsing time of the approximate digital collection family belongs to the first intended digital collection, regularly increasing the amount of the approximate digital collection family to be pushed, with 10% of the number of pushed digital collections as the base and 4% as the increment, increasing in a gradient manner, and the period is the total amount of digital collections in the digital collection storage model. The increment is 10%; if the browsing time of the approximate digital collection family belongs to the second intended digital collection, the approximate digital collection family will be pushed to the user regularly, with 5% of the number of pushed digital collections as the base, and 3% as the increment, showing a gradient increase, and the period is the total amount of digital collections in the digital collection storage model. The increment is 10%; if the browsing time of the approximate digital collection family belongs to the digital collection that the user is not interested in, the approximate digital collection family will be pushed to the user regularly, with 0 of the number of pushed digital collections as the base, and 2% as the increment, showing a gradient increase, and the period is the total amount of digital collections in the digital collection storage model. The increment is 15%.

[0023] Preferably, the step of detecting the changes of the user's digital collections in real time and establishing a digital collection-oriented sharing plan for the user's digital collections according to the digital collection family to which they belong includes: after pushing the first pushed digital collection, if the user browsing time recorded by the digital collection mark point exceeds 3 to 5 times the historical browsing record of the digital collection, then introducing 30% of the second pushed digital collection; if the user browsing time recorded by the digital collection mark point does not exceed 3 times the historical browsing record of the digital collection, then introducing 30% of the third pushed digital collection; if the user browsing time recorded by the digital collection mark point exceeds 5 times the historical browsing record of the digital collection, then introducing 20% ​​of the second pushed digital collection and 20% of the third pushed digital collection; after introducing the specified number of the first pushed digital collection, the second pushed digital collection, and the third pushed digital collection, adding 20% ​​of the approximate digital collection family to form a complete digital collection-oriented sharing plan.

[0024] The beneficial effects of the present invention are as follows: by establishing a unified and systematic seven-layer pyramid digital collection storage model in the form of a binary tree, the user can be helped to find the digital collection of the user's intention more quickly, feature points are extracted according to the types of digital collections, hierarchical feature points are extracted according to the branch type of each layer, all digital collections are divided into digital collection feature direct families vertically and digital collection collateral families horizontally, and the recommendation association index of each level is marked, and then by binding the digital collection with a time record tag and a track record tag, the user's stay time and browsing track on the digital collection are determined to determine whether the user is interested in the digital collection, the state of the intention degree on each digital collection is changed according to the user's interest degree, and then the recommendation index of different specific states is set. The first pushed digital collection is obtained by comparing the browsing history of the first pushed digital collection with the historical browsing history to check the recommendation effect of the first pushed digital collection, so as to formulate the second pushed product in a targeted manner. If the first pushed digital collection is not ideal, different proportions of different recommendation states are formulated for users using different hierarchical recommendation indexes to obtain the third pushed digital collection. A single color and a fixed outline are marked on the digital collection to find an approximate digital collection family in the direct family of the digital collection feature, and the approximate digital collection family is added to the first pushed product, the second pushed product and the third pushed product to obtain the optimal digital collection recommendation ratio. Finally, by real-time monitoring of the recommendation effect of the digital collection, the first pushed product, the second pushed product and the third pushed product are adjusted in proportion to be pushed. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0026] Figure 1 It is a flowchart of a method for digital collection management and targeted sharing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0028] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] As digital collections become more and more popular, transactions of digital collections are becoming more and more frequent. However, since digital collections are unique and virtual, when people browse digital collection platforms, the platforms lack a systematic digital collection recommendation system and are unable to recommend users' intended digital collections in a timely manner. As a result, users often have to search for a very long time on digital collection trading platforms before they can find the digital collections they intend to purchase.

[0031] The present invention aims to provide a method for digital collection management and targeted sharing to solve the problems that there is currently no digital collection recommendation system for digital collections, users are inefficient in finding intended digital collections, it is difficult for users to find digital collections similar to the digital collections they have purchased, and there is currently no accurate push of digital collections on the market.

[0032] A specific embodiment of the present invention provides a method for managing and sharing digital collections. Figure 1 As shown, the following steps are included:

[0033] In step S1, a digital collection storage model is established according to the types of digital collections, and users upload digital collections according to the digital storage model.

[0034] In the embodiment of the present invention, the types of digital collections include: digital pictures, music, videos, 3D models, electronic certificates, digital souvenirs; the digital collection information includes: historical browsing records of digital collections, historical transfer records of digital collections, and historical price fluctuation records of digital collections; the digital collection storage model is a binary tree model, in which the digital collections are bifurcated into the types of digital collections and then each digital collection type is bifurcated into different types of digital collection bifurcation categories, and the structure of each bifurcation part of the bifurcation category is a non-binary bifurcation path, that is, a binary bifurcation method; the digital collection storage model has a multi-layer structure , a maximum of seven-layer fork structure. The first layer of the seven-layer fork structure is in the form of digital collections such as pictures, music, videos, 3D models, electronic tickets, digital souvenirs, etc. For example, the seven-layer fork structure of picture digital collections: the first layer is picture digital collections, the second layer is dynamic pictures / static pictures, the third layer is still lifes / animals, the fourth layer is single-layer pictures / composite pictures, the fifth layer is monochrome pictures / color pictures, the sixth layer is high-pixel pictures / low-pixel pictures, and the seventh layer is simple structure pictures / complex structure pictures. The number of digital collections stored in the branches from the top-level fork structure to the bottom-level fork structure becomes smaller and smaller, and the restrictions become more and more.

[0035] In step S2, feature points are extracted from the digital collections in the digital collection storage model, and the digital collections are classified into a plurality of digital collection feature clusters according to the feature points.

[0036] In an embodiment of the present invention, firstly, type feature points are extracted according to the types of the digital collections in the digital collection storage model. One obvious feature point and two inconspicuous feature points are extracted according to the different types of the digital collections. For example, the obvious feature points of the picture type and the music type are the style type, and the inconspicuous feature points are the size of the digital collection and the type of the digital collection adaptation scene. According to the seven-layer bifurcation structure of the digital collection storage model, one feature point is extracted from each branch, which is the hierarchical feature point. If the obvious feature points of the types of the digital collections are the same, the digital collections are classified into a large family of digital collection features. If the two inconspicuous feature points of the types of the digital collections are the same, the digital collections are classified into a direct family of digital collection features. If at least one of the two inconspicuous feature points of the types of the digital collections is different, the digital collections are classified into a collateral family of digital collection features. According to the number of identical hierarchical feature points of the digital collections, the digital collections are accumulated into corresponding hierarchical recommendation association indexes.

[0037] In step S3, the corresponding digital collection feature families are recommended to the user based on the digital collection history records browsed by the user, and the user's browsing of the digital collections is recorded.

[0038] In an embodiment of the present invention, any pixel point of a digital collection is marked to obtain a digital collection marking point; a duration recording tag and a track recording tag are bound to the digital collection marking point; the duration recording tag records when the user starts browsing the digital collection, and stops recording when the digital collection is switched to obtain the user browsing duration; the track recording tag records when the user starts browsing the digital collection, and stops recording when the digital collection marking point is restored to its original state to obtain the user browsing trajectory; if the user browsing duration is greater than or equal to the average browsing duration of the user, the digital collection is marked as the user's first intended digital collection; if the user browsing trajectory is greater than or equal to the digital collection trajectory / average browsing trajectory of the user, the digital collection is marked as the user's second intended digital collection; if the user browsing duration is less than or equal to the average browsing duration of the user and the user browsing trajectory is less than or equal to the digital collection trajectory / average browsing trajectory of the user, the digital collection is marked as a digital collection that the user is not interested in. The user browses the digital collection for a long time and the browsing trajectory of the user is large when browsing the digital collection. Double verification of the user's intended digital collection is used to make the user's judgment on the intended digital collection more accurate.

[0039] In step S4, four digital collection states are set for the digital collections according to the user's browsing situation of the digital collections, which respectively correspond to the intention recommendation index of the digital collections.

[0040] In an embodiment of the present invention, if the digital collection has the first intended digital collection mark and the second intended digital collection mark, the digital collection is set to a first recommended state; if the digital collection has the first intended digital collection mark or the second intended digital collection mark and the number of collections in the direct family of the digital collection to which the digital collection belongs>the number of collections in the characteristic family of the digital collection to which the digital collection belongs*50%, the digital collection is set to a second recommended state; if the digital collection has the first intended digital collection mark or the second intended digital collection mark and the number of collections in the direct family of the digital collection to which the digital collection belongs<=the number of collections in the characteristic family of the digital collection to which the digital collection belongs*50%, the digital collection is set to a third recommended state; if the digital collection has the digital collection label that the user is not interested in, the digital collection is set to a fourth recommended state, and the recommended state is a hidden state. Setting four recommended states will formulate different digital collection recommendation plans according to different users, so that the digital collections recommended by users can be more refined, and the quality and accuracy of digital collection recommendations can be improved.

[0041] In step S5, the digital collection feature family is accurately pushed to the user based on the digital collection status information.

[0042] In the embodiment of the present invention, digital collections are pushed to users in a ratio of the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status = 5:2:2:1 to obtain a first pushed digital collection; if the user browsing time and the user browsing trajectory recorded in the digital collection collection mark point of the first pushed digital collection are greater than the historical browsing record of the digital collection, the digital collection is pushed in a ratio of the direct family of the digital collection feature of the first pushed digital collection: the collateral family of the digital collection feature of the first pushed digital collection = 5:2 to obtain a second pushed digital collection; if the user browsing time and the user browsing trajectory recorded in the digital collection collection mark point of the first pushed digital collection are less than or equal to the historical browsing record of the digital collection, the user is targeted according to the hierarchical recommendation association index. Share the secondary associated digital collection and get the third pushed digital collection; if the hierarchical association index is greater than or equal to 4, the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status is shared with the user in a ratio of 4:3:3:2 to push the digital collection to the user, and the third pushed digital collection is obtained; if the hierarchical association index is greater than or equal to 2, the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status is shared with the user in a ratio of 3:3:3:2 to push the digital collection to the user, and the third pushed digital collection is obtained; if the hierarchical association index is less than 2, the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status is shared with the user in a ratio of 3:3:3:3 to push the digital collection to the user, and the third pushed digital collection is obtained.

[0043] In step S6, a calibration object is selected from the digital collection, and is associated with the digital collection storage model, and a similarity analysis is performed to obtain an approximate digital collection family.

[0044] In an embodiment of the present invention, a color is randomly selected from the digital collections owned by the user as the calibration color, and then a graphic line outline is randomly selected as the calibration outline when the calibration color is selected; the calibration color is searched for the same color in the direct family of the digital collection characteristics to which the digital collection belongs, and after the same color is found, the graphic line outline of the digital collection where the color is located is recorded; the recorded graphic outline is compared with the calibration outline for overlap, and if the overlap exceeds 80%, a user-intended similar digital collection family label is added to the digital collection, and the digital collection color is first verified, and then a secondary randomly selected outline verification is entered, so that the overlap comparison process is faster and more efficient, and finding similar digital collections is more complete for recommending digital collections to users.

[0045] In step S7, the sharing quantity of the approximate digital collection family is regulated by recording the browsing status of visitors in the approximate digital collection family.

[0046] In the embodiment of the present invention, the digital collection mark points of the approximate digital collection family are recorded regularly, and the browsing time of the approximate digital collection family and the direct family of digital collections to which the approximate digital collection belongs are recorded; if the browsing time of the approximate digital collection family belongs to the first intended digital collection, the approximate digital collection family is pushed to the user regularly, with 10% of the number of pushed digital collections as the base and 4% as the increment, increasing in a gradient manner, and the period is 10% of the total amount of digital collections in the digital collection storage model; if the browsing time of the approximate digital collection family belongs to the second intended digital collection, the approximate digital collection family is pushed to the user regularly. The approximate digital collection family, with 5% of the number of pushed digital collections as the base and 3% as the increment, increases in a gradient manner, and the period is 10% of the total amount of digital collections in the digital collection storage model; if the browsing time of the approximate digital collection family belongs to the digital collection that the user is not interested in, the approximate digital collection family will be pushed to the user regularly, with 0 of the number of pushed digital collections as the base and 2% as the increment, increases in a gradient manner, and the period is 15% of the total amount of digital collections in the digital collection storage model. Every time the total amount of digital collections in the digital collection storage model increases by a fixed amount, the content of the approximate digital collection is changed to better adapt to the changes in the content of the user's intended digital collection.

[0047] In step S8, the changes of the user's digital collections are detected in real time, and a digital collection-oriented sharing plan is established for the user's digital collections according to the digital collection families to which they belong.

[0048] In an embodiment of the present invention, after pushing the first pushed digital collection, if the user browsing time recorded by the digital collection mark point exceeds 3 to 5 times the historical browsing record of the digital collection, 30% of the second pushed digital collection is introduced; if the user browsing time recorded by the digital collection mark point does not exceed 3 times the historical browsing record of the digital collection, 30% of the third pushed digital collection is introduced; if the user browsing time recorded by the digital collection mark point exceeds 5 times the historical browsing record of the digital collection, 20% of the second pushed digital collection is introduced, and 20% of the third pushed digital collection is introduced. Push digital collections; after introducing a specified number of the first pushed digital collections, the second pushed digital collections, and the third pushed digital collections, add 20% of the approximate digital collection family to form a complete targeted sharing plan for the digital collections. The complete targeted sharing plan for the digital collections includes 20% to 30% of the first pushed digital collections, 30% of the second pushed digital collections, 20% to 30% of the second pushed digital collections, and 20% of the approximate digital collection family. What is finally pushed to the user is a digital collection recommendation package. The digital collection recommendation package recommended to the user changes in real time according to the length of time and trajectory of the user's regular browsing of the digital collections.

[0049] The beneficial effects of the present invention are as follows: by establishing a unified and systematic seven-layer pyramid digital collection storage model in the form of a binary tree, the user can be helped to find the digital collection of the user's intention more quickly, feature points are extracted according to the types of digital collections, hierarchical feature points are extracted according to the branch type of each layer, all digital collections are divided into digital collection feature direct families vertically and digital collection collateral families horizontally, and the recommendation association index of each level is marked, and then by binding the digital collection with a time record tag and a track record tag, the user's stay time and browsing track on the digital collection are determined to determine whether the user is interested in the digital collection, the state of the intention degree on each digital collection is changed according to the user's interest degree, and then the recommendation index of different specific states is set. The first pushed digital collection is obtained by comparing the browsing history of the first pushed digital collection with the historical browsing history to check the recommendation effect of the first pushed digital collection, so as to formulate the second pushed product in a targeted manner. If the first pushed digital collection is not ideal, different proportions of different recommendation states are formulated for users using different hierarchical recommendation indexes to obtain the third pushed digital collection. A single color and a fixed outline are marked on the digital collection to find an approximate digital collection family in the direct family of the digital collection feature, and the approximate digital collection family is added to the first pushed product, the second pushed product and the third pushed product to obtain the optimal digital collection recommendation ratio. Finally, by real-time monitoring of the recommendation effect of the digital collection, the first pushed product, the second pushed product and the third pushed product are adjusted in proportion to be pushed.

[0050] The above is only an embodiment of the present invention, and the common knowledge such as the specific technical scheme or characteristics known in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, several modifications and improvements can be made without departing from the technical scheme of the present invention, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the method of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A method for digital collection management and targeted sharing, characterized in that: The method comprises: s1: Establish a digital collection storage model according to the type of digital collection, and the user uploads the digital collection according to the digital storage model; S2: extracting feature points from the digital collection in the digital collection storage model, and classifying the digital collection into a plurality of digital collection feature groups according to the feature points; S3: recommending corresponding digital collection feature families to the user based on the historical records of digital collections browsed by the user, and recording the browsing status of the digital collections of the user; S4: according to the user's browsing situation of the digital collection, four digital collection states are set for the digital collection, which correspond to the intention recommendation index of the digital collection respectively; S5: accurately push the digital collection feature group to the user according to the digital collection status information; S6: Select a calibration object from the digital collection, associate it with the digital collection storage model, perform approximation analysis, and obtain an approximate digital collection family; S7: By recording the browsing conditions of visitors in the similar digital collection family, the sharing quantity of the similar digital collection family is regulated; S8: Detect the changes of the user's digital collections in real time, and establish a targeted sharing plan for the user's digital collections according to the digital collection families to which they belong.

2. A method for digital collection management and targeted sharing according to claim 1, characterized in that: The step of establishing a digital collection storage model according to the type of digital collection, and the user uploading the digital collection according to the digital storage model, includes: The types of digital collections include: digital pictures, music, videos, 3D models, electronic certificates, and digital souvenirs; Digital collection information includes: historical browsing records of digital collections, historical transfer records of digital collections, and historical price fluctuation records of digital collections; The digital collection storage model is a binary tree model, where the digital collection is bifurcated into the digital collection categories, and each digital collection category is bifurcated into different types of digital collection bifurcations. The bifurcations of the bifurcations are either a binary or a binary bifurcations path, i.e., a binary bifurcations method. The digital collection storage model has a multi-layer structure, with a maximum of seven layers of forked structures. The number of digital collections stored in the branches from the top-level forked structure to the bottom-level forked structure becomes smaller and smaller, and the restrictions become more and more.

3. A method for digital collection management and targeted sharing according to claim 2, characterized in that: The step of extracting feature points from the digital collection in the digital collection storage model and classifying the digital collection into a plurality of digital collection feature groups according to the feature points includes: First, extracting type feature points according to the types of the digital collections in the digital collection storage model, and extracting one obvious feature point and two inconspicuous feature points according to the types of the digital collections; According to the seven-layer bifurcation structure of the digital collection storage model, a feature point is extracted from each branch as a hierarchical feature point; If the types of digital collections have the same obvious characteristics, the digital collections are classified into a large family of digital collection characteristics; If two inconspicuous characteristic points of the digital collection types are the same, the digital collections are classified into a direct family of digital collection characteristics; If at least one of the two inconspicuous characteristic points of the digital collection types is different, the digital collection is classified into a digital collection characteristic collateral family; According to the same number of hierarchical feature points of the digital collections, the digital collections are accumulated into corresponding hierarchical recommendation association indexes.

4. A method for digital collection management and targeted sharing according to claim 3, characterized in that: The step of recommending corresponding digital collection feature groups to the user according to the digital collection history records browsed by the user, and recording the user's browsing of the digital collections, comprises: Mark any pixel point of the digital collection to obtain the digital collection marking point; Binding a duration record tag and a track record tag to the digital collection mark point; The duration recording tag records when the user starts browsing the digital collection and stops recording when the digital collection is switched, thereby obtaining the browsing duration of the user; The track record tag records when the user starts browsing the digital collection, and the digital collection mark point is restored to the original state to record the end, so as to obtain the user browsing track; If the browsing time of the user is greater than or equal to the average browsing time of the user, the digital collection is marked as the user's first preferred digital collection; If the user browsing track>=the digital collection track / the average user browsing track, then mark the digital collection as the user's second intended digital collection; If the user browsing time <= the average user browsing time and the user browsing track <= the digital collection track / average user browsing track, the digital collection will be marked as a digital collection that the user is not interested in.

5. A method for digital collection management and targeted sharing according to claim 4, characterized in that: The step of setting four digital collection states for the digital collections, which correspond to the intended recommendation index of the digital collections respectively, according to the digital collection browsing situation of the user, comprises: If the digital collection has the first intended digital collection mark and the second intended digital collection mark, setting the digital collection to a first recommended state; If the digital collection has the first intended digital collection mark or the second intended digital collection mark and the number of collections in the direct family of the digital collection to which the digital collection belongs>the number of collections in the characteristic family of the digital collection to which the digital collection belongs*50%, then the digital collection is set to the second recommended state; If the digital collection has the first intended digital collection mark or the second intended digital collection mark and the number of collections in the direct family of the digital collection to which the digital collection belongs is less than or equal to the number of collections in the characteristic family of the digital collection to which the digital collection belongs * 50%, then the digital collection is set to the third recommendation state; If the digital collection has a digital collection tag that the user is not interested in, the digital collection is set to a fourth recommendation state.

6. A method for digital collection management and targeted sharing according to claim 5, characterized in that: The step of accurately pushing the digital collection feature group to the user according to the digital collection status information includes: Pushing digital collections to the user in a ratio of the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status = 5:2:2:1 to obtain a first pushed digital collection; If the user browsing time and the user browsing track recorded by the digital collection mark point of the first pushed digital collection are greater than the digital collection historical browsing record, the digital collection feature direct family of the first pushed digital collection: the digital collection feature collateral family of the first pushed digital collection = 5:2 is pushed to obtain the second pushed digital collection; If the user browsing time and the user browsing trajectory recorded by the digital collection collection mark point of the first pushed digital collection are <= the digital collection historical browsing record, then according to the hierarchical recommendation association index, the secondary related digital collection is shared for the user to obtain the third pushed digital collection.

7. A method for digital collection management and targeted sharing according to claim 6, characterized in that: If the user browsing time and the user browsing track recorded by the digital collection collection mark point of the first pushed digital collection are less than or equal to the digital collection historical browsing record, then the step of sharing the secondary related digital collection for the user according to the hierarchical recommendation association index to obtain the third pushed digital collection includes: If the hierarchical association index is greater than or equal to 4, the digital collection is pushed to the user in the ratio of the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status = 4:3:3:2, thereby obtaining the third pushed digital collection; If the hierarchical association index is greater than or equal to 2, the digital collection is pushed to the user in a ratio of the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status = 3:3:3:2, thereby obtaining the third pushed digital collection; If the hierarchical association index is less than 2, the digital collection is pushed to the user in the ratio of the first recommendation status: the second recommendation status: the third recommendation status: the fourth recommendation status = 3:3:3:3 to obtain the third pushed digital collection.

8. A method for digital collection management and targeted sharing according to claim 4, characterized in that: The step of selecting a calibration object from the digital collection, associating it with the digital collection storage model, performing a similarity analysis, and obtaining a similar digital collection family includes: Randomly select a color from the digital collection owned by the user as the calibration color, and then randomly select a graphic line outline as the calibration outline when the calibration color is selected; Searching for the same color of the calibrated color in the direct family of the digital collection feature to which the digital collection belongs, and after finding the same color, recording the outline of the graphic line of the digital collection where the color is located; The recorded graphic outline is compared with the calibrated outline for overlap. If the overlap exceeds 80%, a digital collection family label similar to the user's intention will be added to the digital collection.

9. A method for digital collection management and targeted sharing according to claim 8, characterized in that: The step of regulating the number of shares of the similar digital collection family by recording the browsing conditions of visitors in the similar digital collection family includes: By regularly recording the digital collection mark points of the similar digital collection family, the browsing time of the similar digital collection family and the direct family of digital collections to which the similar digital collection belongs are recorded; If the browsing time of the similar digital collection family belongs to the first intended digital collection, the similar digital collection family is pushed to the user regularly, with a base of 10% of the number of pushed digital collections and an increment of 4%, increasing in a gradient manner, and the period is 10% increment of the total amount of digital collections in the digital collection storage model; If the browsing time of the similar digital collection family belongs to the second intended digital collection, the similar digital collection family is pushed to the user regularly, with an increase of 3% from 5% of the number of pushed digital collections as the base, and the cycle is 10% of the total amount of digital collections in the digital collection storage model; If the browsing time of the approximate digital collection family belongs to the digital collection that the user is not interested in, the approximate digital collection family will be pushed to the user regularly, with an increase of 2% in increments from 0 to the number of pushed digital collections, and the period is 15% of the total amount of digital collections in the digital collection storage model.

10. A method for digital collection management and targeted sharing according to claim 7, characterized in that: The step of detecting the changes of the user's digital collections in real time and establishing a digital collection-oriented sharing plan for the user's digital collections according to the digital collection families to which they belong includes: After pushing the first pushed digital collection, if the user browsing time recorded by the digital collection mark point exceeds 3 to 5 times the historical browsing record of the digital collection, then introduce 30% of the second pushed digital collection; If the browsing time of the user recorded in the digital collection mark point is no more than three times of the historical browsing record of the digital collection, 30% of the third pushed digital collection is introduced; If the browsing time of the user recorded in the digital collection mark point exceeds 5 times of the historical browsing record of the digital collection, 20% of the second pushed digital collection and 20% of the third pushed digital collection are introduced; After introducing the specified number of the first pushed digital collections, the second pushed digital collections, and the third pushed digital collections, 20% of the similar digital collection families are added to form a complete digital collection directional sharing plan.