A figure page display method and system based on interest point recognition

Abstract

The present invention discloses a figure page display method and system based on interest point recognition, which relates to the technical field of interest points of figure pages. The present invention includes visual plane technology detection, visual stereo technology detection and personalized recommendation display. In the visual plane technology detection, the number of historical limited edition figure part browsing times, historical limited edition figure part browsing time and historical limited edition figure collection times of each browsing figure type of each user are counted, and the browsing interest point index of each figure page is analyzed to timely reflect the user's browsing behavior, thereby improving the exposure rate of the figure, and then timely understanding the changes in consumer preferences. In the visual stereo technology detection: through the figure page logged in by each user, the three-dimensional space of each user's figure page image is recorded, and the detailed interest point index of each figure page is analyzed, which improves the user's purchase satisfaction, increases the transaction volume of figure products, and improves the product attractiveness of the figure.

Description

Technical Field

[0001] The present invention relates to the technical field of interest points of a figure page, and in particular to a figure page display method and system based on interest point recognition. Background Art

[0002] With the continuous advancement of technology, the display method of the figure page will become more popular and perfect, bringing more convenience and fun to users. The figure page display method with point of interest recognition provides an innovative and interactive way to display and appreciate figures, which not only enhances the shopping experience of consumers, but also provides a novel viewing method for collectors. However, due to the continuous increase in users, it is impossible to understand the user's figure interest points in time, and thus it is necessary to identify the points of interest of the figure page.

[0003] The existing technology for identifying points of interest on the action figure page can meet the basic requirements, but there are also some potential defects and challenges, which are specifically reflected in the following aspects:

[0004] 1. The research on the browsing interest point index of each figure page in the prior art is not in-depth enough. The number of views of the parts of the historical limited edition figures of each browsing type of figures of each user, the browsing time of the parts of the historical limited edition figures and the number of collections of the historical limited edition figures have a crucial impact on their browsing interest points. Since the browsing interest points of each user on each figure page and the user's attention to the figure page are inconsistent, the user's purchase of each figure is affected, the user's demand for the choice of figures is reduced, the user's browsing behavior cannot be reflected in time, thereby reducing the exposure rate of the figures, and then it is impossible to timely understand the changes in consumer preferences, which weakens the prediction of future market trends.

[0005] 2. The existing technology does not pay enough attention to the fine values ​​of facial expressions on each figure page, resulting in the inability to effectively identify the texture details of each browsed figure type, affecting the interest points of appearance users and detail users, thereby reducing user purchase satisfaction, reducing the transaction volume of figure products, reducing the product attractiveness of the figures, and failing to meet market demand. Summary of the invention

[0006] The purpose of the present invention is to provide a figure page display method based on interest point recognition, which solves the problems existing in the background technology.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions: In the first aspect, a figure page display method based on interest point recognition comprises the following steps:

[0008] According to the user's interest tags and the tags of the figures, the browsing times of historical limited edition figures of each figure type on each figure page, the browsing time of historical limited edition figures and the collection times of historical limited edition figures are counted, and the browsing interest point index of each figure page is analyzed.

[0009] By recording the three-dimensional space of each user's logged-in figure page image, the three-dimensional image data of the figure features of each figure page image is obtained, wherein the three-dimensional image data includes the clothing wrinkle restoration value, facial expression refinement value and joint flexibility of each browsed figure type of each figure page, and then the detail interest point index of each figure page is analyzed.

[0010] Based on the browsing interest point index of each figure page and the detail interest point index of each figure page, the interest point recognition coefficient of each figure page is analyzed, and the push content of the interest point of personalized figure page is constructed, and then each figure page is displayed.

[0011] Furthermore, the browsing interest point index of each figure page is analyzed, and its specific analysis method is: based on the statistically analyzed number of browsing times of historical limited edition figure parts of each browsing type of figure on each figure page, the browsing time of historical limited edition figure parts and the number of collection times of historical limited edition figures, the browsing interest point index of each figure page is analyzed, and its specific calculation method is: ,in Expressed as The first page of the hand-made Viewed figures by historical limited edition figures, Expressed as The total number of limited edition figure parts viewed by figure page, Expressed as The first page of the hand-made The browsing time of historical limited edition figures by type of figures, Expressed as The total browsing time of the figure page for the figure type, the history of the limited edition figure parts, Expressed as The first page of the hand-made Viewed historical limited edition figures collection times, Expressed as The total number of limited edition figures collected by the historical figures of the figure page, Indicates the number of the figure page. , It is expressed as the number of pages of the hand-made figures. Indicates the number of the browsing figure type on the figure page. , Represented as the number of browsed figures of the same type.

[0012] Furthermore, the detailed interest point index of each figure page is analyzed, and its specific analysis method is: comparing the historical consumption frequency of each user of each figure page with the consumption frequency interval corresponding to the appearance user stored in the database; if the historical consumption frequency of a user of a certain figure page is within the consumption frequency interval corresponding to the appearance user, then the user is recorded as the appearance user, and each appearance user is obtained.

[0013] The historical consumption price of each user on each figure page is compared with the consumption price range corresponding to the detail users stored in the database. If the historical consumption price of a user on a figure page is within the consumption price range corresponding to the detail user, the user is recorded as the detail user, and each detail user is obtained.

[0014] The historical consumption frequency and historical consumption price of each user on each figure page are compared with the consumption frequency range corresponding to the appearance user and the consumption price range corresponding to the detail user stored in the database. If the historical consumption frequency of the user on a certain figure page is within the consumption frequency range corresponding to the appearance user and the historical consumption price of the user on a certain figure page is within the consumption price range corresponding to the detail user, the user is recorded as a comprehensive user.

[0015] Analyze the detailed interest point index of each figure page, the specific formula is: ,in Expressed as The first page of the hand-made The detailed interest point index of the appearance user, , Indicates the ID of the appearance user. Expressed as the number of appearance users, Expressed as The first page of the hand-made The detail interest point index of the detail user, , The ID of the detailed user. Expressed as the number of detailed users, Expressed as The first page of the hand-made Comprehensive user's detailed interest point index, , Indicates the number of the comprehensive user. Expressed as the number of comprehensive users.

[0016] Furthermore, the detailed interest point index of each appearance user of each figure page is specifically analyzed by: analyzing the detailed interest point index of each appearance user of each figure page, and the specific calculation formula is: ,in Expressed as The first page of the hand-made The clothing details of the user's appearance are restored in accordance with the index. Expressed as The first page of the hand-made The user experience of each appearance meets the index.

[0017] Furthermore, the clothing detail restoration compliance index of each appearance user on each figure page is specifically analyzed by: extracting each historical purchase record of each appearance user on each figure page from the database, and extracting each historical clothing wrinkle restoration value of each browsing figure type of each historical purchase record, and based on each clothing wrinkle restoration value of each browsing figure type on each figure page, if a browsing figure type on a figure page is consistent with a browsing figure type in a historical purchase record of a certain appearance user on the figure page, then comparing each clothing wrinkle restoration value of the browsing figure type on the figure page with each clothing wrinkle restoration value of the browsing figure type in the historical purchase record of the appearance user, and evaluating the clothing detail restoration compliance index of the appearance user on the figure page, and the specific calculation formula is: ,in, Indicates the first The clothing wrinkle restoration value, , A number indicating the value of the garment's wrinkle restoration. It is expressed as the number of clothing wrinkle restoration values. Indicates the first browsing figure type of the user's historical purchase record for this appearance The clothing wrinkle restoration value is then used to obtain the clothing detail restoration compliance index of each user on each figure page. .

[0018] Furthermore, the experience conformity index of each appearance user of each figure page is specifically analyzed by: extracting each historical purchase order of each appearance user of each figure page from the database, and then extracting the browsed figure type and joint flexibility corresponding to each historical purchase order, mapping to obtain the joint flexibility of each historical purchase order corresponding to each browsed figure type, and then extracting the demand range of joint flexibility of each browsed type of figure; based on the joint flexibility of each browsed figure type of each figure page, if a browsed figure type of a figure page is consistent with the browsed figure type of a certain appearance user of the figure page, then compare the joint flexibility of the appearance user of the figure page with the demand range of joint flexibility of the historical purchase order of the appearance user; if the joint flexibility of the appearance user of the figure page is within the demand range of joint flexibility of the historical purchase order of the appearance user, then record the experience conformity index of the appearance user of the figure page as , otherwise, it is recorded as , , get the user experience index of each appearance of each figure page ,in The value of or .

[0019] Furthermore, the detailed interest point index of each detail user of each figure page is specifically analyzed by: based on the obtained facial expression fine value of each browsing figure type of each figure page, the detailed interest point index of each detail user of each figure page is analyzed, and the specific calculation formula is: ,in Expressed as The first page of the hand-made Browse the facial expression details of the figure type. Represents the detailed reference value of facial expressions for browsing figures in the database.

[0020] Furthermore, the specific calculation formula of the interest point recognition coefficient of each figure page is: .

[0021] Furthermore, the specific analysis method for displaying each figure page is as follows: sorting the interest point recognition coefficients of each figure page in descending order to obtain sorted figure pages.

[0022] Combined with the reference interest point recognition coefficient corresponding to the interest point recognition coefficient interval of each figure page stored in the database, the reference interest point recognition coefficient corresponding to the interest point recognition coefficient interval of each figure page stored in the database is compared with the interest point recognition coefficient, and the interest point recognition coefficient of each reference figure page is screened out, and the interest point recognition coefficient of each reference figure page is subtracted from the actual interest point recognition coefficient of each figure page to obtain the interest point recognition coefficient difference of each figure page, and the interest point recognition coefficient difference of each figure page is processed in descending order to obtain the re-ordered figure interest point recognition page, and then displayed.

[0023] The second aspect of the present invention is a system for executing a figure page display method based on interest point recognition, comprising: a visual plane technology detection module: matching the user's interest tags with the figure tags, counting the number of historical limited edition figure part views, historical limited edition figure browsing time and historical limited edition figure collection times of each browsed figure type on each figure page, and analyzing the browsing interest point index of each figure page.

[0024] Visual stereo technology detection module: used to record the three-dimensional space of each user's figure page image through the figure page logged in by each user, and obtain the three-dimensional image data of the figure features of each figure page image, wherein the three-dimensional image data includes the clothing wrinkle restoration value, facial expression refinement value and joint flexibility of each browsed figure type on each figure page, and then analyze the detail interest point index of each figure page.

[0025] Personalized recommendation display module: Based on the browsing interest point index of each figure page and the detail interest point index of each figure page, the interest point recognition coefficient of each figure page is analyzed, and the push content of the interest point of personalized figure page is constructed, and then each figure page is displayed.

[0026] The beneficial effects of the present invention are:

[0027] 1. By tracking the historical browsing paths and click behaviors of each user on the figure page, counting the number of historical limited edition figure part browsing times, historical limited edition figure part browsing time and historical limited edition figure collection times of each user's browsed figure type, analyzing the browsing interest point index of each figure page, timely reflecting the user's browsing behavior, thereby increasing the exposure rate of the figures, and then timely understanding the changes in consumer preferences, improving the prediction of future market trends.

[0028] 2. By recording the three-dimensional space of each user's logged-in figure page image, the three-dimensional image data of the figure features of each figure page image is obtained, and the detail interest point index of each figure page is analyzed, thereby improving the user's purchase satisfaction, increasing the transaction volume of figure products, improving the product attractiveness of the figures, and meeting market demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 The present invention is a schematic flow chart of the steps for implementing the method.

[0031] Figure 2 It is a schematic diagram of the system structure connection of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Reference Figure 1 As shown, the present invention provides a figure page display method based on interest point recognition, including: step one, visual plane technology detection, step two, visual three-dimensional technology detection and step three, personalized recommendation display.

[0034] Step 1: Visual plane technology detection: Match the user's interest tags with the tags of the figures, count the number of views of historical limited edition figures of each figure type on each figure page, the browsing time of historical limited edition figures, and the number of collections of historical limited edition figures, and analyze the browsing interest point index of each figure page.

[0035] In the above embodiment, the browsing interest point index of each figure page is analyzed, and its specific analysis method is: based on the statistical number of browsing times of historical limited edition figure parts of each browsing type of figure on each figure page, the browsing time of historical limited edition figure parts and the number of collection times of historical limited edition figures, the browsing interest point index of each figure page is analyzed, and its specific calculation method is: ,in Expressed as The first page of the hand-made Viewed figures by historical limited edition figures, Expressed as The total number of limited edition figure parts viewed by figure page, Expressed as The first page of the hand-made The browsing time of historical limited edition figures by type of figures, Expressed as The total browsing time of the figure page for the figure type, the history of the limited edition figure parts, Expressed as The first page of the hand-made Viewed historical limited edition figures collection times, Expressed as The total number of limited edition figures collected by the historical figures of the figure page, Indicates the number of the figure page. , It is expressed as the number of pages of the hand-made figures. Indicates the number of the browsing figure type on the figure page. , Represented as the number of browsed figures of the same type.

[0036] In step one, visual plane technology detection, by tracking each user's historical browsing path and click behavior on the figure page, statistics are collected on the number of historical limited edition figure parts browsed by each user for each figure type, the historical limited edition figure part browsing time, and the number of historical limited edition figure collections, and the browsing interest point index of each figure page is analyzed to timely reflect the user's browsing behavior, thereby increasing the exposure rate of the figures, and then timely understanding the changes in consumer preferences, improving the prediction of future market trends.

[0037] Step 2: Visual stereoscopic technology detection: It is used to record the three-dimensional space of each user's figure page image through each user's logged-in figure page, and obtain the three-dimensional image data of the figure features of each figure page image, wherein the three-dimensional image data includes the clothing wrinkle restoration value, facial expression refinement value and joint flexibility of each browsed figure type of each figure page, and then analyze the detail interest point index of each figure page.

[0038] It should be noted that the clothing wrinkle restoration value, facial expression refinement value and joint flexibility of each browsed figure type on each figure page are obtained by analyzing the existing detail analysis technology, texture analysis technology and joint analysis technology respectively.

[0039] It should be noted that the facial expression detail value is expressed as a numerical value that specifically expresses the surface texture of each figure.

[0040] In the above embodiment, the detailed interest point index of each figure page is analyzed, and the specific analysis method is: comparing the historical consumption frequency of each user of each figure page with the consumption frequency interval corresponding to the appearance user stored in the database, if the historical consumption frequency of a user of a certain figure page is within the consumption frequency interval corresponding to the appearance user, then the user is recorded as the appearance user, and each appearance user is obtained.

[0041] The historical consumption price of each user on each figure page is compared with the consumption price range corresponding to the detail users stored in the database. If the historical consumption price of a user on a figure page is within the consumption price range corresponding to the detail user, the user is recorded as the detail user, and each detail user is obtained.

[0042] The historical consumption frequency and historical consumption price of each user on each figure page are compared with the consumption frequency range corresponding to the appearance user and the consumption price range corresponding to the detail user stored in the database. If the historical consumption frequency of the user on a certain figure page is within the consumption frequency range corresponding to the appearance user and the historical consumption price of the user on a certain figure page is within the consumption price range corresponding to the detail user, the user is recorded as a comprehensive user.

[0043] Analyze the detailed interest point index of each figure page, the specific formula is: ,in Expressed as The first page of the hand-made The detailed interest point index of the appearance user, , Indicates the ID of the appearance user. Expressed as the number of appearance users, Expressed as The first page of the hand-made The detail interest point index of the detail user, , The ID of the detailed user. Expressed as the number of detailed users, Expressed as The first page of the hand-made Comprehensive user's detailed interest point index, , Indicates the number of the comprehensive user. Expressed as the number of comprehensive users.

[0044] In the above embodiment, the detailed interest point index of each appearance user of each figure page is specifically analyzed by: analyzing the detailed interest point index of each appearance user of each figure page, and the specific calculation formula is: ,in Expressed as The first page of the hand-made The clothing details of the user's appearance are restored in accordance with the index. Expressed as The first page of the hand-made The user experience of each appearance meets the index.

[0045] In the above embodiment, the clothing detail restoration compliance index of each appearance user on each figure page is specifically analyzed by: extracting each historical purchase record of each appearance user on each figure page from the database, and extracting each historical clothing wrinkle restoration value of the browsed figure type of each historical purchase record, and based on each clothing wrinkle restoration value of each browsed figure type on each figure page, if a browsed figure type on a figure page is consistent with a browsed figure type of a historical purchase record of a certain appearance user on the figure page, then the clothing wrinkle restoration value of the browsed figure type on the figure page is compared with the clothing wrinkle restoration value of the browsed figure type of the historical purchase record of the appearance user, and the clothing detail restoration compliance index of the appearance user on the figure page is evaluated, and the specific calculation formula is: ,in, Indicates the first The clothing wrinkle restoration value, , A number indicating the value of the garment's wrinkle restoration. It is expressed as the number of clothing wrinkle restoration values. Indicates the first browsing figure type of the user's historical purchase record for this appearance The clothing wrinkle restoration value is then used to obtain the clothing detail restoration compliance index of each user on each figure page. .

[0046] In the above embodiment, the experience conformity index of each appearance user of each figure page is specifically analyzed by: extracting each historical purchase order of each appearance user of each figure page from the database, and then extracting the browsed figure type and joint flexibility corresponding to each historical purchase order, mapping to obtain the joint flexibility of each historical purchase order corresponding to each browsed figure type, and then extracting the demand range of joint flexibility of each browsed type of figure; based on the joint flexibility of each browsed figure type of each figure page, if a browsed figure type of a figure page is consistent with the browsed figure type of a certain appearance user of the figure page, then compare the joint flexibility of the appearance user of the figure page with the demand range of joint flexibility of the historical purchase order of the appearance user; if the joint flexibility of the appearance user of the figure page is within the demand range of joint flexibility of the historical purchase order of the appearance user, then record the experience conformity index of the appearance user of the figure page as , otherwise, it is recorded as , , get the user experience index of each appearance of each figure page ,in The value of or .

[0047] In the above embodiment, the detailed interest point index of each detail user of each figure page is specifically analyzed by: based on the obtained facial expression fine value of each browsing figure type of each figure page, the detailed interest point index of each detail user of each figure page is analyzed, and the specific calculation formula is: ,in Expressed as The first page of the hand-made Browse the facial expression details of the figure type. Represents the detailed reference value of facial expressions for browsing figures in the database.

[0048] It should be noted that the specific analysis method of the detail interest point index of each comprehensive user of each figure page is: consistent with the analysis method of the detail interest point index of each appearance user of each figure page, the first detail interest point index of each comprehensive user of each figure page is analyzed to obtain the first detail interest point index of each comprehensive user of each figure page, and consistent with the analysis method of the detail interest point index of each detail user of each figure page, the second detail interest point index of each comprehensive user of each figure page is analyzed to obtain the first detail interest point index and the second detail interest point index of each comprehensive user of each figure page are added together, and divided by 2 to obtain the detail interest point index of each comprehensive user of each figure page.

[0049] In step 2, visual stereo technology detection: through the logged-in figure page of each user, the three-dimensional space of the figure page image of each user is recorded, the three-dimensional image data of the figure features of each figure page image is obtained, and the detail interest point index of each figure page is analyzed, thereby improving the user's purchase satisfaction, increasing the transaction volume of the figure products, improving the product attractiveness of the figure, and meeting the market demand.

[0050] Step 3: Personalized recommendation display: Based on the browsing interest point index of each figure page and the detail interest point index of each figure page, the interest point recognition coefficient of each figure page is analyzed, and the push content of the personalized interest point of the figure page is constructed, and then each figure page is displayed.

[0051] In the above embodiment, the specific calculation formula of the interest point recognition coefficient of each figure page is: .

[0052] In the above embodiment, the specific analysis method for displaying each figure page is as follows: sorting the interest point recognition coefficients of each figure page in descending order to obtain sorted figure pages.

[0053] Combined with the reference interest point recognition coefficient corresponding to the interest point recognition coefficient interval of each figure page stored in the database, the reference interest point recognition coefficient corresponding to the interest point recognition coefficient interval of each figure page stored in the database is compared with the interest point recognition coefficient, and the interest point recognition coefficient of each reference figure page is screened out, and the interest point recognition coefficient of each reference figure page is subtracted from the actual interest point recognition coefficient of each figure page to obtain the interest point recognition coefficient difference of each figure page, and the interest point recognition coefficient difference of each figure page is processed in descending order to obtain the re-ordered figure interest point recognition page, and then displayed.

[0054] Reference Figure 2 As shown, a system for executing a figure page display method based on interest point recognition includes: a visual plane technology detection module: matching the user's interest tags with the figure tags, counting the number of historical limited edition figure part views, historical limited edition figure browsing time and historical limited edition figure collection times of each figure type browsed on each figure page, and analyzing the browsing interest point index of each figure page.

[0055] Visual stereo technology detection module: used to record the three-dimensional space of each user's figure page image through the figure page logged in by each user, and obtain the three-dimensional image data of the figure features of each figure page image, wherein the three-dimensional image data includes the clothing wrinkle restoration value, facial expression refinement value and joint flexibility of each browsed figure type on each figure page, and then analyze the detail interest point index of each figure page.

[0056] Personalized recommendation display module: Based on the browsing interest point index of each figure page and the detail interest point index of each figure page, the interest point recognition coefficient of each figure page is analyzed, and the push content of the interest point of personalized figure page is constructed, and then each figure page is displayed.

[0057] It should be noted that the database is used to store the total number of times, total duration and total number of collections of historical limited edition figure parts of each figure type browsed on each figure page, the consumption frequency range corresponding to the appearance users, the clothing wrinkle restoration value of each appearance user on each figure page, the joint flexibility of each historical purchase order of each appearance user on each figure page, the detailed reference value of facial expression of the figure type browsed, the reference interest point recognition coefficient corresponding to each order number prediction coefficient range, the consumption frequency range corresponding to the appearance users and the consumption frequency range corresponding to the detail users.

[0058] It should be noted that the visual plane technology detection module is connected to the database, the visual stereo technology detection module is connected to the database, the visual plane technology detection module is connected to the visual stereo technology detection module, and the visual stereo technology detection module is connected to the personalized recommendation display module.

[0059] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A figure page display method based on point of interest recognition, characterized in that: include: According to the user's interest tags and the tags of the figures, the browsing times of the parts of the historical limited edition figures of each figure type on each figure page, the browsing time of the historical limited edition figures, and the number of collections of the historical limited edition figures are counted, and the browsing interest point index of each figure page is analyzed; By recording the three-dimensional space of each user's figure page image for each user's login, the three-dimensional image data of the figure features of each figure page image is obtained, wherein the three-dimensional image data includes the clothing wrinkle restoration value, facial expression refinement value and joint flexibility of each browsed figure type of each figure page, and then the detail interest point index of each figure page is analyzed; Based on the browsing interest point index of each figure page and the detail interest point index of each figure page, the interest point recognition coefficient of each figure page is analyzed, and the push content of the interest point of personalized figure page is constructed, and then each figure page is displayed.

2. According to the method of claim 1, the method is characterized in that: The specific analysis method of analyzing the browsing interest point index of each figure page is as follows: Based on the statistics of the number of views of the parts of historical limited edition figures of each browsing type of figures on each figure page, the browsing time of the parts of historical limited edition figures, and the number of collections of historical limited edition figures, the browsing interest point index of each figure page is analyzed. The specific calculation method is: ,in Expressed as The first page of the hand-made Viewed figures by historical limited edition figures, Expressed as The total number of limited edition figure parts viewed by figure page, Expressed as The first page of the hand-made The browsing time of historical limited edition figures by type of figures, Expressed as The total time spent browsing the history of limited edition figures by figure page, Expressed as The first page of the hand-made Viewed historical limited edition figures collection times by figure type, Expressed as The total number of limited edition figures collected by the historical figures of the figure page, Indicates the number of the figure page. , It is expressed as the number of pages of the hand-made figures. Indicates the number of the browsing figure type on the figure page. , Represented as the number of browsed figures of the same type.

3. The method for displaying a figurine page based on point of interest recognition according to claim 2, characterized in that: The specific analysis method of analyzing the detail interest point index of each figure page is as follows: Compare the historical consumption frequency of each user on each figurine page with the consumption frequency interval corresponding to the appearance user stored in the database. If the historical consumption frequency of a user on a figurine page is within the consumption frequency interval corresponding to the appearance user, then record the user as the appearance user, and obtain each appearance user; Compare the historical consumption price of each user on each figurine page with the consumption price range corresponding to the detail user stored in the database. If the historical consumption price of a user on a figurine page is within the consumption price range corresponding to the detail user, record the user as the detail user, and obtain the detail users; The historical consumption frequency and historical consumption price of each user on each figurine page are compared with the consumption frequency interval corresponding to the appearance user and the consumption price interval corresponding to the detail user stored in the database. If the historical consumption frequency of the user on a figurine page is within the consumption frequency interval corresponding to the appearance user and the historical consumption price of the user on a figurine page is within the consumption price interval corresponding to the detail user, the user is recorded as a comprehensive user; Analyze the detailed interest point index of each figure page, the specific formula is: ,in Expressed as The first page of the hand-made The detailed interest point index of the appearance user, , Indicates the ID of the appearance user. Expressed as the number of appearance users, Expressed as The first page of the hand-made The detail interest point index of the detail user, , The ID of the detailed user. Expressed as the number of detailed users, Expressed as The first page of the hand-made Comprehensive user's detailed interest point index, , Indicates the number of the comprehensive user. Expressed as the number of comprehensive users.

4. The method for displaying a figurine page based on point of interest recognition according to claim 3 is characterized in that: The detailed interest point index of each appearance user of each figure page is analyzed in the following specific method: Analyze the detailed interest index of each appearance of each figure page, and the specific calculation formula is: ,in Expressed as The first page of the hand-made The clothing details of the user's appearance are restored in accordance with the index. Expressed as The first page of the hand-made The user experience of each appearance meets the index.

5. The method for displaying a figurine page based on point of interest recognition according to claim 4, characterized in that: The clothing detail restoration compliance index of each appearance user on each figure page is analyzed in the following specific method: The historical purchase records of each appearance user of each figure page are extracted from the database, and the historical clothing wrinkle restoration values ​​of the browsed figure types of each historical purchase record are extracted. Based on the clothing wrinkle restoration values ​​of each browsed figure type of each figure page, if a browsed figure type of a figure page is consistent with a browsed figure type of a historical purchase record of a certain appearance user of the figure page, the clothing wrinkle restoration values ​​of the browsed figure type of the figure page are compared with the clothing wrinkle restoration values ​​of the browsed figure type of the historical purchase record of the appearance user, and the clothing detail restoration compliance index of the appearance user of the figure page is evaluated. The specific calculation formula is: ,in, Indicates the first The clothing wrinkle restoration value, , A number representing the value of clothing wrinkle restoration. It is expressed as the number of clothing wrinkle restoration values. Indicates the first browsing figure type of the user's historical purchase record for this appearance The clothing wrinkle restoration value is then used to obtain the clothing detail restoration compliance index of each user on each figure page. .

6. The method for displaying a figurine page based on point of interest recognition according to claim 4, characterized in that: The user experience compliance index of each appearance of each figure page is analyzed in the following specific method: The historical purchase orders of each appearance user of each figure page are extracted from the database, and then the browsed figure types and joint flexibility corresponding to each historical purchase order are extracted, and the joint flexibility of each historical purchase order corresponding to each browsed figure type is mapped, and then the demand range of joint flexibility of each browsed type of figure is extracted. Based on the joint flexibility of each browsed figure type of each figure page, if a browsed figure type of a figure page is consistent with the browsed figure type of a certain appearance user of the figure page, then the joint flexibility of the appearance user of the figure page is compared with the demand range of joint flexibility of the historical purchase order of the appearance user. If the joint flexibility of the appearance user of a figure page is within the demand range of joint flexibility of the historical purchase order of the appearance user, then the experience compliance index of the appearance user of the figure page is recorded as , otherwise, it is recorded as , , get the user experience index of each appearance of each figure page ,in The value of or .

7. The method for displaying a figurine page based on point of interest recognition according to claim 3, characterized in that: The specific analysis method of the detail interest point index of each detail user of each figure page is as follows: Based on the obtained facial expression fine values ​​of each browsing figure type on each figure page, the detail interest point index of each detail user on each figure page is analyzed, and the specific calculation formula is: ,in Expressed as The first page of the hand-made Browse the facial expression details of the figure type. Represents the detailed reference value of facial expressions for browsing figures in the database.

8. The method for displaying a figurine page based on point of interest recognition according to claim 3, characterized in that: The specific calculation formula of the interest point recognition coefficient of each figure page is: .

9. The method for displaying a figurine page based on point of interest recognition according to claim 8, characterized in that: The specific analysis method for displaying each figure page is as follows: Sorting the interest point recognition coefficients of each figure page in descending order to obtain a sorted figure page; Combined with the reference interest point recognition coefficient corresponding to the interest point recognition coefficient interval of each figure page stored in the database, the reference interest point recognition coefficient corresponding to the interest point recognition coefficient interval of each figure page stored in the database is compared with the interest point recognition coefficient, and the interest point recognition coefficient of each reference figure page is screened out, and the interest point recognition coefficient of each reference figure page is subtracted from the actual interest point recognition coefficient of each figure page to obtain the interest point recognition coefficient difference of each figure page, and the interest point recognition coefficient difference of each figure page is processed in descending order to obtain the re-ordered figure interest point recognition page, and then displayed.

10. A system for executing the method for displaying a figurine page based on point of interest recognition as described in any one of 1 to 9, characterized in that: include: Visual plane technology detection module: Matches the user's interest tags with the tags of the figures, counts the number of views of the parts of the historical limited edition figures of each figure type on each figure page, the browsing time of the historical limited edition figures, and the number of collections of the historical limited edition figures, and analyzes the browsing interest point index of each figure page; Visual stereo technology detection module: used to record the three-dimensional space of each user's figure page image through each user's logged-in figure page, and obtain the three-dimensional image data of the figure features of each figure page image, wherein the three-dimensional image data includes the clothing wrinkle restoration value, facial expression refinement value and joint flexibility of each browsed figure type of each figure page, and then analyze the detail interest point index of each figure page; Personalized recommendation display module: Based on the browsing interest point index of each figure page and the detail interest point index of each figure page, the interest point recognition coefficient of each figure page is analyzed, and the push content of the interest point of personalized figure page is constructed, and then each figure page is displayed.

Images