CN111414509A

CN111414509A - Method and device for providing picture material for small program

Info

Publication number: CN111414509A
Application number: CN202010201754.9A
Authority: CN
Inventors: 江少华
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2020-03-20
Filing date: 2020-03-20
Publication date: 2020-07-14
Anticipated expiration: 2040-03-20
Also published as: CN111414509B

Abstract

The embodiment of the specification discloses a method and a device for providing picture materials for an applet. The method comprises the following steps: acquiring information of an applet, and mining a keyword related to the applet from the information of the applet; vectorizing the keywords to obtain vectors of the keywords; calculating the similarity between the vector of the keyword and the vectors of the plurality of pictures; and selecting pictures serving as image materials of the small programs from the plurality of pictures according to the similarity.

Description

Method and device for providing picture material for small program

Technical Field

The present specification relates to software technology, and more particularly, to a method of providing a picture material for an applet and an apparatus for providing a picture material for an applet.

Background

With the development of software technology and network technology, more and more applets are emerging. The small program is a program which can be directly loaded and used (namely, searched and used) after being installed and searched without downloading. The applet can be carried on a native application or a web application, the native application is an application program directly running on a current operating system, the web application refers to a web application needing to run in a browser, and the applet can realize functions of the applet by relying on the native application and the web application.

Typically, a native application or a web application will provide an applet management platform for an applet to provide a number of different applets to users for use, the applets may belong to different operators, and in some cases, the platform side may need to manage the presentation of the applets.

Disclosure of Invention

The embodiment disclosed by the specification provides a method and a device for providing picture materials for an applet.

According to a first aspect disclosed herein, there is provided a method of providing photo material for an applet, comprising the steps of:

acquiring information of an applet, wherein the information of the applet comprises the name, the category and description information of the applet;

mining keywords about the applet from the information of the applet;

vectorizing the keywords to obtain vectors of the keywords;

calculating the similarity between the vector of the keyword and the vectors of the label information of the plurality of pictures;

and selecting pictures serving as image materials of the small programs from the plurality of pictures according to the similarity.

Optionally, selecting, according to the similarity, a picture from the plurality of pictures as an image material of the applet, including:

and configuring the picture with the highest similarity as an icon or a background picture of the applet.

Optionally, the information of the applet further includes information displayed on a main page of the applet.

Optionally, vectorizing the keyword to obtain a vector of the keyword includes:

and carrying out embedded vector calculation on the keywords through a BERT algorithm to obtain vectors of the keywords.

Optionally, the vector of the tag information of the picture is obtained by:

acquiring label information of the picture;

and carrying out embedded vector calculation on the label information of the picture through a BERT algorithm to obtain a vector of the label information of the picture.

Optionally, calculating similarity between the vector of the keyword and the vector of the tag information of the plurality of pictures includes:

calculating cosine similarity of the vector of the keyword and the vectors of the label information of the plurality of pictures; alternatively, the first and second electrodes may be,

and calculating Euclidean distances between the vector of the keyword and the vectors of the label information of the plurality of pictures.

According to a second aspect disclosed in the present specification, there is provided a method of providing a picture material for an applet, comprising the steps of:

acquiring information of a plurality of small programs, wherein the information of the small programs comprises names, categories and description information of the small programs;

mining a common keyword about the plurality of applets from the information of the plurality of applets;

vectorizing the common keywords to obtain vectors of the common keywords;

calculating the similarity of the vector of the common keyword and the vectors of the label information of the plurality of pictures;

and selecting pictures serving as image materials of the aggregation pages of the small programs from the plurality of pictures according to the similarity.

Optionally, selecting, according to the similarity, a picture from the plurality of pictures as an image material of an aggregated page of the plurality of applets includes:

and configuring the picture with the highest similarity as an icon or a background picture of an aggregation page of the plurality of small programs.

Optionally, vectorizing the common keyword to obtain a vector of the common keyword includes:

and carrying out embedded vector calculation on the common keywords through a BERT algorithm to obtain vectors of the common keywords.

Optionally, the vector of the tag information of the picture is obtained by:

acquiring label information of the picture;

Optionally, calculating similarity between the vector of the common keyword and the vector of the tag information of the plurality of pictures includes:

calculating cosine similarity of the vector of the common keyword and the vectors of the label information of the plurality of pictures; alternatively, the first and second electrodes may be,

and calculating Euclidean distances between the vector of the common keyword and the vectors of the label information of the plurality of pictures.

According to a third aspect disclosed in the present specification, there is provided an apparatus for providing a picture material for an applet, comprising:

the system comprises a keyword extraction module, a keyword extraction module and a keyword extraction module, wherein the keyword extraction module is used for acquiring information of an applet, and the information of the applet comprises the name, the category and description information of the applet; mining keywords about the applet from the information of the applet;

the vectorization processing module is used for vectorizing the keywords to obtain vectors of the keywords;

the similarity calculation module is used for calculating the similarity of the vector of the keyword and the vector of the label information of the plurality of pictures;

and the selecting module is used for selecting pictures serving as image materials of the small programs from the plurality of pictures according to the similarity.

According to a fourth aspect disclosed in the present specification, there is provided an apparatus for providing a picture material for an applet, comprising:

the system comprises a keyword extraction module, a keyword extraction module and a keyword extraction module, wherein the keyword extraction module is used for acquiring information of a plurality of small programs, and the information of the small programs comprises names, categories and description information of the small programs; mining a common keyword about the plurality of applets from the information of the plurality of applets;

the vectorization processing module is used for vectorizing the common keywords to obtain vectors of the common keywords;

the similarity calculation module is used for calculating the similarity of the vector of the common keyword and the vector of the label information of the plurality of pictures;

and the selecting module is used for selecting pictures serving as image materials of the aggregation pages of the small programs from the pictures according to the similarity.

According to a fifth aspect disclosed herein, there is provided an apparatus for providing photo material for an applet, comprising a processor and a memory, the memory storing a computer program which, when executed by the processor, implements the method disclosed in the first or second aspect of the present specification.

Features of embodiments of the present specification and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description, serve to explain the principles of the embodiments of the specification.

FIG. 1 is a schematic diagram of an applet management system provided in an embodiment of the present description;

fig. 2 is a flowchart of a method for providing picture material for an applet according to an embodiment of the present specification;

fig. 3 is a flowchart of a method for providing picture material for an applet according to an embodiment of the present specification;

fig. 4 is a block diagram of an apparatus for providing picture material for an applet, provided in an embodiment of the present specification;

fig. 5 is a block diagram of an apparatus for providing picture material for an applet, provided in an embodiment of the present specification;

fig. 6 is a block diagram of an apparatus for providing picture material for an applet, provided in an embodiment of the present specification;

fig. 7(a) -7(e) are schematic diagrams of applet-related pages provided in an embodiment of the present specification.

Detailed Description

Various exemplary embodiments of the present specification will now be described in detail with reference to the accompanying drawings.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the embodiments, their application, or uses.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

< applet management System >

Fig. 1 is a block diagram of an applet management system provided in an embodiment of the present specification. As shown in fig. 1, the applet management system includes an applet provided by an applet management platform 101 and a plurality of applet providers 103. The applet management platform 101 and the plurality of applet providers 103 may be communicatively coupled via a network 102.

The applet managing platform 101 may be a server for managing the applet, and may have various functions of auditing, recording, online, offline, monitoring, and the like for the applet. The configuration of the server may include, but is not limited to: processor 1011, memory 1012, interface 1013, communication device 1014, input device 1015, output device 1016. The processor 1011 may include, but is not limited to, a central processing unit CPU, a microprocessor MCU, or the like. The memory 1012 may include, but is not limited to, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. Interface device 1013 may include, but is not limited to, a USB interface, a serial interface, a parallel interface, and the like. The communication device 1014 is capable of wired or wireless communication, for example, and may specifically include WiFi communication, bluetooth communication, 2G/3G/4G/5G communication, and the like. Input devices 1015 may include, but are not limited to, a keyboard, a mouse, and the like. Output device 1016 may include, but is not limited to, a display screen or the like. The server may be configured to include only some of the above devices.

The applet provider 103 may also be a server of the applet operator, the configuration of which may include, but is not limited to: processor 1031, memory 1032, interface device 1033, communication device 1034, input device 1035, and output device 1036. The processor 1031 may include, but is not limited to, a central processing unit CPU, a microprocessor MCU, and the like. The memory 1032 may include, but is not limited to, a ROM (read only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, and the like. Interface device 1033 may include, but is not limited to, a USB interface, a serial interface, a parallel interface, and the like. The communication device 1034 is capable of wired or wireless communication, for example, and specifically may include WiFi communication, bluetooth communication, 2G/3G/4G/5G communication, and the like. Input devices 1035 may include, but are not limited to, a keyboard, a mouse, and the like. The output devices 1036 may include, but are not limited to, a display screen or the like. The server may be configured to include only some of the above devices.

In one embodiment applied to the present description, the applet management platform 101 is responsible for managing applets to provide a plurality of different applets to a user. The plurality of applets may be of different categories, such as a gaming category, a financial category, a utility payment service category, a shopping category, a ticketing category, and the like. Each applet may include a number of specific applets below it, for example, a game type applet may include a number of different game applets. The utility payment service class applet may include a water fee applet, an electricity fee applet, a gas fee applet, etc.

The applet management system shown in fig. 1 is illustrative only and is not intended to suggest any limitation as to the scope of use or use of the embodiments of the specification. It will be appreciated by those skilled in the art that although the foregoing describes a number of devices of an applet management platform and applet provider, embodiments of the present description may refer to only some of the devices therein. Those skilled in the art can design instructions based on the disclosed embodiments of the present specification. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

< method for providing picture material for applet >

The applet is a program which can be directly loaded for use (namely search-and-use) after being installed and searched without downloading, and can be loaded on a native application or a web application. A developer (e.g., a third party developer) may develop an applet that is piggybacked onto a native application or a web application using an interface provided by the native application or the web application. The user may enter a specific applet or an applet center using the search functionality of the native application or web application, or based on an active presentation of the native application or web application.

7(a) -7(c) illustrate the page conversion process from native to applet. Fig. 7(a) shows a home page of a native application, which is a payment application, and a plurality of interaction controls such as "scan", "pay", "receive", "credit", "bank card", "applet" are arranged on the home page, and when a user clicks a certain interaction control, a function corresponding to the interaction control is executed or a page corresponding to the interaction control is jumped to. When the user clicks on "applet", jump to the applet centre page shown in figure 7 (b). On the small program center page, a plurality of small programs such as 'red packet', 'payment', 'lottery' and the like are arranged, wherein the 'payment' small program is the aggregation of a plurality of payment small programs (hereinafter, referred to as 'payment' aggregation small program). When the user clicks a certain applet, the page corresponding to the applet is jumped to. For example, when the user clicks on the "pay" syndication applet, a jump is made to the pay center page shown in FIG. 7 (c). On the page of the payment center, a plurality of specific payment small programs of mobile phone fee, broadband fee, electric fee, water fee, gas fee and heating fee are arranged. And when the user clicks a specific payment applet, jumping to a page corresponding to the specific payment applet so as to realize a corresponding payment function. Through the specific payment small programs, the user can realize the functions of paying mobile phone fee, broadband fee, electric fee, water fee, fuel gas fee and heating air fee respectively.

As can be seen from fig. 7(a) -7(c), each applet is displayed to the user in the form of a rectangular box combined with a text label, which is not good enough in appearance and is not good for the user to understand the usage of the applet. By utilizing the method for providing the image materials for the small program, provided by the embodiment of the specification, the small program can be automatically and efficiently matched with the proper image, so that the page is beautified, the user can more intuitively understand the application of the small program, and the probability of using the small program by the user is improved.

< first embodiment >

Referring to fig. 2, the embodiment provides a method for an applet to photograph material, comprising the steps of:

s202, acquiring information of the small program, wherein the information of the small program comprises the name, the category and the description information of the small program.

The name of the applet may be the name of the applet given by the applet provider, such as "XX shopping net", "XX movie ticket", "red pack", "pay" and "draw", and may be used for the purpose of the applet.

The category of the applet is a category that is verified and confirmed by the applet management platform, and is related to the use thereof. The category of the small program can be game category, financing category, utility payment service category, shopping category, ticket category, etc., or can be more detailed category, such as fresh category and clothing category. The lottery possibly belongs to the category of shopping, and commodity samples or commodity coupons are issued to users in a lottery mode to enlarge the influence of commodities and attract the users to browse and purchase related commodities.

In a specific example, an applet may correspond to multiple categories, which may be categories of different angles. For example, an applet that is dedicated to a group movie ticket sales service may have two categories, "group buy" and "movie ticket". For example, a shopping applet for a overseas mother-and-baby product may have two categories, "overseas merchandise" and "mother-and-baby". A "red-pack" applet may have two categories, "game" and "social". The "pay" applet may have two categories, "daily life" and "pay".

In a specific example, an applet may correspond to multiple classes having a hierarchical relationship. For example, a category of applets that sell women's clothing includes "clothing" and "women's clothing," where "women's clothing" is a subcategory under the category "clothing". For example, a category of small programs that sell fruit includes "fresh" and "fruit," where "fruit" is a subcategory under the category "fresh".

The description of the applet, which may also contain a description of the use of the applet, may be set by the applet provider or may be set by the applet management platform. For example, the description of the applet may be "sell case discount ladies". For example, a description of an applet that pays a cell phone fee might be "XX mobile communications company". For example, the description of the applet may be "public interest donation platform initiated by XX", which embodies the use of the applet.

The information of the applet may also include information presented by the main page of the applet. The main page of the applet is the page to which the user jumps after clicking on the applet. For example, for a small program paying the mobile phone fee, an input box labeled as "mobile phone number" and an input box labeled as "recharge amount" may be provided on the main page of the small program, so that the user can input the mobile phone number and the recharge amount that the user wants to recharge, and the "mobile phone number" and the "recharge amount" are information displayed on the main page. It can be seen that the information presented by the main page of the applet is relevant to the purpose of the applet.

The above-mentioned information of the applet is stored in the applet management platform, or may be acquired from the applet provider.

And S204, excavating key words related to the small programs from the information of the small programs.

In this step, keywords about the applet may be mined from the information of the applet by a keyword mining algorithm.

In a specific example, in step S204, keyword mining may be performed using textRank (text ranking) algorithm. the textRank algorithm is originally used as an algorithm for ranking the importance of the web pages, and is applied to mining keywords of texts. the textRank algorithm constructs a network through adjacent relations among words, then iteratively calculates rank values of all word nodes, ranks the rank values, and forms keywords by word nodes corresponding to rank values in the front ranking. Specifically, in one embodiment, the process of mining the keywords of the applet from the information of the applet by using the textRank algorithm is as follows:

s2042, performing word segmentation and part-of-speech tagging on an original text formed by the information of the small program, filtering out stop words, and only keeping words with specified parts-of-speech (nouns, verbs and adjectives) as candidate words.

And S2044, constructing a candidate word graph G (V, E), wherein V is a node set, and E is an edge set. And the node set V is composed of the candidate words obtained in the step S2042, and an edge between any two nodes is constructed by adopting a co-occurrence relation to obtain an edge set E.

And S2046, iteratively propagating the weight of each node in the candidate word graph until convergence.

S2048, carrying out reverse ordering on the node weights, and thus obtaining a plurality of most important words as candidate keywords.

And S2050, marking the candidate keywords in the original text, and if adjacent phrases can be formed, taking the adjacent phrases as the keywords of the applet. And if the adjacent phrases cannot be formed, taking the candidate keywords as the keywords of the small program.

And (4) carrying out keyword mining by using a textRank algorithm, so that the keywords of the document can be extracted by using semantic association among words in the document, wherein the keywords can be separated from the background of a corpus.

And S206, vectorizing the key words of the small program to obtain the vector of the key words of the small program.

In one embodiment, the embedded vector (Embedding) calculation is performed on the keywords by a BERT (Bidirectional Encoder from transformer) algorithm to obtain a vector of the keywords of the applet. One feature of embedded vector (Embedding) calculation is that it can implement establishing a mapping from a high-dimensional vector to a low-dimensional vector, and using the low-dimensional vector to represent a keyword can reduce the calculation amount of step S208.

The BERT algorithm is a pre-training model of N L P (Natural L and generalized processing Natural language processing). the BERT algorithm is a bidirectional encoder algorithm, information of a word before and a word after the word can be considered when a word is processed, so that context semantics can be obtained, character level, word level, sentence level and even sentence relation characteristics can be fully described, a computer can be helped to better understand the language like a human, slight differences among words can be better understood by using the BERT algorithm, and the obtained vector can better represent the real meaning of a keyword of a small program.

And S208, respectively calculating the similarity of the vector of the keyword and the vector of the label information of the plurality of pictures.

In step S208, the gallery has a plurality of pictures, and the pictures in the gallery have tags, which are labels for characters of the pictures. The picture provider can add labels to the pictures and then upload the pictures to the gallery. Or, when the picture is received, the gallery manager adds a label to the picture. A picture may have one or more labels, for example, a picture may be labeled with two labels, "gift" and "gift".

In the case that the picture has a tag, in step S208, the tag information of the picture may be obtained, and an Embedding vector (Embedding) calculation is performed on the tag information of the picture by a BERT algorithm to obtain a vector of the tag information of the picture as a vector of the tag information of the picture. One feature of embedded vector (Embedding) calculation is that it can implement establishing a mapping from a high-dimensional vector to a low-dimensional vector, and using the low-dimensional vector to represent a picture, so as to reduce the calculation amount of step S208.

And calculating the similarity between the vector of the keyword of the small program and the vectors of the label information of the pictures, wherein the similarity between the vector of the keyword of the small program and the vectors of the label information of the pictures can reflect the association degree between the keyword of the small program and the pictures.

In one embodiment, cosine similarity of a vector of keywords of the applet and a vector of tag information of the picture is calculated. Cosine similarity is a measure of similarity between two vectors in a vector space by measuring their cosine of their angle. The range of cosine values is between [ -1,1], and the more the cosine values approach 1, the closer the direction of the vector of the keyword of the applet and the vector of the tag information of the picture is, the higher the association degree of the keyword of the applet and the picture is. The more the cosine value approaches-1, the more the direction of the vector indicating the keyword of the applet and the vector of the tag information of the picture are opposite, the lower the degree of association between the keyword of the applet and the picture is.

In one embodiment, the distance between the vector of the keyword of the applet and the vector of the tag information of the picture is calculated, and the closer the distance, the higher the similarity between the two. For example, the euclidean distance of the vector of the keyword of the applet and the vector of the tag information of the picture is calculated. The smaller the euclidean distance between the vector of the keyword of the applet and the vector of the tag information of the picture is, the higher the similarity between the two is, and the higher the degree of association between the keyword of the applet and the picture is. The larger the euclidean distance between the vector of the keyword of the applet and the vector of the tag information of the picture is, the lower the similarity between the two is, and the lower the degree of association between the keyword of the applet and the picture is.

And S210, selecting pictures serving as image materials of the small programs from the plurality of pictures according to the similarity.

In one embodiment, the picture with the highest similarity to the keywords of the applet is used as the picture material of the applet. In a specific example, the picture with the highest similarity is configured as an icon of the applet. In a specific example, the picture with the highest similarity is configured as the background picture of the applet.

In fig. 7(b), the icon of the "red packet" applet is in the form of a rectangular frame, and the text "red packet" is marked in the rectangular frame, which is not beautiful enough and is not good for the user to understand the purpose of the applet. By using the method of the embodiment of the present specification, the keyword of the "red-envelope" applet includes a "red envelope", the tag of the "red-envelope" picture includes a "red envelope", the similarity calculation in step S208 is performed, the similarity between the keyword of the "red-envelope" applet and the "red-envelope" picture is the highest, and the "red-envelope" picture is selected as the image material of the "red-envelope" applet. In page 7(a), when the user clicks the 'applet', the center page of the jumped-to applet is as shown in fig. 7(d), in page 7(d), the icon of the 'red packet' applet is a red packet picture, and after the user sees the 'red packet' picture, the user intuitively understands that the 'red packet' applet is used for issuing a red packet, so that the user is attracted to interact with friends by using the 'red packet' applet.

In fig. 7(b), the icon of the "lottery" applet is in the form of a rectangular frame, and the text "lottery" is marked in the rectangular frame. With the method of the embodiment of the present specification, the keyword of the "lottery" applet includes "gift" and "bonus", the label of the "gift box" picture includes "gift", the similarity calculation in step S208 is performed, the similarity between the keyword of the "lottery" applet and the "gift box" picture is the highest, and the "gift box" picture is selected as the image material of the "lottery" applet. In the page 7(b), after clicking the "lottery drawing" applet, the user jumps to the page shown in fig. 7(e), and it can be seen that the "gift box" picture is configured as the background picture of the "lottery drawing" applet, and the user clicks the interactive control "try your mood" to draw a lottery. In fig. 7(e), the "lottery" applet is matched with a "gift box" background picture, so that the attraction to the user is improved, and the probability of using the applet by the user is improved.

In one embodiment, at least two pictures are selected according to the similarity from high to low, the selected pictures are fused to obtain a fused picture, and the fused picture is used as a picture material of the small program. For example, pattern elements in the selected picture are extracted, and a fused picture is generated using the pattern elements. For example, the selected pictures are stitched together by a surf (Speeded Up RobustFeatures) -based image stitching algorithm, so as to obtain a fused picture. In one specific example, the fused picture is configured as an icon of an applet. In one specific example, the fused picture is configured as a background picture of the applet.

< second embodiment >

Referring to fig. 3, the embodiment provides a method for an applet to photograph material, comprising the steps of:

s302, acquiring information of a plurality of small programs, wherein the information of the small programs comprises names, categories and description information of the small programs.

Referring to fig. 7(b) and 7(c), the "payment" aggregation applet includes a variety of specific payment applets. In page 7(b), when the user clicks on the "pay" syndication applet, the jump is made to the pay center page shown in fig. 7 (c). On the page of the payment center, a plurality of specific payment small programs of mobile phone fee, broadband fee, electric fee, water fee, gas fee and heating fee are arranged. And when the user clicks a specific payment applet, jumping to a page corresponding to the specific payment applet so as to realize a corresponding payment function. Through the specific payment small programs, the user can realize the functions of paying mobile phone fee, broadband fee, electric fee, water fee, fuel gas fee and heating air fee respectively.

And S304, mining common keywords related to the small programs from the information of the small programs.

In this step, common keywords for the plurality of applets may be mined from the information of the plurality of applets by a keyword mining algorithm.

In a specific example, in step S304, keyword mining may be performed using textRank (text ranking) algorithm. the textRank algorithm is originally used as an algorithm for ranking the importance of the web pages, and is applied to mining keywords of texts. the textRank algorithm constructs a network through adjacent relations among words, then iteratively calculates rank values of all word nodes, ranks the rank values, and forms keywords by word nodes corresponding to rank values in the front ranking. Specifically, in one embodiment, the process of mining the common keywords from the information of the plurality of applets by using the textRank algorithm is as follows:

s3042, performing word segmentation and part-of-speech tagging on an original text formed by the information of the small programs, filtering stop words, and only keeping words with specified parts-of-speech (nouns, verbs and adjectives) as candidate words.

S3044, constructing a candidate word graph G ═ V, E, where V is a node set and E is an edge set. The node set V is composed of the candidate words obtained in step S3042, and an edge between any two nodes is constructed by using a co-occurrence relationship, so as to obtain an edge set E.

S3046 iteratively propagating the weight of each node in the candidate word graph until convergence.

S3048, sorting the node weights in a reverse order to obtain a plurality of most important words as candidate keywords.

S3050, marking the candidate keywords in the original text, and if adjacent phrases can be formed, taking the adjacent phrases as common keywords of the multiple applets. And if the adjacent phrases cannot be formed, taking the candidate keywords as the common keywords of the plurality of small programs.

Referring to fig. 7(b) and 7(c), the "payment" aggregation applet includes a variety of specific payment applets. In page 7(b), when the user clicks on the "pay" syndication applet, the jump is made to the pay center page shown in fig. 7 (c). On the page of the payment center, a plurality of specific payment small programs of mobile phone fee, broadband fee, electric fee, water fee, gas fee and heating fee are arranged. The information of the mobile phone fee payment small program comprises a mobile phone fee, a telephone fee and a payment, the information of the broadband fee payment small program comprises a broadband, a network and a payment, the information of the electric fee payment small program comprises an electric fee and a payment, the information of the water fee payment small program comprises a water fee and a payment, the information of the gas fee payment small program comprises a gas fee and a payment, the information of the heating gas fee payment small program comprises a heating gas fee and a payment, and a common keyword of the small programs is excavated as the payment through the step S304.

S306, vectorizing the common keywords to obtain vectors of the common keywords.

In one embodiment, the embedded vector (Embedding) calculation is performed on the common keywords by a BERT (Bidirectional Encoder from transformer) algorithm to obtain a vector of the common keywords. One feature of embedded vector (Embedding) calculation is that it can implement establishing a mapping from a high-dimensional vector to a low-dimensional vector, and using the low-dimensional vector to represent a common keyword can reduce the calculation amount of step S308.

The BERT algorithm is a pre-training model of N L P (Natural L and graphical processing Natural language processing), is a bidirectional encoder algorithm, can consider the information of a word before and a word after the word when processing a word, thereby obtaining the context semantics, can fully describe the character level, the word level, the sentence level and even the inter-sentence relation characteristics, can help a computer better understand the language like a human, can better understand the subtle difference between words by using the BERT algorithm, and the obtained vector can better represent the real meaning of a common keyword.

And S308, calculating the similarity between the vector of the common keyword and the vectors of the label information of the plurality of pictures.

In step S308, the gallery has a plurality of pictures, and the pictures in the gallery have tags, where the tags are labels for the characters of the pictures. The picture provider can add labels to the pictures and then upload the pictures to the gallery. Or, when the picture is received, the gallery manager adds a label to the picture. A picture may have one or more labels, for example, a picture may be labeled with two labels, "gift" and "gift".

In the case that the picture has a tag, in step S308, the tag information of the picture may be obtained, and an Embedding vector (Embedding) calculation is performed on the tag information of the picture by a BERT algorithm to obtain a vector of the tag information of the picture as a vector of the tag information of the picture. One feature of embedded vector (Embedding) calculation is that it can implement establishing a mapping from a high-dimensional vector to a low-dimensional vector, and using the low-dimensional vector to represent a picture, so as to reduce the calculation amount of step S308.

And calculating the similarity of the vectors of the common keywords of the small programs and the vectors of the label information of the pictures, wherein the similarity of the vectors of the common keywords and the vectors of the label information of the pictures can reflect the association degree of the common keywords and the pictures.

In one embodiment, cosine similarity of a vector of the common keyword and a vector of the tag information of the picture is calculated. Cosine similarity is a measure of similarity between two vectors in a vector space by measuring their cosine of their angle. The range of cosine values is between [ -1,1], and the more the cosine values approach to 1, which indicates that the closer the direction of the vector of the common keyword and the vector of the tag information of the picture is, the higher the association degree of the common keyword and the picture is. The more the cosine value approaches-1, the more opposite the direction of the vector of the common keyword and the vector of the tag information of the picture is, the lower the degree of association of the common keyword and the picture is.

In one embodiment, the distance between the vector of the common keyword and the vector of the tag information of the picture is calculated, and the closer the distance is, the higher the similarity between the two is. For example, the euclidean distance of the vector of the common keyword and the vector of the tag information of the picture is calculated. The smaller the euclidean distance between the vector of the common keyword and the vector of the tag information of the picture is, the higher the similarity between the two is, and the higher the degree of association between the common keyword and the picture is. The larger the euclidean distance between the vector of the common keyword and the vector of the tag information of the picture is, the lower the similarity between the two is, and the lower the degree of association between the common keyword and the picture is.

And S310, selecting pictures serving as image materials of the aggregation pages of the small programs from the pictures according to the similarity.

In one embodiment, the picture with the highest similarity is configured as an icon or a background picture of an aggregated page of the applets. In a specific example, the picture with the highest similarity is configured as an icon of an aggregated page of the plurality of applets. In a specific example, the picture with the highest similarity is configured as a background picture of the aggregated pages of the applets.

Referring to fig. 7(a) -7(c), the "payment" aggregation applet in fig. 7(b) is an aggregation of the various specific payment applets in fig. 7 (c). Referring to fig. 7(b), an icon of the aggregation applet "paying" is in the form of a rectangular frame, and characters "paying" are marked in the rectangular frame, so that the applet is not attractive enough, and is not beneficial to users to understand the purpose of the applet. By using the method of the embodiment of the present specification, the common keyword of the plurality of specific payment applets aggregated by the "payment" aggregation applet is "payment", and the lightning pattern marked with "payment" is selected as the image material of the "payment" aggregation applet through the similarity calculation of step S308. In the page 7(a), when the user clicks the applet, the jump to the applet center page is as shown in fig. 7(d), in the page 7(d), the icon of the 'payment' syndication applet is a lightning pattern marked with 'fee', and after seeing the pattern, the user understands that the quick payment function can be realized through the syndication applet, so that the user is attracted to use the payment applet, and the probability of using the payment applet by the user is improved.

In one embodiment, at least two pictures are selected according to the similarity from high to low, the selected pictures are fused to obtain a fused picture, and the fused picture is used as a picture material of the aggregation page of the plurality of applets. For example, pattern elements in the selected picture are extracted, and a fused picture is generated using the pattern elements. For example, the selected pictures are stitched together by a surf (Speeded Up Robust Features) -based image stitching algorithm, so as to obtain a fused picture. In a specific example, the fused picture is configured as an icon of an aggregated page of the plurality of applets. In a specific example, the picture with the highest similarity is configured as a background picture of the aggregated pages of the applets.

The method of providing picture material for an applet shown in figures 2 and 3 may be implemented by the applet management platform shown in figure 1.

The method for providing the image material for the small program can accurately obtain the image material related to the small program, beautify the page by utilizing the image material, help the user to intuitively understand the purpose of the small program, and attract the user to use the small program.

The method for providing the image materials for the small programs, provided by the embodiment of the invention, has high response speed and is suitable for various operation scenes.

The method for providing the image materials for the small program can reduce the labor work and even avoid manual intervention.

The method for providing the image materials for the small program can accurately obtain the image materials related to the small program, the accuracy can reach more than 70%, and 80% of labor work can be reduced.

The method for providing the image materials for the applets, provided by the embodiment of the invention, can accurately provide the related image materials for the aggregation pages of a plurality of applets, and is particularly suitable for scenes needing to quickly build the aggregation pages.

< apparatus for providing graphic material for applet >

< first embodiment >

Referring to fig. 4, the embodiment provides an apparatus 10 for providing picture material for an applet, including the following modules:

the keyword extraction module 11 is configured to obtain information of an applet, where the information of the applet includes a name, a category, and description information of the applet; mining keywords about the applet from the information of the applet;

a vectorization processing module 12, configured to perform vectorization processing on the keyword to obtain a vector of the keyword;

a similarity calculation module 13, configured to calculate similarities between the vector of the keyword and vectors of tag information of multiple pictures;

and the selecting module 14 is configured to select, according to the similarity, a picture serving as an image material of the applet from the plurality of pictures.

Optionally, the selecting module 14 is configured to configure the picture with the highest similarity as an icon or a background picture of the applet.

Optionally, the vectorization processing module 12 is configured to perform embedded vector calculation on the keyword through a BERT algorithm to obtain a vector of the keyword.

Optionally, a picture vector extraction module is further included. The picture vector extraction module is used for acquiring the label information of the picture; and carrying out embedded vector calculation on the label information of the picture through a BERT algorithm to obtain a vector of the label information of the picture.

Optionally, the similarity calculation module 13 calculates the similarity between the vector of the keyword and the vector of the tag information of the plurality of pictures, including: calculating cosine similarity of the vector of the keyword and the vectors of the label information of the plurality of pictures; or calculating Euclidean distances between the vector of the keyword and the vectors of the label information of the plurality of pictures.

< second embodiment >

Referring to fig. 5, the embodiment provides an apparatus 20 for providing picture material for an applet, including the following modules:

a keyword extraction module 21, configured to obtain information of multiple applets, where the information of an applet includes a name, a category, and description information of the applet; mining a common keyword about the plurality of applets from the information of the plurality of applets;

a vectorization processing module 22, configured to perform vectorization processing on the common keyword to obtain a vector of the common keyword;

a similarity calculation module 23, configured to calculate similarities between the vector of the common keyword and the vectors of the tag information of the multiple pictures;

and the selecting module 24 is configured to select, according to the similarity, a picture serving as an image material of the aggregation page of the multiple applets from the multiple pictures.

Optionally, the selecting module 24 is configured to configure the picture with the highest similarity as an icon or a background picture of an aggregated page of the multiple applets.

Optionally, the vectorization processing module 22 is configured to perform embedded vector calculation on the common keyword through a BERT algorithm to obtain a vector of the common keyword.

Optionally, the similarity calculation module 23 calculates the similarity between the vector of the common keyword and the vector of the tag information of the plurality of pictures, including: calculating cosine similarity of the vector of the common keyword and the vectors of the label information of the plurality of pictures; or, calculating Euclidean distances between the vector of the common keyword and the vectors of the label information of the plurality of pictures.

< third embodiment >

Referring to fig. 6, this embodiment provides an apparatus 30 for providing picture material for an applet, comprising a processor 31 and a memory 32, the memory 32 storing a computer program, which when executed by the processor 31 implements the method for providing picture material for an applet of any one of the preceding embodiments.

The apparatus for providing the image material for the applet may be a server, and the configuration of the server may include but is not limited to: processor, memory, interface device, communication device, input device, output device. The processor may include, but is not limited to, a central processing unit CPU, a microprocessor MCU, or the like. The memory may include, but is not limited to, ROM (read only memory), RAM (random access memory), non-volatile memory such as a hard disk, and the like. The interface means may include, but is not limited to, a USB interface, a serial interface, a parallel interface, etc. The communication means is capable of wired or wireless communication, for example, and may specifically include WiFi communication, bluetooth communication, 2G/3G/4G/5G communication, and the like. Input devices 1015 may include, but are not limited to, a keyboard, a mouse, and the like. The output device may include, but is not limited to, a display screen or the like. The server may be configured to include only some of the above devices.

The device for providing the image materials for the small programs can accurately obtain the image materials related to the small programs.

The device for providing the image materials for the small programs, provided by the embodiment of the invention, has high response speed and is suitable for various operation scenes.

The device for providing the image materials for the small programs can reduce the labor work and even avoid manual intervention.

The device for providing the image materials for the applets can accurately provide the related image materials for the aggregated pages of a plurality of applets.

< applet management platform >

The embodiment of the invention provides an applet management platform which comprises any one of the devices for providing the image materials for the applet. The specific configuration of the applet management platform can be seen in figure 1.

< computer-readable Medium >

Embodiments of the present specification also provide a computer readable medium, on which a computer program is stored, which when executed by a processor, implements any one of the aforementioned methods for providing photo material for an applet.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device and apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Embodiments of the present description may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement aspects of embodiments of the specification.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

Computer program instructions for carrying out operations of embodiments of the present description may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including AN object oriented programming language such as Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" language or similar programming languages.

Aspects of embodiments of the present specification are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present description. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.

The foregoing description of the embodiments of the present specification has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method of providing photo material for an applet, comprising the steps of:

mining keywords about the applet from the information of the applet;

vectorizing the keywords to obtain vectors of the keywords;

2. The method of claim 1, wherein selecting a picture from the plurality of pictures as image material of the applet based on the similarity comprises:

3. The method of claim 1, the applet information further comprising information of a main page presentation of the applet.

4. The method of claim 1, wherein vectorizing the keyword to obtain a vector of the keyword comprises:

5. The method of claim 1, the vector of tag information for the picture is obtained by:

acquiring label information of the picture;

6. The method of claim 1, calculating similarity of the vector of keywords and the vector of label information of the plurality of pictures, comprising:

7. A method of providing photo material for an applet, comprising the steps of:

vectorizing the common keywords to obtain vectors of the common keywords;

8. The method of claim 7, wherein selecting, from the plurality of pictures, a picture that is image material of an aggregated page of the plurality of applets based on the similarity comprises:

9. The method of claim 7, the applet information further comprising information of a main page presentation of the applet.

10. The method of claim 7, wherein vectorizing the common keywords to obtain a vector of the common keywords comprises:

11. The method of claim 7, the vector of tag information for the picture is obtained by:

acquiring label information of the picture;

12. The method of claim 7, calculating a similarity of the vector of common keywords and a vector of label information of a plurality of pictures, comprising:

13. An apparatus for providing picture material for an applet, comprising the following modules:

14. An apparatus for providing picture material for an applet, comprising the following modules:

15. An apparatus for providing photo material for an applet, comprising a processor and a memory, the memory storing a computer program which, when executed by the processor, implements the method of any one of claims 1-12.