CN107729361A - It is automatically synthesized picture method for pushing, device and storage medium - Google Patents

Abstract

The invention discloses a method, device and storage medium for automatically synthesizing pictures. The method includes: obtaining a request for accessing pictures sent by a user equipment, extracting the attributes of pictures to be accessed from the request for accessing pictures, and according to the picture to be accessed The attribute selects the picture material to be synthesized from the picture material library; selects a plurality of picture synthesis rules from the synthesis rule set according to the property of the picture to be accessed, calls the preset scoring rules to score each selected picture synthesis rule, and selects the scoring result The image synthesis rule with the highest score is used as the preset image synthesis rule; the image material to be synthesized is synthesized according to the preset image synthesis rule, and the synthesized image is pushed to the user device. The present invention automatically synthesizes the picture materials to be synthesized by preset synthesis rules, thereby replacing manual operations by machine learning and reducing operating costs.

Description

Pushing method, device and storage medium for automatically synthesized pictures

technical field

The present invention relates to the field of computer technology, in particular to a method, device and storage medium for automatically synthesizing pictures and pushing them.

Background technique

With the vigorous development of Internet shopping, people's demand for product pictures is increasing, and the requirements for pictures are also getting higher and higher.

At present, a large number of pictures of e-commerce companies are designed by designers, and then manually uploaded to the system and manually reviewed by business operators. Such an operation process consumes a lot of human resources, but there is no experience accumulation and data analysis on the operational effects brought by the pictures. There is no corresponding technical solution for the integration of design and technology in the industry.

Contents of the invention

The main purpose of the present invention is to propose a method, device and storage medium for automatically synthesizing pictures, aiming to solve the technical problem of high operating costs due to manual picture processing in the prior art.

In order to achieve the above object, the present invention provides a method for automatically synthesizing pictures, and the method for automatically synthesizing pictures comprises the following steps:

Acquiring the image access request sent by the user equipment, extracting the attribute of the image to be accessed from the image access request, and selecting the image material to be synthesized from the image material library according to the attribute of the image to be accessed;

Select a plurality of picture synthesis rules from the synthesis rule set according to the attributes of the pictures to be accessed, call the preset scoring rules to score the selected picture synthesis rules respectively, and select the picture synthesis rule with the highest score in the scoring results as the preset synthesis picture rule;

Synthesize the image material to be synthesized according to the preset image synthesis rule, and push the synthesized image to the user equipment.

Preferably, the step of obtaining the image access request sent by the user equipment, extracting the attributes of the image to be accessed from the image access request, and selecting the image material to be synthesized from the image material library according to the attribute of the image to be accessed specifically includes:

Obtaining an image access request sent by the user equipment, and extracting attributes of images to be accessed from the image access request;

According to the attribute of the picture to be accessed, the identification information of the picture material to be synthesized is acquired, and the picture material to be synthesized is screened out from the picture material library according to the identification information.

Preferably, according to the attribute of the image to be accessed, the identification information of the image material to be synthesized is obtained, and before the step of selecting the image material to be synthesized from the image material library according to the identification information, the method for automatically synthesizing an image push include:

Acquiring picture material, extracting the picture attribute of the picture material, setting identification information on the picture material according to the picture property, and storing the picture material with the identification information in the picture material library.

Preferably, the step of acquiring the image material, extracting the image attribute of the image material, setting identification information for the image material according to the image attribute, and storing the image material with the identification information in the image material library specifically includes:

Acquiring the type and category of the image material, dividing the image attributes of the image material according to the type and category, setting corresponding identification information for the image material according to the divided image attributes, and setting the identification information The image material is stored in the image material library.

Preferably, after the step of obtaining the picture material, extracting the picture attribute of the picture material, setting identification information for the picture material according to the picture property, and storing the picture material with the identification information in the picture material library, the The method for automatically synthesizing picture pushes includes:

Acquiring the first access data of the picture material by the user equipment, counting the access frequency of the picture material according to the first access data, and displaying the access frequency.

Preferably, the picture composition rule includes at least one of picture type, layer position, layer size, layer-subordinate relationship and layer color system.

Preferably, after the step of synthesizing the picture materials to be synthesized according to the preset rules for synthesizing pictures, and pushing the synthesized pictures to the user equipment, the method for automatically synthesizing pictures includes:

Acquiring second access data of the synthesized picture from the user equipment, scoring the synthesized picture according to the second access data, and updating the material of the picture to be synthesized and the picture synthesis rule according to the scoring result.

Preferably, the acquisition of second access data of the synthesized picture by the user equipment, scoring the synthesized picture according to the second access data, and updating the material of the picture to be synthesized and the synthesized picture according to the scoring result After the above-mentioned picture composition rule step, the described automatic synthesis picture pushing method comprises:

Acquiring the scoring results of the synthesized pictures, and generating a data chart according to the scoring results.

In addition, in order to achieve the above object, the present invention also proposes a push device for automatically synthesized pictures, which includes: a memory, a processor, and an automatic Synthesized picture push program, the automatic synthesized picture push program is configured to realize the steps of the method for automatically synthesized picture push as described above.

In addition, in order to achieve the above object, the present invention also proposes a storage medium, the storage medium is stored with an automatic image synthesis push program, and when the automatic image synthesis push program is executed by the processor, the automatic image synthesis as described above is realized. The steps of the push method.

The present invention grades the picture synthesis rules through the preset scoring rules, and selects the picture synthesis rules with the highest scoring results to automatically synthesize the picture materials to be synthesized, thereby replacing manual operations with machine learning and reducing operating costs.

Description of drawings

Fig. 1 is a schematic structural diagram of a picture synthesis server of a hardware operating environment involved in the scheme of an embodiment of the present invention;

Fig. 2 is a schematic flow chart of the first embodiment of the method for automatically synthesizing pictures and pushing them according to the present invention;

Figure 3 is a schematic diagram of the online process of picture materials in the picture material library;

Fig. 4 is a schematic diagram of a synthesis process of picture materials according to picture synthesis rules;

FIG. 5 is a schematic flow diagram of the second embodiment of the method for automatically synthesizing pictures and pushing them according to the present invention;

FIG. 6 is a schematic flow chart of the third embodiment of the method for automatically synthesizing pictures and pushing them according to the present invention;

FIG. 7 is a schematic flowchart of a fourth embodiment of the method for automatically synthesizing pictures and pushing them according to the present invention;

FIG. 8 is a schematic flowchart of a fifth embodiment of the method for automatically synthesizing pictures and pushing them according to the present invention;

FIG. 9 is a schematic flowchart of the sixth embodiment of the method for automatically synthesizing pictures and pushing them according to the present invention;

FIG. 10 is a schematic flowchart of a seventh embodiment of the method for automatically synthesizing pictures and pushing them according to the present invention.

The realization of the purpose of the present invention, functional characteristics and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

detailed description

It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

Referring to FIG. 1 , FIG. 1 is a schematic structural diagram of a picture synthesis server in a hardware operating environment involved in the solution of an embodiment of the present invention.

As shown in FIG. 1 , the picture composition server may include: a processor 1001 , such as a CPU, a communication bus 1002 , an administrator interface 1003 , a network interface 1004 , and a memory 1005 . Wherein, the communication bus 1002 is used to realize connection and communication between these components. The administrator interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional administrator interface 1003 may also include a standard wired interface and a wireless interface. Optionally, the network interface 1004 may include a standard wired interface and a wireless interface (such as a WIFI interface). The memory 1005 can be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .

Those skilled in the art can understand that the picture composition server structure shown in Figure 1 does not constitute a limitation to the picture composition server, and may include more or less components than those shown in the illustration, or combine some components, or different components layout.

As shown in FIG. 1 , the memory 1005 as a storage medium may include an operating system, a network communication module, an administrator interface module, and an automatic composite image push program.

In the picture synthesis server shown in Figure 1, the network interface 1004 is mainly used to connect to the user terminal and perform data communication with the user terminal; the administrator interface 1003 is mainly used to connect to the administrator terminal and perform data communication with the terminal; the picture synthesis of the present invention The processor 1001 and memory 1005 in the server can be set in the automatically synthesized image pushing device, and the automatically synthesized image pushing device invokes the automatically synthesized image pushing program stored in the memory 1005 through the processor 1001, and performs the following operations:

Acquiring the image access request sent by the user equipment, extracting the attribute of the image to be accessed from the image access request, and selecting the image material to be synthesized from the image material library according to the attribute of the image to be accessed;

Select a plurality of picture synthesis rules from the synthesis rule set according to the attributes of the pictures to be accessed, call the preset scoring rules to score the selected picture synthesis rules respectively, and select the picture synthesis rule with the highest score in the scoring results as the preset synthesis picture rule;

Synthesize the image material to be synthesized according to the preset image synthesis rule, and push the synthesized image to the user equipment.

Further, the processor 1001 may call the automatically synthesized picture push program stored in the memory 1005, and also perform the following operations:

Obtaining an image access request sent by the user equipment, and extracting attributes of images to be accessed from the image access request;

According to the attribute of the picture to be accessed, the identification information of the picture material to be synthesized is acquired, and the picture material to be synthesized is screened out from the picture material library according to the identification information.

Further, the processor 1001 may call the automatically synthesized picture push program stored in the memory 1005, and also perform the following operations:

Acquiring picture material, extracting the picture attribute of the picture material, setting identification information on the picture material according to the picture property, and storing the picture material with the identification information in the picture material library.

Further, the processor 1001 may call the automatically synthesized picture push program stored in the memory 1005, and also perform the following operations:

Acquiring the type and category of the image material, dividing the image attributes of the image material according to the type and category, setting corresponding identification information for the image material according to the divided image attributes, and setting the identification information The image material is stored in the image material library.

Further, the processor 1001 may call the automatically synthesized picture push program stored in the memory 1005, and also perform the following operations:

Acquiring the first access data of the picture material by the user equipment, counting the access frequency of the picture material according to the first access data, and displaying the access frequency.

Further, the processor 1001 may call the automatically synthesized picture push program stored in the memory 1005, and also perform the following operations:

Acquiring second access data of the synthesized picture from the user equipment, scoring the synthesized picture according to the second access data, and updating the material of the picture to be synthesized and the picture synthesis rule according to the scoring result.

Further, the processor 1001 may call the automatically synthesized picture push program stored in the memory 1005, and also perform the following operations:

Acquiring the scoring results of the synthesized pictures, and generating a data chart according to the scoring results.

In this embodiment, through the above scheme, the preset scoring rules are used to score the image synthesis rules, and the image synthesis rules with the highest scoring results are selected to automatically synthesize the image materials to be synthesized, thereby replacing manual operations with machine learning and reducing operating costs.

Based on the above hardware structure, an embodiment of the method for automatically synthesizing pictures and pushing them is proposed in the present invention.

Referring to FIG. 2 , FIG. 2 is a schematic flowchart of a first embodiment of a method for automatically synthesizing pictures and pushing them according to the present invention.

In the first embodiment, the method for pushing automatically synthesized pictures includes the following steps:

Step S10, obtaining the image access request sent by the user equipment, extracting the attribute of the image to be accessed from the image access request, and selecting the image material to be synthesized from the image material library according to the attribute of the image to be accessed;

The user equipment may be a mobile terminal such as a notebook computer, a smart phone, or an IPAD, or may be other user equipment capable of realizing the same or similar functions, which is not limited herein.

The request for accessing pictures may be a keyword input through a website search box, or a search by clicking on a preset keyword, or other methods that can achieve the same or similar functions, which are not limited here.

The attributes of the image to be accessed include the type and type of the image to be accessed by the user. For example, the user accesses a shopping website through a laptop computer, enters women's clothing in the user search bar, and the brand of women's clothing selected by the user, and obtains the access to women's clothing sent by the user through the user equipment. The request for the picture extracts the brand of the women's clothing picture to be accessed from the request for accessing the women's clothing picture.

Select the picture material to be synthesized from the picture material library according to the image attributes to be accessed, that is, select the women's clothing picture related to the brand from the picture material library according to the brand of the women's clothing picture to be accessed.

It should be noted that the picture material library can be a large number of picture materials stored in the picture synthesis database, and the server receives the request for accessing pictures, calls the database according to the request for accessing pictures, and obtains from the database the information related to the picture to be accessed. Image material to be synthesized with matching attributes.

It is understandable that the image material library has different types according to business scenarios, such as brand logos, background images, tasks, and slogans.

In order to facilitate the search for materials, therefore, a material library needs to be established in advance. Referring to FIG. 3, in this embodiment, the material library can be established by referring to the following specific steps:

When the user logs in to the picture material library entrance, when the picture material cannot be provided for the commercial scene, the designer makes the picture material independently, and saves the picture material in the picture material library for the online picture material; in the case of providing the first draft of the picture material , get the review list, review the picture according to the review list, if the review fails, it can be processed in two ways, one way is to reject the review, fill in the modification comments, and after receiving the other party’s review comments to modify After the picture material, continue to review; another way is that the user modifies the first draft of the picture material by himself, saves the modified picture material in the picture material library and puts the picture material online.

Step S20, select a plurality of picture synthesis rules from the synthesis rule set according to the attributes of the pictures to be accessed, call the preset scoring rules to score each of the selected picture synthesis rules, and select the picture synthesis rule with the highest score in the scoring results as the preset Set rules for compositing pictures;

It should be noted that the picture composition rule includes at least one of picture type, layer position, layer size, layer-subordinate relationship, and layer color system.

The picture type can be the format rule of the picture, for example, the picture type is required to be JPEG (Joint Photographic Experts Group Joint Photographic Experts Group), redundant images and color data are removed through lossy compression, and high compression rate can be obtained while Display rich and vivid images, thereby occupying less disk space and obtaining better image quality. It can also be GIF (Graphics Interchange Format), which can realize picture animation display, thereby improving user experience.

The position of the layer, the size of the layer, and the upper-lower relationship of the layer are processed through the rules to process the picture material to be synthesized, so that the refined processing of the picture material to be synthesized can be realized, making the picture material to be synthesized more professional, and It can meet the needs of various groups of people and improve user experience.

The layer color system is a preset image synthesis rule, and the image material to be synthesized is processed through the layer color system, thereby enriching the color of the image material to be synthesized. The properties of the black image to be accessed can filter out layers that are in the same color system as black for processing, and can also be matched with a color that is more visually impactful than black, thereby increasing the diversity of image materials to be synthesized.

The picture synthesis rule set is a large number of synthesis rule sets that are pre-set and stored in the database. The picture synthesis rules can be generated through two methods, one is artificially generated rules, and the rules are generated by professional operators according to design experience and past experience. Business experience formulates different picture synthesis rules for different groups of people. The other is automatic generation of rules. When the number of picture synthesis rules reaches a certain number, the picture synthesis rules are scored by machine learning, and then continue to generate the highest score. rules, and use the image composition rule with the highest score as the preset image composition rule.

It can be understood that the preset scoring rules are the scoring rules designed in the scoring system.

The scoring system configures different scoring formulas for each business scene, scores each synthesized picture, and can also score the picture synthesis rules.

Step S30 , synthesizing the picture materials to be synthesized according to the preset rules for synthesizing pictures, and pushing the synthesized pictures to the user equipment.

In order to improve the efficiency of image synthesis, the machine is used to replace the manual image synthesis operation, as shown in Figure 4, including the following steps S1 to S14, the image synthesis process is performed by the machine, so as to improve the accuracy of image synthesis.

S1: task processing starts;

S2: Obtain the category to which the picture material belongs;

If the acquisition fails, go to step S3: display record abnormality, and continue the synthesis process of the next picture material, and return to step S1;

S4: Obtain the brand to which the picture material belongs;

If the acquisition fails, enter step S3 and return to step S1;

S5: Obtain the template style, category, brand and crowd and select the first layer material;

If the acquisition fails, enter step S3 and return to step S1;

S6: Select the upper layer material according to the category, brand and brand;

If the acquisition fails, enter step S3 and return to step S1;

S7: continue to filter the picture material according to the color layer and color system of the template;

If the acquisition of the picture material fails, return to step S5, and replace the material color system of the first layer layer; continue to try to obtain, if the second acquisition of the picture material fails, then enter step S3, and return to step S1;

S8: Continue to filter the picture material according to the time sequence and the update time of the material;

S9: Start assembling according to the template, base map and component materials;

S10: Detect whether there is overlap between materials;

S11: If there is overlap, perform overlay processing according to the hierarchical relationship between components;

S12: If there is no overlap, check whether the materials have been synthesized;

S13: If the synthesis is completed, synthesize the picture materials of the four groups of people;

S14: After the synthesis is completed, upload the image material to the image material library; if the synthesis is not completed, return to step S5.

It should be noted that when performing image synthesis, the image synthesis device can specify the synthesis speed according to the instructions, and the machine will allocate a reasonable number of processes according to the size of the task and the speed required by the user, and finally use the image synthesis rules and the image materials with corresponding attributes Synthesize the target image.

As can be seen from the above, the composition process may include: obtaining business scene attributes, obtaining image composition rules from the composite image rule set, selecting the best image materials from the image material library, assembling the image materials and pushing them to the application scene. Among them, obtaining business scene attributes can be used to obtain the business attributes of the current business scene according to different business scenarios. For example, the requirement of the current application scenario is to synthesize a picture material and obtain the picture properties of the picture material, such as sports shoes or brands, etc. Wait.

In order to further increase the diversity of image synthesis and adapt to the needs of the general population, a set of image synthesis is established. Through the image synthesis rule set, according to the scoring results of the scoring system and the attributes of business scenarios, the image synthesis rule set can be used to select the most suitable for the current application scene. Appropriate picture synthesis rules, assemble the picture materials obtained from the picture material library according to the picture synthesis rules, and then push the synthesized pictures to the application scenarios of various requirements.

In this embodiment, through the above scheme, the preset scoring rules are used to score the image synthesis rules, and the image synthesis rules with the highest scoring results are selected to automatically synthesize the image materials to be synthesized, thereby replacing manual operations with machine learning and reducing operating costs.

Further, as shown in FIG. 5 , based on the first embodiment, a second embodiment of the method for pushing an automatically synthesized image of the present invention is proposed. In this embodiment, the step S10 specifically includes:

Step S101, acquiring a picture access request sent by the user equipment, and extracting the attributes of the picture to be accessed from the picture access request;

Step S102, according to the attribute of the picture to be accessed, obtain the identification information of the picture material to be synthesized, and filter out the picture material to be synthesized from the picture material library according to the identification information.

It should be noted that before the picture material is saved in the picture material library, each picture material is marked with identification information, and according to the identification information, the picture material to be synthesized can be quickly found, thereby improving the response time of picture screening.

The identification information can reflect the attributes of the picture material, and the picture material to be synthesized can be quickly screened out from the picture material library according to the identification information. For example, for a picture material of women's clothing, by obtaining the attributes of the picture material of women's clothing, that is, the picture of women's clothing displayed in the picture material, mark the identification information of the women's clothing.

It can be understood that the identification information may be marked in the form of a label or in other forms of identification, which is not limited in this embodiment. The label can also be in the form of a multi-level label, for example, a first-level label: women's top; a second-level label: long sleeves, black, so that more accurate picture information can be provided for the picture material, and it is easier to find.

In this embodiment, through the above solution, the picture material to be synthesized is screened out through the identification information of the picture material, and the picture material to be synthesized can be quickly found, thereby improving the response time of picture screening.

Further, as shown in FIG. 6 , based on the second embodiment, a third embodiment of the method for pushing an automatically synthesized image of the present invention is proposed. In this embodiment, before the step S102, the method includes:

Step S100, acquire picture material, extract the picture attribute of the picture material, set identification information on the picture material according to the picture property, and store the picture material with the identification information in the picture material library.

It should be noted that, in general, the user finds the picture material to be synthesized through the picture material attribute, which is often inaccurate, and the searched picture material is too many, resulting in low quality picture material, which is not conducive to picture synthesis. The picture attribute of the material, and set the identification information according to the picture property, so as to facilitate the user's accurate search and improve the quality of the picture to be synthesized. For example, in the past, each picture material in the picture material library is only named Distinguish other picture materials, or distinguish other picture materials by numbering. This method is good for distinguishing other picture materials, but it cannot express the attributes of each picture material. By setting identification information for each picture material, the identification information reflects each picture material. The image attribute of the image material, so as to improve the recognition of the image material, for example, set a first-level label for a women's clothing picture material: women's clothing top; second-level label: long sleeves, black, so as to set more accurate identification information for the picture material , which is easy for users to find.

In this embodiment, the picture material is set with identification information, and when screening the pictures to be synthesized according to the picture attributes, it is convenient for the user to search, and the quality of the screened picture materials to be synthesized is improved.

Further, as shown in FIG. 7 , based on the third embodiment, the fourth embodiment of the method for pushing an automatically synthesized image of the present invention is proposed. In this embodiment, the step S100 specifically includes:

Step S110, acquire the type and category of the picture material, divide the picture attributes of the image material according to the variety and category, set corresponding identification information for the picture material according to the divided picture attributes, and set The picture material of the identification information is stored in the picture material library.

In this embodiment, the picture attributes of the picture material can be divided according to the type and category of the picture material. For example, the picture material is top-loading or bottom-loading, and the top-loading or bottom-loading is the type of the picture material. The attributes of the picture material are divided according to the type of the picture material, and the described Set the corresponding identification information for the picture material, for example, according to the category of the picture material, divide the picture material into the picture attribute of uploading or the picture attribute of downloading, and set the corresponding identification information for the picture material according to the category of the picture material .

It can be understood that the image attributes of the image materials can also be divided by the attributes of the image materials other than the variety and category, and are not limited to the two methods in this embodiment, and other methods that can achieve the same Or a manner with a similar function, which is not limited in this embodiment.

In this embodiment, the type and category of the picture material can be used to set corresponding identification information for the picture material according to the type and category of the picture material, so as to provide multi-level labels for the identification information and refine the identification information. Thereby, the quality of the screened picture material to be synthesized is improved.

Further, as shown in FIG. 8 , based on the third embodiment, the fifth embodiment of the method for pushing an automatically synthesized image of the present invention is proposed. In this embodiment, after the step S100, the method includes:

Step S40, acquiring the first access data of the picture material by the user equipment, counting the access frequency of the picture material according to the first access data, and displaying the access frequency.

It should be noted that, the first access data may be the access information for obtaining the user's access to the picture material, and according to the access information, the number of times the user visits the picture material is recorded, and according to the number of visits, it can be obtained The user's attention to the picture material, and display the counted number of visits, so that the user can intuitively obtain the relevant data of the picture material, and timely adjust the picture material in the picture material library, and the picture material library can Provide more picture materials that are more suitable for the preferences of the general public.

Continuing to refer to Fig. 3, after the picture material goes online, the access data of the picture material can be obtained to visualize the user's visit information and the user's attention information data, and the visit data can include UV (UniqueVisitor independent visitor), PV ( Page Views), CTR, and CTR rank in specific business categories.

In addition, by obtaining the image ranking in the image material library, the optimal image can be obtained according to the image ranking, and the image ranking can be visualized to facilitate data analysis of the image materials in the image material library, so as to make data-oriented changes Operation direction and formulation of operation strategy.

In this embodiment, the data visualization of the picture material in the picture material database can be performed, so as to change the operation direction and formulate the operation strategy based on the data.

Further, as shown in FIG. 9 , based on the first embodiment, the sixth embodiment of the method for pushing an automatically synthesized picture of the present invention is proposed. In this embodiment, after the step S30, the method includes:

Step S50, acquiring second access data of the synthesized picture from the user equipment, scoring the synthesized picture according to the second access data, updating the material of the picture to be synthesized and the picture according to the scoring result Synthesis rules.

The second access data may be access traffic data of the synthesized pictures, and the synthesized pictures may be scored according to the traffic data through a scoring system, and the scoring results may also be displayed.

It is understandable that if the scores of the pictures to be synthesized are not ranked high according to the traffic data, it means that the elements related to the synthesized pictures, such as picture materials and picture synthesis rules, are optimal. In this case Next, by visualizing data, adjusting image materials and image synthesis rules, and performing feedback processing, the image materials and image synthesis rules can be optimized to improve user experience.

It should be noted that when the combined pictures are scored through the scoring system, each combined picture can be scored through a specific scoring formula.

In this embodiment, by obtaining the access traffic data of the synthesized pictures, scoring the synthesized pictures according to the traffic data, and adjusting the picture materials and picture synthesis rules according to the scoring results, so that the picture materials and picture synthesis rules can be adjusted. Optimize processing and improve user experience.

Further, as shown in FIG. 10 , based on the sixth embodiment, the seventh embodiment of the method for pushing an automatically synthesized picture of the present invention is proposed. In this embodiment, after the step S50, the method includes:

Step S60, obtaining the scoring results of the synthesized pictures, and generating a data chart according to the scoring results.

It should be noted that the data chart may include the comprehensive score of the picture material, the picture material with high user attention, and the scoring data of the picture synthesis rules. According to the scoring data, better pictures can be intuitively obtained Combining rules, designers and business personnel analyze the data through data charts to precipitate rules to guide subsequent operations.

In a variety of business scenarios, it can automatically generate pictures that meet the needs and continuously optimize them to generate better pictures. The current data chart on the system shows that in business scenarios: the reuse rate of pictures generated during the schedule reaches 70%, and the corresponding click-through rate of pictures reaches 8%. Freeing them up to focus more on other operational decisions like design enhancements or brand maintenance.

Through this embodiment, the picture data information can be visualized to generate a data chart, and the data chart can be used to guide subsequent operation actions.

In addition, the embodiment of the present invention also proposes a storage medium, the storage medium stores an automatic composite image push program, and when the automatic composite image push program is executed by the processor, the following operations are realized:

Acquiring the image access request sent by the user equipment, extracting the attribute of the image to be accessed from the image access request, and selecting the image material to be synthesized from the image material library according to the attribute of the image to be accessed;

Select a plurality of picture synthesis rules from the synthesis rule set according to the attributes of the pictures to be accessed, call the preset scoring rules to score the selected picture synthesis rules respectively, and select the picture synthesis rule with the highest score in the scoring results as the preset synthesis picture rule;

Synthesize the image material to be synthesized according to the preset image synthesis rule, and push the synthesized image to the user equipment.

Further, when the automatic composite picture pushing program is executed by the processor, the following operations are also realized:

Obtaining an image access request sent by the user equipment, and extracting attributes of images to be accessed from the image access request;

According to the attribute of the picture to be accessed, the identification information of the picture material to be synthesized is acquired, and the picture material to be synthesized is screened out from the picture material library according to the identification information.

Further, when the automatic composite picture pushing program is executed by the processor, the following operations are also realized:

Acquiring picture material, extracting the picture attribute of the picture material, setting identification information on the picture material according to the picture property, and storing the picture material with the identification information in the picture material library.

Further, when the automatic composite picture pushing program is executed by the processor, the following operations are also realized:

Acquiring the type and category of the image material, dividing the image attributes of the image material according to the type and category, setting corresponding identification information for the image material according to the divided image attributes, and setting the identification information The image material is stored in the image material library.

Further, when the automatic composite picture pushing program is executed by the processor, the following operations are also realized:

Acquiring the first access data of the picture material by the user equipment, counting the access frequency of the picture material according to the first access data, and displaying the access frequency.

Further, when the automatic composite picture pushing program is executed by the processor, the following operations are also realized:

Acquiring second access data of the synthesized picture from the user equipment, scoring the synthesized picture according to the second access data, and updating the material of the picture to be synthesized and the picture synthesis rule according to the scoring result.

Further, when the automatic composite picture pushing program is executed by the processor, the following operations are also realized:

Acquiring the scoring results of the synthesized pictures, and generating a data chart according to the scoring results.

In this embodiment, through the above scheme, the preset scoring rules are used to score the image synthesis rules, and the image synthesis rules with the highest scoring results are selected to automatically synthesize the image materials to be synthesized, thereby replacing manual operations with machine learning and reducing operating costs.

It should be noted that, as used herein, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or system. Without further limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system comprising that element.

The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product in essence or in other words, the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , magnetic disk, optical disk), including several instructions to make a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the method described in each embodiment of the present invention.

The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the description of the present invention and the contents of the accompanying drawings, or directly or indirectly used in other related technical fields , are all included in the scope of patent protection of the present invention in the same way.

Claims (10)

1. A method for pushing automatically synthesized pictures, characterized in that, the method for pushing automatically synthesized pictures comprises: Acquiring the image access request sent by the user equipment, extracting the attribute of the image to be accessed from the image access request, and selecting the image material to be synthesized from the image material library according to the attribute of the image to be accessed; Select a plurality of picture synthesis rules from the synthesis rule set according to the attributes of the pictures to be accessed, call the preset scoring rules to score the selected picture synthesis rules respectively, and select the picture synthesis rule with the highest score in the scoring results as the preset synthesis picture rule; Synthesize the image material to be synthesized according to the preset image synthesis rule, and push the synthesized image to the user equipment. 2. The method for automatically synthesizing picture pushes according to claim 1, wherein said acquiring the picture access request sent by the user equipment, extracting the attributes of the picture to be accessed from the request for accessing the picture, and according to the attribute of the picture to be accessed The steps of selecting the picture material to be synthesized from the picture material library include: Obtaining an image access request sent by the user equipment, and extracting attributes of images to be accessed from the image access request; According to the attribute of the picture to be accessed, the identification information of the picture material to be synthesized is acquired, and the picture material to be synthesized is screened out from the picture material library according to the identification information. 3. The method for automatically synthesizing pictures according to claim 2, wherein, according to the attributes of the picture to be accessed, the identification information of the picture material to be synthesized is obtained, and the picture material library is selected from the picture material library according to the identification information. Before the step of screening out the picture materials to be synthesized, the method for automatically synthesizing picture pushes includes: Acquiring picture material, extracting the picture attribute of the picture material, setting identification information on the picture material according to the picture property, and storing the picture material with the identification information in the picture material library. 4. The method for automatically synthesizing picture pushing as claimed in claim 3, characterized in that, the acquisition of the picture material extracts the picture property of the picture material, and the identification information is set for the picture material according to the picture property, and the The steps for storing the picture material with identification information in the picture material library include: Acquiring the type and category of the image material, dividing the image attributes of the image material according to the type and category, setting corresponding identification information for the image material according to the divided image attributes, and setting the identification information The image material is stored in the image material library. 5. The automatic synthesis picture push method as claimed in claim 3, characterized in that, said acquiring picture material, extracting the picture property of said picture material, setting identification information to said picture material according to said picture property, and After the step of storing the picture material of the identification information in the picture material library, the method for automatically synthesizing picture push includes: Acquiring the first access data of the picture material by the user equipment, counting the access frequency of the picture material according to the first access data, and displaying the access frequency. 6. The method for pushing automatically synthesized pictures according to claim 1, wherein the picture synthesis rules include at least A sort of. 7. The method for automatically synthesizing pictures according to claim 1 , wherein the picture materials to be synthesized are synthesized according to the preset rules for synthesizing pictures, and the synthesized pictures are pushed to the user After the equipment step, the method for automatically synthesizing picture pushes includes: Acquiring second access data of the synthesized picture from the user equipment, scoring the synthesized picture according to the second access data, and updating the material of the picture to be synthesized and the picture synthesis rule according to the scoring result. 8. The method for automatically synthesizing pictures according to claim 7, wherein said acquisition of second access data of the user equipment to the synthesized pictures is performed, and the synthesized pictures are processed according to the second access data. The picture is scored, and after the step of updating the picture material to be synthesized and the picture synthesis rule according to the scoring result, the method for pushing the automatically synthesized picture includes: Acquiring the scoring results of the synthesized pictures, and generating a data chart according to the scoring results. 9. A push device for automatically synthesized pictures, characterized in that, the push device for automatically synthesized pictures comprises: a memory, a processor and an automatic synthesized picture push program stored on the memory and operable on the processor, The automatic composite image pushing program is configured to realize the steps of the automatic composite image push method according to any one of claims 1-8. 10. A storage medium, characterized in that, the storage medium is stored with an automatic composite picture push program, and when the automatic composite picture push program is executed by a processor, it realizes the method described in any one of claims 1 to 8. The steps of the method for automatically synthesizing pictures and pushing them.