Product image-text generation method and device, equipment and medium

Abstract

The invention discloses a product image-text generation method and device, equipment and a medium. The method comprises the following steps: dividing image-text element data into a plurality of image-text element data groups; determining image-text key parameters corresponding to the image-text generation instruction text; according to each image-text element data set, the image-text key parameter and the product description text, generating a plurality of corresponding product images and texts, and providing each product image and text for the target user; and after the image-text of the target product is obtained, time information, region information and product information in the image-text of the target product are detected, and a detection result is provided for a target user. According to the embodiment of the invention, after the image-text generation instruction text is obtained, a plurality of product images and texts can be rapidly generated automatically based on the image-text element data set, the image-text key parameters and the product description text, each product image and text is provided for a user, and time information, region information and product information in the product images and texts can be detected.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a method, device, equipment and medium for generating product images and texts. Background Art

[0002] Financial institutions typically have multiple subsidiaries. Each subsidiary is a branch of the financial institution. During the operation of the business systems of each subsidiary, each subsidiary needs to periodically generate new product images and text at preset time points and provide these new product images and text to the subsidiary's users. Product images and text can be images containing text that showcase a specific product of the subsidiary.

[0003] In the related art, a common solution for generating product images and text is that when a subsidiary's business system needs to generate product images and text, the subsidiary's technical staff manually generates new product images and text based on the relevant information of the subsidiary's designated products that need to be displayed. This solution relies on manual operation, which is time-consuming and labor-intensive, and results in low efficiency in generating product images and text. Summary of the Invention

[0004] The present invention provides a method, device, equipment and medium for generating product images and texts, so as to solve the problem that the generation scheme of product images and texts in the related art relies on manual operation, has high time and labor costs, and has low generation efficiency of product images and texts.

[0005] According to one aspect of the present invention, a method for generating product images and text is provided, comprising:

[0006] Acquire each graphic element data, and divide each graphic element data into a plurality of graphic element data groups;

[0007] After obtaining the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text, determining the image-text key parameters corresponding to the image-text generation instruction text;

[0008] generating a plurality of product images and texts corresponding to the image and text generation instruction text according to each image and text element data group, the image and text key parameters, and the product description text, and providing each product image and text to a target user;

[0009] After obtaining the target product image and text corresponding to the image and text generation instruction text fed back by the target user, the time information, region information and product information in the target product image and text are detected according to preset product image and text rules, and the detection result is provided to the target user.

[0010] According to another aspect of the present invention, there is provided a device for generating product images and texts, comprising:

[0011] A data grouping module is used to obtain each graphic element data and divide each graphic element data into multiple graphic element data groups;

[0012] A parameter determination module is used to determine the key parameters of the image and text corresponding to the image and text generation instruction text after obtaining the image and text generation instruction text and the product description text corresponding to the image and text generation instruction text;

[0013] An image and text generation module is used to generate a plurality of product images and texts corresponding to the image and text generation instruction text according to each image and text element data group, the image and text key parameters, and the product description text, and provide each product image and text to a target user;

[0014] The image and text detection module is used to detect the time information, region information and product information in the target product image and text according to preset product image and text rules after obtaining the target product image and text corresponding to the image and text generation instruction text fed back by the target user, and provide the detection results to the target user.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor;

[0017] and a memory communicatively coupled to the at least one processor;

[0018] The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating product images and texts described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating product graphics and text according to any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the method for generating product graphics and text according to any embodiment of the present invention is implemented.

[0021] The technical solution of the embodiment of the present invention obtains each graphic and text element data and divides each graphic and text element data into multiple graphic and text element data groups; after obtaining the graphic and text generation instruction text and the product description text corresponding to the graphic and text generation instruction text, determines the graphic and text key parameters corresponding to the graphic and text generation instruction text; then, based on each graphic and text element data group, the graphic and text key parameters and the product description text, generates multiple product graphics corresponding to the graphic and text generation instruction text, and provides each product graphics to the target user; after obtaining the target product graphics corresponding to the graphic and text generation instruction text fed back by the target user, the time information, regional information and product information in the target product graphics are detected according to the preset product graphics rules, and the detection results are provided to the target user, which solves the problem that the product graphics generation solution in the related art depends on the graphics and text generation instruction text. Due to the problem of relying on manual operation, high time cost and labor cost, and low efficiency of product image and text generation, each image and text element data can be divided into multiple image and text element data groups. After obtaining the image and text generation instruction text, multiple product images and texts can be automatically generated based on the image and text element data group, image and text key parameters and product description text, and each product image and text can be provided to the user. After obtaining the product image and text selected from the generated product images that meets the current product image and text generation requirements of the subsidiary's business system, the time information, regional information and product information in the product image and text can be automatically detected according to the preset product image and text rules, and the detection results can be provided to the user, which reduces the time cost and labor cost of the product image and text generation process and improves the efficiency and accuracy of the product image and text generation process.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a flowchart of a method for generating product images and texts provided in Example 1 of the present invention.

[0025] Figure 2 This is a flowchart of a method for generating product images and texts provided in Example 2 of the present invention.

[0026] Figure 3This is a structural diagram of a device for generating product images and texts provided in Example 3 of the present invention.

[0027] Figure 4 A schematic structural diagram of an electronic device for implementing the method for generating product images and texts according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "target", "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprise", "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with relevant laws, regulations and standards in the relevant regions.

[0031] The information collected as involved in the present invention is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] Example 1

[0033] Figure 1This is a flowchart of a method for generating product images and texts provided in the first embodiment of the present invention. This embodiment is applicable to the case where product images and texts are generated during the operation of a subsidiary's business system. The method can be executed by a device for generating product images and texts, which can be implemented in the form of hardware and / or software, and can be configured in the business system of a subsidiary of a financial institution. The business system of a subsidiary can be a server set up in the subsidiary for processing the business of the subsidiary. Figure 1 As shown, the method includes:

[0034] Step 101: Acquire each graphic element data, and divide each graphic element data into multiple graphic element data groups.

[0035] Optionally, the shared database may be a database set up in a financial institution for storing graphic and text element data shared by business systems of various sub-institutions of the financial institution. The shared database may store a plurality of different graphic and text element data.

[0036] Optionally, for each graphic element data in the shared database, the graphic element data can be a table that can be included in the product image and text for describing a specified animal, plant, person, object, natural landscape, cultural landscape, local attraction, or cultural symbol. The graphic element data can also be an image containing the specified animal, plant, person, object, natural landscape, cultural landscape, local attraction, or cultural symbol that can be used as the product image and text after adding product description text. The product description text can refer to text used to describe the specified products of the subsidiary. The products of the subsidiary include but are not limited to commemorative products provided by the subsidiary and products related to the business of the subsidiary. The graphic element data can also be a graphic that can be included in the product image and text for representing a specified animal, plant, person, object, natural landscape, cultural landscape, local attraction, cultural symbol, or a specified subsidiary of a financial institution. The graphic element data can also be text that can be included in the product image and text for describing a specified animal, plant, person, object, natural landscape, cultural landscape, local attraction, or cultural symbol.

[0037] The graphic element data and related information of the graphic element data in the present invention are information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the graphic element data and related information of the graphic element data comply with the relevant laws, regulations and standards of the relevant regions.

[0038] Optionally, for each graphic element data in the shared database, the graphic element data can be extracted from product graphics used in the business systems of various subsidiaries of the financial institution, or can be designed by technical personnel of various subsidiaries of the financial institution.

[0039] Optionally, each graphic and text element data stored in the shared database may be obtained from the shared database, thereby obtaining each graphic and text element data, and then dividing each graphic and text element data into a plurality of graphic and text element data groups.

[0040] Optionally, each graphic element data is divided into multiple graphic element data groups, including: determining the attribute label data of each graphic element data; wherein the attribute label data includes a type label, a color label, a style label, a theme label, a content type label and a detailed content label; clustering each graphic element data according to the attribute label data of each graphic element data to obtain multiple graphic element data groups; counting the proportion of attribute label data of each graphic element data group; and determining the attribute label data of each graphic element data group according to the proportion of attribute label data of each graphic element data group.

[0041] Therefore, based on the attribute label data of each graphic element data, each graphic element data can be divided into multiple graphic element data groups, and the attribute label data of each graphic element data group can be determined, so that based on the attribute label data of each graphic element data group, graphic element data that meets the requirements of the target user for generating new product graphics can be quickly obtained from the graphic element data group.

[0042] Optionally, the attribute tag data of the graphic element data may be text for describing the graphic element data. The attribute tag data of the graphic element data may include a type tag, a color tag, a style tag, a theme tag, a content type tag, and a detailed content tag.

[0043] Optionally, the type tag of the graphic element data can be text that can be used to indicate whether the graphic element data is a table, image, graphic, or text. The subsidiary's business system stores multiple different preset type tags. A preset type tag can be a pre-set text that indicates whether the graphic element data is a table, image, graphic, or text. Each preset type tag can include: table type, template base type, single graphic element type, and text type. A graphic element data type with a table type tag indicates that the graphic element data is a table. A graphic element data type with a template base type tag indicates that the graphic element data is an image. A graphic element data type with a single graphic element type tag indicates that the graphic element data is a graphic. A graphic element data type with a text type tag indicates that the graphic element data is text. Typically, for each acquired graphic element data, the type tag of the graphic element data is included in each preset type tag. If the graphic element data is a table, the type tag of the graphic element data is a table type. If the graphic element data is an image, the type tag of the graphic element data is a template base type. If the graphic element data is a graphic, the type tag of the graphic element data is a single graphic element type. If the graphic element data is text, the type tag of the graphic element data is a text type.

[0044] Optionally, the color label of the graphic element data can be a text that can be used to describe the color of the graphic element data. The color label can include an overall color label, a main color label, and a main color label. The overall color label of the graphic element data can be a text used to describe the dominant color combination in the graphic element data. The main color label of the graphic element data can be a text used to describe the main color combination in the graphic element data. The main color label of the graphic element data can be a text used to describe the dominant color in the graphic element data. A plurality of different preset color labels are stored in the business system of the subsidiary organization. The preset color label can be a pre-set text used to describe the color of the graphic element data. Normally, for each graphic element data obtained, the color label of the graphic element data will be included in each preset color label.

[0045] Optionally, the style tag of the graphic element data may be a text that can be used to describe the overall recognizable features presented by the graphic element data. A plurality of different preset style tags are stored in the business system of the subsidiary organization. The preset style tag may be a pre-set text for describing the overall recognizable features presented by the graphic element data. Normally, for each graphic element data obtained, the style tag of the graphic element data will be included in each preset style tag. Exemplarily, each preset type tag may include: classical, modern, festive, light, simple, traditional or trendy.

[0046] Optionally, the subject tag of the graphic element data may be text that can be used to characterize a scenario suitable for using the graphic element data. A plurality of different preset subject tags are stored in the subsidiary's business system. A preset subject tag may be pre-set text that characterizes a scenario suitable for using the graphic element data. Typically, for each acquired graphic element data, the subject tag of the graphic element data will be included in each preset subject tag.

[0047] Optionally, the content type label of the graphic element data may be a text that can be used to characterize the type of object described or represented by the graphic element data. A plurality of different preset content type labels are stored in the business system of the subsidiary organization. The preset content type label may be a pre-set text for characterizing the type of object described or represented by the graphic element data. Normally, for each graphic element data obtained, the content type label of the graphic element data will be included in each preset content type label. Exemplarily, each preset content type label may include animals, plants, people, objects, natural landscapes, cultural landscapes, local attractions, cultural symbols, and subsidiary organizations.

[0048] Optionally, the detailed content tag of the graphic element data may be text that can be used to describe in detail the object described or represented by the graphic element data. A plurality of different preset detailed content tags are stored in the business system of the subsidiary organization. The preset detailed content tag may be pre-set text that is used to describe in detail the object described or represented by the graphic element data. Typically, for each acquired graphic element data, the detailed content tag of the graphic element data will be included in each preset detailed content tag.

[0049] Optionally, determining the attribute label data of each graphic element data includes: sending each graphic element data to annotating users; and obtaining each graphic element data and the attribute label data of each graphic element data fed back by the annotating users.

[0050] Optionally, the annotation user may be a technician in the subsidiary organization who is responsible for setting the attribute label data of the graphic and text element data. After receiving each graphic and text element data, the annotation user will analyze each graphic and text element data, select the type label of the graphic and text element data from each preset type label, select the color label of the graphic and text element data from each preset color label, select the style label of the graphic and text element data from each preset style label, select the theme label of the graphic and text element data from each preset theme label, select the content type label of the graphic and text element data from each preset content type label, and select the detailed content label of the graphic and text element data from each preset detailed content label, thereby determining the attribute label data of each graphic and text element data. The annotation user will send each graphic and text element data and the attribute label data of each graphic and text element data to the business system of the subsidiary organization.

[0051] Optionally, it is possible to detect whether the business system of the sub-institution has received each graphic element data and the attribute label data of each graphic element data. After detecting that the business system of the sub-institution has received each graphic element data and the attribute label data of each graphic element data, the each graphic element data and the attribute label data of each graphic element data received by the business system of the sub-institution are obtained, thereby determining the attribute label data of each graphic element data.

[0052] Optionally, a preset clustering algorithm can be used to calculate the similarity between the attribute label data of each acquired graphic element data, cluster the acquired graphic element data according to the similarity between the attribute label data of each acquired graphic element data, and divide the acquired graphic element data into N groups of graphic element data. N is a positive integer greater than or equal to 2. Each group of graphic element data is composed of at least two graphic element data. Each group of graphic element data is a graphic element data group. The preset clustering algorithm can be a pre-set algorithm for calculating the similarity between the attribute label data of each acquired graphic element data, clustering the acquired graphic element data according to the similarity between the attribute label data of each acquired graphic element data, and dividing the acquired graphic element data into N groups of graphic element data, thereby obtaining multiple graphic element data groups. Exemplarily, N is 50, and the total number of each acquired graphic element data is 2000. A preset clustering algorithm can be used to calculate the similarity between the attribute label data of each acquired graphic element data, cluster the acquired graphic element data according to the similarity between the attribute label data of each acquired graphic element data, and divide the acquired graphic element data into 50 groups of graphic element data.

[0053] Optionally, for each graphic element data group, the attribute tag data ratio of the graphic element data group may include: the tag ratio of each preset type tag in the graphic element data group, the tag ratio of each preset color tag in the graphic element data group, the tag ratio of each preset style tag in the graphic element data group, the tag ratio of each preset theme tag in the graphic element data group, the tag ratio of each preset content type tag in the graphic element data group, and the tag ratio of each preset detailed content tag in the graphic element data group. For each preset type tag, the tag ratio of the preset type tag in the graphic element data group may refer to the ratio of the total number of graphic element data in the graphic element data group whose type tag is the preset type tag to the total number of graphic element data contained in the graphic element data group. For each preset color tag, the tag ratio of the preset color tag in the graphic element data group may refer to the ratio of the total number of graphic element data in the graphic element data group whose color tag is the preset color tag to the total number of graphic element data contained in the graphic element data group. For each preset style tag, the tag ratio of the preset style tag in the image and text element data set may refer to the ratio of the total number of image and text element data in the image and text element data set whose style tag is the preset style tag to the total number of image and text element data in the image and text element data set. For each preset theme tag, the tag ratio of the preset theme tag in the image and text element data set may refer to the ratio of the total number of image and text element data in the image and text element data set whose theme tag is the preset theme tag to the total number of image and text element data in the image and text element data set. For each preset content type tag, the tag ratio of the preset content type tag in the image and text element data set may refer to the ratio of the total number of image and text element data in the image and text element data set whose content type tag is the preset content type tag to the total number of image and text element data in the image and text element data set. For each preset detailed content tag, the tag ratio of the preset detailed content tag in the image and text element data set may refer to the ratio of the total number of image and text element data in the image and text element data set whose detailed content tag is the preset detailed content tag to the total number of image and text element data in the image and text element data set.

[0054] Optionally, for each graphic element data group, the attribute label data of the graphic element data group may include a type label, a color label, a style label, a theme label, a content type label, and a detailed content label for the graphic element data group. The type label of the graphic element data group may be text that can be used to indicate that the majority of the graphic element data in the graphic element data group is a table, image, graph, or text. The color label of the graphic element data group may be text that can be used to describe the color of the majority of the graphic element data in the graphic element data group. The style label of the graphic element data group may be text that can be used to describe the overall recognizable characteristics presented by the majority of the graphic element data in the graphic element data group. The theme label of the graphic element data group may be text that can be used to indicate a scenario suitable for using the majority of the graphic element data in the graphic element data group. The content type label of the graphic element data group may be text that can be used to indicate the type of object described or represented by the majority of the graphic element data in the graphic element data group. The detailed content label of the graphic element data group may be text that can be used to describe in detail the majority of the graphic element data in the graphic element data group.

[0055] Optionally, the proportion of attribute label data of each graphic element data group is counted, including: performing the following operations for each graphic element data group: counting the total number of graphic element data contained in the graphic element data group; for each preset type label, counting the total number of graphic element data with the type label of the preset type label in the graphic element data group, calculating the ratio of the total number of graphic element data with the type label of the preset type label in the graphic element data group to the total number of graphic element data contained in the graphic element data group, and obtaining the label proportion of the preset type label in the graphic element data group; for each preset color label, counting the graphic element data; The total number of graphic element data whose color labels in the element data group are preset color labels is calculated, and the ratio of the total number of graphic element data whose color labels in the graphic element data group are preset color labels to the total number of graphic element data contained in the graphic element data group is calculated to obtain the label ratio of the preset color labels in the graphic element data group; for each preset style label, the total number of graphic element data whose style labels in the graphic element data group are preset style labels is counted, and the ratio of the total number of graphic element data whose style labels in the graphic element data group are preset style labels is calculated to the total number of graphic element data contained in the graphic element data group. , obtain the label ratio of the preset style label in the graphic element data group; for each preset theme label, count the total number of graphic element data with the preset theme label in the graphic element data group, calculate the ratio of the total number of graphic element data with the preset theme label in the graphic element data group to the total number of graphic element data contained in the graphic element data group, and obtain the label ratio of the preset theme label in the graphic element data group; for each preset content type label, count the total number of graphic element data with the preset content type label in the graphic element data group, and calculate the content of the graphic element data group. The ratio of the total number of graphic element data whose content type label is the preset content type label to the total number of graphic element data contained in the graphic element data group is calculated to obtain the label ratio of the preset content type label in the graphic element data group; for each preset detailed content label, the total number of graphic element data whose detailed content label is the preset detailed content label in the graphic element data group is counted, and the ratio of the total number of graphic element data whose detailed content label in the graphic element data group is the preset detailed content label to the total number of graphic element data contained in the graphic element data group is calculated to obtain the label ratio of the preset detailed content label in the graphic element data group.

[0056] Optionally, the attribute label data of each graphic element data group is determined according to the proportion of the attribute label data of each graphic element data group, including: performing the following operations for each graphic element data group: sorting the label proportions of each preset type label in the graphic element data group in descending order of numerical value, and determining the preset type label to which the label proportion ranked first belongs as the type label of the graphic element data group; sorting the label proportions of each preset color system label in the graphic element data group in descending order of numerical value, and determining the preset color system label to which the label proportion ranked first belongs as the color system label of the graphic element data group; sorting the label proportions of each preset style label in the graphic element data group in descending order of numerical value, and determining the label proportion ranked first as the color system label of the graphic element data group. The preset style tag to which the proportion belongs is determined as the style tag of the graphic and text element data group; the tag proportions of each preset theme tag in the graphic and text element data group are sorted in descending order of numerical value, and the preset theme tag to which the tag proportion ranked first belongs is determined as the theme tag of the graphic and text element data group; the tag proportions of each preset content type tag in the graphic and text element data group are sorted in descending order of numerical value, and the preset content type tag to which the tag proportion ranked first belongs is determined as the content type tag of the graphic and text element data group; the tag proportions of each preset detailed content tag in the graphic and text element data group are sorted in descending order of numerical value, and the preset detailed content tag to which the tag proportion ranked first belongs is determined as the detailed content tag of the graphic and text element data group.

[0057] Optionally, the method further includes: dividing the image and text element data group into a new image and text element data group based on the sorted sequence of the label ratios of the preset color system labels in the image and text element data group. The image and text element data in the image and text element data group whose label ratios of the color system labels are located in the last M positions in the sorted sequence can be extracted, and the extracted image and text element data can be determined as a new image and text element data group. M is a positive integer greater than or equal to 1.

[0058] Optionally, the method further includes: dividing the image and text element data group into a new image and text element data group based on a sorted sequence of the label ratios of the preset topic tags in the image and text element data group. The image and text element data in the image and text element data group whose label ratios of the topic tags are located in the last K positions in the sorted sequence can be extracted, and the extracted image and text element data can be determined as a new image and text element data group. K is a positive integer greater than or equal to 1.

[0059] Optionally, for each new graphic element data group, the tag ratios of each preset type tag in the graphic element data group, each preset color tag in the graphic element data group, each preset style tag in the graphic element data group, each preset theme tag in the graphic element data group, each preset content type tag in the graphic element data group, and each preset detail tag in the graphic element data group are determined. The tag ratios of each preset type tag in the graphic element data group are then sorted in descending order, and the preset type tag with the highest tag ratio is determined as the type tag of the graphic element data group. The tag ratios of each preset color tag in the graphic element data group are sorted in descending order, and the preset color tag with the highest tag ratio is determined as the color tag of the graphic element data group. The tag ratios of each preset style tag in the graphic element data group are sorted in descending order, and the preset style tag with the highest tag ratio is determined as the style tag of the graphic element data group. The label ratios of each preset topic label in the image and text element data group are sorted in descending order of numerical value, and the preset topic label to which the label ratio ranked first belongs is determined as the theme label of the image and text element data group. The label ratios of each preset content type label in the image and text element data group are sorted in descending order of numerical value, and the preset content type label to which the label ratio ranked first belongs is determined as the content type label of the image and text element data group. The label ratios of each preset detailed content label in the image and text element data group are sorted in descending order of numerical value, and the preset detailed content label to which the label ratio ranked first belongs is determined as the detailed content label of the image and text element data group.

[0060] Step 102: After obtaining the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text, determine the image-text key parameters corresponding to the image-text generation instruction text.

[0061] Optionally, the image and text generation instruction text may be a text for instructing the generation of a new product image and text that is required for use at the current moment. The product description text corresponding to the image and text generation instruction text may be the product description text that needs to be included in the new product image and text that is required for use at the current moment. The image and text generation instruction text and the product description text corresponding to the image and text generation instruction text may be sent by the target user. The target user may be a business person in a subsidiary organization who is responsible for managing product images and texts. Every time a new product image and text needs to be generated, the target user will send the image and text generation instruction text and the product description text corresponding to the image and text generation instruction text to the business system of the subsidiary organization.

[0062] Optionally, it is possible to detect whether the business system of the subsidiary organization has received the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text. Each time it is detected that the business system of the subsidiary organization has received the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text, the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text received by the business system of the subsidiary organization are obtained, thereby obtaining the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text. After obtaining the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text, the image-text key parameters corresponding to the image-text generation instruction text are determined.

[0063] Optionally, the graphic generation instruction text includes type description text, color scheme description text, and style description text. The type description text may be text that describes the target user's requirements for the type label of the graphic element data required for generating new product graphics. The color scheme description text may be text that describes the target user's requirements for the color scheme label of the graphic element data required for generating new product graphics. The style description text may be text that describes the target user's requirements for the style label of the graphic element data required for generating new product graphics.

[0064] Optionally, the key parameters of the image and text corresponding to the image and text generation instruction text may include a target type tag, a target color tag, and a target style tag. The target type tag corresponding to the image and text generation instruction text may refer to a preset type tag selected from various preset type tags that meets the target user's requirements for the type tag of the image and text element data to be used to generate new product images and texts. The target color tag corresponding to the image and text generation instruction text may refer to a preset color tag selected from various preset color tags that meets the target user's requirements for the color tag of the image and text element data to be used to generate new product images and texts. The target style tag corresponding to the image and text generation instruction text may refer to a preset style tag selected from various preset style tags that meets the target user's requirements for the style tag of the image and text element data to be used to generate new product images and texts.

[0065] Optionally, determining the key parameters of the image and text corresponding to the image and text generation instruction text includes: inputting the parameter determination prompt instruction corresponding to the image and text generation instruction text into a pre-trained information extraction model, and obtaining the key parameters of the image and text corresponding to the image and text generation instruction text output by the information extraction model; wherein the key parameters of the image and text include a target type label, a target color label, and a target style label.

[0066] Therefore, based on the image and text generation instruction text and information extraction model, it is possible to quickly select a preset type label that meets the target user's requirements for the type label of the image and text element data needed to generate new product images and texts, a preset color label that meets the target user's requirements for the color label of the image and text element data needed to generate new product images and texts, and a preset style label that meets the target user's requirements for the style label of the image and text element data needed to generate new product images and texts.

[0067] Optionally, a pre-trained information extraction model is provided in the business system of the subsidiary. The pre-trained information extraction model may be a large language model for determining the target type label, target color label, and target style label corresponding to the image-text generation instruction text based on the prompt instruction parameters. The parameter determination prompt instruction can be used to instruct a pre-trained information extraction model to analyze and detect the type description text, color description text, and style description text in the image-text generation instruction text, select a preset type label from each preset type label that meets the target user's requirements for the type label of the image-text element data to be used for generating new product images and texts as described in the type description text as the target type label corresponding to the image-text generation instruction text, select a preset color label from each preset color label that meets the target user's requirements for the color label of the image-text element data to be used for generating new product images and texts as described in the color description text as the target color label corresponding to the image-text generation instruction text, and select a preset style label from each preset style label that meets the target user's requirements for the style label of the image-text element data to be used for generating new product images and texts as described in the style description text as the target style label corresponding to the image-text generation instruction text, thereby determining the text of the target type label, target color label, and target style label corresponding to the image-text generation instruction text. The parameter determination prompt instruction includes the image-text generation instruction text, each preset type label, each preset color label, and each preset style label. The parameter determination prompt instruction is input into a pre-trained information extraction model. The pre-trained information extraction model will analyze and detect the type description text, color description text, and style description text in the image-text generation instruction text in the parameter determination prompt instruction, and select a preset type label from each preset type label that meets the target user's requirements described in the type description text for the type label of the image-text element data to be used to generate new product images and texts as the target type label corresponding to the image-text generation instruction text. Select a preset color label from each preset color label that meets the target user's requirements described in the color description text for the color label of the image-text element data to be used to generate new product images and texts as the target color label corresponding to the image-text generation instruction text. Select a preset style label from each preset style label that meets the target user's requirements described in the style description text for the style label of the image-text element data to be used to generate new product images and texts as the target style label corresponding to the image-text generation instruction text, thereby determining the target type label, target color label, and target style label corresponding to the image-text generation instruction text, and outputting the target type label, target color label, and target style label corresponding to the image-text generation instruction text. The information extraction model can be pre-trained by the technical staff of the subsidiary organization and set in the business system of the subsidiary organization.

[0068] Optionally, the parameter determination prompt instruction corresponding to the image-text generation instruction text is input into a pre-trained information extraction model to obtain the image-text key parameters corresponding to the image-text generation instruction text output by the information extraction model, including: generating the parameter determination prompt instruction corresponding to the image-text generation instruction text according to the image-text generation instruction text, each preset type label, each preset color label, each preset style label and the parameter determination prompt instruction template; inputting the parameter determination prompt instruction corresponding to the image-text generation instruction text into a pre-trained information extraction model to obtain the target type label, target color label and target style label corresponding to the image-text generation instruction text output by the information extraction model.

[0069] Optionally, a parameter determination prompt instruction template is stored in the business system of the subsidiary organization. The parameter determination prompt instruction template is a parameter determination prompt instruction that does not contain the specified graphic generation instruction text, each preset type label, each preset color label, and each preset style label. The parameter determination prompt instruction template contains an instruction text filling position, a type label filling position, a color label filling position, and a style label filling position. The instruction text filling position is used to fill in the position of the graphic generation instruction text that needs to determine the corresponding target type label, target color label, and target style label. The type label filling position is used to fill in the position of each preset type label. The color label filling position is used to fill in the position of each preset color label. The style label filling position is used to fill in the position of each preset style label. After filling the graphic generation instruction text that needs to determine the corresponding target type label, target color label and target style label into the instruction text filling position in the parameter determination prompt instruction template, filling each preset type label into the type label filling position in the parameter determination prompt instruction template, filling each preset color label into the color label filling position in the parameter determination prompt instruction template, and filling each preset style label into the style label filling position in the parameter determination prompt instruction template, you can get the parameter determination prompt instruction corresponding to the graphic generation instruction text that needs to determine the corresponding target type label, target color label and target style label. The parameter determination prompt instruction corresponding to the image-text generation instruction text for which the corresponding target type label, target color label and target style label need to be determined is used to instruct the pre-trained information extraction model to analyze and detect the type description text, color description text and style description text in the image-text generation instruction text in the parameter determination prompt instruction, and select a preset type label from each preset type label that meets the target user's requirements described in the type description text for the type label of the image-text element data to be used to generate new product images and texts as the target type label corresponding to the image-text generation instruction text, select a preset color label from each preset color label that meets the target user's requirements described in the color description text for the color label of the image-text element data to be used to generate new product images and texts as the target color label corresponding to the image-text generation instruction text, and select a preset style label from each preset style label that meets the target user's requirements described in the style description text for the style label of the image-text element data to be used to generate new product images and texts as the target style label corresponding to the image-text generation instruction text, thereby determining the text of the target type label, target color label and target style label corresponding to the image-text generation instruction text.

[0070] Optionally, the parameter determination prompt instruction template stored in the business system of the subsidiary organization can be copied, and the graphic generation instruction text can be filled into the instruction text filling position in the parameter determination prompt instruction template, each preset type label can be filled into the type label filling position in the parameter determination prompt instruction template, each preset color label can be filled into the color label filling position in the parameter determination prompt instruction template, and each preset style label can be filled into the style label filling position in the parameter determination prompt instruction template. Then, the parameter determination prompt instruction corresponding to the graphic generation instruction text can be obtained. Then, the parameter determination prompt instruction corresponding to the image-text generation instruction text is input into a pre-trained information extraction model. The pre-trained information extraction model analyzes and detects the type description text, color description text, and style description text in the image-text generation instruction text in the parameter determination prompt instruction, and selects a preset type label from each preset type label that meets the target user's requirements described in the type description text for the type label of the image-text element data to be used to generate new product images and texts as the target type label corresponding to the image-text generation instruction text. A preset color label is selected from each preset color label that meets the target user's requirements described in the color description text for the color label of the image-text element data to be used to generate new product images and texts as the target color label corresponding to the image-text generation instruction text. A preset style label is selected from each preset style label that meets the target user's requirements described in the style description text for the style label of the image-text element data to be used to generate new product images and texts as the target style label corresponding to the image-text generation instruction text, thereby determining the target type label, target color label, and target style label corresponding to the image-text generation instruction text, and outputting the target type label, target color label, and target style label corresponding to the image-text generation instruction text. The target type label, target color label and target style label corresponding to the image-text generation instruction text output by the pre-trained information extraction model can be obtained, thereby determining the target type label, target color label and target style label corresponding to the image-text generation instruction text, that is, determining the key image-text parameters corresponding to the image-text generation instruction text.

[0071] Step 103 : Generate multiple product images and texts corresponding to the image and text generation instruction text according to each image and text element data group, the image and text key parameters, and the product description text, and provide each product image and text to a target user.

[0072] Optionally, the product image corresponding to the image-text generation instruction text may refer to the product image generated according to the image-text generation instruction text. The multiple product images corresponding to the image-text generation instruction text are multiple product images generated according to the image-text generation instruction text.

[0073] Optionally, multiple product graphics corresponding to the graphic generation instruction text are generated based on each graphic element data group, the graphic key parameters and the product description text, including: determining the target graphic element data group corresponding to the graphic generation instruction text based on the target type label, the target color label, the target style label and the attribute label data of each graphic element data group; obtaining L basic graphic element data from the target graphic element data group; wherein the type label of each basic graphic element data is the same as the target type label, the color label of each basic graphic element data is the same as the target color label, and the style label of each basic graphic element data is the same as the target style label; respectively inputting each basic graphic element data and the product description text into a pre-trained product graphic generation model to obtain product graphics corresponding to each basic graphic element data output by the product graphic generation model, and determining the product graphics corresponding to each basic graphic element data as each product graphics corresponding to the graphic generation instruction text, thereby obtaining L product graphics corresponding to the graphic generation instruction text.

[0074] Therefore, based on the type label, color label and style label, multiple graphic element data that meet the requirements of the target users described by the type description text, color description text and style description text in the graphic generation instruction text can be obtained from each basic graphic element data. Based on the product graphic generation model, the obtained graphic element data and product description text can be combined to generate multiple product graphics.

[0075] Optionally, the target graphic element data group corresponding to the graphic element generation instruction text may refer to a graphic element data group in each graphic element data group that contains graphic element data that meets the target user's requirements as described in the type description text, color description text, and style description text in the graphic element generation instruction text. Typically, for each graphic element data group, if the type label of the graphic element data group is the same as the target type label corresponding to the graphic element generation instruction text, the color label of the graphic element data group is the same as the target color label corresponding to the graphic element generation instruction text, and the style label of the graphic element data group is the same as the target style label corresponding to the graphic element generation instruction text, then the graphic element data group can be determined to be the target graphic element data group corresponding to the graphic element generation instruction text. The type label, color label and style label of each graphic element data group can be detected, and each graphic element data group whose type label is the same as the target type label corresponding to the graphic generation instruction text, whose color label is the same as the target color label corresponding to the graphic generation instruction text, and whose style label is the same as the target style label corresponding to the graphic generation instruction text is determined as the target graphic element data group corresponding to the graphic generation instruction text, thereby determining the target graphic element data group corresponding to the graphic generation instruction text.

[0076] Optionally, basic graphic element data may refer to graphic element data that meets the requirements of the target user described by the type description text, color description text, and style description text in the graphic generation instruction text. Normally, for each graphic element data, if the type label of the graphic element data is the same as the target type label corresponding to the graphic generation instruction text, the color label of the graphic element data is the same as the target color label corresponding to the graphic generation instruction text, and the style label of the graphic element data is the same as the target style label corresponding to the graphic generation instruction text, it can be determined that the graphic element data group is basic graphic element data. L is a positive integer greater than or equal to 2. Exemplarily, L is 3, 5, or 10. The type label, color label and style label of the graphic element data in the target graphic element data group can be detected, and each graphic element data whose type label is the same as the target type label corresponding to the graphic element generation instruction text, whose color label is the same as the target color label corresponding to the graphic element generation instruction text, and whose style label is the same as the target style label corresponding to the graphic element generation instruction text is determined as the basic graphic element data, and then L basic graphic element data are randomly obtained from each basic graphic element data.

[0077] Optionally, a pre-trained product image and text generation model is provided in the business system of the subsidiary. The pre-trained product image and text generation model can be a large language model for combining input basic image and text element data and product description text to obtain product images and text corresponding to the basic image and text element data. The product images and text corresponding to the basic image and text element data can be images containing text that are obtained by combining the basic image and text element data and product description text, and are used to display the designated products of the subsidiary. The basic image and text element data and product description text are input into the pre-trained product image and text generation model. The pre-trained product image and text generation model combines the input basic image and text element data and product description text to obtain product images and text corresponding to the basic image and text element data, and outputs the product images and text corresponding to the basic image and text element data. When the input basic image and text element data is an image, the input product description text can be added to the input basic image and text element data to combine the input basic image and text element data and product description text to obtain the product images and text corresponding to the basic image and text element data. The basic image and text element data after adding the product description text is the product images and text corresponding to the basic image and text element data. When the input basic graphic element data is a table, the input basic graphic element data and product description text can be combined by adding them to a preset blank image to obtain a product graphic corresponding to the basic graphic element data. The preset blank image after adding the basic graphic element data and product description text is the product graphic corresponding to the basic graphic element data. When the input basic graphic element data is a graphic, the input basic graphic element data and product description text can be combined by adding them to a preset blank image to obtain a product graphic corresponding to the basic graphic element data. The preset blank image after adding the basic graphic element data and product description text is the product graphic corresponding to the basic graphic element data. When the input basic graphic element data is text, the input basic graphic element data and product description text can be combined by adding them to a preset blank image to obtain a product graphic corresponding to the basic graphic element data. The preset blank image after adding the basic graphic element data and product description text is the product graphic corresponding to the basic graphic element data. The preset blank image may be a pre-set image that does not contain text. The product image and text generation model may be pre-trained by the technical staff of the subsidiary organization and set in the business system of the subsidiary organization.

[0078] Optionally, for each basic graphic element data obtained, the basic graphic element data and the product description text can be input into a pre-trained product graphic generation model. The pre-trained product graphic generation model will combine the basic graphic element data and the product description text to obtain the product graphic corresponding to the basic graphic element data, and output the product graphic corresponding to the basic graphic element data. The product graphic corresponding to the basic graphic element data output by the pre-trained product graphic generation model can be obtained, and the product graphic corresponding to the basic graphic element data can be determined as the product graphic corresponding to the graphic generation instruction text. Thus, L product graphics corresponding to the graphic generation instruction text are obtained, thereby generating multiple product graphics corresponding to the graphic generation instruction text. The obtained product graphics corresponding to the graphic generation instruction text can be sent to the target user, thereby providing the target user with each product graphic.

[0079] Optionally, if there is no graphic element data group in each graphic element data group whose type label is the same as the target type label corresponding to the graphic element generation instruction text, whose color label is the same as the target color label corresponding to the graphic element generation instruction text, and whose style label is the same as the target style label corresponding to the graphic element generation instruction text, then a preset prompt message is sent to the target user. If it is impossible to obtain L basic graphic element data from the target graphic element data group, for example, the number of basic graphic element data contained in the target graphic element data group is less than L, then a preset prompt message is sent to the target user. The preset prompt message can be a pre-set text used to prompt that the basic graphic element data cannot be obtained based on the graphic element generation instruction text sent by the user, and the graphic element generation instruction text needs to be adjusted and then resent.

[0080] Step 104: After obtaining the target product image and text corresponding to the image and text generation instruction text fed back by the target user, the time information, region information and product information in the target product image and text are detected according to preset product image and text rules, and the detection result is provided to the target user.

[0081] Optionally, the target product image corresponding to the image-text generation instruction text may be a product image selected from the various product images corresponding to the image-text generation instruction text that meets the current product image-text generation requirements of the subsidiary's business system. After the various product images corresponding to the image-text generation instruction text are provided to the target user, the target user may select a product image from the various product images as the target product image corresponding to the image-text generation instruction text, and then send the target product image corresponding to the image-text generation instruction text to the subsidiary's business system.

[0082] Optionally, it is possible to detect whether the business system of the sub-institution has received the target product image and text corresponding to the image and text generation instruction text sent by the target user. When it is detected that the business system of the sub-institution has received the target product image and text corresponding to the image and text generation instruction text sent by the target user, the target product image and text corresponding to the image and text generation instruction text received by the business system of the sub-institution can be obtained, and the time information, regional information and product information in the target product image and text corresponding to the image and text generation instruction text can be detected according to preset product image and text rules.

[0083] Optionally, the subsidiary's business system stores preset product image and text rules. These preset product image and text rules can be text describing the requirements that product images and text must meet. These preset product image and text rules can include time information detection rules, region information detection rules, and product information detection rules. Time information detection rules can be text describing the requirements that time information in product images and text must meet. Time information in product images and text can refer to the year, month, and date included in the product images and text. Requirements that time information in product images and text must meet include, but are not limited to, the year included in the product images and text must be the current year, the month included in the product images and text must be the current month, and the date included in the product images and text must be the current date. Region information detection rules can be text describing the requirements that region information in product images and text must meet. Region information in product images and text can refer to text describing the region of the subsidiary. Requirements that time information in product images and text must meet include, but are not limited to, ensuring that the region described in the region information in the product images and text is the correct region of the subsidiary. Product information detection rules can be text describing the requirements that product information in product images and text must meet. Product information in product images and text can refer to product-related text included in the product images and text. Requirements for product information in product images and text include, but are not limited to, being contained within a product text set. A subsidiary's business system stores a product text set. This product text set can consist of all valid text related to the subsidiary's products that can be used by the subsidiary's business system.

[0084] Optionally, the time information, regional information and product information in the target product image and text are detected according to preset product image and text rules, including: inputting the target product image and text and the time information detection rules into a pre-trained product image and text detection model, and obtaining the time information detection result of the target product image and text output by the product image and text detection model; inputting the target product image and text and the regional information detection rules into a pre-trained product image and text detection model, and obtaining the regional information detection result of the target product image and text output by the product image and text detection model; inputting the target product image and text and the product information detection rules into a pre-trained product image and text detection model, and obtaining the product information detection result of the target product image and text output by the product image and text detection model.

[0085] Therefore, based on the product image and text detection model, it is possible to detect whether the time information, region information and product information in the target product image and text comply with the time information detection rules, region information detection rules and product information detection rules, and obtain corresponding detection results.

[0086] Optionally, a pre-trained product image and text detection model may be installed in the subsidiary's business system. This pre-trained product image and text detection model can be a large language model that analyzes and detects input product images and detection rules, determines whether the product images meet the requirements described by the detection rules, and outputs the detection results of the product images. The detection rules can include time information detection rules, regional information detection rules, or product information detection rules. The product image and text detection model can be pre-trained by the subsidiary's technical staff and installed in the subsidiary's business system.

[0087] Optionally, the product image and time information detection rules are input into a pre-trained product image detection model. The pre-trained product image detection model analyzes and detects the input product image and time information detection rules to determine whether the product image meets the requirements described by the time information detection rules, and outputs the time information detection result of the product image. The time information detection result of the product image can be text that indicates whether the product image meets the requirements described by the time information detection rules. The time information detection result of the product image can be either a passed time information detection or a failed time information detection. If the time information detection result of the product image is a passed time information detection, it indicates that the product image meets the requirements described by the time information detection rules. If the time information detection result of the product image is a failed time information detection, it indicates that the product image does not meet the requirements described by the time information detection rules. The pre-trained product image detection model analyzes and detects the input product image and time information detection rules to determine whether the product image meets the requirements described by the time information detection rules. After determining that the product image meets the requirements described by the time information detection rules, it determines that the time information detection result of the product image is a passed time information detection, and outputs the time information detection result of the product image. The pre-trained product image detection model analyzes and detects the input product image and time information detection rules to determine whether the product image meets the requirements described by the time information detection rules. If it determines that the product image does not meet the requirements described by the time information detection rules, it determines that the time information detection result of the product image is failed and outputs the time information detection result of the product image. You can obtain the time information detection result of the product image output by the product image detection model.

[0088] Optionally, the product image and regional information detection rules are input into a pre-trained product image detection model. The pre-trained product image detection model analyzes and tests the input product image and regional information detection rules to determine whether the product image meets the requirements described in the regional information detection rules, and outputs a regional information detection result for the product image. The regional information detection result for the product image can be text indicating whether the product image meets the requirements described in the regional information detection rules. The regional information detection result for the product image can be either passed or failed. If the regional information detection result for the product image is passed, it indicates that the product image meets the requirements described in the regional information detection rules. If the regional information detection result for the product image is failed, it indicates that the product image does not meet the requirements described in the regional information detection rules. The pre-trained product image detection model analyzes and tests the input product image and regional information detection rules to determine whether the product image meets the requirements described in the regional information detection rules. After determining that the product image meets the requirements described in the regional information detection rules, the model determines that the regional information detection result for the product image is passed and outputs the regional information detection result for the product image. The pre-trained product image detection model analyzes and checks the input product image and regional information detection rules to determine whether the product image meets the requirements described by the regional information detection rules. If it determines that the product image does not meet the requirements described by the regional information detection rules, it determines that the regional information detection result of the product image has failed the regional information detection and outputs the regional information detection result of the product image. The regional information detection result of the product image output by the product image detection model can be obtained.

[0089] Optionally, the product image and product information detection rules are input into a pre-trained product image detection model. The pre-trained product image detection model will analyze and detect the input product image and product information detection rules to determine whether the product image meets the requirements described by the product information detection rules, and output the product information detection result of the product image. The product information detection result of the product image can be text used to indicate whether the product image meets the requirements described by the product information detection rules. The product information detection result of the product image is either passed or failed. If the product information detection result of the product image is passed, it indicates that the product image meets the requirements described by the product information detection rules. If the product information detection result of the product image is failed, it indicates that the product image does not meet the requirements described by the product information detection rules. The pre-trained product image detection model will analyze and detect the input product image and product information detection rules to determine whether the product image meets the requirements described by the product information detection rules. After determining that the product image meets the requirements described by the product information detection rules, it will determine that the product information detection result of the product image is passed and output the product information detection result of the product image. The pre-trained product image detection model analyzes and detects the input product image and product information detection rules to determine whether the product image meets the requirements described in the product information detection rules. If it determines that the product image does not meet the requirements described in the product information detection rules, it determines that the product information detection result of the product image fails the product information detection and outputs the product information detection result of the product image. The product information detection result of the product image output by the product image detection model can be obtained.

[0090] Optionally, the target product image and text and time information detection rules can be input into a pre-trained product image and text detection model, and then the time information detection result of the target product image and text outputted by the product image and text detection model can be obtained. The target product image and text and region information detection rules can be input into a pre-trained product image and text detection model, and then the region information detection result of the target product image and text can be obtained. The target product image and text and product information detection rules can be input into a pre-trained product image and text detection model, and then the product information detection result of the target product image and text can be obtained.

[0091] Optionally, the time information detection results, regional information detection results, and product information detection results of the target product image and text can be sent to the target user, thereby providing the detection results to the target user. The target user can view the time information detection results, regional information detection results, and product information detection results of the target product image and text, and based on the time information detection results, regional information detection results, and product information detection results of the target product image and text, confirm whether there are any problems with the time information, regional information, and product information in the target product image and text, and edit the information confirmed to have problems.

[0092] Optionally, after providing the target user with the product images corresponding to the image and text generation instruction text, if the target user determines that none of the product images meet the current product image and text generation requirements of the subsidiary's business system and is unable to select a product image from the various product images as the target product image corresponding to the image and text generation instruction text, the target user will send product image and text quality prompt information to the subsidiary's business system. The product image and text quality prompt information can be a pre-set text used to prompt that it is impossible to select a product image from the various generated product images as the target product image corresponding to the image and text generation instruction text, and that it is necessary to regenerate the various product images corresponding to the image and text generation instruction text.

[0093] Optionally, after providing each product image and text to the target user, it also includes: after obtaining the product image and text quality prompt information fed back by the target user, continuing to obtain L basic image and text element data from the target image and text element data group; inputting each basic image and text element data and the product description text into a pre-trained product image and text generation model respectively, obtaining the product images and texts corresponding to each basic image and text element data output by the product image and text generation model, determining the product images and texts corresponding to each basic image and text element data as each product image and text corresponding to the image and text generation instruction text, thereby obtaining new L product images and texts corresponding to the image and text generation instruction text; and providing the new L product images and texts corresponding to the image and text generation instruction text to the target user.

[0094] Therefore, when the generated product images and texts do not meet the current product image and text generation requirements of the subsidiary's business system, multiple image and text element data that meet the requirements of the target users described by the type description text, color description text and style description text in the image and text generation instruction text can be re-obtained, and based on the product image and text generation model, the acquired image and text element data and product description text can be combined to generate multiple product images and texts.

[0095] Optionally, it is possible to detect whether the business system of the sub-institution has received the product image and text quality prompt information sent by the target user. When it is detected that the business system of the sub-institution has received the product image and text quality prompt information sent by the target user, the business system of the sub-institution can obtain the product image and text quality prompt information sent by the target user received by the business system of the sub-institution, and continue to obtain L basic image and text element data from the target image and text element data group. Continuing to obtain L basic image and text element data from the target image and text element data group means continuing to randomly obtain L new basic image and text element data from each basic image and text element data in the target image and text element data group. The new L basic image and text element data are L basic image and text element data that are different from the L basic image and text element data randomly obtained last time. Then, for the new L basic graphic and text element data, each basic graphic and text element data and product description text is input into the pre-trained product graphic and text generation model respectively, and the product graphic and text corresponding to each basic graphic and text element data is output by the product graphic and text generation model, and the product graphic and text corresponding to each basic graphic and text element data is determined as each product graphic and text corresponding to the graphic and text generation instruction text, thereby obtaining new L product graphics and texts corresponding to the graphic and text generation instruction text, and the new L product graphics and texts corresponding to the graphic and text generation instruction text are provided to the target user.

[0096] The technical solution of the embodiment of the present invention obtains each graphic and text element data and divides each graphic and text element data into multiple graphic and text element data groups; after obtaining the graphic and text generation instruction text and the product description text corresponding to the graphic and text generation instruction text, determines the graphic and text key parameters corresponding to the graphic and text generation instruction text; then, based on each graphic and text element data group, the graphic and text key parameters and the product description text, generates multiple product graphics corresponding to the graphic and text generation instruction text, and provides each product graphics to the target user; after obtaining the target product graphics corresponding to the graphic and text generation instruction text fed back by the target user, the time information, regional information and product information in the target product graphics are detected according to the preset product graphics rules, and the detection results are provided to the target user, which solves the problem that the product graphics generation solution in the related art depends on the graphics and text generation instruction text. Due to the problem of relying on manual operation, high time cost and labor cost, and low efficiency of product image and text generation, each image and text element data can be divided into multiple image and text element data groups. After obtaining the image and text generation instruction text, multiple product images and texts can be automatically generated based on the image and text element data group, image and text key parameters and product description text, and each product image and text can be provided to the user. After obtaining the product image and text selected from the generated product images that meets the current product image and text generation requirements of the subsidiary's business system, the time information, regional information and product information in the product image and text can be automatically detected according to the preset product image and text rules, and the detection results can be provided to the user, which reduces the time cost and labor cost of the product image and text generation process and improves the efficiency and accuracy of the product image and text generation process.

[0097] The technical solution of the embodiment of the present invention can help the business system of the subsidiary organization to accurately and quickly generate product pictures and texts, realize efficient, low-cost and business-effective intelligent picture and text generation services, and enable the business system of the subsidiary organization to better serve the users of the subsidiary organization.

[0098] The technical solution of the embodiment of the present invention can integrate intelligent computing technology and big model technology into the automatic generation scenario of product images and texts of the business system of the subsidiary organization, effectively optimize the product image and text generation process of the business system of the subsidiary organization, improve the product service level and work efficiency of the business system of the subsidiary organization, reduce the operating cost of the business system of the subsidiary organization, and improve the product service level of the business system of the subsidiary organization.

[0099] The technical solution of the embodiment of the present invention can classify and combine graphic and text element data, analyze the key demand points of the product graphic and text generation process through intelligent analysis methods, realize accurate analysis, matching and intelligent combination of graphic and text element data, and provide convenient and efficient graphic and text generation services.

[0100] Example 2

[0101] Figure 2This is a flowchart of a method for generating product images and texts provided in the second embodiment of the present invention. This embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the method includes:

[0102] Step 201: Acquire data of each graphic element and determine attribute tag data of each graphic element.

[0103] The attribute tag data includes a type tag, a color tag, a style tag, a theme tag, a content type tag, and a detailed content tag.

[0104] Step 202: Cluster each graphic and text element data according to its attribute label data to obtain a plurality of graphic and text element data groups.

[0105] Step 203: Count the percentage of attribute label data in each graphic element data group.

[0106] Step 204 : Determine the attribute label data of each graphic and text element data group according to the proportion of the attribute label data of each graphic and text element data group.

[0107] Step 205: After obtaining the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text, the parameter determination prompt instruction corresponding to the image-text generation instruction text is input into a pre-trained information extraction model to obtain the image-text key parameters corresponding to the image-text generation instruction text output by the information extraction model.

[0108] The key parameters of the image and text include target type label, target color label and target style label.

[0109] Step 206 : Determine a target graphic element data group corresponding to the graphic element generation instruction text according to the target type label, the target color system label, the target style label, and the attribute label data of each graphic element data group.

[0110] Step 207: Obtain L basic graphic element data from the target graphic element data group.

[0111] The type label of each basic graphic element data is the same as the target type label, the color label of each basic graphic element data is the same as the target color label, and the style label of each basic graphic element data is the same as the target style label.

[0112] Step 208: Input each basic graphic and text element data and the product description text into a pre-trained product graphic and text generation model respectively, obtain the product graphic and text corresponding to each basic graphic and text element data output by the product graphic and text generation model, determine the product graphic and text corresponding to each basic graphic and text element data as each product graphic and text corresponding to the graphic and text generation instruction text, thereby obtaining L product graphics and texts corresponding to the graphic and text generation instruction text, and provide each product graphic and text to the target user.

[0113] Step 209: After obtaining the target product image and text corresponding to the image and text generation instruction text fed back by the target user, the target product image and text and the time information detection rules are input into a pre-trained product image and text detection model to obtain the time information detection result of the target product image and text output by the product image and text detection model.

[0114] Step 210: Input the target product image and text and regional information detection rules into a pre-trained product image and text detection model to obtain the regional information detection result of the target product image and text output by the product image and text detection model.

[0115] Step 211: Input the target product image and product information detection rules into a pre-trained product image detection model to obtain a product information detection result of the target product image output by the product image detection model.

[0116] Step 212: Provide the target user with the time information detection result, the region information detection result, and the product information detection result of the target product image and text.

[0117] The technical solution of the embodiment of the present invention can divide each graphic element data into multiple graphic element data groups based on the attribute label data of each graphic element data, and determine the attribute label data of each graphic element data group. It can quickly select a preset type label that meets the target user's requirements for the type label of the graphic element data to be used for generating new product graphics, a preset color label that meets the target user's requirements for the color label of the graphic element data to be used for generating new product graphics, and a preset style label that meets the target user's requirements for the style label of the graphic element data to be used for generating new product graphics based on the graphic element data generation instruction text and information extraction model. The preset style tag can obtain multiple graphic element data that meet the requirements of the target users described by the type description text, color description text and style description text in the graphic generation instruction text from various basic graphic element data based on the type tag, color tag and style tag. The obtained graphic element data and product description text can be combined based on the product graphic generation model to generate multiple product graphics. Based on the product graphic detection model, the time information, regional information and product information in the target product graphic can be detected to see whether they comply with the time information detection rules, regional information detection rules and product information detection rules to obtain corresponding detection results.

[0118] Example 3

[0119] Figure 3 This is a schematic diagram of the structure of a device for generating product images and texts provided in the third embodiment of the present invention. The device can be configured in the business system of a subsidiary of a financial institution. Figure 3 As shown, the device includes: a data grouping module 301, a parameter determination module 302, a picture and text generation module 303 and a picture and text detection module 304.

[0120] Among them, the data grouping module 301 is used to obtain each graphic element data and divide each graphic element data into multiple graphic element data groups; the parameter determination module 302 is used to determine the graphic key parameters corresponding to the graphic generation instruction text after obtaining the graphic generation instruction text and the product description text corresponding to the graphic generation instruction text; the graphic generation module 303 is used to generate multiple product graphics corresponding to the graphic generation instruction text based on each graphic element data group, the graphic key parameters and the product description text, and provide each product graphics to the target user; the graphic detection module 304 is used to detect the time information, regional information and product information in the target product graphics according to preset product graphic rules after obtaining the target product graphics corresponding to the graphic generation instruction text fed back by the target user. The detection result is provided to the target user.

[0121] The technical solution of the embodiment of the present invention obtains each graphic and text element data and divides each graphic and text element data into multiple graphic and text element data groups; after obtaining the graphic and text generation instruction text and the product description text corresponding to the graphic and text generation instruction text, determines the graphic and text key parameters corresponding to the graphic and text generation instruction text; then, based on each graphic and text element data group, the graphic and text key parameters and the product description text, generates multiple product graphics corresponding to the graphic and text generation instruction text, and provides each product graphics to the target user; after obtaining the target product graphics corresponding to the graphic and text generation instruction text fed back by the target user, the time information, regional information and product information in the target product graphics are detected according to the preset product graphics rules, and the detection results are provided to the target user, which solves the problem that the product graphics generation solution in the related art depends on the graphics and text generation instruction text. Due to the problem of relying on manual operation, high time cost and labor cost, and low efficiency of product image and text generation, each image and text element data can be divided into multiple image and text element data groups. After obtaining the image and text generation instruction text, multiple product images and texts can be automatically generated based on the image and text element data group, image and text key parameters and product description text, and each product image and text can be provided to the user. After obtaining the product image and text selected from the generated product images that meets the current product image and text generation requirements of the subsidiary's business system, the time information, regional information and product information in the product image and text can be automatically detected according to the preset product image and text rules, and the detection results can be provided to the user, which reduces the time cost and labor cost of the product image and text generation process and improves the efficiency and accuracy of the product image and text generation process.

[0122] In an optional implementation of an embodiment of the present invention, optionally, when the data grouping module 301 performs the operation of dividing each graphic element data into multiple graphic element data groups, it is specifically used to: determine the attribute label data of each graphic element data; wherein the attribute label data includes a type label, a color label, a style label, a theme label, a content type label and a detailed content label; cluster each graphic element data according to the attribute label data of each graphic element data to obtain multiple graphic element data groups; count the proportion of attribute label data of each graphic element data group; determine the attribute label data of each graphic element data group according to the proportion of attribute label data of each graphic element data group.

[0123] In an optional implementation of an embodiment of the present invention, optionally, when the parameter determination module 302 performs the operation of determining the key parameters of the graphic and text corresponding to the graphic and text generation instruction text, it is specifically used to: input the parameter determination prompt instruction corresponding to the graphic and text generation instruction text into a pre-trained information extraction model, and obtain the graphic and text key parameters corresponding to the graphic and text generation instruction text output by the information extraction model; wherein, the graphic and text key parameters include target type labels, target color labels and target style labels.

[0124] In an optional implementation of an embodiment of the present invention, optionally, when the graphic and text generation module 303 performs the operation of generating multiple product graphics corresponding to the graphic and text generation instruction text according to each graphic and text element data group, the graphic and text key parameters and the product description text, it is specifically used to: determine the target graphic and text element data group corresponding to the graphic and text generation instruction text according to the target type label, the target color label, the target style label and the attribute label data of each graphic and text element data group; obtain L basic graphic and text element data from the target graphic and text element data group; wherein, each basic graphic and text element data The type label is the same as the target type label, the color label of each basic graphic element data is the same as the target color label, and the style label of each basic graphic element data is the same as the target style label; each basic graphic element data and the product description text are respectively input into a pre-trained product graphic element generation model to obtain the product graphic corresponding to each basic graphic element data output by the product graphic generation model, and the product graphic corresponding to each basic graphic element data is determined as each product graphic corresponding to the graphic generation instruction text, thereby obtaining L product graphics corresponding to the graphic generation instruction text.

[0125] In an optional implementation of an embodiment of the present invention, optionally, when the image and text detection module 304 performs the operation of detecting the time information, regional information and product information in the target product image and text according to preset product image and text rules, it is specifically used to: input the target product image and text and the time information detection rules into a pre-trained product image and text detection model to obtain the time information detection result of the target product image and text output by the product image and text detection model; input the target product image and text and the regional information detection rules into the pre-trained product image and text detection model to obtain the regional information detection result of the target product image and text output by the product image and text detection model; input the target product image and text and the product information detection rules into the pre-trained product image and text detection model to obtain the product information detection result of the target product image and text output by the product image and text detection model.

[0126] In an optional implementation of an embodiment of the present invention, optionally, the image and text generation module 303 is also used to: after obtaining the product image and text quality prompt information fed back by the target user, continue to obtain L basic image and text element data from the target image and text element data group; input each basic image and text element data and the product description text into a pre-trained product image and text generation model respectively, and obtain the product images and texts corresponding to each basic image and text element data output by the product image and text generation model; determine the product images and texts corresponding to each basic image and text element data as each product image and text corresponding to the image and text generation instruction text, thereby obtaining new L product images and texts corresponding to the image and text generation instruction text; and provide the new L product images and texts corresponding to the image and text generation instruction text to the target user.

[0127] The device for generating product images and texts provided in the embodiment of the present invention can execute the method for generating product images and texts provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0128] Example 4

[0129] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement the method for generating product graphics and text of an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, electronic devices, blade electronic devices, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0130] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0131] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0132] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for generating product images and text.

[0133] In some embodiments, the method for generating product graphics and text may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on a heterogeneous hardware accelerator via a ROM and / or a communication unit. When the computer program is loaded into RAM and executed by a processor, one or more steps of the method for generating product graphics and text described above may be performed. Alternatively, in other embodiments, the processor may be configured to execute the method for generating product graphics and text by any other appropriate means (e.g., by means of firmware).

[0134] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or electronic device.

[0136] In the context of the present invention, computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0137] To provide interaction with a user, the systems and techniques described herein can be implemented on a heterogeneous hardware accelerator that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the heterogeneous hardware accelerator. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0138] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as data electronics), or a computing system that includes middleware components (e.g., application electronics), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0139] A computing system may include a client and an electronic device. The client and electronic device are generally remote from each other and typically interact via a communication network. The client-electronic device relationship is established by computer programs running on the respective computers and establishing a client-electronic device relationship. The electronic device may be a cloud electronic device, also known as a cloud computing electronic device or cloud host, a host product within a cloud computing service ecosystem that addresses the management difficulties and limited business scalability of traditional physical hosts and VPS services.

[0140] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0141] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for generating product images and texts, characterized in that: include: Acquire each graphic element data, and divide each graphic element data into a plurality of graphic element data groups; After obtaining the image-text generation instruction text and the product description text corresponding to the image-text generation instruction text, determining the image-text key parameters corresponding to the image-text generation instruction text; generating a plurality of product images and texts corresponding to the image and text generation instruction text according to each image and text element data group, the image and text key parameters, and the product description text, and providing each product image and text to a target user; After obtaining the target product image and text corresponding to the image and text generation instruction text fed back by the target user, the time information, region information and product information in the target product image and text are detected according to preset product image and text rules, and the detection result is provided to the target user.

2. The method for generating product images and texts according to claim 1, characterized in that: Each graphic element data is divided into multiple graphic element data groups, including: Determine attribute tag data of each graphic element data; wherein the attribute tag data includes type tag, color tag, style tag, theme tag, content type tag and detailed content tag; Clustering each graphic and text element data according to the attribute label data of each graphic and text element data to obtain multiple graphic and text element data groups; Count the percentage of attribute label data in each graphic element data group; The attribute label data of each graphic and text element data group is determined according to the attribute label data ratio of each graphic and text element data group.

3. The method for generating product images and texts according to claim 2, characterized in that: Determining the key parameters of the image and text corresponding to the image and text generation instruction text includes: The parameter determination prompt instruction corresponding to the image-text generation instruction text is input into a pre-trained information extraction model to obtain the image-text key parameters corresponding to the image-text generation instruction text output by the information extraction model; wherein the image-text key parameters include target type label, target color label and target style label.

4. The method for generating product images and texts according to claim 3, characterized in that: Generating a plurality of product images and texts corresponding to the image and text generation instruction text according to each image and text element data group, the image and text key parameters, and the product description text, including: Determining a target graphic element data group corresponding to the graphic element generation instruction text according to the target type label, the target color system label, the target style label, and the attribute label data of each graphic element data group; Acquire L basic graphic element data from the target graphic element data group; wherein the type label of each basic graphic element data is the same as the target type label, the color system label of each basic graphic element data is the same as the target color system label, and the style label of each basic graphic element data is the same as the target style label; Each basic graphic and text element data and the product description text are respectively input into a pre-trained product graphic and text generation model to obtain the product graphic and text corresponding to each basic graphic and text element data output by the product graphic and text generation model, and the product graphic and text corresponding to each basic graphic and text element data are determined as each product graphic and text corresponding to the graphic and text generation instruction text, thereby obtaining L product graphics and texts corresponding to the graphic and text generation instruction text.

5. The method for generating product images and texts according to claim 1, characterized in that: Detecting the time information, region information, and product information in the target product image and text according to preset product image and text rules includes: Inputting the target product image and text and time information detection rules into a pre-trained product image and text detection model to obtain a time information detection result of the target product image and text output by the product image and text detection model; Inputting the target product image and text and regional information detection rules into a pre-trained product image and text detection model to obtain a regional information detection result of the target product image and text output by the product image and text detection model; The target product image and text and product information detection rules are input into a pre-trained product image and text detection model to obtain a product information detection result of the target product image and text output by the product image and text detection model.

6. The method for generating product images and texts according to claim 4, characterized in that: After providing each product image and text to the target users, it also includes: After obtaining the product image and text quality prompt information fed back by the target user, continue to obtain L basic image and text element data from the target image and text element data group; Inputting each basic graphic element data and the product description text into a pre-trained product graphic generation model, obtaining product graphics corresponding to each basic graphic element data output by the product graphic generation model, determining the product graphics corresponding to each basic graphic element data as each product graphics corresponding to the graphic generation instruction text, thereby obtaining L new product graphics corresponding to the graphic generation instruction text; The new L product images and texts corresponding to the image and text generation instruction text are provided to the target user.

7. A device for generating product images and texts, characterized in that: include: A data grouping module is used to obtain each graphic element data and divide each graphic element data into multiple graphic element data groups; A parameter determination module is used to determine the key parameters of the image and text corresponding to the image and text generation instruction text after obtaining the image and text generation instruction text and the product description text corresponding to the image and text generation instruction text; An image and text generation module is used to generate a plurality of product images and texts corresponding to the image and text generation instruction text according to each image and text element data group, the image and text key parameters, and the product description text, and provide each product image and text to a target user; The image and text detection module is used to detect the time information, region information and product information in the target product image and text according to preset product image and text rules after obtaining the target product image and text corresponding to the image and text generation instruction text fed back by the target user, and provide the detection results to the target user.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating product graphics according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating product graphics and text according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the method for generating product graphics and text according to any one of claims 1 to 6.

Images