Method, system and device for automatically generating image and medium

Abstract

The invention belongs to the technical field of data processing, and discloses a method, system and device for automatically generating an image and a medium, and the method comprises the steps: obtaining user interaction data of social software, and carrying out the preprocessing of the user interaction data, and obtaining target data; performing relation extraction on the target data to obtain a relation set; compressing the relation set to obtain a compressed relation set; performing user relationship classification on the compressed relationship set to obtain a user relationship category; constructing a user relationship knowledge graph based on the user relationship category; and generating a dynamic image based on the user relation knowledge graph, and visually displaying the dynamic image. According to the invention, the relation between figures can be accurately extracted, so that a complex figure relation graph can be automatically generated.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular relates to a method, system, device and medium for automatically generating an image. Background Art

[0002] With the rapid development of internet technology, online social networking has become an important way for people to communicate in modern society. In particular, the widespread use of smartphones and mobile internet has enabled users to interact through social applications anytime and anywhere, greatly expanding the time and space limitations of social interaction.

[0003] From forums and blogs in the early days to WeChat, Weibo, Douyin, Kuaishou, and more, social media has evolved in diverse forms to meet the needs of different user groups. These platforms allow users to express themselves more richly through text, images, audio, video, and other forms.

[0004] A large amount of user social data has been accumulated in social software. These user data contain information about people's relationships in the real world. By exploring the relationship information in social software, we can reveal user behavior patterns, interests and hobbies, social relationships, etc., and provide support for personalized services.

[0005] However, since the social data in social software are usually short texts, the data is fragmented and semantically sparse, it is difficult to accurately extract complex person relationships from the social data of social software. Summary of the Invention

[0006] The purpose of the present invention is to provide a method, system, device and medium for automatically generating images to solve the problem in the prior art that it is difficult to accurately extract complex character relationships from the social data of social software because the social data in social software is usually small texts, the data is fragmented and semantically sparse.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for automatically generating an image, the method comprising: Obtain user interaction data from social software, pre-process the user interaction data, and obtain target data; Extract relations from target data to obtain a relation set; Compress the relationship set to obtain a compressed relationship set; Perform user relationship classification on the compressed relationship set to obtain user relationship categories; Build a user relationship knowledge graph based on user relationship categories; Generate dynamic images based on the user relationship knowledge graph and visualize the dynamic images.

[0008] Preferably, the target data is a plurality of sentences, and relationship extraction is performed on the target data to obtain a relationship set, including: Determine whether each sentence has at least two usernames. If so, mark the sentence as a sentence to be identified. Extracting features of the sentence to be recognized based on a dependency analysis method to obtain key feature words, wherein the key feature words are used to represent the relationship between at least two user names; A relationship set is constructed based on the user name and key feature words of each sentence to be recognized.

[0009] Preferably, the relationship set is compressed to obtain a compressed relationship set, including: In the relationship set, a first preset number of key feature words are selected as compression objects; Calculate the contribution score of the compressed object and determine whether the contribution score reaches the preset score. If so, retain the key feature words corresponding to the compressed object; if not, discard the key feature words corresponding to the compressed object; Reselecting a first preset number of key feature words from the remaining key feature words in the relationship set as compression objects until all key feature words in the relationship set are selected; All retained key feature words are extracted, and a compressed relationship set is constructed based on all retained key feature words.

[0010] Preferably, user relationship classification is performed on the compressed relationship set to obtain user relationship categories, including: Obtain several sample feature words, each of which has a relationship category label; Clustering several sample feature words based on clustering algorithm to obtain multiple category clusters; Selecting a second preset number of sample feature words from each category cluster as a sample set; For any key feature word in the compressed relation set, calculate the similarity between the key feature word and the sample set of each category cluster, sort the similarities from large to small, and obtain the similarity sequence of the key feature word; Extract the first m similarities from the similar sequence of the key feature word, and count the relationship category labels of the sample feature words corresponding to the first m similarities; where m is a positive integer; Based on the k-nearest neighbor algorithm, the category probability of the relationship category label between the key feature word and the sample feature words corresponding to the first m similarities is calculated; The final category of the key feature word is determined based on the category probability, and the final category of the key feature word is used as the user relationship category corresponding to the key feature word.

[0011] Preferably, building a user relationship knowledge graph based on user relationship categories includes: The user name is used as the node, and the user relationship category corresponding to the user name is used as the edge of the node; Build a user relationship knowledge graph based on nodes and edges between nodes.

[0012] Preferably, generating a dynamic image based on a user relationship knowledge graph includes: Constructing an image display area, selecting a third preset number of nodes and corresponding edges from the user relationship knowledge graph and adding them to the image display area; Render the nodes and corresponding edges added to the image display area to obtain a display image; Configure a display time limit for the displayed image. When the display time of the displayed image reaches the display time limit, update the nodes and corresponding edges in the image display area, and re-render the updated image display area to obtain a dynamic image.

[0013] Preferably, each node in the user relationship knowledge graph is deployed with an event listener, and the event listener is used to listen to the administrator's active selection of nodes to be displayed; the method further includes: Get the nodes that the administrator actively selects to be displayed; The nodes that the administrator actively selects to be displayed and the nodes and edges within a preset range adjacent to the nodes are added to the image display area, so as to perform rendering in the image display area and obtain the display image required by the user.

[0014] In a second aspect, the present invention provides a system for automatically generating an image, for implementing the above-mentioned method for automatically generating an image, the system comprising: The data acquisition module is used to obtain user interaction data of social software, pre-process the user interaction data, and obtain target data; The relationship extraction module is used to extract relationships from target data and obtain a relationship set; A relation compression module is used to compress the relation set to obtain a compressed relation set; A category determination module is used to classify the user relationships on the compressed relationship set to obtain user relationship categories; Graph construction module, used to build user relationship knowledge graph based on user relationship categories; The image generation module is used to generate dynamic images based on the user relationship knowledge graph and to visualize the dynamic images.

[0015] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for automatically generating an image when executing the computer program.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned method of automatically generating an image when executed by a processor.

[0017] Beneficial effects: 1. The present invention performs relationship extraction after preprocessing user interaction data. Since most user interaction data are short texts, there will be a large number of low-correlation relationship features in the relationship set. At this time, by compressing the relationship set, a large number of low-correlation relationships can be reduced, thereby improving the accuracy of relationship extraction between characters and facilitating the automatic generation of complex character relationship graphs. 2. After obtaining the user's highly correlated relationship set, the present invention can analyze the relationship set to obtain user relationship categories; then use the user relationship categories to construct a user relationship knowledge graph, and generate a dynamic image based on the user relationship knowledge graph. The generated dynamic image can dynamically display the user's character relationship in the social software, thereby improving the display effect of the character relationship in the social software and facilitating user viewing. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings: Figure 1 is a flow chart of a method for automatically generating an image provided by one embodiment of the present invention; Figure 2 It is a block diagram of a system for automatically generating images provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly introduced below in conjunction with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0020] Example 1 Figure 1This is a flow chart of a method for automatically generating an image provided by one embodiment of the present invention. Figure 1 As shown, this embodiment provides a method for automatically generating an image, the method comprising: Step S10: Obtain user interaction data of the social software, pre-process the user interaction data, and obtain target data; in this embodiment, the social software can be WeChat, QQ, Weibo, Bilibili, Douyin and other software, and the user interaction data can be text data such as friends circles and comments posted by users in the social software, or it can be video data. If it is video data, the video data needs to be converted into text data, mainly converting the audio part of the video.

[0021] In this embodiment, preprocessing mainly includes data cleaning and data formatting. Data cleaning is used to remove irrelevant information, such as advertisements, system messages, etc., and to process missing values and outliers. Data formatting mainly involves users converting audio data into text data, or converting other data into text data, and at the same time dividing the text data into sentences to obtain several sentences, which are used as target data.

[0022] Step S20: extracting relationships from the target data to obtain a relationship set.

[0023] As a further optimization of this embodiment, the target data is a plurality of sentences, and relationship extraction is performed on the target data to obtain a relationship set, including: Step S201: Determine whether each sentence contains at least two user names. If so, mark the sentence as a sentence to be identified. In this embodiment, when a sentence contains at least two user names, the two users in the sentence may have a relationship; therefore, the sentence is marked as a sentence to be identified.

[0024] Step S202: extracting features from the sentence to be recognized based on dependency analysis to obtain key feature words, where the key feature words are used to represent the relationship between at least two user names.

[0025] Dependency parsing is an important technique in natural language processing (NLP). It is used to analyze the dependencies between words in a sentence. The goal of dependency parsing is to construct a dependency syntax tree, in which words are nodes and the relationships between words are edges.

[0026] Dependency Relation: This refers to the type of relationship between words in a sentence. Examples include "subject-predicate relationship," "verb-object relationship," "attributive-predicate relationship," "adverbial-predicate relationship," and "parallel relationship."

[0027] In this embodiment, by performing word segmentation on the sentence to be recognized, dividing the sentence into separate words, and then performing radial dependency analysis, the key feature words of the sentence can be obtained; for example: Wang met his friend Li in the park, where "encountered" and "friend" are both feature keywords of "Li" and "Wang".

[0028] Step S203: construct a relationship set based on the user name and key feature words of each sentence to be recognized.

[0029] In this embodiment, through steps S201 to S203, all key feature words in the user interaction data can be extracted.

[0030] Step S30: compress the relationship set to obtain a compressed relationship set.

[0031] In this embodiment, among the extracted key feature words, some keywords have a relatively low contribution to the relationship between characters. For example, among the two key feature words "encounter" and "friend", the contribution of "encounter" to the relationship between "Li" and "Wang" is relatively low, while the contribution of "friend" to the relationship between "Li" and "Wang" is relatively high. Similarly, in the entire relationship set, there are also some key feature words whose contribution to the relationship between characters is not too high. Therefore, the relationship set needs to be compressed to reduce the amount of data in the relationship set.

[0032] Specifically, the relationship set is compressed to obtain a compressed relationship set including: Step S301: In a relationship set, a first preset number of key feature words are selected as compression objects.

[0033] Step S302: Calculate the contribution score of the compressed object and determine whether the contribution score reaches a preset score. If so, retain the key feature words corresponding to the compressed object; if not, discard the key feature words corresponding to the compressed object. In this embodiment, the calculation expression of the contribution score of the compressed object is as follows: ; Where, is the contribution score of the compressed object, is the relationship type corresponding to the compressed object, is the i-th key feature word in the compression object, I is the first preset number, is the probability of the relationship type appearing in the target data, is the probability that the i-th key feature word and relationship type appear simultaneously in the target data, is the probability that the relation type does not appear in the target data, is the probability that the i-th key feature word appears simultaneously in the target data, is the probability that the relationship type does not appear in the target data and the i-th key feature word appears in the target data.

[0034] In this embodiment, the average value of the sum of the contribution scores of all key feature words is used as the preset score, and the contribution score of each key feature word can be calculated using the above formula.

[0035] Step S303: reselecting a first preset number of key feature words from the remaining key feature words in the relationship set as compression objects, until all key feature words in the relationship set are selected.

[0036] Step S304: extract all the retained key feature words, and construct a compressed relationship set based on all the retained key feature words.

[0037] Therefore, through steps S301 to S304, key feature words with small contribution scores can be greatly reduced, which is beneficial to the subsequent classification of user relationships and improves the accuracy and efficiency of classification.

[0038] In this embodiment, since the contributions of different numbers of combinations of key feature words to the relationships between characters are also different, during the compression processing, the contribution of different numbers of combinations of key feature words to the relationships between characters can be judged by adjusting the selection value of the first preset number to ensure the rationality of the relationship set construction.

[0039] Step S40: performing user relationship classification on the compressed relationship set to obtain user relationship categories.

[0040] As a further optimization of this embodiment, user relationship classification is performed on the compressed relationship set to obtain user relationship categories, including: Step S401: Acquire several sample feature words, each of which has a relationship category label.

[0041] Step S402: clustering the sample feature words based on a clustering algorithm to obtain multiple category clusters; wherein the clustering algorithm adopts K-means clustering to cluster the sample feature words into k clusters, and the sample feature words in each cluster have the same category label.

[0042] Step S403: Select a second preset number of sample feature words from each category cluster as a sample set; in this embodiment, since the data volume of several sample feature words is relatively large, the amount of subsequent calculation is large; this embodiment selects a certain amount of representative sample feature words in each cluster as a sample set. These representative sample feature words have the same category label. While ensuring the classification accuracy, the amount of subsequent data calculation can be greatly reduced, thereby improving the efficiency of classification.

[0043] Step S404: For any key feature word in the compressed relationship set, calculate the similarity between the key feature word and the sample set of each category cluster, sort the similarities from large to small, and obtain a similarity sequence of the key feature word.

[0044] In this embodiment, before calculating the similarity between the key feature word and the sample set of each category cluster, it is necessary to calculate the similarity using a cosine similarity function.

[0045] Step S405: extracting the first m similarities from the similarity sequence of the key feature word, and counting the relationship category labels of the sample feature words corresponding to the first m similarities; wherein m is a positive integer.

[0046] Step S406: Based on the k-nearest neighbor algorithm, the category probability of the relationship category label between the key feature word and the sample feature words corresponding to the first m similarities is calculated.

[0047] Step S407: determining the final category of the key feature word based on the category probability, and using the final category of the key feature word as the user relationship category corresponding to the key feature word.

[0048] Step S50: Construct a user relationship knowledge graph based on user relationship categories.

[0049] As a further optimization of this embodiment, a user relationship knowledge graph is constructed based on user relationship categories, including: Step S501: using a user name as a node and the user relationship category corresponding to the user name as an edge of the node; Step S502: Construct a user relationship knowledge graph based on the nodes and the edges between the nodes.

[0050] Step S60: Generate a dynamic image based on the user relationship knowledge graph and visualize the dynamic image.

[0051] As a further optimization of this embodiment, generating a dynamic image based on the user relationship knowledge graph includes: Step S601: construct an image display area, select a third preset number of nodes and corresponding edges from the user relationship knowledge graph and add them to the image display area.

[0052] Step S602: Render the nodes and corresponding edges added to the image display area to obtain a display image.

[0053] Step S603: Configure a display time limit for the display image. When the display time of the display image reaches the display time limit, update the nodes and corresponding edges in the image display area, and re-render the updated image display area to obtain a dynamic image.

[0054] The present invention configures a display time limit for displayed images in an image display area, so that the rendered image can be displayed dynamically, and the complex character relationships in social software can be dynamically displayed, thereby improving the visual experience of the user relationship knowledge graph.

[0055] As a further optimization of this embodiment, each node in the user relationship knowledge graph is deployed with an event listener, and the event listener is used to listen to the administrator's active selection of nodes to be displayed; the method further includes: Step a10: Obtain the nodes that the administrator actively selects to be displayed.

[0056] Step a20: adding the node that the administrator actively selects to be displayed and the nodes and edges within a preset range adjacent to the node to the image display area, so as to perform rendering in the image display area and obtain the display image required by the user.

[0057] In this embodiment, when the administrator wants to specifically view the character relationships of a certain user, he or she can enter the requirements of the node corresponding to the user he or she wants to view. After obtaining the requirements, the node is searched, and after finding the node, the edges corresponding to the node and the adjacent nodes are displayed; thereby improving the ease of use of the user relationship knowledge graph.

[0058] In this embodiment, dynamic images can be displayed through a touch display, and the event listener can also listen to the administrator's touch sliding events, and change the image in the image display area through the touch sliding events; at this time, the administrator can slide the screen to view the character relationships of different users, further improving convenience.

[0059] The present invention performs relationship extraction after preprocessing the user interaction data. Since most of the user interaction data are short texts, there will be a large number of low-correlation relationship features in the relationship set. At this time, by compressing the relationship set, a large number of low-correlation relationships can be reduced, thereby improving the accuracy of relationship extraction between users and facilitating the automatic generation of complex character relationship graphs; secondly, after obtaining the user's high-correlation relationship set, the relationship set can be analyzed to obtain user relationship categories; then, the user relationship category is used to construct a user relationship knowledge graph, and a dynamic image is generated based on the user relationship knowledge graph. The generated dynamic image can dynamically display the user's character relationships in the social software, thereby improving the display effect of the character relationships in the social software and facilitating user viewing.

[0060] Example 2 Figure 2 FIG is a block diagram of a system for automatically generating images provided by one embodiment of the present invention. Figure 2As shown, this embodiment provides a system for automatically generating an image, which is used to implement the method for automatically generating an image in the first embodiment. The system includes: The data acquisition module is used to obtain user interaction data of social software, pre-process the user interaction data, and obtain target data; The relationship extraction module is used to extract relationships from target data and obtain a relationship set; A relation compression module is used to compress the relation set to obtain a compressed relation set; A category determination module is used to classify the user relationships on the compressed relationship set to obtain user relationship categories; Graph construction module, used to build user relationship knowledge graph based on user relationship categories; The image generation module is used to generate dynamic images based on the user relationship knowledge graph and to visualize the dynamic images.

[0061] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for automatically generating an image in the first embodiment is implemented.

[0062] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for automatically generating an image in the first embodiment is implemented.

[0063] The present invention performs relationship extraction after preprocessing the user interaction data. Since most of the user interaction data are short texts, there will be a large number of low-correlation relationship features in the relationship set. At this time, by compressing the relationship set, a large number of low-correlation relationships can be reduced, thereby improving the accuracy of relationship extraction between users and facilitating the automatic generation of complex character relationship graphs; secondly, after obtaining the user's high-correlation relationship set, the relationship set can be analyzed to obtain user relationship categories; then, the user relationship category is used to construct a user relationship knowledge graph, and a dynamic image is generated based on the user relationship knowledge graph. The generated dynamic image can dynamically display the user's character relationships in the social software, thereby improving the display effect of the character relationships in the social software and facilitating user viewing.

[0064] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0066] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for automatically generating an image, characterized in that: The method comprises: Obtain user interaction data from social software, pre-process the user interaction data, and obtain target data; Extract relations from target data to obtain a relation set; Compress the relationship set to obtain a compressed relationship set; Perform user relationship classification on the compressed relationship set to obtain user relationship categories; Build a user relationship knowledge graph based on user relationship categories; Generate dynamic images based on the user relationship knowledge graph and visualize the dynamic images.

2. The method for automatically generating an image according to claim 1, wherein: The target data is a plurality of sentences, and relationship extraction is performed on the target data to obtain a relationship set, including: Determine whether each sentence has at least two usernames. If so, mark the sentence as a sentence to be identified. Extracting features of the sentence to be recognized based on a dependency analysis method to obtain key feature words, wherein the key feature words are used to represent the relationship between at least two user names; A relationship set is constructed based on the user name and key feature words of each sentence to be recognized.

3. The method for automatically generating an image according to claim 2, wherein: Compress the relation set to obtain a compressed relation set, including: In the relationship set, a first preset number of key feature words are selected as compression objects; Calculate the contribution score of the compressed object and determine whether the contribution score reaches the preset score. If so, retain the key feature words corresponding to the compressed object; if not, discard the key feature words corresponding to the compressed object; Reselecting a first preset number of key feature words from the remaining key feature words in the relationship set as compression objects until all key feature words in the relationship set are selected; All retained key feature words are extracted, and a compressed relationship set is constructed based on all retained key feature words.

4. The method for automatically generating an image according to claim 3, wherein: Perform user relationship classification on the compressed relationship set to obtain user relationship categories, including: Obtain several sample feature words, each of which has a relationship category label; Clustering several sample feature words based on clustering algorithm to obtain multiple category clusters; Selecting a second preset number of sample feature words from each category cluster as a sample set; For any key feature word in the compressed relation set, calculate the similarity between the key feature word and the sample set of each category cluster, sort the similarities from large to small, and obtain the similarity sequence of the key feature word; Extract the first m similarities from the similar sequence of the key feature word, and count the relationship category labels of the sample feature words corresponding to the first m similarities; where m is a positive integer; Based on the k-nearest neighbor algorithm, the category probability of the relationship category label between the key feature word and the sample feature words corresponding to the first m similarities is calculated; The final category of the key feature word is determined based on the category probability, and the final category of the key feature word is used as the user relationship category corresponding to the key feature word.

5. The method for automatically generating an image according to any one of claims 2 to 4, characterized in that: Build a user relationship knowledge graph based on user relationship categories, including: The user name is used as the node, and the user relationship category corresponding to the user name is used as the edge of the node; Build a user relationship knowledge graph based on nodes and edges between nodes.

6. The method for automatically generating an image according to claim 5, wherein: Generate dynamic images based on user relationship knowledge graph, including: Constructing an image display area, selecting a third preset number of nodes and corresponding edges from the user relationship knowledge graph and adding them to the image display area; Render the nodes and corresponding edges added to the image display area to obtain a display image; Configure a display time limit for the displayed image. When the display time of the displayed image reaches the display time limit, update the nodes and corresponding edges in the image display area, and re-render the updated image display area to obtain a dynamic image.

7. The method for automatically generating an image according to claim 6, wherein: Each node in the user relationship knowledge graph is deployed with an event listener, and the event listener is used to listen to the administrator's active selection of nodes to be displayed; the method further includes: Get the nodes that the administrator actively selects to be displayed; The nodes that the administrator actively selects to be displayed and the nodes and edges within a preset range adjacent to the nodes are added to the image display area, so as to perform rendering in the image display area and obtain the display image required by the user.

8. A system for automatically generating images, used to implement the method for automatically generating images according to any one of claims 1 to 7, characterized in that: The system comprises: The data acquisition module is used to obtain user interaction data of social software, pre-process the user interaction data, and obtain target data; The relationship extraction module is used to extract relationships from target data and obtain a relationship set; A relation compression module is used to compress the relation set to obtain a compressed relation set; A category determination module is used to classify the user relationships on the compressed relationship set to obtain user relationship categories; Graph construction module, used to build user relationship knowledge graph based on user relationship categories; The image generation module is used to generate dynamic images based on the user relationship knowledge graph and to visualize the dynamic images.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for automatically generating an image according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for automatically generating an image according to any one of claims 1 to 7 is implemented.

Images