Powerpoint quality detection method and device, electronic equipment and storage medium

Abstract

The invention provides a presentation file quality detection method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence, in particular to the field of document quality detection. According to the specific implementation scheme, a to-be-detected presentation file is obtained; wherein the to-be-detected presentation file comprises a plurality of pages of slides; converting each page of slide in the to-be-detected PowerPoint into structured data in a preset format; wherein the structured data represents elements contained in the slide and the distribution condition of the elements; determining a quality score of the to-be-detected PowerPoint according to the structured data corresponding to each page of slide; wherein the quality score represents the quality of the to-be-detected presentation file. And in combination with the element layout condition of each page of slides, the quality detection precision of the PowerPoint is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of document quality detection in the field of artificial intelligence, and in particular, to a method, device, electronic device, and storage medium for detecting the quality of a presentation. Background Art

[0002] People often need to use PPT (PowerPoint, presentation) to record and view information in work and life. However, the quality of some PPTs is low, which will affect the user's viewing of information. Therefore, it is necessary to detect the quality of PPTs so as to modify or delete low-quality PPTs.

[0003] Currently, most of the PPT quality detection methods are manual evaluation methods, which waste manpower and time, and the efficiency and accuracy of quality detection are low. Summary of the Invention

[0004] The present disclosure provides a method, device, electronic device, and storage medium for detecting the quality of a presentation.

[0005] According to a first aspect of the present disclosure, there is provided a method for detecting the quality of a presentation, including:

[0006] Obtaining a presentation to be detected; wherein, the presentation to be detected includes multiple slides;

[0007] Converting each slide in the presentation to be detected into structured data in a preset format; wherein, the structured data represents the elements contained in the slide and the distribution between the elements;

[0008] Determining a quality score of the presentation to be detected according to the structured data corresponding to each slide; wherein, the quality score represents the quality level of the presentation to be detected.

[0009] According to a second aspect of the present disclosure, there is provided a device for detecting the quality of a presentation, including:

[0010] An obtaining unit, configured to obtain a presentation to be detected; wherein, the presentation to be detected includes multiple slides;

[0011] A conversion unit, configured to convert each slide in the presentation to be detected into structured data in a preset format; wherein, the structured data represents the elements contained in the slide and the distribution between the elements;

[0012] A detection unit, configured to determine a quality score of the presentation to be detected according to the structured data corresponding to each slide; wherein, the quality score represents the quality level of the presentation to be detected.

[0013] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor;

[0016] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method described in the first aspect of the present disclosure.

[0017] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described in the first aspect of the present disclosure.

[0018] According to a fifth aspect of the present disclosure, there is provided a computer program product including a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect of the present disclosure are implemented.

[0019] According to the technology of the present disclosure, the detection efficiency and accuracy of the PPT quality are improved.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0022] Figure 1 is a schematic flowchart of a method for detecting the quality of a presentation according to an embodiment of the present disclosure;

[0023] Figure 2 is a schematic flowchart of a method for detecting the quality of a presentation according to an embodiment of the present disclosure;

[0024] Figure 3 is a schematic diagram of the evaluation criteria for a presentation according to an embodiment of the present disclosure;

[0025] Figure 4 is a schematic flowchart of a method for detecting the quality of a presentation according to an embodiment of the present disclosure;

[0026] Figure 5 is a structural block diagram of a device for detecting the quality of a presentation according to an embodiment of the present disclosure;

[0027] Figure 6 It is a structural block diagram of a quality detection device for a presentation according to an embodiment of the present disclosure;

[0028] Figure 7 It is a block diagram of an electronic device for implementing the quality detection method of a presentation according to an embodiment of the present disclosure;

[0029] Figure 8 It is a block diagram of an electronic device for implementing the quality detection method of a presentation according to an embodiment of the present disclosure. Detailed implementation manners

[0030] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted below.

[0031] PPT is a type of formatted document that can carry multiple elements. For example, a PPT can contain elements such as text, pictures, and audio. With the in-depth development of artificial intelligence, PPT documents can be automatically generated according to user needs. However, the quality of automatically generated PPT documents varies, and the quality detection of PPTs still widely relies on manual evaluation, with low efficiency and accuracy of quality detection.

[0032] Currently, there are also automatic evaluation methods for PPTs. For example, an LLM (Large Language Model) can be used to score individual elements in a PPT, and then the evaluation results of individual elements are comprehensively evaluated to obtain the quality detection result of the entire PPT. However, PPT is a type of document with requirements for page space layout. Considering only the quality of individual elements is difficult to evaluate spatial layout problems, such as element overlap and overflow, which affects the accuracy of quality detection.

[0033] Each slide in a PPT can also be converted into a picture format, and the picture is used as input to score a single picture, and then the scores of each picture are combined for comprehensive evaluation. However, relying solely on pictures is difficult to evaluate low-quality problems such as content duplication between multiple pages and the visualization problem of elements. For example, if the text in a slide is blocked by an image in that slide, the text cannot be recognized from the picture converted from that slide, resulting in a visualization problem and affecting the accuracy of quality detection.

[0034] The present disclosure provides a method, an apparatus, an electronic device, and a storage medium for quality detection of presentation documents, which are applied to the field of document quality detection in the field of artificial intelligence to improve the detection efficiency and accuracy of PPT quality.

[0035] It should be noted that the data in this embodiment is not targeted at a specific user and does not reflect the personal information of a specific user. It should be noted that the data in this embodiment comes from a public dataset.

[0036] In the technical solution of the present disclosure, the processing of collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0037] To enable readers to more deeply understand the implementation principle of the present disclosure, the following Figures 1 - 8 is used to further refine the embodiments.

[0038] Figure 1 As shown in the flowchart of a method for quality detection of a presentation document provided according to an embodiment of the present disclosure, this method can be executed by a quality detection device for a presentation document. As Figure 1 shown, this method includes the following steps:

[0039] S101. Obtain a presentation document to be detected; wherein, the presentation document to be detected includes multiple slides.

[0040] Exemplarily, an online PPT can be captured as the presentation document to be detected, or a PPT can be manually uploaded as the presentation document to be detected. The presentation document to be detected includes multiple slides. If the obtained presentation document contains only one slide, then this presentation document can be determined as a low-quality PPT, that is, the quality of this presentation document is poor.

[0041] In this embodiment, the presentation document to be detected can be a PPT in an online database. The PPT in the database can be browsed or downloaded by users for their use. If the quality of the PPT in the database is poor, it will affect the user experience. Therefore, it is necessary to perform quality detection on the PPT in the database.

[0042] In this embodiment, obtaining the presentation document to be detected includes: obtaining a pre-stored presentation document dataset; wherein, the presentation document dataset includes multiple initial presentation documents; obtaining the browsing information of each initial presentation document in the presentation document dataset; wherein, the browsing information characterizes the usage situation of the presentation document; and determining the initial presentation document whose browsing information meets the preset selection conditions as the presentation document to be detected.

[0043] Specifically, a presentation dataset is pre-stored, and the presentation dataset includes multiple presentations. For example, a dataset containing a large number of presentations can be obtained from an online database. The presentations in the presentation dataset are used as the initial presentations. The presentations in the presentation dataset can be filtered to obtain the presentations to be tested. For example, multiple initial presentations can be randomly selected as the presentations to be tested.

[0044] The initial presentations in the presentation dataset are documents published online for users to view or download. Each initial presentation corresponds to its own viewing information, and the viewing information of each initial presentation in the presentation dataset is obtained. The viewing information can characterize the usage situation of the PPT document, and the viewing information can be updated in real time during the user's use of the PPT. For example, the viewing information can include the number of views, downloads, and aborted downloads of the PPT. The aborted download count refers to the number of times the PPT is interrupted by the user before the download is completed. For example, the quality of the PPT is poor, resulting in the user not wanting to continue the download.

[0045] Selection conditions are preset. The selection conditions refer to the conditions for selecting the presentations to be detected from the presentation dataset. For example, the preset selection conditions can be to select the initial presentations with the number of views less than the preset view count threshold, the number of downloads less than the preset download count threshold, or the number of aborted downloads greater than the preset aborted count threshold as the presentations to be detected. Another example is to sort the initial presentations according to the number of views of each initial presentation, and use the initial presentation with the least number of views as the presentation to be detected. In this embodiment, the preset selection conditions are not specifically limited.

[0046] In this embodiment, the presentations to be detected are likely to be low-quality presentations. Therefore, the initial presentations that may be low-quality can be selected from the presentation dataset as the presentations to be detected. For each initial presentation, it is determined whether the viewing information meets the preset selection conditions. If so, the initial presentation is determined to be a presentation to be detected; if not, the initial presentation is determined not to be a presentation to be detected.

[0047] The beneficial effect of this setting is that the presentation dataset is filtered and screened, so as to preferentially perform quality detection on the PPTs that may be of low quality, which is conducive to quickly finding low-quality PPTs, reducing the computational amount of quality detection, and improving the quality detection efficiency of PPTs.

[0048] S102. Convert each slide in the presentation to be detected into structured data in a preset format, where the structured data represents the elements contained in the slide and the distribution among the elements.

[0049] Exemplarily, a PPT contains various modal elements. For example, it may contain text, pictures, audio, video, etc. The PPT document containing multi-modal data can be converted into a structured format document to achieve the unification of data formats in the PPT. The format conversion can be performed using a preset PPT editing technology. In this embodiment, the preset PPT editing technology is not specifically limited.

[0050] A preset format can be set in advance. For example, the preset format can be XML format or JSON format. For each slide in the presentation to be detected, it can be converted into structured data in the preset format, and the structured data represents that slide. In the structured data, it can include the content, font, color, line spacing of the elements contained in the slide, as well as the distribution among the elements, etc.

[0051] The slide can include text and pictures. The structured data needs to represent all the content in the slide and information such as the size and boundary of the slide. For example, there is "allergen" in the slide. For the text "allergen", the corresponding structured data can contain information such as the font, color, opacity, font size, line spacing, line height of "allergen".

[0052] S103. Determine the quality score of the presentation to be detected according to the structured data corresponding to each slide, where the quality score represents the quality level of the presentation to be detected.

[0053] Exemplarily, each slide corresponds to its own structured data. By combining the structured data corresponding to each slide, the quality of the presentation to be detected is evaluated to obtain the quality score of the presentation to be detected. The quality score can represent the quality level of the presentation to be detected. The better the quality, the higher the quality score.

[0054] The rule for determining the quality score can be set in advance. For example, the richness of the elements in the slide can be used as the basis for the quality score. That is, in the presentation to be detected, the more types of elements contained in the slide, the higher the quality score. The types of elements contained in each slide can be determined according to the structured data. If there is a slide that contains only one type of element, it is determined that the quality score of the presentation to be detected is relatively low. Also, for example, according to the structured data, it can be determined whether the text formats in each slide are consistent. If so, the quality score is relatively high; if not, the quality score is relatively low.

[0055] It is also possible to first score each slide based on the structured data of that slide. For example, according to the structured data, it can be determined whether the layout of various elements in the slide is reasonable, so as to obtain the score of that slide. Then, combining the scores of each slide, the quality score of the presentation to be detected is obtained.

[0056] A threshold for the quality score can be set in advance. If the quality score of the presentation to be detected is less than or equal to the threshold, the presentation to be detected is considered a low-quality PPT; if the quality score of the presentation to be detected is greater than the threshold, the presentation to be detected is considered a high-quality PPT. For low-quality PPTs, they can be modified or eliminated, thereby improving the user experience of using PPTs.

[0057] In the embodiments of the present disclosure, by obtaining the presentation to be detected, performing format conversion on the presentation to be detected, and obtaining the structured data corresponding to each slide in the presentation to be detected, all the information contained in each slide is obtained. This avoids the problem of information omission in the slide when converting the slide into a picture, and improves the accuracy of the quality detection of PPTs. Combining the structured data of each slide, comprehensively evaluating the element content and layout of the presentation to be detected saves manpower and time, reduces subjective influence, and further improves the accuracy and efficiency of quality detection.

[0058] Figure 2 It is a schematic flowchart of a method for detecting the quality of a presentation provided by the embodiments of the present disclosure.

[0059] In this embodiment, determining the quality score of the presentation to be detected according to the structured data corresponding to each slide includes: for each slide, determining a first score and a second score of the slide according to the structured data corresponding to the slide; where the first score represents the rationality of the layout of elements in the slide, and the second score represents the rationality of the content of elements in the slide; according to the first score and the second score of each slide, determining the quality score of the presentation to be detected.

[0060] This embodiment is based on the above embodiment, as Figure 2 shown, the method includes the following steps:

[0061] S201. Obtain the presentation to be detected; where the presentation to be detected includes multiple slides.

[0062] Exemplarily, this step can refer to the above step S101 and will not be elaborated.

[0063] S202. Convert each slide in the presentation to be detected into structured data in a preset format, where the structured data represents the elements contained in the slide and the distribution between the elements.

[0064] Exemplarily, this step can refer to step S102 above and will not be elaborated here.

[0065] S203. For each slide, determine a first score and a second score of the slide according to the structured data corresponding to the slide, where the first score represents the rationality of the layout of the elements in the slide, and the second score represents the rationality of the content of the elements in the slide.

[0066] Exemplarily, each slide corresponds to its own structured data. For each slide in the presentation to be detected, determine the structured data of that slide. According to the structured data corresponding to that slide, determine the first score of that slide, and according to the structured data corresponding to that slide, determine the second score of that slide. The first score can represent the rationality of the layout of the elements in the slide. For example, it can represent whether the elements in the slide overlap or exceed the page boundary, etc. The second score can represent the rationality of the content of the elements in the slide. For example, it can represent whether the content of the elements in the slide conforms to the theme of the presentation to be detected, and whether the meanings expressed by the content of various types of elements in the slide are consistent, etc.

[0067] The structured data can represent the association relationship between different elements on the same slide. The association relationship can include the attributes of different elements and the layout between different elements, etc. According to the association relationship between different elements, the first score can be obtained, that is, the first score is a page - dimension score of the entire page by combining multiple elements on the same page. The structured data can also represent the element information of any one element in the slide. The element information can include the content and position of the element, etc. According to the element information of each single element, the second score can be obtained, that is, the second score is an element - dimension score.

[0068] In this embodiment, the structured data includes the attribute information and element category of the elements in the slide. The attribute information represents the presentation format of the element in the slide. Determining the first score of the slide according to the structured data corresponding to the slide includes: determining the attribute information of the elements belonging to the same element category in the slide according to the structured data corresponding to the slide; and determining the first score of the slide according to the attribute information of the elements belonging to the same element category in the slide.

[0069] Specifically, the structured data may include the attribute information and element categories of the elements in the slide. The attribute information can characterize the presentation format of the elements in the slide. For example, it may include attributes such as font, font size, color, line spacing, etc. The element category characterizes the type of the element. For example, it may include text category, picture category, audio category, video category, etc. The elements can also be classified into more fine-grained categories. For example, the text category can further be divided into title category, body text category, annotation category, etc.

[0070] For each slide, determine the element categories contained in the slide from the structured data of the slide, and obtain the attribute information of each element. For each element category contained in the slide, determine the attribute information of all the elements belonging to the element category in the slide. Determine the attribute information of the elements belonging to the same element category as the same-category attribute information. Determine the first score of the slide according to the same-category attribute information corresponding to various element categories in the slide. For example, for each element category in the slide, determine whether there are differences in the same-category attribute information of the element category, that is, whether the attributes of the elements of the same category are the same. If for any element category, the attributes of all the elements are consistent, it can be determined that the score of the first score is relatively high; if there is an element category where the attributes of the elements are different, it can be determined that the score of the first score is relatively low.

[0071] For example, if there are two paragraphs of text and two pictures in a slide, and if the formats such as font and font size of these two paragraphs of text are exactly the same, and the formats such as size and resolution of the two pictures are also exactly the same, it can be determined that the first score is 1 point; if the formats such as size and resolution of the two pictures are exactly the same, but the two paragraphs of text use two different fonts respectively, it can be determined that the second score is -1 point.

[0072] The beneficial effect of such a setting is to determine the elements of the same type in each slide and determine whether the attributes of the same-type elements are consistent. For example, determine whether the color matching, alignment, spacing, and font size are consistent, so as to score the slide at the page level and improve the scoring accuracy.

[0073] In this embodiment, determining the first score of the slide according to the attribute information of the elements belonging to the same element category in the slide includes: if the attribute information of the elements belonging to the same element category in the slide is consistent, determining that the first score of the slide is a preset first score value; if the attribute information of the elements belonging to the same element category in the slide is inconsistent, determining that the first score of the slide is a preset second score value.

[0074] Specifically, obtain the attribute information of elements belonging to the same element category from the structured data. For various element categories, determine whether the attribute information of different elements belonging to the same element category is consistent. For example, determine whether the line spacing and font size are the same among different texts belonging to the text category; determine whether the color matching is the same among different pictures belonging to the picture category, etc.

[0075] A first score and a second score are preset. The first score can be 1 point, and the second score can be -1 point. If, for all element categories, the attribute information among different elements belonging to the same element category is consistent, then determine that the first score of the slide is the preset first score, that is, count 1 point; if there exists any element category where the attribute information among different elements in this element category is inconsistent, then determine that the first score of the slide is the preset second score, that is, count -1 point.

[0076] The beneficial effect of such a setting is that by comparing the attribute information, the layout professionalism of similar elements on the page can be evaluated, the comprehensiveness of quality inspection can be improved, and thus the detection accuracy can be improved.

[0077] In this embodiment, the first score can also characterize the richness of elements in the slide. The number of element categories contained in the slide can be obtained from the structured data. If the slide contains multiple element categories, then determine that the first score is the first score, indicating that the element types in the slide are rich; if it is determined that the slide contains only one element category, then determine that the first score is the second score, indicating that the element types in the slide are few.

[0078] In this embodiment, the structured data includes the position information of the elements in the slide; determining the first score of the slide according to the structured data corresponding to the slide includes: determining the area information of the overlapping area in the slide according to the position information of each element in the slide; where the overlapping area represents the area in the slide where elements overlap; determining the first score of the slide according to the area information of the overlapping area.

[0079] Specifically, the structured data includes the position information of each element in the slide on the page, and the position information can be in the form of coordinates. Obtain the position information of each element from the structured data, and according to the position information of each element, determine whether there are multiple elements at the same position, that is, determine whether there is an area where elements overlap in the slide. Determine the area information of the overlapping area, that is, determine the size of the overlapping area. For example, if there is an overlap between a picture and text in the slide and the picture completely covers the text, then the area where the text is located can be determined as the overlapping area between the picture and the text.

[0080] Determine the first score of the slide based on the area information of the overlapping region. For example, the larger the area of the overlapping region, the smaller the first score. Another example is that as long as there is an overlapping region in the slide, the first score is determined to be a preset second score value, that is, -1 point. If there is no overlapping region in the slide, the first score is determined to be a preset first score value, that is, 1 point.

[0081] The beneficial effect of such a setting is to determine whether there are multiple elements at the same position in the slide, that is, to determine whether there is an overlap of elements, so as to evaluate the layout coordination of the slide and improve the comprehensiveness and accuracy of quality inspection.

[0082] In this embodiment, the structured data includes the content information of the elements in the slide; determining the second score of the slide according to the structured data corresponding to the slide includes: performing semantic recognition processing on the content information in the structured data to obtain the semantic information of the content information; where the semantic information represents the logical clarity degree of the content information; determining the second score of the slide according to the semantic information of the content information.

[0083] Specifically, the structured data may include the specific content information of the elements in the slide. According to the content information of each element, the slide can be evaluated in terms of elements to obtain the second score of the slide.

[0084] If there is a text element in the slide, obtain the specific text content from the structured data; if there is a picture element in the slide, the picture can be converted into a text-based explanatory note. In this embodiment, the process of converting the picture to text is not specifically limited. If the picture contains text, the text in the picture can also be extracted to obtain the text content. If there is an audio-video element in the picture, the voice of the audio-video can be converted into text content. In this embodiment, the process of converting the voice to text is not specifically limited. That is to say, the content information in this embodiment can refer to the text content.

[0085] Perform semantic recognition processing on the content information. For example, an LLM model, that is, a large model, can be pre-constructed, and the prompt (prompt word) of the large model can be pre-designed. The content information is input into the large model, and the large model performs semantic recognition processing on the content information based on the preset prompt to obtain the semantic information of the content information. In this embodiment, the model structure of the large model is not specifically limited.

[0086] Semantic information can characterize the logical clarity of content information. For example, it can characterize whether the content information is redundant, concise and easy to read, or logically complete. According to the semantic information of the content information, the second score of the slide is determined. For example, if the semantic information characterizes the content information as redundant, complicated, and untrue, the second score is determined to be -1 point; if the semantic information characterizes the content information as concise, easy to read, and logically complete, the second score is determined to be 0 points; if the semantic information characterizes the content information as having a clear structure and inspiring viewpoints, the second score is determined to be 1 point.

[0087] The prompt words of the large model can be:

[0088]

Evaluation Criteria

[0089] Evaluation criteria for content professionalism:

[0090] -1 point: There are authenticity and timeliness issues in the content, the content is redundant and complicated, and the content is not relevant to the theme

[0091] 0 point: The content is concise, easy to read, logically complete, and the content is relevant to the theme

[0092] 1 point: The content has a clear structure, professional details, or inspiring viewpoints

[0093] Please score according to the input content.

[0094] The beneficial effect of such a setting is to evaluate the professionalism of the content in the slide, realize quality inspection from the dimension of element content, and improve the comprehensiveness and accuracy of quality inspection.

[0095] In this embodiment, the structured data includes the position information of the elements in the slide; according to the structured data corresponding to the slide, determining the second score of the slide includes: if the position information of each element in the slide is within the preset position range, determining the second score of the slide as the preset first score value; if there is position information of an element in the slide that is not within the preset position range, determining the second score of the slide as the preset second score value.

[0096] Specifically, for each element in the slide, obtain the position information of each element from the structured data. A position range is preset, and the elements in the slide should not exceed the preset position range. For example, the preset position range is the page range of the visualization interface. Determine whether the position information of the elements in the slide is within the preset position range. If all elements are within the preset position range, determine the second score of the slide as the preset first score value, that is, count 1 point; if there is one or more elements not within the preset position range, determine the second score of the slide as the preset second score value, that is, count -1 point.

[0097] The beneficial effect of such a setting is that the position coordinates of each element are determined. If an element exceeds the page, the slide of this page is considered a low-quality page and is scored -1 point. This realizes the evaluation of the layout professionalism of each slide from the dimension of elements, improving the accuracy of quality detection.

[0098] S204. Determine the quality score of the presentation to be detected according to the first score and the second score of each slide.

[0099] Exemplarily, combine the first scores and the second scores of all slides to determine the quality score of the entire presentation to be detected. For example, the first score and the second score can be added, or the average value can be calculated as the final quality score. Another example, if both the first score and the second score are 1 point, the final quality score is 1 point; if there is a -1 point in the first score or the second score, the final quality score is -1 point.

[0100] Figure 3 It is a schematic diagram of the evaluation criteria for the presentation. The quality of the PPT can be evaluated from two aspects, including layout typesetting and content elements. Layout typesetting can refer to the evaluation of the coordination relationship, layout professionalism, and layout diversity among the elements on the page. The coordination relationship among the elements refers to whether the filling of the elements in the slide is reasonable and whether there is occlusion and overlap; the layout professionalism refers to whether the elements in the slide are aligned, whether the attributes such as spacing are unified, and whether the color matching is unified, etc.; the layout diversity refers to whether there are various types of elements in the slide. Content elements can refer to the evaluation of the relevance, structure, professionalism, richness, etc. of the element content. Content relevance refers to whether the semantics between the contents of different elements are relevant and whether the element content is relevant to the theme, etc.; content structuring refers to whether there is a certain structure in the layout of the elements on the page and whether it is chaotic, etc.; content professionalism refers to whether the content of the text elements is authentic, timely, logically clear, concise, etc., and whether the multimedia elements are clear, etc.; content richness refers to whether the description of the element content on the page is single.

[0101] In this embodiment, by comprehensively considering the first score and the second score, a comprehensive score of the entire presentation to be detected is realized in the page dimension and the element dimension, improving the accuracy of the quality detection of the PPT.

[0102] In the embodiments of the present disclosure, by obtaining a presentation to be detected, performing format conversion on the presentation to be detected, and obtaining structured data corresponding to each slide in the presentation to be detected, all information contained in each slide can be obtained. This avoids the problem of information omission in the slide when converting the slide into a picture, and improves the accuracy of the quality detection of the PPT. Combining the structured data of each slide, comprehensively evaluating the element content and layout of the presentation to be detected saves manpower and time, reduces subjective influence, and further improves the accuracy and efficiency of the quality detection.

[0103] Figure 4 It is a schematic flowchart of a method for detecting the quality of a presentation provided by an embodiment of the present disclosure.

[0104] In this embodiment, the structured data includes the element categories of the elements in the slide, and the element categories include the title category; determining the quality score of the presentation to be detected according to the first score and the second score of each slide includes: determining the number of elements with the element category of the title category in the slide as the title number; if the title number is greater than a preset number threshold, determining the slide as the first target page; determining the structured score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of the first target pages; wherein, the structured score represents the layout richness of the presentation to be detected; determining the quality score of the presentation to be detected according to the structured score of the presentation to be detected, and the first score and the second score of each slide.

[0105] This embodiment is based on the above embodiment, as Figure 4 shown, the method includes the following steps:

[0106] S401. Obtain the presentation to be detected; wherein, the presentation to be detected includes multiple slides.

[0107] S402. Convert each slide in the presentation to be detected into structured data in a preset format; wherein, the structured data represents the elements contained in the slide and the distribution between the elements.

[0108] S403. For each slide, determine the first score and the second score of the slide according to the structured data corresponding to the slide; wherein, the first score represents the rationality of the layout of the elements in the slide, and the second score represents the rationality of the content of the elements in the slide.

[0109] S404. Determine the number of elements with the element category of the title category in the slide as the title number.

[0110] Exemplarily, for each slide, determine the structured data of the slide. The structured data characterizes the element categories of the elements contained in the slide. The element categories may include a title category and a body text category. The elements of the title category are usually laid out above the elements of the body text category, and the attribute information of the elements of the title category may be different from the attribute information of the elements of the body text category. For example, the elements of the title category usually need to be bolded.

[0111] In the structured data, each element is labeled with its own element category. Based on the structured data, the elements of the title category can be determined. Determine the number of elements of the title category as the number of titles. The slide may include titles of different levels. For example, it may include a main title and sub-titles under the main title. Titles of various levels can belong to the title category.

[0112] For example, there may be three titles in a slide. Among them, there is a main title "1.1, AAAA" and two sub-titles "1.11, BBBB" and "1.12, CCCC".

[0113] S405. If the number of titles is greater than a preset number threshold, determine the slide as the first target page.

[0114] Exemplarily, a number threshold is preset. This number threshold is the minimum number of titles in the slides of a high-quality PPT. For example, the preset number threshold is 1. Compare the number of titles corresponding to the slide with the preset number threshold. If the number of titles is greater than the preset number threshold, it indicates that the slide is of relatively high quality, the layout of this page of the slide is a structured layout, and determine this page of the slide as the first target page; if the number of titles is less than or equal to the preset number threshold, it indicates that the slide is of relatively low quality.

[0115] S406. Determine the structured score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of the first target pages; wherein, the structured score characterizes the layout richness of the presentation to be detected.

[0116] Exemplarily, determine the number of the first target pages in the presentation to be detected as the first quantity, and determine the total number of slides in the presentation to be detected. Determine the structured score of the presentation to be detected according to the first quantity and the total number of pages. The structured score can characterize the layout richness of the presentation to be detected. The larger the first quantity or the larger the proportion of the first quantity in the total number of pages, it indicates that most pages in the presentation to be detected are refined with multiple titles, the layout of the slide is more structured, and the higher the structured score.

[0117] In this embodiment, determining the structured score of the presentation to be detected based on the total number of pages in the presentation to be detected and the number of first target pages includes: determining the structured layout rate of the presentation to be detected based on the total number of pages in the presentation to be detected and the number of first target pages; wherein, the structured layout rate represents the ratio between the total number of pages in the presentation to be detected and the number of first target pages; if the structured layout rate is equal to or greater than a preset first ratio threshold, determining that the structured score is a preset first score; if the structured layout rate is less than the preset first ratio threshold, determining that the structured score is a preset second score.

[0118] Specifically, divide the first quantity by the total number of pages in the presentation to be detected, and the calculation result is the structured layout rate. That is, the structured layout rate can represent the proportion of slides with structures in the presentation to be detected in the entire presentation.

[0119] A first ratio threshold is preset, and the structured layout rate is compared with the preset first ratio threshold. If the structured layout rate is equal to or greater than the preset first ratio threshold, determining that the structured score is a preset first score, counting 1 point; if the structured layout rate is less than the preset first ratio threshold, determining that the structured score is a preset second score, counting -1 point.

[0120] The beneficial effect of such a setting is to calculate the structured layout rate of the entire PPT document, realize cross-page evaluation of the PPT, and improve the accuracy of PPT quality detection.

[0121] S407. Determine the quality score of the presentation to be detected according to the structured score of the presentation to be detected, and the first score and the second score of each page of the slide.

[0122] Exemplarily, combining the structured score of the entire presentation, and the first score and the second score of each page of the slide, realizes quality detection of the presentation to be detected from three aspects: cross-page dimension, single-page dimension, and element dimension, improving the comprehensiveness and accuracy of quality detection.

[0123] The three scores can be added or averaged to obtain the quality score. It can also be determined whether there is a -1 point among the three scores. If there is a -1 point, determining that the quality score is -1 point; if all three scores are 1 point, the quality score is 1 point; if there is no -1 point among the three scores but includes 0 points, the quality score is 0 point.

[0124] In this embodiment, determining the quality score of the presentation to be detected according to the first score and the second score of each slide includes: if it is determined that there are elements of a preset category in the structured data corresponding to the slide, then the slide is determined as the second target page; wherein, the preset category is at least one of the element categories; determining the page element score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of second target pages; wherein, the page element score represents the content richness in the presentation to be detected; determining the quality score of the presentation to be detected according to the page element score of the presentation to be detected, and the first score and the second score of each slide.

[0125] Specifically, one or more element categories are preset as the preset category. For example, the preset category may include the illustration category and the chart category, etc. According to the structured data corresponding to the slide, it is determined whether there are elements of the preset category in the slide. If so, it is determined that the slide contains professional content such as illustrations and charts, and the slide is of high quality, and the slide is determined as the second target page; if there are no elements of the preset category in the slide, it is considered that the slide is of low quality.

[0126] Determine the number of second target pages in the presentation to be detected as the second quantity. Determine the page element score of the presentation to be detected according to the total number of pages in the presentation to be detected and the second quantity. The page element score represents the content richness in the presentation to be detected. If the page contains elements of the preset category, the page is relatively rich. The larger the second quantity, or the larger the proportion of the second quantity in the total number of pages, the higher the page element score.

[0127] Combining the page element score of the entire presentation, and the first score and the second score of each slide, quality detection of the presentation to be detected is carried out from three aspects: the cross-page dimension, the single-page dimension, and the element dimension, improving the comprehensiveness and accuracy of quality detection.

[0128] The three scores can be added or averaged to obtain the quality score. It can also be determined whether there is a score of -1 among the three scores. If there is a score of -1, then the quality score is determined to be -1; if all three scores are 1, then the quality score is 1; if there is no score of -1 among the three scores, but includes a score of 0, then the quality score is 0. In this embodiment, the structured score and the page element score of the entire presentation can also be combined, and the first score and the second score of each slide, to perform multi-dimensional quality detection on the presentation to be detected, and obtain the quality score of the entire presentation.

[0129] The beneficial effect of such a setting is that, by integrating different dimensions, the presentation to be detected is comprehensively detected to judge the content richness of the presentation to be detected, thereby improving the detection accuracy of the PPT quality.

[0130] In this embodiment, according to the total number of pages in the presentation to be detected and the number of second target pages, the page element score of the presentation to be detected is determined, including: according to the total number of pages in the presentation to be detected and the number of second target pages, the element proportion ratio of the presentation to be detected is determined; wherein, the element proportion ratio represents the ratio between the total number of pages in the presentation to be detected and the number of second target pages; if the element proportion ratio is equal to or greater than a preset second ratio threshold, it is determined that the page element score is a preset first score; if the element proportion ratio is less than the preset second ratio threshold, it is determined that the page element score is a preset second score.

[0131] Specifically, divide the second quantity by the total number of pages in the presentation to be detected, and the calculation result is the element proportion ratio. That is, the element proportion ratio can represent the proportion of the slides with professional content in the presentation to be detected in the whole presentation.

[0132] A second ratio threshold is preset, and the element proportion ratio is compared with the preset second ratio threshold. If the element proportion ratio is equal to or greater than the preset second ratio threshold, it is determined that the page element score is a preset first score, counting 1 point; if the element proportion ratio is less than the preset second ratio threshold, it is determined that the page element score is a preset second score, counting -1 point.

[0133] The beneficial effect of such a setting is that the element proportion ratio of the entire PPT document is calculated to achieve cross-page evaluation of the PPT and improve the detection accuracy of the PPT quality.

[0134] In this embodiment, the structured data includes the position information and element category of the elements in the slide; according to the first score and the second score of each page of the slide, the quality score of the presentation to be detected is determined, including: for each page of the slide, according to the position information and element category of each element in the slide, the layout template of the slide is determined; wherein, the layout template represents the layout of the elements of different element categories in the slide; if there are at least two pages of slides with the same layout template, then at least two pages of slides are determined as the third target pages; according to the total number of pages in the presentation to be detected and the number of third target pages, the layout repetition score of the presentation to be detected is determined; wherein, the layout repetition score represents the layout repetition degree of different pages in the presentation to be detected; according to the layout repetition score of the presentation to be detected, and the first score and the second score of each page of the slide, the quality score of the presentation to be detected is determined.

[0135] Specifically, for each slide, obtain the position information and element categories of each element from the structured data. According to the position information and element categories of the elements in the slide, determine the layout template of the slide. The layout template characterizes the layout of elements of different element categories in the slide. For example, in the layout template, text elements are in the upper half of the page, and picture elements are in the lower half of the page. The layout templates of different slides may be the same or different.

[0136] Pair up the slides in the presentation to be detected and compare the layout templates of every two slides. If there are at least two slides with the same layout template, then determine these at least two slides as the third target pages. For example, if there are two slides with the layout template where the upper half of the page is text and the lower half is a picture, then these two slides are the third target pages. If in the presentation to be detected, the layout template of each page is different, then there are no third target pages.

[0137] Determine the number of the third target pages in the presentation to be detected as the third quantity. According to the total number of pages and the third quantity in the presentation to be detected, determine the layout repetition score of the presentation to be detected. The layout repetition score characterizes the degree of layout repetition of different pages in the presentation to be detected. The more pages with the same layout, the lower the layout repetition score. For example, the more the third quantity, or the greater the proportion of the third quantity to the total number of pages, the lower the layout repetition score.

[0138] Combining the layout repetition score of the entire presentation, as well as the first score and the second score of each slide, realizes quality detection of the presentation to be detected from three aspects: the cross-page dimension, the single-page dimension, and the element dimension, improving the comprehensiveness and accuracy of quality detection.

[0139] The three scores can be added or averaged to obtain the quality score. It can also be determined whether there is a score of -1 among the three scores. If there is a score of -1, then determine the quality score as -1; if all three scores are 1, then the quality score is 1; if there is no score of -1 among the three scores but includes a score of 0, then the quality score is 0. In this embodiment, it is also possible to combine the structured score, the page element score, the layout repetition score of the entire presentation, as well as the first score and the second score of each slide, to realize multi-dimensional quality detection of the presentation to be detected from the cross-page dimension, the single-page dimension, and the element dimension, and obtain the quality score of the entire presentation.

[0140] The beneficial effect of such a setting is to comprehensively detect the presentation to be detected from different dimensions, judge the content richness of the presentation to be detected, and improve the detection accuracy of the PPT quality.

[0141] In this embodiment, determining the layout repetition score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages includes: determining the repetition ratio of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages; wherein, the repetition ratio represents the ratio between the total number of pages in the presentation to be detected and the number of third target pages; if the repetition ratio is less than a preset third ratio threshold, determining that the layout repetition score is a preset first score; if the repetition ratio is equal to or greater than the preset third ratio threshold, determining that the layout repetition score is a preset second score.

[0142] Specifically, dividing the third quantity by the total number of pages in the presentation to be detected, and the calculation result is the repetition ratio. That is, the repetition ratio can represent the proportion of the slides with repeated layouts in the presentation to be detected in the entire presentation.

[0143] There is a preset third ratio threshold in advance, and the repetition ratio is compared with the preset third ratio threshold. If the repetition ratio is less than the preset third ratio threshold, determining that the layout repetition score is a preset first score, counting 1 point; if the repetition ratio is equal to or greater than the preset third ratio threshold, determining that the page element score is a preset second score, counting -1 point.

[0144] The beneficial effect of such a setting is to calculate the ratio of the repeated layouts in the entire PPT document, realize the cross-page evaluation of the PPT, and improve the accuracy of the PPT quality detection.

[0145] In this embodiment, the structured data includes the content information and element categories of the elements in the slide, and the element categories include text categories; determining the quality score of the presentation to be detected according to the first scores and second scores of each page of the slide includes: for each page of the slide, obtaining the content information of the elements belonging to the text category from the structured data of the slide as the text content; determining the similarity between the text contents of every two pages of the slide; wherein, the similarity represents the semantic similarity degree of the text content; according to all the determined similarities, determining the text professionalism score of the presentation to be detected; wherein, the text professionalism score represents the professionalism degree of the text content in the presentation to be detected; according to the text professionalism score of the presentation to be detected, as well as the first scores and second scores of each page of the slide, determining the quality score of the presentation to be detected.

[0146] Specifically, for the text category elements in the slides, obtain the content information of the text category elements from the structured data of the slides, that is, obtain the text content. If there is text content on multiple slides in the presentation to be detected, the similarity of the text content on these pages can be calculated. Determine the similarity between the text content of every two slides. The similarity can represent the degree of semantic similarity. For example, it can be calculated by cosine similarity. The edit distance between the text content of every two pages can also be calculated. The greater the edit distance, the lower the similarity. The edit distance represents how many times the text needs to be edited to become another text. In this embodiment, the calculation methods of similarity and edit distance are not specifically limited.

[0147] Every two slides can correspond to a similarity. For the entire presentation to be detected, multiple similarities can be calculated. According to all the calculated similarities, determine the text professional score of the presentation to be detected. For example, the average value of the similarities can be calculated, and based on the average value, determine the text professional score. The text professional score can represent the professional degree of the text content in the presentation to be detected. The higher the similarity, the lower the professional degree, and the lower the text professional score.

[0148] Combined with the text professional score of the entire presentation, as well as the first score and the second score of each slide, implement quality detection of the presentation to be detected from three aspects: cross-page dimension, single-page dimension, and element dimension, improving the comprehensiveness and accuracy of quality detection.

[0149] The three scores can be added or averaged to obtain the quality score. It can also be determined whether there is a score of -1 among the three scores. If there is a score of -1, then determine that the quality score is -1; if all three scores are 1, then the quality score is 1; if there is no score of -1 among the three scores but includes a score of 0, then the quality score is 0. In this embodiment, the structured score, page element score, layout repetition score, text professional score of the entire presentation, as well as the first score and the second score of each slide can also be combined to implement multi-dimensional quality detection of the presentation to be detected from the cross-page dimension, single-page dimension, and element dimension, and obtain the quality score of the entire presentation. For example, among the structured score, page element score, layout repetition score, text professional score, as well as the first score and the second score of each slide, if there is a preset number of scores of -1, then the quality score is -1; if there is a preset number of scores of 1, then the quality score is 1; in other cases, it is 0.

[0150] The beneficial effect of such a setting is that by comprehensively considering different dimensions, automatically conduct a comprehensive detection of the presentation to be detected, judge the content richness of the presentation to be detected, and improve the detection accuracy of the PPT quality.

[0151] In this embodiment, according to all the determined similarities, the text professionalism score of the presentation to be detected is determined, including: if all the determined similarities are less than the preset similarity threshold, it is determined that the text professionalism score is the preset first score; if there is a similarity equal to or greater than the preset similarity threshold, it is determined that the text professionalism score is the preset second score.

[0152] Specifically, a similarity threshold is preset, and each similarity is compared with the preset similarity threshold respectively. If all similarities are less than the preset similarity threshold, it is determined that the text professionalism score is the preset first score, which is counted as 1 point; if there is one or more similarities equal to or greater than the preset similarity threshold, it is determined that the text professionalism score is the preset second score, which is counted as -1 point.

[0153] The beneficial effect of such a setting is to calculate the similarity of the text content of the entire PPT document, realize the cross-page evaluation of the PPT, and improve the accuracy of the PPT quality detection.

[0154] In the embodiment of the present disclosure, by obtaining the presentation to be detected, performing format conversion on the presentation to be detected, and obtaining the structured data corresponding to each page of the slide in the presentation to be detected, all the information contained in each page of the slide can be obtained. This avoids the problem of information omission in the slide when the slide is converted into a picture, and improves the accuracy of the PPT quality detection. Combining the structured data of each page of the slide, comprehensively evaluating the element content and layout of the presentation to be detected saves manpower and time, reduces subjective influence, and further improves the accuracy and efficiency of the quality detection.

[0155] Figure 5 It is a structural block diagram of a presentation quality detection device provided by the embodiment of the present disclosure. For the sake of illustration, only the parts related to the embodiment of the present disclosure are shown. Referring to Figure 5 , the presentation quality detection device 500 includes: an acquisition unit 501, a conversion unit 502, and a detection unit 503.

[0156] The acquisition unit 501 is used to acquire the presentation to be detected; wherein, the presentation to be detected includes multiple pages of slides;

[0157] The conversion unit 502 is used to convert each page of the slide in the presentation to be detected into structured data in a preset format; wherein, the structured data represents the elements contained in the slide and the distribution situation between the elements;

[0158] The detection unit 503 is used to determine the quality score of the presentation to be detected according to the structured data corresponding to each page of the slide; wherein, the quality score represents the quality level of the presentation to be detected.

[0159] Figure 6 The following is a structural block diagram of a presentation quality detection device provided by an embodiment of the present disclosure, as Figure 6 shown. The presentation quality detection device 600 includes an acquisition unit 601, a conversion unit 602, and a detection unit 603. Among them, the detection unit 603 includes a first determination module 6031 and a second determination module 6032.

[0160] The first determination module 6031 is configured to determine a first score and a second score of each slide according to the structured data corresponding to the slide; wherein, the first score represents the rationality of the layout of elements in the slide, and the second score represents the rationality of the content of elements in the slide;

[0161] The second determination module 6032 is configured to determine the quality score of the presentation to be detected according to the first scores and second scores of each page of the slide.

[0162] In one example, the structured data includes the attribute information and element category of the elements in the slide, and the attribute information represents the presentation format of the elements in the slide; the first determination module 8031 includes:

[0163] An attribute determination sub-module, configured to determine the attribute information of the elements belonging to the same element category in the slide according to the structured data corresponding to the slide;

[0164] An attribute matching sub-module, configured to determine the first score of the slide according to the attribute information of the elements belonging to the same element category in the slide.

[0165] In one example, the attribute matching sub-module is specifically configured to:

[0166] If the attribute information of the elements belonging to the same element category in the slide is all consistent, determine that the first score of the slide is a preset first score value;

[0167] If the attribute information of the elements belonging to the same element category in the slide is inconsistent, determine that the first score of the slide is a preset second score value.

[0168] In one example, the structured data includes the position information of the elements in the slide; the first determination module 6031 includes:

[0169] An area determination sub-module, configured to determine the area information of the overlapping area in the slide according to the position information of each element in the slide; wherein, the overlapping area represents the area where there are overlapping elements in the slide;

[0170] A score determination sub-module, configured to determine a first score of the slide according to the area information of the overlapping region.

[0171] In one example, the structured data includes content information of elements in the slide; the first determination module 6031 includes:

[0172] A semantic recognition sub-module, configured to perform semantic recognition processing on the content information in the structured data to obtain semantic information of the content information; wherein, the semantic information represents the logical clarity degree of the content information;

[0173] A semantic matching sub-module, configured to determine a second score of the slide according to the semantic information of the content information.

[0174] In one example, the structured data includes position information of elements in the slide; the first determination module 6031 includes:

[0175] A first determination sub-module, configured to determine that the second score of the slide is a preset first score value if the position information of each element in the slide is within a preset position range;

[0176] A second determination sub-module, configured to determine that the second score of the slide is a preset second score value if there is position information of an element in the slide that is not within the preset position range.

[0177] In one example, the structured data includes element categories of elements in the slide, and the element categories include a title category; the second determination module 6032 includes:

[0178] A title determination sub-module, configured to determine the number of elements with the element category of the title category in the slide as the title number;

[0179] A quantity comparison sub-module, configured to determine that the slide is a first target page if the title number is greater than a preset quantity threshold;

[0180] A first score sub-module, configured to determine a structured score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of first target pages; wherein, the structured score represents the layout richness of the presentation to be detected;

[0181] A first comprehensive sub-module, configured to determine a quality score of the presentation to be detected according to the structured score of the presentation to be detected, and the first score and the second score of each page of the slide.

[0182] In one example, the first score sub-module is specifically configured to:

[0183] Determine the structured layout rate of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of first target pages; wherein, the structured layout rate represents the ratio between the total number of pages in the presentation to be detected and the number of first target pages;

[0184] If the structured layout rate is equal to or greater than a preset first ratio threshold, determine that the structured score is a preset first score;

[0185] If the structured layout rate is less than the preset first ratio threshold, determine that the structured score is a preset second score.

[0186] In one example, the second determination module 6032 includes:

[0187] A category determination sub-module, configured to determine the slide as a second target page if it is determined that there are elements of a preset category in the structured data corresponding to the slide; wherein, the preset category is at least one of the element categories;

[0188] A second score sub-module, configured to determine the page element score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of second target pages; wherein, the page element score represents the content richness in the presentation to be detected;

[0189] A second comprehensive sub-module, configured to determine the quality score of the presentation to be detected according to the page element score of the presentation to be detected, and the first score and the second score of each page of the slide.

[0190] In one example, the second score sub-module is specifically configured to:

[0191] Determine the element occupancy ratio of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of second target pages; wherein, the element occupancy ratio represents the ratio between the total number of pages in the presentation to be detected and the number of second target pages;

[0192] If the element occupancy ratio is equal to or greater than a preset second ratio threshold, determine that the page element score is a preset first score;

[0193] If the element occupancy ratio is less than the preset second ratio threshold, determine that the page element score is a preset second score.

[0194] In one example, the structured data includes the position information and element categories of the elements in the slide; the second determination module 6032 includes:

[0195] A template determination sub-module, which is used to determine the layout template of each slide according to the position information and element categories of the elements in the slide; wherein, the layout template characterizes the layout of elements of different element categories in the slide.

[0196] A template comparison sub-module, which is used to determine at least two slides with the same layout template as the third target pages if there are at least two slides with the same layout template.

[0197] A third scoring sub-module, which is used to determine the layout repetition score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages; wherein, the layout repetition score characterizes the degree of layout repetition of different pages in the presentation to be detected.

[0198] A third comprehensive sub-module, which is used to determine the quality score of the presentation to be detected according to the layout repetition score of the presentation to be detected, and the first score and the second score of each slide.

[0199] In one example, the third scoring sub-module is specifically used for:

[0200] Determine the repetition ratio of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages; wherein, the repetition ratio characterizes the ratio between the total number of pages in the presentation to be detected and the number of third target pages.

[0201] If the repetition ratio is less than a preset third ratio threshold, determine that the layout repetition score is a preset first score value.

[0202] If the repetition ratio is equal to or greater than the preset third ratio threshold, determine that the layout repetition score is a preset second score value.

[0203] In one example, the structured data includes the content information and element categories of the elements in the slide, and the element categories include text categories; the second determination module 6032 includes:

[0204] A text determination sub-module, which is used to obtain the content information of the elements belonging to the text category from the structured data of each slide as the text content.

[0205] A similarity determination sub-module, which is used to determine the similarity between the text contents of every two slides; wherein, the similarity characterizes the semantic similarity degree of the text contents.

[0206] A fourth scoring sub-module, configured to determine a text professionalism score of the presentation to be detected according to all determined similarities; wherein, the text professionalism score represents the professionalism of the text content in the presentation to be detected.

[0207] A fourth comprehensive sub-module, configured to determine a quality score of the presentation to be detected according to the text professionalism score of the presentation to be detected, and the first score and the second score of each slide.

[0208] In one example, the fourth scoring sub-module is specifically configured to:

[0209] If all determined similarities are less than a preset similarity threshold, determine that the text professionalism score is a preset first score value.

[0210] If there is a similarity equal to or greater than the preset similarity threshold, determine that the text professionalism score is a preset second score value.

[0211] In one example, the obtaining unit 601 includes:

[0212] A dataset obtaining module, configured to obtain a pre-stored presentation dataset; wherein, the presentation dataset includes a plurality of initial presentations.

[0213] An information obtaining module, configured to obtain the browsing information of each initial presentation in the presentation dataset; wherein, the browsing information represents the usage situation of the presentation.

[0214] A presentation determining module, configured to determine the initial presentation whose browsing information meets a preset selection condition as the presentation to be detected.

[0215] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device.

[0216] Figure 7 As shown in the block diagram of an electronic device provided by an embodiment of the present disclosure, Figure 7 as shown, the electronic device 700 includes: at least one processor 702; and a memory 701 communicatively connected to the at least one processor 702; wherein, the memory stores instructions executable by the at least one processor 702, and the instructions are executed by the at least one processor 702 to enable the at least one processor 702 to execute the quality detection method of the presentation of the present disclosure.

[0217] The electronic device 700 further includes a receiver 703 and a transmitter 704. The receiver 703 is configured to receive instructions and data sent by other devices, and the transmitter 704 is configured to send instructions and data to external devices.

[0218] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, and a computer program product.

[0219] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, which includes: a computer program stored in a readable storage medium, and at least one processor of the electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to enable the electronic device to execute the solution provided in any of the above embodiments.

[0220] Figure 8 FIG. shows a schematic block diagram of an exemplary electronic device 800 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0221] As Figure 8 shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0222] A plurality of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disc, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0223] The computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 executes the various methods and processes described above, such as the method for detecting the quality of a presentation. For example, in some embodiments, the method for detecting the quality of a presentation can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for detecting the quality of a presentation described above can be executed. Alternatively, in other embodiments, the computing unit 801 can be configured to execute the method for detecting the quality of a presentation by any other suitable means (e.g., by means of firmware).

[0224] The various embodiments of the systems and techniques described above in this document 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), complex 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 can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0225] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program code is executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0226] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0227] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds 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, speech input, or tactile input).

[0228] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend 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), and the Internet.

[0229] A computer system may include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system or a server combined with a blockchain.

[0230] It should be understood that various forms of processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0231] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for detecting the quality of a presentation, comprising: Obtain a presentation to be detected; wherein the presentation to be detected includes multiple pages of slides; Convert each slide in the presentation to be detected into structured data in a preset format; wherein the structured data represents the elements contained in the slide and the distribution between the elements; The quality score of the presentation to be detected is determined according to the structured data corresponding to each page of the slides; wherein the quality score represents the quality of the presentation to be detected.

2. The method according to claim 1, wherein: Determining the quality score of the presentation to be detected according to the structured data corresponding to each slide, including: For each slide, determine a first score and a second score of the slide according to the structured data corresponding to the slide; wherein the first score represents the rationality of the layout of the elements in the slide, and the second score represents the rationality of the content of the elements in the slide; The quality score of the presentation to be detected is determined according to the first score and the second score of each slide.

3. The method according to claim 2, wherein: The structured data includes attribute information and element categories of elements in the slide, wherein the attribute information represents the presentation format of the elements in the slide; Determining a first score of the slide according to the structured data corresponding to the slide includes: Determining attribute information of elements in the slide that belong to the same element category according to the structured data corresponding to the slide; A first score of the slide is determined according to the attribute information of the elements in the slide that belong to the same element category.

4. The method according to claim 3, wherein: Determining a first score of the slide according to attribute information of elements in the slide belonging to the same element category includes: If the attribute information of the elements belonging to the same element category in the slide are all consistent, determining the first score of the slide to be a preset first score; If there is inconsistency in the attribute information of the elements belonging to the same element category in the slide, the first score of the slide is determined to be a preset second score.

5. The method according to any one of claims 2 to 4, wherein: The structured data includes position information of elements in the slide; Determining a first score of the slide according to the structured data corresponding to the slide includes: Determine area information of an overlapping region in the slide according to position information of each element in the slide; wherein the overlapping region represents an area in the slide where elements overlap; A first score of the slide is determined according to the area information of the overlapping region.

6. The method according to any one of claims 2 to 5, wherein: The structured data includes content information of elements in the slide; Determining a second score of the slide according to the structured data corresponding to the slide includes: Performing semantic recognition processing on the content information in the structured data to obtain semantic information of the content information; wherein the semantic information represents the logical clarity of the content information; A second score of the slide is determined according to the semantic information of the content information.

7. The method according to any one of claims 2 to 6, wherein: The structured data includes position information of elements in the slide; Determining a second score of the slide according to the structured data corresponding to the slide includes: If the position information of each element in the slide is within the preset position range, determining the second score of the slide to be the preset first score; If the position information of the element in the slide is not within the preset position range, the second score of the slide is determined to be a preset second score.

8. The method according to any one of claims 2 to 7, wherein: The structured data includes element categories of elements in the slides, and the element categories include title categories; determining the quality score of the presentation to be detected according to the first score and the second score of each page of the slides, including: Determine the number of elements in the slide whose element category is the title category, which is the number of titles; If the number of titles is greater than a preset number threshold, determining the slide as the first target page; Determine a structured score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of first target pages; wherein the structured score represents the layout richness of the presentation to be detected; The quality score of the presentation to be detected is determined according to the structured score of the presentation to be detected, and the first score and the second score of each slide.

9. The method according to claim 8, wherein: Determining a structured score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of first target pages includes: Determining a structured layout rate of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of first target pages; wherein the structured layout rate represents a ratio between the total number of pages in the presentation to be detected and the number of first target pages; If the structured layout ratio is equal to or greater than a preset first ratio threshold, determining the structured score to be a preset first score; If the structured layout ratio is less than a preset first ratio threshold, the structured score is determined to be a preset second score.

10. The method according to claim 8, wherein: Determining the quality score of the presentation to be detected according to the first score and the second score of each slide, including: If it is determined that there are elements of a preset category in the structured data corresponding to the slide, the slide is determined as the second target page; wherein the preset category is at least one of the element categories; Determining a page element score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of second target pages; wherein the page element score represents the content richness of the presentation to be detected; The quality score of the presentation to be detected is determined according to the page element scores of the presentation to be detected, and the first score and the second score of each slide.

11. The method according to claim 10, wherein: Determining the page element score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of second target pages includes: Determine the element proportion ratio of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of second target pages; wherein the element proportion ratio represents the ratio between the total number of pages in the presentation to be detected and the number of second target pages; If the element proportion ratio is equal to or greater than a preset second ratio threshold, determining that the page element score is a preset first score; If the element proportion ratio is less than a preset second ratio threshold, the page element score is determined to be a preset second score.

12. The method according to any one of claims 2 to 11, wherein: The structured data includes location information and element categories of elements in the slide; Determining the quality score of the presentation to be detected according to the first score and the second score of each slide, including: For each slide, a layout template of the slide is determined according to the position information and element category of each element in the slide; wherein the layout template represents the layout of elements of different element categories in the slide; If there are at least two pages of slides with the same layout template, the at least two pages of slides are determined as the third target page; Determining a layout repetition score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages; wherein the layout repetition score represents the degree of layout repetition of different pages in the presentation to be detected; The quality score of the presentation to be detected is determined according to the layout repetition score of the presentation to be detected, and the first score and the second score of each slide.

13. The method according to claim 12, wherein: Determining a layout repetition score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages, including: Determine the repetition ratio of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages; wherein the repetition ratio represents the ratio between the total number of pages in the presentation to be detected and the number of third target pages; If the repetition ratio is less than a preset third ratio threshold, determining the layout repetition score to be a preset first score; If the repetition ratio is equal to or greater than a preset third ratio threshold, the layout repetition score is determined to be a preset second score.

14. The method according to any one of claims 2 to 13, wherein: The structured data includes content information and element categories of elements in the slides, and the element categories include text categories; determining the quality score of the presentation to be detected according to the first score and the second score of each page of the slides, including: For each slide, content information of an element belonging to a text category is obtained from the structured data of the slide, which is text content; Determine the similarity between the text contents of every two slides; wherein the similarity represents the semantic similarity of the text contents; Determine the text professional score of the presentation to be detected according to all the determined similarities; wherein the text professional score represents the professional level of the text content in the presentation to be detected; The quality score of the presentation to be detected is determined according to the text professional score of the presentation to be detected, and the first score and the second score of each slide.

15. The method according to claim 14, wherein: According to all the determined similarities, the text professional score of the presentation to be detected is determined, including: If all the determined similarities are less than a preset similarity threshold, the text professional score is determined to be a preset first score; If there is a similarity that is equal to or greater than a preset similarity threshold, the text professional score is determined to be a preset second score.

16. The method according to any one of claims 1 to 15, wherein: Get the presentation to be tested, including: Acquire a pre-stored presentation data set; wherein the presentation data set includes a plurality of initial presentations; Obtaining browsing information of each initial presentation in the presentation data set; wherein the browsing information represents a usage situation of the presentation; The initial presentation whose browsing information meets the preset selection condition is determined as the presentation to be detected.

17. A presentation quality detection device, comprising: An acquisition unit, used for acquiring a presentation to be detected; wherein the presentation to be detected includes a plurality of slides; A conversion unit, used to convert each slide in the presentation to be detected into structured data in a preset format; wherein the structured data represents the elements contained in the slide and the distribution between the elements; The detection unit is used to determine the quality score of the presentation to be detected according to the structured data corresponding to each page of the slide; wherein the quality score represents the quality of the presentation to be detected.

18. The device according to claim 17, wherein: The detection unit comprises: A first determination module is used to determine, for each slide, a first score and a second score of the slide according to the structured data corresponding to the slide; wherein the first score represents the rationality of the layout of the elements in the slide, and the second score represents the rationality of the content of the elements in the slide; The second determination module is used to determine the quality score of the presentation to be detected according to the first score and the second score of each slide.

19. The device according to claim 18, wherein: The structured data includes attribute information and element categories of elements in the slide, wherein the attribute information represents the presentation format of the elements in the slide; The first determining module includes: An attribute determination submodule, used to determine attribute information of elements belonging to the same element category in the slide according to the structured data corresponding to the slide; The attribute matching submodule is used to determine the first score of the slide according to the attribute information of the elements belonging to the same element category in the slide.

20. The device according to claim 19, wherein The attribute matching submodule is specifically used for: If the attribute information of the elements belonging to the same element category in the slide are all consistent, determining the first score of the slide to be a preset first score; If there is inconsistency in the attribute information of the elements belonging to the same element category in the slide, the first score of the slide is determined to be a preset second score.

21. The device according to any one of claims 18 to 20, wherein: The structured data includes position information of elements in the slide; The first determining module includes: An area determination submodule, used to determine the area information of the overlapping area in the slide according to the position information of each element in the slide; wherein the overlapping area represents the area where the elements in the slide overlap; The score determination submodule is used to determine the first score of the slide according to the area information of the overlapping region.

22. The device according to any one of claims 18 to 21, wherein: The structured data includes content information of elements in the slide; The first determining module includes: A semantic recognition submodule, configured to perform semantic recognition processing on the content information in the structured data to obtain semantic information of the content information; wherein the semantic information represents the logical clarity of the content information; The semantic matching submodule is used to determine the second score of the slide according to the semantic information of the content information.

23. The device according to any one of claims 18 to 22, wherein: The structured data includes position information of elements in the slide; The first determining module includes: A first determination submodule, configured to determine that the second score of the slide is a preset first score if the position information of each element in the slide is within a preset position range; The second determination submodule is configured to determine that the second score of the slide is a preset second score value if the position information of the element in the slide is not within a preset position range.

24. The device according to any one of claims 18 to 23, wherein: The structured data includes element categories of elements in the slide, and the element categories include title categories; The second determining module includes: The title determination submodule is used to determine the number of elements in the slide whose element category is the title category, which is the number of titles; A quantity comparison submodule, configured to determine that the slide is a first target page if the quantity of the titles is greater than a preset quantity threshold; A first scoring submodule, used to determine a structured score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of first target pages; wherein the structured score represents the layout richness of the presentation to be detected; The first comprehensive submodule is used to determine the quality score of the presentation to be detected according to the structured score of the presentation to be detected, and the first score and the second score of each slide.

25. The device according to claim 24, wherein: The first submodule is specifically used for: Determining a structured layout rate of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of first target pages; wherein the structured layout rate represents a ratio between the total number of pages in the presentation to be detected and the number of first target pages; If the structured layout ratio is equal to or greater than a preset first ratio threshold, determining the structured score to be a preset first score; If the structured layout ratio is less than a preset first ratio threshold, the structured score is determined to be a preset second score.

26. The device according to claim 24, wherein: The second determining module includes: A category determination submodule, for determining the slide as a second target page if it is determined that there are elements of a preset category in the structured data corresponding to the slide; wherein the preset category is at least one of the element categories; A second scoring submodule, used to determine the page element score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of second target pages; wherein the page element score represents the content richness of the presentation to be detected; The second comprehensive submodule is used to determine the quality score of the presentation to be detected according to the page element scores of the presentation to be detected, and the first score and the second score of each slide.

27. The device according to claim 26, wherein: The second submodule is specifically used for: Determine the element proportion ratio of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of second target pages; wherein the element proportion ratio represents the ratio between the total number of pages in the presentation to be detected and the number of second target pages; If the element proportion ratio is equal to or greater than a preset second ratio threshold, determining that the page element score is a preset first score; If the element proportion ratio is less than a preset second ratio threshold, the page element score is determined to be a preset second score.

28. The device according to any one of claims 18 to 27, wherein: The structured data includes location information and element categories of elements in the slide; The second determining module includes: The template determination submodule is used to determine the layout template of each slide according to the position information and element category of each element in the slide; wherein the layout template represents the layout of elements of different element categories in the slide; A template comparison submodule, configured to determine the at least two slides as the third target page if the layout templates of at least two slides are consistent; A third scoring submodule, used to determine a layout repetition score of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages; wherein the layout repetition score represents the degree of layout repetition of different pages in the presentation to be detected; The third comprehensive submodule is used to determine the quality score of the presentation to be detected according to the layout repetition score of the presentation to be detected, and the first score and the second score of each slide.

29. The device according to claim 28, wherein The third submodule is specifically used for: Determine the repetition ratio of the presentation to be detected according to the total number of pages in the presentation to be detected and the number of third target pages; wherein the repetition ratio represents the ratio between the total number of pages in the presentation to be detected and the number of third target pages; If the repetition ratio is less than a preset third ratio threshold, determining the layout repetition score to be a preset first score; If the repetition ratio is equal to or greater than a preset third ratio threshold, the layout repetition score is determined to be a preset second score.

30. The device according to any one of claims 18 to 29, wherein: The structured data includes content information and element categories of elements in the slide, and the element categories include text categories; the second determination module includes: A text determination submodule is used to obtain content information of elements belonging to the text category from the structured data of each slide, which is text content; A similarity determination submodule is used to determine the similarity between the text contents of every two slides; wherein the similarity represents the semantic similarity of the text contents; A fourth score submodule is used to determine the text professional score of the presentation to be detected according to all the determined similarities; wherein the text professional score represents the professional level of the text content in the presentation to be detected; The fourth comprehensive submodule is used to determine the quality score of the presentation to be detected according to the text professional score of the presentation to be detected, and the first score and the second score of each slide.

31. The device according to claim 30, wherein The fourth submodule is specifically used for: If all the determined similarities are less than a preset similarity threshold, the text professional score is determined to be a preset first score; If there is a similarity that is equal to or greater than a preset similarity threshold, the text professional score is determined to be a preset second score.

32. The device according to any one of claims 17 to 31, wherein: The acquisition unit comprises: A data set acquisition module, used to acquire a pre-stored presentation data set; wherein the presentation data set includes a plurality of initial presentations; An information acquisition module, used to acquire browsing information of each initial presentation in the presentation data set; wherein the browsing information represents the usage of the presentation; The document determination module is used to determine the initial presentation document whose browsing information meets the preset selection condition as the presentation document to be detected.

33. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 16.

34. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-16.

35. A computer program product, wherein: The invention comprises a computer program, which implements the steps of the method according to any one of claims 1 to 16 when being executed by a processor.

Images