Electronic page retrieval method and device, learning equipment, and readable storage medium
By acquiring and comparing page images taken by the learning device, determining its complexity and comparison times, the problem of low page retrieval accuracy in different versions of the same textbook is solved, and more efficient electronic page matching and learning content output is achieved.
Patent Information
- Application Number
- CN202010574041.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-06-22
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2040-06-22
AI Technical Summary
When existing learning devices retrieve different versions of electronic pages of the same textbook, the accuracy rate is low, and it is impossible to determine which version of the page is used to output related learning content.
By obtaining the page identification information in the page image, multiple similar electronic pages are retrieved, the complexity information of each page is obtained, the number of comparisons is determined based on the complexity, and multiple comparisons are performed to determine the target electronic page.
Improve the search accuracy of electronic pages and ensure that the output learning content best matches the target page.
Smart Images

Figure CN111737500B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of learning equipment, and in particular to a method and device for retrieving electronic pages, a learning device, and a readable storage medium. Background Art
[0002] With the development of science and technology, learning devices such as point-reading machines, learning machines or tutoring machines have become the mainstream high-tech digital products that integrate point-reading, online learning and multimedia playback functions. Students can use learning devices to study after class, and students can use learning devices to take pictures to obtain page images during the learning process. The learning device searches based on the page image to retrieve the corresponding electronic page and output the learning content associated with the electronic page.
[0003] However, in practice, it is found that the same textbook can have multiple versions published in different years, which often results in multiple matching electronic pages being retrieved when the learning device is searching. The multiple matching electronic pages are very similar, with only a few minor differences, such as electronic pages belonging to the same textbook but published in different years. In this case, it is impossible to determine which electronic page to use to obtain the associated learning content for output. It can be seen that the existing electronic page retrieval accuracy is low. Summary of the invention
[0004] The embodiments of the present application disclose a method and device for searching electronic pages, a learning device, and a readable storage medium, which can improve the search accuracy of electronic pages.
[0005] The first aspect of the embodiment of the present application discloses a method for searching an electronic page, comprising:
[0006] Obtaining page identification information from the page image captured by the camera module;
[0007] Retrieving and obtaining at least two similar electronic pages matching the page identification information;
[0008] Obtaining complexity information corresponding to each of the electronic pages; the complexity information includes distinguishing feature information and complexity, the distinguishing feature information is used to characterize the distinguishing features of the electronic page and other similar electronic pages, and the complexity is used to characterize the obviousness of the distinguishing features;
[0009] Determining the number of comparisons for each of the electronic pages according to the complexity of each of the electronic pages;
[0010] According to the comparison times of each electronic page, the page image is compared with the distinguishing characteristic information of each electronic page for multiple times to obtain multiple comparison results corresponding to each electronic page;
[0011] According to the multiple comparison results corresponding to each of the electronic pages, a target electronic page is determined from the at least two similar electronic pages.
[0012] A second aspect of an embodiment of the present application discloses a device for searching an electronic page, comprising:
[0013] The identification acquisition unit is used to acquire page identification information in the page image captured by the camera module;
[0014] A retrieval unit, used for retrieving and obtaining at least two similar electronic pages matching the page identification information;
[0015] An information acquisition unit, used to acquire complexity information corresponding to each of the electronic pages; the complexity information includes distinguishing feature information and complexity, the distinguishing feature information is used to characterize the distinguishing features of the electronic page and other similar electronic pages, and the complexity is used to characterize the obviousness of the distinguishing features;
[0016] A first determining unit, configured to determine the number of comparisons of each electronic page according to the complexity of each electronic page;
[0017] A comparison unit, used for comparing the page image with the distinguishing characteristic information of each electronic page multiple times according to the comparison times of each electronic page, so as to obtain multiple comparison results of each electronic page;
[0018] The second determining unit is used to determine a target electronic page from the at least two similar electronic pages according to the multiple comparison results corresponding to each of the electronic pages.
[0019] A third aspect of an embodiment of the present application discloses a learning device, including:
[0020] A memory storing executable program code;
[0021] a processor coupled to the memory;
[0022] The processor calls the executable program code stored in the memory to execute an electronic page retrieval method disclosed in the first aspect of the embodiment of the present application.
[0023] The fourth aspect of the embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute a method for retrieving an electronic page disclosed in the first aspect of the embodiment of the present application. The computer-readable storage medium includes a ROM / RAM, a magnetic disk or an optical disk, etc.
[0024] A fifth aspect of the embodiments of the present application discloses a computer program product. When the computer program product is run on a computer, the computer is enabled to execute part or all of the steps of any one of the methods of the first aspect.
[0025] A sixth aspect of an embodiment of the present application discloses an application publishing platform, which is used to publish a computer program product. When the computer program product runs on a computer, the computer executes part or all of the steps of any one of the methods of the first aspect.
[0026] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0027] In the embodiment of the present application, by acquiring the page identification information in the page image captured by the camera module, if at least two similar electronic pages matching the page identification information are retrieved, the complexity information corresponding to each electronic page is acquired, and the complexity information includes distinguishing feature information and complexity, and then the number of comparisons of each electronic page is determined according to the complexity of each electronic page, and then the page image is compared with the distinguishing feature information of each electronic page for multiple times according to the number of comparisons of each electronic page, so as to obtain multiple comparison results corresponding to each electronic page, and finally the target electronic page is determined from at least two similar electronic pages according to the multiple comparison results corresponding to each electronic page. It can be seen that in the implementation of the embodiment of the present application, when multiple electronic pages are retrieved, the number of comparisons of each electronic page is adaptively determined according to the complexity of different electronic pages, and then the page image is compared with each electronic page for multiple times according to the number of comparisons of each electronic page, so that the electronic page can be determined based on the distinguishing feature information and the multiple comparison method, thereby improving the retrieval accuracy of the electronic page. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0029] Figure 1 This is an application scenario diagram of an electronic page retrieval method disclosed in an embodiment of the present application;
[0030] Figure 2 It is a flowchart of a method for retrieving an electronic page disclosed in an embodiment of the present application;
[0031] Figure 3 It is a flowchart of another electronic page retrieval method disclosed in an embodiment of the present application;
[0032] Figure 4 It is a flowchart of another electronic page retrieval method disclosed in an embodiment of the present application;
[0033] Figure 5 It is a structural schematic diagram of an electronic page retrieval device disclosed in an embodiment of the present application;
[0034] Figure 6 It is a structural schematic diagram of another electronic page retrieval device disclosed in an embodiment of the present application;
[0035] Figure 7 It is a structural schematic diagram of a learning device disclosed in an embodiment of the present application. DETAILED DESCRIPTION
[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0037] It should be noted that the terms "first", "second", "third", etc. in the specification and claims of the present application are used to distinguish different objects rather than to describe a specific order. The terms "including" and "having" in the embodiments of the present application and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device including a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0038] The embodiments of the present application disclose a method and device for retrieving electronic pages, a learning device, and a readable storage medium, which can improve the retrieval accuracy of electronic pages. Among them, the method shown in the embodiments of the present application is applicable to a retrieval device for electronic pages, and the retrieval device for electronic pages is applied to learning devices such as learning machines, point reading machines, and tutoring machines. Among them, the operating systems of various types of learning devices include but are not limited to Android operating system, IOS operating system, Symbian operating system, Windows operating system, etc., which are not limited in the embodiments of the present application. The execution subject of the embodiments of the present application is described in detail in combination with the accompanying drawings using a learning device as an example, and it should be understood that it should not constitute any limitation to the present application.
[0039] In order to better understand the electronic page search method disclosed in the embodiment of the present application, the application scenario of the electronic page search method is described below. Figure 1 , Figure 1 is an application scenario diagram of an electronic page retrieval method disclosed in an embodiment of the present application. It can be understood that, Figure 1 This is only an exemplary application scenario diagram of the electronic page retrieval method disclosed in the embodiment of the present application. Figure 1 The application scenarios obtained by optimizing or deforming the above-mentioned components and capable of realizing the technical solution of the present application all belong to the protection scope of the present application and are not specifically limited thereto.
[0040] exist Figure 1 In the application scenario shown, the user can learn by using the learning device 10 and placing the physical page 40 on the desktop where the learning device 10 is placed. During the learning process, the user can start the learning device 10 to take a picture of the physical page 40 to obtain a page image, retrieve the electronic page for the page image, determine the electronic page corresponding to the page image, and then output the associated learning content of the electronic page to the user. Figure 1 As shown, the learning device 10 may be provided with a shooting module 20, which may be provided on a side of the learning device 10 equipped with an electronic screen. The camera module 20 is used to shoot a physical page 40 to obtain a page image. A reflective device 30 (e.g., a reflector, a prism, or a convex lens, etc.) may also be provided directly in front of the shooting module 20. The mirror surface of the reflective device 30 forms a preset angle with the lens surface of the shooting module 20. The reflective device 30 is used to change the optical path of the shooting module 20, so that the shooting module 20 shoots the physical page 40 to obtain a page image. By using the imaging of the physical page 40 in the reflective device 30 obtained by shooting the shooting module 20 of the learning device 10, without manually changing the placement of the learning device 10, the shooting process can be simplified and the shooting efficiency can be improved. Optionally, the physical page 40 may be a book page or paper page placed on a desktop and within the shooting range of the learning device, or an electronic page displayed on a mobile terminal (such as a mobile phone or a tablet computer, etc.), the mobile terminal is a terminal device different from the learning device, and the mobile terminal may be a terminal device placed on the desktop where the learning device is placed and within the shooting range of the learning device. Further optionally, when the physical page 40 is a book page or paper page, the physical page 40 may specifically be a textbook or a teaching material exercise book, etc., which is not specifically limited in the embodiment of the present application.
[0041] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of a method for retrieving an electronic page disclosed in an embodiment of the present application. Figure 2 As shown, the electronic page retrieval method may include the following steps:
[0042] 201. The learning device obtains page identification information in the page image captured by the camera module.
[0043] As an optional implementation, the learning device can start the camera module set in the learning device to shoot the physical page (such as a book page or a paper page, etc.) placed on the desktop to obtain a page image when receiving a preset trigger instruction. Among them, the preset trigger instruction is used to trigger the learning device to start the camera module to shoot, which can be any pre-set user interaction instruction. The user interaction instruction may include but is not limited to the instructions input by the user in any interaction mode such as voice interaction, remote control interaction, gesture interaction, image interaction, voiceprint interaction, and somatosensory interaction. The specific interaction mode used for input is not specifically limited in the embodiment of the present application.
[0044] In an embodiment of the present application, page identification information can be used to identify which page the page image belongs to, or it can be used to identify which book the page image belongs to and which page in the book it is located on. It can be an identification pattern or an identification code, and the present application does not limit this. Optionally, the page identification information can be printed on a specified area on the physical page, such as the upper left corner, lower left corner, upper left corner or lower right corner.
[0045] In some embodiments, before the learning device obtains the page identification information in the page image captured by the camera module, it can also determine whether the page image captured by the camera module meets the preset standard. If it does not meet the preset standard, the camera module can be controlled to shoot again to capture a new page image that meets the preset standard, and then obtain the page identification information in the new page image. Among them, the preset standard can be used to characterize the clarity of the image or the completeness of the page content in the image, so as to ensure the integrity and clarity of the page image, thereby improving the efficiency and accuracy of electronic page retrieval.
[0046] 202. The learning device retrieves and obtains at least two similar electronic pages that match the page identification information.
[0047] In an embodiment of the present application, at least two similar electronic pages that match the page identification information may be electronic pages having the same textbook number or the same textbook type and the same page identification information as the physical page represented by the page image, wherein the same textbook number may refer to the same textbook number, the same textbook type may refer to textbooks of the same type, and the same page identification information may refer to the same textbook number and the same page number, that is, they may be pages of the same page number belonging to the same textbook but different versions.
[0048] 203. The learning device obtains complexity information corresponding to each electronic page, wherein the complexity information includes distinguishing feature information and complexity, wherein the distinguishing feature information is used to characterize the distinguishing features between the electronic page and other similar electronic pages, and the complexity is used to characterize the degree of obviousness of the distinguishing features.
[0049] In some embodiments, the learning device may store multiple electronic books and multiple electronic pages included in each electronic book, and store the corresponding complexity information associated with each electronic page, and the complexity information may include distinguishing feature information and complexity, wherein the distinguishing feature information may be used to characterize the distinguishing features of the electronic page and other similar electronic pages of different versions but with the same textbook number and the same page number, and the complexity refers to the obvious degree of distinguishing features between the electronic page and other similar electronic pages. The higher the obvious degree of distinguishing features, the lower the complexity, and conversely, the lower the obvious degree of distinguishing features, the higher the complexity.
[0050] The obviousness of the distinguishing features may refer to the number of distinguishing features between the electronic page and other similar electronic pages, the degree of concentration of the distinguishing features on the electronic page, or the form of the distinguishing features (such as graphics, text, or formula, etc.).
[0051] 204. The learning device determines the number of comparisons for each electronic page according to the complexity of each electronic page. The number of comparisons for an electronic page is positively correlated with its complexity. The higher the complexity, the more comparisons; the lower the complexity, the fewer comparisons. Optionally, the number of comparisons is at least 2.
[0052] 205. The learning device compares the page image with the distinguishing feature information of each electronic page and the page image multiple times according to the number of comparisons of each electronic page, so as to obtain multiple comparison results corresponding to each electronic page.
[0053] The distinguishing feature information of the electronic page may refer to the distinguishing features of the electronic page and other similar electronic pages, or may refer to information that can be linked to the distinguishing features of the electronic page and other similar electronic pages. Optionally, the multiple comparison results may include the results of each comparison, and the results of each comparison may include but are not limited to the similarity between the electronic page and the page image or the probability value of the electronic page being the target electronic page, etc. The specific value of the comparison result is not specifically limited in this application.
[0054] For example, assuming that three similar electronic pages are retrieved, namely electronic pages A, B and C, based on the complexity included in their respective pre-stored complexity information, it can be determined that the number of comparisons for electronic pages A, B and C are 3 times, 2 times and 4 times respectively. Then, based on the distinguishing feature information included in their respective pre-stored complexity information, the distinguishing feature information of electronic page A can be compared with the page image for 3 times to obtain 3 comparison results a of electronic page A, and the distinguishing feature information of electronic page B can be compared with the page image for 2 times to obtain 2 comparison results b of electronic page B, and the distinguishing feature information of electronic page C can be compared with the page image for 4 times to obtain 4 comparison results c of electronic page C.
[0055] In some embodiments, the learning device compares the distinguishing feature information of the electronic page and the page image multiple times according to the comparison times of each electronic page, which can be specifically preprocessed to obtain a processed image, and then the learning device extracts features from the processed image to obtain image feature information, so that the distinguishing feature information and image feature information of the electronic page can be compared multiple times according to the comparison times of each electronic page. The preprocessing includes but is not limited to analog to digital converter (A / D), binarization, image smoothing, transformation, enhancement, restoration and filtering, so that the page image can be digitized to improve the accuracy of the comparison result.
[0056] 206. The learning device determines a target electronic page from at least two similar electronic pages according to multiple comparison results corresponding to each electronic page.
[0057] In some embodiments, the learning device determines the target electronic page from at least two similar electronic pages based on the multiple comparison results corresponding to each electronic page by calculating the average value of the multiple comparison results of each electronic page based on the multiple comparison results corresponding to each electronic page, and if the average value of the multiple comparison results reaches a preset average threshold, the electronic page to which the multiple comparison results belong is determined to be the target electronic page; or, it is determined whether the values of the multiple comparison results of each electronic page all reach a preset result threshold, and if the values of the multiple comparison results all reach the preset result threshold, the electronic page to which the multiple comparison results belong is determined to be the target electronic page. In this way, the multiple comparison results can be comprehensively referenced to ensure the accuracy of the determined target electronic page.
[0058] As an optional implementation, before the learning device determines the target electronic page from at least two similar electronic pages based on the multiple comparison results corresponding to each electronic page, it may also determine whether the multiple comparison results corresponding to each electronic page show a stable trend, and exclude some electronic pages for which the multiple comparison results are judged not to show a stable trend, so as to obtain the remaining electronic pages for which the multiple comparison results show a stable trend. Then, the learning device may determine the target electronic page from at least two similar electronic pages based on the multiple comparison results corresponding to each electronic page by specifically determining the target electronic page from at least two similar electronic pages based on the multiple comparison results corresponding to each remaining electronic page.
[0059] Further optionally, if each comparison result includes the similarity between the electronic page and the page image, the learning device determines whether the multiple comparison results of each electronic page show a stable trend by specifically determining whether the similarities between the electronic page and the page image represented by each comparison result of each electronic page are within a preset similarity range; if so, it is determined that the multiple comparison results show a stable trend; otherwise, it is determined that the multiple comparison results do not show a stable trend.
[0060] Or optionally, if each comparison result includes a probability value that the electronic page to which it belongs is the target electronic page, the learning device determines whether the multiple comparison results of each electronic page present a stable trend by specifically determining whether the probability values of the electronic page represented by each comparison result of each electronic page that the electronic page to which it belongs is the target electronic page are all within a preset probability range. If so, it is determined that the multiple comparison results present a stable trend; otherwise, it is determined that the multiple comparison results do not present a stable trend.
[0061] Through this implementation, by judging the stability of multiple comparison results, the target electronic page is determined only from electronic pages whose multiple comparison results show a stable trend, which can narrow the range of at least two similar electronic pages and further improve the retrieval accuracy of electronic pages.
[0062] In some embodiments, after the learning device determines the target electronic page from at least two similar electronic pages, it can output the associated learning content corresponding to the target electronic page, and the associated learning content may include but is not limited to video materials, text materials, or voice materials. Further optionally, the learning device can output the associated learning content corresponding to the target electronic page by first identifying whether there is a designated partial area in the page image, and if so, obtaining the position information of the designated partial area in the page image, and obtaining the output of the associated learning content corresponding to the designated partial area based on the position information of the designated partial area. Through this implementation, it is possible to output the associated learning content and recommend it to the user for learning, thereby improving the user experience.
[0063] It can be seen that by implementing the method provided in the above embodiment, when retrieving multiple electronic pages, the number of comparisons of each electronic page is adaptively determined according to the complexity of different electronic pages, and then the page image is compared with each electronic page multiple times according to the number of comparisons of each electronic page. The electronic page can be determined based on distinguishing feature information and multiple comparisons, thereby improving the retrieval accuracy of the electronic page.
[0064] See also Figure 3 , Figure 3 FIG. 1 is a flow chart of another electronic page search method disclosed in an embodiment of the present application. Figure 3 As shown, the electronic page retrieval method may include the following steps:
[0065] 301. The learning device obtains page identification information in the page image captured by the camera module.
[0066] In some embodiments, before executing any of the electronic page retrieval methods disclosed in the embodiments of the present application, the learning device can scan and classify similar electronic pages belonging to the same page of the same book stored in the database, and mark each electronic page to form the complexity information of each electronic page, and then store the complexity information of each electronic page in association with the electronic page to which it belongs. Then, when executing any of the electronic page retrieval methods disclosed in the embodiments of the present application, the complexity information of each electronic page can be quickly obtained, thereby accelerating the retrieval efficiency of the electronic page. Specifically, the learning device can scan multiple electronic pages stored in the database to obtain multiple page sets; wherein the multiple page sets are different, each page set includes at least two electronic pages with the same book identification information and the same page identification information, and the first similarity of the at least two electronic pages reaches a first specified threshold, and then each electronic page in each page set is marked with complexity to obtain the complexity information of each electronic page, and the complexity information of each electronic page is stored in association with the electronic page to which it belongs.
[0067] The first similarity refers to the similarity between any electronic page in any page set and any other similar electronic page with the same book identification information and the same page identification information. In other words, the similarity between any two electronic pages in any page set reaches the first specified threshold.
[0068] Further optionally, the learning device can obtain distinguishing feature information of each electronic page in each page set and other similar electronic pages in the page set to which it belongs, and then obtain the degree of obviousness of the distinguishing features represented by the distinguishing feature information based on the distinguishing feature information, wherein the higher the degree of obviousness, the more distinguishing features there are between the electronic page and other similar electronic pages in the page set to which it belongs, and then use this to mark the complexity of each electronic page in each page set. Specifically, each electronic page can be marked with complexity according to the degree of obviousness of the distinguishing features to obtain the complexity of each electronic page, wherein the higher the degree of obviousness of the distinguishing features, the smaller the complexity, and finally the distinguishing feature information and complexity are used as the complexity information of the electronic page to which it belongs.
[0069] 302. The learning device retrieves and obtains at least two similar electronic pages that match the page identification information.
[0070] 303. If at least two similar electronic pages are not marked as locked pages, the learning device determines the number of comparisons for each electronic page according to the complexity corresponding to each electronic page.
[0071] Among them, the locked page may be an electronic page that is locked based on a user operation instruction during the retrieval process of historical electronic pages. The retrieval process of historical electronic pages may refer to the retrieval process of electronic pages executed by the learning device at any time before the current time. The user operation instruction may be used to instruct the learning device to lock a certain electronic page, and may also be used to instruct the learning device to lock the electronic book where a certain electronic page is located.
[0072] As an optional implementation, if there is a locked electronic page marked as a locked page in at least two similar electronic pages, the learning device may first determine the number of locked electronic pages in at least two similar electronic pages, and if the number of locked electronic pages is equal to one, determine the locked electronic page as the target electronic page; if the number of locked electronic pages is greater than one, perform the step of determining the number of comparisons of each electronic page according to the complexity corresponding to each electronic page on the locked electronic page. Thus, the false positive rate can be reduced by locking the electronic pages, and the retrieval efficiency and accuracy of the electronic pages can be further improved.
[0073] 304-305. For the description of steps 304-305, please refer to the detailed description of steps 205-206 in the above embodiment, which will not be repeated in the present invention.
[0074] 306. If the complexity corresponding to the target electronic page reaches a preset complexity threshold, the learning device outputs prompt information for marking the target electronic page as a locked page.
[0075] The preset complexity threshold may be a certain value pre-set by the developer according to the actual situation. When the complexity corresponding to the target electronic page reaches the preset complexity threshold, it can be considered that the obvious degree of the distinguishing features between the target electronic page and other similar electronic pages is very low, and it is difficult to identify the distinguishing features, that is, the target electronic page is more matched and similar to the page image, then it can be considered that the textbook version recently used by the user is the textbook version to which the target electronic page belongs, then the textbook version to which the target electronic page belongs can be locked, so that when the electronic page is searched again later, the locked textbook version can be determined as the search range first, and then the search range of the electronic page can be refined, thereby improving the search efficiency and accuracy of the electronic page.
[0076] 307. When receiving a user confirmation instruction for the prompt information, the learning device obtains book identification information of the electronic book where the target electronic page is located.
[0077] In some embodiments, the learning device may output prompt information in the form of voice, or may pop up text prompt information on an electronic screen (such as toast information, which is a lightweight prompt method, often appearing in the form of a small pop-up box, which generally disappears automatically after 1 to 2 seconds, and may appear at any position in the middle or lower part of the screen). The embodiment of the present application does not specifically limit the method of outputting prompt information. Among them, the user-determined instruction for the prompt information may be any pre-set user interaction instruction, and the user interaction instruction may include but is not limited to the instruction input by the user in any interaction mode such as voice interaction, remote control interaction, gesture interaction, image interaction, voiceprint interaction, and somatosensory interaction. The specific interaction mode used for input is not specifically limited in the embodiment of the present application.
[0078] Among them, the book identification information can be information used to identify which electronic book the target page belongs to, and it can be stored in association with the storage location of the target electronic page on the learning device. When the storage location of the target electronic page on the learning device is obtained, it can be linked to the book identification information of the target electronic page. It can be proprietary coding information, digital information or picture information, etc. This application does not make specific limitations on this.
[0079] 308. The learning device locks the electronic book according to the book identification information, so that each electronic page included in the electronic book is marked as a locked page.
[0080] Optionally, the page identification information of each electronic page may carry the book identification information of the electronic book in which it is located, and the learning device may establish a link between the book identification information and the locking information, thereby locking the electronic book so that each electronic page included in the electronic book is marked as a locked page.
[0081] It can be seen that the implementation of the method provided in the above embodiment can determine the electronic page based on the distinguishing feature information and multiple comparisons, thereby improving the retrieval accuracy of the electronic page.
[0082] In addition, upon receiving a user instruction to lock a certain electronic page, the textbook version most recently used by the user is considered to be the textbook version to which the electronic page belongs, and the textbook version to which the electronic page belongs is locked, so that when the electronic page is searched again subsequently, the locked textbook version can be prioritized as the search range, thereby refining the search scope of the electronic page and improving the retrieval efficiency and accuracy of the electronic page.
[0083] See also Figure 4 , Figure 4 FIG. 1 is a flow chart of another electronic page search method disclosed in an embodiment of the present application. Figure 4 As shown, the electronic page retrieval method may include the following steps:
[0084] 401 to 405. For the description of steps 401 to 405, please refer to the detailed description of steps 201 to 205 in the above embodiment, which will not be repeated in the present invention.
[0085] 406. The learning device calculates the variance value of the multiple comparison results of each electronic page according to the multiple comparison results corresponding to each electronic page.
[0086] In the embodiments of the present application, the variance value of the multiple comparison results can be used to characterize the data fluctuation degree of the multiple comparison results, which can be a special term variance in applied mathematics. In probability theory and statistics, the variance of a set of data is used to measure the fluctuation degree of a set of data (i.e., the deviation of this set of data from the mean). When the amount of data is the same, the larger the variance, the larger the fluctuation degree of the data, and the more unstable it is; the smaller the variance, the smaller the fluctuation degree of the data, and the more stable it is. Therefore, by calculating the variance value of the multiple comparison results of each electronic page, the data fluctuation degree of the multiple comparison results can be obtained.
[0087] 407. If the variance value meets the preset range, it is determined that the multiple comparison results meet the preset conditions.
[0088] The preset range may be a numerical range preset by a developer, and when the variance value calculated based on the multiple comparison results falls within this numerical range, it is determined that the multiple comparison results meet the preset conditions.
[0089] 408. The learning device determines a second similarity between the electronic page to which the multiple comparison results belong and the page image according to the multiple comparison results.
[0090] In some embodiments, the learning device determines the second similarity between the electronic page to which the multiple comparison results belong and the page image according to the multiple comparison results after determining that the multiple comparison results meet the preset conditions, thereby narrowing the scope of the electronic pages and improving the retrieval accuracy of the electronic pages. The second similarity refers to the similarity between any similar electronic page and the page image whose multiple comparison results meet the preset conditions, and the second similarities corresponding to different electronic pages may be the same or different.
[0091] 409. The learning device excludes electronic pages whose second similarity does not reach a second specified threshold value to obtain at least one similar electronic page after exclusion, wherein the second similarity of the at least one similar electronic page after exclusion reaches a second specified threshold value.
[0092] Optionally, after obtaining the second similarity between the electronic page and the page image whose comparison results meet preset conditions multiple times, the learning device can further narrow the scope of the electronic pages by excluding electronic pages whose second similarity does not reach a second specified threshold, and obtaining at least one similar electronic page whose second similarity reaches the second specified threshold.
[0093] 410. The learning device determines whether the number of at least one similar electronic page is greater than or equal to two. If so, go to step 404; otherwise, go to step 411.
[0094] Furthermore, the learning device can determine whether the number of at least one similar electronic page determined after narrowing the scope is equal to one. If so, the unique electronic page is directly determined to be the target electronic page. However, if it is not equal to one, and the number is greater than or equal to two, the comparison operation can be repeated multiple times on the at least one similar electronic page, that is, turn to step 404, so that steps 404 to 410 can be repeated on the at least one similar electronic page until the number of electronic pages whose second similarity with the page image reaches the second specified threshold is one, and the unique electronic page is determined to be the target electronic page.
[0095] 411. If the number of at least one similar electronic page is equal to one, the learning device determines that the unique electronic page is a target electronic page.
[0096] It can be seen that the implementation of the method provided in the above embodiment can determine the electronic page based on the distinguishing feature information and multiple comparisons, thereby improving the retrieval accuracy of the electronic page.
[0097] In addition, after obtaining multiple comparison results of each electronic page, the data fluctuation degree of the multiple comparison results can be further judged. If the data fluctuation degree is small and the multiple comparison results are judged to be relatively stable, then the second similarity between the electronic page to which the multiple comparison results belong and the page image is determined based on the multiple comparison results to perform a threshold judgment to further narrow the range of the electronic pages, until a unique final search result is determined and then output, thereby further improving the search accuracy of the electronic pages, ensuring the search effect of the electronic pages, and improving the user experience.
[0098] See also Figure 5 , Figure 5 Schematic diagram of a structure of an electronic page search device disclosed in an embodiment of the present application. Figure 5 As shown, the electronic page search device may include an identification acquisition unit 501, a search unit 502, an information acquisition unit 503, a first determination unit 504, a comparison unit 505 and a second determination unit 506; wherein,
[0099] The identification acquisition unit 501 is used to acquire page identification information in the page image captured by the camera module.
[0100] The retrieval unit 502 is used to retrieve and obtain at least two similar electronic pages matching the page identification information.
[0101] The information acquisition unit 503 is used to acquire the complexity information corresponding to each electronic page. The complexity information includes distinguishing feature information and complexity. The distinguishing feature information is used to represent the distinguishing features of the electronic page and other similar electronic pages. The complexity is used to represent the complexity of the obviousness of the distinguishing features.
[0102] The first determining unit 504 is used to determine the comparison times of each electronic page according to the complexity of each electronic page.
[0103] The comparison unit 505 is used to compare the page image with the distinguishing characteristic information of each electronic page multiple times according to the comparison times of each electronic page, so as to obtain multiple comparison results of each electronic page.
[0104] The second determining unit 506 is configured to determine a target electronic page from at least two similar electronic pages according to multiple comparison results corresponding to each electronic page.
[0105] In some embodiments, Figure 5 The electronic page retrieval device shown may also include a shooting unit not shown in the figure, which is used to start the camera module set in the learning device to shoot the physical page (such as a book page or a paper page, etc.) placed on the desktop to obtain a page image when receiving a preset trigger instruction. Among them, the preset trigger instruction is used to trigger the camera module to shoot, which can be any pre-set user interaction instruction. The user interaction instruction may include but is not limited to the user in any interaction mode such as voice interaction, remote control interaction, gesture interaction, image interaction, voiceprint interaction, somatosensory interaction, etc. The specific interaction mode used for input is not specifically limited in the embodiment of the present application.
[0106] In some embodiments, the identification acquisition unit 501 can be used to determine whether the page image captured by the camera module meets the preset standard. If it does not meet the preset standard, the camera module can be controlled to shoot again to capture a new page image that meets the preset standard, and then obtain the page identification information in the new page image. Among them, the preset standard can be used to characterize the clarity of the image or the completeness of the page content in the image, so as to ensure the integrity and clarity of the page image, thereby improving the efficiency and accuracy of electronic page retrieval.
[0107] In some embodiments, the comparison unit 505 can be used to pre-process the page image to obtain a processed image, and then extract features from the processed image to obtain image feature information, so that the distinguishing feature information and image feature information of each electronic page can be compared multiple times according to the comparison times of each electronic page to obtain multiple comparison results of each electronic page. The pre-processing includes but is not limited to analog to digital converter (A / D), binarization, image smoothing, transformation, enhancement, restoration and filtering, so that the page image can be digitized and the accuracy of the comparison result can be improved.
[0108] As an optional implementation, Figure 5The electronic page search device shown may also include a judgment unit (not shown) for judging whether the multiple comparison results of each electronic page show a stable trend before the second determination unit 506 determines the target electronic page from at least two similar electronic pages based on the multiple comparison results, and excluding some electronic pages whose multiple comparison results are not stable, so as to obtain the remaining electronic pages whose multiple comparison results show a stable trend. Accordingly, the second determination unit 506 may be specifically used to determine the target electronic page from at least two similar electronic pages based on the multiple comparison results of each remaining electronic page.
[0109] Further optionally, if each comparison result includes the similarity between the electronic page and the page image, the judgment unit is used to judge whether the multiple comparison results of each electronic page show a stable trend. Specifically, it can be judged whether the similarity between the electronic page and the page image represented by each comparison result of each electronic page is within a preset similarity range; if so, it is judged that the multiple comparison results show a stable trend; otherwise, it is judged that the multiple comparison results do not show a stable trend.
[0110] Or optionally, if each comparison result includes a probability value that the electronic page to which it belongs is the target electronic page, the judgment unit is used to judge whether the multiple comparison results of each electronic page show a stable trend. Specifically, it can be judged whether the probability value of the electronic page represented by each comparison result of each electronic page is the target electronic page is within a preset probability range. If so, it is judged that the multiple comparison results show a stable trend; otherwise, it is judged that the multiple comparison results do not show a stable trend.
[0111] Through this implementation, by judging the stability of multiple comparison results, the target electronic page is determined only from electronic pages whose multiple comparison results show a stable trend, which can narrow the range of at least two similar electronic pages and further improve the retrieval accuracy of electronic pages.
[0112] As an optional implementation, Figure 5The electronic page retrieval device shown may also include a recommendation unit (not shown) for outputting the associated learning content corresponding to the target electronic page after the second determination unit 506 determines the target electronic page from at least two similar electronic pages based on multiple comparison results. The associated learning content may include but is not limited to video materials, text materials, or voice materials. Further optionally, the recommendation unit may be specifically used to identify whether there is a designated partial area in the page image, and if so, obtain the position information of the designated partial area in the page image, and obtain the output of the associated learning content corresponding to the designated partial area based on the position information of the designated partial area. Through this implementation, the associated learning content can be output and recommended to the user for learning, thereby improving the user experience.
[0113] It can be seen that the device provided in the above embodiment is implemented. When multiple electronic pages are retrieved, the number of comparisons of each electronic page is adaptively determined according to the complexity of different electronic pages, and then the page image is compared with each electronic page multiple times according to the number of comparisons of each electronic page. The electronic page can be determined based on distinguishing feature information and multiple comparisons, thereby improving the retrieval accuracy of the electronic page.
[0114] See also Figure 6 , Figure 6 is a schematic diagram of the structure of another electronic page search device disclosed in an embodiment of the present application. Figure 6 The electronic page retrieval device shown is Figure 5 The retrieval device of the electronic page shown is optimized and obtained Figure 5 In comparison, Figure 6 The electronic page retrieval device shown may also include an output unit 507, a locking unit 508, a scanning unit 509, a marking unit 510 and a determination unit 511; wherein,
[0115] The output unit 507 is used to output prompt information for marking the target electronic page as a locked page after the second determination unit 506 determines the target electronic page from at least two similar electronic pages based on multiple comparison results, if the complexity corresponding to the target electronic page reaches a preset complexity threshold.
[0116] The locking unit 508 is configured to mark the target electronic page as a locked page upon receiving a user confirmation instruction for the prompt information.
[0117] In some embodiments, the output unit 507 may be used to output prompt information for marking the target electronic page as a locked page by outputting voice prompt information for marking the target electronic page as a locked page in voice form, or by popping up text prompt information for marking the target electronic page as a locked page on an electronic screen.
[0118] Optionally, the first determining unit 504 may be configured to determine the number of comparisons for each electronic page according to the complexity corresponding to each electronic page when at least two similar electronic pages are not marked as locked pages.
[0119] In some embodiments, the first determination unit 504 can be used to determine the number of locked electronic pages in at least two similar electronic pages when there is a locked electronic page marked as a locked page in at least two similar electronic pages. If the number of locked electronic pages is equal to one, the locked electronic page is determined to be the target electronic page; if the number of locked electronic pages is greater than one, the locked electronic page is subjected to the step of determining the number of comparisons of each electronic page according to the complexity corresponding to each electronic page. Thus, the false positive rate can be reduced by locking the electronic pages, and the search efficiency and accuracy of the electronic pages can be further improved.
[0120] As an optional implementation, the locking unit 508 may include the following subunits:
[0121] The first acquisition subunit 5081 is used to acquire the book identification information of the electronic book where the target electronic page is located when receiving a user confirmation instruction for the prompt information.
[0122] The locking subunit 5082 is used to lock the electronic book according to the book identification information, so that each electronic page included in the electronic book is marked as a locked page.
[0123] Optionally, Figure 6 The electronic page retrieval device shown may also include the following units:
[0124] The scanning unit 509 is used to scan multiple electronic pages stored in the database to obtain multiple page sets before the identification acquisition unit 501 acquires the page identification information in the page image captured by the camera module; wherein the multiple page sets are different, and each page set includes at least two electronic pages with the same book identification information and the same page identification information, and the first similarity of at least two electronic pages reaches a first specified threshold.
[0125] The marking unit 510 is used to mark the complexity of each electronic page in each page set to obtain complexity information of each electronic page.
[0126] Further optionally, the marking unit 510 may specifically include the following subunits:
[0127] The second acquisition subunit 5101 is used to obtain distinguishing feature information of each electronic page in each page set and other similar electronic pages in the page set to which it belongs; and, based on the distinguishing feature information, obtain the degree of obviousness of the distinguishing features represented by the distinguishing feature information; wherein the higher the degree of obviousness, the more distinguishing features there are between the electronic page and other similar electronic pages in the page set to which it belongs.
[0128] The marking subunit 5102 is used to mark the complexity of each electronic page according to the degree of prominence of the distinguishing features, so as to obtain the complexity of each electronic page.
[0129] The third acquisition subunit 5103 is used to use the distinguishing feature information and the complexity as the complexity information of the corresponding electronic page.
[0130] In some embodiments, the second determining unit 506 may include the following subunits:
[0131] The determination subunit 5061 is used to determine the second similarity between the electronic page to which the multiple comparison results belong and the page image according to the multiple comparison results when the multiple comparison results meet the preset condition.
[0132] The trigger sub-unit 5062 is used to trigger the above-mentioned first determination unit 504 to repeatedly perform the above-mentioned operation of determining the number of comparisons of each electronic page according to the complexity corresponding to each electronic page, for the electronic pages whose second similarity reaches the second specified threshold when the number of electronic pages whose second similarity reaches the second specified threshold is greater than or equal to two, until the number of electronic pages whose second similarity with the page image reaches the second specified threshold is one, and the unique electronic page is determined to be the target electronic page.
[0133] In some embodiments, Figure 6 The retrieval device for the electronic page shown may also include a determination unit 511, which is used to calculate the variance value corresponding to the multiple comparison results of each electronic page based on the multiple comparison results corresponding to each electronic page; when the variance value is within a preset range, it is determined that the multiple comparison results meet the preset conditions, and the above-mentioned determination subunit 5061 is triggered to perform the above-mentioned operation of determining the second similarity between the electronic page to which the multiple comparison results belong and the page image based on the multiple comparison results.
[0134] It can be seen that the implementation of the device provided in the above embodiment can determine the electronic page based on the distinguishing feature information and multiple comparison methods, thereby improving the retrieval accuracy of the electronic page.
[0135] In addition, upon receiving a user instruction to lock a certain electronic page, the textbook version most recently used by the user is considered to be the textbook version to which the electronic page belongs, and the textbook version to which the electronic page belongs is locked, so that when the electronic page is searched again subsequently, the locked textbook version can be prioritized as the search range, thereby refining the search scope of the electronic page and improving the retrieval efficiency and accuracy of the electronic page.
[0136] In addition, after obtaining the multiple comparison results of each electronic page, it is possible to further judge the data fluctuation degree of the multiple comparison results. If the data fluctuation degree is small and the multiple comparison results are judged to be relatively stable, then the second similarity between the electronic page to which the multiple comparison results belong and the page image is determined based on the multiple comparison results to perform a threshold judgment to further narrow the range of the electronic pages until a unique final search result is determined and then output, thereby further improving the search accuracy of the electronic pages, ensuring the search effect of the electronic pages, and improving the user experience.
[0137] See also Figure 7 , Figure 7 is a structural diagram of another learning device disclosed in the embodiment of the present application. Figure 7 As shown, the learning device may include:
[0138] A memory 701 storing executable program codes;
[0139] a processor 702 coupled to the memory 701;
[0140] The processor 702 calls the executable program code stored in the memory 701 to execute the electronic page retrieval method described in the above embodiments.
[0141] It should be noted that Figure 7 The learning device shown may also include power supply, input button, speaker, microphone, screen, RF circuit, Wi-Fi module, Bluetooth module, sensor and other components not shown, which are not described in this embodiment. It may also include speaker module, camera module, display screen, light projection module, battery module, wireless communication module (such as mobile communication module, WIFI module, Bluetooth module, etc.), sensor module (such as proximity sensor, pressure sensor, etc.), input module (such as microphone, button) and user interface module (such as charging interface, external power supply interface, card slot, wired headset interface, etc.) and other components not shown.
[0142] An embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the electronic page retrieval method described in the above embodiments.
[0143] The embodiments of the present application further disclose a computer program product, wherein when the computer program product is executed on a computer, the computer is enabled to execute part or all of the steps of the methods in the above method embodiments.
[0144] The embodiments of the present application also disclose an application publishing platform, wherein the application publishing platform is used to publish a computer program product, wherein when the computer program product runs on a computer, the computer executes part or all of the steps of the method in the above method embodiments.
[0145] It should be understood that "one embodiment" or "some embodiments" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for the present application.
[0146] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0147] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0148] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0149] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the above-mentioned methods of various embodiments of the present application.
[0150] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.
[0151] Those skilled in the art can understand that some or all of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.
[0152] The above is a detailed introduction to an electronic page retrieval method and device, a learning device, and a readable storage medium disclosed in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for a person skilled in the art, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for retrieving an electronic page, characterized in that: include: Obtaining page identification information from the page image captured by the camera module; Retrieving and obtaining at least two similar electronic pages matching the page identification information; the at least two similar electronic pages include an electronic page having the same textbook number and the same page number as the physical page represented by the page image; Obtaining complexity information corresponding to each of the electronic pages; the complexity information includes distinguishing feature information and complexity, the distinguishing feature information is used to characterize the distinguishing features of the electronic page and other similar electronic pages of different versions but with the same textbook number and the same page number, and the complexity is used to characterize the obviousness of the distinguishing features; Determining the number of comparisons for each of the electronic pages according to the complexity of each of the electronic pages; According to the comparison times of each electronic page, the image feature information of the page image is compared with the distinguishing feature information of each electronic page for multiple times to obtain multiple comparison results corresponding to each electronic page, wherein the image feature information of the page image is obtained by extracting features from the page image; According to the multiple comparison results corresponding to each of the electronic pages, a target electronic page is determined from the at least two similar electronic pages.
2. The method according to claim 1, characterized in that Determining the number of comparisons of each electronic page according to the complexity of each electronic page includes: If the at least two similar electronic pages are not marked as locked pages, determining the number of comparisons for each of the electronic pages according to the complexity of each of the electronic pages; And, after determining the target electronic page from the at least two similar electronic pages according to the multiple comparison results corresponding to each of the electronic pages, the method further includes: If the complexity corresponding to the target electronic page reaches a preset complexity threshold, outputting prompt information for prompting the target electronic page to be marked as the locked page; When a user confirmation instruction for the prompt information is received, the target electronic page is marked as the locked page.
3. The method according to claim 2, characterized in that The step of marking the target electronic page as the locked page includes: Acquire the book identification information of the electronic book where the target electronic page is located; The electronic book is locked according to the book identification information, so that each electronic page included in the electronic book is marked as the locked page.
4. The method according to claim 1, characterized in that: Before acquiring the page identification information in the page image captured by the camera module, the method further includes: Scanning multiple electronic pages stored in a database to obtain multiple page sets; wherein the multiple page sets are different, each of the page sets includes at least two electronic pages having the same book identification information and the same page identification information, and the first similarity of the at least two electronic pages reaches a first specified threshold; A complexity mark is performed on each of the electronic pages in each of the page sets to obtain complexity information of each of the electronic pages.
5. The method according to claim 4, characterized in that The step of marking the complexity of each electronic page in each of the page sets to obtain the complexity information of each electronic page includes: Obtaining distinguishing characteristic information of each electronic page in each page set and other similar electronic pages in the page set to which it belongs; According to the distinguishing feature information, obtaining the degree of obviousness of the distinguishing feature represented by the distinguishing feature information; wherein the higher the degree of obviousness, the more distinguishing features there are between the electronic page and other similar electronic pages in the page set to which it belongs; Marking the complexity of each of the electronic pages according to the degree of prominence of the distinguishing features to obtain the complexity of each of the electronic pages; The distinguishing feature information and the complexity are used as the complexity information of the corresponding electronic page.
6. The method according to any one of claims 1 to 5, characterized in that: The step of determining a target electronic page from the at least two similar electronic pages according to the multiple comparison results corresponding to each of the electronic pages includes: If the multiple comparison results meet the preset condition, determining a second similarity between the electronic page to which the multiple comparison results belong and the page image according to the multiple comparison results; If the number of electronic pages whose second similarity reaches the second specified threshold is greater than or equal to two, the step of determining the number of comparisons for each electronic page based on the complexity of each electronic page is repeated for the electronic pages whose second similarity reaches the second specified threshold, until the number of electronic pages whose second similarity with the page image reaches the second specified threshold is one, and the unique electronic page is determined to be the target electronic page.
7. The method according to claim 6, characterized in that The method further comprises: Calculate the variance value of the multiple comparison results of each electronic page according to the multiple comparison results corresponding to each electronic page; If the variance value meets the preset range, it is determined that the multiple comparison results meet the preset conditions.
8. A device for searching electronic pages, characterized in that: include: The identification acquisition unit is used to acquire page identification information in the page image captured by the camera module; A retrieval unit, configured to retrieve and obtain at least two similar electronic pages matching the page identification information; the at least two similar electronic pages include an electronic page having the same textbook number and the same page number as the physical page represented by the page image; An information acquisition unit is used to acquire complexity information corresponding to each of the electronic pages; the complexity information includes distinguishing feature information and complexity, the distinguishing feature information is used to characterize the distinguishing features of the electronic page and other similar electronic pages of different versions but with the same textbook number and the same page number, and the complexity is used to characterize the obviousness of the distinguishing features; A first determining unit, configured to determine the number of comparisons of each electronic page according to the complexity of each electronic page; a comparison unit, configured to compare the image feature information of the page image with the distinguishing feature information of each electronic page for multiple times according to the comparison times of each electronic page, so as to obtain multiple comparison results of each electronic page, wherein the image feature information of the page image is obtained by extracting features from the page image; The second determining unit is used to determine a target electronic page from the at least two similar electronic pages according to the multiple comparison results corresponding to each of the electronic pages.
9. A learning device, characterized in that: include: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the electronic page retrieval method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the electronic page retrieval method according to any one of claims 1 to 7.
