An information processing method, device and computer readable storage medium

Abstract

Embodiments of the present application disclose an information processing method, device and computer readable storage medium; after displaying an information processing page, the information processing page comprises an information display canvas and an information entry interface, the information display canvas comprises at least one interactive region, receives to-be-processed information entered in the information entry interface, identifies the type of the to-be-processed information, then, according to the identification result, filters out a target interactive control corresponding to the type of the to-be-processed information from a preset interactive control set, adds the to-be-processed information and the target interactive control to the interactive region, and displays on the information display canvas; the scheme can greatly reduce the information processing time in the interactive process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to an information processing method and device and a computer readable storage medium. BACKGROUND

[0002] In recent years, with the development of Internet technology, the interaction between people has become very convenient, especially the interaction on the social platform, such as likes. As a kind of emotional interaction, the single interaction mode of the like makes the like interaction mode single. In view of the single interaction mode, the user currently adds a label on the dynamic content, and the label is manually matched with an interaction control style in the background. After the matching is completed, the label is displayed.

[0003] In the research and practice of the prior art, the inventor of the present application found that the label information is processed based on the manual background, which consumes a lot of time. In addition, from the perspective of the user, the label needs to be manually added during the publication of the dynamic content, which also increases the operation time. Therefore, the information processing time in the interaction process is greatly increased. SUMMARY

[0004] The embodiments of the present application provide an information processing method, device and computer readable storage medium. The information processing time in the interaction process can be reduced.

[0005] An information processing method comprises the following steps:

[0006] An information processing page is displayed, the information processing page comprises an information display canvas and an information entry interface, and the information display canvas comprises at least one interaction area;

[0007] The information to be processed entered in the information entry interface is received;

[0008] The type of the information to be processed is identified;

[0009] According to the identification result, a target interaction control corresponding to the type of the information to be processed is selected from a preset interaction control set;

[0010] The information to be processed and the target interaction control are added to the interaction area, and displayed on the information display canvas.

[0011] Optionally, the embodiments of the present application further provide another information processing method, which comprises the following steps:

[0012] An information processing page is displayed, the information processing page comprises an information sharing control and an information display canvas, and the information display canvas comprises at least one interaction area;

[0013] When a triggering operation for the information sharing control is received, an information publishing page is displayed, the information publishing page comprising at least one information input control and a publishing control;

[0014] When information to be processed is input through the information input control is received, the information to be processed is displayed on the information publishing page;

[0015] When a triggering operation for the publishing control is received, the information to be processed is displayed on the information display canvas of the information processing page, and the target interactive control corresponding to the information to be processed is displayed on the interactive region;

[0016] When a triggering operation for the target interactive control is detected, an interaction record is displayed on the interactive region.

[0017] Correspondingly, an information processing apparatus is provided in an embodiment of the present application, comprising:

[0018] a display unit configured to display an information processing page, the information processing page comprising an information display canvas and an information entry interface, the information display canvas comprising at least one interactive region;

[0019] a receiving unit configured to receive information to be processed entered on the information entry interface;

[0020] an identifying unit configured to identify the type of the information to be processed;

[0021] a screening unit configured to screen, according to the identification result, a target interactive control corresponding to the type of the information to be processed from a preset interactive control set;

[0022] a processing unit configured to add the information to be processed and the target interactive control to the interactive region and display them on the information display canvas.

[0023] Optionally, an information processing apparatus is also provided in an embodiment of the present application, comprising:

[0024] an information processing display unit configured to display an information processing page, the information processing page comprising an information sharing control and an information display canvas, the information display canvas comprising at least one interactive region;

[0025] a publishing page display unit configured to display, when a triggering operation for the information sharing control is received, an information publishing page, the information publishing page comprising at least one information input control and a publishing control;

[0026] an information to be processed display unit configured to display, when information to be processed is input through the information input control is received, the information to be processed on the information publishing page;

[0027] an interactive display unit, configured to display the to-be-processed information on an information display canvas of the information processing page and display a target interactive control corresponding to the to-be-processed information on the interactive region when a triggering operation for the publishing control is received;

[0028] an interaction record display unit, configured to display an interaction record on the interactive region when a triggering operation for the target interactive control is detected.

[0029] Optionally, in some embodiments, the identification unit can be specifically configured to extract at least one to-be-identified image from the to-be-processed information, identify the content of the to-be-identified image, and determine the type of the to-be-processed information according to the identification result.

[0030] Optionally, in some embodiments, the identification unit can be specifically configured to, when there is one to-be-identified image in the to-be-processed information, identify the content of the to-be-identified image by using a trained identification model to obtain the identification result; and when there are at least two to-be-identified images in the to-be-processed information, identify the content of the to-be-identified images by using the trained identification model to obtain at least two initial identification results, and fuse the initial identification results to obtain the identification result.

[0031] Optionally, in some embodiments, the identification unit can be specifically configured to classify the initial identification results, obtain a weighting coefficient corresponding to the initial identification result according to the classification result, weight the initial identification result based on the weighting coefficient, and fuse the weighted initial identification results to obtain the identification result.

[0032] Optionally, in some embodiments, the identification unit can be specifically configured to perform feature extraction on the to-be-identified image to obtain local features of the to-be-identified image, perform feature coding on the local features to obtain coded local features, fuse the coded local features to obtain fused features, and identify the content of the to-be-identified image based on the fused features.

[0033] Optionally, in some embodiments, the identification unit can be specifically configured to collect a plurality of image samples, the image samples including images with labeled identification results, predict the identification results of the image samples by using a preset identification model to obtain predicted identification results of the image samples, and converge the preset identification model according to the predicted identification results and the labeled identification results to obtain the trained identification model.

[0034] Optionally, in some embodiments, the screening unit can be specifically configured to acquire the type of the interactive control in the preset interactive control set; match the type of the to-be-processed information with the type of the interactive control; and screen out the target interactive control corresponding to the type of the to-be-processed information from the preset interactive control set according to the matching result.

[0035] Optionally, in some embodiments, the processing unit can be specifically configured to acquire the first receiving time of the to-be-processed information; identify the target interaction area corresponding to the first receiving time in the interaction area; add the to-be-processed information and the target interactive control to the target interaction area; and display the content of the target interaction area on the information display canvas.

[0036] Optionally, in some embodiments, the processing unit can be specifically configured to query the display content of the interaction area; when the interaction area has display content, acquire the second receiving time at which the interaction area receives the display content; sort the first receiving time and the second receiving time; and identify the target interaction area corresponding to the first receiving time in the interaction area according to the sorting result.

[0037] Optionally, in some embodiments, the processing unit can be specifically configured to divide the target interaction area into an information display area and an interaction area; add the to-be-processed information to the information display area; and add the target interactive control to the interaction area.

[0038] Optionally, in some embodiments, the processing unit can be specifically configured to generate an interaction record when detecting a trigger operation on the target interactive control; and display the interaction record in the interaction area.

[0039] Optionally, in some embodiments, the processing unit can be specifically configured to acquire the identity of a terminal performing a trigger operation on the target interactive control and count once when detecting the trigger operation; accumulate the count to obtain a total count; and take the total count and the identity as an interaction record.

[0040] In addition, an electronic device is also provided in the embodiments of the present application, which comprises a processor and a memory, the memory stores an application program, and the processor is configured to run the application program in the memory to implement the information processing method provided in the embodiments of the present application.

[0041] In addition, a computer readable storage medium is also provided in the embodiments of the present application, the storage medium stores a plurality of instructions, the instructions are suitable for being loaded by a processor to execute the steps in any one of the information processing methods provided in the embodiments of the present application.

[0042] After displaying the information processing page, the information processing page includes an information display canvas and an information entry interface, the information display canvas includes at least one interactive area, receives the to-be-processed information entered in the information entry interface, identifies the type of the to-be-processed information, then according to the identification result, filters out the target interactive control corresponding to the type from the preset interactive control set, adds the to-be-processed information and the target interactive control to the interactive area, and displays on the information display canvas; since the scheme automatically identifies the type of the to-be-processed information after receiving the to-be-processed information, directly matches the target interactive control according to the identified type, does not need to manually match, and does not need the user to manually add a label in the publishing process, therefore, the time for information processing in the interactive process can be greatly reduced. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0044] Figure 1 is a scene schematic diagram of the information processing method provided by the embodiments of the present application;

[0045] Figure 2 is a flow schematic diagram of the information processing method provided by the embodiments of the present application;

[0046] Figure 3 is a schematic diagram of the information processing page provided by the embodiments of the present application;

[0047] Figure 4 is a schematic diagram of the information processing page provided by the embodiments of the present application;

[0048] Figure 5 is a schematic diagram of the information entry page provided by the embodiments of the present application;

[0049] Figure 6 is a structural schematic diagram of the simple identification module of the identification model provided by the embodiments of the present application;

[0050] Figure 7 is a structural schematic diagram of the dimension reduction identification module of the identification model provided by the embodiments of the present application;

[0051] Figure 8 is a schematic diagram of the preset interactive control style provided by the embodiments of the present application;

[0052] Figure 9 is a schematic diagram of the target interactive area provided by the embodiments of the present application;

[0053] Figure 10 is a schematic diagram of the interactive record display provided by an embodiment of the present application;

[0054] Figure 11 is another schematic diagram of the interactive record display provided by an embodiment of the present application;

[0055] Figure 12 is another flowchart of the information processing method provided by an embodiment of the present application;

[0056] Figure 13 is a schematic diagram of the information publishing page provided by an embodiment of the present application;

[0057] Figure 14 is a flowchart of the target interactive control display provided by an embodiment of the present application;

[0058] Figure 15 is another flowchart of the information processing provided by an embodiment of the present application;

[0059] Figure 16 is a structural diagram of the information processing device provided by an embodiment of the present application;

[0060] Figure 17 is a structural diagram of the identification unit of the information processing device provided by an embodiment of the present application;

[0061] Figure 18 is a structural diagram of the screening unit of the information processing device provided by an embodiment of the present application;

[0062] Figure 19 is another structural diagram of the information processing device provided by an embodiment of the present application;

[0063] Figure 20 is another structural diagram of the information processing provided by an embodiment of the present application;

[0064] Figure 21 is a structural diagram of the electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0065] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0066] The embodiment of the application provides an information processing method, device and computer readable storage medium. The information processing device can be integrated in an electronic device, which can be a server or a terminal or the like.

[0067] For example, referring to Figure 1 For example, the information processing device is integrated in an electronic device, and an information processing page is displayed, the information processing page comprising an information display canvas and an information input interface, the information display canvas comprising at least one interactive region, receiving to-be-processed information input in the information input interface, identifying the type of the to-be-processed information, filtering out target interactive controls corresponding to the type from a preset interactive control set according to the identification result, adding the to-be-processed information and the target interactive controls to the interactive region, and displaying on the information display canvas.

[0068] The following will be described in detail. It should be noted that the sequence of the following embodiments is not limited as the preferred sequence of the embodiments.

[0069] The embodiment will be described from the perspective of the information processing device, which can be integrated in an electronic device, which can be a terminal or the like. The terminal can include a tablet computer, a notebook computer, a personal computer (PC), and the like.

[0070] An information processing method comprises the following steps.

[0071] An information processing page is displayed, the information processing page comprising an information display canvas and an information input interface, the information display canvas comprising at least one interactive region, receiving to-be-processed information input in the information input interface, identifying the type of the to-be-processed information, filtering out target interactive controls corresponding to the type from a preset interactive control set according to the identification result, adding the to-be-processed information and the target interactive controls to the interactive region, and displaying on the information display canvas.

[0072] As shown in Figure 2 The specific process of the information processing method is as follows.

[0073] 101. An information processing page is displayed.

[0074] The information processing page comprises an information display canvas and an information input interface, and the information display canvas comprises at least one interactive region.

[0075] The so-called information display canvas can be a display medium for displaying information streams. The information stream can be a scrollable and continuously updated content stream, and the content in the content stream can be text, images, language, or video. For example, the information display canvas can include multiple interactive areas, each of which is independent of each other, and can display information content and interactive controls for commenting on or liking the information content.

[0076] For example, the user operates through the client's login page, thereby triggering the display of the information processing page, the information processing page is as follows: Figure 3 For example, the user can enter the preset identity information and other information on the login page through the client, and after passing the verification, the information processing page is triggered, such as Figure 4 As shown, the user can also directly trigger the display information processing page through the client.

[0077] For example, in Figure 3 The information processing page may include a search control. In the application embodiment, the control may be expressed in various forms, such as an input box, an icon, and a button. After the user enters the content to be searched in the search input box, based on the triggering operation of the search control, the processed information related to the search content can be displayed on the information display canvas of the information processing page. The information processing page may also include a user personal center control. When the user triggers the control, a personal information page matching the user's personal identity information may be displayed. The personal information page may include the identity information, pending information, and / or processed information stored by the user to the application through the client. The personal center control may also trigger a login page. When the user successfully logs in through the login page, the personal identity information, pending information, and / or processed information may be displayed. The information processing page may also include an information entry interface. The entry interface may be "transmit" or "upload", etc., which is mainly used for the user to upload the pending information to the information processing device for processing through the interface, so that the pending information can be displayed on the information display canvas for the user and other users to browse. The information processing page may also include a classification control. When the user triggers the classification control, the information processed or displayed on the information display canvas can be classified and a classification list can be generated. When the user triggers a type in the classification list, the displayed information corresponding to that type can be displayed on the information display canvas. The information processing page may also include a follow control. When the user successfully applies through the login page, the user triggers the follow control, and the processed or displayed information published by other users corresponding to the user's identity in the information processing device can be displayed on the information display canvas.

[0078] It is emphasized that the processed information in the information display canvas can be dynamically updated, and the time of user publishing is taken as a reference to realize dynamic updating. For example, A user publishes a first to-be-processed information at 10:00 am, and the information is displayed on the information display canvas after being processed by the information processing apparatus. A user or another user publishes a second to-be-processed information at 10:10 am, and the information is displayed on the information display canvas after being processed by the information processing apparatus. At this time, the information on the information display canvas changes from one to two. The display order of the second to-be-processed information published later can be prior to that of the first to-be-processed information. Alternatively, it can be understood that the to-be-processed information published later is displayed at the head of the information display canvas.

[0079] 102. receiving the to-be-processed information entered in the information entry interface.

[0080] The to-be-processed information can be information that a user wants to enter through the client and publish to the information display canvas. The content of the information can be any one of text, image, audio, and / or video, or a combination of multiple types. For example, the information can be a combination of image and text, or a combination of image, video, and text.

[0081] For example, the to-be-processed information entered by the user by triggering the information entry interface control of the information processing page is received. For example, the user can trigger the information entry interface control of the information processing page. At this time, the information entry page can be displayed, as shown in FIG. 6. Figure 5 The information entry page can include a text entry control, an image entry control, an expression entry control, an image preview control, a video entry control, an audio entry control, a cancel control, and a publish control, etc. The user can enter the to-be-processed information by operating the above controls. For example, the user enters the text to be entered through the text entry control, and enters the image to be entered through the image entry control. After the entry is completed, a preview or thumbnail of the entered image can be generated on the information entry page. If the user is not satisfied with the preview or thumbnail and needs to replace or change the position, the image preview control can be triggered to delete or change the position. The action of deleting can be performed by a delete button of the image preview control or by long pressing the preview or thumbnail. The action of changing the position can be performed by dragging the image to change the position. The user can also enter the expression through the expression entry control. When the user enters the information to be entered through various entry controls of the information entry page, if the user is not satisfied with the entered to-be-processed information, the cancel control can be triggered to return to the information processing page. If the user is satisfied with the entered to-be-processed information, the publish control can be triggered to generate the to-be-processed information, and the information processing apparatus receives the to-be-processed information.

[0082] 103. identifying the type of the to-be-processed information.

[0083] The type of the to-be-processed information can be a type of evaluating content of the to-be-processed information. For example, if the to-be-processed information is news or views on sports, the type of the to-be-processed information can be considered as sports. For another example, if the to-be-processed information is a promotional image of a game, the type of the to-be-processed information can be considered as the game.

[0084] For example, an image type in the to-be-processed information can be identified, and then the type of the to-be-processed information can be determined. Specifically, the following can be performed:

[0085] S1, extracting at least one to-be-identified image from the to-be-processed information.

[0086] For example, the content of the to-be-processed information is classified by a content format. According to a classification result, at least one to-be-identified image input by a user through an image input control is extracted from the to-be-processed information. For example, the user can input a file in a format of jpg, bmp, tif (formats corresponding to image data) through the image input control. The content of the to-be-processed information is classified by a format. For example, content in a text format is classified as a text category, content in an audio format is classified as an audio category, content in a video format is classified as a video category, and content in an image format is classified as an image category. According to the classification result, at least one to-be-identified image is extracted from the to-be-processed information.

[0087] S2, identifying the content of the to-be-identified image.

[0088] (1) When there is one to-be-identified image in the to-be-processed information, the content of the to-be-identified image is identified by using a trained recognition model, and an identification result is obtained.

[0089] For example, when there is one to-be-identified image in the to-be-processed information, the content of the to-be-identified image is identified by using a trained recognition model. The specific identification process can be as follows:

[0090] C1, extracting features of the to-be-identified image to obtain local features of the to-be-identified image.

[0091] For example, a convolutional neural network can be used to extract bottom-layer features by setting a fixed step and scale in the trained recognition model. For example, an Inception simple module (a simple recognition module) of a GoogleNet model (an image recognition model) can be used to extract bottom-layer features, such as Figure 6As shown, the common local features of the image to be recognized are extracted in advance by the Inception simple module, such as Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradient (HOG), and / or Local Bianray Pattern (LBP) and the like.

[0092] It is emphasized that if the Inception simple module is used, the pooling layer will not change the number of feature channels, and after splicing, the number of feature channels will be large, and after several layers of such module stacking, the number of channels will be larger and larger, resulting in an increase in parameters and calculation amount. Therefore, in order to improve this shortcoming, the Inception dimension reduction module (dimension reduction recognition module) can also be used, such as Figure 7 As shown, the Inception dimension reduction module introduces three 1x1 convolution layers for dimension reduction. The so-called dimension reduction is to reduce the number of channels, and the 1x1 convolution used can also correct the linear features.

[0093] C2, feature encoding is performed on the local features to obtain encoded local features.

[0094] The feature encoding can be an encoding action of using a feature transformation algorithm to encode the bottom features.

[0095] For example, the extracted local features are mainly bottom features, and the bottom features contain a large amount of redundancy and noise. In order to improve the robustness of feature expression, feature encoding needs to be performed on the local features to obtain encoded local features. For example, vector quantization encoding, sparse coding, local linear constraint coding, Fisher vector coding and the like can be used for encoding.

[0096] C3, the encoded local features are fused to obtain fused features.

[0097] The feature fusion can also be referred to as feature convergence, which mainly refers to taking the maximum value or average value of each dimension feature in a space range to obtain a certain feature invariable feature expression.

[0098] The fused features can be a fixed dimension vector describing the image to be recognized.

[0099] For example, the maximum value or the average value of each dimension feature of the coded local feature in a certain spatial range can obtain the feature expression of the feature of the to-be-identified image without deformation. For example, the coded local feature can be fused by using the pyramid feature matching mode to obtain the fused feature. Specifically, the to-be-identified image can be uniformly divided into blocks, feature fusion is performed on each block to obtain the fused feature of each block, and then the fused feature of each block is fused again to obtain the fused feature of the to-be-identified image, that is, the fixed-dimension feature vector of the to-be-identified image.

[0100] C4, identifying the content of the to-be-identified image based on the fused feature.

[0101] For example, the fixed-dimension feature vector of the to-be-identified image is classified by using a classifier to obtain the identification result of the content of the to-be-identified image, which can be the content of the to-be-identified image and the type corresponding to the content, and the identification process is completed. For example, the fixed-dimension feature vector of the to-be-identified image can be classified by using a support vector machine (SVM) and a random forest method.

[0102] (2) When there are at least two to-be-identified images in the to-be-processed information, the content of the to-be-identified image is identified by using the trained identification model to obtain at least two initial identification results, and the initial identification results are fused to obtain the identification result.

[0103] For example, when there are at least two to-be-identified images in the to-be-processed information, the content of the to-be-identified image is identified by using the trained identification model, the identification process of the to-be-identified image is described in steps C1-C4, at least two initial identification results are obtained, for example, when there are three to-be-identified images in the to-be-processed information, the three to-be-identified images are identified respectively to obtain the identification results of the three to-be-identified images, which are the probability value of type A, the probability value of type B and the probability value of type C. The initial identification results are classified, for example, type A is a scene image of a game, and types B and C are character images of a game, and the initial identification results can be classified into two categories: game scene and game character image. According to the classification result, the weighting coefficients corresponding to the initial identification results are obtained, for example, the preset weighting coefficient of the game scene is 0.7, and the weighting coefficient of the game character is 0.3. According to the weighting coefficients, the initial identification results are weighted respectively, and the weighted initial identification results are fused to obtain the identification result. For example, the maximum value of the probability value of type A, the probability value of type B and the probability value of type C can be selected as the identification result, or the three identification results can be comprehensively analyzed to obtain the type of the to-be-identified image as a game.

[0104] The trained recognition model can be trained by a plurality of image samples. Specifically, the trained recognition model can be trained by other devices and provided to the information processing apparatus, or the information processing apparatus can train the trained recognition model by itself. Before the step of "recognizing the to-be-recognized image by using the trained recognition model", the information processing method can further include the following steps:

[0105] (1) Collect a plurality of image samples, the image samples including images with labeled recognition results.

[0106] For example, a plurality of images can be collected as original image samples by a database, a network, and an image collection device. Then, the original image samples are preprocessed, such as de-duplication, cropping, rotation, and / or flipping, to obtain image samples that meet the input standards of the preset recognition model. Then, the preprocessed image samples are labeled by type to obtain labeled image samples.

[0107] (2) The recognition result of the image sample is predicted by using the preset recognition model to obtain a predicted recognition result of the image sample.

[0108] For example, the preset recognition model is used to extract features of the image sample to obtain local features of the image sample. The local features are encoded to obtain encoded local features. The encoded local features are fused to obtain fused features. Based on the fused features, the image sample is recognized to obtain a predicted result of the image sample.

[0109] (3) The preset recognition model is converged according to the predicted recognition result and the labeled recognition result to obtain a trained recognition model.

[0110] For example, the preset recognition model can be converged according to the predicted recognition result and the labeled recognition result by using an interpolation loss function to obtain a trained recognition model. For example, the preset recognition model can be converged as follows:

[0111] The Dice function (a loss function) is used to adjust parameters for feature fusion in the preset recognition model according to the labeled recognition result and the predicted recognition result of the image sample to obtain a trained recognition model.

[0112] Optionally, to improve the accuracy of the context features, in addition to the Dice function, other loss functions such as a cross-entropy loss function can be used for convergence. Specifically, the preset recognition model can be converged as follows:

[0113] The parameters for feature fusion in the preset recognition model are adjusted according to the recognition result labeled by the image sample and the predicted recognition result by using a cross-entropy loss function, and the parameters for feature fusion in the preset recognition model are adjusted according to the labeled result and the predicted recognition result of the image sample by using an interpolation loss function, to obtain a trained recognition model

[0114] S3. According to the recognition result, the type of the information to be processed is confirmed.

[0115] For example, according to the recognition result of the image to be recognized, the type of the information to be processed is confirmed. The recognition result can be the content of the image to be recognized and the type corresponding to the content. The type of the content of the image to be recognized can be obtained, and the type of the content of the image to be recognized and the type of the information to be processed are related to each other. For example, according to the type of the content of the image to be recognized, matching is performed in a preset type set of information to be processed. For example, the type of the content of the image to be recognized is a game, and the preset type set of information to be processed can include games, dances, music, animations, paintings, and the like. According to the type of the content of the image to be recognized, matching is performed in the preset type set of information to be processed. It can be confirmed that the type of the information to be processed is a game. For example, the content of the image to be recognized is a promotional image of a piece of music, and it can be confirmed that the type of the information to be processed is music.

[0116] 104. According to the recognition result, the target interactive control corresponding to the type of the information to be processed is selected from the preset interactive control set.

[0117] The interactive control can be a control for user interaction. For example, taking like as an example, the interactive control can be a like button, and the user triggers the like button to indicate that the user likes the displayed information.

[0118] For example, the type of the interactive control in the preset interactive control set is obtained. For example, the style or type of each interactive control in the preset interactive control set is obtained, and each style or type corresponds to an information type. For example, as shown in Figure 8 The type of the information to be processed can be matched with the type of the interactive control. For example, taking the type of the information to be processed as a game as an example, the interactive control style corresponding to the game type is matched in the preset interactive control set. After successful matching, the interactive control that matches successfully is selected from the preset interactive control set. For example, still taking the game as an example, the interactive control corresponding to the game is selected from the preset interactive control set, and the interactive control is used as the target interactive control.

[0119] 105. The information to be processed and the target interactive control are added to the interactive area and displayed on the information display canvas.

[0120] A1, acquire a first receiving time of the to-be-processed information, and identify a target interactive area corresponding to the first receiving time in the interactive area.

[0121] The receiving time can be the time when the user inputs the to-be-processed information through the information input interface, for example, the user inputs the to-be-processed information at 201X year X month X day XX hour 05 minutes 02 seconds, and the receiving time is 201X year X month X day XX hour XX minutes XX seconds. When the display content of the interactive area is queried, if the display content of the interactive area exists, the second receiving time when the interactive area receives the display content is acquired, for example, the interactive area also displays other processed information, the second receiving time when the information processing device receives the other processed information is acquired, for example, the interactive area also displays a processed information, the second receiving time when the information processing device receives the processed information is acquired, for example, 201X year X month X day XX hour 01 minute 01 second, the first receiving time and the second receiving time are sorted, obviously, the interactive area corresponding to the to-be-processed information of the first receiving time should be in front of the interactive area corresponding to the processed information of the second receiving time, if there are two interactive areas on the information display canvas, the interactive area corresponding to the first receiving time should be above the interactive area corresponding to the second receiving time, and the interactive area above the interactive area corresponding to the second receiving time is taken as the target interactive area.

[0122] A2, add the to-be-processed information and the target interactive control to the target interactive area.

[0123] For example, the target interactive area is divided into an information display area and an interactive area, the to-be-processed information is added to the information display area, and the target interactive control is added to the interactive area, as shown in FIG. 1C, the information display area is used to display the to-be-processed information, including displaying images, texts, audios and / or videos of the to-be-processed information. The interactive area is used to add the target interactive control, for example, taking the like activity as an example, the interactive area is used to place a like button. Figure 9

[0124] A3, display the content of the target interactive area on the information display canvas.

[0125] ​For example, after the to-be-processed information and the target interactive control are added, the to-be-processed information and the target interactive control added in the target interactive region are displayed on the information display canvas. For example, taking a like as an interactive activity, the content information published by a user and a like button are displayed on the information display canvas, so that the user or another user triggers the like button to interact with the content information published by the user. The user identity of the publisher of the to-be-processed information and the publishing time (i.e., the first receiving time) can also be displayed in the information display region. The publishing time (i.e., the first receiving time) can be directly displayed as a time, for example, 20XX X month X day X hour X minute X second, or a difference between the publishing time and the current time, for example, the publishing time is 10:50, and the current time is 10:51, so that 1 minute ago is displayed.

[0126] Optionally, after the to-be-processed information and the target interactive control are displayed on the information display canvas, the following steps can also be included:

[0127] (1) When a trigger operation for the target interactive control is detected, an interaction record is generated.

[0128] For example, when a trigger operation for the target interactive control is detected, the identity of the terminal that triggers the operation is obtained, and the number of times is counted once. For example, when a user (the user who publishes the information or another user) triggers the target interactive control, the identity of the user, such as an account, a nickname, or the like, is obtained, and the number of interactions is recorded once. The number of times is accumulated to obtain the total number of times, and when multiple users trigger the target interactive control, each trigger is recorded once, and the number of times is accumulated to obtain the total number of users or the total number of people who interact, for example, taking a like as an interactive activity, when three users like, the identities of the three users are obtained, and the total number of interactions is recorded as 3. The total number of times and the identity are taken as an interaction record, for example, when there is one user interaction, the interaction record is the identity of the user, and the number of interactions is 1. The identity and the number of interactions are taken as the first interaction record, when a second user appears, the identity of the second user is obtained, and the number of interactions is accumulated to obtain the number of interactions as 2. The identities of the two users and the total number of interactions 2 are taken as the second interaction record, and when a third user appears, the identity of the third user is obtained, and the number of interactions is accumulated to obtain the total number of interactions as 3. The identities of the three users and the total number of interactions 3 are taken as the third interaction record. It can be found that the interaction record is dynamically changed, and each time the target interactive control is triggered, a new interaction record needs to be generated.

[0129] (2) The interaction record is displayed in the interactive region.

[0130] For example, the total number of interactions in the interaction record can be displayed beside the target interaction control, such as Figure 10 As shown in the figure, the total number of interactions display area and the target interaction control are taken as a whole, and the total number of interactions display area beside the target interaction space is increased by 1 each time the target interaction control is triggered by the user. The identity of the user in the interaction record can also be displayed below the total number of interactions display area, such as Figure 11 As shown in the figure. Another interaction number control can also be added to display the total number of interactions on the interaction number control, and the identity is associated with the interaction number control in the form of a list, for example, when the user triggers the interaction number control, the identity list can be displayed. As can be seen from the above, after the information processing page is displayed, the information processing page includes an information display canvas and an information entry interface, the information display canvas includes at least one interaction area, receives the to-be-processed information entered in the information entry interface, identifies the type of the to-be-processed information, then according to the identification result, filters out the target interaction control corresponding to the type from the preset interaction control set, adds the to-be-processed information and the target interaction control to the interaction area, and displays on the information display canvas; Since the scheme automatically identifies the type of the to-be-processed information after receiving the to-be-processed information, directly matches the target interaction control according to the identified type, does not need to manually match, and does not need the user to manually add a tag during publishing, therefore, the time for information processing in the interaction process can be greatly reduced.

[0131] According to the method described in the above embodiment, the following will be further described in detail by way of example.

[0132] In this embodiment, the information processing device is specifically integrated into a terminal or the like, and can specifically include a tablet computer, a notebook computer, and a personal computer (PC) or the like.

[0133] As shown in the figure, an information processing method, the specific process is as follows: Figure 12

[0134] 201, the terminal displays an information processing page.

[0135] The information processing page can include an information sharing control and an information display canvas, and the information canvas includes at least one interaction area.

[0136] ​For example, the user can input preset identity information and the like on the login page through the client of the terminal, and after verification, trigger the electronic device to display an information processing page. The user can input preset identity information and the like on the login page through the client, and after verification, trigger the electronic device to display an information processing page. The information processing page displayed by the electronic device is as shown in Figure 3

[0137] 202. When receiving a trigger operation on the information sharing control, the terminal displays an information publishing page.

[0138] The information publishing page includes at least one information input control and a publishing control. The information publishing page can be a page for the user to input and publish image, text, audio and / or video information to be processed.

[0139] For example, when the user triggers the information sharing control on the information processing page through the client of the terminal, the information publishing page is displayed, as shown in Figure 13 For example, the user can trigger the information sharing control through touch, swipe or scroll trigger actions, and when the information processing device receives the user's trigger operation on the information sharing control through the terminal, the information publishing page is displayed on the user's terminal.

[0140] 203. When receiving information to be processed input through the information input control, the terminal displays the information to be processed on the information publishing page.

[0141] The information input control can include a text input control, an image input control, an expression input control, a video input control and an audio input control, and can input text, image, expression, video and audio information through these information input controls.

[0142] For example, the user can input the information to be processed through the operation of the above control, for example, the user inputs the text to be input through the text input control, and inputs the image to be input through the image input control. After inputting, a preview or thumbnail of the input image can be generated on the information input page. If the user is not satisfied with the preview or thumbnail and needs to replace or change the position, the image preview control can be triggered to delete or change the position. The specific deletion action can be through the delete button of the image preview control, or the preview or thumbnail can be selected by long pressing. The action of changing the position can be to drag the image to change the position; the user can also input the required expression through the expression input control. When the user inputs information through these information input controls, the information input by the user can be displayed in real time on the information publishing page.

[0143] ​204、When receiving the triggering operation for the publishing control, the terminal displays the to-be-processed information on the information display canvas of the information processing page, and displays the target interactive control corresponding to the to-be-processed information in the interaction area.

[0144] For example, when the user triggers the publishing control on the information publishing page of the client through the terminal, the to-be-processed information input by the user on the publishing page is saved, and an image is extracted from the to-be-processed information, and the content of the image is identified, for example, a trained identification model can be used to identify the content of the image, and according to the identification result, the type of the to-be-processed information is determined. According to the type of the to-be-processed information, the target interactive control matching the type of the to-be-processed information is selected from the preset interactive control set, for example, if the type of the to-be-processed information is a game, the target interactive control corresponding to the game type is selected from the preset interactive control set. The to-be-processed information is displayed on the information display canvas of the information processing page, and the target interactive control is displayed in the interaction area, as shown in Figure 14 .

[0145] 205、When detecting the triggering operation for the target interactive control, the terminal displays the interaction record in the interaction area.

[0146] The interaction record can be the number of interactions with the target user, the user identity of the interaction, and the interaction content, for example, one or more users like or comment on the to-be-processed information shared by the target user, and the like. For example, the number of likes, the number of visits, the visitor record, and the comment information.

[0147] For example, during the display of the to-be-processed information shared by the target user on the information processing page, the target user himself or other users trigger the target interactive control, at this time, the total number of triggers is recorded, and the user identity of the user triggering the target interactive control is obtained, if there are users inputting comment information after triggering the target interactive control, the input comment information also needs to be obtained, and the interaction record is generated based on the total number of triggers, the user identity, and the comment information, and is displayed in the interaction area of the information processing page, as shown in Figure 11 .

[0148] From the above, the embodiment of the application displays an information processing page, which includes an information sharing control and an information display canvas, and at least one interaction area on the information canvas. When a triggering operation of the user on the information sharing control is detected, an information publishing page is displayed, which includes at least one information input control and a publishing control. When the user inputs the to-be-processed information through the information input control, the to-be-processed information is displayed on the information publishing page. When a triggering operation of the user on the publishing control is detected, the to-be-processed information is displayed on the information display canvas of the information processing page, and the target interactive control corresponding to the to-be-processed information is displayed in the interaction area. When a triggering operation of the user on the target interactive control is detected, the interaction record is displayed in the interaction area. Since the type of the to-be-processed information is automatically identified after the to-be-processed information is received, the target interactive control is directly matched according to the identified type of the to-be-processed information, without manual matching. Moreover, the user does not need to manually add a label in the publishing process. Therefore, the time for information processing in the interaction process can be greatly reduced.

[0149] According to the method described in the above embodiment, the following will be further described in detail by way of example.

[0150] In this embodiment, the information processing device is specifically integrated in an electronic device, which can be a terminal or the like, and can specifically include a tablet computer, a notebook computer, a personal computer (PC), and the like. The interactive control is taken as a like control for illustration.

[0151] As shown in Figure 15 , an information processing method specifically includes the following process:

[0152] 301. The electronic device displays an information processing page.

[0153] For example, the user can input preset identity information and the like on the login page through the client, and after verification, trigger the electronic device to display the information processing page. The user can input preset identity information and the like on the login page through the client, and after verification, trigger the electronic device to display the information processing page. The information processing page displayed by the electronic device is as shown in Figure 3 .

[0154] 302. The electronic device receives to-be-processed information input in the information input interface.

[0155] For example, the user can trigger the information input interface control of the information processing page. At this time, the electronic device can display an information input page, as shown in Figure 5As shown, the information entry page can include a text entry control, an image entry control, an expression entry control, an image preview control, a video entry control, an audio entry control, a cancel control, and a publish control, etc. The electronic device receives information of various formats entered by the user through various entry controls of the information entry page, and generates the information into the to-be-processed information.

[0156] 303. The electronic device extracts at least one to-be-identified image from the to-be-processed information.

[0157] For example, the electronic device can classify the content of the to-be-processed information by content format, and according to the classification result, extract at least one to-be-identified image entered by the user through the image entry control from the to-be-processed information. For example, the user can enter a file in image format such as jpg, bmp, and tif (formats corresponding to image data) through the image entry control. The content of the to-be-processed information is classified by format, for example, the content corresponding to the text format is classified as text, the content corresponding to the audio format is classified as audio, the content corresponding to the video format is classified as video, and the content corresponding to the image format is classified as image. According to the classification result, at least one to-be-identified image is extracted from the to-be-processed information.

[0158] 304. The electronic device identifies the content of the to-be-identified image.

[0159] (1) When there is one to-be-identified image in the to-be-processed information, the trained recognition model is used to identify the content of the to-be-identified image to obtain a recognition result.

[0160] For example, the electronic device can use the trained recognition model to identify the type of the to-be-identified image, and the specific identification process is as follows:

[0161] B1. The electronic device extracts features of the to-be-identified image to obtain local features of the to-be-identified image.

[0162] For example, the electronic device can set a fixed step size and scale in the trained recognition model, and use a convolutional neural network to extract low-level features, such as using the Inception module of the GoogleNet model (an image recognition model) to extract low-level features, as shown in Figure 6 As shown, the Inception simple module extracts common local features of the to-be-identified image, such as Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradient (HOG), and / or Local Binary Pattern (LBP) local features.

[0163] B2, the electronic device feature encodes the local features to obtain encoded local features.

[0164] For example, the electronic device can use vector quantization encoding, sparse coding, local linear constraint coding, Fisher vector coding, and the like to encode the local features to obtain the encoded local features.

[0165] B3, the electronic device fuses the encoded local features to obtain fused features.

[0166] For example, the electronic device can use pyramid feature matching to fuse the encoded local features to obtain the fused features. Specifically, the electronic device can uniformly divide the to-be-recognized image into blocks, fuse the features in each block to obtain the fused features of each block, and then fuse the fused features of each block again to obtain the fused features of the to-be-recognized image, i.e., the fixed-dimension feature vector of the to-be-recognized image.

[0167] B4, the electronic device identifies the content of the to-be-recognized image based on the fused features.

[0168] For example, the electronic device can use support vector machine (SVM) and random forest to classify the fixed-dimension feature vector of the to-be-recognized image, thereby obtaining the recognition result of the content of the to-be-recognized image. The recognition result can be the content of the to-be-recognized image and the type corresponding to the content, thereby completing the recognition process.

[0169] (2) When there are at least two to-be-recognized images in the to-be-processed information, the trained recognition model is used to identify the content of the to-be-recognized image to obtain at least two initial recognition results, and the initial recognition results are fused to obtain the recognition result.

[0170] For example, when there are at least two to-be-recognized images in the to-be-processed information, the electronic device also adopts the trained recognition model to recognize the content of each to-be-recognized image, and the recognition process of the to-be-recognized image is described with reference to steps B1-B4, and at least two initial recognition results are obtained. For example, when there are three to-be-recognized images in the to-be-processed information, the three to-be-recognized images are recognized respectively, and the recognition results of the three to-be-recognized images are obtained, which are respectively the probability value of type A, the probability value of type B, and the probability value of type C. The initial recognition results are classified, for example, the type A is a scene image of a game, and the types B and C are respectively a character image of a game, and the initial recognition results can be classified into two categories of game scene and game character image. According to the classification result, the weighting coefficient corresponding to the initial recognition result is obtained, for example, the preset weighting coefficient of the game scene is 0.7, and the weighting coefficient of the game character is 0.3. According to the weighting coefficient, the initial recognition results are weighted respectively, the weighted initial recognition results are fused, and the recognition result is obtained. For example, after weighting the probability value of type A, the probability value of type B, and the probability value of type C, the maximum value can be selected as the recognition result from the three, or the three recognition results can be comprehensively analyzed to obtain the type of the to-be-recognized image as a game.

[0171] The trained recognition model can be trained by a plurality of image samples, which can be trained by other devices and provided to the information processing apparatus, or can be trained by the information processing apparatus itself, that is, before the step of "recognizing the to-be-recognized image by using the trained recognition model", the information processing method can further include:

[0172] (1) Collecting a plurality of image samples, the image samples including images with labeled recognition results.

[0173] For example, a plurality of images can be collected as original image samples through a database, a network, and an image collection device, and then the original image samples are preprocessed, such as de-duplication, cropping, rotation, and / or flipping, to obtain image samples meeting the input standard of the preset recognition model. Then, the preprocessed image samples are labeled by type to obtain labeled image samples.

[0174] (2) Using a preset recognition model to predict the recognition result of the image sample, to obtain the predicted recognition result of the image sample.

[0175] For example, the preset recognition model is used to extract features of the image sample to obtain local features of the image sample, the local features are encoded to obtain encoded local features, the encoded local features are fused to obtain fused features, and the image sample is recognized based on the fused features to obtain the predicted recognition result of the image sample.

[0176] (3) According to the predicted recognition result and the labeled recognition result, the preset recognition model is converged to obtain a trained recognition model.

[0177] For example, according to the predicted recognition result and the labeled recognition result, the preset recognition model is converged by an interpolation loss function to obtain a trained recognition model. For example, the following can be specifically implemented:

[0178] The Dice function (a loss function) is adopted to adjust the parameters for feature fusion in the preset recognition model according to the labeled recognition result and the predicted recognition result of the image sample, and a trained recognition model is obtained.

[0179] Optionally, in order to improve the accuracy of the context feature, in addition to the Dice function, other loss functions such as the cross-entropy loss function can also be used for convergence. The following can be specifically implemented:

[0180] The cross-entropy loss function is adopted to adjust the parameters for feature fusion in the preset recognition model according to the labeled recognition result and the predicted recognition result of the image sample, and the interpolation loss function is adopted to adjust the parameters for feature fusion in the preset recognition model according to the labeled recognition result and the predicted recognition result of the image sample, and a trained recognition model is obtained.

[0181] 305. The electronic device confirms the type of the to-be-processed information according to the recognition result.

[0182] For example, the electronic device confirms the type of the to-be-processed information according to the recognition result of the to-be-recognized image. The recognition result can be the content of the to-be-recognized image and the type corresponding to the content. The type of the content of the to-be-recognized image can be obtained, and the type of the content of the to-be-recognized image and the type of the to-be-processed information are associated with each other. For example, according to the type of the content of the to-be-recognized image, matching is performed in a preset type set of to-be-processed information. For example, the type of the content of the to-be-recognized image is a game, and the preset type set of to-be-processed information can include games, dances, music, animations, and paintings, etc. According to the type of the content of the to-be-recognized image, matching is performed in the preset type set of to-be-processed information, and it can be confirmed that the type of the to-be-processed information is a game. For another example, the content of the to-be-recognized image is a promotional image of a piece of music, and it can be confirmed that the type of the to-be-processed information is music.

[0183] 306. The electronic device screens out a target like control corresponding to the type of the to-be-processed information from a preset like control set according to the recognition result.

[0184] For example, the electronic device obtains the style or type of each like control in the preset like control set, and each style or type corresponds to an information type, such as Figure 8As shown, games, dances, music, animations, and paintings can be included. The type of the information to be processed is matched with the type of the like control. For example, if the type of the information to be processed is a game, the like control style corresponding to the game type is matched in the preset like control set. After a successful match, the like control that successfully matches is filtered out in the preset like control set. For example, still taking the game as an example, the like control corresponding to the game is filtered out in the preset like control set and the like control is used as the target like control.

[0185] 307. The electronic device adds the information to be processed and the target like control to the interactive area and displays them on the information display canvas.

[0186] E1. The electronic device obtains a first receiving time of the information to be processed, and identifies a target interaction area corresponding to the first receiving time in the interaction area.

[0187] For example, if a user enters information to be processed at XX:05:02 on X / X / 201X, the reception time is XX:XX:XX on X / X / 201X. When querying the displayed content in the interactive area, if there is displayed content in the interactive area, the second reception time when the interactive area receives the displayed content is obtained. For example, if the interactive area also displays other processed information, the second reception time when the information processing device receives the other processed information is obtained. For example, if a processed information is also displayed in the interactive area, the second reception time when the information processing device receives the processed information is obtained, such as XX:01:01 on X / X / 201X. The first reception time and the second reception time are sorted. Obviously, the interactive area for the information to be processed corresponding to the first reception time should be before the interactive area for the processed information corresponding to the second reception time. If there are two interactive areas on the information display canvas, the interactive area corresponding to the first reception time should be above the interactive area corresponding to the second reception time. The interactive area above the interactive area corresponding to the second reception time is used as the target interactive area.

[0188] E2. The electronic device adds the information to be processed and the target like control to the target interaction area.

[0189] For example, the electronic device divides the target interaction area into an information display area and a like area, adds the information to be processed to the information display area, and adds the target like control to the like area. Figure 9 As shown, the information display area is used to display the information to be processed, including images, text, audio and / or video of the information to be processed. The like area is used to add a target like control.

[0190] E3. The electronic device displays the content of the target interaction area on the information display canvas.

[0191] For example, the electronic device displays the content of the target interaction area on the information display canvas, which may mainly be content information posted by users and a like button, so that the user himself or other users can trigger the like button to interact with the content information posted by the user. The user identity identifier and the publishing time (i.e., the first receiving time) of the publisher of the information to be processed may also be displayed in the information display area. The publishing time (i.e., the first receiving time) may be displayed directly, for example, directly displaying Xh:X ...

[0192] Optionally, after the electronic device displays the information to be processed and the target like control on the information display canvas, the following steps may be further included:

[0193] (1) When a trigger operation for a target like control is detected, an interaction record is generated.

[0194] For example, when a trigger operation for a target like control is detected, the identity of the terminal that triggered the operation is obtained and counted once. For example, when a user (the user who posted the information or other users) triggers the target like control, the user's identity is obtained, such as the user's account, nickname, and other identity identifiers, and the interaction is recorded once. The count times are accumulated to obtain the total number of counts. When there are multiple users triggering the target like control, each trigger records an interaction once, and the total number of interactive users or the total number of interactive users is accumulated on the previous number of interactions. For example, taking the interactive activity like as an example, when there are three users who like, the identities of the three users are obtained, and the total number of interactions or the total number of people is recorded as 3. The total number of counts and the identity identifier are used as the interaction record. For example, when there is a user interaction, the interaction record is the user's identity identifier and the number of interactions is 1. The identity identifier and the number of interactions are used as the first interaction record. When a second user appears, the second user identity identifier is obtained, and the number of interactions is accumulated, resulting in a number of interactions of 2. The identity identifiers of the two users and the total number of interactions of 2 are used as the second interaction record. When a third user appears, the third user identity identifier is obtained, and the number of interactions is continued to be accumulated, resulting in a total number of interactions of 3. The identity identifiers of the three users and the total number of interactions of 3 are used as the third interaction record. It can be found that the interaction record changes dynamically. Whenever the target like control is triggered, a new interaction record needs to be generated.

[0195] (2) Display interaction records in the interaction area.

[0196] For example, the total number of interactions in the interaction record can be displayed beside the target like control, as shown in Figure 10 The total number of interactions display area and the target like control are displayed as a whole, and the total number of interactions display area beside the target interaction space displays the number of interactions increasing by 1 each time the user triggers the target like control. The identity of the user in the interaction record can also be displayed below the total number of interactions display area, as shown in Figure 11 Another interaction number control can also be added to display the total number of interactions on the interaction number control, and the identity is associated with the interaction number control in the form of a list, for example, when the user triggers the interaction number control, the identity list can be displayed.

[0197] As can be seen from the above, after the electronic device displays the information processing page, the information processing page includes an information display canvas and an information entry interface, the information display canvas includes at least one interaction area, receives the to-be-processed information entered in the information entry interface, identifies the type of the to-be-processed information, and then filters out the target like control corresponding to the type from the preset like control set according to the identification result, adds the to-be-processed information and the target like control to the interaction area, and displays on the information display canvas; since the scheme automatically identifies the type of the to-be-processed information after receiving the to-be-processed information, directly matches the target like control according to the identified type, does not need to manually match, and does not need the user to manually add a label during publishing, the time for information processing in the interaction process can be greatly reduced.

[0198] In order to better implement the above method, the embodiment of the present application also provides an information processing device, which can be integrated in an electronic device such as a server or a terminal, etc. The terminal can include a tablet computer, a notebook computer, and / or a personal computer, etc.

[0199] For example, as shown in Figure 16 The information processing device can include a display unit 401, an extraction unit 402, an identification unit 403, a filtering unit 404, and a processing unit 405, as follows:

[0200] (1) the display unit 401;

[0201] The display unit 401 is configured to display an information processing page, the information processing page including an information display canvas and an information entry interface, the information display canvas including at least one interaction area.

[0202] For example, the display unit 401 can be specifically configured to enable a user to input preset identity information, etc. on a login page through a client, trigger the display of an information processing page after verification, and enable the user to directly trigger the display of the information processing page through the client.

[0203] (2) the receiving unit 402;

[0204] The receiving unit 402 is configured to receive the to-be-processed information input via the information input interface.

[0205] For example, the receiving unit 402 can be specifically configured to receive the to-be-processed information input by a user via the information input interface control of the information processing page.

[0206] (3) the identifying unit 403;

[0207] The identifying unit 403 is configured to identify the type of the to-be-processed information.

[0208] The identifying unit 403 can include an extracting sub-unit 4031, an identifying sub-unit 4032, and a determining sub-unit 4033, as shown in Figure 17 and specifically as follows:

[0209] The extracting sub-unit 4031 is configured to extract at least one to-be-identified image from the to-be-processed information.

[0210] The identifying sub-unit 4032 is configured to identify the content of the to-be-identified image.

[0211] The determining sub-unit 4033 is configured to determine the type of the to-be-processed information according to the identification result.

[0212] For example, the extracting sub-unit 4031 extracts at least one to-be-identified image from the to-be-processed information, the identifying sub-unit 4032 identifies the type of the to-be-identified image, and the determining sub-unit 4033 determines the type of the to-be-processed information according to the identification result.

[0213] (4) the screening unit 404;

[0214] The screening unit 404 is configured to screen a target interactive control corresponding to the type from a preset interactive control set according to the identification result.

[0215] The screening unit 404 can include an obtaining sub-unit 4041, a matching sub-unit 4042, and a screening sub-unit 4043, as shown in Figure 18 and specifically as follows:

[0216] The obtaining sub-unit 4041 is configured to obtain the types of the interactive controls in the preset interactive control set.

[0217] The matching sub-unit 4042 is configured to match the type of the to-be-processed information with the types of the interactive controls.

[0218] The screening sub-unit 4043 is configured to screen a target interactive control corresponding to the type of the to-be-processed information from the preset interactive control set according to the matching result.

[0219] For example, the obtaining sub-unit 4041 obtains the type of the interactive control in the preset interactive control set, the matching sub-unit 4042 matches the type of the to-be-processed information with the type of the interactive control, and the screening sub-unit 4043 screens a target interactive control corresponding to the type of the to-be-processed information from the preset interactive control set according to the matching result.

[0220] (5) the processing unit 405;

[0221] The processing unit 405 is configured to add the to-be-processed information and the target interactive control to the interactive region and display the interactive region on the information display canvas.

[0222] For example, the processing unit 405 can be specifically configured to obtain a first receiving time of the to-be-processed information, identify a target interactive region corresponding to the first receiving time in the interactive region, add the to-be-processed information and the target interactive control to the target interactive region, and display the content of the target interactive region on the information display canvas.

[0223] Optionally, the processing unit 405 can be specifically configured to, when detecting a trigger operation on the target interactive control, obtain an identity of a terminal performing the trigger operation, count once, accumulate the number of counts to obtain a total number of counts, and display the total number of counts and the identity as an interactive record on the interactive region.

[0224] Optionally, the information processing apparatus can further include a collecting unit 406 and a training unit 407, as shown in Figure 19 The specific implementation is as follows:

[0225] The collecting unit 406 is configured to collect a plurality of image samples, the image samples including images with labeled recognition results.

[0226] The training unit 407 is configured to use a preset recognition model to predict the recognition results of the image samples, obtain predicted recognition results of the image samples, and converge the preset recognition model according to the predicted recognition results and the labeled results to obtain a trained recognition model.

[0227] For example, the collecting unit 406 collects a plurality of image samples, the image samples including images with labeled recognition results, the training unit 407 uses a preset recognition model to predict the recognition results of the image samples, obtains predicted recognition results of the image samples, and converges the preset recognition model according to the predicted recognition results and the labeled results to obtain a trained recognition model.

[0228] Optionally, the embodiment of the present application also provides another information processing device, which is applied to a terminal. The information processing device may include an information processing display unit 408, a publishing page display unit 409, a to-be-processed information display unit 410, an interaction display unit 411, and an interaction record display unit 412. Figure 20 As shown, the details are as follows:

[0229] An information processing display unit 408 is configured to display an information processing page, the information processing page including an information sharing control and an information display canvas, the information canvas including at least one interactive area;

[0230] The publishing page display unit 409 is configured to display an information publishing page when a user triggers an operation on the information sharing control. The information publishing page includes at least one information input control and a publishing control.

[0231] The pending information display unit 410 is configured to display the pending information on the information publishing page when receiving the pending information input by the user through the information input control;

[0232] The interactive display unit 411 is configured to display the information to be processed on the information display canvas of the information processing page and display the target interactive control corresponding to the information to be processed in the interactive area when a trigger operation for the publishing control is received from the user;

[0233] The interaction record display unit 412 is configured to display the interaction record in the interaction area when a trigger operation of a user on a target interactive control is detected.

[0234] For example, the information processing display unit 408 displays an information processing page, which includes an information sharing control and an information display canvas, and the information canvas includes at least one interactive area. The publishing page display unit 409 displays an information publishing page when receiving a user trigger operation on the information sharing control, and the information publishing page includes at least one information input control and a publishing control. The pending information display unit 410 displays the pending information on the information publishing page when receiving the user input of the pending information through the information input control. The interaction display unit 411 displays the pending information on the information display canvas of the information processing page when receiving the user trigger operation on the publishing control, and displays the target interactive control corresponding to the pending information in the interactive area. The interaction record display unit 412 displays the interaction record in the interactive area when detecting the user trigger operation on the target interactive control. In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiment and will not be repeated here.

[0235] From the above, the display unit 401 displays the information processing page, the information processing page includes an information display canvas and an information entry interface, the information display canvas includes at least one interactive area, the receiving unit 402 receives the to-be-processed information entered in the information entry interface, the identifying unit 403 identifies the type of the to-be-processed information, then the screening unit 404 screens out the target interactive control corresponding to the type of the to-be-processed information from the preset interactive control set according to the identification result, and the processing unit 405 adds the to-be-processed information and the target interactive control to the interactive area and displays on the information display canvas. Since the scheme automatically identifies the type of the to-be-processed information after receiving the to-be-processed information, directly matches the target interactive control according to the identified type, does not need manual matching, and does not need the user to manually add a label in the publishing process, the time for information processing in the interactive process can be greatly reduced.

[0236] The embodiment of the present application also provides an electronic device, as shown in the figure, which shows a structural schematic diagram of the electronic device related to the embodiment of the present application, in particular: Figure 21

[0237] The electronic device can include a processor 501 with one or more processing cores, a memory 502 with one or more computer readable storage media, a power supply 503, an input unit 504 and the like. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the electronic device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements. Among them: Figure 21 The processor 501 is the control center of the electronic device, connects various parts of the entire electronic device through various interfaces and lines, executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 502 and calling data stored in the memory 502, thereby overall detecting the electronic device. Optionally, the processor 501 can include one or more processing cores; preferably, the processor 501 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 501.

[0238]

[0239] ​​The memory 502 can be used to store software programs and modules, and the processor 501 executes various function applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the electronic device, etc. In addition, the memory 502 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory 502 can also include a memory controller to provide the processor 501 with access to the memory 502.

[0240] The electronic device also includes a power supply 503 for powering various components. Preferably, the power supply 503 can be logically connected to the processor 501 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 503 can also include one or more direct current or alternating current power supplies, a recharging system, a power supply fault detection circuit, a power supply converter or inverter, a power supply status indicator, and the like.

[0241] The electronic device can also include an input unit 504, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0242] Although not shown, the electronic device can also include a display unit and the like, which will not be described here. Specifically, in the present embodiment, the processor 501 in the electronic device will load the executable file corresponding to the process of one or more application programs into the memory 502 according to the following instructions, and run the application programs stored in the memory 502 by the processor 501, so as to realize various functions, as follows:

[0243] display an information processing page, the information processing page including an information display canvas and an information entry interface, the information display canvas including at least one interactive area, receiving the to-be-processed information entered in the information entry interface, identifying the type of the to-be-processed information, then, according to the identification result, screening out a target interactive control corresponding to the type of the to-be-processed information from a preset interactive control set, adding the to-be-processed information and the target interactive control to the interactive area, and displaying on the information display canvas. Or

[0244] display an information processing page, the information processing page including an information sharing control and an information display canvas, the information display canvas including at least one interactive region; when detecting a triggering operation of the user on the information sharing control, display an information publishing page, the information publishing page including at least one information input control and a publishing control; when receiving information to be processed input by the user through the information input control, display the information to be processed on the information publishing page; when detecting a triggering operation of the user on the publishing control, display the information to be processed on the information display canvas of the information processing page, and display a target interactive control corresponding to the information to be processed on the interactive region; and when detecting a triggering operation of the user on the target interactive control, display an interaction record on the interactive region.

[0245] The specific implementation of each operation can refer to the foregoing embodiments, and will not be described herein.

[0246] As can be seen from the foregoing, after the information processing page is displayed, the information processing page includes an information display canvas and an information input interface, the information display canvas including at least one interactive region, the information to be processed input on the information input interface, the type of the information to be processed is identified, then, according to the identification result, the target interactive control corresponding to the type of the information to be processed is selected from the preset interactive control set, the information to be processed and the target interactive control are added to the interactive region, and are displayed on the information display canvas; since the type of the information to be processed is automatically identified after the information to be processed is received, the target interactive control is directly matched according to the identified type, manual matching is not required, and the user does not need to manually add a label in the publishing process, therefore, the time for information processing in the interaction process can be greatly reduced.

[0247] Those skilled in the art can understand that all or part of the steps in the various methods of the foregoing embodiments can be completed by instructions, or by related hardware controlled by the instructions, the instructions can be stored in a computer readable storage medium, and loaded and executed by a processor.

[0248] To this end, the embodiment of the present application provides a computer readable storage medium, which stores a plurality of instructions, the instructions can be loaded by a processor to execute the steps in any information processing method provided by the embodiment of the present application. For example, the instructions can execute the following steps:

[0249] Display an information processing page, the information processing page comprising an information display canvas and an information entry interface, the information display canvas comprising at least one interactive area, receiving information to be processed entered in the information entry interface, identifying the type of the information to be processed, then, according to the identification result, filtering out a target interactive control corresponding to the type of the information to be processed from a preset interactive control set, adding the information to be processed and the target interactive control to the interactive area, and displaying on the information display canvas. Or

[0250] Display an information processing page, the information processing page comprising an information display canvas and an information entry interface, the information display canvas comprising at least one interactive area, receiving information to be processed entered in the information entry interface, identifying the type of the information to be processed, then, according to the identification result, filtering out a target interactive control corresponding to the type of the information to be processed from a preset interactive control set, adding the information to be processed and the target interactive control to the interactive area, and displaying on the information display canvas. Or

[0251] The specific implementation of each operation can refer to the foregoing embodiments, and will not be described here.

[0252] The computer readable storage medium can include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, an optical disk, etc.

[0253] Due to the instructions stored in the computer readable storage medium, the steps of any of the information processing methods provided by the embodiments of the present application can be executed, and thus the beneficial effects of any of the information processing methods provided by the embodiments of the present application can be achieved. Details are described in the foregoing embodiments, and will not be described here.

[0254] The above describes in detail the information processing method, device and computer readable storage medium provided by the embodiments of the present application. The principle and implementation manner of the present application are described by applying specific examples in this paper. The above embodiment description is only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. An information processing method, characterized in that: include: Displaying an information processing page, the information processing page including an information display canvas and an information entry interface, the information display canvas including at least one interactive area; Receiving information to be processed entered in the information entry interface; Identifying the type of the information to be processed; According to the recognition result, a target interactive control corresponding to the type of the information to be processed is screened out from a preset interactive control set; wherein the target interactive control is used for a user to perform a touch operation; Adding the information to be processed and the target interactive control to the interactive area and displaying them on the information display canvas; The information processing page also includes a classification control. When a trigger is received for the classification control, the information that has been processed or displayed on the information display canvas is classified and a classification list is generated; when a trigger is received for a type in the classification list, information corresponding to the type is displayed on the information display canvas.

2. The information processing method according to claim 1, wherein: The identifying the type of the information to be processed includes: Extracting at least one image to be identified from the information to be processed; Identifying the content of the image to be identified; According to the recognition result, the type of the information to be processed is determined.

3. The information processing method according to claim 2, wherein: The identifying the content of the image to be identified includes: When there is an image to be recognized in the information to be processed, the trained recognition model is used to recognize the content of the image to be recognized to obtain the recognition result; When there are at least two images to be identified in the information to be processed, the trained recognition model is used to identify the content of the images to be identified to obtain at least two initial recognition results, and the initial recognition results are fused to obtain the recognition result.

4. The information processing method according to claim 3, wherein: The fusing of the multiple initial recognition results to obtain the recognition result includes: classifying the initial recognition results; According to the classification result, obtaining a weighting coefficient corresponding to the initial recognition result; weighting the initial recognition result based on the weighting coefficient; The weighted initial recognition results are fused to obtain the recognition result.

5. The information processing method according to any one of claims 3 or 4, characterized in that: The identifying the content of the image to be identified by using the trained recognition model includes: Extracting features of the image to be identified to obtain local features of the image to be identified; Performing feature encoding on the local features to obtain encoded local features; Fusing the encoded local features to obtain fused features; Based on the fused features, the content of the image to be identified is identified.

6. The information processing method according to claim 3, wherein: Before using the trained recognition model to recognize the image to be recognized, the method includes: Collecting a plurality of image samples, wherein the image samples include images on which recognition results have been marked; Using a preset recognition model to predict the recognition result of the image sample to obtain the predicted recognition result of the image sample; The preset recognition model is converged according to the predicted recognition result and the labeled recognition result to obtain the trained recognition model.

7. The information processing method according to claim 1, wherein: The step of screening out a target interactive control corresponding to the type of the information to be processed from a preset interactive control set according to the recognition result includes: Obtaining the type of interactive controls in the preset interactive control set; Matching the type of the information to be processed with the type of the interactive control; According to the matching result, a target interactive control corresponding to the type of the information to be processed is filtered out from the preset interactive control set.

8. The information processing method according to claim 1, wherein: The adding the information to be processed and the target interactive control to the interactive area and displaying them on the information display canvas includes: Obtaining a first receiving time of the information to be processed; identifying a target interaction area corresponding to the first receiving time in the interaction area; Adding the information to be processed and the target interactive control to the target interactive area; The content of the target interaction area is displayed on the information display canvas.

9. The information processing method according to claim 8, characterized in that The identifying, in the interaction area, a target interaction area corresponding to the receiving time includes: Querying the display content of the interactive area; When there is display content in the interactive area, obtaining a second receiving time at which the interactive area receives the display content; sorting the first receiving time and the second receiving time; According to the sorting result, a target interaction area corresponding to the first receiving time is identified in the interaction area.

10. The information processing method according to claim 8, wherein: Adding the information to be processed and the target interactive control to the target interactive area includes: Dividing the target interactive area into an information display area and an interactive area; Adding the information to be processed to the information display area; Add the target interactive control to the interactive area.

11. The information processing method according to claim 10, wherein: After displaying the content of the target interaction area on the information display canvas, the method further includes: When a triggering operation on the target interactive control is detected, generating an interaction record; The interaction record is displayed in the interaction area.

12. The information processing method according to claim 11, wherein: When a trigger operation for the target interactive control is detected, generating an interaction record includes: When a triggering operation on the target interactive control is detected, obtaining the identity of the terminal that triggered the operation and counting it once; Accumulating the count times to obtain a total count number; The total number of counts and the identity identifier are used as an interaction record.

13. An information processing method, characterized in that: include: Displaying an information processing page, the information processing page including an information sharing control and an information display canvas, the information canvas including at least one interactive area; When a trigger operation for the information sharing control is detected, an information publishing page is displayed, wherein the information publishing page includes at least one information input control and a publishing control; When receiving information to be processed input through the information input control, displaying the information to be processed on the information publishing page; When a trigger operation for the publishing control is detected, the information to be processed is displayed on the information display canvas of the information processing page, and a target interactive control corresponding to the information to be processed is displayed in the interactive area; wherein the target interactive control is used for a user to perform a touch operation; When a triggering operation of the user on the target interactive control is detected, the interaction record is displayed in the interaction area; The information processing page also includes a classification control. When a trigger is received for the classification control, the information that has been processed or displayed on the information display canvas is classified and a classification list is generated; when a trigger is received for a type in the classification list, information corresponding to the type is displayed on the information display canvas.

14. An information processing device, characterized in that: include: A display unit, configured to display an information processing page, wherein the information processing page includes an information display canvas, a classification control, and an information entry interface, and the information display canvas includes at least one interactive area; A receiving unit, configured to receive the information to be processed entered in the information entry interface; an identification unit, configured to identify the type of the information to be processed; a screening unit, configured to screen out a target interactive control corresponding to the type of the information to be processed from a preset interactive control set according to the recognition result; wherein the target interactive control is configured to be touched by a user; A processing unit is used to add the information to be processed and the target interactive control to the interactive area and display them on the information display canvas; it is also used to classify the information that has been processed or displayed on the information display canvas and generate a classification list when receiving a trigger for the classification control; when receiving a trigger for a type in the classification list, it displays information corresponding to the type on the information display canvas.

15. An information processing device, characterized in that: include: An information processing display unit, configured to display an information processing page, the information processing page including an information sharing control, a classification control, and an information display canvas, the information canvas including at least one interactive area; a publishing page display unit, configured to display an information publishing page upon receiving a trigger operation for the information sharing control, the information publishing page including at least one information input control and a publishing control; a to-be-processed information display unit, configured to display the to-be-processed information on the information publishing page when receiving the to-be-processed information input through the information input control; an interactive display unit, configured to display the information to be processed on the information display canvas of the information processing page and display a target interactive control corresponding to the information to be processed in the interactive area when a trigger operation for the publishing control is received; wherein the target interactive control is configured for a user to perform a touch operation; An interaction record display unit, configured to display the interaction record in the interaction area when a trigger operation on the target interactive control is detected; A processing unit is used to classify the information that has been processed or displayed on the information display canvas and generate a classification list when receiving a trigger for the classification control; and to display information corresponding to the type on the information display canvas when receiving a trigger for a type in the classification list.

16. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores an application program, and the processor is configured to run the application program in the memory to execute the information processing method according to any one of claims 1 to 13.

17. A computer-readable storage medium, characterized in that The storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the information processing method according to any one of claims 1 to 13.

Images