Page display method and device, terminal and storage medium

Abstract

The embodiment of the invention provides a page display method and device, a terminal and a storage medium, and relates to the technical field of the Internet, and the method comprises the steps: in a process of playing a target advertisement, in response to a display instruction for the target advertisement, obtaining a target problem corresponding to the target advertisement; displaying the text of the target question, and / or playing the voice of the target question; in response to the obtained answer voice, converting the answer voice into an answer text to obtain a to-be-detected answer of the target question; calculating a target matching degree between the to-be-detected answer and each target answer of the target question; if the target matching degree of the to-be-detected answer and any target answer is larger than the matching degree threshold value, the landing page of the target advertisement corresponding to the target answer is displayed, the landing page containing the information of the target advertisement needing to be known can be displayed, the personalized requirement of a user is met, and the user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of Internet technology, and in particular to a page display method, apparatus, terminal and storage medium. Background Technology

[0002] Users will see displayed advertisements when using the functions provided by the terminal. For example, an advertisement may be played before a video. If a user is interested in the advertisement content, they can input a display command into the terminal. In response to the user's display command, the terminal displays the advertisement's landing page.

[0003] In related technologies, each advertisement corresponds to a fixed landing page. However, having the same landing page for all users fails to meet the personalized needs of different users and degrades the user experience. Summary of the Invention

[0004] The purpose of this invention is to provide a page display method, apparatus, terminal, and storage medium to display landing pages that meet user needs and improve user experience. The specific technical solution is as follows:

[0005] In a first aspect of the present invention, a page display method is provided, the method being applied to a terminal, the method comprising:

[0006] During the playback of the target advertisement, in response to the display instruction for the target advertisement, the question corresponding to the target advertisement is obtained as the target question;

[0007] Display the text of the target question, and / or play the audio of the target question;

[0008] In response to the acquired answer speech, the answer speech is converted into answer text to obtain the target question's answer to be detected;

[0009] The matching degree between the answer to be detected and each target answer of the target question is calculated as the target matching degree; wherein, the target answer is pre-configured information associated with the content of the target advertisement; different target answers correspond to different landing pages of the target advertisement;

[0010] If the target matching degree between the answer to be detected and any target answer is greater than the matching degree threshold, the landing page of the target advertisement corresponding to the target answer is displayed.

[0011] Optionally, during the playback of the target advertisement, in response to a display instruction for the target advertisement, obtaining a question corresponding to the target advertisement as the target question includes: during the playback of the target advertisement, in response to a display instruction for the target advertisement, detecting whether voice recognition permission has been enabled; if voice recognition permission is enabled, obtaining a question corresponding to the target advertisement as the target question; if voice recognition permission is not enabled, displaying a permission enabling prompt page; wherein the permission enabling prompt page displays an operation button for enabling voice recognition permission; in response to a preset operation on the operation button, enabling voice recognition permission and obtaining a question corresponding to the target advertisement as the target question.

[0012] Optionally, obtaining the question corresponding to the target advertisement as the target question includes: obtaining the question corresponding to the target advertisement from the advertisement question database according to the correspondence between advertisements and questions, as the target question; wherein, the advertisement question database includes questions corresponding to each advertisement.

[0013] Optionally, before calculating the matching degree between the answer to be detected and each target answer of the target question as the target matching degree, the method further includes: obtaining the target answer of the target question from an advertising feature library according to the correspondence between questions and answers; wherein, the advertising feature library includes the answers to the questions corresponding to each advertisement; the target answer includes at least one tag keyword associated with the content of the target advertisement.

[0014] Optionally, calculating the matching degree between the answer to be detected and each target answer of the target question, as the target matching degree, includes: segmenting the answer to be detected into words and determining the keywords to be detected from the segmentation results; for each target answer of the target question, determining the tag keywords that match the keywords to be detected from the target answer, as the target keywords; wherein, the target keywords include: keywords that are the same as the keywords to be detected, or synonyms of the keywords to be detected; and calculating the matching degree between the answer to be detected and the target answer based on the target keywords, as the target matching degree.

[0015] Optionally, the step of calculating the matching degree between the answer to be detected and the target answer based on the target keywords, as the target matching degree, includes: determining the number of target keywords to obtain the matching degree between the answer to be detected and the target answer, as the target matching degree; or, calculating the weighted sum of the importance of the target keywords according to the preset weight of each tag keyword to obtain the matching degree between the answer to be detected and the target answer, as the target matching degree.

[0016] Optionally, after displaying the text of the target question and / or playing the audio of the target question, the method further includes: if no audio response is obtained within a first preset time period, obtaining the number of times the target question has been displayed as the first count; if the first count is less than a first value, obtaining the question corresponding to the target advertisement as the target question, and returning to the steps of displaying the text of the target question and / or playing the audio of the target question; if the first count is greater than the first value, displaying the default landing page of the target advertisement.

[0017] Optionally, after calculating the matching degree between the answer to be detected and each target answer of the target question as the target matching degree, the method further includes: if the target matching degree between the answer to be detected and each target answer is less than the matching degree threshold, obtaining the number of times the target question is displayed as the second count; if the second count is less than the second value, obtaining a new question corresponding to the target advertisement as the target question, and returning to the steps of displaying the text of the target question and / or playing the audio of the target question; if the second count is greater than the second value, displaying the default landing page of the target advertisement.

[0018] Optionally, before displaying the text of the target question and / or playing the audio of the target question, the method further includes: stopping the playback of the target advertisement.

[0019] Optionally, displaying the text of the target question and / or playing the audio of the target question includes: continuing to play the image and audio of the target advertisement, and displaying the text of the target question in the upper view of the advertisement playback interface; or: continuing to play the image of the target advertisement and stopping the audio of the target advertisement; playing the audio of the target question; or: continuing to play the image of the target advertisement and stopping the audio of the target advertisement; displaying the text of the target question in the upper view of the advertisement playback interface, and playing the audio of the target question.

[0020] Optionally, after calculating the matching degree between the answer to be tested and each target answer of the target question as the target matching degree, the method further includes: if the target matching degree between the answer to be tested and each target answer is less than the matching degree threshold, recording the number of responses to the answer to be tested; if the number of responses to the answer to be tested is greater than a third value, sending the answer to be tested to the server so that the server counts the total number of responses to the answer to be tested by each user; if the total number of responses is greater than a fourth value, generating page retrieval information for the answer to be tested; after obtaining a new landing page generated based on the page retrieval information, recording the answer to be tested as a new target answer in the advertising feature library, and recording the new target answer corresponding to the new landing page.

[0021] In a second aspect of the invention, a page display device is also provided, the device being applied to a terminal, the device comprising:

[0022] The question acquisition module is used to acquire the question corresponding to the target advertisement as the target question in response to the display instruction for the target advertisement during the playback of the target advertisement;

[0023] The problem display module is used to display the text of the target problem and / or play the audio of the target problem;

[0024] The voice acquisition module is used to convert the acquired answer voice into answer text in response to the acquired answer voice, so as to obtain the answer to be detected for the target question;

[0025] The answer detection module is used to calculate the matching degree between the answer to be detected and each target answer of the target question, as the target matching degree; wherein, the target answer is pre-configured information associated with the content of the target advertisement; different target answers correspond to different landing pages of the target advertisement;

[0026] The first page display module is used to display the landing page of the target advertisement corresponding to the target answer if the target matching degree between the answer to be detected and any target answer is greater than the matching degree threshold.

[0027] Optionally, the question acquisition module is specifically configured to: during the playback of the target advertisement, in response to a display instruction for the target advertisement, detect whether voice recognition permission has been enabled; if voice recognition permission is enabled, acquire the question corresponding to the target advertisement as the target question; if voice recognition permission is not enabled, display a permission enabling prompt page; wherein the permission enabling prompt page displays an operation button for enabling voice recognition permission; in response to a preset operation on the operation button, enable voice recognition permission and acquire the question corresponding to the target advertisement as the target question.

[0028] Optionally, the question acquisition module is specifically used to: according to the correspondence between advertisements and questions, acquire the question corresponding to the target advertisement from the advertisement question library as the target question; wherein, the advertisement question library includes the questions corresponding to each advertisement.

[0029] Optionally, the device further includes: an answer acquisition module, configured to, before the answer detection module performs the calculation of the matching degree between the answer to be detected and each target answer of the target question, and uses it as the target matching degree, perform the acquisition of the target answer of the target question from the advertising feature library according to the correspondence between the question and the answer; wherein, the advertising feature library includes the answers to the questions corresponding to each advertisement; the target answer includes at least one tag keyword associated with the content of the target advertisement.

[0030] Optionally, the answer detection module is specifically used for: segmenting the answer to be detected into words, and determining the keywords to be detected from the segmentation results; for each target answer to the target question, determining the tag keywords that match the keywords to be detected from the target answer, as target keywords; wherein, the target keywords include: keywords that are the same as the keywords to be detected, or synonyms of the keywords to be detected; and calculating the matching degree between the answer to be detected and the target answer based on the target keywords, as the target matching degree.

[0031] Optionally, the answer detection module is specifically used to: determine the number of target keywords, obtain the matching degree between the answer to be detected and the target answer, and use it as the target matching degree; or, calculate the weighted sum of the importance of the target keywords according to the preset weight of each tag keyword, obtain the matching degree between the answer to be detected and the target answer, and use it as the target matching degree.

[0032] Optionally, the device further includes:

[0033] The first count module is used to, after the question display module displays the text of the target question and / or plays the audio of the target question, if no audio response is obtained within a first preset time period, count the number of times the target question has been displayed as the first count;

[0034] The first triggering module is configured to, if the first number is less than the first value, obtain the question corresponding to the target advertisement as the target question, and trigger the question display module to execute the steps of displaying the text of the target question and / or playing the audio of the target question;

[0035] The second page display module is used to display the default landing page of the target advertisement if the first number is greater than the first value.

[0036] Optionally, the device further includes:

[0037] The second count module is used to calculate the matching degree between the answer to be detected and each target answer of the target question in the answer detection module, and then, if the target matching degree between the answer to be detected and each target answer is less than the matching degree threshold, obtain the number of times the target question has been displayed, and use it as the second count.

[0038] The second triggering module is used to, if the second number is less than the second value, obtain a new question corresponding to the target advertisement as the target question, and trigger the question display module to perform the steps of displaying the text of the target question and / or playing the audio of the target question;

[0039] The third page display module is used to display the default landing page of the target advertisement if the second count is greater than the second value.

[0040] Optionally, the device further includes:

[0041] The stop playback module is used to stop playing the target advertisement before the problem display module displays the text of the target problem and / or plays the audio of the target problem.

[0042] Optionally, the question display module is specifically used to: continue playing the image and audio of the target advertisement, and display the text of the target question in the upper view of the advertisement playback interface; or; continue playing the image of the target advertisement and stop playing the audio of the target advertisement; play the audio of the target question; or; continue playing the image of the target advertisement and stop playing the audio of the target advertisement; display the text of the target question in the upper view of the advertisement playback interface, and play the audio of the target question.

[0043] Optionally, the device further includes:

[0044] The response count acquisition module is used to calculate the matching degree between the answer to be detected and each target answer of the target question in the answer detection module, and use it as the target matching degree. Then, if the target matching degree between the answer to be detected and each target answer is less than the matching degree threshold, the response count of the answer to be detected is recorded.

[0045] The answer update module is used to send the answer to be tested to the server if the number of responses to the answer to be tested is greater than a third value, so that the server can count the total number of responses to the answer to be tested by each user. If the total number of responses is greater than a fourth value, the module generates page retrieval information for the answer to be tested. After obtaining a new landing page generated based on the page retrieval information, the module records the answer to be tested as a new target answer in the advertising feature library and records the correspondence between the new target answer and the new landing page.

[0046] In another aspect of the present invention, a terminal is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus.

[0047] Memory, used to store computer programs;

[0048] When a processor executes a program stored in memory, it implements any of the page display method steps described above.

[0049] In another aspect of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored therein, and the computer program, when executed by a processor, implements any of the page display methods described above.

[0050] In another aspect of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the page display methods described above.

[0051] The technical solution provided in this invention, during the playback of a target advertisement, responds to a display instruction for the target advertisement by obtaining the question corresponding to the target advertisement as the target question; displaying the text of the target question, and / or playing the audio of the target question; responding to the obtained audio response, converting the audio response into audio response to obtain the answer to be tested for the target question; calculating the matching degree between the answer to be tested and each target answer of the target question as the target matching degree; the target answer is pre-configured information associated with the content of the target advertisement; different target answers correspond to different landing pages of the target advertisement; if the target matching degree between the answer to be tested and any target answer is greater than the matching degree threshold, the landing page of the target advertisement corresponding to that target answer is displayed.

[0052] Based on the above processing, the user's answer to be tested can reflect the information of the target advertisement that the user needs to know. The matching degree between the answer to be tested and the target answer is greater than the matching degree threshold. The landing page corresponding to the displayed target answer is a landing page that matches the user's answer to be tested, that is, a landing page containing the information of the target advertisement that the user needs to know can be displayed, meeting the user's personalized needs and improving the user experience. Furthermore, compared to existing technologies where one advertisement displays one fixed landing page, and multiple advertisements need to be placed to display multiple landing pages for an advertisement, this embodiment of the invention can display multiple landing pages for advertisements according to the user's needs, which can improve page display efficiency. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0054] Figure 1 This is a flowchart of the first page display method provided in the embodiments of the present invention;

[0055] Figure 2 This is a schematic diagram of a first interface provided in an embodiment of the present invention;

[0056] Figure 3 This is a flowchart of the second page display method provided in this embodiment of the invention;

[0057] Figure 4 This is a schematic diagram of a permission enabling prompt page provided in an embodiment of the present invention;

[0058] Figure 5 A schematic diagram of a problem display page provided in an embodiment of the present invention;

[0059] Figure 6 This is a flowchart of the third page display method provided in this embodiment of the invention;

[0060] Figure 7 This is a flowchart of the fourth page display method provided in this embodiment of the invention;

[0061] Figure 8 This is a structural diagram of a page display device provided in an embodiment of the present invention;

[0062] Figure 9 This is a structural diagram of a terminal provided in an embodiment of the present invention. Detailed Implementation

[0063] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention.

[0064] In related technologies, each advertisement corresponds to a fixed landing page. Showing the same landing page to all users fails to meet the personalized needs of different users and degrades the user experience.

[0065] To address the aforementioned issues, this invention provides a page display method. During the playback of a target advertisement, if a display instruction for the target advertisement is detected, in response to the instruction, the terminal obtains the target question corresponding to the target advertisement and asks the user the question. Based on the user's voice response, a landing page for the target advertisement that matches the user's needs is displayed, satisfying the user's personalized requirements and improving the user experience. Furthermore, compared to existing technologies where one advertisement displays one fixed landing page, requiring multiple advertisements to be displayed to achieve multiple landing pages, this invention can display multiple landing pages according to the user's needs, improving page display efficiency.

[0066] See Figure 1 , Figure 1 A flowchart of a page display method provided in an embodiment of the present invention, the method comprising the following steps:

[0067] S101: During the playback of the target advertisement, in response to the display instruction for the target advertisement, obtain the question corresponding to the target advertisement as the target question.

[0068] S102: Display the text of the target question, and / or play the audio of the target question.

[0069] S103: In response to the acquired answer speech, convert the answer speech into answer text to obtain the answer to be detected for the target question.

[0070] S104: Calculate the matching degree between the answer to be tested and each target answer of the target question, and use it as the target matching degree.

[0071] The target answer is pre-configured information associated with the content of the target ad; different target answers correspond to different landing pages for the target ad.

[0072] S105: If the target matching degree between the answer to be detected and any target answer is greater than the matching degree threshold, display the landing page of the target advertisement corresponding to that target answer.

[0073] Based on the page display method provided in this embodiment of the invention, the user's answer to be tested can reflect the information of the target advertisement that the user needs to know. The matching degree between the answer to be tested and the target answer is greater than a matching degree threshold. The landing page corresponding to the displayed target answer is a landing page that matches the user's answer to be tested, that is, a landing page containing the information of the target advertisement that the user needs to know can be displayed, meeting the user's personalized needs and improving the user experience. Furthermore, compared to the prior art where one advertisement displays one fixed landing page, and multiple advertisements need to be placed to display multiple landing pages for an advertisement, this embodiment of the invention can display multiple landing pages for advertisements according to the user's needs, improving page display efficiency.

[0074] In step S101, the terminal plays an advertisement before responding to the target service. For example, when a user wants to watch a target video, they input a playback command for the target video into the terminal. Before playing the target video, the terminal plays a target advertisement on the first interface. The target advertisement is set according to service requirements and is intended to be played when the target video is played.

[0075] After the terminal starts playing the target advertisement, if the user is interested in it, the user can input a display command for the target advertisement into the terminal. For example, the first screen displays an operation button for entering the landing page of the target advertisement. After the user clicks the operation button, the terminal receives the user's input command for displaying the target advertisement.

[0076] See Figure 2 , Figure 2 This is a schematic diagram of a first interface provided in an embodiment of the present invention. Figure 2 The terminal is playing a car advertisement. The first screen also displays an operation button 201 for skipping the advertisement (i.e., skipping the advertisement after 110 seconds) and an operation button 202 for entering the advertisement page. When the user clicks the operation button 202, the terminal detects the user's click operation, determines that it has received a display instruction for the target advertisement, and then determines that the landing page of the target advertisement needs to be displayed.

[0077] In response to a display instruction for a target advertisement, the terminal obtains the question corresponding to the target advertisement as the target question.

[0078] In some embodiments, when playing a target advertisement, it is necessary to call the speaker when the target question is played to the user in subsequent voice messages, and to call the microphone when obtaining the user's answer voice. Therefore, it is necessary to enable the permission to call the microphone and the permission to call the speaker, which is to enable the voice recognition permission.

[0079] Enable voice recognition permissions on the terminal as follows:

[0080] In one implementation, during the playback of the target advertisement, the terminal displays a permission activation prompt page, which includes an operation button for enabling voice recognition permission. Accordingly, if the user enables voice recognition permission, a preset operation (such as clicking) is performed on the operation button. Upon receiving the user's preset operation on the operation button, the terminal activates voice recognition permission.

[0081] In another implementation, Figure 1 Based on this, see Figure 3 Step S101 includes the following steps:

[0082] S1011: During the playback of the target advertisement, in response to the display instruction for the target advertisement, detect whether voice recognition permission has been enabled.

[0083] S1012: If voice recognition permission is detected to be enabled, obtain the question corresponding to the target advertisement and use it as the target question.

[0084] S1013: If it is detected that voice recognition permission is not enabled, a permission enabling prompt page is displayed; the permission enabling prompt page displays an operation button for enabling voice recognition permission; in response to the preset operation of the operation button, voice recognition permission is enabled, and the question corresponding to the target advertisement is obtained as the target question.

[0085] Voice recognition permissions include permission to access the microphone and permission to access the speaker. Voice recognition permissions are enabled when both microphone and speaker permissions are enabled.

[0086] If voice recognition permission is detected, the microphone and speaker can be directly accessed, and the terminal can then obtain the target question corresponding to the target advertisement.

[0087] If voice recognition permission is not enabled, the system cannot use the speaker to play the target question to the user, nor can it use the microphone to capture the user's voice response, thus preventing the user from skipping advertisements. The terminal displays a permission enabling prompt page, which includes buttons for enabling voice recognition permission.

[0088] Correspondingly, if the user enables voice recognition permission, a preset action (such as a click) will be performed on the operation button. After receiving the user's preset action on the operation button, the terminal enables voice recognition permission and stops playing the target advertisement. Then, it obtains the target question corresponding to the target advertisement.

[0089] See Figure 4 , Figure 4This is a schematic diagram of a permission enabling prompt page provided in an embodiment of the present invention. The permission enabling prompt page is displayed as a pop-up window in the upper view of the first interface. The permission enabling prompt page displays the prompt message "Allow microphone and speaker access?", an operation button 401 for allowing microphone and speaker access under any circumstances, an operation button 402 for allowing microphone and speaker access during operation, and an operation button 403 for disabling microphone and speaker access.

[0090] Both operation buttons 402 and 403 are used to enable voice recognition permissions. After detecting a user's click on operation button 402 or operation button 403, the terminal enables the use of the microphone and speaker.

[0091] In some embodiments, if the terminal detects that voice recognition permission has been enabled, the voice recognition permission may be enabled by displaying a permission activation prompt page on the terminal when launching the application providing the target service, and by following the user's instructions on the permission activation prompt page. The target service is the service that the terminal needs to respond to after the advertisement finishes playing. For example, if the target service is a video playback service, then the application providing the target service is a video application.

[0092] Alternatively, voice recognition permissions can be set by the user through a permission settings page. For example, when a user needs to enable voice recognition permissions, they input a command to the terminal to display the settings page. Upon receiving the command, the settings page is displayed, showing an operation button for enabling voice recognition permissions. If the user needs to enable voice recognition permissions, they perform a preset operation (such as clicking) on ​​that operation button. After receiving the user's preset operation on the operation button, the terminal enables voice recognition permissions.

[0093] Based on the above processing, if voice recognition permission is already enabled, the target question can be obtained directly. The user will only be prompted to enable voice recognition permission when it is not enabled. This eliminates the need to prompt the user to enable voice recognition permission every time an advertisement is played, saving system resources on the terminal and improving the user experience.

[0094] In some embodiments, the terminal obtains the target question corresponding to the target advertisement in the following manner:

[0095] Based on the correspondence between advertisements and questions, the question corresponding to the target advertisement is retrieved from the advertisement question database and used as the target question. The advertisement question database includes questions corresponding to each advertisement.

[0096] The advertising question library includes questions for each advertisement, and the questions for different advertisements are set based on the advertiser's business needs.

[0097] For example, Ad 1 is an advertisement for car A. The questions corresponding to Ad 1 are: A1: What model of car do you like? A2: What price range of car do you need? A3: What aspects of the car's performance do you want to know about?

[0098] Advertisement 2 is an advertisement for phone B. The questions corresponding to advertisement 2 are: What features of the phone are you interested in? and what performance aspects of the phone would you like to know about?

[0099] In one implementation, an advertising question database is stored on a server, and a primary correspondence between advertisements and questions is also recorded on the server. The terminal sends a request to the server to retrieve the question corresponding to a target advertisement; this request carries the identifier of the target advertisement. Upon receiving the request, the server, based on the identifier of the target advertisement and according to the primary correspondence, determines the target question from the advertising question database and sends the target question to the terminal. The terminal receives the target question sent by the server.

[0100] The target ad corresponds to a single question. By directly retrieving this question, you obtain the target question. For example, if the target ad is for car A, the target question is: What performance features of car A would you like to know about?

[0101] A targeted advertisement might involve multiple questions, each describing the advertisement's content from different perspectives. For example, a targeted advertisement for car A might introduce its comfort features, safety features, and price advantages.

[0102] The target ad's corresponding question 1 is: What performance features of car A would you like to know? The target ad's corresponding question 2 is: What is your expected price range for car A? The target ad's corresponding question 3 is: What configuration of car A would you like to know?

[0103] The target problem is obtained by randomly selecting a problem. For example, a completely random algorithm can be used to select a target problem. Alternatively, a pseudo-random algorithm can be used. The pseudo-random algorithm can be either a random algorithm or a shuffle algorithm.

[0104] Alternatively, based on the business requirements of the target advertisement, relevant questions are obtained to form the target questions. Technical staff pre-configure the display order of these target questions according to the business requirements of the target advertisement. Each time a question is posed to a user, the target questions are retrieved sequentially according to their display order.

[0105] For example, in the example above, if the target ad's business requirement is primarily to promote the performance advantages of car A, followed by its price advantages, and finally its configuration advantages, then the display order of the target questions would be: Question 1, Question 2, Question 3.

[0106] Based on the above processing, the advertising problem database is set up on the server without occupying the local memory of the terminal, saving the terminal's system resources and improving the user experience.

[0107] Regarding step S102, in one implementation, if the target advertisement is short, to avoid the target advertisement finishing playing before the user completes their question, the terminal stops playing the target advertisement before displaying the target question.

[0108] After the target advertisement stops playing, the terminal displays the target question in the following manner:

[0109] Method 1: The terminal displays the text of the target question. For example, the terminal displays a pop-up window containing the text of the target question in the upper view of the first interface.

[0110] Method 2: The terminal plays the audio of the target question.

[0111] Method 3: The terminal displays the text of the target question and plays the audio of the target question.

[0112] For example, see Figure 5 , Figure 5 This is a schematic diagram of a problem display page provided in an embodiment of the present invention. Figure 5 The pop-up window 501 displays the text of the target question, "What performance features of phone B would you like to know?", and the terminal plays the audio of the target question through the speaker, "What performance features of phone B would you like to know?"

[0113] In another implementation, if the target advertisement is long and will not finish playing before the user completes their question, the terminal will not stop playing the target advertisement. Instead, while playing the target advertisement, the target question will be displayed in the following manner.

[0114] In Method 1, when only the text of the target question is displayed, the terminal can continue playing the images and audio of the target advertisement. For example, a pop-up containing the text of the target question can be displayed only in the upper view of the advertisement playback interface.

[0115] Method Two: When playing only the audio of the target question, to avoid conflict between the audio of the target advertisement and the audio of the target question, the terminal continues to play the image of the target advertisement but stops playing the audio of the target advertisement. For example, the target advertisement is muted.

[0116] Method 3: While displaying the text of the target question and playing its audio, to avoid conflicts between the audio of the target ad and the audio of the target question, continue playing the image of the target ad and stop playing its audio. For example, display the text of the target question in the upper view of the ad playback interface and play its audio.

[0117] In step S103, after displaying the text of the target question and / or playing the audio of the target question, the terminal activates its microphone to acquire the user's voice input. After acquiring the user's voice input, the terminal converts the voice input into text (i.e., the answer text) to obtain the answer to be tested for the target question.

[0118] Regarding step S104, the landing page for the target ad is a page containing detailed information about the target ad. One target question can correspond to multiple target answers.

[0119] The target answer is pre-configured information associated with the content of the target advertisement; this pre-configured information is determined based on business needs. Different target answers include at least one tag keyword that describes the content of the target advertisement from different perspectives. One target answer corresponds to one landing page for a target advertisement, which contains the content of the target advertisement described by the corresponding target answer.

[0120] For example, Ad 1 is an advertisement for car A. The corresponding question A1 for Ad 1 is: What performance advantages of car A would you like to know about? The keywords in Answer 1 for Question A1 include: safety and comfort. The landing page for Answer 1 includes information about the safety and comfort aspects of car A. The keywords in Answer 2 for Question A1 include: shock absorption and noise reduction. The landing page for Answer 2 includes information about the shock absorption and noise reduction aspects of car A.

[0121] Question A2 is: What features of car A would you like to know? The keywords in answer 1 for question A2 include: engine, chassis. The landing page for answer 1 includes information about car A's engine and chassis. The keywords in answer 2 for question A2 include: battery. The landing page for answer 2 includes information about car A's battery.

[0122] Advertisement 2 is for merchandise related to the B anime series. The corresponding question for Advertisement 2 is: Which character from the B anime do you like? The first answer to Question B1 contains the keyword "Character 1". The landing page for Answer 1 includes information about merchandise related to Character 1. The second answer to Question B1 contains the keyword "Character 2". The landing page for Answer 2 includes information about merchandise related to Character 2.

[0123] Question B2 is: Which look of character 1 in animation B do you like best? The answer to Question B2 includes the keywords: "Look 1" and "Look 2". The landing page for this answer includes introductions to merchandise featuring character 1 in looks 1 and look 2.

[0124] The terminal retrieves the target answer to the target question from the advertising feature database according to the correspondence between questions and answers (which can be called the second correspondence). The advertising feature database includes: the answers to the questions corresponding to each preset advertisement.

[0125] In one implementation, an advertising feature database is stored on a server, and a second correspondence is also recorded on the server. The terminal sends a request to the server to obtain the target answer to a target question; this request carries the identifier of the target question. Upon receiving the request, the server determines the target answer to the target question from the advertising feature database based on the target question identifier and the second correspondence, and then sends the target answer to the terminal. The terminal receives the target answer sent by the server.

[0126] Based on the above processing, the advertising feature library is set on the server without occupying the local memory of the terminal, saving the terminal's system resources and improving the user experience.

[0127] In some embodiments, a knowledge graph for multi-dimensional question answering can be pre-constructed based on a first correspondence between advertisements and questions, a second correspondence between questions and answers, and a third correspondence between answers and landing pages. For example, advertisements, questions, answers, and landing pages can be used as nodes in the knowledge graph. The connections between these nodes can be determined based on the three correspondences mentioned above, resulting in a knowledge graph that records these three correspondences. Subsequently, when a terminal requests a target question (or target answer) from the server, the server can query this knowledge graph to obtain the target question (or target answer) requested by the terminal, enabling unified management of advertisements, questions, answers, and landing pages.

[0128] The terminal can calculate the matching degree between the answer to be detected and each target answer in the following way:

[0129] In one implementation, after obtaining the user's input speech, an ASR (Automatic Speech Recognition) model is used to convert the speech into text, thus obtaining the answer to the target question.

[0130] Then, use the text vectorization algorithm to vectorize the answer text to obtain the feature vector of the answer to be detected. For each target answer, use the text vectorization algorithm to vectorize the target answer to obtain the feature vector of the target answer. Calculate the similarity between the feature vector of the answer to be detected and the feature vector of the target answer as the target matching degree between the answer to be detected and the target answer. Among them, the text vectorization algorithm can be the word2vec (word to vector) algorithm.

[0131] In another implementation, based on Figure 1 and referring to Figure 6 , before step S104, the method may include the following steps:

[0132] S106: According to the correspondence between the question and the answer, obtain the target answer of the target question from the advertisement feature library.

[0133] Among them, the advertisement feature library includes the answers to the questions corresponding to each advertisement; the target answer includes at least one label keyword associated with the content of the target advertisement.

[0134] Correspondingly, step S104 may include the following steps:

[0135] S1041: Segment the answer to be detected and determine the keywords to be detected from the segmentation result.

[0136] S1042: For each target answer of the target question, determine the label keyword that matches the keyword to be detected from the target answer as the target keyword.

[0137] Among them, the target keyword includes: the keyword that is the same as the keyword to be detected, or the synonym of the keyword to be detected.

[0138] S1043: Based on the target keyword, calculate the matching degree between the answer to be detected and the target answer as the target matching degree.

[0139] The terminal segments the answer to be detected according to the preset segmentation algorithm and removes the preset stop words from the segmentation result to obtain the keywords to be detected. For example, the preset segmentation algorithm is the jieba segmentation algorithm. The preset stop words are set by technicians according to business requirements. For example, the preset stop words include: "is", "of", "and", "了" etc.

[0140] Or,

[0141] The terminal segments the answer to be detected according to a preset word segmentation algorithm and removes preset stop words from the segmentation results. From the segmentation results after removing preset stop words, keywords that describe the content of the target advertisement from the aspects required by the target question are determined, and these are the keywords to be detected.

[0142] For example, if the target question is "What performance advantages of car A would you like to know?", then keywords describing car performance are extracted from the word segmentation results of the answer to be tested and used as the keywords to be tested. If the target question is "Which color of phone B do you like?", then keywords describing color are extracted from the word segmentation results of the answer to be tested and used as the keywords to be tested.

[0143] In one implementation, each keyword (which can be called the target keyword) in the tag keywords of the target answer is obtained. For each keyword (which can be called the candidate keyword) in the word segmentation result after removing preset stop words, if the candidate keyword contains the target keyword, it can be determined that the candidate keyword is a keyword that describes the content of the target advertisement from the aspects required by the target question, that is, the keyword to be detected.

[0144] Each target answer includes tag keywords that describe the target advertisement from different perspectives. Accordingly, for each target answer, the terminal can determine the tag keywords that are the same as the keyword to be detected, or the tag keywords that are synonyms of the keyword to be detected, from that target answer to obtain the target keyword.

[0145] For example, the target ad is for phone B. The target question is: What performance advantages of phone B would you like to know? The answers to the target question are: charging speed and camera. The user's answers include the keywords to be detected: charging speed and camera. The terminal can determine that "camera" is a synonym for "camera". Therefore, the target keywords are: charging speed and camera.

[0146] In one implementation, the terminal determines the number of target keywords as the target matching degree between the answer to be detected and the target answer.

[0147] In another implementation, the terminal obtains the preset weights of each tag keyword in the target answer, and calculates the weighted sum of the importance of the target keywords according to the preset weights of each tag keyword, so as to obtain the target matching degree between the answer to be detected and the target answer of the target question.

[0148] You can assign the same importance to all tag keywords, or you can assign different importance to each tag keyword based on business needs. The preset weight of tag keywords can also be set based on business requirements.

[0149] For example, the target ad is for phone B. The target question is: What performance advantages of phone B would you like to know? The answers to the target question are: charging speed and camera. Since the business need of the target ad is to promote the camera performance of phone B, the keyword "camera" is assigned a higher importance, while the keyword "charging speed" is assigned a lower importance.

[0150] Based on the above processing, fuzzy matching is performed between the keywords to be detected in the answer to be tested and the tag keywords in the target answer. This avoids inconsistencies between the user's answer to be tested and the target answer, which could lead to an inability to determine a landing page that meets the user's needs. This prevents the display of landing pages that do not meet user needs and improves user experience. Furthermore, matching based on the semantics of the answer to be tested improves matching accuracy. Additionally, the target matching degree is determined according to the importance of the target keywords. The importance of the target keywords is set according to business needs to meet those needs and ensure effective ad playback.

[0151] Regarding step S105, when the target matching degree between the answer to be detected and any target answer is greater than the matching degree threshold, it can be determined that the user wants to learn about the target advertisement from the aspects described by the target answer, and then the landing page of the target advertisement corresponding to the target answer is displayed.

[0152] For example, the terminal sends the identifier of the target answer to the server. The server determines the landing page corresponding to the target answer based on the mapping between the target answer and the landing page (i.e., the third mapping). The server obtains the page data of the landing page and sends it to the terminal. Accordingly, after receiving the page data, the terminal displays the landing page according to the received data.

[0153] The matching threshold is preset according to business needs.

[0154] In one implementation, when determining the target match degree based on the number of target keywords, the match degree threshold is determined based on the number of tag keywords in the target answer. For example, if the number of tag keywords in the target answer is 3, the match degree threshold is 2. If the number of tag keywords in the target answer is 5, the match degree threshold is 3.

[0155] In another implementation, when determining the target relevance based on the importance of the target keywords, the relevance threshold is determined based on the total importance of all tag keywords. For example, the relevance threshold could be 60% of the total importance of all tag keywords.

[0156] In some embodiments, if the user cannot answer the target question correctly, that is, if the answer to be tested does not match any of the target answers, the terminal can adjust the target question and ask the user again. Accordingly, after step S104, the method may further include the following steps:

[0157] If the target matching degree between the answer to be tested and each target answer is less than the matching degree threshold, obtain the number of times the target question is displayed as the second count; if the second count is less than the second value, obtain the new question corresponding to the target advertisement as the target question, and return to the steps of displaying the text of the target question and / or playing the audio of the target question; if the second count is greater than the second value, display the default landing page of the target advertisement.

[0158] When the target match degree between the answer to be tested and each target answer is less than the match degree threshold, it indicates that no landing page matching the user's needs has been determined based on the current target question. The terminal can obtain the number of times the target question has been displayed (i.e., the second count). If the second count is less than the second value, it indicates that the number of times the question has been asked to the user is insufficient. In order to determine the landing page matching the user's needs, the terminal obtains a new question corresponding to the target advertisement as the target question. The terminal displays the text of the new target question and / or plays the audio of the target question, asking the user the question again, and determines which landing page of the target advertisement to display based on the user's audio response.

[0159] For example, the target ad is for phone B. The initial target question is: What performance advantages of phone B would you like to know? After the user's test results do not match any of the target answers, another question from the target ad, "What color phone B do you like?", is obtained as the new target question.

[0160] If the second count is greater than the second value, it indicates that the user has been asked questions multiple times, and the user's expected answer does not match any of the target answers. This means that there is currently no landing page that meets the user's needs, so the questioning stops, and the terminal displays the default landing page of the target advertisement. The default landing page is different from the landing pages corresponding to each target answer. The default landing page contains the main content of the target advertisement set according to business requirements.

[0161] The second number refers to the total number of times each target question is displayed. This second value is set based on business needs. To display the target ad's landing page as quickly as possible, the second value can be set to a smaller value, for example, 2. To ensure that a landing page that meets user needs is obtained, a larger value can be set, for example, 4.

[0162] Based on the above processing, when the answer to be tested does not match any of the target answers and the number of questions asked is low, the system continues to ask the user questions to obtain a landing page that meets the user's needs, thus improving the user experience. If the number of questions asked is high, in order to display the landing page as quickly as possible, the system stops asking the user questions and directly displays the default landing page, avoiding the problem of long questioning times affecting the user's browsing of the landing page and improving the user experience.

[0163] In some embodiments, after the terminal asks a question to the user, there may be a situation where the user's voice response is not received, for example, the user did not have time to answer. The terminal may ask the user a question again. Accordingly, after step S103, the method may further include the following steps:

[0164] If no answer is received within the first preset time period, the number of times the target question is displayed is obtained as the first count; if the first count is less than the first value, the question corresponding to the target advertisement is obtained as the target question, and the steps of displaying the text of the target question and / or playing the audio of the target question are returned; if the first count is greater than the first value, the default landing page of the target advertisement is displayed.

[0165] If no user-inputted voice response is received within the first preset time period, it may be because the user did not provide a voice response. In this case, the number of times the target question was displayed (i.e., the first time count) is recorded. The first preset time period is set according to business requirements.

[0166] If the first count is less than the first value, it indicates that fewer questions were asked to the user. In order to obtain a landing page that meets the user's needs, the terminal retrieves the question corresponding to the target advertisement again as the target question. Since no user's voice response was received, it cannot be determined whether the user's answer to the current target question can match the corresponding landing page. Therefore, the target question retrieved this time can be the same as the previous question or a different question.

[0167] Then, the terminal displays the text of the target question, and / or plays the audio of the target question, asks the user the question again, and obtains the user's audio response again, and determines which landing page of the target advertisement to display based on the user's audio response.

[0168] If the first count is greater than the first value, it indicates that multiple questions have been asked to the user without obtaining their voice response. This may be due to a microphone malfunction on the device, preventing the acquisition of the user's voice reply. The device then stops asking questions and displays the default landing page for the target advertisement.

[0169] The first count refers to the total number of times each target question is displayed. This first value is set according to business requirements. The first value can be the same as or different from the second value.

[0170] Based on the above processing, if no voice response is received from the user and the number of questions is low, continuing to ask the user questions to obtain a landing page that meets their needs can improve the user experience. To display the landing page as quickly as possible, no more questions are asked; the default landing page is displayed directly. This avoids prolonged questioning time, which could hinder the user's browsing of the landing page and further improve the user experience.

[0171] In some embodiments, after step S104, the method may further include the following steps:

[0172] If the target matching degree between the answer to be tested and each target answer is less than the matching degree threshold, the number of times the answer to be tested is answered is recorded. If the number of times the answer to be tested is answered is greater than the third value, the answer to be tested is sent to the server so that the server can count the total number of times each user answers the answer to be tested. If the total number of times the answer is greater than the fourth value, the page retrieval information of the answer to be tested is generated. After obtaining the new landing page generated based on the page retrieval information, the answer to be tested is recorded as the new target answer in the advertising feature library, and the new target answer and the new landing page are recorded.

[0173] If the target match score between the answer to be tested and each target answer is less than the match score threshold, it indicates that there is currently no landing page corresponding to the answer to be tested. The terminal records the number of times the answer to the answer to be tested has been answered. This number of answers represents the number of times the same user has answered.

[0174] When the number of responses to the answer to be tested exceeds the third value, it indicates a strong demand from the user for the landing page corresponding to the answer to be tested, and the terminal sends the answer to be tested to the server. The third value is set by technical personnel according to business needs.

[0175] The server tracks the total number of responses from each user to the answer to be tested. When the total number of responses exceeds a fourth threshold, it generates page retrieval information for the answer to be tested. This page retrieval information includes the keywords to be tested in the answer and the total number of responses to the answer. This information is used to guide technical staff in designing landing pages for target ads based on the keywords in the answer. Subsequently, based on the page retrieval information generated by the server, technical staff design landing pages for target ads corresponding to the answer to be tested, resulting in new landing pages.

[0176] Next, the server retrieves a new landing page generated based on the page retrieval information of the answer to be tested. This new landing page is the landing page corresponding to the answer to be tested. After retrieving the new landing page generated based on the page retrieval information, the server records the answer to be tested as the new target answer in the advertising question database and records the new target answer and the new landing page corresponding to it.

[0177] Based on the above processing, new landing pages can be designed based on the user's answer to the test, ensuring the diversity of landing pages and continuously enriching the landing pages of target ads to meet the personalized needs of more users and further improve the user experience.

[0178] See Figure 7 See Figure 7 , Figure 7 A flowchart illustrating a page display method provided in an embodiment of the present invention.

[0179] S701: Advertising display.

[0180] S702: Determine whether the advertising audio is enabled. If yes, proceed to step S704.

[0181] S703: Voice Question Answering Knowledge Graph.

[0182] S704: Question about advertising.

[0183] S705: Obtain user voice response.

[0184] S706: Determine whether the acquisition was successful. If yes, proceed to step S707; otherwise, proceed to step S704.

[0185] S707: Speech parsing semantics.

[0186] S708: Determine if the answer exists. If yes, proceed to step S709; otherwise, proceed to step S704.

[0187] S709: Get Answers - Landing Page Mapping Matrix

[0188] S710: Get a personalized landing page.

[0189] S711: Failed to retrieve voice information n times; or, no answer was found after n attempts to ask questions.

[0190] S712: Get the default landing page.

[0191] S713: Display landing page.

[0192] The above method is implemented through a user-side, a parsing layer, and an intelligent decision-making layer. The user-side interacts with the user via voice. The parsing layer analyzes the interactive voice based on a voice knowledge graph. The intelligent decision-making layer provides personalized landing page recommendations based on the voice parsing results.

[0193] In step S701, the terminal displays the advertisement during the advertisement display stage, which means playing the target advertisement.

[0194] For steps S702 to S710: During the voice interaction phase, it is determined whether the advertising voice is enabled, that is, whether the voice recognition permission is enabled. If the voice recognition permission is not enabled, the user is prompted to "start the voice recognition function". After the voice recognition permission is enabled, the advertisement pauses playback and the user asks a question by voice.

[0195] The terminal obtains the target question corresponding to the target advertisement based on the voice question-answering knowledge graph (i.e., the advertising question library), and asks the advertisement question, that is, displays the text of the target question, and / or plays the voice of the target advertisement.

[0196] Then, the system retrieves the user's voice response and determines whether the retrieval was successful. If the user's voice response is successfully retrieved, the semantics of the response are parsed to obtain the answer to the target question. If the user's voice response is not retrieved, the advertisement question is asked again, and so on, looping n times, where n≥0.

[0197] The process involves determining if an answer exists, specifically whether a target answer matches the answer being tested. If a target answer exists, the personalized landing page corresponding to that target answer is retrieved based on the answer-landing page mapping matrix (i.e., the third correspondence). If no target answer exists, the ad question is asked again, and this process is repeated n times, where n ≥ 0.

[0198] For steps S711 to S713: After obtaining the personalized landing page, display it. If obtaining the voice recording fails after n attempts, or if the user's answer does not exist after n attempts, it is determined that a personalized landing page that meets the user's needs cannot be obtained. In this case, obtain the default landing page and display it.

[0199] Based on the page display method provided in this invention, a combination of natural language processing and dynamic routing is used to analyze the characteristics of user voice content in real time, enabling precise redirection to the advertising landing page. Furthermore, the integration of voice interaction and advertising display can quickly capture user interests. Personalized landing pages can be accessed for each user and each question, thereby accurately identifying user needs and ultimately improving advertising conversion rates.

[0200] See Figure 8 , Figure 8 This is a structural diagram of a page display device provided in an embodiment of the present invention. The device is applied to a terminal and includes:

[0201] The question acquisition module 801 is used to acquire the question corresponding to the target advertisement as the target question in response to the display instruction for the target advertisement during the playback of the target advertisement.

[0202] The problem display module 802 is used to display the text of the target problem and / or play the audio of the target problem;

[0203] The voice acquisition module 803 is used to convert the acquired answer voice into answer text in response to the acquired answer voice, so as to obtain the answer to be detected for the target question;

[0204] The answer detection module 804 is used to calculate the matching degree between the answer to be detected and each target answer of the target question, as the target matching degree; wherein, the target answer is pre-configured information associated with the content of the target advertisement; different target answers correspond to different landing pages of the target advertisement;

[0205] The first page display module 805 is used to display the landing page of the target advertisement corresponding to the target answer if the target matching degree between the answer to be detected and any target answer is greater than the matching degree threshold.

[0206] Optionally, the question acquisition module 801 is specifically configured to: during the playback of the target advertisement, in response to a display instruction for the target advertisement, detect whether voice recognition permission has been enabled; if voice recognition permission is enabled, acquire the question corresponding to the target advertisement as the target question; if voice recognition permission is not enabled, display a permission enabling prompt page; wherein the permission enabling prompt page displays an operation button for enabling voice recognition permission; in response to a preset operation on the operation button, enable voice recognition permission and acquire the question corresponding to the target advertisement as the target question.

[0207] Optionally, the question acquisition module 801 is specifically used to: according to the correspondence between advertisements and questions, acquire the question corresponding to the target advertisement from the advertisement question library as the target question; wherein, the advertisement question library includes the questions corresponding to each advertisement.

[0208] Optionally, the device further includes:

[0209] The answer acquisition module is used to calculate the matching degree between the answer to be detected and each target answer of the target question before the answer detection module 804 calculates the matching degree as the target matching degree, and then retrieves the target answer of the target question from the advertising feature library according to the correspondence between the question and the answer; wherein, the advertising feature library includes the answers to the questions corresponding to each advertisement; the target answer includes at least one tag keyword associated with the content of the target advertisement.

[0210] Optionally, the answer detection module 804 is specifically used for: segmenting the answer to be detected into words, and determining the keywords to be detected from the segmentation results; for each target answer to the target question, determining the tag keywords that match the keywords to be detected from the target answer, as target keywords; wherein, the target keywords include: keywords that are the same as the keywords to be detected, or synonyms of the keywords to be detected; and calculating the matching degree between the answer to be detected and the target answer based on the target keywords, as the target matching degree.

[0211] Optionally, the answer detection module 804 is specifically used to: determine the number of target keywords, obtain the matching degree between the answer to be detected and the target answer, and use it as the target matching degree; or, calculate the weighted sum of the importance of the target keywords according to the preset weight of each tag keyword, obtain the matching degree between the answer to be detected and the target answer, and use it as the target matching degree.

[0212] Optionally, the device further includes:

[0213] The first count module is used to, after the question display module 802 displays the text of the target question and / or plays the audio of the target question, execute the following: if no audio response is obtained within a first preset time period, the first count is obtained.

[0214] The first triggering module is configured to, if the first number is less than the first value, obtain the question corresponding to the target advertisement as the target question, and trigger the question display module 802 to perform the steps of displaying the text of the target question and / or playing the audio of the target question;

[0215] The second page display module is used to display the default landing page of the target advertisement if the first number is greater than the first value.

[0216] Optionally, the device further includes:

[0217] The second count module is used to calculate the matching degree between the answer to be detected and each target answer of the target question in the answer detection module 804, and use it as the target matching degree. Then, if the target matching degree between the answer to be detected and each target answer is less than the matching degree threshold, the module obtains the number of times the target question is displayed, and uses it as the second count.

[0218] The second triggering module is used to, if the second number is less than the second value, obtain a new question corresponding to the target advertisement as the target question, and trigger the question display module 802 to perform the steps of displaying the text of the target question and / or playing the voice of the target question;

[0219] The third page display module is used to display the default landing page of the target advertisement if the second count is greater than the second value.

[0220] Optionally, the device further includes:

[0221] The stop playback module is used to stop playing the target advertisement before the problem display module 802 executes the process of displaying the text of the target problem and / or playing the audio of the target problem.

[0222] Optionally, the problem display module 802 is specifically used to: continue playing the image and audio of the target advertisement, and display the text of the target problem in the upper view of the advertisement playback interface; or; continue playing the image of the target advertisement and stop playing the audio of the target advertisement; play the audio of the target problem; or; continue playing the image of the target advertisement and stop playing the audio of the target advertisement; display the text of the target problem in the upper view of the advertisement playback interface, and play the audio of the target problem.

[0223] Optionally, the device further includes:

[0224] The response count acquisition module is used to calculate the matching degree between the answer to be detected and each target answer of the target question in the answer detection module 804, and use it as the target matching degree. Then, if the target matching degree between the answer to be detected and each target answer is less than the matching degree threshold, the module records the number of responses to the answer to be detected.

[0225] The answer update module is used to send the answer to be tested to the server if the number of responses to the answer to be tested is greater than a third value, so that the server can count the total number of responses to the answer to be tested by each user. If the total number of responses is greater than a fourth value, the module generates page retrieval information for the answer to be tested. After obtaining a new landing page generated based on the page retrieval information, the module records the answer to be tested as a new target answer in the advertising feature library and records the correspondence between the new target answer and the new landing page.

[0226] Based on the page display device provided in this embodiment of the invention, the user's answer to be tested can reflect the information of the target advertisement that the user needs to know. The matching degree between the answer to be tested and the target answer is greater than a matching degree threshold. The landing page corresponding to the displayed target answer is a landing page that matches the user's answer to be tested, that is, a landing page containing the information of the target advertisement that the user needs to know can be displayed, meeting the user's personalized needs and improving the user experience. Furthermore, compared to the prior art where one advertisement displays one fixed landing page, and multiple advertisements need to be placed to display multiple landing pages for an advertisement, this embodiment of the invention can display multiple landing pages for advertisements according to the user's needs, improving page display efficiency.

[0227] This invention also provides a terminal, such as... Figure 9 As shown, it includes a processor 901, a communication interface 902, a memory 903, and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904.

[0228] Memory 903 is used to store computer programs;

[0229] When processor 901 executes a program stored in memory 903, it performs the following steps:

[0230] During the playback of the target advertisement, in response to the display instruction for the target advertisement, the question corresponding to the target advertisement is obtained as the target question;

[0231] Display the text of the target question, and / or play the audio of the target question;

[0232] In response to the acquired answer speech, the answer speech is converted into answer text to obtain the target question's answer to be detected;

[0233] The matching degree between the answer to be detected and each target answer of the target question is calculated as the target matching degree; wherein, the target answer is pre-configured information associated with the content of the target advertisement; different target answers correspond to different landing pages of the target advertisement;

[0234] If the target matching degree between the answer to be detected and any target answer is greater than the matching degree threshold, the landing page of the target advertisement corresponding to the target answer is displayed.

[0235] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0236] The communication interface is used for communication between the aforementioned terminal and other devices.

[0237] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0238] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0239] In another embodiment of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored therein, and when the computer program is executed by a processor, it implements any of the page display methods described in the above embodiments.

[0240] In another embodiment of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the page display methods described in the above embodiments.

[0241] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0242] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0243] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for devices, terminals, computer-readable storage media, and computer program products are basically similar to the method embodiments, and therefore the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0244] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A page display method, characterized in that, The method is applied to a terminal, and the method includes: During the playback of the target advertisement, in response to the display instruction for the target advertisement, the question corresponding to the target advertisement is obtained as the target question; Display the text of the target question, and / or play the audio of the target question; In response to the acquired answer speech, the answer speech is converted into answer text to obtain the target question's answer to be detected; The matching degree between the answer to be detected and each target answer of the target question is calculated as the target matching degree; wherein, the target answer is pre-configured information associated with the content of the target advertisement; different target answers correspond to different landing pages of the target advertisement; If the target matching degree between the answer to be detected and any target answer is greater than the matching degree threshold, the landing page of the target advertisement corresponding to the target answer will be displayed.

2. The method according to claim 1, characterized in that, During the playback of the target advertisement, in response to a display instruction for the target advertisement, the method of obtaining a question corresponding to the target advertisement as the target question includes: During the playback of the target advertisement, in response to the display instruction for the target advertisement, it is detected whether voice recognition permission has been enabled; If voice recognition permission is detected to be enabled, obtain the question corresponding to the target advertisement and use it as the target question; If voice recognition permission is not enabled, a permission enabling prompt page is displayed; wherein, the permission enabling prompt page displays an operation button for enabling voice recognition permission; in response to a preset operation on the operation button, voice recognition permission is enabled, and the question corresponding to the target advertisement is obtained as the target question.

3. The method according to claim 2, characterized in that, The step of obtaining the question corresponding to the target advertisement, as the target question, includes: Based on the correspondence between advertisements and questions, the question corresponding to the target advertisement is obtained from the advertisement question database and used as the target question; wherein, the advertisement question database includes the questions corresponding to each advertisement.

4. The method according to claim 1, characterized in that, Before calculating the matching degree between the answer to be detected and each target answer of the target question, as the target matching degree, the method further includes: Based on the correspondence between questions and answers, the target answer to the target question is obtained from the advertising feature library; wherein, the advertising feature library includes the answers to the questions corresponding to each advertisement; the target answer includes at least one tag keyword associated with the content of the target advertisement.

5. The method according to claim 4, characterized in that, The calculation of the matching degree between the answer to be detected and each target answer of the target question, as the target matching degree, includes: The answer to be detected is segmented into words, and the keywords to be detected are determined from the segmentation results; For each target answer to the target question, a tag keyword that matches the keyword to be detected is determined from the target answer as the target keyword; wherein, the target keyword includes: a keyword that is the same as the keyword to be detected, or a synonym of the keyword to be detected; Based on the target keywords, the matching degree between the answer to be detected and the target answer is calculated, which is used as the target matching degree.

6. The method according to claim 5, characterized in that, The step of calculating the matching degree between the answer to be detected and the target answer based on the target keywords, as the target matching degree, includes: The number of target keywords is determined, and the matching degree between the answer to be detected and the target answer is obtained, which is used as the target matching degree; or, According to the preset weights of each tag keyword, the weighted sum of the importance of the target keyword is calculated to obtain the matching degree between the answer to be detected and the target answer, which is used as the target matching degree.

7. The method according to claim 1, characterized in that, After displaying the text of the target question and / or playing the audio of the target question, the method further includes: If no response voice is obtained within the first preset time period, the number of times the target question is displayed is obtained as the first count; If the first number is less than the first value, obtain the question corresponding to the target advertisement as the target question, and return to the steps of displaying the text of the target question and / or playing the audio of the target question; If the first count is greater than the first value, the default landing page of the target advertisement will be displayed.

8. The method according to claim 1, characterized in that, After calculating the matching degree between the answer to be detected and each target answer of the target question, as the target matching degree, the method further includes: If the target matching degree between the answer to be detected and each target answer is less than the matching degree threshold, the number of times the target question is displayed is obtained as the second count; If the second number is less than the second value, obtain a new question corresponding to the target advertisement as the target question, and return to the steps of displaying the text of the target question and / or playing the voice of the target question; If the second count is greater than the second value, the default landing page of the target advertisement will be displayed.

9. The method according to claim 1, characterized in that, Before displaying the text of the target question and / or playing the audio of the target question, the method further includes: Stop playing the target advertisement.

10. The method according to claim 1, characterized in that, The display of the text of the target question and / or the playback of the audio of the target question include: Continue playing the images and audio of the target advertisement, and display the text of the target question in the upper view of the advertisement playback interface; or; Continue playing the image of the target advertisement, and stop playing the audio of the target advertisement; play the audio of the target question; or; Continue playing the image of the target advertisement and stop playing the audio of the target advertisement; display the text of the target question in the upper view of the advertisement playback interface and play the audio of the target question.

11. The method according to claim 1, characterized in that, After calculating the matching degree between the answer to be detected and each target answer of the target question, as the target matching degree, the method further includes: If the target matching degree between the answer to be tested and each target answer is less than the matching degree threshold, record the number of times the answer to be tested was answered; If the number of responses to the answer to be tested is greater than a third value, the answer to be tested is sent to the server so that the server can count the total number of responses to the answer to be tested by each user. If the total number of responses is greater than a fourth value, page retrieval information for the answer to be tested is generated. After obtaining a new landing page generated based on the page retrieval information, the answer to be tested is recorded as a new target answer in the advertising feature library, and the new target answer and the new landing page are recorded to correspond.

12. A page display device, characterized in that, The device is used in a terminal, and the device includes: The question acquisition module is used to acquire the question corresponding to the target advertisement as the target question in response to the display instruction for the target advertisement during the playback of the target advertisement; The problem display module is used to display the text of the target problem and / or play the audio of the target problem; The voice acquisition module is used to convert the acquired answer voice into answer text in response to the acquired answer voice, so as to obtain the answer to be detected for the target question; The answer detection module is used to calculate the matching degree between the answer to be detected and each target answer of the target question, as the target matching degree; wherein, the target answer is pre-configured information associated with the content of the target advertisement; different target answers correspond to different landing pages of the target advertisement; The first page display module is used to display the landing page of the target advertisement corresponding to the target answer if the target matching degree between the answer to be detected and any target answer is greater than the matching degree threshold.

13. A terminal, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method described in any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-11.

Images