Display device, interaction method, and storage medium

Abstract

The present disclosure relates to a display device, an interaction method and a storage medium, applied to the technical field of display, and solves the problem that the existing display device can only perform semantic analysis when a fixed time is reached after detecting user access data without feeding back response information to the user, thereby being difficult to feed back effective information to the user in time, resulting in poor user experience. The display device comprises a controller configured to: in response to a preset update rule, obtain target access data within a preset time length of a user, the target access data being access data for which the display device has not determined response information; update a dynamic dictionary library based on the target access data, the dynamic dictionary library being used for semantic understanding of the access data; in response to current access data of the user, and based on the dynamic dictionary library, determine response information corresponding to the current access data; and a display configured to display the response information corresponding to the current access data.

Description

Technical Field

[0001] This disclosure relates to the field of display technology, and more particularly to a display device, interaction method, and storage medium. Background Technology

[0002] Display devices can semantically understand user access data and provide corresponding response content. For example, if a user searches for a song on a display device, the device will show the user the search results for that song.

[0003] However, when parsing user access data, display devices may encounter parsing errors or fail to find the corresponding response content. In such cases, the device cannot display the response content corresponding to the access data to the user, making it difficult to meet the user's access needs and reducing the user experience. Summary of the Invention

[0004] To address, or at least partially address, the aforementioned technical problems, this disclosure provides a display device, an interaction method, and a storage medium that can update a dynamic dictionary database after a preset update time. This facilitates timely and effective semantic analysis of user access data upon receipt, thereby improving the user experience.

[0005] In a first aspect, this disclosure provides a display device, the display device comprising:

[0006] The controller is configured to: in response to a preset update rule, acquire target access data within a preset time period, wherein the target access data is access data for which the display device has not determined response information;

[0007] Based on the target access data, the dynamic dictionary is updated, and the dynamic dictionary is used to perform semantic understanding on the access data;

[0008] In response to the user's current access data, and based on the dynamic dictionary, determine the response information corresponding to the current access data;

[0009] The display is configured to show response information corresponding to the currently accessed data.

[0010] Secondly, this disclosure provides an interaction method, including:

[0011] In response to a preset update rule, target access data within a preset time period is obtained, wherein the target access data is access data for which the display device has not determined a response information;

[0012] Based on the target access data, the dynamic dictionary is updated, and the dynamic dictionary is used to perform semantic understanding on the access data;

[0013] In response to the user's current access data, and based on the dynamic dictionary, determine the response information corresponding to the current access data;

[0014] Displays the response information corresponding to the currently accessed data.

[0015] Thirdly, this disclosure provides a computer-readable storage medium, including: storing a computer program on the computer-readable storage medium, wherein the computer program, when executed by a processor, implements the interaction method as shown in the second aspect.

[0016] Fourthly, this disclosure provides a computer program product, characterized in that it includes: when the computer program product is run on a computer, causing the computer to implement the interaction method as shown in the second aspect.

[0017] Compared with the prior art, the technical solution provided in this disclosure has the following advantages: The display device can detect the current time in real time, determine the trigger of the preset update rule when the preset update time is reached, and respond to the preset update rule to obtain the unresponsive target access data within the preset time length of the user. Based on the target access data, the dynamic dictionary is updated to facilitate timely and effective semantic understanding of the user's access data. By responding to the user's current access data, the corresponding information corresponding to the current access data is determined based on the dynamic dictionary, and the response information is displayed to provide feedback to the user. Through the above method, the dynamic dictionary can be updated after the preset update time, which facilitates timely and effective semantic analysis of the access data when the user's access data is received to respond to the user and improve the user experience. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram illustrating an operational scenario between a display device and a control device according to one or more embodiments of the present disclosure;

[0021] Figure 2 This is a hardware configuration block diagram of a control device 100 according to one or more embodiments of the present disclosure;

[0022] Figure 3This is a hardware configuration block diagram of a display device 200 according to one or more embodiments of the present disclosure;

[0023] Figure 4 This is a schematic diagram of the software configuration in a display device 200 according to one or more embodiments of the present disclosure;

[0024] Figure 5 This is a schematic diagram showing the icon control interface of an application in a display device 200 according to one or more embodiments of the present disclosure;

[0025] Figure 6A This is a system framework diagram for control according to one or more embodiments of the present disclosure;

[0026] Figure 6B This is an architecture diagram illustrating control according to one or more embodiments of this disclosure;

[0027] Figure 7A A flowchart illustrating an interaction method provided in an embodiment of this disclosure;

[0028] Figures 7B-7F This is a schematic diagram of the interface of a display device provided in an embodiment of the present disclosure;

[0029] Figure 8A A schematic diagram illustrating the implementation principle of a cache library provided in this embodiment of the disclosure;

[0030] Figure 8B This is a schematic diagram of the connection of a triple provided in an embodiment of the present disclosure;

[0031] Figures 8C-8G This is a schematic diagram of the interface of another display device provided in an embodiment of this disclosure. Detailed Implementation

[0032] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0033] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0034] Currently, when display devices analyze user access data, they mainly rely on manual methods and the mining and labeling of unresponsive data without distinguishing business functions. They uniformly execute encyclopedia interfaces on all user access data, splitting and searching each entity word in a sentence, resulting in slow analysis efficiency.

[0035] Among them, the previous data expansion did not combine keywords, that is, the expansion of the domain center words. For example, when requesting "Frozen", the expanded words finally included "shadow ice", and the name of the novel was marked, which would lead to incorrect extraction of tags, resulting in inconsistent tag supplementation with the user's intention. The incorrect marking would have an adverse impact on the semantic understanding based on the existing knowledge base.

[0036] In addition, the current data analysis has a lag, generally 24 hours and partially relies on manual work. It cannot achieve fast semantic coverage for some live programs or sudden hot news to give users a good experience.

[0037] Therefore, when the display device cannot respond to the user's access data, it is difficult to display the response content corresponding to the access data to the user, and the user cannot meet the access requirements.

[0038] To solve the above problems, in the embodiments of the present disclosure, the display device can detect the current time in real time. When it is determined that the preset update time is reached, the preset update rule is determined, and in response to the preset update rule, the target access data that has not been responded within the preset time length of the user is obtained. According to the target access data, the dynamic dictionary library is updated, which is convenient for timely and effective semantic understanding of the user's access data. By responding to the user's current access data, based on the dynamic dictionary library, the corresponding information corresponding to the current access data is determined, and the response information is displayed to feedback to the user. Through the above method, the dynamic dictionary library can be updated after the preset update time, which is convenient for semantic analysis of the access data in a timely and effective manner when receiving the user's access data to respond to the user and improve the user experience.

[0039] Figure 1 It is a schematic diagram of the operation scenario between the display device and the control device for one or more embodiments of the present disclosure. As Figure 1 shown, the user can speak voice control information to the display device 200, or the user can send voice control information to the control device 100 of the display device 200 (or the intelligent device 300 associated with the display device 200) to implement information interaction with the display device 200, which is convenient for the display device 200 to collect the user's voice control information as the user's access data, convenient for the display device 200 to update the dynamic dictionary library to effectively analyze the user's access data, and convenient for timely responding to the user.

[0040] Among them, the user can turn on the display device through the remote control or the mobile phone, and perform text search on the display device through the remote control or the mobile phone, so that the display device can collect the user's access data based on the user's search content, and thus, effectively interact with the user.

[0041] For example, a user can open the search box on the display device via a remote control or mobile phone button, and then use the selection buttons on the remote control or the mobile phone to arrange and combine the characters in the search box to form the user's access data. The characters in the search box can include: pinyin letters, numbers, and other symbols. Users can select characters to combine multiple characters, and after combining the characters, they can click / trigger the search button to search for the desired content on the display device.

[0042] It should be noted that users can combine the characters in the search box in various ways to obtain search results, such as combining multiple pinyin letters with numbers, or combining multiple pinyin letters with other characters, or combining numbers with other characters. This disclosure does not impose any specific limitations on this.

[0043] Other characters may include: custom characters and fixed characters. Custom characters can be preset by the user in the search character options based on search habits / search needs, saving the user time in concatenating characters when searching. Fixed characters can be characters that are fixedly stored in the system of the display device.

[0044] In addition, users can also open the search box of the display device by voice control via remote control or mobile phone, and input the corresponding search content by voice in the search box through the voice interaction function of the remote control or mobile phone to form user access data.

[0045] In some embodiments, the control device 100 may be a remote control, and communication between the remote control and the display device may include infrared protocol communication, Bluetooth protocol communication, wireless or other wired methods to control the display device 200. Users can control the display device 200 by inputting user commands through buttons on the remote control, voice input, and control panel input. In some embodiments, mobile terminals, tablet computers, computers, laptops, and other smart devices may also be used to control the display device 200.

[0046] In some embodiments, the display device 200 may receive instructions not through the aforementioned smart device or control device, but through touch, gesture, or voice input.

[0047] In some embodiments, the display device 200 can also be controlled in ways other than the control device 100 and the smart device 300. For example, it can be controlled by directly receiving the user's voice commands through a module configured inside the display device 200 for acquiring voice commands, or it can be controlled by receiving the user's voice commands through a voice control device set outside the display device 200.

[0048] In some embodiments, the smart device 300 can connect and communicate with the software application installed on the display device 200 via a network communication protocol to achieve one-to-one control operation and data communication. Audio and video content displayed on the smart device 300 can also be transmitted to the display device 200 for synchronized display. The display device 200 also communicates with the server 400 via various communication methods, allowing the display device 200 to connect via a local area network (LAN), wireless local area network (WLAN), and other networks. The server 400 can be a cluster or multiple clusters, and may include one or more types of servers. The server 400 can provide various content and interactive features to the display device 200. The display device 200 can be a liquid crystal display, an OLED display, or a projection display device, etc. In addition to providing broadcast television reception functions, the display device 200 can also be equipped with a smart network television function that provides computer support.

[0049] Figure 2 An exemplary block diagram of the configuration of the control device 100 according to an exemplary embodiment is shown. Figure 2 As shown, the control device 100 includes a controller 110, a communication interface 130, a user input / output interface 140, a memory, and a power supply. The control device 100 can receive user input commands and convert them into commands that the display device 200 can recognize and respond to, acting as an intermediary for interaction between the user and the display device 200. The communication interface 130 is used for external communication and includes at least one of a Wi-Fi chip, a Bluetooth module, NFC, or a replacement module. The user input / output interface 140 includes at least one of a microphone, a touchpad, a sensor, buttons, or a replacement module.

[0050] Figure 3 A hardware configuration block diagram of a display device 200 according to an exemplary embodiment is shown. For example... Figure 3The display device 200 shown includes at least one of a tuner / demodulator 210, a communicator 220, a detector 230, an external device interface 240, a controller 250, a display 260, an audio output interface 270, a memory, a power supply, and a user interface (i.e., a user input interface) 280. The controller 250 includes a central processing unit, a video processor, an audio processor, a graphics processor, RAM, ROM, and a first to nth interface for input / output. The display 260 may be at least one of a liquid crystal display, an OLED display, a touch display, and a projection display, and may also be a projection device and a projection screen. The tuner / demodulator 210 receives broadcast television signals via wired or wireless means, and demodulates audio and video signals, such as EPG data signals, from multiple wireless or wired broadcast television signals. The communicator 220 is a component used to communicate with external devices or servers according to various communication protocol types. For example, the communicator may include at least one of a Wi-Fi module, a Bluetooth module, a wired Ethernet module, other network communication protocol chips or near-field communication protocol chips, and an infrared receiver. The display device 200 can establish the transmission and reception of control signals and data signals with the external control device 100 or server 400 via the communicator 220. The detector 230 is used to collect signals from the external environment or to interact with external systems. The controller 250 and the tuner / demodulator 210 can be located in different separate devices; that is, the tuner / demodulator 210 can also be located in an external device of the main device containing the controller 250, such as an external set-top box. The user interface 280 can be used to receive control signals from the control device 100 (e.g., an infrared remote control).

[0051] In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in memory. The controller 250 controls the overall operation of the display device 200. The user can input user commands through a graphical user interface (GUI) displayed on the monitor 260, and the user input interface receives the user input commands through the GUI. Alternatively, the user can input user commands by inputting specific sounds or gestures, and the user input interface receives the user input commands by recognizing the sounds or gestures through sensors.

[0052] In some embodiments, a "user interface" is the medium through which an application or operating system interacts and exchanges information with a user, converting information between its internal form and a form acceptable to the user. A common form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed graphically. It can be interface elements such as icons, windows, and controls displayed on the screen of an electronic device. Controls can include at least one of the visual interface elements such as icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, and widgets.

[0053] Figure 4 This is a schematic diagram of the software configuration in a display device 200 according to one or more embodiments of the present disclosure, such as... Figure 4 As shown, the system is divided into four layers, from top to bottom: the Applications layer (referred to as the "Application Layer"), the Application Framework layer (referred to as the "Framework Layer"), the Android runtime and system library layer (referred to as the "System Runtime Library Layer"), and the kernel layer.

[0054] In some embodiments, at least one application runs in the application layer. These applications may be Windows programs, system settings programs, or clock programs that come with the operating system; they may also be applications developed by third-party developers. In specific implementations, the applications in the application layer include, but are not limited to, the examples above.

[0055] In some embodiments, the system runtime library layer provides support for the upper layer, namely the framework layer. When the framework layer is used, the Android operating system runs the C / C++ libraries contained in the system runtime library layer to implement the functions that the framework layer needs to perform.

[0056] In some embodiments, the kernel layer is a layer between hardware and software, and includes at least one of the following drivers: audio driver, display driver, Bluetooth driver, camera driver, WIFI driver, USB driver, HDMI driver, sensor driver (such as fingerprint sensor, temperature sensor, pressure sensor, etc.), and power driver, etc.

[0057] Figure 5 This is a schematic diagram showing the icon control interface of an application in a display device 200 according to one or more embodiments of the present disclosure, such as... Figure 5As shown, the application layer contains at least one application whose corresponding icon control can be displayed on the screen, such as: live TV application icon control, video-on-demand application icon control, media center application icon control, application center icon control, game application icon control, etc. Live TV applications can provide live television from different signal sources. Video-on-demand applications can provide video from different storage sources. Unlike live TV applications, video-on-demand provides video display from certain storage sources. Media center applications can provide applications for playing various multimedia content. The application center can provide storage for various applications.

[0058] In some embodiments, the display device described above is a terminal device with display functionality, such as a television or a flat-panel television. In this display device:

[0059] In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in memory. The controller 250 controls the overall operation of the display device 200. The user can input user commands through a graphical user interface (GUI) displayed on the monitor 260, and the user input interface receives the user input commands through the GUI. Alternatively, the user can input user commands by inputting specific sounds or gestures, and the user input interface receives the user input commands by recognizing the sounds or gestures through sensors.

[0060] The output interface (display 260, and / or audio output interface 270) is configured to output user interaction information;

[0061] Communicator 220 is used to communicate with server 400;

[0062] Controller 250 is configured to: in response to a preset update rule, acquire target access data within a preset time period, wherein the target access data is access data for which the display device has not determined response information;

[0063] Based on the target access data, the dynamic dictionary is updated, and the dynamic dictionary is used to perform semantic understanding on the access data;

[0064] In response to the user's current access data, and based on the dynamic dictionary, determine the response information corresponding to the current access data;

[0065] Display 260 is configured to display response information corresponding to the currently accessed data.

[0066] In some embodiments, the target access data includes: at least two sets of access data, each set of access data including at least two access data, wherein the matching degree between entity words in the at least two access data is greater than the matching degree threshold;

[0067] The controller 250 is specifically configured as follows:

[0068] Calculate the similarity for each set of access data to obtain the first similarity value;

[0069] If the first similarity value of the first access data is detected to be greater than the preset first threshold, then the first access data is compared with the preset word library to obtain the second similarity value.

[0070] If the second similarity value of the second access data is detected to be greater than the preset second threshold, then the entity words in the second access data and the corresponding matching words in the preset dictionary are added to the dynamic dictionary.

[0071] In some embodiments, the controller 250 is specifically configured to:

[0072] If the second similarity value of the third access data is detected to be less than or equal to the preset second threshold, the domain information of the trusted entity words in the third access data and the trusted entity words are obtained, and the trusted entity words are the entity words with the highest confidence in the third access data;

[0073] The trusted entity words and their domain information are added to the cache library, and the dynamic dictionary library is updated based on the cache library.

[0074] In some embodiments, the controller 250 is specifically configured to:

[0075] If the first similarity value of the fourth access data is detected to be less than or equal to a preset first threshold, then the fourth access data is added to the cache library;

[0076] Update the dynamic dictionary library based on the cache library.

[0077] In some embodiments, the cache library includes: candidate words, or, candidate words and domain information corresponding to the candidate words;

[0078] The controller 250 is specifically configured as follows:

[0079] The cache library determines that the first word has corresponding domain information, and the domain information corresponding to the first word determines the first entity word corresponding to the first word, wherein the first word is at least one word among the candidate words;

[0080] Add the first entity word and the domain information corresponding to the first word to the dynamic dictionary library.

[0081] In some embodiments, the controller 250 is specifically configured to:

[0082] If it is determined from the cache library that the second word does not have corresponding domain information, the second word is segmented to obtain at least one segmented word, and the second word is at least one word among the candidate words;

[0083] If at least one of the segmented words is determined to have a corresponding second entity word, the domain information corresponding to the second entity word and the second word is added to the dynamic dictionary.

[0084] In some embodiments, the dynamic dictionary is stored in a preset cache area;

[0085] The controller 250 is specifically configured as follows:

[0086] Based on the cache library, update the dynamic dictionary library in the preset cache area.

[0087] In some embodiments, the display 260 is specifically configured as follows:

[0088] Based on the display area corresponding to the currently accessed data, display the response information corresponding to the currently accessed data.

[0089] In summary, the display device in this embodiment can detect the current time in real time. When it determines that a preset update time has been reached, it determines to trigger a preset update rule and responds to the preset update rule by acquiring the unresponsive target access data within a preset time period. Based on the target access data, it updates the dynamic dictionary database, which facilitates timely and effective semantic understanding of the user's access data. By responding to the user's current access data, it determines the corresponding information based on the dynamic dictionary database and displays the response information to provide feedback to the user. Through the above method, the dynamic dictionary database can be updated after the preset update time, which facilitates timely and effective semantic analysis of the access data received from the user to respond to the user and improve the user experience.

[0090] Figure 6A This is a system framework diagram for control according to one or more embodiments of the present disclosure, such as... Figure 6AAs shown, the system may include a data acquisition module 601, a dictionary update module 602, an information determination module 603, and an information display module 604. The system, through the data acquisition module 601 responding to a preset update rule, acquires target access data within a preset time period from the user. This target access data refers to access data for which the display device has not yet determined a response. The dictionary update module 602 updates the dynamic dictionary based on the target access data. This dynamic dictionary is used for semantic understanding of the access data. The information determination module 603 responds to the user's current access data and determines the corresponding response information based on the dynamic dictionary. The information display module 604 then displays the response information corresponding to the current access data. Thus, the system can update the dynamic dictionary after a preset update time, facilitating timely and effective semantic analysis of the access data received from the user to respond to the user and improve the user experience.

[0091] Figure 6B This is an architecture diagram illustrating control according to one or more embodiments of the present disclosure. Based on the above system framework, the implementation of the present disclosure in the Android system is as follows: Figure 6B As shown, the Android system mainly includes the application layer, framework layer, system runtime library layer, and kernel layer. The implementation logic is mainly reflected in the application layer, which includes the data acquisition module, dictionary update module, information determination module, and information display module.

[0092] The interaction method provided in this embodiment continuously monitors time information through a display device. When the current time reaches a preset update time, it determines that a preset update rule has been met. By responding to the preset update rule, it obtains the user's access data within a certain period (such as the hour before the current time). The access data describes data for which the display device responded but did not receive a response. The access data is used to update the dynamic dictionary in the display device to perform semantic analysis on other user access data. When new user access data is received, the dynamic dictionary can be used to perform semantic understanding on the access data to obtain response information corresponding to the new access data. The response information corresponding to the new access data is then displayed to the user, making it easier for the user to understand. This allows for timely response to the user's access needs, improves the user experience, and enhances user stickiness.

[0093] To illustrate this solution in more detail, the following will use examples to illustrate it. Figure 7A To explain, it is understandable that Figure 7A The steps involved may include more or fewer steps in actual implementation, and the order of these steps may also be different, as long as the interaction method provided in the embodiments of this disclosure can be achieved. The embodiments of this disclosure do not limit the steps.

[0094] like Figure 7A As shown, Figure 7A This is a flowchart illustrating an interaction method provided in an embodiment of the present disclosure. The interaction method specifically includes the following steps:

[0095] S710: In response to a preset update rule, obtain the target access data within a preset time period.

[0096] The preset update rule can be an access time used to provide update prompts. For example, the preset update rule can be a time period corresponding to an hour. When it is determined that the current time has reached one hour since the last update, it is determined that the preset update rule has been met.

[0097] The preset time length can be a preset time period earlier than the current access time, such as the hour preceding the current access time.

[0098] For example, if a user's current access time is 2022.6.6, 10:10, then the corresponding preset time length can be 2022.6.6, 9:10. The preset time length can be adaptively set based on update rules, such as being set to the first half hour or the first half hour. This disclosure does not make specific limitations on this.

[0099] The target access data may be access data for which the display device has not determined the response information. That is, after receiving the target access data sent by the user, the display device does not find the response information corresponding to the target access data, or the response information found to be corresponding to the target access data has a low degree of matching with the target access data, and does not provide feedback to the user.

[0100] It should be noted that users can enter target access data through the search box on the display interface of the display device, or users can search for target access data by voice input, so that the display device can receive the target access data sent by the user.

[0101] like Figure 7B As shown in the example, users can enter characters in the search box of the display device using a remote control or other control device to obtain target access data, and then trigger the "Search" button to send the target access data to the display device.

[0102] The search box on the display device can also be set to display the user's habitual phrases, thus facilitating quick input for the user.

[0103] like Figure 7CAs exemplarily shown, one or more display areas for displaying the user's habitual phrases can be set around the search box of the display device. For example, display area 1 is used to display the user's first habitual phrase, display area 2 is used to display the user's second habitual phrase, and display area 3 is used to display the user's third habitual phrase.

[0104] The display positions of display areas 1, 2, and 3 can be determined based on the display position of the search box. For example, they can be set below the display position of the search box. Alternatively, the display positions of display areas 1, 2, and 3 can be hidden on the search interface of the display device. After the user triggers the display indicator, the display content corresponding to display areas 1, 2, and 3 can be displayed. This disclosure does not specifically limit the display positions of display areas 1, 2, and 3.

[0105] The user's habitual phrases displayed in the search interface of the display device can be set and modified by the user, or set by the display device based on the user's historical access data. This disclosure does not impose specific limitations on this.

[0106] Specifically, users' habitual terms can be some access data that users access most frequently, such as the first habitual term being "popular movies", the second habitual term being "popular variety shows", and the third habitual term being "the most popular TV series", etc.

[0107] like Figure 7D As shown in the example, users can trigger the voice interaction function of the display device through preset voice commands. After the voice interaction function of the display device is activated, the user can speak the specific characters corresponding to the target access data, so that the display device can obtain the target access data based on the voice data input by the user.

[0108] In addition, after obtaining the target access data within the user's preset time period, the target access data can be cleaned to obtain valid data.

[0109] Data cleaning can include: cleaning punctuation marks, cleaning some intent words, etc.

[0110] Punctuation cleaning can be a cleaning operation performed on all punctuation marks included in the target access data. When the sentences in the target access data are long and contain multiple periods, the target access data can be segmented based on the periods to obtain multiple segmented sentences, and then the punctuation marks of each segmented sentence can be cleaned.

[0111] In particular, when cleaning punctuation marks in each segment of a sentence, corresponding operations can be performed simultaneously, thereby enabling effective and rapid mark cleaning.

[0112] Some intent words can be such as "I want", "help me", "voice assistant image words", "play", etc. Cleaning some intent words can be done by removing some of the set intent words. For example, if the target access data is "play song 1", then removing some intent words will result in "song 1".

[0113] Based on the above example, assuming the target access data received by the display device is "Voice assistant, I want to listen to song 2", after cleaning the target access data by removing punctuation marks, we get "Voice assistant, I want to listen to song 2". After cleaning some intent words and removing "Voice assistant" and "I want", we finally get "Listen to song 2".

[0114] Among them, relevant metrics can be added to the target access data. Specifically, the metrics may include: text content (after data cleaning), number of accesses, location business, location method, and time.

[0115] Please refer to Table 1 below for details.

[0116] Table 1 Data Display Table 1

[0117]

[0118]

[0119] Among them, "123" represents a correct song title, while "423" and "523" represent songs that sound the same as the correct song title but have different characters.

[0120] Location services refer to the context services corresponding to the text content, such as music and chat. The returned response is the reply returned to the user by the display device based on the search of the target access data. The time is displayed in the form of a timestamp. The location method corresponds to different search engines, such as R for the first search engine and S for the second search engine.

[0121] In addition, when performing data analysis on target access data, the location business set for analysis can be filtered based on business type. Some preset businesses (such as proprietary businesses or businesses in specific applications) will not be analyzed, and the corpus with the location method of strong operation will not be analyzed.

[0122] S720: Update the dynamic dictionary based on the target access data.

[0123] Among them, the dynamic dictionary can be a dictionary pre-built based on the user's historical access data, which can be used to perform semantic understanding of the access data, making it easier to analyze user intent in a timely and effective manner.

[0124] The dynamic dictionary can store entity words and their corresponding domain information. Entity words can be text content as exemplified above, and domain information can be location services as exemplified above, specifically including: music, movie, teleplay, chat, etc.

[0125] S730: Respond to the user's current access data and determine the response information corresponding to the current access data based on a dynamic dictionary.

[0126] Among them, the user's current access data is the access data sent by the user to the display device at the current time, such as "Play song 2", "I want to listen to song 2", "Search song 2", "Play movie 3", "I want to watch movie 3", "Search movie 3", "Play TV series 4", "I want to watch TV series 4", "Search TV series 4", "I want to chat", "Voice assistant", "Open voice assistant", etc.

[0127] After receiving the user's current access data, the display device can match the current access data (text content) with entity words in the dynamic dictionary to obtain matching entity words. This allows the display device to quickly find the associated response information based on the matching entity words and provide timely feedback to the user.

[0128] For example, if a user's current access data is "play song 2", the matching entity word obtained by matching it is "song 2" and the domain information corresponding to "song 2" is "music", then the response information corresponding to the current access data can be "music song 2".

[0129] The user's current access data is "play movie 3". The matching entity word obtained by matching it is "movie 3". The domain information corresponding to "movie 3" is "movie". Therefore, the response information corresponding to the current access data is "movie movie 3".

[0130] The user's current access data is "play TV series 4", and the matching entity word obtained by matching it is "TV series 4". The domain information corresponding to "TV series 4" is "teleplay". Therefore, the response information corresponding to the current access data is "teleplay TV series 4".

[0131] The user's current access data is "I want to chat". The matching entity word obtained by matching it is "chat". The domain information corresponding to "chat" is "chat". Therefore, the response information corresponding to the current access data is "chat chat".

[0132] S740: Display the response information corresponding to the currently accessed data.

[0133] The display device can show the user the response information corresponding to the currently accessed data on the display interface based on the obtained response information.

[0134] The display device can display the response information corresponding to the currently accessed data within a preset area. The preset area can be a sub-area of ​​the display interface of the display device, or the preset area can be the entire display area of ​​the display interface of the display device.

[0135] like Figure 7E As shown in the example, when the response information corresponding to the current access data is "music song 2", the response information "music song 2" corresponding to the current access data can be displayed in the display area 4, so that users can effectively obtain the search results.

[0136] like Figure 7F As shown in the example, when the response information corresponding to the current access data is "movie movie 3", the response information corresponding to the current access data can be displayed in the display area 5.

[0137] It should be noted that the data analysis of the target access data and the data response of the current access data in this disclosure can be implemented on different service resources. For example, the data analysis process can be carried out in the test environment service for word segmentation, extraction and data analysis, without occupying the online speech understanding server resources, and thus will not affect the semantic response speed of the official environment service.

[0138] Based on the description of the above embodiments, the target access data may include: multiple sets of access data, each set of access data may include multiple access data entries, and the matching degree between entity words in the multiple access data entries is greater than the matching degree threshold.

[0139] The target access data can be clustered to obtain multiple sets of clustered data (multiple sets of access data). Each set of clustered data includes multiple access data, and each access data contains entity words. Furthermore, the matching degree of the entity words in the multiple access data included in each set of clustered data is greater than the matching degree threshold.

[0140] It should be noted that when performing clustering, similarity clustering can be performed based on the Term Frequency–Inverse Document Frequency (TF-IDF) method combined with edit distance and pinyin similarity algorithm. When clustering, the correct data from the previous hour and the same time period of the previous day are added to cluster and classify the user's original data.

[0141] When updating the dynamic dictionary, each set of access data can be processed independently. By performing similarity matching on each set of access data, a first similarity value is determined for each set of access data. If the first similarity value of the first access data is found to be greater than a preset first threshold, the first access data is further compared with a preset dictionary to obtain a second similarity value. If the second similarity value of the second access data is found to be greater than a preset second threshold, the entity words in the second access data and the corresponding matching words in the preset dictionary are added to the dynamic dictionary. Thus, the entity words with high accuracy in the user access data can be effectively determined based on the preset dictionary.

[0142] The first access data consists of one or more sets of access data with a similarity value greater than a preset first threshold, and the second access data consists of one or more access data from this set of access data.

[0143] The preset terminology can be a pre-built hot term database that stores entity names (comparison words) from correct user statements within a certain period of time. For example, it can store entity names such as video names, music names, and news entries from correct user statements in the past month. It can be mainly determined through ranking lists and user data statistics.

[0144] Specifically, the hot word library can be sorted according to the time dimension, with time priority as follows: the hour before the same day > the same time period of the previous day > other time periods of the same day (other priorities decrease as time decreases), and then sorted according to the number of requests, and finally sorted by the total number of user requests.

[0145] Specifically, when the second similarity value of the third access data is detected to be less than or equal to the preset second threshold, the domain information of the trusted entity words and trusted entity words in the third access data is obtained, the domain information of the trusted entity words and trusted entity words is added to the cache library, and the dynamic dictionary library is updated based on the cache library.

[0146] Among them, trusted entity words are the entity words with the highest confidence level in the third access data.

[0147] The first access data consists of one or more sets of access data with a similarity value greater than a preset first threshold, and the third access data consists of one or more access data from this set of access data.

[0148] This allows us to select the entity words with the highest confidence to add to the cache, making it easier to expand the entity words and increase the word count of the dynamic dictionary.

[0149] In addition, when the target access data is a set of data or a single data item, the second similarity can be calculated directly.

[0150] Specifically, if the first similarity value of the fourth accessed data is less than or equal to a preset first threshold, the fourth accessed data is added to the cache library; based on the cache library, the dynamic dictionary library is updated.

[0151] The fourth access data consists of one or more sets of access data with a similarity value less than or equal to a preset first threshold. By adding the fourth access data to the cache library to expand the full words, the word count of the dynamic dictionary library is further expanded.

[0152] like Figure 8A As an example, the caching library (extensible library) is constructed as follows.

[0153] S810, Obtain raw data.

[0154] The raw data consists of user access data acquired within a preset time period.

[0155] S820. Calculate the similarity of the original data and determine the first similarity value.

[0156] Similarity calculation may include: TF-IDF method combined with edit distance method, and Pinyin similarity algorithm.

[0157] S830. Determine if the first similarity value is greater than T1. If yes, execute S840; otherwise, execute S880.

[0158] Where T1 is the preset first threshold.

[0159] S840: Generate a unified statement cluster to obtain multiple sets of access data.

[0160] Among these methods, by generating a uniform statement distance, multiple access data can be clustered.

[0161] S850. Determine whether the second similarity value is greater than T2. ​​If yes, execute S860; otherwise, execute S870.

[0162] T1 is a preset second threshold, and the second similarity value is obtained by comparing the similarity of multiple sets of access data with the hot word library.

[0163] S860, Output the mapping pair between the error correction word and the original word.

[0164] S870. Select the most reliable corpus and combine it with keywords for searching, and add it to the database to be expanded.

[0165] Among them, keywords (key words, business positioning words, such as film and television, music, news, etc.) are predetermined in advance and can be determined through benchmark word matching and knowledge graph inference. Benchmark words can be set with different mappings according to different businesses. The preliminary mapping is shown in Table 2 below.

[0166] Table 2 Mapping Table

[0167] field keywords generalization Film and television Movie Movies, films, video apps Film and television TV drama Drama, TV series Film and television video look music song Songs, music, listen, musicApp

[0168] For the inference of the indicator map, the domain can be determined by establishing triples () using semantic tags, mainly covering statements without intentional words but with relevant tags. A connection diagram can be found in [reference needed]. Figure 8B As shown in the example.

[0169] S880, outputs a single text and adds it to the library to be expanded.

[0170] The cache library may include candidate words, or candidate words and their corresponding domain information. When updating the dynamic dictionary library based on the cache library, it can be determined from the cache library that the first word has corresponding domain information. Based on the domain information corresponding to the first word, the first entity word corresponding to the first word is determined. The first word is at least one word among the candidate words. The first entity word and the domain information corresponding to the first word are added to the dynamic dictionary library.

[0171] The first word is one or more words in the cache library that contain domain information.

[0172] In addition, the dynamic dictionary can be expanded based on some words whose domain information is not present in the cache library, thereby increasing the vocabulary of the dynamic dictionary.

[0173] Specifically, it can be determined from the cache that the second word does not have corresponding domain information, and the second word is segmented to obtain at least one segmented word, which is at least one word among the candidate words; it can also be determined that at least one segmented word has a corresponding second entity word, and the domain information corresponding to the second entity word and the second word is added to the dynamic dictionary.

[0174] The second term is one or more terms for which domain information is not present in the cache.

[0175] For second words that do not have domain information, they can be labeled. The words to be labeled can be processed using a sequence labeling algorithm to remove intent words. For other mining methods, Chinese syntactic segmentation algorithms can be used with the maximum matching algorithm. If a match is found, the analysis of this word ends. This can eliminate the problem of mining data granularity being too fine, which would lead to the addition of other irrelevant intent statements to the knowledge base and affect word segmentation in other cases.

[0176] The dynamic dictionary is stored in a preset cache. When updating the dynamic dictionary, the dynamic dictionary in the preset cache can be updated based on the cache.

[0177] Specifically, the dynamic dictionary can be used as a secondary word segmentation dictionary through the storage function of the search server (Elastic Search, es). Only the cache related to the dynamic dictionary is refreshed, without any online pressure. It can automatically add frequently requested annotations and error correction words after a 1-hour delay, ensuring user experience and the accuracy of semantic understanding.

[0178] When performing semantic understanding on the user's current access data, semantic understanding can be achieved by using a main dictionary plus a dynamic dictionary. First, the main dictionary can be used for word segmentation. If there is only one word segmentation, semantic understanding can be performed directly. For other cases, word segmentation can be performed based on the main dictionary and then by a second-level word segmentation dictionary (dynamic dictionary).

[0179] When displaying the response information corresponding to the currently accessed data, the display device can display the response information corresponding to the currently accessed data in the display area of ​​the display interface, making it convenient for users to browse.

[0180] In some embodiments, the display area corresponding to the currently accessed data may be a sub-area of ​​the current display interface, such as... Figure 8C As shown in the example of Interface 1, the display area corresponding to the currently accessed data can be as follows: Figure 8D As shown in the example.

[0181] In other embodiments, the display area corresponding to the currently accessed data may be the entire display area in the current display interface, and the display area corresponding to the currently accessed data may be as follows: Figure 8E As shown in the example.

[0182] In some other embodiments, the display area corresponding to the currently accessed data may be a sub-area different from another display interface currently displayed. The display area corresponding to the currently accessed data may be as follows: Figure 8F Interface 2 is shown as an example.

[0183] In some other embodiments, the display area corresponding to the currently accessed data may be the entire display area of ​​another display interface different from the currently displayed one. The display area corresponding to the currently accessed data may be as follows: Figure 8G As shown in the example.

[0184] In summary, by executing the above-described interaction method on a display device, this disclosure enables the display device to detect the current time in real time. Upon determining that a preset update time has been reached, the device determines to trigger a preset update rule and responds to the preset update rule by acquiring unresponsive target access data within a preset time period. Based on the target access data, the dynamic dictionary is updated, facilitating timely and effective semantic understanding of the user's access data. By responding to the user's current access data, the device determines the corresponding information based on the dynamic dictionary and displays this response information to provide feedback to the user. This method allows the dynamic dictionary to be updated after the preset update time, enabling timely and effective semantic analysis of the access data received from the user to respond to the user and improve the user experience.

[0185] This disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described interactive method and achieves the same technical effect. To avoid repetition, further details are omitted here.

[0186] The computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0187] This disclosure provides a computer program product, characterized in that it includes: when the computer program product is run on a computer, causing the computer to implement the above-described interaction method.

[0188] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the discussion in some embodiments above is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the principles and practical applications, thereby enabling those skilled in the art to better utilize the embodiments and various different variations of the embodiments suitable for specific application considerations.

Claims

1. A display device, characterized in that, include: The controller is configured to: in response to a preset update rule, acquire target access data within a preset time period, wherein the target access data is access data for which the display device has not determined response information; Based on the target access data, the dynamic dictionary is updated, and the dynamic dictionary is used to perform semantic understanding on the access data; In response to the user's current access data, and based on the dynamic dictionary, determine the response information corresponding to the current access data; The display is configured to show response information corresponding to the currently accessed data; The target access data includes: at least two sets of access data, each set of access data includes at least two access data, and the matching degree between entity words in at least two access data is greater than the matching degree threshold; The controller is specifically configured as follows: Calculate the similarity for each set of access data to obtain the first similarity value; If the first similarity value of the first access data is detected to be greater than the preset first threshold, then the first access data is compared with the preset word library to obtain the second similarity value. If the second similarity value of the second access data is detected to be greater than the preset second threshold, then the entity words in the second access data and the corresponding matching words in the preset dictionary are added to the dynamic dictionary library. Wherein, the first access data is one or more sets of access data with a first similarity value greater than a preset first threshold, and the second access data is one or more access data in the first access data with a second similarity value greater than a preset second threshold.

2. The display device according to claim 1, characterized in that, The controller is specifically configured as follows: If the second similarity value of the third access data is detected to be less than or equal to the preset second threshold, the domain information of the trusted entity words in the third access data and the trusted entity words are obtained, and the trusted entity words are the entity words with the highest confidence in the third access data; The trusted entity words and their domain information are added to the cache library, and the dynamic dictionary library is updated based on the cache library. The third access data refers to one or more access data entries in the first access data whose second similarity value is not greater than a preset second threshold.

3. The display device according to claim 1, characterized in that, The controller is specifically configured as follows: If the first similarity value of the fourth access data is detected to be less than or equal to a preset first threshold, then the fourth access data is added to the cache library; Update the dynamic dictionary library based on the cache library; The fourth access data is one or more sets of access data whose first similarity value is not greater than a preset first threshold.

4. The display device according to claim 2 or 3, characterized in that, The cache library includes: candidate words, or candidate words and the domain information corresponding to the candidate words; The controller is specifically configured as follows: The cache library determines that the first word has corresponding domain information, and the domain information corresponding to the first word determines the first entity word corresponding to the first word, wherein the first word is at least one word among the candidate words; Add the first entity word and the domain information corresponding to the first word to the dynamic dictionary library.

5. The display device according to claim 4, characterized in that, The controller is specifically configured as follows: If it is determined from the cache library that the second word does not have corresponding domain information, the second word is segmented to obtain at least one segmented word, and the second word is at least one word among the candidate words; If at least one of the segmented words is determined to have a corresponding second entity word, the domain information corresponding to the second entity word and the second word is added to the dynamic dictionary.

6. The display device according to claim 2 or 3, characterized in that, The dynamic dictionary is stored in a preset cache area; The controller is specifically configured as follows: Based on the cache library, update the dynamic dictionary library in the preset cache area.

7. The display device according to claim 1, characterized in that, The display is specifically configured as follows: Based on the display area corresponding to the currently accessed data, display the response information corresponding to the currently accessed data.

8. An interaction method, characterized in that, include: In response to a preset update rule, target access data within a preset time period is obtained, wherein the target access data is access data for which the display device has not determined a response information; Based on the target access data, the dynamic dictionary is updated, and the dynamic dictionary is used to perform semantic understanding on the access data; In response to the user's current access data, and based on the dynamic dictionary, determine the response information corresponding to the current access data; Display the response information corresponding to the currently accessed data; The target access data includes: at least two sets of access data, each set of access data includes at least two access data, and the matching degree between entity words in at least two access data is greater than the matching degree threshold; The step of updating the dynamic dictionary based on the target access data includes: Calculate the similarity for each set of access data to obtain the first similarity value; If the first similarity value of the first access data is detected to be greater than the preset first threshold, then the first access data is compared with the preset word library to obtain the second similarity value. If the second similarity value of the second access data is detected to be greater than the preset second threshold, then the entity words in the second access data and the corresponding matching words in the preset dictionary are added to the dynamic dictionary library. Wherein, the first access data is one or more sets of access data with a first similarity value greater than a preset first threshold, and the second access data is one or more access data in the first access data with a second similarity value greater than a preset second threshold.

9. A computer-readable storage medium, characterized in that, include: A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the interaction method as described in claim 8.

Images