Voice search method and system for movie and television play scene lines and smart television

Abstract

The invention discloses a film and television play scene line voice search method and system and a smart television, and the method comprises the steps: receiving voice information of a user, and obtaining a voice text according to the voice information; obtaining an expression intention of the user according to the voice text; constructing a large-model plot scene line word search service, and if the expression intention is a search plot scene line word, inputting the search plot scene line word into the large-model plot scene line word search service to obtain structured data; and obtaining a corresponding query result according to the structured data. According to the method and the device, the purpose of accurately searching the expression of the line of the plot scene in any film and television can be realized by utilizing the large model, and the user experience and the search efficiency are improved.

Description

Technical Field

[0001] The present application relates to the field of voice search technology, and in particular to a method, system and smart TV for voice search of movie and TV plot scenes and lines. Background Art

[0002] In the existing technical solutions, the first letter of the movie title is selected by the remote control to search, and the search is limited to the movie title, actors, etc.; or the movie title, actor and other information are identified through traditional voice commands to search for the movie title and actors.

[0003] However, the existing technology can only search for actors based on the initial pinyin of the film name, which is complicated to operate and inefficient, and cannot accurately search for the plot, scenes, and lines played in the film and television; and traditional voice command search is limited to searching based on the film name, actor, director, and film and television tags accurately expressed by the user, and cannot accurately search for the plot, scenes, and classic lines played in the film and television.

[0004] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0005] The main purpose of this application is to provide a voice search method, system and smart TV for film and television plot scenes and lines, aiming to solve the problem that the prior art is limited to searching based on specific tags expressed by users and cannot search based on the plot, scenes and lines of the film and television.

[0006] A first aspect of an embodiment of the present application provides a method for voice search of film and television plot scene lines, the method comprising the following steps: receiving a user's voice information, and obtaining a voice text based on the voice information; obtaining the user's expression intention based on the voice text; constructing a large model plot scene line search service, if the expression intention is to search for plot scene lines, then inputting the searched plot scene lines into the large model plot scene line search service to obtain structured data; and obtaining corresponding query results based on the structured data.

[0007] Optionally, in one embodiment of the present application, the voice information is voice audio; the receiving of the user's voice information and obtaining voice text based on the voice information specifically includes: after the voice input function of the smart TV is activated, collecting the user's voice audio and sending it to a voice recognition service; the voice recognition service converts the voice audio into corresponding voice text.

[0008] Optionally, in one embodiment of the present application, obtaining the user's expression intention based on the voice text specifically includes: the voice recognition service inputs the voice text into the intention recognition service; the intention recognition service recognizes the expression intention corresponding to the voice text, wherein the expression intention includes searching for plot scene lines and voice control.

[0009] Optionally, in one embodiment of the present application, the structured data includes movie titles and episode information; if the expression intention is to search for plot scene lines, the searched plot scene lines are input into the large model plot scene lines search service to obtain structured data, specifically including: if the expression intention is to search for plot scene lines, the large model plot scene lines search service is called using the voice text; the large model plot scene lines search service processes the voice text according to the prompt words to obtain the movie title and episode information.

[0010] Optionally, in one embodiment of the present application, the large model plot scene dialogue search service processes the voice text according to the prompt word to obtain the movie name and episode information, specifically including: the large model plot scene dialogue search service dynamically replaces the query in the prompt word with the search word corresponding to the voice text; searches for matching film and television plot scene dialogues in the knowledge base according to the search word to obtain the movie name and episode information.

[0011] Optionally, in one embodiment of the present application, the query result includes film and television information and playback information; the corresponding query result is obtained based on the structured data, specifically: according to the film title and the episode information, the corresponding film and television information and playback information are searched in the film and television resource library.

[0012] Optionally, in an embodiment of the present application, the corresponding film and television information and playback information are queried in a film and television resource library according to the film title and the episode information, and then also includes: starting a player according to the playback information to play the film and television content corresponding to the film and television information.

[0013] The second aspect of the embodiment of the present application further provides a voice search system for film and television plot scenes and lines, wherein the voice search system for film and television plot scenes and lines includes:

[0014] A voice collection and recognition module is used to receive the user's voice information and obtain a voice text according to the voice information;

[0015] An intention recognition module, used to obtain the user's expression intention according to the voice text;

[0016] A large model plot scene line search module is used to construct a large model plot scene line search service. If the expression intention is to search for plot scene lines, the searched plot scene lines are input into the large model plot scene line search service to obtain structured data;

[0017] The film and television information query and playback module is used to obtain corresponding query results based on the structured data.

[0018] A third aspect of an embodiment of the present application further provides a smart TV, wherein the smart TV comprises: a memory, a processor, and a voice search program for film and television plot scene lines stored in the memory and executable on the processor, wherein the voice search program for film and television plot scene lines implements the steps of the voice search method for film and television plot scene lines as described above when executed by the processor.

[0019] A fourth aspect of an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a voice search program for film and television plot scene lines, and when the voice search program for film and television plot scene lines is executed by a processor, the steps of the voice search method for film and television plot scene lines as described above are implemented.

[0020] Beneficial effects: The present application provides a method, system and smart TV for voice search of film and television plot scenes and lines. By introducing the understanding and search capabilities of a large model, the present application can use the large model to achieve the purpose of accurately searching for the expressions of plot scenes and lines in any film and television, thereby improving user experience and search efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 It is a flow chart of a preferred embodiment of the voice search method for film and television plot scene lines of the present application;

[0023] Figure 2 It is a flowchart of specific implementation steps of the entire execution process in a preferred embodiment of the voice search method for film and television plot scenes and lines of the present application;

[0024] Figure 3 It is a structural diagram of a preferred embodiment of the voice search system for film and television plot scenes and lines of the present application;

[0025] Figure 4This is a structural diagram of a preferred embodiment of the smart TV of the present application.

[0026] Description of reference numerals:

[0027] 100. Voice collection and recognition module; 200. Intent recognition module; 300. Large model plot scene dialogue search module; 400. Film and television information query and playback module. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical scheme and effect of the present application clearer and more specific, the technical scheme in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. The described embodiments are only possible technical implementations of the present application, not all possible implementations. Based on the embodiments in the present application, those skilled in the art can completely combine the embodiments of the present application to obtain other embodiments without creative work, and these embodiments are also within the scope of protection of the present application.

[0029] The embodiments of the present application can be applied to the following scenarios, such as televisions, projectors, computers and other terminal devices.

[0030] First, the nouns involved in the embodiments of the present application are introduced:

[0031] json: JavaScript Object Notation, a lightweight data exchange format that is easy for humans to read and write, and also easy for machines to parse and generate;

[0032] name: name, refers to the title of the film or TV series;

[0033] Episode: refers to an episode in a TV series;

[0034] query: the text that the user inputs through voice, which will be dynamically replaced with the ${query} position in the prompt word as the input of the large model plot scene line search service;

[0035] list: A list refers to an array in JSON format that contains information about multiple movies and TV series.

[0036] Assistant: refers to the role of the big model in this scenario, that is, an assistant who helps users search for lines in film and television plots and scenes;

[0037] Task: refers to the specific work that the big model needs to complete, that is, returning the names of film and television works that meet the requirements based on user input;

[0038] requirement: refers to the restrictions and regulations on the output content of the large model;

[0039] Example: An example refers to an example of user input and corresponding output given to illustrate how the large model should process the input and return the result.

[0040] In the related technology, for example, all current smart TVs with voice capabilities are used as examples. The following scenario is used: existing smart TVs all have a dialogue capability for voice input via the remote control. Usually, when users want to search for film and television content, they use the inefficient and single search method of selecting the film and television name by the remote control, or searching for basic information such as the film name and actors by voice, which cannot meet the user's more complex expression search. For example: when a user wants to watch a film, when he only remembers one scene, "I want to watch a film about a man and a woman blowing the wind at the bow of a boat"; when he only remembers one plot, "I want to watch a film about a man fighting a kangaroo on the moon"; when he only remembers one line, "I want to watch the film about telling Lao Mo that I want to eat fish", the traditional smart TV search cannot meet the user's search needs and directly find the corresponding film.

[0041] In the above user search scenario, this application can accurately search for "Titanic" by voice inputting "I want to watch a movie about a man and a woman enjoying the breeze at the bow"; "I want to watch a movie about a man fighting a kangaroo on the moon" can accurately search for "Alone on the Moon"; "I want to watch the movie about telling Old Mo that I want to eat fish" can accurately search for "The 14th Episode of the Furious"; thus satisfying users with a more complex and intelligent film and television search experience. This application can accurately find the corresponding movie as long as the plot scene lines expressed by the user, and if it is a TV series, it can also accurately locate which episode it is.

[0042] Based on the interactive characteristics of existing smart TVs, this application needs to meet the needs of users' more complex film and television search scenarios to achieve a complex ability to search for any plot scene and lines in a film and television through voice, thereby achieving a more intelligent and accurate search experience. The key technology is to solve the problem of being able to use a large model in the TV system to realize the expression of any plot scene and lines in the film and television, and to accurately search for them.

[0043] The following describes the voice search method, system and smart TV for film and television plot scenes and lines according to the embodiments of the present application with reference to the accompanying drawings. In response to the problem that the above-mentioned related technologies are limited to searches based on specific tags expressed by users, and cannot be searched based on the plot, scenes and lines of the film and television, the present application provides a voice search method for film and television plot scenes and lines. In this method, by introducing the understanding and search capabilities of a large model, the large model can be used to achieve the purpose of accurately searching for the expressions of plots, scenes and lines in any film and television, thereby improving user experience and search efficiency. As a result, the technical problem that the related technologies are limited to searches based on specific tags expressed by users, and cannot be searched based on the plot, scenes and lines of the film and television, is solved.

[0044] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0045] The preferred embodiment of the present application describes a voice search method for movie and TV plot scenes and lines, such as Figure 1 As shown, the voice search method for film and television plot scene lines includes the following steps:

[0046] In step S101, voice information of a user is received, and a voice text is obtained according to the voice information.

[0047] In a possible implementation, the voice information is voice audio; after the voice input function of the smart TV is activated, the user's voice audio is collected and sent to a voice recognition service; the voice recognition service converts the voice audio into corresponding voice text.

[0048] Specifically, the user presses the voice input button of the smart TV remote control to initiate a voice conversation; the smart TV terminal collects the user's audio and transmits it to the voice recognition service; the voice recognition service converts the audio into text, namely voice text.

[0049] In step S102, the user's expression intention is obtained according to the voice text.

[0050] In one possible implementation, the speech recognition service inputs the speech text into an intent recognition service; the intent recognition service recognizes the expression intent corresponding to the speech text, wherein the expression intent includes searching for plot scene lines and voice control.

[0051] Specifically, the voice text is input into the big model intent recognition service; the big model intent recognition service analyzes the text content and identifies the user's intention, such as searching for lines in film and television plots and scenes.

[0052] In step S103, a large model plot scene line search service is constructed. If the expression intention is to search for plot scene lines, the searched plot scene lines are input into the large model plot scene line search service to obtain structured data.

[0053] In one possible implementation, the structured data includes movie titles and episode information; if the expression intention is to search for plot scene lines, the large model plot scene line search service is called using the voice text; the large model plot scene line search service processes the voice text according to the prompt words to obtain the movie title and episode information.

[0054] In a possible implementation, the large model plot scene dialogue search service dynamically replaces the query in the prompt word with the search word corresponding to the voice text; searches for matching film and television plot scene dialogues in the knowledge base according to the search word to obtain the film name and episode information.

[0055] Specifically, if it is recognized that the user's intention is to search for film and television plot scene lines, the text corresponding to the user's voice is used to call the large model plot scene line search service; the large model plot scene line search service processes the input text according to the prompt words (including roles, tasks, requirements and examples); the prompt words guide the large model to return json format data that meets the requirements, including the movie name and episode information.

[0056] Furthermore, the text entered by the user is replaced at the ${query} position in the prompt word; the complete prompt word is input into the big model, and a request is made to return data in json format that meets the requirements; the big model processes the prompt word and the input text, and returns json data containing the movie name and episode.

[0057] In step S104, a corresponding query result is obtained according to the structured data.

[0058] In a possible implementation, the query result includes film and television information and playback information. According to the film name and the series information, the corresponding film and television information and playback information are queried in the film and television resource library; according to the playback information, a player is started to play the film and television content corresponding to the film and television information.

[0059] Specifically, based on the structured data (movie names and episodes) returned by the big model, the smart TV terminal accesses the film and television resource library to query the detailed information and playback information of the film and television; the final film and television playback information (including playback links, cover pictures, etc.) is returned to the smart TV terminal, and the smart TV terminal starts the player according to the playback information and starts playing the film and television content.

[0060] This application uses the understanding and search capabilities of large models of film and television data to allow users to use natural language to describe what they want to find, whether it is a specific scene, plot or line, to get accurate results. This makes the search process more intuitive and convenient, greatly improving the user experience. The understanding ability based on the large model allows users to search using everyday language without strictly following specific formats or keywords, reducing the user's cognitive burden. Compared with the prior art, this application not only solves the problem of users' complex search needs, but also provides a more intelligent, natural and efficient search experience, thus bringing users a new way of searching for film and television.

[0061] like Figure 2 As shown, the voice search method for the above-mentioned film and television plot scene lines of the present application is further described below through a specific embodiment:

[0062] First, the user needs to press and hold the voice input button on the remote control of the smart TV, and then the user will initiate a voice conversation. The terminal collects the user's audio and transmits it to the voice recognition service to identify the text corresponding to the user's voice, and then inputs the text corresponding to the voice into the big model intention recognition service, which intends to identify the intention corresponding to the current user's voice text. If the user's voice intention is to search for the plot scene lines of a film or TV series, the big model plot scene lines search service will be called with the text corresponding to the current user's voice. The big model plot scene lines search service is a general big model that has learned all the knowledge on the Internet. When using this big model to search, since the big model cannot return structured data for the search, it is necessary to customize the prompt words for this scene to allow the big model to complete specific tasks for this film or TV series plot scene lines. The part in the middle of "" is the prompt word, and the prompt word is as follows:

[0063] "##Role

[0064] You are a movie and TV plot scene line search assistant.

[0065] ##Task##

[0066] Return the names of TV dramas and movies that meet the requirements based on user input. Your return content can only be the required JSON format data, and cannot contain any other explanatory information.

[0067] ##Require##

[0068] 1. You have the ability to search online. If necessary, you can search online to find relevant movies and TV series.

[0069] 2. You can directly use the json format. The json format is: [{"name":"xx","episode":"xx"},{"name":"xx","episode":"xx"}], where name in the json format is the name of the movie and episode is the episode. If it is a movie, the default episode returns "1". The maximum number of movies and TV shows in the json list is 5.

[0070] 3. It is strictly forbidden to output additional explanations or introductions other than json.

[0071] ##Example##

[0072] <Incorrect example>

[0073] User input: What is the most popular TV series recently?

[0074] Output: xxx’s recent popular TV series include "xxx", "xxx", and "xxx". Since the update and release of TV series and movies will change over time, it is recommended to obtain the latest and most comprehensive information through official channels or TV series and movies platforms.

[0075] <Correct example>:

[0076] Example:

[0077] User input: I want to watch Li Yunlong's video

[0078] Output: {“name”:”Drawing Sword”,”episode”:”14”}

[0079] ##User Input##

[0080] Input: ${query}

[0081] ”

[0082] The ${query} in the above prompt word is the text that dynamically replaces the user's voice input.

[0083] Then, according to the customized json structured data returned by the large model plot scene line search service, the corresponding search results of the film name and series are obtained, and then according to the structured film and television name and series, the TV film and television resource library is searched for the film and television information and playback information of the film and television, and the final film and television playback information result is returned to the smart TV terminal, and the smart TV terminal will start the player to play the film and television according to the film and television information. In this way, the search effect of complex expressions of plot scenes and lines is achieved. According to the implementation of the above technical process, when the user says in voice: "I want to watch a film about a man fighting a kangaroo on the moon", "Lone Moon" can be played directly on the TV.

[0084] Through such a process, smart TVs can intelligently search and play film and television content that meets user needs based on user voice input, achieving a search effect for complex expressions of plot scenes and lines.

[0085] Next, the voice search system for film and television plot scene lines proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0086] Figure 3 It is a structural diagram of a voice search system for movie and TV plot scene lines according to an embodiment of the present application.

[0087] like Figure 3 As shown, the voice search system for film and television plot scenes and lines includes: a voice collection and recognition module 100, an intention recognition module 200, a large model plot scene and line search module 300 and a film and television information query and playback module 400.

[0088] Specifically, the voice collection and recognition module 100 is used to receive the user's voice information and obtain the voice text according to the voice information;

[0089] The intention recognition module 200 is used to obtain the user's expression intention according to the voice text;

[0090] A large model plot scene line search module 300 is used to construct a large model plot scene line search service. If the expression intention is to search for plot scene lines, the searched plot scene lines are input into the large model plot scene line search service to obtain structured data;

[0091] The film and television information query and playback module 400 is used to obtain corresponding query results according to the structured data.

[0092] Figure 4 This is a structural diagram of a smart TV provided in an embodiment of the present application. The smart TV may include:

[0093] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0094] When the processor 502 executes the program, the voice search method for movie and TV plot scene lines provided in the above embodiment is implemented.

[0095] Furthermore, the smart TV also includes:

[0096] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0097] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0098] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0099] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EIS) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0100] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0101] The processor 502 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0102] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the voice search method for movie and TV plot scene lines is implemented as described above.

[0103] One embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the present application Figure 1 A voice search method for film and television plot scene lines provided by any embodiment in the corresponding embodiments.

[0104] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0105] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0106] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable storage medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary, and then storing it in a computer memory.

[0108] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0109] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0110] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0111] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

[0112] It should be understood that the application of the present application is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to this application.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A voice search method for movie and TV plot scenes and lines, characterized in that: The voice search method for film and television plot scene lines includes: Receive a user's voice message and obtain a voice text according to the voice message; Obtaining the user's expression intention according to the voice text; Constructing a large model plot scene line search service, if the expression intention is to search for plot scene lines, inputting the searched plot scene lines into the large model plot scene line search service to obtain structured data; According to the structured data, a corresponding query result is obtained.

2. The voice search method for movie and TV plot scenes and lines according to claim 1, characterized in that: The voice information is voice audio; The receiving of the user's voice information and obtaining the voice text according to the voice information specifically includes: After the voice input function of the smart TV is activated, the user's voice audio is collected and sent to the voice recognition service; The speech recognition service converts the speech audio into corresponding speech text.

3. The voice search method for movie and TV plot scenes and lines according to claim 2, characterized in that: The obtaining the user's expression intention according to the voice text specifically includes: The speech recognition service inputs the speech text into the intent recognition service; The intent recognition service recognizes the expression intent corresponding to the voice text, wherein the expression intent includes searching for plot scene lines and voice control.

4. The voice search method for movie and TV plot scenes and lines according to claim 1, characterized in that: The structured data includes movie titles and episode information; If the expression intention is to search for plot scene lines, the searched plot scene lines are input into the large model plot scene lines search service to obtain structured data, which specifically includes: If the expression intention is to search for lines in a plot scene, then the voice text is used to call a plot scene line search service of the big model; The large-scale model plot scene dialogue search service processes the voice text according to the prompt words to obtain the movie name and episode information.

5. The voice search method for movie and TV plot scenes and lines according to claim 4, characterized in that: The large model plot scene dialogue search service processes the voice text according to the prompt words to obtain the movie name and episode information, specifically including: The large model plot scene dialogue search service dynamically replaces the query in the prompt word with the search word corresponding to the voice text; According to the search term, matching film and television plot scene lines are searched in the knowledge base to obtain the film name and episode information.

6. The voice search method for movie and TV plot scenes and lines according to claim 4, characterized in that: The query results include film and television information and playback information; The corresponding query results are obtained according to the structured data, specifically: According to the film title and the series information, the corresponding film and television information and playback information are queried in the film and television resource library.

7. The voice search method for movie and TV plot scenes and lines according to claim 6, characterized in that: According to the film title and the series information, the corresponding film and television information and playback information are searched in the film and television resource library, and then the following is further included: The player is started according to the playing information to play the film and television content corresponding to the film and television information.

8. A voice search system for movie and TV plot scenes and lines, characterized in that: The voice search system for film and television plot scenes and lines includes: A voice collection and recognition module is used to receive the user's voice information and obtain a voice text according to the voice information; An intention recognition module, used to obtain the user's expression intention according to the voice text; A large model plot scene line search module is used to construct a large model plot scene line search service. If the expression intention is to search for plot scene lines, the searched plot scene lines are input into the large model plot scene line search service to obtain structured data; The film and television information query and playback module is used to obtain corresponding query results based on the structured data.

9. A smart TV, characterized in that: The smart TV comprises: a memory, a processor, and a voice search program for film and television plot scene lines stored in the memory and executable on the processor. When the voice search program for film and television plot scene lines is executed by the processor, the steps of the voice search method for film and television plot scene lines as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a voice search program for film and television plot scene lines, and when the voice search program for film and television plot scene lines is executed by the processor, the steps of the voice search method for film and television plot scene lines are implemented as described in any one of claims 1-7.

Images