A control method and system of a set-top box, and a storage medium

Abstract

The embodiment of the application discloses a control method and system of a set top box and a storage medium. The control method of the set top box is applied to a control system. The control system comprises a service platform, a set top box, a third-party application platform and a terminal device. The set top box communicates with the service platform through a first interface. The set top box communicates with the third-party application platform through a second interface. The set top box communicates with the terminal device through a third interface. The set top box acquires a third-party application from the third-party application platform. When the third-party application is running, the set top box detects voice information and sends the voice information to the service platform. The service platform generates a control instruction according to the display content of a current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set top box. If the set top box is successfully adapted with a license side based on the control instruction, the set top box calls the terminal device to realize a service function corresponding to the voice information. The intelligence and the function extensibility of the set top box can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of set top boxes, and particularly relates to a control method and system of a set top box and a storage medium. BACKGROUND

[0002] A digital video conversion box (STB), commonly known as a set top box or set top box, is a device that connects a television set with an external signal source. It can convert compressed digital signals into television content and display it on a television set. With the development of technology and intelligence, set top boxes are becoming more and more intelligent. From the original application of only playing TV programs, to games, Internet and other applications, the set top box provides more and more applications for users, greatly facilitating users.

[0003] The voice assistant installed in the set top box on the market does not have universality, and when another set top box license is opened, the set top box needs to be upgraded to use, which brings a great use risk. That is, the related art has the problems of long development and adaptation cycle, high risk of upgrading the license, and greatly reduces the intelligence and functional expandability of the set top box. SUMMARY

[0004] The embodiments of the present application provide a control method and system of a set top box and a storage medium, which can shorten the development and adaptation cycle, greatly reduce the risk, and improve the intelligence and functional expandability of the set top box.

[0005] The technical scheme of the embodiments of the present application is as follows:

[0006] In a first aspect, the embodiments of the present application provide a control method of a set top box, which is applied to a control system, wherein the control system comprises a business platform, a set top box, a third-party application platform and a terminal device; the set top box communicates with the business platform through a first interface; the set top box communicates with the third-party application platform through a second interface; the set top box communicates with the terminal device through a third interface; and the method comprises:

[0007] The set top box obtains a third-party application from the third-party application platform;

[0008] When running the third-party application, the set top box detects voice information and sends the voice information to the business platform;

[0009] The business platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set top box;

[0010] If the set-top box is successfully adapted with the license party based on the control instruction, the set-top box calls the terminal device to realize the service function corresponding to the voice information.

[0011] In a second aspect, the embodiments of the present application provide a control system, an acquisition unit, a detection unit, a sending unit, a generation unit, a calling unit,

[0012] The acquisition unit is configured to acquire a third-party application from a third-party application platform.

[0013] The detection unit is configured to detect voice information when the third-party application is running.

[0014] The sending unit is configured to send the voice information to a service platform.

[0015] The generation unit is configured to generate a control instruction according to display content of a current interface corresponding to the third-party application and the voice information.

[0016] The sending unit is further configured to send the control instruction to a set-top box.

[0017] The calling unit is configured to call a terminal device to realize a service function corresponding to the voice information if the set-top box is successfully adapted with the license party based on the control instruction.

[0018] In a third aspect, the embodiments of the present application provide a control system, the control system comprising a processor and a memory storing instructions executable by the processor, when the instructions are executed by the processor, the control method of the set-top box is implemented.

[0019] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, the computer readable storage medium storing a program, the program being executed by a processor to implement the control method of the set-top box.

[0020] The embodiment of the application provides a control method and system of a set top box and a storage medium, the control method of the set top box is applied to a control system, wherein the control system comprises a service platform, a set top box, a third-party application platform and a terminal device; the set top box communicates with the service platform through a first interface; the set top box communicates with the third-party application platform through a second interface; the set top box communicates with the terminal device through a third interface; the set top box obtains a third-party application from the third-party application platform; when the third-party application is run, the set top box detects voice information and sends the voice information to the service platform; the service platform generates a control instruction according to display content of a current interface corresponding to the third-party application and the voice information and sends the control instruction to the set top box; if the set top box is successfully adapted based on the control instruction and a license party, the set top box calls the terminal device to realize a service function corresponding to the voice information. That is to say, in the embodiment of the application, the unified input and output interface of the middleware can be used, the communication with the service platform and the underlying system is completed through the middleware, the set top box has unified license party capability, meanwhile, the set top box can expose various services of an operating system to the outside, the scene is determined by combining the display content and the voice information, and the voice capability can be dynamically expanded. The development and adaptation cycle can be shortened, the risk can be greatly reduced, and the intelligence and the function expansibility of the set top box are improved. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 The control system is shown in the schematic diagram of the component structure Figure One ;

[0022] Figure 2 The control method of the set top box is shown in the schematic diagram of the implementation process Figure One ;

[0023] Figure 3 The control method of the set top box is shown in the schematic diagram of the implementation process Figure Two ;

[0024] Figure 4 The control method of the set top box is shown in the schematic diagram of the implementation process Figure Three ;

[0025] Figure 5 The control method of the set top box is shown in the schematic diagram of the implementation process Figure Four ;

[0026] Figure 6 The control system is shown in the schematic diagram of the overall architecture

[0027] Figure 7 The control method of the set top box is shown in the schematic diagram of the implementation process Figure Five ;

[0028] Figure 8 The control system is shown in the schematic diagram of the component structure Figure Two ;

[0029] Figure 9 A schematic diagram of a configuration of a control system Figure Three . DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It can be understood that the specific embodiments described herein are only used to explain the related application, and not to limit the application. In addition, it should be noted that, for the convenience of description, only the parts related to the application are shown in the drawings.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing the embodiments of the present application only, and is not intended to limit the present application.

[0032] In the following description, "some embodiments" are related to a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. It should be noted that the terms "first\second\third" related to the embodiments of the present application are only used to distinguish similar objects, and do not represent a specific order of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence as allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0033] Digital video conversion box (Set Top Box, STB), commonly known as set-top box or on-box, is a device connected to the television and external signal source. It can convert compressed digital signals into television content and display it on the television. The signal can come from cable, satellite antenna, broadband network and terrestrial broadcast. In addition to the image and sound provided by analog television, set-top box can also receive digital content, including electronic program guide, Internet web page, etc. It enables users to watch digital television programs on existing televisions, and can interact with digital entertainment, education and commercial activities through the network.

[0034] With the development of technology and intelligence, set-top box is also more and more intelligent. From the original application of playing only television programs, it has changed to many applications such as game and Internet, providing more and more applications for users, greatly facilitating users. With the help of set-top box, users can not only receive and watch basic digital programs, but also enjoy some special application services, such as video on demand, quasi-video on demand, electronic program menu, data broadcast, PVR, Internet information browsing, game, etc.

[0035] On the one hand, the voice assistants installed on set-top boxes on the market are not universal. The software terminal versions and functions of set-top boxes in different provinces are different, which makes it difficult to manage the voice assistant versions. Every software terminal upgrade brings great risks.

[0036] On the other hand, currently available voice assistants that support voice control require a new version release every time a user installs a third-party application to enable voice control integration. This means that Android application packages (APKs) downloaded from third-party stores often lack support for skill integration. Furthermore, when a user subscribes to a different set-top box provider, the set-top box needs to be forcibly upgraded to function, posing a significant risk to the user.

[0037] In other words, due to the large number of set-top box models and the significant differences in software interfaces, there are problems such as long development and adaptation cycles for new services and functions, as well as high upgrade risks for license holders, which greatly reduces the intelligence and functional scalability of set-top boxes.

[0038] To address the aforementioned issues, in the embodiments of this application, the control system utilizes middleware to unify input / output interfaces. This middleware facilitates communication with the business platform and underlying systems, enabling the set-top box to possess unified licensing capabilities. Simultaneously, it exposes various operating system services and, by combining displayed content and voice information, determines the scene, achieving dynamic expansion of voice capabilities. This shortens development and adaptation cycles, significantly reduces risks, and enhances the set-top box's intelligence and functional scalability.

[0039] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0040] One embodiment of this application provides a control method for a set-top box, which is applied to a control system. The control system includes a service platform, a set-top box, a third-party application platform, and a terminal device. The set-top box communicates with the service platform through a first interface; the set-top box communicates with the third-party application platform through a second interface; and the set-top box communicates with the terminal device through a third interface.

[0041] Figure 1 Schematic diagram of the control system's structure Figure One ,like Figure 1 As shown, the control system 10 may include a service platform 11, a set-top box 12, a third-party application platform 13, and terminal equipment 14.

[0042] It should be noted that in the embodiments of the present application, the set top box 12 can communicate with the service platform 11 through the first interface 15, and the set top box 12 can communicate with the third-party application platform 13 through the second interface 16, and the set top box 12 can communicate with the terminal device 14 through the third interface 17.

[0043] Further, in the embodiments of the present application, part of the software system of the set top box 12 can be regarded as middleware, wherein the middleware can interact with the service platform 11 through the first interface 15, and the middleware can interact with the third-party software provided by the third-party application platform 13 through the second interface 16, and the middleware can interact with the set top box underlying operating system running in the terminal device 14 through the third interface 17. The set top box underlying operating system can be an operating system running in the terminal device 14. For example, the set top box underlying operating system is an Android system of the terminal device.

[0044] It should be noted that in the embodiments of the present application, the middleware can provide capability support for the upper-layer service through the first interface 15 and the second interface 16, and the middleware can make capability requirements for the set top box underlying operating system through the third interface 17.

[0045] That is to say, for the problem of large interface difference, the control system in the present application can unify the input and output interfaces by means of the middleware, and the communication with the service platform and the underlying system is completed through the middleware.

[0046] It can be understood that in the embodiments of the present application, the service platform 11 in the control system 10 can include at least one platform implementing a plurality of different functions. For example, the service platform 11 can include a network management platform, a voice service platform, an authentication platform, etc. The present application does not make specific limitation. The voice service platform can be a voice-related service platform for realizing voice interaction and control. Specifically, the service platform 11 can be a cloud with different functional modules.

[0047] Further, in the embodiments of the present application, when the set top box 12 interacts with the service platform 11 through the first interface 15, the authentication platform can obtain authentication information for identity verification from the set top box 12 through the first interface 15; the voice service platform can obtain device information of the middleware from the set top box 12 through the first interface 15, and the voice service platform can issue service data to the set top box 12 through the first interface 15; the network management platform can issue network management commands, set top box parameters, configuration information, etc. to the set top box 12 through the first interface 15.

[0048] Further, in the embodiment of the present application, when the set-top box 12 interacts with the third-party application platform 13 through the second interface 16, the set-top box 12 implements the play control capability through the second interface 16; the set-top box 12 implements the page rendering capability through the second interface 16; the set-top box 12 implements the data storage and the like through the second interface 16.

[0049] It should be noted that, in the embodiment of the present application, when the set-top box 12 interacts with the terminal device 14 through the third interface 17, the set-top box 12 implements the update of the boot animation or the start picture through the third interface 17; the set-top box 12 implements the notification of the error code through the third interface 17; the set-top box 12 implements the MediaProcessor play interface through the third interface 17; the set-top box 12 implements the setting of the set-top box hardware parameters through the third interface 17 and the like.

[0050] Further, in the embodiment of the present application, the set-top box 12 in the control system 10 can be configured with a processor, a memory and at least one function module. Different function modules are used to implement different functions.

[0051] It can be understood that, in the embodiment of the present application, the set-top box 12 can be configured with a plurality of function modules such as a player, a browser, a setting module, a network management module, a data center and an error code module.

[0052] Correspondingly, in the embodiment of the present application, the set-top box 12 can implement the player function through the player; the set-top box 12 can implement the browser function through the browser; the set-top box 12 can implement the setting function through the setting module; the set-top box 12 can implement the network management function through the network management module; the set-top box 12 can implement the setting function through the setting module; the set-top box 12 can implement the data center function through the data center; and the set-top box 12 can implement the error code function through the error code module.

[0053] That is to say, in the embodiment of the present application, based on the at least one function module configured by the set-top box 12, the set-top box 12 can implement different functions, thereby providing unified capability support for the set-top box service.

[0054] Correspondingly, in the embodiment of the present application, based on the at least one function module configured by the set-top box 12, such as the player, the browser, the network management module and the like, the first interface 15 can include a first player interface, a first browser interface, a terminal network management interface and the like.

[0055] Correspondingly, in the embodiment of the present application, based on the at least one function module configured by the set-top box 12, such as the player, the browser, the data center and the like, the second interface 16 can include a second player interface, a second browser interface, a data center interface and the like.

[0056] Accordingly, in the embodiments of this application, based on at least one functional module configured in the set-top box 12, such as a network management module, an error code module, a player, a settings module, a data center, etc., the third interface 17 may include a terminal management service interface, an error code interface, a third player interface, a settings interface, a system attribute interface, etc.

[0057] It should be noted that, in the embodiments of this application, for the set-top box 12 in the control system 10, through the setting of middleware and the interaction with the business platform, third-party application platform and terminal device, on the one hand, it needs to have the ability of a unified license holder, and on the other hand, it needs to expose various services of the operating system to the outside world.

[0058] Furthermore, in the embodiments of this application, since the middleware has the capability to unify license holders, when a new third-party license holder is added, protocol integration can be performed according to the middleware specification. Specifically, the original middleware protocol remains unchanged, and the license holder will adapt accordingly, so there is no need to upgrade the middleware.

[0059] In other words, in the embodiments of this application, the middleware with unified licensee capability can maintain the middleware protocol unchanged when a new third-party license is added.

[0060] It should be noted that, in the embodiments of this application, the capability requirements of the set-top box 12 in the control system 10 may include: browser, player, network management, data and other related capability requirements. The specific rules mainly include general capabilities, so that the set-top box 12 can support different service types such as live broadcast service, video-on-demand service, replay service, and live time-shift service.

[0061] Figure 2 A schematic diagram of the control method for a set-top box. Figure One ,like Figure 2 As shown in the embodiments of this application, the method for controlling the set-top box by the control system may include the following steps:

[0062] Step 101: The set-top box obtains third-party applications from the third-party application platform.

[0063] In the embodiments of this application, the set-top box in the control system can first obtain third-party applications from a third-party application platform in the control system.

[0064] It is understood that, in the embodiments of this application, the set-top box in the control system can also be replaced by other smart devices that have the function of converting digital signals into television content.

[0065] It should be noted that in the embodiments of the present application, in order to realize dynamic expansion of voice capability, when a new APK application needs to be launched on the set-top box application market, the APK approval process can be submitted first, and skills and corresponding scenes can be dynamically created in the approval process, and the APK can be put online after passing the audit. After going online, the set-top box can download the APK application independently, and because the skills have passed the audit, the voice capability realizes hot deployment.

[0066] Further, in the embodiments of the present application, before the set-top box obtains the third-party application from the third-party application platform, the third-party application platform can first perform skill addition, dialogue training, and model authorization processing on the third-party application.

[0067] It should be noted that in the embodiments of the present application, because the new APK application needs to have voice interaction function, the skill addition, dialogue training and the like can be completed through the interaction platform first, and the model authorization processing can also be performed. Correspondingly, the end-side upgrade is not required on the set-top box side, so that the intelligent adaptation of voice can be realized.

[0068] Step 102, when running the third-party application, the set-top box detects voice information and sends the voice information to the business platform.

[0069] In the embodiments of the present application, after the set-top box obtains the third-party application from the third-party application platform, when running the third-party application, the set-top box can detect voice information, and then can send the detected voice information to the business platform in the control system.

[0070] It can be understood that in the embodiments of the present application, when the set-top box is installed and running, the voice detection processing can be performed through the voice recognition module, so as to obtain the voice information. The voice information can be voice content corresponding to voice on-demand.

[0071] That is, in the embodiments of the present application, because the control system can realize dynamic expansion of voice capability, the user voice on-demand can directly arouse the third-party application and perform voice interaction of the third-party application.

[0072] It should be noted that after detecting the voice information, the set-top box can directly send the voice information to the business platform, and the business platform can perform the analysis processing of the voice information.

[0073] It can be understood that in the embodiments of the present application, when the set-top box is connected through the Internet television set-top box terminal technology specification, the whole process voice interaction can be supported.

[0074] In step 103, the service platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set-top box.

[0075] In the embodiments of the present application, after the set-top box detects the voice information and sends the voice information to the service platform when running the third-party application, the service platform can generate a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and send the control instruction to the set-top box.

[0076] It should be noted that in the embodiments of the present application, the display content of the current interface displayed on the display screen of the video playing device when the set-top box runs the third-party application corresponds to the third-party application. The service platform can first acquire the display content of the current interface.

[0077] It can be understood that in the embodiments of the present application, the display content of the current interface can be sent to the service platform by the set-top box, or sent to the service platform by the video playing device. That is, when acquiring the display content of the current interface, one way is that the video playing device directly sends the display content of the current interface of the display screen to the service platform in the control system, and the other way is that the set-top box first acquires the display content of the current interface of the display screen of the video playing device, and then sends the display content of the current interface to the service platform in the control system.

[0078] Further, in the embodiments of the present application, after the service platform respectively acquires the display content of the current interface corresponding to the third-party application and the voice information, the service platform can further generate a control instruction according to the display content and the voice information, and send the control instruction to the set-top box.

[0079] It can be understood that in the embodiments of the present application, the control instruction is used to respond to the voice information and control the set-top box to realize the corresponding service capability.

[0080] In step 104, if the set-top box is successfully adapted with the license party based on the control instruction, the set-top box calls the terminal device to realize the service function corresponding to the voice information.

[0081] In the embodiments of the present application, after the service platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set-top box, if the set-top box is successfully adapted with the license party based on the control instruction, the set-top box can call the terminal device to realize the service function corresponding to the voice information.

[0082] It should be noted that in the embodiments of the present application, after the set top box receives the control instruction issued by the service platform, the set top box can perform adaptation processing with the corresponding license party according to the control instruction, if the set top box can successfully adapt with the license party, then the set top box can execute processing corresponding to the voice information detected during the voice on-demand by calling the terminal device, and realize the corresponding service function.

[0083] It can be understood that in the embodiments of the present application, since the set top box has the ability of unified license party, when the license party is added, the protocol can be directly connected according to the middleware specification, and the set top box protocol is not changed, and the license party will be adapted, without the need to upgrade the set top box.

[0084] Further, in the embodiments of the present application, the license party can be a broadcast control party in each region, and the control instruction can be a special instruction obtained by the license party configured by the service platform based on the general initial instruction, so the set top box does not need to perform firmware upgrade and adaptation processing.

[0085] It should be noted that in the embodiments of the present application, since the control instruction is generated based on the display content of the current interface and the voice information corresponding to the voice on-demand, the service function implemented by the set top box in response to the control instruction is corresponding to the display content and the voice information. For example, the display content is a movie list, and the voice information is "movie A", then the implemented service function can be playing movie A in the movie list; the display content is a search home page, and the voice information is "movie A", then the implemented service function can be searching movie A.

[0086] Further, in the embodiments of the present application, Figure 3 The implementation flow of the control method of the set top box Figure Two As shown in the figure, Figure 3 After the service platform generates the control instruction according to the display content of the current interface of the third-party application and the voice information, and sends the control instruction to the set top box, that is, after step 103, the control method of the set top box of the control system can further include the following steps:

[0087] Step 105, if the set top box fails to adapt with the license party based on the control instruction, the set top box performs resource re-search processing and failure feedback processing.

[0088] In the embodiments of this application, the service platform generates control commands based on the display content of the current interface corresponding to the third-party application and the voice information, and sends the control commands to the set-top box. If the set-top box fails to adapt to the license holder based on the control commands, the set-top box can choose to re-search and process according to the control commands. At the same time, it can feed back the adaptation failure information to the service platform.

[0089] Furthermore, in the embodiments of this application, the set-top box's on-demand resource retrieval can be divided into licensed resources and internet resources. After receiving the control command issued by the service platform, if the set-top box fails to adapt to the licensed provider based on the control command, the set-top box can choose to re-process the internet resource retrieval according to the control command.

[0090] Accordingly, in the embodiments of this application, after the set-top box determines that it cannot be successfully adapted to the licensee, it can also synchronize the adaptation failure information to the business platform (cloud), so that product operators can organize troubleshooting after obtaining the adaptation failure information.

[0091] It is understood that, in the embodiments of this application, after the set-top box receives the control command issued by the service platform, if the set-top box fails to adapt to the licensee based on the control command, the set-top box can also use voice prompt processing to indicate the failure of the voice-on-demand response, so that the executor of the voice-on-demand is aware that the voice-on-demand has failed.

[0092] It should be noted that, in the embodiments of this application, the terminal device can be any device with storage and communication functions. Specifically, the terminal device is not limited to various types of terminal devices such as laptops, tablets, desktop computers, mobile devices (e.g., mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices, in-vehicle devices, and wearable devices).

[0093] Furthermore, in the embodiments of this application, Figure 4 A schematic diagram of the control method for a set-top box. Figure Three ,like Figure 4 As shown, the method by which the business platform generates control commands based on the displayed content of the current interface corresponding to the third-party application and the voice information may include the following steps:

[0094] Step 201: The business platform determines the first scenario corresponding to the displayed content and the second scenario corresponding to the voice information.

[0095] In the embodiments of the present application, the business platform can determine the scene type corresponding to the display content of the current interface of the third-party application according to the obtained display content, i.e., the first scene; at the same time, the business platform can also determine the scene type corresponding to the voice information according to the received voice information, i.e., the second scene.

[0096] In step 202, the business platform determines a target scene according to the first scene and the second scene, and performs parsing processing on the voice information based on the target scene to obtain a parsing result.

[0097] In the embodiments of the present application, after determining the first scene corresponding to the display content and the second scene corresponding to the voice information, the business platform can further determine a target scene according to the first scene and the second scene, and then perform parsing processing on the voice information based on the target scene to finally obtain a parsing result.

[0098] Further, in the embodiments of the present application, the business platform can compare the first scene and the second scene first, and then determine the final target scene according to the comparison result. The target scene is obtained based on the display content of the current interface of the third-party application and the voice information of the voice on-demand.

[0099] It should be noted that in the embodiments of the present application, if the comparison result is that the first scene and the second scene are the same, i.e., the scene predicted based on the display content of the current interface of the third-party application is consistent with the scene predicted based on the voice information, then the business platform can determine the first scene or the second scene as the final target scene.

[0100] It should be noted that in the embodiments of the present application, if the comparison result is that the first scene and the second scene are different, i.e., the scene predicted based on the display content of the current interface of the third-party application is inconsistent with the scene predicted based on the voice information, then the business platform can further determine the target scene according to the first scene, the second scene and a scene recognition model.

[0101] It can be understood that in the embodiments of the present application, the scene recognition model is a model obtained by pre-training and used for scene induction processing. Specifically, through the scene recognition model, the scene predicted based on the display content of the current interface of the third-party application and the scene predicted based on the voice information can be weighted and fused, and finally the target scene is obtained.

[0102] Further, in the embodiments of the present application, when the voice information of the user's voice on-demand is inconsistent with the display content of the current interface, the scene induction processing needs to be performed, that is, the target scene generation processing is performed. Specifically, when the scene induction processing is performed, the display content of the current interface can be further determined according to the skill domain, and then the skill domain not belonging to the scene information is filtered, so that the response can be more focused on the real intention concerned by the user's voice on-demand, and the user satisfaction is improved.

[0103] It should be noted that, in the embodiments of the present application, in order to ensure the accuracy of scene prediction, the present application proposes a weighted fusion scene prediction method, which avoids the noise interference of different expressions of the same intention and different scenes, and also considers the scene information of different expressions and screen states, so as to obtain more useful information for vector representation and improve the accuracy of intention recognition, and finally obtain accurate scene information.

[0104] Further, in the embodiments of the present application, the jth sample representation matrix of the ith category can be first calculated according to the following formula (1). The nonlinear conversion is performed by using an activation function squash.

[0105]

[0106] Wherein, S w The scene weighting coefficient can be b w The scene polarization can be trained according to the user's on-demand habits.

[0107] It can be understood that, in the embodiments of the present application, during the establishment of the scene recognition model, the related features and favorite data set establishment and parameter training of the user are selected, so that the obtained scene recognition model has stronger relevance with the user than other models (for example, different users are identified by voiceprint), different users are identified by different scene recognition models, and then the model can be adjusted according to the user, so that different users have different voice operation habits, and personalized recognition bias can be obtained during scene recognition.

[0108] Then, the weighted sum of the converted sample representation is obtained, and the scene information is obtained.

[0109] It should be noted that, in the embodiments of the present application, in order to improve the model effect, the k samples in each class can be selected to represent the class vector As shown in the following formula (2):

[0110]

[0111] Wherein, N iis the total number of samples in the category i. The fused category-level feature is denoted as Then, the following formula (3) is obtained.

[0112]

[0113] wherein ω represents a weight value of the scene feature, and satisfies ω1+ω2=1. A class vector that can better represent rich semantic information is given a larger weight, and vice versa. Wherein ω1 represents the large screen scene weight, and ω2 represents the voice analysis scene weight.

[0114] Further, the class vector after fusion is compressed by the activation function squash function, and is nonlinearly mapped to the interval [0, 1] to obtain a new class vector as shown in the following formula (4):

[0115]

[0116] Finally, the best class vector can be obtained by iterating multiple times.

[0117] It should be noted that the class vector obtained by training according to the above method can effectively improve the accuracy of scene recognition, and can improve the accuracy by more than 37% through verification, greatly improving the scene recognition capability of the control system, and can be packaged into a standard interface for use by third-party manufacturers.

[0118] Step 203, the business platform generates an initial instruction based on the analysis result, performs license side adaptation processing based on the initial instruction, and obtains a control instruction.

[0119] In the embodiments of the present application, after the business platform determines the target scene according to the first scene and the second scene, and performs analysis processing on the voice information based on the target scene to obtain an analysis result, the business platform can generate a corresponding initial instruction using the analysis result, and then the business platform can perform adaptation processing of the license side based on the initial instruction, and finally obtain a corresponding control instruction.

[0120] Further, in the embodiments of the present application, the license side can be a broadcast control side in each region, and the initial instruction generated by the business platform based on the analysis result can be a general instruction. The business platform can configure different license sides by region (such as by province), and finally adapt the initial instruction to a special instruction of the license side, i.e. generate a corresponding control instruction, and issue the control instruction to the set-top box.

[0121] It can be understood that, in the embodiments of the present application, since the control instruction acquired by the set-top box and issued by the service platform is a special instruction corresponding to the license party, the set-top box does not need to perform firmware upgrading and adaptation processing.

[0122] Further, in the embodiments of the present application, Figure 5 Implementation flow of the control method for the set-top box Figure Four As shown in Figure 5 The method for the control system to control the set-top box can include the following steps:

[0123] Step 301, the service platform receives current hot word information.

[0124] Step 302, the service platform determines a target label according to a pre-stored hot word template and the current hot word information, and sends the target label to the set-top box.

[0125] Step 303, the set-top box performs search processing according to the target label.

[0126] In the embodiments of the present application, the service platform can first receive current hot word information; then can further determine a target label according to a pre-stored hot word template and the current hot word information, and then can send the target label to the set-top box; accordingly, the set-top box can perform search processing according to the target label, thereby being able to support the electrical program guide (EPG) hot word function.

[0127] It should be noted that, in the embodiments of the present application, the current hot word information can be the hot word content currently displayed on the display screen of the video playing device. The current hot word information can include movie name, classification, label page information, user information, etc.

[0128] It can be understood that, in the embodiments of the present application, the current hot word information can be sent to the service platform by the set-top box, or can be sent to the service platform by the video playing device. That is, when acquiring the current hot word information, one way is that the video playing device directly sends the current hot word information currently displayed on the display screen to the service platform in the control system; another way is that the set-top box first acquires the current hot word information currently displayed on the display screen of the video playing device, and then sends the current hot word information to the service platform in the control system.

[0129] Further, in the embodiments of the present application, the pre-stored hot word template can be used for analyzing and processing the current hot word information. The service platform can pre-configure and store the hot word template.

[0130] It should be noted that in the embodiments of the present application, after receiving the current hot word information, the business platform can determine the target label corresponding to the current hot word information through the pre-stored hot word template, and then send the target label to the set top box for subsequent processing.

[0131] Further, in the embodiments of the present application, after receiving the target label corresponding to the current hot word information issued by the business platform, the set top box can perform search processing according to the target label.

[0132] It can be understood that in the embodiments of the present application, the target label can be used to divide the types of hot word information, for example, the target label generated for hot word information corresponding to a movie name includes action film, documentary, comedy, historical film, etc.

[0133] The embodiments of the present application provide a control method of a set top box, which is applied to a control system, wherein the control system comprises a business platform, a set top box, a third-party application platform and a terminal device; the set top box communicates with the business platform through a first interface; the set top box communicates with the third-party application platform through a second interface; the set top box communicates with the terminal device through a third interface; the set top box obtains a third-party application from the third-party application platform; when running the third-party application, the set top box detects voice information and sends the voice information to the business platform; the business platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set top box; if the set top box is successfully adapted with the license side based on the control instruction, the set top box calls the terminal device to realize the business function corresponding to the voice information. That is, in the embodiments of the present application, the unified input and output interface of the middleware can be used to complete the communication with the business platform and the underlying system through the middleware, so that the set top box has unified license side capability, can expose the services of the operating system to the outside, and can determine the scene by combining the display content and the voice information, thereby realizing the dynamic expansion of voice capability. The development and adaptation cycle can be shortened, the risk can be greatly reduced, and the intelligence and functional expansibility of the set top box can be improved.

[0134] Based on the above embodiments, further, the control system of the set top box provided by the embodiments of the present application can be a control system of a set top box with dynamic expansion of voice capability, wherein the control system can be composed of middleware, a business platform, a third-party application platform and a set top box underlying operating system.

[0135] Further, in the embodiments of the present application, Figure 6 The overall architecture of the control system is shown in FIG. 1, which comprises a middleware, a business platform, a third-party application platform and a set top box underlying operating system. Figure 6As shown, the control system of the set top box can mainly include middleware, a service platform, a third-party application platform, and a set top box underlying operating system. The middleware can interact with the service platform through a northbound interface N1 (first interface). The middleware can interact with the third-party application platform through a northbound interface N2 (second interface). The middleware can interact with the set top box underlying operating system through a southbound interface S (third interface).

[0136] It should be noted that in the embodiments of the present application, the middleware in the control system can be part of a software system of any intelligent device having a function of converting a digital signal into television content. For example, the middleware can be part of a software system in a set top box or a smart television, and the present application does not make specific limitations.

[0137] It can be understood that in the embodiments of the present application, the service platform in the control system can include at least one platform implementing a plurality of different functions. For example, the service platform can include a network management platform, a voice service platform, an authentication platform, and the like. The present application does not make specific limitations. The voice service platform can be a voice-related service platform implementing voice interaction and control.

[0138] Further, in the embodiments of the present application, the set top box underlying operating system can be an operating system running in a terminal device. For example, the set top box underlying operating system is an Android system of the terminal device.

[0139] It should be noted that in the embodiments of the present application, from the overall function, the middleware can provide capability support for the upper-layer service through the northbound interface (interface N1, interface N2), and at the same time, the middleware can make capability requirements for the set top box underlying operating system (terminal device) through the southbound interface (interface S).

[0140] It can be understood that in the embodiments of the present application, the northbound interface N1 (first interface) is mainly used for the middleware to interact with the service platform. For example, the authentication platform can obtain authentication information for identity verification from the middleware through the northbound interface N1. The voice service platform can obtain device information of the middleware from the middleware through the northbound interface N1, and at the same time, the voice service platform can issue service data to the middleware through the northbound interface N1. The network management platform can issue network management commands, set top box parameters, configuration information, and the like to the middleware through the northbound interface N1.

[0141] Further, in the embodiments of the present application, the northbound interface N2 (second interface) is mainly used for the middleware to interact with the third-party application platform. For example, the middleware implements a play control capability through the northbound interface N2. The middleware implements a page rendering capability through the northbound interface N2. The middleware implements data storage through the northbound interface N2.

[0142] It should be noted that in the embodiments of the present application, the southbound interface S (the third interface) is mainly used for interaction between the middleware and the bottom layer operating system of the set top box. For example, the middleware realizes the update of the boot animation or the start picture through the southbound interface S; the middleware realizes the notification of the error code through the southbound interface S; the middleware realizes the MediaProcessor playing interface through the southbound interface S; the middleware realizes the setting of the hardware parameters of the set top box through the southbound interface S, and the like.

[0143] Further, in the embodiments of the present application, the middleware in the control system can be configured with a processor, a memory and at least one functional module. Different functional modules are used to realize different functions.

[0144] It can be understood that in the embodiments of the present application, the middleware can be configured with a player, a browser, a setting module, a network management module, a data center and an error code module, and the like.

[0145] Correspondingly, in the embodiments of the present application, the middleware can realize the player function through the player; the middleware can realize the browser function through the browser; the middleware can realize the setting function through the setting module; the middleware can realize the network management function through the network management module; the middleware can realize the setting function through the setting module; the middleware can realize the data center function through the data center; and the middleware can realize the error code function through the error code module.

[0146] That is to say, in the embodiments of the present application, based on the at least one functional module configured by the middleware, the middleware can realize different functions, so as to provide unified capability support for the set top box service.

[0147] Correspondingly, in the embodiments of the present application, based on the at least one functional module configured by the middleware, such as the player, the browser, the network management module and the like, the northbound interface N1 (the first interface) can include a player northbound interface (a first player interface), a browser northbound interface (a first browser interface), a terminal network management northbound interface (a terminal network management interface), and the like.

[0148] Correspondingly, in the embodiments of the present application, based on the at least one functional module configured by the middleware, such as the player, the browser, the data center and the like, the northbound interface N2 (the second interface) can include a player northbound interface (a second player interface), a browser northbound interface (a second browser interface), a data center northbound interface (a data center interface), and the like.

[0149] Correspondingly, in the embodiments of the present application, based on at least one function module configured by the middleware, such as a network management module, an error code module, a player, a setting module, a data center, etc., the southbound interface S (the third interface) can include a terminal management service southbound interface (terminal management service interface), an error code southbound interface (error code interface), a player southbound interface (third player interface), a setting southbound interface (setting interface), a system attribute southbound interface (system attribute interface), etc.

[0150] It should be noted that, in the embodiments of the present application, for the middleware in the control system, on the one hand, it needs to have the ability of a unified license party, and on the other hand, it needs to expose each service of the operating system to the outside.

[0151] Further, in the embodiments of the present application, since the middleware has the ability of a unified license party, when a third-party license party is added, the protocol can be connected according to the middleware specification. Specifically, the original middleware protocol is not changed, and the license party will be adapted, so there is no need to upgrade the middleware.

[0152] That is to say, in the embodiments of the present application, the middleware with the ability of a unified license party can keep the middleware protocol unchanged when a third-party license is added.

[0153] It should be noted that, in the embodiments of the present application, the capability requirement of the middleware in the control system can include: browser, player, network management, data, and other related capability requirements, and the specific rules mainly include general capabilities, so that the middleware can support different business types such as live broadcast business, on-demand business, review business, and live broadcast time shift business.

[0154] It can be understood that, in the embodiments of the present application, the live broadcast business refers to supporting a user to select a channel number and watch a television program, and the platform side pushes the same audio and video stream to all users who select the live broadcast channel, and plays the predetermined content to provide the user with a television program. Correspondingly, for the live broadcast business, the middleware needs to support the following functions or requirements:

[0155] 1. The user can enter the live broadcast channel through the set-top box by the EPG page link or directly inputting the channel number.

[0156] 2. During the live broadcast watching process, the remote controller can be used to switch between multiple live broadcast channels, and the user can leave the current live broadcast channel at any time.

[0157] Among them, the broadcast action is com.komect.askill.iptv.LIVE.

[0158] The broadcast intent.getExtras() extension information is shown in Table 1.

[0159] Table 1

[0160]

[0161]

[0162] It can be understood that, in the embodiments of the present application, the on-demand service is a service supporting playing, pausing, fast-forwarding, rewinding, and the like of audio and video content stored on the platform side by the user. Correspondingly, for the on-demand service, the middleware needs to support the following functions or requirements:

[0163] 1. The user can control the set-top box to select an on-demand program in the EPG for playing through the remote controller.

[0164] 2. The user can perform 2X, 4X, 8X, 16X, 32X fast-forwarding or rewinding, time axis dragging time shifting, positioning playing, and the like in the on-demand program playing.

[0165] 3. The user can exit the on-demand program currently playing at any time in the on-demand program playing through the remote controller operation.

[0166] 4. There is no mosaic, no obvious jumping, no stagnation, and no lip sync phenomenon in the normal playing of the video content.

[0167] 5. In the fast-forwarding, rewinding, pausing and resuming, positioning playing, and the like of the video content, the image frame is displayed clearly and without mosaic.

[0168] The broadcast action is com.komect.askill.iptv.VIDEO.

[0169] The broadcast intent.getExtras() extension information is shown in Table 2.

[0170] Table 2

[0171]

[0172]

[0173]

[0174] It can be understood that, in the embodiments of the present application, the look-back service is a service supporting playing, pausing, fast-forwarding, rewinding, and the like of a television program that has been broadcast live on the platform side within a specified time. For the television look-back service. Correspondingly, for the look-back service, the middleware needs to support the following functions or requirements:

[0175] 1. The user can control the set-top box to select a look-back program in the EPG for playing through the remote controller.

[0176] 2、 User can perform 2X, 4X, 8X, 16X, 32X fast forward, fast backward, time axis dragging, time shifting, positioning, playing and other operations in the TV review play.

[0177] 3、 User can exit the TV review program being played at any time in the TV review service through remote control operation.

[0178] The broadcast action is com.komect.askill.iptv.TVBACK.

[0179] The broadcast intent.getExtras() extension information is shown in Table 3.

[0180] Table 3

[0181]

[0182]

[0183] It can be understood that in the embodiments of the present application, the live time shifting service is a service supporting the user to perform short pause, reverse and fast forward operations on the live channel being played in real time. Accordingly, for the live time shifting service, the middleware needs to support the following functions or requirements:

[0184] 1、 User can control the set top box to switch between live and instant time shifting (instant time shifting pause) through the remote control.

[0185] It can be understood that the control proposed in the embodiments of the present application proposes a unified requirement for the set top box service bearing mechanism through the setting of the middleware, and in the case of keeping the overall function and service bearing capacity of the set top box unchanged, the intermediate layer (middleware) is separated from the original software system of the set top box, and the communication with the underlying license party and the operating system is completed. Thus, the problems of long development and adaptation cycle of new services and new functions caused by the large number of set top box models and large differences in software interfaces can be effectively solved.

[0186] It can be understood that the control system proposed in the embodiments of the present application, through the setting of the middleware, can make the set top box middleware expose various capability calling interfaces to the outside, and the interface can be used for communication with third party services, so that after installing a new APK, the service can be directly called according to the standard specification, and the dynamic expansion of voice capability can be realized without upgrading the voice assistant version after the APK is installed.

[0187] Further, the control method of the set-top box provided in the embodiments of the present application can support the dynamic EPG hotword function. Specifically, the service platform can first receive current hotword information, then can further determine a target label according to a pre-stored hotword template and the current hotword information, and then can send the target label to the set-top box; correspondingly, the set-top box can perform search processing according to the target label.

[0188] It should be noted that in the embodiments of the present application, the current hotword information can be hotword content currently displayed on the display screen of the video playing device. The current hotword information can include movie name, classification, tab page information, user information, and the like.

[0189] It can be understood that in the embodiments of the present application, the current hotword information can be sent to the service platform by the set-top box, or can be sent to the service platform by the video playing device. That is, when the current hotword information is acquired, one way is that the video playing device directly sends the current hotword information currently displayed on the display screen to the service platform in the control system, and another way is that the set-top box first acquires the current hotword information currently displayed on the display screen of the video playing device, and then sends the current hotword information to the service platform in the control system.

[0190] Further, in the embodiments of the present application, the pre-stored hotword template can be used for analyzing and processing the current hotword information. The service platform can pre-configure and store the hotword template.

[0191] It should be noted that in the embodiments of the present application, after the service platform receives the current hotword information, the target label corresponding to the current hotword information can be determined through the pre-stored hotword template, and then the target label can be sent to the set-top box for subsequent processing.

[0192] Further, in the embodiments of the present application, after the set-top box receives the target label corresponding to the current hotword information issued by the service platform, the set-top box can perform search processing according to the target label.

[0193] For example, in the embodiments of the present application, the natural language processing (NLP) engine in the service platform can configure a general hotword template. When the received hotword content is matched and analyzed according to the hotword template, the corresponding content name and content label are obtained, and then the content name and content label are issued to the set-top box, so that the set-top box completes the search logic according to the content label.

[0194] It should be noted that in the embodiments of the present application, the third-party vendor APK submits for review, and then applies for a voice access process, at which time the intent and the word slot can be dynamically configured on the World Wide Web (Web), and after the review, the model takes effect, and the corpus supporting the cloud NLP engine is dynamically added, so that the voice capability that can be dynamically expanded can be realized by installing the APK.

[0195] Further, the control system of the set-top box proposed in the embodiments of the present application can be a control system of a set-top box that can dynamically expand voice capability. In the case of access by the set-top box through the Internet television set-top box terminal technology specification, full-process voice interaction can be supported.

[0196] Specifically, in the embodiments of the present application, when voice on-demand is performed in different interface states of an application, different business functions can be realized according to different display contents of the current interface based on the same voice on-demand content (i.e., voice information). For example, when the display content of the current interface is a video list interface, if it is detected that the voice on-demand of the user is a specific film name, the corresponding executed processing is to select the film on the video list interface; when the display content of the current interface is a home page, if it is detected that the voice on-demand of the user is a specific film name, the corresponding executed processing is to perform a video search.

[0197] It can be understood that in the embodiments of the present application, the display content of the current interface can be sent by the set-top box to the business platform, or can be sent by the video playing device to the business platform. That is, when the display content of the current interface is acquired, one way is that the video playing device directly sends the display content of the current interface of the display screen to the business platform in the control system, and the other way is that the set-top box first acquires the display content of the current interface of the display screen of the video playing device, and then sends the display content of the current interface to the business platform in the control system.

[0198] It should be noted that in the embodiments of the present application, the scene information can be represented as a json format string, as follows:

[0199] Table 4

[0200]

[0201]

[0202]

[0203] The scene registration command words in Table 4 are described as follows:

[0204] _scene is the scene identifier, the naming rule is that the application package name is in front of the scene name.

[0205] _commands is the command description, containing the command and the statement sent back to the application, stored in the form of key-value pairs. The key is the command id, and the value is various possible statements of the function. Specifically, it can be divided into three categories:

[0206] 1. Command word phrases, such as: open, exit;

[0207] 2. Predefined semantics, starting with "$P", such as: $P(_PLAY);

[0208] 3. Fuzzy slot, starting with "$W" followed by the name of the slot, such as: $W(video) where "video" corresponds to the name of the slot in the _fuzzy_words node;

[0209] 4. Prefix plus fuzzy slot, starting with a prefix plus "$" followed by the name of the slot, such as: I want to see $(video) where "video" corresponds to the name of the slot in the _fuzzy_words node;

[0210] 5. Fuzzy slot plus suffix, starting with "$" followed by the name of the slot plus suffix, such as: $(video) movie where "video" corresponds to the name of the slot in the _fuzzy_words node;

[0211] The content of _fuzzy_words corresponds to the custom slot in the _commands node. If there is no custom slot in the _commands node, the _fuzzy_words node does not exist.

[0212] Further, in the embodiments of the present application, when the voice information of the user's voice on-demand does not match the display content of the current interface, the scene induction processing needs to be performed, that is, the target scene generation processing is performed. Specifically, according to the statistical model, the scene involved in a daily spoken language generally does not exceed 2, which can be adjusted according to the length of the sentence of the voice information. When performing scene induction processing, the display content of the current interface can be further determined according to the skill domain, and then the skill domain not belonging to the scene information is filtered, so that the response can be more focused on the real intention of the user's voice on-demand, and the user satisfaction is improved.

[0213] It should be noted that, in the embodiments of the present application, in order to ensure the accuracy of scene induction, the embodiments of the present application propose a weighted fusion scene induction method, which avoids the noise interference of different expressions of the same intention and different scenes, and also considers the scene information of different expressions and screen states, so as to obtain more useful information for vector representation and improve the accuracy of intention recognition, and finally obtain accurate scene information.

[0214] Further, in the embodiments of the present application, the sample representation matrix of the jth sample of the ith category can be obtained according to the above formula (1) The nonlinear conversion is performed using the activation function squash, and then the weighted sum of the converted sample representation can be obtained.

[0215] It should be noted that, in the embodiments of the present application, in order to improve the model effect, the average of k samples in each category can be selected to represent the category vector As shown in the above formula (2), the fused category-level feature is marked as As shown in the above formula (3).

[0216] Further, the category vector after fusion is compressed by the activation function squash function to make it nonlinearly mapped to the interval [0, 1] to obtain a new category vector as shown in the above formula (4). Finally, the best category vector can be obtained by iterating multiple times.

[0217] It should be noted that the The accuracy of scene recognition can be effectively improved, and the accuracy can be improved by more than 37% through verification, which greatly improves the scene recognition capability of the control system and can be packaged into a standard interface for use by third-party manufacturers.

[0218] Further, in the embodiments of the present application, for a control system including middleware, a business platform, a third-party application platform, and a set-top box underlying operating system, when implementing dynamic expansion of voice capabilities, the manufacturer can first upload a new APK application to the set-top box application market at this time, which needs to submit an APK approval process. In this process, the manufacturer can be guided to dynamically create skills and corresponding scenes, and after passing the audit, the APK can be put online. When the new APK is online, users can download the APK application independently, and because the skill has passed the audit, the voice capability is implemented hot. Correspondingly, the user voice on-demand can directly arouse the application and perform voice interaction of the application. In the interaction scene, both the weight of screen display and the weight of user voice information are included. After the scene is recognized, the context-based sentence analysis is performed, and the license plate side is adapted by the middleware, and finally the set-top box on-demand is implemented.

[0219] It should be noted that in the embodiments of the present application, since the new APK application needs to have voice interaction function, the skill addition, dialogue training and the like can be completed through the interaction platform first, and the model authorization processing can also be performed, and correspondingly, the end side upgrade is not required on the set top box side, so that the intelligent adaptation of voice can be realized.

[0220] Figure 7 Implementation flowchart of the control method of the set top box Figure Five As shown in Figure 7 The middleware downloads and runs the application, and detects the voice information (step 401); the NLP engine receives the voice information (step 402); and determines whether the target scene can be directly determined (step 403), that is, whether the first scene corresponding to the display content of the current interface is consistent with the second scene corresponding to the voice information; if consistent, the first scene or the second scene is directly determined as the target scene (step 404); if not consistent, the target scene needs to be further inferred according to the first scene or the second scene (step 405); then, the voice information can be analyzed based on the target scene to obtain the corresponding analysis result (step 406); further, the control instruction can be generated according to the analysis result (step 407); and the control instruction is issued to the middleware (step 408); the middleware determines whether the corresponding license side can be successfully adapted according to the control instruction (step 409); if successfully adapted, the corresponding business function can be further completed (step 410); if the adaptation fails, the re-search processing and failure information feedback processing are required (step 411).

[0221] It should be noted that the control system of the set top box with dynamically expandable voice capability proposed in the embodiments of the present application can be considered to include a cloud. The main modules of the cloud (i.e., the business platform) can include a voice information processing module, a natural language processing module, an NLP engine module, a skill module, a context analysis module, and a middleware module.

[0222] Further, in the embodiments of the present application, the voice information processing module can be used to convert the user voice file into text information, and in the conversion process, the user uploaded hot words in each field are matched preferentially.

[0223] Further, in the embodiments of the present application, the natural language processing module can perform sensitive word filtering according to the obtained text information spoken by the user, then preferentially match the question and answer pair, and finally perform NLP analysis, and transmit each skill domain and the analysis result obtained by the analysis to the intelligent terminal.

[0224] Further, in the embodiments of the present application, the NLP engine module can distribute the NLP analysis result to the skill domain. The cloud performs corresponding logical processing according to various skill domains. When the voice interaction information is incomplete, the cloud triggers multi-round interaction. The module can hierarchically analyze the skill domain.

[0225] Further, in the embodiments of the present application, the context analysis module can be used to determine the scene according to a weighting algorithm based on the content identifier uploaded by the current terminal with a screen and the NLP analysis result, and preferentially recommend the content displayed on the screen.

[0226] Further, in the embodiments of the present application, the middleware module can complete the connection of the license plate party and the three-party business, encapsulate the northbound interface for the business platform and the three-party application, and can realize seamless access without the adaptation work of the set-top box and the license plate party.

[0227] In summary, the control system of the set-top box provided in the embodiments of the present application can be connected through the Internet television set-top box terminal technology specification, and supports full-process voice interaction. The voice on-demand can execute different functions according to the same content according to the current interface state in different interface states of the application, and the weighting of the large-screen display and the voice analysis is comprehensively considered in the scene determination process, thereby improving the hit rate. For example, when the user selects a specific film in the film list interface by saying a specific film name, and when the user says a specific film name in the home page state, the film search is performed.

[0228] The embodiments of the present application provide a control method of a set-top box. The control method of the set-top box is applied to a control system. The control system includes a business platform, a set-top box, a third-party application platform, and a terminal device. The set-top box communicates with the business platform through a first interface. The set-top box communicates with the third-party application platform through a second interface. The set-top box communicates with the terminal device through a third interface. The set-top box obtains a third-party application from the third-party application platform. When the third-party application is running, the set-top box detects voice information and sends the voice information to the business platform. The business platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set-top box. If the set-top box is successfully adapted with the license plate party based on the control instruction, the set-top box calls the terminal device to realize the business function corresponding to the voice information. That is, in the embodiments of the present application, the unified input and output interface can be realized by means of the middleware, the communication with the business platform and the underlying system can be realized by means of the middleware, the set-top box has the unified license plate party capability, the operating system services can be exposed to the outside, the scene can be determined according to the display content and the voice information, and the voice capability can be dynamically expanded. The development and adaptation cycle can be shortened, the risk can be greatly reduced, and the intelligence and the functional expansibility of the set-top box are improved.

[0229] Based on the above embodiments, in another embodiment of the application, Figure 8 For the composition structure of the control system Figure Two As Figure 8 It is shown that the control system 10 proposed in the embodiments of the application can include an acquisition unit 18, a detection unit 19, a sending unit 110, a generation unit 111, a calling unit 112,

[0230] The acquisition unit 18 is configured to acquire a third-party application from a third-party application platform.

[0231] The detection unit 19 is configured to detect voice information when the third-party application is running.

[0232] The sending unit 110 is configured to send the voice information to a service platform.

[0233] The generation unit 111 is configured to generate a control instruction according to display content of a current interface corresponding to the third-party application and the voice information.

[0234] The sending unit 110 is further configured to send the control instruction to a set-top box.

[0235] The calling unit 112 is configured to call a terminal device to implement a service function corresponding to the voice information if the set-top box is successfully adapted with a license party based on the control instruction.

[0236] In the embodiments of the application, further, Figure 9 For the composition structure of the control system Figure Three As Figure 9 It is shown that the control system 10 proposed in the embodiments of the application can further include a processor 113 and a memory 114 in which processor-executable instructions are stored. Further, the control system 10 can further include a communication interface 115, and a bus 116 for connecting the processor 113, the memory 114, and the communication interface 115.

[0237] In the embodiments of the present application, the processor 113 can be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, or a microprocessor. It can be understood that, for different devices, the electronic device used to implement the functions of the processor can also be other devices, and the embodiments of the present application are not limited specifically. The control system 10 can further include a memory 114, which can be connected with the processor 113, wherein the memory 114 is configured to store executable program codes, the program codes including computer operation instructions, and the memory 114 can include a high-speed RAM memory and can also include a non-volatile memory, for example, at least two disk memories.

[0238] In the embodiments of the present application, the bus 116 is configured to connect the communication interface 115, the processor 113, and the memory 114, and enable mutual communication among these devices.

[0239] In the embodiments of the present application, the memory 114 is configured to store instructions and data.

[0240] Further, in the embodiments of the present application, the processor 113 is configured to acquire a third-party application from a third-party application platform by the set-top box; when running the third-party application, the set-top box detects voice information and sends the voice information to the service platform; the service platform generates a control instruction according to the display content of a current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set-top box; if the set-top box is successfully adapted with a license party based on the control instruction, the set-top box calls the terminal device to implement a service function corresponding to the voice information.

[0241] In practical applications, the memory 114 can be a volatile memory, such as a random-access memory (RAM), or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), or a combination of the above types of memories, and provides instructions and data to the processor 17.

[0242] The embodiment of the present application provides a control system, which comprises a service platform, a set-top box, a third-party application platform and a terminal device; the set-top box communicates with the service platform through a first interface; the set-top box communicates with the third-party application platform through a second interface; the set-top box communicates with the terminal device through a third interface; the set-top box acquires a third-party application from the third-party application platform; when the third-party application is running, the set-top box detects voice information and sends the voice information to the service platform; the service platform generates a control instruction according to display content of a current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set-top box; if the set-top box is successfully adapted with a license party based on the control instruction, the set-top box calls the terminal device to realize a service function corresponding to the voice information. That is to say, in the embodiment of the present application, the middleware unified input and output interface can be used to complete communication with the service platform and the underlying system through the middleware, so that the set-top box has unified license party capability, can expose services of an operating system to the outside, and can determine a scene by combining display content and voice information, thereby realizing dynamically expandable voice capability. The development and adaptation cycle can be shortened, the risk can be greatly reduced, and the intelligence and functional expansibility of the set-top box are improved.

[0243] The embodiment of the present application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the control method of the set-top box.

[0244] Specifically, the program instruction corresponding to the control method of the set-top box in the embodiment can be stored on a storage medium such as an optical disc, a hard disk, a U disk, and the like. When the program instruction corresponding to the control method of the set-top box in the storage medium is read by an electronic device or is executed, the following steps are included:

[0245] The set-top box acquires a third-party application from the third-party application platform;

[0246] When the third-party application is running, the set-top box detects voice information and sends the voice information to the service platform;

[0247] The service platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set-top box;

[0248] If the set-top box is successfully adapted with the license party based on the control instruction, the set-top box invokes the terminal device to realize the service function corresponding to the voice information.

[0249] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage, etc.) containing computer-usable program code.

[0250] The present application is described with reference to the implementation flowcharts and / or block diagrams of the method, equipment (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment produce a method implemented in the implementation flowcharts and / or block diagrams. Figure One The implementation flowcharts and / or block diagrams Figure One The implementation flowcharts and / or block diagrams

[0251] These computer program instructions can also be stored in a computer-readable storage medium that can guide the computer or other programmable data processing equipment to work in a specific way, so that the instructions stored in the computer-readable storage medium produce a product including instruction devices that implement the functions specified in the implementation flowcharts and / or block diagrams. Figure One The implementation flowcharts and / or block diagrams Figure One The implementation flowcharts and / or block diagrams

[0252] These computer program instructions can also be loaded into a computer or other programmable data processing equipment, so that a series of operation steps are performed on the computer or other programmable equipment to produce a computer-implemented process, so that the instructions executed on the computer or other programmable equipment provide steps for implementing the functions specified in the implementation flowcharts and / or block diagrams. Figure One The implementation flowcharts and / or block diagrams Figure One The implementation flowcharts and / or block diagrams

[0253] The above description is only the preferred embodiment of the application, not intended to limit the protection scope of the application.

Claims

1. A control method of a set-top box, characterized by, The control method of the set top box is applied to a control system, wherein the control system comprises a service platform, a set top box, a third-party application platform and a terminal device; the set top box communicates with the service platform through a first interface; the set top box communicates with the third-party application platform through a second interface; the set top box communicates with the terminal device through a third interface; the method comprises: The set top box obtains a third-party application from the third-party application platform; When the third-party application is running, the set top box detects voice information and sends the voice information to the service platform; The service platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set top box; If the set top box is successfully adapted with a license party based on the control instruction, the set top box calls the terminal device to realize a service function corresponding to the voice information; wherein the set top box comprises a middleware for unified input and output interface to complete the communication between the set top box, the service platform and the underlying system; the middleware is used to unify the license party, and the middleware protocol is not changed when a third-party license is added; the underlying system is an operating system running in the terminal device.

2. The method of claim 1, wherein, The service platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, comprising: The service platform determines a first scene corresponding to the display content and a second scene corresponding to the voice information; The service platform determines a target scene according to the first scene and the second scene, and analyzes and processes the voice information based on the target scene to obtain an analysis result; The service platform generates an initial instruction based on the analysis result, performs license party adaptation processing based on the initial instruction, and obtains the control instruction.

3. The method of claim 2, wherein, The service platform determines a target scene according to the first scene and the second scene, comprising: If the first scene and the second scene are the same, the first scene or the second scene is determined as the target scene.

4. The method of claim 2, wherein, The service platform determines a target scene according to the first scene and the second scene, comprising: If the first scene and the second scene are different, the target scene is determined according to the first scene, the second scene and a scene recognition model.

5. The method of claim 1, wherein, After the service platform generates a control instruction according to the display content of the current interface corresponding to the third-party application and the voice information, and sends the control instruction to the set top box, the method further comprises: If the set top box fails to adapt with the license party based on the control instruction, the set top box performs resource re-search processing and failure feedback processing.

6. The method of claim 1, wherein, The service platform comprises a network management platform, a voice service platform and an authentication platform.

7. The method of claim 1, wherein, The set top box is configured with at least one functional module in a player, a browser, a setting module, a network management module, a data center and an error code module; correspondingly, The first interface comprises a first player interface, a first browser interface and a terminal network management interface; The second interface comprises a second player interface, a second browser interface, and a data center interface. The third interface comprises a terminal management service interface, an error code interface, a third player interface, a setting interface, and a system attribute interface.

8. The method of claim 7, wherein, The set-top box supports at least one of a live broadcast service, an on-demand service, a review service, and a live broadcast time shift service.

9. The method of claim 5, wherein, The method further comprises: The service platform receives current hotword information. The service platform determines a target label according to a pre-stored hotword template and the current hotword information, and sends the target label to the set-top box. The set-top box performs search processing according to the target label.

10. The method of claim 1, wherein, Before the set-top box acquires the third-party application from the third-party application platform, the method further comprises: The third-party application platform performs skill addition, dialogue training, and model authorization processing on the third-party application.

11. A control system characterized by, The control system is configured to perform the method of any one of claims 1-10, and comprises an acquisition unit, a detection unit, a sending unit, a generation unit, and a calling unit. The acquisition unit is configured to acquire the third-party application from the third-party application platform. The detection unit is configured to detect voice information when the third-party application is running. The sending unit is configured to send the voice information to a service platform. The generation unit is configured to generate a control instruction according to display content of a current interface corresponding to the third-party application and the voice information. The sending unit is further configured to send the control instruction to a set-top box. The calling unit is configured to call a terminal device to implement a service function corresponding to the voice information if the set-top box is successfully adapted with a license party based on the control instruction.

12. A control system characterized by, The control system comprises a processor and a memory storing instructions executable by the processor, and when the instructions are executed by the processor, the method of any one of claims 1-10 is implemented.

13. A computer-readable storage medium having stored thereon a program for application in a control system, characterized in that The program is executed by a processor, and the method of any one of claims 1-10 is implemented.

Images