Linkage control system based on voice recognition

Abstract

The invention relates to the technical field of man-machine interaction, in particular to a linkage control system based on voice recognition, which comprises a voice acquisition module, a central controller and at least one interaction execution device, after the text is converted, a target control instruction and a target interaction execution device are determined according to a preset instruction library, the instruction is sent to a target device, and the interaction execution device drives a power assembly to execute a preset physical action after receiving the instruction. The problems that an existing interaction device is single in interaction form and cannot achieve linkage control are solved, unified linkage control over multiple devices is achieved by binding the voice instruction with diversified physical actions, the interaction form is enriched, and the entertainment experience and the system expansibility are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of human-computer interaction, and particularly relates to a linkage control system based on voice recognition. BACKGROUND

[0002] In entertainment places such as theme parks and large shopping malls, various interactive devices are often arranged to attract tourists, such as robots or decorations with cartoon shapes. These interactive devices usually have certain interaction capabilities, such as being able to carry out preset voice dialog, or triggering fixed actions or sound effects through sensors sensing the approach of tourists. For example, there is a control system for interactive electronic animation performances, which can control electronic animation actors to make corresponding actions in response to sensor messages of the audience.

[0003] However, the interactive devices in the prior art still have the following technical defects: first, the interaction form is relatively single, usually being a "one-to-one" simple response or fixed mode triggered based on touch, infrared sensing and other sensors, and cannot understand and execute complex instructions issued by users through natural language, so the directness and naturalness of the interaction need to be improved. Secondly, the various interactive devices in the scene usually work independently, lack a unified control core, and cannot realize linkage control of multiple different types and functions of electromechanical equipment in the scene to cooperatively complete a complex interactive task according to a voice instruction of a user, such as simultaneously controlling a gift throwing device, a moving device and a light and sound effect device, which leads to an insufficiently rich overall interactive experience and a weak sense of immersion. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a linkage control system based on voice recognition to overcome the problems in the prior art.

[0005] To achieve the above purpose, the present application adopts the following technical solutions:

[0006] The present application provides a linkage control system based on voice recognition, comprising:

[0007] a voice collection module, configured to collect a voice instruction of a user;

[0008] a central controller, in communication connection with the voice collection module and at least one interactive execution device;

[0009] the central controller is configured to receive the voice instruction collected by the voice collection module, convert the voice instruction into text information, determine a target control instruction and a target interactive execution device based on a preset instruction library according to the text information, and send the target control instruction to the target interactive execution device;

[0010] The interactive execution device is internally provided with a power component and is in communication connection with the central controller.

[0011] The interactive execution device is configured to receive a target control instruction from the central controller, drive the power component, and execute a preset physical action corresponding to the target control instruction.

[0012] Further, the system described above, when the central controller fails to determine the target control instruction according to the text information, controls the system to output preset voice feedback information.

[0013] Further, the system described above, the interactive execution device comprises at least one of a gift throwing device, a lottery device, a bubble generating device, a time device, a movable striking device, a manned moving device and a seesaw device.

[0014] Further, the system described above, the interactive execution device further comprises a wireless radio frequency receiving module for receiving and executing a control instruction sent by a handheld remote controller.

[0015] Further, the system described above, the central controller further comprises a management module.

[0016] The management module is configured to receive a modification instruction for the instruction library and update the instruction library according to the modification instruction.

[0017] Further, the system described above, the communication connection between the central controller and the interactive execution device adopts an MQTT protocol or an HTTP protocol.

[0018] The beneficial effects of the present application are:

[0019] 1. The application enriches the interaction form and improves the entertainment. The application deeply binds the natural language instruction of the user and the diversified physical action, and realizes the unified scheduling of one or more independent execution devices by the central controller, which greatly enriches the content and form of human-computer interaction, and significantly improves the entertainment of the device and the immersive experience of the tourists. 2. The application realizes unified intelligent control and improves the management efficiency. The application realizes the centralized and intelligent voice control of the multiple different types of interactive devices in the scene by the central controller, the tourists can interact with multiple devices through a unified entrance, and the manager can also uniformly maintain and upgrade the function of the entire interactive system. 3. The system has strong expansibility and good adaptability. The system architecture of the application has good expansibility, and the function of the system can be easily expanded by updating the instruction library of the central controller or adding new interactive execution devices, without the need to modify the core architecture, which has good maintainability and adaptability to new needs in the future. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0021] Figure 1 is a structural schematic diagram of an embodiment of a linkage control system based on speech recognition provided by the present application;

[0022] Figure 2 is a structural schematic diagram of a gift delivery device of an embodiment of a linkage control system based on speech recognition provided by the present application;

[0023] Figure 3 is a structural schematic diagram of a prize drawing device of an embodiment of a linkage control system based on speech recognition provided by the present application;

[0024] Figure 4 is a structural schematic diagram of a movable striking device of an embodiment of a linkage control system based on speech recognition provided by the present application;

[0025] Figure 5 is a structural schematic diagram of a bubble device of an embodiment of a linkage control system based on speech recognition provided by the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be described in detail. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present application.

[0027] Embodiment one

[0028] Figure 1 is a structural schematic diagram of an embodiment of a linkage control system based on speech recognition provided by the present application. Please refer to Figure 1 , the present embodiment can include:

[0029] a speech collection module 10, a central controller 20 and at least one interactive execution device 30. In an embodiment of the present application, the interactive execution device 30 can be specifically a gift delivery device 31. The whole system can be deployed in an interactive scene with a large "tree demon" cartoon model as the theme.

[0030] Specifically, the voice collection module 10 can be a high-sensitivity microphone array with far-field pickup and noise reduction capabilities. The microphone array is installed at the branch bifurcation of the "Big Tree Demon" model. This layout can ensure the all-around collection of voice commands issued by the user 1, and does not affect the overall appearance of the model. The microphone array is connected to the central controller 20 deployed in the background room through a universal serial bus interface to ensure the stability and low delay of audio data transmission. Its core function is to capture the voice signal of the user 1 in real time, and after preliminary signal amplification and filtering processing, the digitized audio stream data is sent to the central controller 20.

[0031] The central controller 20 is the core control center of the system, responsible for processing all core logic. In this embodiment, the central controller 20 is a high-performance background server. The server runs a custom-developed control software system, which can be logically divided into the following key functional units:

[0032] The voice recognition unit receives the audio stream from the voice collection module 10 and can call a cloud voice recognition service (for example, by connecting to a third-party voice recognition platform through an application programming interface) to perform real-time voice-to-text processing. This unit can accurately convert the user's voice command, such as "Tree Demon, what gift have you prepared for me today", into the corresponding text string "Tree Demon, what gift have you prepared for me today". To ensure response speed and recognition accuracy, the system can prompt the user 1 to input voice commands with a length of no more than 40 Chinese characters.

[0033] The natural language understanding and decision-making unit receives the text information output by the voice recognition unit, and its core is an intent recognition engine based on a pre-set instruction library. The instruction library can be stored in the database of the server (for example, using MySQL or PostgreSQL database), and its table structure can be designed to include instruction templates (supporting regular expression matching), intent identification, target device address, control instruction content, etc. When receiving the text information, the unit traverses the instruction library and uses a text matching algorithm (such as regular expression matching) to find the most suitable entry. Once a match is found, the user's intent is determined, and the target control instruction and the target interactive execution device 30 to be executed are generated.

[0034] The communication and management unit is responsible for maintaining communication connections with all interactive execution devices 30 in the scene, and sending specific target control instructions to the designated target interactive execution device 30 according to the results of the decision-making unit.

[0035] As the interactive execution device 30 in this embodiment, the specific physical structure of the gift delivery device 31 can be referred to Figure 2The device has the appearance of a "big tree demon" model, and its interior is supported by a solid main steel frame 310. In the crown part of the "big tree demon", 10 gift baskets 311 are hung through multiple high-strength steel wire ropes 313. Each steel wire rope 313 passes through a pulley block and is connected to an independent reel motor 312 installed inside the tree trunk. The reel motor 312 can be a stepper motor or a servo motor with an encoder to achieve precise control of the lifting position and speed of the gift basket 311. Each reel motor 312 is connected to a motor driver, and all motor drivers are uniformly controlled by an embedded controller (for example, a Raspberry Pi with a Linux operating system or a more powerful embedded industrial computer). The embedded controller serves as the local control core of the gift throwing device 31 and is built-in with a network communication module.

[0036] In this embodiment, the communication connection between the central controller 20 and the gift throwing device 31 adopts the message queue telemetry transfer protocol. This protocol is a lightweight message protocol based on the publish / subscribe mode, suitable for Internet of Things application scenarios. Among them, the central controller 20 acts as a publisher, and the embedded controller in the gift throwing device 31 acts as a subscriber. After the embedded controller is started, it is connected to the message queue telemetry transfer protocol agent server in the local area network and subscribes to a specific topic.

[0037] In one specific application scenario, when user 1 stands in front of the "big tree demon" model and issues the voice instruction "Tree demon, what gift have you prepared for me today?", the process starts. The voice collection module 10 arranged on the model captures this voice and uploads it as an audio data stream to the central controller 20. The voice recognition unit of the central controller 20 receives the audio data and converts it into text information "Tree demon, what gift have you prepared for me today?". The natural language understanding and decision-making unit receives the text and matches it in the instruction library, finding that the word "gift" in the text hits the preset pattern *(gift|gift). Accordingly, the system determines the user's intention and the target interactive execution device, and generates the corresponding target control instruction, for example, a JSON format string indicating that the device is required to perform a "lowering" action, with the target being the No. 7 gift basket. The device communication and management unit publishes the above-mentioned JSON string as a message body to the topic. The embedded controller of the gift delivery device 31 immediately receives this instruction because it subscribes to the topic. After parsing the JSON content, it learns that it needs to control the No. 7 reel motor 312. Therefore, the controller sends a pulse signal to the No. 7 reel motor 312 through the driver, controls it to rotate at a preset smooth speed, and slowly lowers the steel wire rope 313 suspending the No. 7 gift basket 311. When the gift basket 311 is lowered to a height where user 1 can easily take it, the motor stops. After user 1 takes the gift, another instruction such as "Thank you, tree demon" can be issued. The system will recognize the intention of "recycling the basket" through the same process and send an instruction to control the reel motor 312 to rotate in the opposite direction, returning the empty gift basket 311 to its original position. After the action is completed, the gift delivery device 31 can publish a message to another state topic to report the task completion status to the central controller 20, thereby forming a complete control closed loop.

[0038] In addition, as an optional implementation, the system also has abnormal handling capability. If the voice instruction of user 1 (for example, "Tree demon, can you fly?") cannot be matched to any preset intention in the instruction library after text conversion, the central controller 20 will be configured to perform a preset feedback process instead of being unresponsive. Specifically, the central controller 20 will call a text-to-speech engine to convert a preset voice feedback information (such as "This question is a bit brain-burning, looking forward to my wisdom upgrading soon!") into an audio file and play it through the speakers arranged in the scene. This helps to improve the naturalness of the interaction and the user experience, avoiding the interruption of the interaction due to the inability to recognize the instruction.

[0039] Embodiment Two

[0040] This embodiment is based on embodiment one, further demonstrating how the central controller 20 uniformly identifies, addresses and controls multiple interactive execution devices 30 of different types and functions, to embody the expansibility and linkage characteristics of the application.

[0041] Referring to Figure 1 In this embodiment, in addition to the gift delivery device 31 described in embodiment 1, the system is also connected to three other interactive execution devices 30 of different types through a local area network, including: a turtle-shaped manned mobile device 32, whose power components are electric motors and wheels, and can carry a child to slowly travel along a preset route; a lottery device 33 with a built-in elastic ball launching mechanism, which looks like a small tree hole, and whose power components are launching electromagnets or small motors, and can randomly launch an elastic ball with a number; and a seesaw device (not marked separately in the figure) that can be driven to rotate by a motor.

[0042] In this embodiment, the communication connection between the newly added interactive execution devices 30 and the central controller 20 can be based on the Hypertext Transfer Protocol. The embedded controller (such as ESP32 or higher ARM development board) inside each interactive execution device 30 runs a lightweight Web server program and provides a set of RESTful style application programming interfaces. The central controller 20 sends HTTP requests (such as POST or GET requests) to the specific IP addresses and ports of these devices to issue control instructions.

[0043] To achieve selective control of different devices, the natural language understanding and decision unit of the central controller 20 is enhanced. Its instruction library not only contains the mapping of intent and instruction, but also adds a keyword and device address mapping table.

[0044] In specific practice, user 1 issues a voice to the system: "Let the turtle take me for a circle". The voice collection module 10 and the central controller 20 of the system convert the voice into text "Let the turtle take me for a circle". The decision unit first extracts the preset keyword "turtle" from the text. According to the keyword and device address mapping table, the system determines that the target interactive execution device is the mobile device 32. Then, the system further analyzes the text and identifies that the intent of "take a circle" is "start the tour mode". Finally, the system generates a target control instruction, which is an HTTP POST request, and the request body is a JSON object. The central controller 20 sends this POST request to the mobile device 32. The embedded controller of the mobile device 32 receives the request, parses it and drives its power components, starting to travel along the preset A route for 3 minutes.

[0045] Meanwhile, due to the multi-thread or asynchronous processing architecture of the software system of the central controller 20, the system can concurrently process requests from different users. When another user 1 says "I want to draw a lottery" in front of the lottery device 33, the system performs the same operation to obtain the text "I want to draw a lottery". The system extracts the keyword "draw a lottery", thereby determining that the target interactive execution device is the lottery device 33 and identifying that the intention is "to execute a lottery". The generated target control instruction is an HTTP POST request. The central controller 20 sends the request to the lottery device 33. As shown in Figure 3

[0046] In the above manner, the system in this embodiment realizes a unified voice interaction entrance, can intelligently analyze user instructions, and distribute the instructions to interactive execution devices 30 with different functions in a scene, realizes concurrent linkage control of multiple amusement facilities in a region, thereby constructing an intelligent miniature amusement scene and improving the overall interest and management efficiency of the scene.

[0047] Embodiment Three

[0048] This embodiment further illustrates the diversity of "interactive execution devices" and the wide range of "preset physical actions" executed in the scheme of the present application. It should be noted that these actions can not only be functional actions (such as gift delivery, movement), but also atmosphere creation, timing tasks, physical feedback, etc., thereby supporting a wider range of application scenarios.

[0049] In this embodiment, in addition to the devices mentioned in embodiments one and two, the system is also integrated with the following new types of interactive execution devices 30:

[0050] Time-telling device: In the trunk of the "tree demon" model, a program-controlled cuckoo time-telling device is installed, and its power component is a micro motor driving the cuckoo model to enter and exit the small door and a sound unit.

[0051] Movable striking device: As shown in Figure 4 The main part of the device is marked as a striking device 340, and a thick soft bag target 341 is provided on the trunk for users to hit. The device is installed with multiple pulleys 342 at the bottom and placed on a short track 343 laid on the ground. Its power component is a motor driving the pulleys 342 to rotate. Behind the soft bag target 341, a pressure sensor is installed as a non-voice input signal source.

[0052] Bubble generating device: As shown in Figure 5 ​The bubble device 350 shown, in several main branches of the "Big Tree Demon", embedded in a plurality of commercial bubble machine 351, its power components for bubble machine motor and fan.

[0053] When the user 1 wishes to increase the atmosphere and say the command "come on the atmosphere", the central controller 20 receives and analyzes the command, and matches the intention of "creating atmosphere" in its command library. The intention can be configured to link multiple devices. For example, the central controller 20 can send instructions to the bubble device 350 and the light control system in the scene (which can also be regarded as an interactive execution device) at the same time. Specifically, it sends instructions to the bubble device 350, which makes the embedded bubble machine 351 start and blow bubbles for 30 seconds; at the same time, it sends instructions to the light controller to switch the light to a soft color mode.

[0054] For the time device, the action trigger does not come from the user's voice. The central controller 20 runs an accurate clock service and task scheduler inside. The scheduler is configured to automatically trigger tasks at every hour. For example, when the system time reaches 3:00:00 pm, the scheduler automatically generates a control instruction and sends it to the time device. After receiving the instruction, the time device controls the cuckoo model to pop out and chirp three times to complete the time. As can be seen, the control source of the system described in the present application can be diverse, not limited to real-time user voice.

[0055] When the user 1 walks in front of the movable striking device 340 and hits the soft bag target 341 with force, the pressure sensor installed behind the target immediately detects the impact force and sends a signal containing the pressure value (for example, through the Message Queue Telemetry Transport protocol or the Hypertext Transfer Protocol) to the central controller 20. After receiving this non-voice input signal, the central controller 20 makes a judgment according to the preset logic: if the pressure value exceeds the set threshold (for example, 500 Newton), it is considered as a valid "heavy blow". Immediately, the central controller 20 sends a moving instruction to the local controller of the striking device 340. After receiving the instruction, the power component of the striking device 340 drives the pulley 342 to quickly retreat 50 centimeters on the track 343, thereby simulating the effect of being "hit back" by the user, providing physical feedback and interactive interest.

[0056] This embodiment shows that the system architecture provided by the present application has high flexibility, and the "interactive execution device" controlled by the system can be a variety of mechatronic devices, and the "physical action" executed by the system covers multiple dimensions such as function, atmosphere, timing, feedback, etc. The system can not only respond to direct voice commands, but also combine timing tasks and other sensor inputs to achieve rich and colorful linkage control effects, so it is widely applicable.

[0057] Embodiment four

[0058] The embodiment mainly illustrates the practicability, reliability and maintainability of the scheme in actual deployment and long-term operation, which is embodied in the redundant design of the control mode and the dynamic expansion capability of the instruction library.

[0059] Firstly, in order to improve the system reliability and prevent the interactive function from being completely paralyzed due to network failure or temporary downtime of the central controller 20, part of the key interactive execution devices 30 in the embodiment are designed to support dual-mode control. Taking the gift throwing device 31 in embodiment one as an example, in addition to receiving network instructions from the central controller 20 through Ethernet, the motor driver of the embedded controller inside it is also connected in parallel with an independent wireless radio frequency receiving module. Correspondingly, the system is equipped with a handheld remote controller, which is provided with physical buttons such as "up", "down", "stop", etc., each of which corresponds to a unique radio frequency code. Under normal circumstances, the system is fully automatically controlled by voice from the central controller 20. However, when network failure occurs, or on-site staff need to perform device debugging, gift replenishment, emergency intervention and other operations, the handheld remote controller can be used. When the staff presses the "down" button, the remote controller transmits the corresponding radio frequency signal. The wireless radio frequency receiving module on the gift throwing device 31 receives and decodes the signal and directly sends a control signal to the driver of the reel motor 312, thereby bypassing the embedded controller and the network communication link, and directly driving the motor to perform the down action. This local manual control through the handheld remote controller, as an effective supplement and backup of voice intelligent control, ensures the usability and operation continuity of the device under various conditions.

[0060] Secondly, in order to ensure the scalability and long-term usability of the system, the central controller 20 of the present application is designed to support convenient function expansion, the core of which is the dynamic updating capability of the instruction library. The software system of the central controller 20 contains a special management module, which provides a Web-based background management interface that authorized operators can access through a browser. The management module has the following functions:

[0061] Unknown instruction recording and analysis: the system automatically records all voice texts that fail to successfully match the instruction library and displays them in list form in the background interface, while counting the frequency of occurrence of each unknown instruction.

[0062] Online editing of the instruction library: the operator can browse, modify, delete existing instruction rules, and easily add new instructions.

[0063] After the system runs for a period of time, when the system records that the frequency of occurrence of a certain unknown instruction (for example, "Tree spirit, sing a song") reaches a preset threshold, the updating process can be triggered. The operator receives the modification instruction for the instruction library through the management module, and the specific operation is as follows: clicking the "add instruction" button to enter the editing page. In the "instruction text mode" input box, a regular expression capable of covering multiple questions is input. In the "target action" configuration area, one or a series of linkage actions can be defined. For example, a two-step action sequence can be configured: first, selecting the target device as "scene sound system", selecting the action as "play audio", and uploading a pre-recorded music file; second, selecting the target device as "scene light controller", selecting the action as "start flashing mode", and setting the duration (such as 180 seconds) matching the length of the song. After saving the newly added "instruction text-physical action" binding relationship, the management module receives the updating information containing the newly added instruction text and the corresponding physical action binding relationship, and inserts it as a new record into the instruction database in the back end. Thereafter, when user 1 says "sing a song for me" to the system again, the new rule can be successfully matched, and the corresponding control instructions are sent to the sound system and the light controller in sequence to realize the linkage performance of playing music and light flashing. It can be understood that the method of the system also includes receiving updating information for updating the instruction library, and updating the instruction library according to the updating information. This design enables the interactive ability of the system to evolve and enrich continuously, and the system can adapt to new interactive requirements without modifying the underlying code, thereby improving the life cycle and maintainability of the system.

[0064] It can be understood that the same or similar parts in the above embodiments can be mutually referred to, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0065] It should be noted that, in the description of the present application, the terms "first", "second", etc. are only for the purpose of description, and cannot be understood as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise specified, the meaning of "a plurality of" is at least two.

[0066] Any process or method descriptions in flow charts or otherwise described herein represent embodiments that can be implemented as code (e.g., instructions for execution by a processor) that can be executed by a computer, and that includes one or more steps that can be performed under the control of one or more computer systems configured with the code. The computer systems can be configured to perform specific functions (e.g., a computer system with a device that is a scene sound system configured to play audio) based on the code. The embodiments of the present application are not limited to the details of the above-described methods.

[0067] It should be understood that each part of the present application can be realized by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be realized by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if realized by hardware, and as in another embodiment, it can be realized by any one or a combination of the following technologies known in the art: discrete logic circuit with logic gate circuit for implementing logic function on data signal, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA) and the like.

[0068] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment method can be completed by a program instructing the relevant hardware, and the program can be stored in a computer readable storage medium, and when executed, includes one or a combination of steps of the embodiment method.

[0069] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of software functional module. The integrated module, if realized in the form of software functional module and sold or used as an independent product, can also be stored in a computer readable storage medium.

[0070] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc.

[0071] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above-mentioned terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0072] Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A linkage control system based on speech recognition, characterized in that: include: Voice collection module, used to collect user's voice commands; a central controller, the central controller being communicatively connected to the voice acquisition module and at least one interactive execution device; The central controller is used to receive the voice instructions collected by the voice collection module, convert the voice instructions into text information, determine the target control instructions and the target interactive execution device according to the text information based on a preset instruction library, and send the target control instructions to the target interactive execution device; The interactive execution device has a built-in power component and is in communication with the central controller; The interactive execution device is used to receive the target control instruction from the central controller, drive the power component, and execute the preset physical action corresponding to the target control instruction.

2. The system according to claim 1, wherein: When the central controller fails to determine the target control instruction according to the text information, it controls the system to output preset voice feedback information.

3. The system according to claim 2, characterized in that The interactive execution device includes at least one of a gift delivery device, a lottery device, a bubble generation device, a time reporting device, a movable striking device, a manned moving device and a seesaw device.

4. The system according to claim 1, wherein: The interactive execution device also includes a wireless radio frequency receiving module for receiving and executing control instructions sent by a handheld remote controller.

5. The system according to claim 1, wherein: The central controller further includes: a management module; The management module is used to receive a modification instruction for the instruction library and update the instruction library according to the modification instruction.

6. The system according to claim 1, wherein: The communication connection between the central controller and the interactive execution device adopts the MQTT protocol or the HTTP protocol.

Images