Intelligent control method and system for building block toy

Abstract

The application discloses an intelligent control method and control system of a building block toy, and relates to the technical field of building block toys, which comprises the following steps: placing an AI voice module in the building block toy and obtaining sensing parameters of a voice sensor, placing the voice sensor based on the sensing parameters; obtaining external control data and executable instructions, obtaining standard execution actions based on the executable instructions, and controlling the building block; the application is used for solving the problem that in the existing intelligent control method of the building block toy, the installation position of the sensor is not effectively optimized when the building block toy interacts with the outside world, so that the building block toy cannot fully receive sound sources of different angles due to its own sensor, the building block toy cannot accurately perform correct interaction actions, and the user's interaction experience is affected.

Description

Technical Field

[0001] This invention relates to the field of building block toy technology, specifically to an intelligent control method and control system for building block toys. Background Technology

[0002] Building blocks are cubic wooden or plastic solid toys, typically decorated with letters or pictures on each surface, allowing for different arrangements or building activities. Intelligent control of building blocks refers to the ability of them to receive instructions, perform actions, and interact with other devices through built-in smart chips or sensors. This technology enables building blocks not only to operate according to preset programs but also to be controlled by external devices, achieving a richer and more interactive experience.

[0003] Existing methods for intelligent control of building block toys typically focus on improving the interface of the toys. For example, optimizing the connection between the main controller and actuators can improve the reliability of the toys during use. While this approach optimizes the operation of the building block toys themselves, it lacks effective optimization regarding the sensor placement when the toys interact with the outside world. This can lead to the toys' sensors failing to fully receive sound sources from different angles, resulting in inaccurate execution of interactive actions and negatively impacting the user experience. For instance, patent application CN115693308A discloses a type of granular intelligent building block toy. The control system, as described above, uses modular Type-C plugs and sockets to connect the main controller and actuators, effectively ensuring the reliability of the control system. Other improvements in intelligent control for building block toys, typically focusing on the linkage control of the system, still suffer from a lack of effective optimization in the sensor placement when the building block toys interact with the outside world. This results in the building block toys' sensors failing to fully receive sound sources from different angles, leading to inaccurate execution of interactive actions and impacting the user experience. Therefore, it is necessary to improve existing intelligent control methods for building block toys. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art by proposing an intelligent control method and control system for building block toys. This solution addresses the lack of effective optimization in the installation position of sensors when building block toys interact with the outside world, which leads to the building block toys being unable to fully receive sound sources from different angles due to their own sensors. Consequently, the building block toys cannot accurately execute the correct interactive actions, resulting in a negative impact on the user's interactive experience.

[0005] To achieve the above objectives, in a first aspect, this application provides an intelligent control method for building block toys, comprising the following steps:

[0006] An AI voice module is placed in a building block toy and the sensing parameters of multiple voice sensors are obtained. Voice sensors are placed in the building block toy based on the sensing parameters. External control data is obtained based on the received data from multiple voice sensors and the external control data is transmitted to the AI ​​voice module.

[0007] The system retrieves preset action instructions from the building block toys and records them as executable instructions. Based on the executable instructions, it analyzes the data received by the AI ​​voice module and filters the preset execution actions from the building block toys based on the analysis results to obtain standard execution actions.

[0008] Control the blocks based on standard execution actions.

[0009] Furthermore, placing an AI voice module in the building block toy and acquiring sensing parameters from multiple voice sensors includes:

[0010] Obtain the size data of the building block toy, and based on the size data, obtain a 3D model of the building block toy, denoted as the 3D model of the building block; establish a spatial coordinate system, denoted as the speech test coordinate system, where the units of the X-axis, Y-axis, and Z-axis of the speech test coordinate system are all cm; place the 3D model of the building block within the speech test coordinate system, and align the plane of the front view of the obtained 3D model of the building block with the XZ plane, the plane of the left view of the obtained 3D model of the building block with the YZ plane, and the plane of the top view of the obtained 3D model of the building block with the XY plane;

[0011] Obtain the smallest rectangles that enclose the front view, left view, and top view of the 3D block model, and denote them as rectangle 1, rectangle 2, and rectangle 3, respectively; denote the rectangular body formed by rectangle 1, rectangle 2, and rectangle 3 that encloses the 3D block model as the parametric analysis rectangular body.

[0012] Furthermore, placing an AI voice module in building block toys and acquiring sensing parameters from multiple voice sensors also includes:

[0013] For any face α of the parametric analysis rectangular body: draw a perpendicular line from the center of face α to face α, and denote it as the face perpendicular line; denote the ray that does not coincide with the three-dimensional model of the block among the two rays with the center of face α as the endpoint within the face perpendicular line as the speech test ray; obtain the maximum receiving distance of the speech sensor for speech and the minimum decibel of audio that can be received at the maximum receiving distance, and denote them as L and B respectively.

[0014] The line segment in the speech test ray from the endpoint to a point L away from the endpoint is denoted as the speech test line segment.

[0015] Furthermore, placing an AI voice module in building block toys and acquiring sensing parameters from multiple voice sensors also includes:

[0016] For any point β in the speech test line segment: place the building block toy in the environment used for audio testing, and based on the positional relationship between point β and the building block toy, obtain the real-world position of point β, and denote it as point β. 1 At point β 1 A light source is placed facing the end of the speech test ray, and the area on the surface of the building block toy illuminated by the light source is marked as the speech test area;

[0017] At point β 1 An audio playback device is placed at the location specified in the text, and its orientation is adjusted to align with the endpoint of the voice test ray. The audio playback device plays a voice audio signal at a decibel level of B. Voice sensors are placed at all suitable locations within the voice test area. The data received by the voice sensors are sequentially recorded as one-way received data DX1 to one-way received data DX2. c , where c is the number of locations where a voice sensor can be placed within the voice test area;

[0018] For any one-way received data DX, compare the audio similarity between the one-way received data DX and the audio played by the audio playback device, and record the comparison result as the one-way reception ratio; obtain the one-way reception ratio of all one-way received data DX.

[0019] The audio reception parameters of point β are obtained using the ratio fluctuation algorithm. The ratio fluctuation algorithm is as follows: Where F represents the audio reception parameters, and DB... i DB represents the one-way reception ratio of the i-th one-way received data in all one-way received data DX. sq This is the average of all one-way reception ratios.

[0020] Furthermore, placing an AI voice module in building block toys and acquiring sensing parameters from multiple voice sensors also includes:

[0021] Obtain the audio receiving parameters corresponding to all points in the voice test line segment, and record the point corresponding to the minimum audio receiving parameter as the optimal face point of face α.

[0022] Based on the analysis method of face α, all faces of the parametric analysis rectangular body are analyzed, and the best face point of each face is obtained. For any face α of the parametric analysis rectangular body, the planes in the parametric analysis rectangular body that are not parallel to face α are denoted as associative planes. The best face point of face α is connected to the best face points of all associative planes respectively, and the resulting line segments are denoted as associative line segments.

[0023] For any associative line segment, when the associative line segment intersects with the 3D block model, the intersection point in the speech test area corresponding to surface α is recorded as a usable intersection point, and all usable intersection points corresponding to associative line segments are obtained.

[0024] Furthermore, placing an AI voice module in building block toys and acquiring sensing parameters from multiple voice sensors also includes:

[0025] When none of the associable line segments intersect with the 3D block model or intersect with the speech test area corresponding to face α, the point in the speech test area corresponding to face α that is closest to each associable line segment is recorded as the available intersection point.

[0026] Obtain all available intersection points corresponding to all faces of the parameter analysis matrix, and record the positions of all available intersection points in the parameter analysis matrix as the sensing parameters of the voice sensor.

[0027] Furthermore, voice sensors are placed in the building block toy based on sensing parameters; external control data is acquired based on the received data from multiple voice sensors, and the external control data is transmitted to the AI ​​voice module, including:

[0028] A voice sensor is placed in the building block toy based on all sensing parameters, and an AI voice module is placed inside the building block toy. The AI ​​voice module is used to receive the received audio and recognize the received audio based on the AI ​​built into the AI ​​voice module. The AI ​​voice module is connected to the execution unit of the building block toy.

[0029] Connect the voice sensor and the AI ​​voice module using a data cable; when any voice sensor receives audio and the audio decibel is greater than B, record the audio data received by the voice sensor as external control data, and transmit the external control data to the AI ​​voice module via the data cable.

[0030] Furthermore, the data received by the AI ​​voice module is analyzed based on executable instructions, and the preset execution actions in the building block toy are filtered based on the analysis results to obtain standard execution actions, including:

[0031] The system acquires preset action instructions from the building block toys and records them as executable instructions. When the AI ​​voice module receives external control data, it uses AI recognition to acquire data in the external control data that is the same as the executable instructions. When there is data in the external control data that is the same as the executable instructions, the execution action corresponding to the executable instruction that appears most frequently in the external control data is recorded as the standard execution action.

[0032] If no data identical to the executable instruction exists in the external control data, the standard execution action will not be acquired.

[0033] Furthermore, controlling the blocks based on standard execution actions includes:

[0034] When the AI ​​recognition module obtains the standard execution action, it transmits the standard execution action to the execution unit of the building block toy, and the execution unit of the building block toy executes the standard execution action.

[0035] Secondly, this application also provides an intelligent control system for building block toys, including a sensing voice receiving module, a voice command analysis module, and an action execution module;

[0036] The sensing voice receiving module is used to place an AI voice module in the building block toy and acquire the sensing parameters of multiple voice sensors. Based on the sensing parameters, voice sensors are placed in the building block toy. External control data is acquired based on the received data from multiple voice sensors and the external control data is transmitted to the AI ​​voice module.

[0037] The voice command analysis module is used to obtain the preset action commands in the building block toys, which are recorded as executable commands. Based on the executable commands, the data received by the AI ​​voice module is analyzed, and based on the analysis results, the preset execution actions in the building block toys are filtered to obtain standard execution actions.

[0038] The action execution module is used to control the blocks based on standard actions.

[0039] The beneficial effects of this invention are as follows: This application first places an AI voice module in a building block toy and obtains the sensing parameters of multiple voice sensors. Based on the sensing parameters, voice sensors are placed in the building block toy. External control data is obtained based on the received data from multiple voice sensors, and the external control data is transmitted to the AI ​​voice module. The advantage of this is that by obtaining the sensing parameters of multiple voice sensors based on the building block toy, the placement position of the voice sensors that conforms to the actual application of the building block toy can be obtained based on the building block toy's own structure and its reception of external sounds. This helps the AI ​​voice module to receive sound sources from different angles outside the building block toy after the voice sensors are placed, thereby enabling the building block toy to make correct interactive actions and improve the user's interactive experience.

[0040] This application also obtains preset action instructions from the building block toy, denoted as executable instructions. Based on the executable instructions, the data received by the AI ​​voice module is analyzed, and based on the analysis results, the preset execution actions in the building block toy are filtered to obtain standard execution actions. Finally, the building blocks are controlled based on the standard execution actions. The advantage of this is that by obtaining executable instructions and obtaining standard execution actions through the AI ​​voice module, action instructions conveyed in the external environment can be obtained with the assistance of multiple voice sensors. The AI ​​voice module can accurately parse the action instructions and control the building block toy to execute standard execution actions, so that the building block toy can fully receive sound sources from different angles and accurately execute the correct interactive actions, thereby improving the user's interactive experience. Attached Figure Description

[0041] Figure 1 This is a schematic diagram of the system of the present invention;

[0042] Figure 2 This is a flowchart of the steps of the method of the present invention;

[0043] Figure 3 This is a schematic diagram of the minimum rectangle obtained based on the three-dimensional model of building blocks according to the present invention;

[0044] Figure 4 This is a schematic diagram illustrating the acquisition of usable intersection points according to the present invention;

[0045] Figure 5 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] Example 1, please refer to Figure 1 As shown, this application provides an intelligent control system for building block toys, including a sensing voice receiving module, a voice command analysis module, and an action execution module;

[0048] The sensing voice receiving module is used to place an AI voice module in the building block toy and acquire the sensing parameters of multiple voice sensors. Based on the sensing parameters, voice sensors are placed in the building block toy. External control data is acquired based on the received data from multiple voice sensors and the external control data is transmitted to the AI ​​voice module.

[0049] The sensor voice receiving module includes a sensing parameter acquisition unit and a voice receiving unit; the sensing parameter acquisition unit is configured with a sensing parameter acquisition strategy, which includes:

[0050] Obtain the size data of the building block toy, and based on the size data, obtain a 3D model of the building block toy, denoted as the 3D model of the building block; establish a spatial coordinate system, denoted as the speech test coordinate system, where the units of the X-axis, Y-axis, and Z-axis of the speech test coordinate system are all cm; place the 3D model of the building block within the speech test coordinate system, and align the plane of the front view of the obtained 3D model of the building block with the XZ plane, the plane of the left view of the obtained 3D model of the building block with the YZ plane, and the plane of the top view of the obtained 3D model of the building block with the XY plane;

[0051] Obtain the smallest rectangles that enclose the front view, left view, and top view of the 3D block model, and denote them as rectangle 1, rectangle 2, and rectangle 3, respectively; denote the rectangular body formed by rectangle 1, rectangle 2, and rectangle 3 that encloses the 3D block model as the parametric analysis rectangular body;

[0052] In specific implementation processes, for example, during a data processing operation, the smallest rectangle obtained based on the block 3D model is as follows: Figure 3 As shown, the rectangular body LL1 is a parameter analysis rectangular body composed of rectangle 1, rectangle 2 and rectangle 3. For the surface α composed of points ZZ1, ZZ2, ZZ3 and ZZ4, it can be found through analysis that ray YS is the voice test ray. By obtaining the voice test ray, the sound reception of the block toy surface facing surface α can be analyzed. This helps to obtain the position where the voice sensor can be placed in the block toy in subsequent analysis, so as to fully obtain the sound sources from different angles outside the block toy, thereby improving the accuracy of the block toy in performing interactive actions.

[0053] For any face α of the parametric analysis rectangular body: draw a perpendicular line from the center of face α to face α, and denote it as the face perpendicular line; denote the ray that does not coincide with the three-dimensional model of the block among the two rays with the center of face α as the endpoint within the face perpendicular line as the speech test ray; obtain the maximum receiving distance of the speech sensor for speech and the minimum decibel of audio that can be received at the maximum receiving distance, and denote them as L and B respectively.

[0054] In the specific implementation process, for example, during a data processing, if the maximum receiving distance of the voice sensor for voice is 3m and the minimum decibel of audio that can be received at 3m is 50 decibels, then L and B can be set to 3m and 50 decibels respectively. By obtaining L and B, the range of sound reception analysis on the surface of the building block toy in the voice test ray can be limited to ensure that the data obtained from the analysis are all valid data.

[0055] The line segment in the speech test ray from the endpoint to a point L away from the endpoint is denoted as the speech test line segment;

[0056] For any point β in the speech test line segment: place the building block toy in the environment used for audio testing, and based on the positional relationship between point β and the building block toy, obtain the real-world position of point β, and denote it as point β. 1 At point β 1 A light source is placed facing the end of the speech test ray, and the area on the surface of the building block toy illuminated by the light source is marked as the speech test area;

[0057] At point β 1 An audio playback device is placed at the location specified in the text, and its orientation is adjusted to align with the endpoint of the voice test ray. The audio playback device plays a voice audio signal at a decibel level of B. Voice sensors are placed at all suitable locations within the voice test area. The data received by the voice sensors are sequentially recorded as one-way received data DX1 to one-way received data DX2. c , where c is the number of locations where a voice sensor can be placed within the voice test area;

[0058] For any one-way received data DX, compare the audio similarity between the one-way received data DX and the audio played by the audio playback device, and record the comparison result as the one-way reception ratio; obtain the one-way reception ratio of all one-way received data DX.

[0059] In the specific implementation process, the available audio similarity comparison methods can be selected to obtain the one-way reception ratio, such as AudioCompare, AudioDedupe, or Similarity.

[0060] The audio reception parameters of point β are obtained using the ratio fluctuation algorithm. The ratio fluctuation algorithm is as follows: Where F represents the audio reception parameters, and DB... i DB represents the one-way reception ratio of the i-th one-way received data in all one-way received data DX. sq This is the average of all one-way reception ratios;

[0061] In a specific implementation process, for example, during a single data processing session, if the one-way reception ratios of all the one-way received data DX are 80%, 70%, 65%, 50%, and 60%, then the audio reception parameter can be calculated to be approximately 0.015. In actual analysis, the smaller the audio reception parameter, the higher and more accurate the one-way received data DX at that point is in terms of audio reception efficiency. Therefore, in subsequent analysis, the point corresponding to the smallest audio reception parameter can be selected for analysis.

[0062] Obtain the audio receiving parameters corresponding to all points in the voice test line segment, and record the point corresponding to the minimum audio receiving parameter as the optimal face point of face α.

[0063] Based on the analysis method of face α, all faces of the parametric analysis rectangular body are analyzed, and the best face point of each face is obtained. For any face α of the parametric analysis rectangular body, the planes in the parametric analysis rectangular body that are not parallel to face α are denoted as associative planes. The best face point of face α is connected to the best face points of all associative planes respectively, and the resulting line segments are denoted as associative line segments.

[0064] For any associable line segment, when the associable line segment intersects with the 3D block model, the intersection point in the speech test area corresponding to surface α is recorded as the available intersection point, and all available intersection points corresponding to associable line segments are obtained.

[0065] In the specific implementation process, for example, during a data processing session, the optimal pastry ZL is obtained as follows: Figure 4 As shown, point ZL is the optimal face point, and lines KX1 to KX4 are connectable line segments. Through analysis, it can be seen that points KJ1 to KJ3 are usable intersection points. This means that KJ1 to KJ3 can receive sound sources facing face α while also effectively receiving sound sources in other directions besides face α. Thus, after installing the voice sensor, the building block toy can fully extract sounds from different directions.

[0066] When none of the associable line segments intersect with the 3D block model or intersect with the speech test area corresponding to face α, the point in the speech test area corresponding to face α that is closest to each associable line segment is recorded as the available intersection point.

[0067] Obtain all available intersection points corresponding to all faces of the parameter analysis matrix, and record the positions of all available intersection points in the parameter analysis matrix as the sensing parameters of the voice sensor.

[0068] The voice receiving unit is configured with a voice receiving strategy, which includes: placing a voice sensor in the building block toy based on all sensing parameters, and placing an AI voice module inside the building block toy. The AI ​​voice module is used to receive the received audio and recognize the received audio based on the AI ​​built into the AI ​​voice module. The AI ​​voice module is connected to the execution unit of the building block toy.

[0069] Connect the voice sensor and the AI ​​voice module using a data cable; when any voice sensor receives audio and the audio decibel is greater than B, record the audio data received by the voice sensor as external control data, and transmit the external control data to the AI ​​voice module via the data cable.

[0070] The voice command analysis module is used to obtain the preset action commands in the building block toys, which are recorded as executable commands. Based on the executable commands, the data received by the AI ​​voice module is analyzed, and based on the analysis results, the preset execution actions in the building block toys are filtered to obtain standard execution actions.

[0071] The voice command analysis module includes a voice command analysis unit, which is configured with a voice command analysis strategy. The voice command analysis strategy includes: acquiring preset action commands from the building block toy and recording them as executable commands; when the AI ​​voice module receives external control data, acquiring data in the external control data that is the same as the executable command based on AI recognition; when there is data in the external control data that is the same as the executable command, recording the execution action corresponding to the executable command that appears most frequently in the external control data as the standard execution action.

[0072] If no data identical to the executable instruction exists in the external control data, the standard execution action will not be acquired.

[0073] The action execution module is used to control the building blocks based on standard execution actions. When the standard execution action is obtained by the AI ​​recognition module, the standard execution action is transmitted by the AI ​​recognition module to the execution unit of the building block toy, and the standard execution action is executed based on the execution unit of the building block toy.

[0074] Example 2, please refer to Figure 2 As shown, this application also provides an intelligent control method for building block toys, including the following steps:

[0075] Step S1: Place an AI voice module in the building block toy and obtain the sensing parameters of multiple voice sensors; place voice sensors in the building block toy based on the sensing parameters; obtain external control data based on the received data from multiple voice sensors and transmit the external control data to the AI ​​voice module.

[0076] Step S1 includes: Step S101, obtaining the size data of the building block toy, and obtaining a three-dimensional model of the building block toy based on the size data of the building block toy, denoted as the three-dimensional model of the building block; establishing a spatial coordinate system, denoted as the voice test coordinate system, wherein the units of the X-axis, Y-axis and Z-axis of the voice test coordinate system are all cm; placing the three-dimensional model of the building block in the voice test coordinate system, and aligning the plane of the front view of the obtained three-dimensional model of the building block with the XZ plane, aligning the plane of the left view of the obtained three-dimensional model of the building block with the YZ plane, and aligning the plane of the top view of the obtained three-dimensional model of the building block with the XY plane;

[0077] Step S102: Obtain the smallest rectangles that enclose the front view, left view, and top view of the 3D block model, and denote them as rectangle 1, rectangle 2, and rectangle 3, respectively; denote the rectangular body formed by rectangle 1, rectangle 2, and rectangle 3 that encloses the 3D block model as the parametric analysis rectangular body.

[0078] Step S103: For any face α of the parameter analysis rectangle: draw a perpendicular line from the center of face α to face α, and denote it as the face perpendicular line; denote the ray that does not coincide with the three-dimensional model of the block among the two rays with the center of face α as the endpoint within the face perpendicular line as the speech test ray; obtain the maximum receiving distance of the speech sensor for speech and the minimum decibel of audio that can be received at the maximum receiving distance, and denote them as L and B respectively;

[0079] Step S104: The line segment in the speech test ray from the endpoint to the point with a distance L from the endpoint is recorded as the speech test line segment;

[0080] Step S105, for any point β in the voice test line segment: place the building block toy in the environment used for audio testing, and based on the positional relationship between point β and the building block toy, obtain the real-world position of point β, and record it as point β. 1 At point β 1 A light source is placed facing the end of the speech test ray, and the area on the surface of the building block toy illuminated by the light source is marked as the speech test area;

[0081] Step S106, at point β 1 An audio playback device is placed at the location specified in the text, and its orientation is adjusted to align with the endpoint of the voice test ray. The audio playback device plays a voice audio signal at a decibel level of B. Voice sensors are placed at all suitable locations within the voice test area. The data received by the voice sensors are sequentially recorded as one-way received data DX1 to one-way received data DX2. c , where c is the number of locations where a voice sensor can be placed within the voice test area;

[0082] Step S107: For any one-way received data DX, compare the audio similarity between the one-way received data DX and the audio played by the audio playback device, and record the comparison result as the one-way reception ratio; obtain the one-way reception ratio of all one-way received data DX.

[0083] Step S108: Obtain the audio reception parameters of point β using the ratio fluctuation algorithm. The ratio fluctuation algorithm is as follows: Where F represents the audio reception parameters, and DB... i DB represents the one-way reception ratio of the i-th one-way received data in all one-way received data DX. sq This is the average of all one-way reception ratios;

[0084] Step S109: Obtain the audio receiving parameters corresponding to all points in the voice test line segment, and record the point corresponding to the smallest audio receiving parameter as the best surface point of surface α.

[0085] Step S110: Analyze all faces of the parametric analysis rectangular body based on the analysis method for face α, and obtain the best face point for each face; For any face α of the parametric analysis rectangular body, denote the planes in the parametric analysis rectangular body that are not parallel to face α as associatable planes, connect the best face point of face α to the best face points of all associatable planes respectively, and denote the resulting line segments as associatable line segments;

[0086] Step S111: For any associative line segment, when there is an intersection between the associative line segment and the 3D block model, the intersection point in the speech test area corresponding to surface α is recorded as a usable intersection point, and all usable intersection points corresponding to associative line segments are obtained.

[0087] Step S112: When none of the associatable line segments intersect with the 3D block model or intersect with the speech test area corresponding to face α, the point in the speech test area corresponding to face α that is closest to each associatable line segment is recorded as the available intersection point.

[0088] Step S113: Obtain all available intersection points corresponding to all faces of the parameter analysis matrix, and record the positions of all available intersection points in the parameter analysis matrix as the sensing parameters of the voice sensor;

[0089] Step S114: Based on all sensing parameters, a voice sensor is placed in the building block toy, and an AI voice module is placed inside the building block toy. The AI ​​voice module is used to receive the received audio and recognize the received audio based on the AI ​​built into the AI ​​voice module. The AI ​​voice module is connected to the execution unit of the building block toy.

[0090] Step S115: Connect the voice sensor and the AI ​​voice module using a data cable; when any voice sensor receives audio and the audio decibel is greater than B, record the audio data received by the voice sensor as external control data, and transmit the external control data to the AI ​​voice module via the data cable.

[0091] Step S2: Obtain the preset action instructions in the building block toy, and record them as executable instructions. Analyze the data received by the AI ​​voice module based on the executable instructions, and filter the preset execution actions in the building block toy based on the analysis results to obtain standard execution actions.

[0092] Step S2 includes: Step S201, obtaining the preset action instructions in the building block toy and recording them as executable instructions; when the AI ​​voice module receives external control data, it obtains the data in the external control data that is the same as the executable instructions based on AI recognition; when there is data in the external control data that is the same as the executable instructions, the execution action corresponding to the executable instruction that appears most frequently in the external control data is recorded as the standard execution action.

[0093] Step S202: When there is no data in the external control data that is the same as the executable instruction, the standard execution action is not acquired.

[0094] Step S3: Control the blocks based on standard execution actions; Step S3 includes:

[0095] When the AI ​​recognition module obtains the standard execution action, it transmits the standard execution action to the execution unit of the building block toy, and the execution unit of the building block toy executes the standard execution action.

[0096] Example 3, please refer to Figure 5 As shown, Figure 5 A schematic diagram of an electronic device is provided, which may include a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call these instructions. When the processor executes a computer-readable instruction, it performs steps similar to those in an intelligent control method for a building block toy to achieve the following functions: First, an AI voice module is placed in the building block toy, and sensing parameters from multiple voice sensors are acquired. Based on these parameters, voice sensors are placed in the building block toy. External control data is acquired based on the received data from the multiple voice sensors and transmitted to the AI ​​voice module. Then, preset action instructions from the building block toy are acquired, designated as executable instructions. The data received by the AI ​​voice module is analyzed based on these executable instructions, and the preset execution actions in the building block toy are filtered based on the analysis results to obtain standard execution actions. Finally, the building blocks are controlled based on the standard execution actions.

[0097] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the intelligent control method for building block toys described above to achieve the following functions: First, an AI voice module is placed in the building block toy and the sensing parameters of multiple voice sensors are acquired. Based on the sensing parameters, voice sensors are placed in the building block toy. External control data is acquired based on the received data from the multiple voice sensors and transmitted to the AI ​​voice module. Then, preset action instructions in the building block toy are acquired and recorded as executable instructions. Based on the executable instructions, the data received by the AI ​​voice module is analyzed, and based on the analysis results, preset execution actions in the building block toy are filtered to obtain standard execution actions. Finally, the building blocks are controlled based on the standard execution actions.

[0099] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the technical solutions described above, or the parts that contribute to the prior art, can be embodied in the form of software products. These computer software products can be stored in computer-readable storage media, such as ROM / RAM, magnetic disks, optical disks, etc., and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0100] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An intelligent control method for a building block toy, characterized in that, Includes the following steps: An AI voice module is placed in a building block toy and the sensing parameters of multiple voice sensors are obtained. Voice sensors are placed in the building block toy based on the sensing parameters. External control data is obtained based on the received data from multiple voice sensors and the external control data is transmitted to the AI ​​voice module. The system retrieves preset action instructions from the building block toys and records them as executable instructions. Based on the executable instructions, it analyzes the data received by the AI ​​voice module and filters the preset execution actions from the building block toys based on the analysis results to obtain standard execution actions. Control the blocks based on standard execution actions; The process of placing an AI voice module in a building block toy and acquiring sensing parameters from multiple voice sensors includes: acquiring the size data of the building block toy and acquiring a 3D model of the building block toy based on the size data, denoted as the 3D model of the building block; establishing a spatial coordinate system, denoted as the voice test coordinate system, where the units of the X-axis, Y-axis, and Z-axis of the voice test coordinate system are all cm; placing the 3D model of the building block within the voice test coordinate system, and aligning the plane of the front view of the 3D model of the building block with the XZ plane, aligning the plane of the left view of the 3D model of the building block with the YZ plane, and aligning the plane of the top view of the 3D model of the building block with the XY plane; Obtain the smallest rectangles that enclose the front view, left view, and top view of the 3D block model, and denote them as rectangle 1, rectangle 2, and rectangle 3, respectively; denote the rectangular body formed by rectangle 1, rectangle 2, and rectangle 3 that encloses the 3D block model as the parametric analysis rectangular body; For any face α of the parametric analysis rectangular body: draw a perpendicular line from the center of face α to face α, denoted as the face perpendicular line; denote the ray that does not coincide with the 3D model of the block among the two rays with the center of face α as the endpoint within the face perpendicular line as the speech test ray; obtain the maximum receiving distance of the speech sensor for speech and the minimum decibel of audio that can be received at the maximum receiving distance, and denote them as L and B respectively; denote the line segment between the endpoint and the point with a length L from the endpoint in the speech test ray as the speech test line segment; For any point β in the speech test line segment: place the building block toy in the environment used for audio testing, and based on the positional relationship between point β and the building block toy, obtain the real-world position of point β, and denote it as point β. 1 At point β 1 A light source is placed facing the end of the speech test ray, and the area on the surface of the building block toy illuminated by the light source is marked as the speech test area; At point β 1 An audio playback device is placed at the location specified in the text, and its orientation is adjusted to align with the endpoint of the voice test ray. The audio playback device plays a voice audio signal at a decibel level of B. Voice sensors are placed at all suitable locations within the voice test area. The data received by the voice sensors are sequentially recorded as one-way received data DX1 to one-way received data DX2. c , where c is the number of locations where a voice sensor can be placed within the voice test area; For any one-way received data DX, compare the audio similarity between the one-way received data DX and the audio played by the audio playback device, and record the comparison result as the one-way reception ratio; obtain the one-way reception ratio of all one-way received data DX; use the ratio fluctuation algorithm to obtain the audio reception parameters of point β. The ratio fluctuation algorithm is as follows: Where F represents the audio reception parameters, and DB... i DB represents the one-way reception ratio of the i-th one-way received data in all one-way received data DX. sq This is the average of all one-way reception ratios; Obtain the audio receiving parameters corresponding to all points in the speech test line segment, and record the point corresponding to the minimum audio receiving parameter as the optimal face point of face α; analyze all faces of the parameter analysis rectangle based on the analysis method of face α, and obtain the optimal face point of each face; for any face α of the parameter analysis rectangle, record the planes in the parameter analysis rectangle that are not parallel to face α as associable planes, connect the optimal face point of face α with the optimal face points of all associable planes respectively, and record the resulting line segments as associable line segments; for any associable line segment, when the associable line segment intersects with the block 3D model, record the intersection point in the speech test area corresponding to face α as a usable intersection point, and obtain the usable intersection points corresponding to all associable line segments; When none of the associable line segments intersect with the 3D block model or intersect with the speech test area corresponding to face α, the point in the speech test area corresponding to face α that is closest to each associable line segment is recorded as the available intersection point; obtain the available intersection points corresponding to all faces of the parameter analysis matrix, and record the positions of all available intersection points in the parameter analysis matrix as the sensing parameters of the speech sensor.

2. The intelligent control method for a building block toy according to claim 1, characterized in that, The process involves placing voice sensors within building block toys based on sensing parameters; acquiring external control data based on data received from multiple voice sensors; and transmitting this external control data to the AI ​​voice module, including: A voice sensor is placed in the building block toy based on all sensing parameters, and an AI voice module is placed inside the building block toy. The AI ​​voice module is used to receive the received audio and recognize the received audio based on the AI ​​built into the AI ​​voice module. The AI ​​voice module is connected to the execution unit of the building block toy. Connect the voice sensor and the AI ​​voice module using a data cable; when any voice sensor receives audio and the audio decibel is greater than B, record the audio data received by the voice sensor as external control data, and transmit the external control data to the AI ​​voice module via the data cable.

3. The intelligent control method for a building block toy according to claim 2, characterized in that, The data received by the AI ​​voice module is analyzed based on executable instructions, and the preset execution actions in the building block toy are filtered based on the analysis results to obtain standard execution actions, including: The system acquires preset action instructions from the building block toys and records them as executable instructions. When the AI ​​voice module receives external control data, it uses AI recognition to acquire data in the external control data that is the same as the executable instructions. When there is data in the external control data that is the same as the executable instructions, the execution action corresponding to the executable instruction that appears most frequently in the external control data is recorded as the standard execution action. If no data identical to the executable instruction exists in the external control data, the standard execution action will not be acquired.

4. The intelligent control method for a building block toy according to claim 3, characterized in that, Controlling building blocks based on standard execution actions includes: When the AI ​​recognition module obtains the standard execution action, it transmits the standard execution action to the execution unit of the building block toy, and the execution unit of the building block toy executes the standard execution action.

5. An intelligent control system for a building block toy, used to implement the intelligent control method for a building block toy as described in any one of claims 1-4, characterized in that, It includes a sensor voice receiving module, a voice command analysis module, and an action execution module; The sensing voice receiving module is used to place an AI voice module in the building block toy and acquire the sensing parameters of multiple voice sensors. Based on the sensing parameters, voice sensors are placed in the building block toy. External control data is acquired based on the received data from multiple voice sensors and the external control data is transmitted to the AI ​​voice module. The voice command analysis module is used to obtain the preset action commands in the building block toys, which are recorded as executable commands. Based on the executable commands, the data received by the AI ​​voice module is analyzed, and based on the analysis results, the preset execution actions in the building block toys are filtered to obtain standard execution actions. The action execution module is used to control the blocks based on standard actions.

Images