An electronic sandbox intelligent interaction method and system based on artificial intelligence

Abstract

The present invention belongs to the technical field of electronic sandbox, and provides an intelligent interaction method and system of electronic sandbox based on artificial intelligence. The method comprises: parsing the control voice input by the received user to obtain the voice control instruction; extracting the sandbox content information from the first interface and the second interface of the electronic sandbox respectively, analyzing the first correlation and the second correlation between the voice control instruction and the sandbox content information; extracting the macro display level of the displayed content from the first interface of the electronic sandbox, analyzing the third correlation between the macro display level and the voice control instruction, and obtaining the optimization value by comparison; using the optimization value to optimize the first correlation to the fourth correlation, determining the interface corresponding to the larger one of the fourth correlation and the second correlation as the target interface, and responding to the voice control instruction in the target interface. The present invention accurately determines the target interface targeted by the voice control instruction based on the correlation between the voice instruction and each display interface.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic sand tables, and more particularly, to an intelligent interaction method and system for an electronic sand table based on artificial intelligence. Background Art

[0002] With the continuous progress of technology, as a display and interaction tool integrating multiple technologies, the electronic sand table has been widely used in many fields. It combines multimedia technology, touch technology, and speech recognition technology, greatly improving the user experience and information display effect.

[0003] Users can manually touch the display screen of the electronic sand table to realize functions such as zooming, panning, and clicking to view details of the displayed content. The operation is convenient and intuitive. At the same time, the input method of voice control commands also provides users with a more diversified interaction experience. Users only need to say the corresponding commands, and the electronic sand table can quickly respond, further improving the interaction efficiency. This characteristic of being able to respond to both touch operations and voice commands makes the electronic sand table play an important role in scenarios such as urban planning display, real estate marketing, and teaching and training.

[0004] Currently, electronic sand tables with split-screen display functions are quite popular. Through split-screen, more display content can be provided for users to meet their needs for multi-tasking or comparing content in multiple regions. However, in the split-screen state, since the electronic sand table often cannot accurately determine which split-screen interface the user's voice command is directed at, when executing the voice command, it may operate on the wrong split-screen, thus affecting the user experience, which limits the application and promotion of the electronic sand table in some complex scenarios.

[0005] Therefore, developing a technology that can accurately identify the split-screen interface corresponding to the voice command during split-screen display is of great significance for improving the performance of the electronic sand table. Summary of the Invention

[0006] In view of the above technical problems, the present invention provides an intelligent interaction method, system, electronic device, computer storage medium, and computer program product for an electronic sand table based on artificial intelligence.

[0007] The present invention discloses an intelligent interaction method for an electronic sand table based on artificial intelligence. The method includes the following steps: when a user operates on a first interface of the electronic sand table, parse the received control voice input by the user to obtain a voice control instruction; respectively extract first sand table content information and second sand table content information from the first interface and the second interface of the electronic sand table, and analyze a first correlation degree and a second correlation degree between the voice control instruction and the first sand table content information and the second sand table content information; extract a macro display level of the display content from the first interface of the electronic sand table, analyze a third correlation degree between the macro display level and the voice control instruction, and obtain a first optimization value according to the third correlation degree; use the first optimization value to optimize the first correlation degree to a fourth correlation degree, and determine the interface corresponding to the larger value of the fourth correlation degree and the second correlation degree as the target interface, and respond to the voice control instruction in the target interface.

[0008] Optionally, the extracting a macro display level of the display content from the first interface of the electronic sand table includes: extracting recognizable object objects and their size information from the first interface of the electronic sand table, and using a deep learning model to perform uniformity analysis on the size information of each of the object objects corresponding to the first interface to obtain object uniformity; if the object uniformity is higher than a uniformity threshold, determine that the macro display level of the display content is a first value, otherwise determine that the macro display level of the display content is a second value; where the first value is greater than the second value.

[0009] Optionally, the analyzing a third correlation degree between the macro display level and the voice control instruction, and obtaining a first optimization value according to the third correlation degree includes: obtaining the upper body posture of the user who issued the control voice corresponding to the first interface, predicting the probability that the user is performing microscopic viewing according to the upper body posture, and obtaining a second optimization value according to the probability; using the second optimization value to optimize the macro display level, analyzing a third correlation degree between the optimized macro display level and the voice control instruction, and obtaining a first optimization value according to the third correlation degree.

[0010] Optionally, the responding to the voice control instruction in the target interface includes: determining a controlled object corresponding to the voice control instruction in the target interface, and adjusting the display mode and / or outputting auxiliary information of the controlled object according to the control instruction in the voice control instruction.

[0011] The present invention also discloses an intelligent interaction system for an electronic sand table based on artificial intelligence. The system includes a voice pickup and parsing module, a first correlation analysis module, a second correlation analysis module, and a voice response processing module. The voice pickup and parsing module is configured to parse the received control voice input by the user to obtain a voice control instruction when the user operates on the first interface of the electronic sand table. The first correlation analysis module is configured to respectively obtain first sand table content information and second sand table content information from the first interface and the second interface of the electronic sand table, and analyze the first correlation and the second correlation between the voice control instruction and the first sand table content information and the second sand table content information. The second correlation analysis module is configured to obtain the macro display level of the display content from the first interface of the electronic sand table, analyze the third correlation between the macro display level and the voice control instruction, and obtain a first optimization value according to the third correlation. The voice response processing module is configured to use the first optimization value to optimize the first correlation into a fourth correlation, determine the interface corresponding to the larger of the fourth correlation and the second correlation as the target interface, and respond to the voice control instruction in the target interface.

[0012] Optionally, the second correlation analysis module is configured to: obtain the recognizable object and its size information from the first interface of the electronic sand table, and use a deep learning model to perform uniformity analysis on the size information of each of the objects corresponding to the first interface to obtain the object uniformity; if the object uniformity is higher than the uniformity threshold, determine that the macro display level of the display content is the first value, otherwise determine that the macro display level of the display content is the second value; wherein, the first value is greater than the second value.

[0013] Optionally, the second correlation analysis module is further configured to: obtain the upper body posture of the user who issues the control voice corresponding to the first interface, predict the probability that the user is performing a microscopic view according to the upper body posture, and obtain a second optimization value according to the probability; use the second optimization value to optimize the macro display level, analyze the third correlation between the optimized macro display level and the voice control instruction, and obtain a first optimization value according to the third correlation.

[0014] Optionally, the voice response processing module is configured to: determine the controlled object corresponding to the voice control instruction in the target interface, and adjust the display mode and / or output the accessory information of the controlled object according to the control instruction in the voice control instruction.

[0015] The present invention also discloses an electronic device, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method as described in any of the foregoing.

[0016] The present invention also discloses a computer storage medium, where the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in any of the foregoing.

[0017] The present invention also discloses a computer program product, which contains computer code. When the computer code is executed by a processor of an electronic device, the method as described in any of the foregoing is implemented.

[0018] The intelligent interaction method of the electronic sand table based on artificial intelligence according to the present invention determines the target interface targeted by the voice control instruction of the user by analyzing the correlation between the voice instruction and the content information of each sub-screen and the macro display level, effectively avoiding the situation where the voice instruction is misjudged to the wrong sub-screen, and can greatly improve the user interaction experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 is a schematic flowchart of an intelligent interaction method of an electronic sand table based on artificial intelligence disclosed in an embodiment of the present invention.

[0021] Figure 2 is a schematic diagram of the sub-screen display of the electronic sand table disclosed in an embodiment of the present invention.

[0022] Figure 3 is a schematic structural diagram of an intelligent interaction system of an electronic sand table based on artificial intelligence disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The following specific embodiments illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0024] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0025] Regarding the above technical problems, as Figure 1 shown, an embodiment of the present invention discloses an intelligent interaction method for an electronic sand table based on artificial intelligence. The method includes the following steps: S101, when a user operates on a first interface of the electronic sand table, parse the received control voice input by the user to obtain a voice control instruction.

[0026] When the electronic sand table is triggered to be split-screen displayed (the first interface and the second interface, as Figure 2 shown), for example, when the user is operating on the first interface (such as a touch operation, etc.), the voice receiving device (such as a microphone, etc.) of the electronic sand table simultaneously receives the voice information spoken by the user. At this time, through voice parsing and natural language processing technologies, the voice input by the user is converted into a specific voice control instruction that the electronic sand table can recognize and process. For example, the user may say "Enlarge and display the roof of that building", and the system converts it into a corresponding instruction format through parsing for subsequent execution.

[0027] S102, respectively extract first sand table content information and second sand table content information from the first interface and the second interface of the electronic sand table, and analyze the first correlation degree and the second correlation degree between the voice control instruction and the first sand table content information and the second sand table content information.

[0028] From the split-screen interface of the electronic sand table, that is, the first interface and the second interface, respectively extract the content information currently displayed on each of them. The content information includes but is not limited to terrain, buildings, rivers, etc., and may also include colors, shapes, sizes, etc. For example, the first interface shows an overview image of a certain city, and the second interface shows a landmark building in that city.

[0029] Then, analyze the degree of association between the above voice control instruction and the sand table content information extracted from the two interfaces. The correlation degree can be represented by a numerical value, and the higher the numerical value, the stronger the correlation between the voice control instruction and the content information of that interface. For example, if the voice control instruction is "View the building distribution in this area", and the first interface just shows relevant content such as building models in that area, then the first correlation degree may be higher; if the second interface shows other irrelevant content, the second correlation degree is lower.

[0030] It should be noted that the above-mentioned correlation degree can be obtained by analyzing using artificial intelligence algorithms (such as semantic analysis, pattern matching, etc.). For example, a corresponding correlation degree analysis model is constructed based on artificial intelligence algorithms. The correlation degree analysis model can also be constructed based on general large models, such as DeepSeek, Llama, etc.

[0031] S103. Obtain the macroscopic display level of the display content extracted from the first interface of the electronic sand table, analyze the third correlation degree between the macroscopic display level and the voice control instruction, and obtain a first optimization value according to the third correlation degree.

[0032] Extract the macroscopic display level of the current display content from the first interface that the user is operating on. The macroscopic display level can be understood as the degree of detail or the size of the scope of content display. For example, the macroscopic display level corresponding to the overall layout view of the city is high, and the macroscopic display level corresponding to the view of a specific block is low.

[0033] Next, analyze the degree of association between the macroscopic display level and the voice control instruction in a similar manner as described above to obtain the third correlation degree. For example, if the voice control instruction is "View the overall traffic plan of the city" and the first interface is currently at a high macroscopic display level of the overall layout view of the city, then the third correlation degree is relatively high; if the first interface is at a microscopic display level of the detailed block plan, the third correlation degree is relatively low. According to the calculated third correlation degree, a first optimization value (such as 0.9, 1.2) is obtained through a pre-set comparison rule or algorithm. This first optimization value is used to adjust the subsequent correlation degree to more accurately determine the target interface corresponding to the voice control instruction.

[0034] It should be noted that generally, the determination of the first optimization value only needs to be carried out for one of the display interfaces. Because by using the first optimization value to increase or decrease the correlation degree of one of the display interfaces, the correlation degrees of the two display interfaces can be more clearly distinguished, so as to accurately screen out the target interface. Therefore, a first optimization value can also be determined for the second interface, or a first optimization value can be determined for both the first interface and the second interface at the same time, which will not be elaborated here.

[0035] S104. Use the first optimization value to optimize the first correlation degree into a fourth correlation degree, determine the interface corresponding to the larger of the fourth correlation degree and the second correlation degree as the target interface, and respond to the voice control instruction in the target interface.

[0036] Use the first optimization value obtained in step S103 to optimize the first correlation degree calculated in step S102 to obtain the fourth correlation degree. The optimization method can be an addition operation or a multiplication operation on the first correlation degree, and the specific method is not limited.

[0037] Then, compare the magnitudes of the fourth correlation degree and the second correlation degree, and determine the interface corresponding to the larger correlation degree as the target interface. For example, if the fourth correlation degree is greater than the second correlation degree, then the first interface is the target interface; otherwise, the second interface is the target interface.

[0038] Finally, in the determined target interface, perform corresponding operations and responses according to the requirements of the voice control command, such as performing operations like zooming in, zooming out, switching perspectives, etc., so as to achieve the accurate execution of voice commands by the electronic sand table in the split-screen state, and solve the problem that voice commands are prone to errors in the background technology.

[0039] The intelligent interaction method of the electronic sand table based on artificial intelligence according to the present invention determines the target interface targeted by the user's voice control command through the correlation degree analysis of the voice command with the content information of each split screen and the macro display level, effectively avoiding the situation where the voice command is misjudged to the wrong split screen, and can greatly improve the user interaction experience.

[0040] Optionally, obtaining the macro display level of the display content from the first interface of the electronic sand table includes: obtaining the recognizable object and its size information from the first interface of the electronic sand table, and using a deep learning model to perform uniformity analysis on the size information of each of the objects corresponding to the first interface to obtain the object uniformity; if the object uniformity is higher than the uniformity threshold, then determine that the macro display level of the display content is the first value, otherwise determine that the macro display level of the display content is the second value; where the first value is greater than the second value.

[0041] In this embodiment, image recognition is performed on the first interface of the electronic sand table, and various objects included therein can be recognized, and the size information of these objects can be obtained. These objects can be various elements presented in the electronic sand table interface, such as mountains, rivers, buildings, glass, doors and windows, decorations, etc.

[0042] Use a deep learning model to perform uniformity analysis on the size information of each object corresponding to the obtained first interface, so as to obtain the object uniformity. The uniformity analysis is used to measure the degree of difference between the sizes of these objects. If the object sizes are relatively close, then the uniformity is high; conversely, if the object size differences are large, the uniformity is low.

[0043] The display view of the electronic sand table can be divided into, for example, an aerial view and a close-up view. In the aerial view, the recognizable objects are mostly large elements such as mountains, rivers, and buildings. The size differences between these large elements are relatively small in this view, so the uniformity is relatively high. In the close-up view of a certain building, the recognizable objects are mostly small elements such as glass, doors, windows, and decorations. The size differences between these small elements are relatively large in this view, so the uniformity is relatively low.

[0044] Based on the above characteristics, the present invention is configured to compare the calculated object uniformity with a preset uniformity threshold. When the object uniformity is higher than the uniformity threshold, it indicates that the current display interface is in a more macroscopic display view, such as an aerial view, and the macroscopic display level of the display content is determined to be a larger first value. When the object uniformity is lower than the uniformity threshold, it means that the current display interface is in a more detailed display view, such as when magnifying a certain building for viewing, and the macroscopic display level of the display content is determined to be a smaller second value.

[0045] In the above manner, it is possible to accurately and quickly determine the macroscopic degree of the display content on the first interface of the electronic sand table, providing a quantitative basis for analyzing the correlation between the voice control instruction and the macroscopic display level, and helping to more accurately achieve the accurate response to the voice instruction in the split-screen state of the electronic sand table.

[0046] Optionally, analyzing the third correlation between the macroscopic display level and the voice control instruction, and obtaining a first optimization value according to the third correlation includes: obtaining the upper body posture of the user who issues the control voice corresponding to the first interface, predicting the probability that the user is performing a microscopic view according to the upper body posture, and obtaining a second optimization value according to the probability; using the second optimization value to optimize the macroscopic display level, analyzing the third correlation between the optimized macroscopic display level and the voice control instruction, and obtaining a first optimization value according to the third correlation.

[0047] In this embodiment, the first sand table content information and the second sand table content information are the own attribute information of each object displayed in the display interface (such as the central or largest or most prominent key object), such as the terrain, buildings, rivers, etc. mentioned above, and may also include color, shape, size, etc. The macroscopic display level refers to the size of the display view of the corresponding display interface, that is, the aerial view, close-up view, etc. mentioned above.

[0048] Considering that the object uniformity may not correspond exactly to the macroscopic display level, to improve the accuracy of the determined macroscopic display level, the present invention also uses technologies such as image recognition (based on cameras arranged on-site in the electronic sand table) and posture detection (based on wearable devices arranged on the user) to obtain the upper body posture of the user, predicts the probability of the user performing microscopic viewing based on the obtained upper body posture, matches a second optimization value according to this probability, then optimizes the macroscopic display level with this second optimization value, and finally analyzes the third correlation degree between the optimized macroscopic display level and the voice control instruction.

[0049] When the user leans forward significantly and the head is close to the screen, it indicates that the user is viewing the first display interface at a close distance, that is, the above probability is greater; conversely, when the user maintains a backward-leaning posture, it may be a macroscopic viewing, that is, the above probability is smaller. And when the user maintains the upper body posture of "close viewing" the first display interface, at this time, the first display interface is probably a macroscopic view, and the user maintains this upper body posture to see the local microscopic content in the macroscopic view; when the user maintains the upper body posture of "distant viewing" the first display interface, at this time, the first display interface is probably a microscopic view. Since the display sizes of the objects in the microscopic view are large enough, the user does not need to maintain the upper body posture of close viewing to see the local microscopic content in the microscopic view. Based on the above corresponding relationship, the present invention sets to match a second optimization value (such as 1.1, 0.8) according to the above probability and preset comparison data, where the second optimization value is positively correlated with the above probability.

[0050] Similar to the foregoing analysis of the correlation degree between the voice control instruction and the sand table content information, the analysis of this third correlation degree can also be completed using a correlation degree analysis model, but this correlation degree analysis model can be different from the foregoing correlation degree analysis model, such as different training data, which will not be elaborated here. Furthermore, the correlation between the optimized macroscopic display level of the first interface and the voice control instruction is analyzed, that is, the third correlation degree, which reflects the degree of fit between the voice instruction and the current interface analyzed from the perspective of the display field of view. For example, if the macroscopic display level is a high level of the overall urban layout view and the voice instruction is to view the overall traffic condition map of the city, the correlation degree is high; if the voice instruction is to view the internal structure of a certain building, the correlation degree is low.

[0051] It should be noted that both the first interface and the second interface can be switched to a high macroscopic display level or a low macroscopic display level.

[0052] Optionally, the responding to the voice control instruction in the target interface includes: determining a controlled object corresponding to the voice control instruction in the target interface, and adjusting the display mode of the controlled object and / or outputting associated information according to the control instruction in the voice control instruction.

[0053] In this embodiment, after determining the target interface to be controlled by the user, the electronic sand table parses out the controlled object and specific control content (such as zooming in or bringing up a certain content) from the voice control instruction, and controls the controlled object in the target interface to execute the corresponding control instruction.

[0054] As Figure 3 shown, an embodiment of the present invention also discloses an intelligent interaction system for an electronic sand table based on artificial intelligence. The system includes a voice pickup and parsing module, a first correlation analysis module, a second correlation analysis module, and a voice response processing module. The voice pickup and parsing module is configured to parse the received control voice input by the user to obtain a voice control instruction when the user operates on the first interface of the electronic sand table. The first correlation analysis module is configured to respectively extract first sand table content information and second sand table content information from the first interface and the second interface of the electronic sand table, and analyze the first correlation and the second correlation between the voice control instruction and the first sand table content information and the second sand table content information. The second correlation analysis module is configured to extract the macroscopic display level of the display content from the first interface of the electronic sand table, analyze the third correlation between the macroscopic display level and the voice control instruction, and obtain a first optimization value according to the third correlation. The voice response processing module is configured to use the first optimization value to optimize the first correlation into a fourth correlation, determine the interface corresponding to the larger of the fourth correlation and the second correlation as the target interface, and respond to the voice control instruction in the target interface.

[0055] Optionally, the second correlation analysis module is configured to: extract the recognizable object and its size information from the first interface of the electronic sand table, and use a deep learning model to perform uniformity analysis on the size information of each of the objects corresponding to the first interface to obtain the object uniformity. If the object uniformity is higher than the uniformity threshold, it is determined that the macroscopic display level of the display content is the first value, otherwise it is determined that the macroscopic display level of the display content is the second value, where the first value is greater than the second value.

[0056] Optionally, the second correlation analysis module is further configured to: analyze the third correlation between the macro display level and the voice control instruction, and obtain a first optimization value according to the third correlation; obtain the upper body posture of the user who issues the control voice corresponding to the first interface, predict the probability that the user is performing microscopic viewing according to the upper body posture, and obtain a second optimization value according to the probability; use the second optimization value to optimize the macro display level, analyze the third correlation between the optimized macro display level and the voice control instruction, and obtain a first optimization value according to the third correlation.

[0057] Optionally, the voice response processing module is configured to: determine a controlled object corresponding to the voice control instruction in the target interface, and adjust the display mode and / or output accessory information of the controlled object according to the control instruction in the voice control instruction.

[0058] An embodiment of the present invention also discloses an electronic device, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, where the processor executes the computer program to implement the method as described in the foregoing embodiments.

[0059] An embodiment of the present invention also discloses a computer storage medium, where the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in the foregoing embodiments.

[0060] The above computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0061] An embodiment of the present invention also discloses a computer program product, where the computer program product contains computer code, and when the computer code is executed by a processor of an electronic device, the method as described in the foregoing embodiments is implemented.

[0062] It should be understood that the various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0063] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub - combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An electronic sandbox intelligent interaction method based on artificial intelligence, characterized in that: The method comprises the following steps: when a user operates a first interface of an electronic sand table, parsing a control voice input by the user to obtain a voice control instruction; extracting first sand table content information and second sand table content information from the first interface and the second interface of the electronic sand table respectively, and analyzing a first correlation degree and a second correlation degree between the voice control instruction and the first sand table content information and the second sand table content information; extracting a macro display level of display content from the first interface of the electronic sand table, analyzing a third correlation degree between the macro display level and the voice control instruction, and obtaining a first optimization value according to the third correlation degree; optimizing the first degree of association to a fourth degree of association using the first optimization value, determining an interface corresponding to a larger one of the fourth degree of association and the second degree of association as a target interface, and responding to the voice control instruction in the target interface; The analyzing the third correlation between the macro display level and the voice control instruction, and obtaining the first optimization value according to the third correlation, includes: obtaining the upper body posture corresponding to the user who issued the control voice and the first interface, predicting the probability that the user is performing micro viewing according to the upper body posture, and obtaining the second optimization value according to the probability comparison; The macro display level is optimized using the second optimization value, a third correlation between the optimized macro display level and the voice control instruction is analyzed, and a first optimization value is obtained by comparison based on the third correlation.

2. The electronic sandbox intelligent interaction method based on artificial intelligence according to claim 1, characterized in that: The extracting of the macro display level of the display content from the first interface of the electronic sandbox includes: extracting identifiable objects and their size information from the first interface of the electronic sandbox, and using a deep learning model to perform uniformity analysis on the size information of each object corresponding to the first interface to obtain the object uniformity; if the object uniformity is higher than a uniformity threshold, determining the macro display level of the display content to be a first value, otherwise determining the macro display level of the display content to be a second value; wherein the first value is greater than the second value.

3. The electronic sandbox intelligent interaction method based on artificial intelligence according to claim 1, characterized in that: The responding to the voice control instruction in the target interface includes: determining a controlled object corresponding to the voice control instruction in the target interface, and adjusting the display mode and / or outputting auxiliary information of the controlled object according to the control instruction in the voice control instruction.

4. An electronic sandbox intelligent interactive system based on artificial intelligence, characterized by: The system includes a voice pickup and analysis module, a first relevance analysis module, a second relevance analysis module, and a voice response processing module; the voice pickup and analysis module is used to analyze the control voice input by the user when the user operates the first interface of the electronic sandbox, and obtain the voice control instruction; The first correlation analysis module is used to extract the first sandbox content information and the second sandbox content information from the first interface and the second interface of the electronic sandbox, respectively, and analyze the first correlation and the second correlation between the voice control instruction and the first sandbox content information and the second sandbox content information; the second correlation analysis module is used to extract the macro display level of the display content from the first interface of the electronic sandbox, analyze the third correlation between the macro display level and the voice control instruction, and obtain a first optimization value according to the third correlation; the voice response processing module is used to optimize the first correlation to a fourth correlation using the first optimization value, determine the interface corresponding to the larger one of the fourth correlation and the second correlation as the target interface, and respond to the voice control instruction in the target interface; The second association analysis module is further used to: obtain the upper body posture of the user who issues the control voice and the first interface, predict the probability that the user is performing microscopic viewing according to the upper body posture, and obtain a second optimization value according to the probability comparison; The macro display level is optimized using the second optimization value, a third correlation between the optimized macro display level and the voice control instruction is analyzed, and a first optimization value is obtained by comparison based on the third correlation.

5. The electronic sandbox intelligent interactive system based on artificial intelligence according to claim 4 is characterized by: The second association analysis module is used to: extract identifiable objects and their size information from the first interface of the electronic sandbox, and use a deep learning model to perform uniformity analysis on the size information of each object corresponding to the first interface to obtain the object uniformity; if the object uniformity is higher than the uniformity threshold, the macro display level of the display content is determined to be a first value, otherwise, the macro display level of the display content is determined to be a second value; wherein the first value is greater than the second value.

6. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 3.

7. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 3.

8. A computer program product, characterized in that: The computer program product includes computer codes, and when the computer codes are executed by a processor of an electronic device, the method according to any one of claims 1 to 3 is implemented.

Images