Electronic sand table intelligent interaction method and system based on artificial intelligence

Abstract

The invention belongs to the technical field of electronic sand tables, and provides an electronic sand table intelligent interaction method and system based on artificial intelligence. The method comprises the following steps: analyzing received control voice input by a user to obtain a voice control instruction; respectively extracting sand table content information from a first interface and a second interface of the electronic sand table, and analyzing a first correlation degree and a second correlation degree between the voice control instruction and the sand table content information; extracting a macroscopic display level of the display content from a first interface of the electronic sand table, analyzing a third association degree between the macroscopic display level and the voice control instruction, and comparing to obtain an optimized value; and optimizing the first association degree into a fourth association degree by using the optimization value, determining an interface corresponding to the larger one of the fourth association degree and the second association degree as a target interface, and responding to the voice control instruction in the target interface. According to the invention, the target interface which the voice control instruction aims at is accurately determined based on the association degree between the voice instruction and each display interface.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic sandboxes, and in particular to an intelligent interaction method and system for an electronic sandbox based on artificial intelligence. Background Art

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

[0003] Users can manually touch the display screen of the electronic sand table to achieve 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 interactive experience. Users only need to say the corresponding command, and the electronic sand table can respond quickly, further improving the interaction efficiency. This feature of being able to respond to touch operations and voice commands at the same time 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 sandboxes with split-screen display functions are quite popular. Split-screen can provide users with more display content and meet users' needs for multi-tasking or multi-region content comparison. However, in the split-screen state, the electronic sandbox often cannot accurately determine which split-screen interface the user's voice command is directed to, resulting in the possibility of operating the wrong split-screen when executing the voice command, thus affecting the user's experience. This limits the application and promotion of electronic sandboxes in some complex scenarios.

[0005] Therefore, developing a technology that can accurately identify the split-screen interface corresponding to voice commands when the split-screen display is displayed is of great significance to improving the performance of the electronic sandbox. Summary of the invention

[0006] In response to the above technical problems, the present invention provides an electronic sandbox intelligent interaction method, system, electronic device, computer storage medium and computer program product based on artificial intelligence.

[0007] The present invention discloses an electronic sandbox intelligent interaction method based on artificial intelligence, and the method comprises the following steps: when a user operates a first interface of the electronic sandbox, parsing a control voice input by the user received to obtain a voice control instruction; extracting first sandbox content information and second sandbox content information from the first interface and the second interface of the electronic sandbox respectively, analyzing a first correlation degree and a second correlation degree between the voice control instruction and the first sandbox content information and the second sandbox content information; extracting a macro display level of displayed content from the first interface of the electronic sandbox, 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 correlation degree to a fourth correlation degree using the first optimization value, determining an interface corresponding to the larger one of the fourth correlation degree and the second correlation degree as a target interface, and responding to the voice control instruction in the target interface.

[0008] Optionally, extracting the macro display level of the displayed 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 object uniformity; if the object uniformity is higher than a uniformity threshold, determining the macro display level of the displayed content to be a first value, otherwise determining the macro display level of the displayed content to be a second value; wherein the first value is greater than the second value.

[0009] Optionally, the analyzing the third correlation between the macro display level and the voice control instruction and deriving a first optimization value based on the third correlation includes: obtaining the upper body posture corresponding to the user who issues the control voice and the first interface, predicting the probability that the user is performing a micro viewing based on the upper body posture, and deriving a second optimization value based on the probability comparison; optimizing the macro display level using the second optimization value, analyzing the third correlation between the optimized macro display level and the voice control instruction, and deriving a first optimization value based on the third correlation comparison.

[0010] Optionally, responding to the voice control instruction in the target interface includes: determining a controlled object in the target interface corresponding to the voice control instruction, 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 electronic sandbox intelligent interaction system based on artificial intelligence, the system comprising a voice pickup and analysis module, a first correlation analysis module, a second correlation 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 to obtain a 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 of the voice control instruction with 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 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 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 object uniformity; if the object uniformity is higher than a uniformity threshold, then 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.

[0013] Optionally, the second correlation analysis module is further used to: obtain the upper body posture corresponding to the user who issues the control voice and the first interface, predict the probability that the user is performing a microscopic view based on the upper body posture, and obtain a second optimization value based on the probability comparison; 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 the first optimization value based on the third correlation comparison.

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

[0015] The present invention also discloses 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 any of the above methods.

[0016] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0017] The present invention also discloses a computer program product, which includes computer codes. When the computer codes are executed by a processor of an electronic device, any of the above methods is implemented.

[0018] The electronic sandbox intelligent interaction method based on artificial intelligence of the present invention determines the target interface targeted by the user's voice control command by analyzing the correlation between the voice command and the content information of each split screen and the macro display level, thereby effectively avoiding the situation where the voice command is misjudged to the wrong split 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 certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a flow chart of an electronic sandbox intelligent interaction method based on artificial intelligence disclosed in an embodiment of the present invention.

[0021] Figure 2 It is a schematic diagram of the split-screen display of the electronic sandbox disclosed in an embodiment of the present invention.

[0022] Figure 3 It is a structural schematic diagram of an electronic sandbox intelligent interactive system based on artificial intelligence disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0024] In addition, the technical features involved in the 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] In response to the above technical issues, such as Figure 1 As shown, an embodiment of the present invention discloses an electronic sandbox intelligent interaction method based on artificial intelligence, and the method includes the following steps: S101, when a user operates a first interface of the electronic sandbox, the control voice received from the user input is parsed to obtain a voice control instruction.

[0026] When the electronic sandbox is triggered to display in split screen (first interface and second interface, such as Figure 2 In the case of a user operating the first interface (such as a touch operation), the voice receiving device (such as a microphone) of the electronic sandbox simultaneously receives the voice information spoken by the user. At this time, the voice input by the user is converted into a specific voice control instruction that the electronic sandbox can recognize and process through voice analysis and natural language processing technology. For example, the user may say "enlarge the roof of that building", and the system converts it into a corresponding instruction format through analysis for subsequent execution.

[0027] S102, extracting first sandbox content information and second sandbox content information from the first interface and the second interface of the electronic sandbox respectively, and analyzing first and second correlations between the voice control command and the first and second sandbox content information.

[0028] From the split screen interface of the electronic sand table, namely the first interface and the second interface, the currently displayed content information is extracted respectively. The content information includes but is not limited to topography, buildings, rivers, etc., and may also include color, shape, size, etc. For example, the first interface displays an overview image of a city, and the second interface displays a landmark building of the city.

[0029] Then, the correlation between the above voice control command and the sandbox content information extracted from the two interfaces is analyzed. The correlation can be expressed as a numerical value, and the higher the numerical value, the stronger the correlation between the voice control command and the content information of the interface. For example, if the voice control command is "check the building distribution in this area", and the first interface happens to display the building model and other related content in the area, then the first correlation may be higher; if the second interface displays other irrelevant content, the second correlation is lower.

[0030] It should be noted that the above-mentioned relevance can be obtained by using artificial intelligence algorithms (such as semantic analysis, pattern matching, etc.), for example, building a corresponding relevance analysis model based on artificial intelligence algorithms. The relevance analysis model can also be built based on a general large model, such as DeepSeek, Llama, etc.

[0031] S103, extracting a macro display level of the displayed content from the first interface of the electronic sandbox, analyzing a third correlation between the macro display level and the voice control instruction, and obtaining a first optimization value according to the third correlation.

[0032] The macro display level of the currently displayed content is extracted from the first interface being operated by the user. The macro display level can be understood as the detail level or scope of the content display. For example, the macro display level corresponding to the overall layout of the city is high, and the macro display level corresponding to the specific block view is low.

[0033] Next, the degree of association between the macro display level and the voice control command is analyzed in a manner similar to the above to obtain a third degree of association. For example, if the voice control command is "view the city's overall traffic plan", and the first interface is currently at a high macro display level of the city's overall layout vision, then the third degree of association is high; if the first interface is at a micro display level of detailed block planning, the third degree of association is low. Based on the calculated third degree of association, a first optimization value (for example, 0.9, 1.2) is obtained through a pre-set comparison rule or algorithm. The first optimization value is used to adjust the subsequent degree of association to more accurately determine the target interface corresponding to the voice control command.

[0034] It should be noted that, generally speaking, the determination of the first optimization value only needs to be for one of the display interfaces, because by using the first optimization value to increase or decrease the correlation of one of the display interfaces, the correlation of the two display interfaces can be more clearly distinguished, thereby accurately screening out the target interface. Therefore, the first optimization value can also be determined for the second interface, or the first optimization value can be determined for both the first interface and the second interface at the same time, and the details will not be repeated.

[0035] S104, using the first optimization value to optimize the first correlation degree to a fourth correlation degree, determining an interface corresponding to a larger one of the fourth correlation degree and the second correlation degree as a target interface, and responding to the voice control instruction in the target interface.

[0036] The first optimization value obtained in step S103 is used to optimize the first correlation calculated in step S102 to obtain a fourth correlation. The optimization method may be to perform an addition operation or a multiplication operation on the first correlation, which is not specifically limited.

[0037] Then, the fourth correlation degree is compared with the second correlation degree, and the interface corresponding to the larger correlation degree is determined as the target interface. For example, if the fourth correlation degree is greater than the second correlation degree, the first interface is the target interface; otherwise, the second interface is the target interface.

[0038] Finally, in the determined target interface, corresponding operations and responses are performed according to the requirements of the voice control instructions, such as zooming in, zooming out, switching perspectives, etc., thereby realizing the accurate execution of voice commands in the split-screen state of the electronic sandbox, solving the problem of easy errors in the execution of voice commands in the background technology.

[0039] The electronic sandbox intelligent interaction method based on artificial intelligence of the present invention determines the target interface targeted by the user's voice control command by analyzing the correlation between the voice command and the content information of each split screen and the macro display level, thereby 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, extracting the macro display level of the displayed 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 object uniformity; if the object uniformity is higher than a uniformity threshold, determining the macro display level of the displayed content to be a first value, otherwise determining the macro display level of the displayed content to be a second value; wherein 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 to identify various objects included therein and obtain size information of these objects. These objects may be various elements presented in the electronic sand table interface, such as mountains, rivers, buildings, glass, doors and windows, and decorations.

[0042] The deep learning model is used to perform uniformity analysis on the size information of each object corresponding to the first interface, thereby obtaining the uniformity of the object. The uniformity analysis is used to measure the degree of difference between the sizes of these objects. If the sizes of the objects are relatively close, the uniformity is high; conversely, if the sizes of the objects are very different, the uniformity is low.

[0043] The display field of the electronic sand table can be divided into a high-altitude bird's-eye view, a local detailed view, etc. In the high-altitude bird's-eye view, the identifiable objects are mostly large elements such as mountains, rivers, and buildings. In this field of view, the size difference between these large elements is relatively small, so the uniformity is high; in the local detailed view of a building, the identifiable objects are mostly small elements such as glass, doors and windows, and decorations. In this field of view, the size difference between these small elements is relatively large, and the uniformity is low.

[0044] Based on the above characteristics, the present invention is configured to compare the calculated uniformity of the object with a preset uniformity threshold. When the uniformity of the object is higher than the uniformity threshold, it indicates that the current display interface is in a more macroscopic display field of view, such as a high-altitude bird's-eye view, and the macroscopic display level of the displayed content is determined to be a larger first value. When the uniformity of the object is lower than the uniformity threshold, it indicates that the current display interface is a more subtle display field of view, such as zooming in on a building, and the macroscopic display level of the displayed content is determined to be a smaller second value.

[0045] Through the above method, the macro level of the display content of the first interface of the electronic sandbox can be accurately and quickly judged, which provides a quantitative basis for the subsequent analysis of the correlation between voice control commands and macro display levels, and helps to more accurately realize the accurate response of the electronic sandbox to voice commands in the split-screen state.

[0046] Optionally, the analyzing the third correlation between the macro display level and the voice control instruction and deriving a first optimization value based on the third correlation includes: obtaining the upper body posture corresponding to the user who issues the control voice and the first interface, predicting the probability that the user is performing a micro viewing based on the upper body posture, and deriving a second optimization value based on the probability comparison; optimizing the macro display level using the second optimization value, analyzing the third correlation between the optimized macro display level and the voice control instruction, and deriving a first optimization value based on the third correlation comparison.

[0047] In this embodiment, the first sandbox content information and the second sandbox content information are the attribute information of each object (such as the central, largest or most prominent key object) displayed in the display interface, such as the aforementioned topography, buildings, rivers, etc., and may also include color, shape, size, etc. The macro display level refers to the size of the display field of the corresponding display interface, that is, the aforementioned high-altitude bird's-eye view, local detailed view, etc.

[0048] Taking into account that the uniformity of the object may not correspond 100% to the macro display level, in order to improve the accuracy of the determined macro display level, the present invention also uses image recognition (based on cameras deployed on the electronic sand table), posture detection (based on wearable devices deployed on the user) and other technologies to obtain the user's upper body posture, and predict the probability of the user performing microscopic viewing based on the obtained upper body posture, and obtain a second optimization value based on the probability matching, and then optimize the macro display level based on the second optimization value, and finally analyze the third correlation between the optimized macro display level and the voice control command.

[0049] When the user's body leans forward with a large amplitude 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; on the contrary, when the user keeps the body leaning back, it may be a macroscopic view, that is, the above probability is smaller. When the user maintains the upper body posture of viewing the first display interface at a "close distance", the first display interface is most likely a macroscopic field of view, and the user maintains this upper body posture in order to see the local tiny content in the macroscopic field of view; when the user maintains the upper body posture of viewing the first display interface at a "long distance", the first display interface is most likely a microscopic field of view. Since the display size of the objects in the microscopic field of view is large enough, the user does not need to maintain the upper body posture of viewing at a close distance, and can also see the local tiny content in the microscopic field of view. Based on the above corresponding relationship, the present invention is set to obtain a second optimization value (for example, 1.1, 0.8) according to the above probability and the preset control data matching, wherein the second optimization value is positively correlated with the above probability.

[0050] Similar to the aforementioned analysis of the correlation between the voice control command and the sandbox content information, the correlation analysis model can also be used to complete the analysis of the third correlation, but the correlation analysis model can be different from the aforementioned correlation analysis model, such as the difference in training data, which will not be described in detail. Furthermore, the correlation between the optimized macro display level of the first interface and the voice control command, that is, the third correlation, is analyzed, which reflects the degree of fit between the voice command and the current interface analyzed from the perspective of the display field of view. For example, if the macro display level is a high level of the overall layout of the city, and the voice command is to view the overall traffic status map of the city, the correlation between the two is high; if the voice command is to view the internal structure of a building, the correlation is low.

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

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

[0053] In this embodiment, after determining the target interface that the user wants to control, the electronic sandbox will parse the controlled object and specific control content (such as zooming in or calling out a certain content) from the voice control command, and control the controlled object in the target interface to execute the corresponding control command.

[0054] like Figure 3 As shown, the embodiment of the present invention further discloses an electronic sandbox intelligent interaction system based on artificial intelligence, the system comprising a voice pickup and analysis module, a first correlation analysis module, a second correlation 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 to 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 of the voice control instruction with 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 the 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 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 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 object uniformity; if the object uniformity is higher than a uniformity threshold, then 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.

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

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

[0058] An embodiment of the present invention further discloses 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 described in the above embodiment.

[0059] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0060] The computer-readable storage medium described above may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0061] An embodiment of the present invention further discloses a computer program product, which includes computer code. When the computer code is executed by a processor of an electronic device, the method described in the above embodiment is implemented.

[0062] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described 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 this document does not limit this.

[0063] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in 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; The first optimization value is used to optimize the first correlation degree to a fourth correlation degree, an interface corresponding to a larger one of the fourth correlation degree and the second correlation degree is determined as a target interface, and the voice control instruction is responded to in the target interface.

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 analyzing the third correlation between the macro display level and the voice control instruction and obtaining a first optimization value according to the third correlation includes: obtaining the upper body posture corresponding to the user who issues the control voice and 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 comparison; optimizing the macro display level using the second optimization value, analyzing the third correlation between the optimized macro display level and the voice control instruction, and obtaining a first optimization value according to the third correlation comparison.

4. 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.

5. 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 displayed 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 use the first optimization value to optimize the first correlation to 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.

6. The electronic sandbox intelligent interactive system based on artificial intelligence according to claim 5, characterized in that: 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.

7. The electronic sandbox intelligent interactive system based on artificial intelligence according to claim 6, characterized in that: 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.

8. 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 4.

9. 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 4.

10. 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 4 is implemented.

Images