Intelligent interaction method and device based on billiard table and intelligent billiard table

Abstract

The invention discloses an intelligent interaction method and device based on a billiard table and the intelligent billiard table. According to the technical scheme provided by the invention, based on the camera arranged on the billiard table, the user action information is acquired, and the billiard table surface image is acquired to obtain the game playing information; comparing the user action information and / or the game information with an operation information comparison table, and matching to determine corresponding operation information; according to the operation information, conversion is carried out to generate control information for corresponding functions of accessory equipment of the billiard table; according to the control information, the accessory equipment is controlled to execute a function corresponding to the control information, and a corresponding target operation item is completed. According to the method, the action information and the desktop information of the billiard table user are collected and compared with the preset information, so that the function needing to be executed currently is determined in an intelligent interaction mode, the operation amount of the user is effectively reduced, convenience is improved, and the intelligent degree of the exercise assisting process is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of sports assistance, and in particular to an intelligent interaction method and device based on a billiard table, and an intelligent billiard table. Background Art

[0002] In recent years, with the gradual development of social economy, various cultural and sports activities have become more and more popular among the people, and billiards has gradually become popular in this process.

[0003] In daily billiards games, participants are usually required to perform operations such as arranging and stacking billiard balls before the start of the game, which invisibly increases the extra time spent by participants in the game. In addition, for automated billiard tables with automatic arranging functions, participants are also required to control the billiard tables by pressing buttons, etc. It can be seen that users still need to perform relatively complex operations to complete the control of the billiard tables. The overall intelligence level of the billiard tables is low, resulting in extra time spent on related operations during the game, which affects the user experience of the billiard table users. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides an intelligent interaction method based on a billiard table and a corresponding intelligent interaction device, computing equipment and computer storage medium based on a billiard table.

[0005] According to one aspect of the present invention, there is provided an intelligent interaction method based on a billiard table, the method comprising:

[0006] Based on the camera set on the billiard table, the user's action information is obtained according to the action of the billiard table user; the billiard table image is obtained according to the billiard table surface to obtain the game information;

[0007] Compare the user action information and / or game information with the operation information comparison table to match and determine the corresponding operation information;

[0008] According to the operation information, convert and generate control information for corresponding functions of the billiard table and its auxiliary equipment;

[0009] According to the control information, the console pool table and its auxiliary equipment execute the functions corresponding to the control information and complete the corresponding target operation items.

[0010] In the above solution, the action information at least includes user gesture information and / or user posture information;

[0011] The method of acquiring a billiard table image and obtaining game information further includes:

[0012] Using a camera to obtain a billiard tabletop image;

[0013] The scattering of billiard balls on the current billiard table is determined according to the billiard table image, and the game information is further determined; wherein the game information at least includes the start of the game, the end of the game or a violation.

[0014] In the above solution, the step of comparing the user action information and / or the game information with the operation information comparison table to match and determine the corresponding operation information further includes:

[0015] Based on multiple operation items, multiple preset actions and multiple preset game information, each operation item is matched with different preset actions and / or preset game information to generate an operation information comparison table;

[0016] Compare the user action information and / or game information with each preset action and / or preset game information in the operation information comparison table, and determine the target preset action and / or target preset game information that matches the user action information and / or game information from the operation information comparison table;

[0017] Based on the target preset action and / or the target preset game information, corresponding operation information is determined.

[0018] In the above scheme, the control information is used to control the auxiliary device to execute the function corresponding to the control information and complete the corresponding target operation item, further including:

[0019] Based on the control information, determining the target units from the billiard table and its attached equipment required to complete the functions included in the control information;

[0020] Sending control information to corresponding target units;

[0021] According to the control information, the target unit is controlled to execute the target operation item.

[0022] In the above scheme, the intelligent interaction method based on the billiard table further includes:

[0023] Based on the audio acquisition device, first voice information of the user of the billiard table is obtained;

[0024] Performing semantic analysis on first voice information of a user of the billiard table to determine operation information corresponding to the first voice information;

[0025] At least one expansion interface is provided to achieve function expansion through the linkage of hardware and / or software.

[0026] In the above scheme, the semantic analysis of the first voice information of the billiard table user to determine the operation information corresponding to the first voice information further includes:

[0027] Based on all functions of the billiard table and its corresponding auxiliary equipment, a command matching library corresponding to each function of the billiard table is constructed according to the command feature words corresponding to each function;

[0028] A first instruction judgment model is constructed based on the LSTM neural network, and model training is completed to obtain a trained second instruction judgment model;

[0029] Performing text conversion and word segmentation processing on the first voice information of the billiard table user to obtain first text information;

[0030] Using the second instruction judgment model and combining with the instruction matching library, a semantic analysis is performed on the first text information to obtain a semantic similarity prediction value between the first text information and the instruction feature word;

[0031] The semantic similarity prediction value is compared with the similarity threshold to determine the operation information corresponding to the first voice information.

[0032] In the above scheme, the first instruction judgment model is constructed based on the LSTM neural network, and the model training is completed to obtain the trained second instruction judgment model, which further includes:

[0033] Building a first instruction judgment model based on a neural network;

[0034] The first instruction judgment model is trained by collecting voice information previously acquired by the billiard table audio collection device as a training set; wherein the training set includes a feature training set and a general training set, wherein the feature training set is voice information containing any instruction feature words, and the general training set is voice information not containing instruction feature words; in the training set, the ratio of the number of samples contained in the feature training set to the number of samples contained in the general training set is greater than a preset ratio; wherein,

[0035] The objective function in training is

[0036]

[0037] Where N is the total number of samples, t i is the true label of the sample, s i is the semantic similarity prediction value, α is the regularization parameter, and w is the weight coefficient of the L2 regularization term.

[0038] According to another aspect of the present invention, there is provided an intelligent interactive device based on a billiard table, comprising: a collection module, a matching module, a control information generation module and an operation module; wherein:

[0039] The acquisition module is used to obtain user action information based on the action of the user of the billiard table based on the camera set on the billiard table; obtain the billiard table image for the billiard table surface and obtain the game information;

[0040] The matching module is used to compare the user action information and / or game information with the operation information comparison table, and match and determine the corresponding operation information;

[0041] The control information generation module is used to convert and generate control information for corresponding functions of the billiard table and its auxiliary equipment according to the operation information;

[0042] The operation module is used to control the console pool table and its auxiliary equipment to execute the functions corresponding to the control information and complete the corresponding target operation items according to the control information.

[0043] According to another aspect of the present invention, there is provided a smart billiard table, which applies the above-mentioned smart interaction method based on a billiard table, and at least comprises: a table body, a guide rail, a placement mechanism and a collection device; wherein,

[0044] The table body further comprises: table legs, a table top, a ball bag and a table edge; wherein the table top is rectangular;

[0045] The placing mechanism is located on one side of a short side of the rectangular desktop;

[0046] The guide rail has a downward slope, and respectively goes from the two corner pockets on the side where the placement mechanism is located, passes under the ball pockets on the long sides of each, and finally converges at the short side on the other side and connects to the placement mechanism;

[0047] The acquisition device is used to acquire image information and / or audio information near the billiard table.

[0048] In the above scheme, after the billiard ball falls into the ball pocket, it enters the guide rail and moves along the guide rail to the placement mechanism;

[0049] The placing mechanism is used to place the collected billiard balls at preset positions on the table according to a preset style after the game is over.

[0050] According to the technical solution provided by the present invention, based on the camera arranged on the billiard table, the user action information is obtained according to the action of the user of the billiard table; the billiard table image is obtained according to the billiard table surface to obtain the game information; the user action information and / or the game information is compared with the operation information comparison table to match and determine the corresponding operation information; according to the operation information, the control information for the corresponding functions of the billiard table and its ancillary equipment is converted and generated; according to the control information, the billiard table and its ancillary equipment are controlled to execute the functions corresponding to the control information to complete the corresponding target operation items. By setting an image acquisition device for a multifunctional billiard table with functions such as sorting and stacking, an intelligent action comparison or game situation comparison is performed based on the collected action information of the current user of the billiard table and the desktop information of the billiard table, and it is determined whether the action information or game situation corresponds to a certain function of the intelligent billiard table and its auxiliary equipment, and the operation information for the function is determined accordingly, and the operation information is further converted into control information of the functional unit corresponding to the billiard table and its auxiliary equipment to complete the control of the unit and then complete the corresponding operation items, so as to realize the intelligent control of the various functions of the billiard table by the user, and avoid the need for participants to sort, stack and place the billiards by themselves during the billiards game. In the case of stacking and other operations, the extra time required by the user during the exercise is greatly reduced through action and gesture control, which effectively improves the user experience; through intelligent semantic analysis of the collected voice information of the current user of the billiard table, it is determined whether the voice information involves a certain function of the smart billiard table, and the operation information corresponding to the function is determined, and the corresponding operation items have been completed, so that the user can realize voice control of various functions of the billiard table and its ancillary equipment, further reducing the extra operations required by the user and improving the user experience; at the same time, by setting the expansion interface, it provides the possibility for subsequent function expansion, further improving the flexibility of function selection. In addition, semantic analysis of voice information requires text conversion and word segmentation of the voice information, and a judgment model is constructed based on a deep learning method. The model is used to perform semantic analysis on the converted text information and the pre-stored command information corresponding to the various functions of the pool table, and the similarity match between the two is determined. Based on the similarity, it is predicted whether the currently collected audio data contains operation information corresponding to the function, thereby effectively improving the accuracy of semantic comparison, which is conducive to better determining the user's actual intention to match the corresponding function; further, by constructing a feature training set and a general training set according to the presence or absence of specific command feature words, and further forming a training set according to a specific ratio, and using the binary cross entropy loss function as the objective function for model training, the targetedness and training effect of the model training are effectively improved.

[0051] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0052] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0054] Figure 1 A schematic flow chart of an intelligent interaction method based on a billiard table according to an embodiment of the present invention is shown;

[0055] Figure 2 A schematic diagram showing a flow chart of a method for determining a voice information source according to an embodiment of the present invention;

[0056] Figure 3 A schematic flow chart showing an audio determination method for a billiard table function instruction according to an embodiment of the present invention;

[0057] Figure 4 A structural block diagram of an intelligent interactive device based on a billiard table according to an embodiment of the present invention is shown;

[0058] Figure 5 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown;

[0059] Figure 6 A schematic structural diagram of a smart billiard table according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0060] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0061] Figure 1 A schematic flow chart of an intelligent interaction method based on a billiard table according to an embodiment of the present invention is shown, and the method comprises the following steps:

[0062] Step S101, based on a camera installed on the billiard table, obtain user action information based on the actions of the user of the billiard table; obtain a billiard table image based on the billiard table, and obtain game information.

[0063] Preferably, the action information at least includes user gesture information and / or user posture information.

[0064] Specifically, using a camera, aiming at a billiard table, an image of the billiard table is obtained;

[0065] The scattering of billiard balls on the current billiard table is determined according to the billiard table image, and the game information is further determined; wherein the game information at least includes the start of the game, the end of the game or a violation.

[0066] Preferably, for example, if all the billiard balls on the current billiard table are in the stacked positions before the start of the game, the game information is determined to be the start of the game; if all the billiard balls of a certain suit on the current billiard table are pocketed, or if all the billiard balls except the white ball are pocketed, the game information is determined to be the end of the game; for another example, when the white ball on the billiard table is pocketed, the game information is determined to be a violation.

[0067] Step S102, comparing the user action information and / or game information with the operation information comparison table, and matching and determining the corresponding operation information.

[0068] Specifically, according to the first voice information, a functional sentence related to the function of the billiard table is extracted therefrom;

[0069] Analyze the function statement to determine the pool table functions contained in the function statement and the corresponding target operation items;

[0070] According to the target operation item, operation information corresponding to the first voice information is generated.

[0071] Step S103: convert and generate control information for corresponding functions of the billiard table and its accessory equipment according to the operation information.

[0072] Preferably, at least one expansion interface is provided for realizing the expansion of functions through the linkage of hardware and / or software. New functions corresponding to the hardware are added by external hardware, and new functions corresponding to the software are realized by reversely controlling the table through an external memory containing the software.

[0073] Step S104, according to the control information, the console pool table and its auxiliary equipment execute the functions corresponding to the control information and complete the corresponding target operation items.

[0074] Specifically, based on the control information, a target unit required to complete the function included in the control information is determined from the billiard table and its accessory equipment;

[0075] Sending control information to corresponding target units;

[0076] According to the control information, the target unit is controlled to execute the target operation item.

[0077] According to the intelligent interaction method based on the billiard table provided in this embodiment, based on the camera arranged on the billiard table, the user action information is obtained according to the action of the user of the billiard table; the billiard table image is obtained according to the billiard table surface to obtain the game information; the user action information and / or the game information is compared with the operation information comparison table, and the corresponding operation information is determined by matching; according to the operation information, the control information for the corresponding functions of the billiard table and its ancillary equipment is converted and generated; according to the control information, the billiard table and its ancillary equipment are controlled to execute the functions corresponding to the control information to complete the corresponding target operation items. According to the intelligent interaction method based on the billiard table provided by the present embodiment, an image acquisition device is provided for the multifunctional billiard table with functions such as sorting and stacking, and intelligent action comparison or game situation comparison is performed according to the collected action information of the current user of the billiard table and the desktop information of the billiard table, to judge whether the action information or game situation corresponds to a certain function of the intelligent billiard table and its auxiliary equipment, and to determine the operation information for the function accordingly, and further convert the operation information into control information of the functional unit corresponding to the billiard table and its auxiliary equipment to complete the control of the unit, and then complete the corresponding operation items, so as to realize the intelligent control of various functions of the billiard table by the user, avoid the situation that the participants need to sort, stack and other operations by themselves during the billiards movement, greatly reduce the extra time required by the user during the movement through action and gesture control, and effectively improve the user experience; at the same time, by setting an expansion interface, it provides the possibility for subsequent function expansion, and further improves the flexibility of function selection.

[0078] Figure 2 FIG. 4 is a flow chart showing a method for comparing and determining operation information according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0079] Step S201, based on multiple operation items, multiple preset actions and multiple preset game information, each operation item is matched with different preset actions and / or preset game information to generate an operation information comparison table.

[0080] Step S202, compare the user action information / or game information with each preset action and / or preset game information in the operation information comparison table, and determine the target preset action and / or target preset game information that matches the user action information / or game information from the operation information comparison table.

[0081] Preferably, in the operation information comparison table, the end of the game and the re-stacking of the billiard balls are matched.

[0082] Step S203, determining corresponding operation information based on the target preset action and / or the target preset game information.

[0083] According to the above method, by presetting a comparison table of multiple operation items, multiple preset actions and multiple preset game information, intelligent action comparison or game situation comparison is performed, and it is accurately determined whether the current action information or game situation corresponds to a certain function of the smart billiard table and its auxiliary equipment, and the operation information for the function is determined accordingly, that is, from a large amount of action image information and billiard table desktop information, the interference of invalid actions or invalid game situations on the billiard table control process is effectively eliminated, the accuracy of the selection of corresponding operation information in the overall control process is improved, and the possibility of erroneous operation is greatly reduced.

[0084] Figure 3 A schematic diagram showing a flow chart of an audio determination method for intelligent billiard table operation information according to an embodiment of the present invention;

[0085] like Figure 3 As shown, the method comprises the following steps:

[0086] Step S301: acquiring first voice information of a pool table user based on an audio acquisition device.

[0087] Step S302: semantically analyzing the first voice information of the user of the billiard table to determine the operation information corresponding to the first voice information.

[0088] Specifically, based on all the functions of the billiard table, an instruction matching library corresponding to each function of the billiard table is constructed according to instruction feature words corresponding to each function.

[0089] Specifically, a first instruction judgment model is constructed based on the LSTM neural network, and model training is completed to obtain a trained second instruction judgment model.

[0090] Preferably, a first instruction judgment model is constructed based on a neural network;

[0091] The first instruction judgment model is trained by collecting voice information previously acquired by the billiard table audio collection device as a training set; wherein the training set includes a feature training set and a general training set, wherein the feature training set is voice information containing any instruction feature words, and the general training set is voice information not containing instruction feature words; in the training set, the ratio of the number of samples contained in the feature training set to the number of samples contained in the general training set is greater than a preset ratio; wherein,

[0092] The objective function in training is

[0093]

[0094] Where N is the total number of samples, t i is the true label of the sample, s iis the semantic similarity prediction value, α is the regularization parameter, and w is the weight coefficient of the L2 regularization term.

[0095] Preferably, the preset ratio may be 2:1, that is, the number of samples in the feature training set is twice the number of samples in the general training set, or the preset ratio may also be adjusted according to user needs.

[0096] Specifically, text conversion and word segmentation processing are performed on the first voice information of the billiard table user to obtain the first text information.

[0097] Specifically, the second instruction judgment model is used in combination with the instruction matching library to perform semantic analysis on the first text information to obtain a semantic similarity prediction value between the first text information and the instruction feature word.

[0098] Specifically, the semantic similarity prediction value is compared with the similarity threshold to determine whether the first voice information contains operation information.

[0099] According to the above method, by performing intelligent semantic analysis on the collected voice information of the current user of the billiard table, it is determined whether the voice information involves a certain function for the smart billiard table, and the operation information corresponding to the function is determined, and the corresponding operation items have been completed, so that the user can realize voice control of various functions of the billiard table and its accessories, further reducing the additional operations required by the user and improving the user experience; in addition, the semantic analysis of the voice information requires text conversion and word segmentation processing of the voice information, and a judgment model is constructed based on the deep learning method. The model is used to perform semantic analysis on the converted text information and the pre-stored instruction information corresponding to the various functions of the billiard table to determine the similarity match between the two, and based on the similarity, it is predicted whether the currently collected audio data contains the operation information corresponding to the function, thereby effectively improving the accuracy of the semantic comparison, which is conducive to better determining the actual intention of the user to match the corresponding function; further, by constructing a feature training set and a general training set according to the presence or absence of specific instruction feature words, and further forming a training set according to a specific ratio, and using the binary cross entropy loss function as the objective function for model training, the pertinence and training effect of the model training are effectively improved.

[0100] Figure 4 FIG. 4 shows a structural block diagram of an intelligent interactive device based on a billiard table according to an embodiment of the present invention. Figure 4 As shown, the device includes: a collection module 401, a matching module 402, a control information generation module 403 and an operation module 404; wherein,

[0101] The acquisition module 401 is used to obtain user action information based on the action of the user of the billiard table based on the camera set on the billiard table; obtain the billiard table image for the billiard table surface to obtain the game information.

[0102] Specifically, the action information at least includes user gesture information and / or user posture information.

[0103] Specifically, the audio acquisition module 401 is further used for:

[0104] Using a camera to obtain a billiard tabletop image;

[0105] The scattering of billiard balls on the current billiard table is determined according to the billiard table image, and the game information is further determined; wherein the game information at least includes the start of the game, the end of the game or a violation.

[0106] The matching module 402 is used to compare the user action information and / or game information with the operation information comparison table, and match and determine the corresponding operation information.

[0107] Specifically, the matching module 402 is further used to:

[0108] Based on multiple operation items, multiple preset actions and multiple preset game information, each operation item is matched with different preset actions and / or preset game information to generate an operation information comparison table;

[0109] Compare the user action information and / or game information with each preset action and / or preset game information in the operation information comparison table, and determine the target preset action and / or target preset game information that matches the user action information and / or game information from the operation information comparison table;

[0110] Based on the target preset action and / or the target preset game information, corresponding operation information is determined.

[0111] The control information generating module 403 is used to convert and generate control information for corresponding functions of the billiard table and its auxiliary devices according to the operation information.

[0112] The operation module 404 controls the table and its auxiliary equipment to perform the functions corresponding to the control information and complete the corresponding target operation items according to the control information.

[0113] Specifically, the operation module 404 is further used to:

[0114] Based on the control information, determining the target units from the billiard table and its attached equipment required to complete the functions included in the control information;

[0115] Sending control information to corresponding target units;

[0116] According to the control information, the target unit is controlled to execute the target operation item.

[0117] Specifically, the intelligent interactive device based on the billiard table further includes: an audio comparison module 405 and an expansion module 406;

[0118] The audio comparison module 405 is used to obtain the first voice information of the user of the billiard table based on the audio acquisition device;

[0119] Semantic analysis is performed on first voice information of a user of the billiard table to determine operation information corresponding to the first voice information.

[0120] Specifically, the audio comparison module 405 is further used for:

[0121] Based on all functions of the billiard table and its corresponding auxiliary equipment, a command matching library corresponding to each function of the billiard table is constructed according to the command feature words corresponding to each function;

[0122] A first instruction judgment model is constructed based on the LSTM neural network, and model training is completed to obtain a trained second instruction judgment model;

[0123] Preferably, a first instruction judgment model is constructed based on a neural network;

[0124] The first instruction judgment model is trained by collecting voice information previously acquired by the billiard table audio collection device as a training set; wherein the training set includes a feature training set and a general training set, wherein the feature training set is voice information containing any instruction feature words, and the general training set is voice information not containing instruction feature words; in the training set, the ratio of the number of samples contained in the feature training set to the number of samples contained in the general training set is greater than a preset ratio; wherein,

[0125] The objective function in training is

[0126]

[0127] Where N is the total number of samples, t i is the true label of the sample, s i is the semantic similarity prediction value, α is the regularization parameter, and w is the weight coefficient of the L2 regularization term.

[0128] Performing text conversion and word segmentation processing on the first voice information of the billiard table user to obtain first text information;

[0129] Using the second instruction judgment model and combining with the instruction matching library, a semantic analysis is performed on the first text information to obtain a semantic similarity prediction value between the first text information and the instruction feature word;

[0130] The semantic similarity prediction value is compared with the similarity threshold to determine the operation information corresponding to the first voice information.

[0131] The expansion module 406 includes at least one expansion interface for implementing function expansion through the linkage of hardware and / or software.

[0132] According to the present embodiment, a smart interactive device based on a billiard table is provided, comprising: an acquisition module, a matching module, a control information generation module and an operation module; wherein the acquisition module is used to obtain user action information based on the action of the user of the billiard table, based on a camera arranged on the billiard table; obtain a billiard table image for the billiard table surface, and obtain game information; the matching module is used to compare the user action information and / or game information with the operation information comparison table, and match and determine the corresponding operation information; the control information generation module is used to convert and generate control information for the corresponding functions of the billiard table and its accessory equipment according to the operation information; the operation module is used to control the billiard table and its accessory equipment to perform the functions corresponding to the control information according to the control information, and complete the corresponding target operation items. The intelligent interactive device based on a billiard table provided by the present embodiment sets an image acquisition device for a multifunctional billiard table with functions such as sorting and stacking, and performs intelligent action comparison or game situation comparison according to the action information of the current user of the billiard table and the tabletop information of the billiard table, and judges whether the action information or game situation corresponds to a certain function of the intelligent billiard table and its auxiliary equipment, and determines the operation information for the function accordingly, and further converts the operation information into control information of the functional unit corresponding to the billiard table and its auxiliary equipment to complete the control of the unit, and then completes the corresponding operation item, so as to realize the intelligent control of various functions of the billiard table by the user, and avoid the occurrence of errors during billiard movement. In situations where participants need to perform operations such as arranging and stacking by themselves, the extra time required by users during exercise can be greatly reduced through action and gesture control, which effectively improves the user experience. Intelligent semantic analysis is performed on the collected voice information of the current user of the pool table to determine whether the voice information involves a certain function of the smart pool table, and the operation information corresponding to the function is determined, and the corresponding operation items have been completed, so that the user can voice control the various functions of the pool table and its ancillary equipment, further reducing the extra operations required by the user and improving the user experience. At the same time, by setting an expansion interface, it provides the possibility for subsequent function expansion, further improving the flexibility of function selection.In addition, semantic analysis of voice information requires text conversion and word segmentation of the voice information, and a judgment model is constructed based on a deep learning method. The model is used to perform semantic analysis on the converted text information and the pre-stored command information corresponding to the various functions of the pool table, and the similarity match between the two is determined. Based on the similarity, it is predicted whether the currently collected audio data contains operation information corresponding to the function, thereby effectively improving the accuracy of semantic comparison, which is conducive to better determining the user's actual intention to match the corresponding function; further, by constructing a feature training set and a general training set according to the presence or absence of specific command feature words, and further forming a training set according to a specific ratio, and using the binary cross entropy loss function as the objective function for model training, the targetedness and training effect of the model training are effectively improved.

[0133] The present invention also provides a non-volatile computer storage medium, which stores at least one executable instruction, and the executable instruction can execute the intelligent interaction method based on the billiard table in any of the above method embodiments.

[0134] Figure 5 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0135] like Figure 5 As shown, the computing device may include: a processor (processor) 502 , a communications interface (Communications Interface) 504 , a memory (memory) 506 , and a communication bus 508 .

[0136] in:

[0137] The processor 502 , the communication interface 504 , and the memory 506 communicate with each other via a communication bus 508 .

[0138] The communication interface 504 is used to communicate with other devices such as clients or other servers.

[0139] The processor 502 is used to execute the program 510, and specifically can execute the relevant steps in the above-mentioned embodiment of the intelligent interaction method based on the billiard table.

[0140] Specifically, the program 510 may include program codes, and the program codes include computer operation instructions.

[0141] The processor 502 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0142] The memory 506 is used to store the program 510. The memory 506 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0143] Program 510 can be specifically used to enable processor 502 to execute an intelligent interaction method based on a billiard table in any of the above-mentioned method embodiments. The specific implementation of each step in program 510 can refer to the corresponding descriptions in the corresponding steps and units in the above-mentioned intelligent interaction method embodiment based on a billiard table, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0144] Figure 6 FIG. 4 shows a schematic diagram of the structure of a smart billiard table according to an embodiment of the present invention. Figure 6 As shown, the billiard table uses the above-mentioned billiard training data tracking and analysis system, including: a table body 601, a guide rail 602 and a placement mechanism 603; wherein,

[0145] The table body further includes: table legs 6011, a table top 6012, a ball bag 6013 and a table edge 6014; wherein the table top 6012 is rectangular;

[0146] The placing mechanism 603 is located on one side of a short side of the rectangular tabletop 6012;

[0147] The guide rail 602 has a downward slope, and it goes around from the two corner pockets on the side where the placement mechanism 603 is located, through the bottom of the ball pockets on each long side, and finally converges at the short side on the other side and connects to the placement mechanism 603.

[0148] Specifically, after the billiard ball falls into the ball pocket 6013, it enters the guide rail 602 and moves along the guide rail 602 to the placement mechanism 603;

[0149] The placing mechanism 6013 is used to place the collected billiard balls at a preset position on the table 6012 according to a preset style after the game is over.

[0150] Specifically, the smart billiard table may further include a collection device 604. The collection device 604 is used to collect image information and / or audio information near the billiard table.

[0151] Preferably, the acquisition device 604 may include multiple cameras and / or audio acquisition units arranged at different positions of the smart billiard table, or around the smart billiard table.

[0152] The billiard table provided in this embodiment automatically gathers the billiard balls entering the ball pockets through guide rails and placement mechanisms, and automatically discharges them after the game is completed, taking over the placement work of the athletes, reducing the time spent between games, and improving the user experience.

[0153] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0154] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0155] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all of the features of the individual embodiments previously disclosed. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0156] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0157] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0158] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0159] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent interaction method based on a billiard table, comprising: Based on a camera disposed on the billiard table, user action information is obtained according to actions of a user of the billiard table; For the billiard table, obtain the billiard table image and obtain the game information; Compare the user action information and / or game information with the operation information comparison table to match and determine the corresponding operation information; According to the operation information, convert and generate control information for corresponding functions of the billiard table and its auxiliary equipment; According to the control information, the console pool table and its auxiliary equipment execute the functions corresponding to the control information and complete the corresponding target operation items.

2. The method according to claim 1, characterized in that The action information at least includes user gesture information and / or user posture information; The method of acquiring a billiard table image and obtaining game information further includes: Using a camera to obtain a billiard tabletop image; The scattering of billiard balls on the current billiard table is determined according to the billiard table image, and the game information is further determined; wherein the game information at least includes the start of the game, the end of the game or a violation.

3. The method according to claim 1, characterized in that: The comparing the user action information and / or game information with the operation information comparison table to match and determine the corresponding operation information further includes: Based on multiple operation items, multiple preset actions and multiple preset game information, each operation item is matched with different preset actions and / or preset game information to generate an operation information comparison table; Compare the user action information and / or game information with each preset action and / or preset game information in the operation information comparison table, and determine the target preset action and / or target preset game information that matches the user action information and / or game information from the operation information comparison table; Based on the target preset action and / or the target preset game information, corresponding operation information is determined.

4. The method according to claim 1, characterized in that The controlling of the auxiliary device to execute the function corresponding to the control information and complete the corresponding target operation item according to the control information further includes: Based on the control information, determining the target units from the billiard table and its attached equipment required to complete the functions included in the control information; Sending control information to corresponding target units; According to the control information, the target unit is controlled to execute the target operation item.

5. The method according to claim 1, characterized in that The intelligent interaction method based on the billiard table further includes: Based on the audio acquisition device, first voice information of the user of the billiard table is obtained; Performing semantic analysis on first voice information of a user of the billiard table to determine operation information corresponding to the first voice information; At least one expansion interface is provided to achieve function expansion through the linkage of hardware and / or software.

6. The method according to claim 5, characterized in that The performing semantic analysis on the first voice information of the user of the billiard table to determine the operation information corresponding to the first voice information further includes: Based on all functions of the billiard table and its corresponding auxiliary equipment, a command matching library corresponding to each function of the billiard table is constructed according to the command feature words corresponding to each function; A first instruction judgment model is constructed based on the LSTM neural network, and model training is completed to obtain a trained second instruction judgment model; Performing text conversion and word segmentation processing on the first voice information of the billiard table user to obtain first text information; Using the second instruction judgment model and combining with the instruction matching library, a semantic analysis is performed on the first text information to obtain a semantic similarity prediction value between the first text information and the instruction feature word; The semantic similarity prediction value is compared with the similarity threshold to determine the operation information corresponding to the first voice information.

7. The method according to claim 6, characterized in that The first instruction judgment model is constructed based on the LSTM neural network, and the model training is completed to obtain the trained second instruction judgment model, further comprising: Building a first instruction judgment model based on a neural network; The first instruction judgment model is trained by collecting voice information previously acquired by the billiard table audio collection device as a training set; wherein the training set includes a feature training set and a general training set, wherein the feature training set is voice information containing any instruction feature words, and the general training set is voice information not containing instruction feature words; in the training set, the ratio of the number of samples contained in the feature training set to the number of samples contained in the general training set is greater than a preset ratio; wherein, The objective function in training is Where N is the total number of samples, t i is the true label of the sample, s i is the semantic similarity prediction value, α is the regularization parameter, and w is the weight coefficient of the L2 regularization term.

8. An intelligent interactive device based on a billiard table, comprising: Acquisition module, matching module, control information generation module and operation module; wherein, The acquisition module is used to obtain user action information based on the action of the user of the billiard table based on the camera set on the billiard table; obtain the billiard table image for the billiard table surface and obtain the game information; The matching module is used to compare the user action information and / or game information with the operation information comparison table, and match and determine the corresponding operation information; The control information generation module is used to convert and generate control information for corresponding functions of the billiard table and its auxiliary equipment according to the operation information; The operation module is used to control the console pool table and its auxiliary equipment to perform the functions corresponding to the control information and complete the corresponding target operation items according to the control information.

9. A smart billiard table, the smart billiard table applying the smart interaction method based on a billiard table according to claim 1, comprising at least: Table, guide rails, placement mechanism and collection equipment; among them, The table body further comprises: table legs, a table top, a ball bag and a table edge; wherein the table top is rectangular; The placing mechanism is located on one side of a short side of the rectangular desktop; The guide rail has a downward slope, and respectively goes from the two corner pockets on the side where the placement mechanism is located, passes under the ball pockets on the long sides of each, and finally converges at the short side on the other side and connects to the placement mechanism; The acquisition device is used to acquire image information and / or audio information near the billiard table.

10. The billiard table according to claim 9, characterized in that: After the billiard ball falls into the pocket, it enters the guide rail and moves along the guide rail to the placement mechanism; The placing mechanism is used to place the collected billiard balls at preset positions on the table according to a preset style after the game is over.

Images