WO2018006367A1

WO2018006367A1 - Item purchasing method and system based on multimodal input in games

Info

Publication number: WO2018006367A1
Application number: PCT/CN2016/089210
Authority: WO
Inventors: 邱楠; 杨新宇; 王昊奋
Original assignee: 深圳狗尾草智能科技有限公司
Priority date: 2016-07-07
Filing date: 2016-07-07
Publication date: 2018-01-11
Also published as: CN106457046A

Abstract

An item purchasing method and system based on multimodal input in games, comprising: obtaining multimodal input information of a user (S10); recognizing item information in the multimodal input information according to a preset item information recognition policy (S20); recognizing a purchasing intention in the multimodal input information according to a preset intention recognition policy (S30); and if the purchasing intention in the multimodal input information is yes, opening a corresponding item purchasing display box according to the item information, wherein the opening command of the item purchasing display box is associated with the item information (S40). By means of the recognition of the item information in multimodal input information and the recognition of a purchasing intention, the requirement of a user is recognized, and a corresponding item purchasing display box is directly opened according to the item information in the multimodal input information, so that a complicated program operation is avoided. In addition, due to reduced operation steps, the probability of operation failure and misoperation is also avoided, thereby improving the success rate.

Description

Method and system for purchasing props based on multimodal input in game

Technical field

The invention relates to the field of robot interaction technology, and in particular relates to a method and system for purchasing props based on multimodal input in a game.

Background technique

At present, with the development of network technology, games are better developed in mobile terminals. In view of the structural particularity of mobile terminals, the operational convenience of games is limited. Therefore, voice technology applied to games has begun to be valued.

The application of speech technology to games is primarily the interaction between the player and the player, or the interaction of the player with the virtual robot in the game. In other words, the game system is controlled by voice technology. However, the control of the game system is currently based on manual control. For example, when you want to open the item system to buy things in the game, you still need to open the item home page first, and then select one item downwards. This makes the operation cumbersome, and because the speech recognition technology is uncertain, It is easy to cause failure.

Summary of the invention

The object of the present invention is to provide a method and system for purchasing props based on multimodal input in a game with simple operation, few operation steps and easy success.

The object of the present invention is achieved by the following technical solutions:

A method for purchasing props based on multimodal input in a game, comprising:

Obtaining multimodal input information of the user;

Identifying item information in the multimodal input information according to a preset item information identification strategy;

Identifying purchase intentions in the multimodal input information according to a preset intent recognition strategy;

If the purchase intention in the multimodal input information is YES, the corresponding item purchase display frame is opened according to the item information, wherein the open command of the item purchase display frame is associated with the item information.

Preferably, the method further includes:

Identify purchase quantity information in multimodal input information.

Preferably, the method further includes:

It is determined whether the multi-modal input information has the purchase quantity information, and if so, the purchase of the item is directly completed; if not, the display of the item purchase display frame is maintained.

Preferably, identifying the item information in the multimodal input information comprises:

Identify the item attribute information in the item information.

Preferably, the method further includes:

Prompting to the user whether to confirm the purchase information, and obtaining the second multimodal input information given by the user according to the prompt information, identifying the confirmed purchase information in the second multimodal input information, and confirming that the purchase information is The purchase of the item is completed according to the confirmation purchase information.

A prop purchase system based on multimodal input in a game, comprising:

a multi-modal input information acquiring module, configured to acquire multi-modal input information of the user;

The item information identifying module is configured to identify the item information in the multimodal input information according to the preset item information identification strategy;

The intent recognition module identifies the purchase intention in the multimodal input information according to the preset intent recognition strategy;

The item purchase module, if the purchase intention in the multimodal input information is yes, opens a corresponding item purchase display frame according to the item information, wherein the item purchase display frame opening command is associated with the item information.

Preferably, the system further comprises:

A quantity identification module for identifying purchase quantity information in the multimodal input information.

Preferably, the system further comprises:

The purchase quantity confirmation module is configured to determine whether the multi-modal input information has the purchase quantity information, and if so, directly complete the purchase of the item; if not, the display of the item purchase display box is maintained.

Preferably, the item information identification module includes:

The item attribute identifying unit is configured to identify the item attribute information in the item information.

Preferably, the system further comprises:

The purchase confirmation module: prompting the user to confirm the purchase information, and obtaining the second multimodal input information given by the user according to the prompt information, identifying the confirmation purchase information in the second multimodal input information, and confirming The purchase information is YES, and the purchase of the item is completed based on the confirmation purchase information.

Compared with the prior art, the present invention has the following advantages: by inputting information in a multimodal state The identification of the information, as well as the recognition of the purchase intention, thereby identifying the user's needs, according to the prop information in the multimodal input information, directly open the corresponding item purchase display box, thus avoiding cumbersome program operations. At the same time, due to the reduction of the operation steps, the probability of operation failure and misoperation is also avoided, and the success rate is improved.

DRAWINGS

1 is a flowchart of a method for parallel execution management of skill packets based on single intention according to Embodiment 1 of the present invention;

2 is a schematic diagram of a single-intention-based skill package parallel execution management system according to a second embodiment of the present invention.

detailed description

Although the flowcharts describe various operations as a sequential process, many of the operations can be implemented in parallel, concurrently or concurrently. The order of the operations can be rearranged. Processing may be terminated when its operation is completed, but may also have additional steps not included in the figures. Processing can correspond to methods, functions, procedures, subroutines, subroutines, and the like.

Computer devices include user devices and network devices. The user equipment or the client includes but is not limited to a computer, a smart phone, a PDA, etc.; the network device includes but is not limited to a single network server, a server group composed of multiple network servers, or a cloud computing-based computer or network server. cloud. The computer device can operate alone to carry out the invention, and can also access the network and implement the invention through interoperation with other computer devices in the network. The network in which the computer device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.

The terms "first," "second," and the like may be used herein to describe the various elements, but the elements should not be limited by these terms, and the terms are used only to distinguish one element from another. The term "and/or" used herein includes any and all combinations of one or more of the associated listed items. When a unit is referred to as being "connected" or "coupled" to another unit, it can be directly connected or coupled to the other unit, or an intermediate unit can be present.

The terminology used herein is for the purpose of describing the particular embodiments, The singular forms "a", "an", It will also be understood that the terms "comprising" and / or "comprising", as used herein, are intended to mean the stated features, integers, steps, operations, units and/or components. The existence or addition of one or more other features, integers, steps, operations, units, components and/or combinations thereof may be present.

The invention will now be further described with reference to the drawings and preferred embodiments.

Embodiment 1

As shown in FIG. 1, a specific embodiment of a method for purchasing a prop based on multimodal input in a game is provided, the method comprising the steps of:

S10. Acquire multi-modal input information of the user.

Specifically, the multi-modal input information of the user is obtained through operation of the smart terminal, wherein the smart terminal may include a handheld mobile terminal such as a mobile phone, a tablet, or the like, or a non-handheld terminal device such as a computer or a smart TV. The multimodal input information includes one or more of voice information, gesture information, expression information, scene information, image information, video information, face information, pupil iris information, light sense information, and fingerprint information. . The smart terminal is provided with a multi-modal input and input module such as a microphone, a sensor, a camera, a touch screen, and the like. For example, a voice recognition module is provided in the smart terminal. Generally speaking, the voice recognition module can identify the vocabulary appearing in the input voice information through the co-occurrence probability between the vocabulary of the large-scale real corpus, or through the artificial neural network. The method and the speech processing mechanism based on the grammar rules identify the meanings in the speech information and the like. For example, the smart terminal is provided with a video recognition module, which can recognize the expression of a face in the video information.

S20. Identify item information in the multimodal input information according to a preset item information identification strategy.

Specifically, taking the voice information as an example, the voice recognition method of the vocabulary appearing in the input voice signal can be identified by taking the co-occurrence probability between the vocabulary of the large-scale real corpus as an example. In the props recognition strategy of the speech recognition system, the item name and its related attribute information are collected on a large scale. For example, the props information about the "necklace" is first collected in the voice system, so that when the voice information appears in the necklace "The voice system can recognize the item information.

S30. Identify a purchase intention in the multimodal input information according to a preset intent recognition strategy.

Similarly, taking the voice information as an example, the voice recognition method of the vocabulary appearing in the input voice signal can be identified by the co-occurrence probability between the vocabulary of the large-scale real corpus. In the item recognition strategy of the speech recognition system, the vocabulary related to the purchase intention is first collected on a large scale, so that when the same vocabulary appears in the voice information, the voice system can recognize the purchase intention.

S40. If the purchase intention in the multimodal input information is yes, the corresponding item purchase display frame is opened according to the item information, wherein the item purchase display frame opening command and the item information Interest correlation.

Taking the voice information as an example, when the item information and the purchase intention are simultaneously recognized in the voice information, the corresponding item purchase display box is opened, wherein the corresponding item purchase display frame is for directly identifying the voice information. The direct display page of the item information can display the icon, name, attribute, quantity and other information of the item, and the user can judge whether it matches the item information in the voice information. The opening command of the corresponding item purchase display frame is associated with the vocabulary related to the item information in the voice system, so that when the voice system recognizes the vocabulary, the corresponding open command is executed. Alternatively, the item information and the purchase intent can be identified in a manner that the voice information is combined with other multimodal inputs. For example, the item information is identified by the voice information, and the purchase intention is identified by the expression information.

In this embodiment, the method further includes:

S50. Identify purchase quantity information in the multimodal input information.

For example, the number of purchases in the voice information may be identified, or the gesture in the video information may be identified, and the item system may open the corresponding item purchase display frame according to the purchase quantity information according to the The purchase quantity information modifies the purchase quantity value of the item so that the corresponding item purchase display box displays the same value as the current purchase quantity information.

In this embodiment, the method further includes:

S60. Determine whether the multi-modal input information has the purchase quantity information, and if so, directly complete the purchase of the item; if not, maintain the display of the item purchase display frame.

For example, when it is recognized that the voice information has the purchase quantity information, it can be determined that the user's purchase intention and the purchase quantity are determined, and thus, the item system directly completes the item according to the item information, the purchase intention, and the purchase quantity simultaneously recognized. Purchase action. For example, when the speech recognition system recognizes that the user's input voice is: "I want to buy 100 necklaces", where "I want to buy" is the purchase intention, "100" is the purchase quantity, and "necklace" is the prop information, so that the voice The recognition system simultaneously recognizes the item information, the purchase intention, and the purchase quantity, so that the corresponding item display frame can be opened, the purchase quantity value of the item can be changed, and the operation of the item purchase process can be completed.

In this embodiment, identifying the item information in the multimodal input information includes: identifying item attribute information in the item information. For example, if the necklace contains different attributes such as "golden necklace", "silver necklace", and "crystal necklace". When the word "necklace" is recognized by the voice information, the corresponding item purchase display box will display the upper directory of the necklace item, and the second time voice input is required and the attribute information of the item is added in the voice input twice. . That is to say, the word "necklace" in the upper position is also associated with the track of the superior directory of the "necklace" in the item system. With a display box. Of course, if the corresponding attribute information is included in the voice information input for the first time, the item system directly opens the corresponding item purchase display box according to the associated open command. For example, when the voice recognition system recognizes that the user's input voice is: "I want to buy 100 crystal necklaces", the voice recognition system recognizes the item information, the purchase intention, and the number of purchases, so that the corresponding crystal necklace prop display box can be opened. And change the purchase quantity of the crystal necklace to 100, and complete the operation of the item purchase process.

As another alternative manner of this embodiment, for the purchase operation of the item, the method may further include the steps of:

S70, prompting the user to confirm the purchase information, and acquiring the second multimodal input information given by the user according to the prompt information, identifying the confirmed purchase information in the second multimodal input information, and confirming the purchase information. As a result, the purchase of the item is completed based on the confirmation of the purchase information. For example, when the voice recognition system recognizes that the input voice of the user is: “I want to buy 100 crystal necklaces”, the user is prompted whether to confirm the purchase of 100 crystal necklaces, and the user can give a second multi-modality according to the prompt information. The information is input, and the second multimodal input information is used to identify the confirmed purchase information, and the purchase process of the item is completed.

Embodiment 2

As shown in FIG. 2, a specific embodiment of a multi-modal input-based item purchasing system in a game according to the above embodiment includes: a multi-modal input information acquiring module 10 for acquiring multi-modal input information of a user. The item information identification module 20 is configured to identify the item information in the multimodal input information according to the preset item information identification strategy; the intent identification module 30 identifies the purchase intention in the multimodal input information according to the preset intent recognition strategy. The item purchase module 40 opens the corresponding item purchase display frame according to the item information if the purchase intention in the multimodal input information is YES, wherein the item purchase display frame opening command is associated with the item information.

In this embodiment, the system further includes:

The quantity identification module 50 is configured to identify purchase quantity information in the multimodal input information.

In this embodiment, the system further includes:

The purchase quantity confirmation module 60 is configured to determine whether the multi-modal input information has the purchase quantity information, and if so, directly complete the purchase of the item; if not, the display of the item purchase display frame is maintained.

In this embodiment, the item information identification module 20 includes:

In this embodiment, the system further includes:

The purchase confirmation module 70: prompts the user whether to confirm the purchase information, and acquires the second multimodal input information given by the user according to whether the purchase information is confirmed, and identifies the confirmation in the second multimodal input information. The purchase information is confirmed, and the purchase information is confirmed as Yes, and the purchase of the item is completed based on the confirmation purchase information.

The above is a further detailed description of the present invention in connection with the specific preferred embodiments, and the specific embodiments of the present invention are not limited to the description. It will be apparent to those skilled in the art that the present invention may be made without departing from the spirit and scope of the invention.

Claims

A method for purchasing a prop based on multimodal input in a game, comprising:

Get the user's bracket:

Obtaining multimodal input information of the user;

Identifying item information in the multimodal input information according to a preset item information identification strategy;

Identifying purchase intentions in the multimodal input information according to a preset intent recognition strategy;

If the purchase intention in the multimodal input is YES, the corresponding item purchase display frame is opened according to the item information, wherein the open command of the item purchase display frame is associated with the item information.
The method of claim 1, wherein the method further comprises:

The purchase quantity information in the multimodal input information is identified.
The method of claim 1, wherein the method further comprises:

It is determined whether the multi-modal input information has the purchase quantity information, and if so, the purchase of the item is directly completed; if not, the display of the item purchase display frame is maintained.
The method for purchasing props based on multimodal input in a game according to claim 1, wherein the identifying the prop information in the multimodal input information comprises:

Identify the item attribute information in the item information.
The method of claim 1, wherein the method further comprises:

Prompting to the user whether to confirm the purchase information, and obtaining the second multimodal input information given by the user according to the prompt information, identifying the confirmed purchase information in the second multimodal input information, and confirming that the purchase information is The purchase of the item is completed according to the confirmation purchase information.
A prop purchase system based on multimodal input in a game, comprising:

a multi-modal input information acquiring module, configured to acquire multi-modal input information of the user;

The item information identifying module is configured to identify the item information in the multimodal input information according to the preset item information identification strategy;

The intent recognition module identifies the purchase intention in the multimodal input information according to the preset intent recognition strategy;

The item purchase module, if the purchase intention in the multimodal input information is yes, opens a corresponding item purchase display frame according to the item information, wherein the item purchase display frame opening command is associated with the item information.
The multi-modal input-based item purchasing system of the game according to claim 6, wherein the system further comprises:

A quantity identification module for identifying purchase quantity information in the multimodal input information.
The in-game multi-modal input-based item purchasing system of claim 7, wherein the system further comprises:

The purchase quantity confirmation module is configured to determine whether the multi-modal input information has the purchase quantity information, and if so, directly complete the purchase of the item; if not, the display of the item purchase display box is maintained.
The multi-modal input-based item purchasing system of the game according to claim 6, wherein the item information identifying module comprises:

The item attribute identifying unit is configured to identify the item attribute information in the item information.
The in-game multimodal input based item purchasing system according to claim 6, wherein the system further comprises:

The purchase confirmation module: prompting the user to confirm the purchase information, and obtaining the second multimodal input information given by the user according to the prompt information, identifying the confirmation purchase information in the second multimodal input information, and confirming The purchase information is YES, and the purchase of the item is completed based on the confirmation purchase information.