JPWO2021046449A5

JPWO2021046449A5 -

Info

Publication number: JPWO2021046449A5
Application number: JP2022514586A
Authority: JP
Publication date: 2023-09-13

Description

図５Ａの例では、モーフィングインターフェースシステム１３０は、テキスト文字列「Book me a flight」（「飛行機を予約してください」）を含む初期ユーザー入力５３０Ａを受け取る。モーフィングインターフェースシステム１３０は、ユーザー入力５３０Ａがフライト予約インテントに最も関連付けられている可能性が高いと判定し、それに応じて、フライト予約インターフェース５００は、ほぼ瞬時に表示される。インターフェース５００は、ウィジェット５４０を含み得る。ウィジェットは、インターフェースに関連するエンティティに関連する情報を表示または収集するインターフェースレイアウトの一部であり得る。場合によっては、ウィジェット５４０は、入力フィールド（例えば、テキストフィールド、チェックボックス、または他のデータ入力フォーマット）であり得る。インターフェース５００は、エンティティ認識モジュール１４５によって決定されたエンティティ値を追加(populate)することができるウィジェット５４０を表示し得る。様々な実施形態では、インターフェース５００は、エンティティ認識モジュール１４５が入力フィールドに追加(populate)する値を決定する前であっても、インターフェース５００にするエンティティのためのいくつか、またはすべてのウィジェット５４０を表示し得る。例えば、図５Ａは、フライト予約の目的地の値を入力するためのスペースを含むウィジェット５４０Ａを含む。図５Ｂは同様に、フライト予約の日付の値を入力するためのスペースを含む出発・帰着日ウィジェット５４０Ｂと乗客の人数を示すウィジェット５４０Ｃとを含み、エンティティ認識モジュール１４５が「1 passenger Economy」（「１人、エコノミー」）の値が最も可能性が高い入力値であると予測し、それに応じてウィジェット５４０Ｃに追加された値が表示される。 In the example of FIG. 5A, morphing interface system 130 receives initial user input 530A that includes the text string "Book me a flight." Morphing interface system 130 determines that user input 530A is most likely associated with a flight booking intent, and accordingly, flight booking interface 500 is displayed almost instantly. Interface 500 may include widgets 540. A widget may be a part of an interface layout that displays or collects information related to entities associated with the interface. In some cases, widget 540 can be an input field (eg, a text field, check box, or other data entry format). Interface 500 may display a widget 540 that can populate entity values determined by entity recognition module 145. In various embodiments, the interface 500 populates some or all widgets 540 for the entity in the interface 500 even before the entity recognition module 145 determines the values to populate the input fields. can be displayed. For example, FIG. 5A includes a widget 540A that includes a space for entering a destination value for a flight reservation. FIG. 5B similarly includes a departure/return date widget 540B that includes a space for entering a date value for the flight reservation, and a widget 540C that indicates the number of passengers, and the entity recognition module 145 indicates "1 passenger Economy"("1 passenger Economy"). 1 person, economy'') is the most likely input value, and the added value in widget 540C is displayed accordingly.

図６Ｃは、例示的な実施形態による、より多くのユーザー入力５３０Ｆを受け取り、インターフェースが図６Ａからモーフィング（morph）し続けるにつれて、ピザＴシャツ購入に関連するインターフェースのために表示されるレイアウトを示す図である。図６Ｃにおいて、ユーザー入力５３０Ｆは、追加情報を含む。特に、ユーザーが入力を追加したため、ユーザー入力５３０Ｆが、「I want to order a pizza T-Shirt」（「ピザＴシャツを注文したい」）を含むようになった。インテントマッチングモジュール１４０は、追加のユーザー入力を分析し、以前に選択されたピザ注文インテントがもはや最も適用可能なインテントではなくなり、新しい最も関連性のあるインテントがシャツ注文インテントであると決定する。モーフィングインターフェースシステム１３０は、シャツ購入インテントに適用可能なインターフェース５００を選択し、クライアントデバイス１１０でディスプレイをモーフィング(morph)して、選択されたインテントに関連するレイアウトを表示する。例えば、ピザレストランの提案を表示するのではなく、図６Ｃのインターフェース５００は、購入可能なピザをテーマとしたＴシャツの選択肢を表示するようになった。すなわち、ユーザーインターフェース５００は、ユーザーが追加の入力情報を提供し続けるにつれて、ピザの注文を表示する図６Ｂに示されるインターフェースから、明らかに瞬時にピザＴシャツ購入オプションを表示する図６Ｃに示されるインターフェースにモーフィング(morph)する。例示的なシャツ購入インテントに関連するウィジェット５４０Ｍは、その時ユーザーが購入のために選択することができるピザＴシャツの写真を含み得る。 FIG. 6C shows the layout displayed for an interface related to a pizza T-shirt purchase as more user input 530F is received and the interface continues to morph from FIG. 6A, according to an example embodiment. It is a diagram. In FIG. 6C, user input 530F includes additional information. In particular, user input 530F now includes "I want to order a pizza T-Shirt" because the user added the input. The intent matching module 140 analyzes the additional user input and determines that the previously selected pizza order intent is no longer the most applicable intent and the new most relevant intent is the shirt order intent. I decide. Morphing interface system 130 selects an interface 500 applicable to the shirt purchase intent and morphs the display on client device 110 to display a layout associated with the selected intent. For example, rather than displaying pizza restaurant suggestions, the interface 500 of FIG. 6C now displays a selection of pizza-themed T-shirts available for purchase. That is, the user interface 500 changes from the interface shown in FIG. 6B , which displays a pizza order, to the interface shown in FIG. 6C, which displays a pizza T-shirt purchase option, apparently instantaneously as the user continues to provide additional input information. morph into the interface that is used. The widget 540M associated with the exemplary shirt purchase intent may include a photo of a pizza t-shirt that the user can then select for purchase.

さらに、コンピュータシステム７００は、静的メモリ７０６、グラフィックスディスプレイ７１０（例えば、プラズマディスプレイパネル（ＰＤＰ）、液晶ディスプレイ（ＬＣＤ）、またはプロジェクター）を含むことができる。コンピュータシステム７００は、また、文字数字入力デバイス７１２（例えば、キーボード）、カーソル制御デバイス７１４（例えば、マウス、トラックボール、ジョイスティック、モーションセンサー、または他のポインティング機器）、信号生成デバイス７１８（例えば、スピーカー）、およびネットワークインターフェースデバイス７２０を含み得、これらは、また、バス７０８を介して通信するように構成されている。 Additionally, computer system 700 can include static memory 706 and a graphics display 710 (eg, a plasma display panel (PDP), liquid crystal display (LCD), or projector) . Computer system 700 also includes an alphanumeric input device 712 (e.g., a keyboard), a cursor control device 714 (e.g., a mouse, trackball, joystick, motion sensor, or other pointing device), and a signal generation device 718 (e.g., speakers). ), and a network interface device 720, which are also configured to communicate via bus 708.

Claims

receiving a first user input including an input string from a user device;
generating a set of natural language processing signals based on the first user input;
selecting an intent consistent with the first user input, the selection being based on the natural language processing signal, and the intent corresponding to a computer-executable function;
identifying a first interface associated with the intent;
extracting from the first user input a set of values associated with an entity of the first interface;
substantially simultaneously with said receiving said first user input, enabling display as said first interface on said user device, said first interface being displayed including a value from said set of values; and,
A method performed on a computer that includes.

receiving a second user input including a text string from the user device;
generating an updated set of natural language processing signals based on a combination of the first user input and the second user input;
selecting an intent that matches the combination of the first user input and the second user input, the selection being based on the updated set of natural language processing signals;
identifying a second interface associated with the newly selected intent;
extracting a second set of values associated with an entity of the second interface from the combination of the first user input and the second user input;
enabling the second interface for display on the user device, the second interface for display including values from the second set of values;
The computer-implemented method of claim 1, further comprising:

2. The computer-implemented method of claim 1, wherein the first user input is a voice input.

Selecting an intent that matches the user input includes comparing the first user input with one or more previously received user input strings; selecting an intent selected in response to at least one of the previously received user input strings in response to the first user input matching a user input string received at 2. The computer-implemented method of claim 1, comprising:

2. The computer-implemented method of claim 1, wherein selecting an intent that matches the user input includes applying a trained computer model to predict the most applicable intent.

2. The computer-implemented method of claim 1, wherein the interface includes a set of related entities.

3. The computer-implemented method of claim 2 , wherein the first interface and the second interface are the same interface.

3. The computer-implemented method of claim 2 , wherein the first interface and the second interface are different interfaces.

The computer-implemented method of claim 1, wherein the input string is a text string.

2. The computer-implemented method of claim 1, wherein the input string is a voice input.

one or more computer processors for executing computer program instructions;
a non-transitory computer-readable storage medium containing stored instructions executable by at least one processor, the instructions, when executed, causing the processor to:
receiving a first user input including an input string from a first user device;
generating a set of natural language processing signals based on the first user input;
selecting an intent consistent with the first user input, the selection being based on the natural language processing signal, and the intent corresponding to a computer-executable function;
identifying a first interface associated with the intent;
extracting from the first user input a set of values associated with an entity of the first interface; and
substantially simultaneously upon said receipt of said first user input, said first interface on said user device enables display, said first interface for display including a value from said set of values; to make
a computer readable storage medium;
computer systems including;

The instructions further include stored instructions which, when executed, cause the processor to further:
receiving a second user input from the user device including a text string;
generating an updated set of natural language processing signals based on a combination of the first user input and the second user input;
selecting an intent that matches the combination of the first user input and the second user input, the selection being based on the updated set of natural language processing signals;
identifying a second interface associated with the newly selected intent;
extracting a second set of values associated with an entity of the second interface from the combination of the first user input and the second user input; and
enabling the second interface for display on the user device, the second interface for display including values of the second set of values;
The computer system according to claim 11.

12. The computer system of claim 11, wherein the first user input is a voice input.

The instructions for causing the processor to select an intent that matches the user input include instructions for comparing the first user input with one or more previously received user input strings, and the one or more previously received user input strings. in response to said first user input matching a further previously received user input string; and in response to said at least one of said previously received user input strings. 12. The computer system of claim 11, including instructions for selecting a tent.

12. The computer of claim 11, wherein the instructions for causing the processor to select an intent that matches the user input include instructions for causing the processor to apply a trained computer model to predict the most applicable intent. system.

12. The computer system of claim 11, wherein an interface includes a set of related entities.

13. The computer system of claim 12 , wherein the first interface and the second interface are the same interface.

13. The computer system of claim 12 , wherein the first interface and the second interface are different interfaces.

12. The computer system of claim 11, wherein the input string is a text string.

The computer system according to claim 11, wherein the input character string is a voice input.