Watson NLC 服务与对话服务的集成示例

Question

From the Watson Dialog document，表示连接NLC的配置设置。但是如果没有运行示例应用程序，很难理解它是如何工作的。大多数可以用谷歌搜索的例子都没有这样的设置。我试图找到一些示例，这些示例使用 'classifier' 设置和 'INTENT:{xxxxxx}' 设置等指定的设置，每个文档。如果有人能对此提供帮助，那就太好了，非常感谢。

Answer 1

这里是一个使用 demo NLC training data 的例子。将该文本保存到 CSV 文件。

创建您的 NLC 服务。服务名称无关紧要。
创建后，单击 "Access Beta Toolkit"。您将需要重新登录，并允许工具包访问 NLC 服务。
单击 "Upload training data" 按钮。 Select 您之前保存的 CSV 文件。如果有效，您将看到您的意图 + 问题。如果失败，最常见的问题是没有给它一个 csv 文件扩展名。
单击 "Create classifier"。名字并不重要。
点击trainingdata/classifiers查看是否编译完成。可能需要一些时间才能完成。
分类器完成编译后，它应该会显示 分类器 ID 值。示例：3d84bfx43-nlc-10356

将以下文本复制到 XML 文件。在您看到 CLASSIFIER_ID_GOES_HERE 更改为您的分类器 ID 的位置。

<?xml version="1.0" encoding="UTF-8"?>
<dialog xsi:noNamespaceSchemaLocation="WatsonDialogDocument_1.1.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
    <flow>
        <folder label="Main">
            <output>
                <prompt selectionType="RANDOM">
                    <item>Enter your weather related question.</item>
                </prompt>
                <getUserInput>
                    <search ref="folder_200143"/>
                    <default>
                        <output>
                            <prompt selectionType="RANDOM">
                                <item>I couldn't determine what you are asking about.</item>
                            </prompt>
                        </output>
                    </default>
                </getUserInput>
            </output>
        </folder>
        <folder label="Library">
            <folder label="NLC Intents" id="folder_200143">
                <input isAutoLearnCandidate="false" isRelatedNodeCandidate="true">
                    <grammar>
                        <item>conditions</item>
                    </grammar>
                    <output>
                        <prompt selectionType="RANDOM">
                            <item>I believe you are asking about conditions. </item>
                        </prompt>
                    </output>
                </input>
                <input>
                    <grammar>
                        <item>temperature</item>
                    </grammar>
                    <output>
                        <prompt selectionType="RANDOM">
                            <item>I believe you are asking about temperture. </item>
                        </prompt>
                    </output>
                </input>
            </folder>
        </folder>
        <folder label="Global"/>
        <folder label="Concepts"/>
    </flow>
    <constants>
        <var_folder name="Home"/>
    </constants>
    <variables>
        <var_folder name="Home">
            <var name="CLASSIFIER_CLASS_0" type="TEXT" description="auto-created"/>
            <var name="CLASSIFIER_CONF_0" type="TEXT" description="auto-created"/>
            <var name="CLASSIFIER_CLASS_1" type="TEXT" description="auto-created"/>
            <var name="CLASSIFIER_CONF_1" type="TEXT" description="auto-created"/>
        </var_folder>
    </variables>
    <settings>
        <setting name="AUTOLEARN" type="USER">false</setting>
        <setting name="LANGUAGE" type="USER">en-US</setting>
        <setting name="RESPONSETIME" type="USER">-2</setting>
        <setting name="MAXAUTOLEARNITEMS" type="USER">4</setting>
        <setting name="NUMAUTOSETRELATED" type="USER">0</setting>
        <setting name="TIMEZONEID" type="USER">Australia/Sydney</setting>
        <setting name="AUTOSETRELATEDNODEID" type="USER">0</setting>
        <setting name="INPUTMASKTYPE" type="USER">0</setting>
        <setting name="CONCEPTMATCHING" type="USER">0</setting>
        <setting name="DNR_NODE_ID">-15</setting>
        <setting name="MULTISENT">0</setting>
        <setting name="USE_CONCEPTS">3</setting>
        <setting name="ENTITIES_SCOPE">3</setting>
        <setting name="USER_LOGGING">2</setting>
        <setting name="USE_TRANSLATIONS">3</setting>
        <setting name="USE_STOP_WORDS">3</setting>
        <setting name="USE_SPELLING_CORRECTIONS">3</setting>
        <setting name="USE_AUTOMATIC_STOPWORDS_DETECTION">0</setting>
        <setting name="PLATFORM_VERSION">10.1</setting>
        <setting name="UI_COLOUR"></setting>
        <setting name="PARENT_ACCOUNT"></setting>
        <setting name="AL_NONE_LABEL">None of the above</setting>
        <setting name="CLS_SEARCH_MODE">0</setting>
        <setting name="CLS_MODEL">0</setting>
        <setting name="CLS_ENDPOINT"></setting>
        <setting name="CLS_USERNAME"></setting>
        <setting name="CLS_PASSWORD"></setting>
        <setting name="CLS_MODELNAME">CLASSIFIER_ID_GOES_HERE</setting>
        <setting name="CLS_ADVANCED_SETTINGS">false</setting>
        <setting name="CLS_MAXNBEST">3</setting>
        <setting name="CLS_USE_OFFTOPIC">false</setting>
        <setting name="DEFAULT_DNR_RETURN_POINT_CANDIDATE">-1</setting>
    </settings>
    <specialSettings>
        <specialSetting label="DNR Join Statement">
            <variations/>
        </specialSetting>
        <specialSetting label="AutoLearn Statement">
            <variations/>
        </specialSetting>
    </specialSettings>
</dialog>

将该文件上传到您的对话服务并进行测试。

Watson NLC 服务与对话服务的集成示例

Integration example of the Watson NLC service with the Dialog service

ibm-watson

watson-dialog