技术领域technical field
本发明涉及通信领域，特别是指一种即时通讯方法、装置、终端设备和系统。The present invention relates to the communication field, in particular to an instant messaging method, device, terminal equipment and system.
背景技术Background technique
随着互联网和移动互联网的发展，即时通讯已成为人们在线交流的主要平台，如QQ和MSN，各自拥有数亿用户。但其主流的交流方式是以文字和语音的形式为主。用图片进行表达和交流的情况仅体现在：聊天或发表文章时应用的非个性化卡通形象表情，卡通形式的礼物或照片。这种图像表达形式，是非个性化的，即没有用户本人的形象参与到图像中进行的表达，使图像不能丰富准确地表达用户的意思，而且也无法体现用户本人在即时通讯工具中使用的图像中的参与。With the development of the Internet and mobile Internet, instant messaging has become the main platform for people to communicate online, such as QQ and MSN, each with hundreds of millions of users. But its mainstream communication method is mainly in the form of text and voice. The use of pictures to express and communicate is only reflected in: non-personalized cartoon emoticons used in chatting or publishing articles, gifts or photos in cartoon form. This form of image expression is non-personalized, that is, there is no image of the user participating in the expression in the image, so that the image cannot express the meaning of the user richly and accurately, and it cannot reflect the image used by the user himself in the instant messaging tool. participation in.
而且，当前图片的使用都是用户手动拼接图片或扫描上传人工画好的图片、照片或者卡通画。人们在表达自己的意思的时候，如果有配图需求，则需要通过在网上或自己的图库中找到自己满意的图片。这样，一是效率低下，二是很难找到自己满意的图片。通常，图片和文字不相匹配，也达不到图文并茂的效果。Moreover, the current use of pictures is that users manually stitch pictures or scan and upload artificially drawn pictures, photos or cartoons. When people express themselves, if they need pictures, they need to find pictures they are satisfied with online or in their own gallery. In this way, one is inefficient, and the other is that it is difficult to find a picture that you are satisfied with. Usually, pictures and text do not match, and the effect of both pictures and texts cannot be achieved.
发明内容Contents of the invention
本发明要解决的技术问题是提供一种即时通讯方法、装置、终端设备和系统，可以实现图像随输入的文字即时显示的效果，且该图像是与输入的文字的语义相匹配的图像。The technical problem to be solved by the present invention is to provide an instant messaging method, device, terminal equipment and system, which can realize the effect of real-time display of an image along with the input text, and the image is an image that matches the semantics of the input text.
为解决上述技术问题，本发明的实施例提供一种即时通讯方法，应用于一通讯平台，包括：In order to solve the above technical problems, an embodiment of the present invention provides an instant messaging method applied to a communication platform, including:
从图像元素库中调取一第一图像元素；calling a first image element from the image element library;
通过所述即时通讯平台的输入平台获得输入的文字；Obtain the input text through the input platform of the instant messaging platform;
确定后一时刻输入的文字与前一时刻输入的文字组成的具有一确定语义的第一特征词；Determining the first feature word with a definite semantic meaning formed by the text input at the next moment and the text input at the previous moment;
从所述图像元素库中获得与所述第一特征词相匹配的第二图像元素，其中，所述第二图像元素是所述第一图像元素的个性化图像元素；obtaining a second image element matching the first feature word from the image element library, wherein the second image element is a personalized image element of the first image element;
将所述第二图像元素对应的图像即时输出显示。Immediately output and display the image corresponding to the second image element.
其中，即时通讯方法还包括：Among them, instant messaging methods also include:
在确定第一特征词后，根据即时输入的文字，再确定第二特征词；After determining the first feature word, determine the second feature word according to the text input immediately;
所述图像元素库中获得与所述第二特征词相匹配的第三图像元素；A third image element matching the second feature word is obtained from the image element library;
将所述第三图像元素对应的图像，与前一时刻输出显示的第二图像元素对应的图像，组合成一新的图像；Combining the image corresponding to the third image element and the image corresponding to the second image element output and displayed at the previous moment into a new image;
将所述新的图像即时输出显示。Immediately output and display the new image.
其中，将所述第三图像元素对应的图像，与前一时刻输出显示的第二图像元素对应的图像，组合成一新的图像的步骤包括：Wherein, the step of combining the image corresponding to the third image element and the image corresponding to the second image element output and displayed at the previous moment into a new image includes:
按照所述第二特征词与第一特征词之间的语义关系，确定所述第二图像元素与所述第三图像元素之间的组合顺序；According to the semantic relationship between the second feature word and the first feature word, determine the combination sequence between the second image element and the third image element;
按照所述组合顺序，将所述第二图像元素对应的图像与所述第三图像元素对应的图像组合成新的图像。According to the combination sequence, the image corresponding to the second image element and the image corresponding to the third image element are combined into a new image.
其中，按照所述组合顺序，将所述第二图像元素对应的图像与所述第三图像元素对应的图像组合成新的图像的步骤包括：Wherein, according to the combination order, the step of combining the image corresponding to the second image element and the image corresponding to the third image element into a new image includes:
按照所述组合顺序，依次获得所述组合顺序中，与所述第二图像元素对应的第一显示区域，以及与所述第三图像元素对应的第二显示区域；According to the combination sequence, the first display area corresponding to the second image element and the second display area corresponding to the third image element in the combination sequence are sequentially obtained;
按照所述第一显示区域确定的位置，将所述第二图像元素对应的图像显示在所述第一显示区域中，并按照所述第二显示区域确定的位置，将所述第三图像元素对应的图像显示在所述第二显示区域中；Display the image corresponding to the second image element in the first display area according to the position determined in the first display area, and display the image corresponding to the third image element in accordance with the position determined in the second display area a corresponding image is displayed in the second display area;
将所有显示区域中显示的图像元素组合成所述新的图像。Combining image elements displayed in all display areas to form the new image.
其中，即时通讯方法还包括：Among them, instant messaging methods also include:
将即时输出显示的图像发送给网络端的服务器，所述即时输出显示的图像中具有与输入的文字同步显示的文字框。The image for immediate output and display is sent to the server at the network end, and the image for immediate output and display has a text box displayed synchronously with the input text.
其中，将即时输出显示的图像发送给网络端的服务器的步骤包括：Wherein, the steps of sending the image displayed by the instant output to the server on the network side include:
将即时输出显示的图像以个性化封装方式，发送给网络端的服务器。Send the image displayed by the instant output to the server on the network side in a personalized package.
其中，所述图像元素库中的图像元素包括：第一人称相应的特征词对应的图像元素或者所述第一人称相应的特征词对应的图像元素的个性化图像元素；Wherein, the image elements in the image element library include: the image elements corresponding to the characteristic words corresponding to the first person or the personalized image elements corresponding to the image elements corresponding to the characteristic words corresponding to the first person;
所述图像元素为：平面图像、动态图像和/或三维图像。The image elements are: plane images, dynamic images and/or three-dimensional images.
本发明的实施例还提供一种即时通讯装置，包括：Embodiments of the present invention also provide an instant messaging device, including:
调取模块，用于从图像元素库中调取一第一图像元素；A calling module, used to call a first image element from the image element library;
输入模块，用于通过所述即时通讯平台的输入平台获得输入的文字；The input module is used to obtain the input text through the input platform of the instant messaging platform;
第一确定模块，用于确定后一时刻输入的文字与前一时刻输入的文字组成的具有一确定语义的第一特征词；The first determination module is used to determine the first feature word with a certain semantic meaning formed by the input text at the next moment and the input text at the previous moment;
第一匹配模块，用于从所述图像元素库中获得与所述第一特征词相匹配的第二图像元素，其中，所述第二图像元素是所述第一图像元素的个性化图像元素；A first matching module, configured to obtain a second image element matching the first feature word from the image element library, wherein the second image element is a personalized image element of the first image element ;
输出模块，用于将所述第二图像元素对应的图像即时输出显示。An output module, configured to output and display the image corresponding to the second image element in real time.
其中，即时通讯装置还包括：Among them, the instant messaging device also includes:
第二确定模块，用于在确定第一特征词后，根据即时输入的文字，再确定第二特征词；The second determining module is used to determine the second characteristic word according to the text input immediately after determining the first characteristic word;
第二匹配模块，所述图像元素库中获得与所述第二特征词相匹配的第三图像元素；In the second matching module, a third image element matching the second feature word is obtained from the image element library;
图像处理模块，用于将所述第三图像元素对应的图像，与前一时刻输出显示的第二图像元素对应的图像，组合成一新的图像；An image processing module, configured to combine the image corresponding to the third image element and the image corresponding to the second image element output and displayed at the previous moment into a new image;
所述输出模块进一步用于将所述新的图像即时输出显示。The output module is further configured to output and display the new image immediately.
其中，即时通讯装置还包括：Among them, the instant messaging device also includes:
网络模块，用于将即时输出显示的图像发送给网络端的服务器；和/或The network module is used to send the image displayed by the immediate output to the server on the network side; and/or
更新模块，用于对所述图像元素库的图像元素进行添加、修改或者删除。The update module is used to add, modify or delete the image elements in the image element library.
本发明的实施例还提供一种终端设备，包括：显示模块，还包括：如上所述的即时通讯装置；其中，所述显示模块用于显示新的图像。An embodiment of the present invention also provides a terminal device, including: a display module, and further includes: the instant messaging device as described above; wherein, the display module is used to display a new image.
本发明的实施例还提供一种即时通讯系统，包括：终端设备和服务器，Embodiments of the present invention also provide an instant messaging system, including: a terminal device and a server,
所述终端设备从位于所述服务器中的图像元素库中调取一第一图像元素，并通过所述即时通讯平台的输入平台获得输入的文字，并确定后一时刻输入的文字与前一时刻输入的文字组成的具有一确定语义的第一特征词，并将所述第一特征词传输给所述服务器；The terminal device retrieves a first image element from the image element library located in the server, and obtains the input text through the input platform of the instant messaging platform, and determines the difference between the input text at the next moment and the text at the previous moment. A first feature word with a certain semantic meaning formed by the input text, and transmitting the first feature word to the server;
所述服务器从所述图像元素库中获得与所述第一特征词相匹配的第二图像元素，其中，所述第二图像元素是所述第一图像元素的个性化图像元素，并将所述第二图像元素输出至所述终端设备；The server obtains a second image element matching the first feature word from the image element library, wherein the second image element is a personalized image element of the first image element, and the outputting the second image element to the terminal device;
所述终端设备将所述第二图像元素对应的图像即时输出显示。The terminal device outputs and displays the image corresponding to the second image element in real time.
其中，所述终端设备还用于在确定第一特征词后，根据即时输入的文字，再确定第二特征词，并将所述第二特征词传输给所述服务器；Wherein, the terminal device is further configured to determine the second characteristic word according to the immediately input text after determining the first characteristic word, and transmit the second characteristic word to the server;
所述服务器还用于从所述图像元素库中获得与所述第二特征词相匹配的第三图像元素，并将所述第三图像元素对应的图像，与前一时刻输出显示的第二图像元素对应的图像，组合成一新的图像，并将所述新的图像输出至所述终端设备；The server is further configured to obtain a third image element matching the second feature word from the image element library, and output and display the image corresponding to the third image element with the second image element displayed at the previous moment. Combining the images corresponding to the image elements into a new image, and outputting the new image to the terminal device;
所述终端设备将所述新的图像即时输出显示。The terminal device outputs and displays the new image immediately.
本发明的上述技术方案的有益效果如下：The beneficial effects of above-mentioned technical scheme of the present invention are as follows:
上述方案中，通过将即时输入的文字即时进行语义分析，得到特征词，并从图像元素库中获得与该特征词匹配的图像元素，并即时输出该图像元素，从而实现图像随输入的文字即时显示的效果，且该图像是与输入的文字的语义相匹配的图像。In the above scheme, the feature word is obtained by performing semantic analysis on the text input immediately, and the image element matching the feature word is obtained from the image element library, and the image element is output in real time, so that the image is real-time with the input text. The effect displayed, and the image is an image that matches the semantics of the input text.
附图说明Description of drawings
图1为本发明的实施例即时通讯方法的流程示意图；Fig. 1 is a schematic flow chart of an instant messaging method according to an embodiment of the present invention;
图2为图1所示方法在手机终端上的应用的第一实施例示意图；Fig. 2 is the schematic diagram of the first embodiment of the application of the method shown in Fig. 1 on the mobile phone terminal;
图3为接续图2所示实例的另一实施例示意图；Fig. 3 is a schematic diagram of another embodiment continuing the example shown in Fig. 2;
图4为本发明的方法中将生成的新的图像结合其它图像元素形成虚拟化礼物的第一实例图；Fig. 4 is a first example diagram of combining the generated new image with other image elements to form a virtual gift in the method of the present invention;
图5为本发明的方法中将生成的新的图像结合其它图像元素形成虚拟化礼物的第二实例图；Fig. 5 is a second example diagram of combining the generated new image with other image elements to form a virtual gift in the method of the present invention;
图6为本发明的实施例即时通讯装置的一实施例结构示意图；FIG. 6 is a schematic structural diagram of an embodiment of an instant messaging device according to an embodiment of the present invention;
图7为本发明的实施例即进通讯装置的另一实施例结构示意图；FIG. 7 is a schematic structural diagram of another embodiment of the instant communication device according to the embodiment of the present invention;
图8为本发明的实施例移动终端的结构示意图；FIG. 8 is a schematic structural diagram of a mobile terminal according to an embodiment of the present invention;
图9为本发明的即时通讯系统的实施例结构示意图。FIG. 9 is a schematic structural diagram of an embodiment of the instant messaging system of the present invention.
具体实施方式Detailed ways
为使本发明要解决的技术问题、技术方案和优点更加清楚，下面将结合附图及具体实施例进行详细描述。In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.
如图1所示，本发明的实施例提供一种即时通讯方法，应用于一通讯平台，包括：As shown in Figure 1, the embodiment of the present invention provides a kind of instant communication method, is applied to a communication platform, comprises:
步骤11，从图像元素库中调取一第一图像元素；Step 11, calling a first image element from the image element library;
步骤12，通过所述即时通讯平台的输入平台获得输入的文字；Step 12, obtaining the input text through the input platform of the instant messaging platform;
步骤13，确定后一时刻输入的文字与前一时刻输入的文字组成的具有一确定语义的第一特征词；Step 13, determining the first feature word with a certain semantic meaning formed by the input text at the next moment and the input text at the previous moment;
步骤14，从所述图像元素库中获得与所述第一特征词相匹配的第二图像元素，其中，所述第二图像元素是所述第一图像元素的个性化图像元素；Step 14, obtaining a second image element matching the first feature word from the image element library, wherein the second image element is a personalized image element of the first image element;
步骤15，将所述第二图像元素对应的图像即时输出显示。Step 15, immediately output and display the image corresponding to the second image element.
本发明的该实施例通过将即时输入的文字即时进行语义分析，得到特征词，并从图像元素库中获得与该特征词匹配的图像元素，并即时输出该图像元素，从而实现图像随输入的文字即时显示的效果，且该图像是与输入的文字的语义相匹配的图像。In this embodiment of the present invention, the feature words are obtained by performing semantic analysis on the text input immediately, and the image elements matching the feature words are obtained from the image element library, and the image elements are output in real time, thereby realizing the image with the input The text is displayed instantly, and the image is an image that matches the semantics of the entered text.
在上述实施例中，输入平台输入的文字具体可以是通过文字输入平台输入的，也可以是通过语音输入平台输入的，当是语音输入平台时，文字是经过语音识别工具识别后的文字，或者是在语音识别工具识别后，再进一步由用户确认后的文字。In the above-mentioned embodiments, the text input by the input platform may be input through the text input platform, or may be input through the voice input platform. When it is a voice input platform, the text is the text recognized by the voice recognition tool, or It is a text that is further confirmed by the user after being recognized by the voice recognition tool.
在本发明的另一实施例中，包括上述步骤11-15的基础上，还包括：In another embodiment of the present invention, on the basis of including the above steps 11-15, it also includes:
步骤16，在确定第一特征词后，根据即时输入的文字，再确定第二特征词；Step 16, after determining the first characteristic word, determine the second characteristic word according to the text input immediately;
步骤17，所述图像元素库中获得与所述第二特征词相匹配的第三图像元素；Step 17, obtaining a third image element matching the second feature word from the image element library;
步骤18，将所述第三图像元素对应的图像，与前一时刻输出显示的第二图像元素对应的图像，组合成一新的图像；Step 18, combining the image corresponding to the third image element and the image corresponding to the second image element output and displayed at the previous moment into a new image;
步骤19，将所述新的图像即时输出显示。Step 19, output and display the new image immediately.
具体地，如图2所示，首先点击一下图像元素输入按钮(如图2中的最左边的第一幅图)，系统即可从图像元素库中调取第一图像元素(如图2中的从左边起的第二幅图)，通过输入平台输入文字“今天晚上吃鱼火锅又香又辣太好吃了”，当顺序输入上述一句文字时，是按照每输入一个字，就进行语义分析，判断当前刚输入的文字与前一文字是否能够具有一确定语义，若有，则可以将当前刚输入的文字与前一文字组成一特征词，并即时从图像元素库中即时查找与该特征词相匹配的图像元素，若查找到，则将该图像元素调出并即时输出显示；上述语句中，如当输入到文字“上”时，可以确定一特征词为“今天晚上”，则从图像元素库中调出与该特征词匹配的一图像元素，即图2中从左边起的第四幅图(即最右边的图)中的背景层；当输入到“锅”时，可以匹配到“吃鱼火锅”的特征词，则从图像元素库中调出与该特征词匹配的图像元素，即最先调取的第一图像元素对应的身体层的图像元素；依次类推，可以得到表情层的图像元素，对应的特征词应当时“太好吃了”；最后判断该输入的语句无主语，默认为第一人称，即用户事先调取的第一人称对应的第一图像元素(如图2中的从左边起的第二幅图的人物头像)，添加该人物头像对应的个性化头像，即添加第一图像元素对应的头像层的图像元素。Specifically, as shown in Figure 2, first click the image element input button (the first picture on the far left in Figure 2), and the system can call the first image element from the image element library (as shown in Figure 2 The second picture from the left of the above), through the input platform, input the text "Tonight, the fish hot pot is delicious, spicy and delicious". Analyze and judge whether the currently just-input text and the previous text can have a definite semantic meaning. If so, the current just-input text and the previous text can be combined into a feature word, and the feature word can be instantly searched from the image element library If the matching image element is found, the image element will be called out and output and displayed in real time; in the above statement, if it is input into the text "up", it can be determined that a characteristic word is "tonight", then from the image An image element matched with the feature word is called out in the element library, i.e. the background layer in the fourth picture from the left (i.e. the rightmost figure) in Figure 2; when input to "pot", it can be matched to For the feature word of "eating fish hot pot", the image element matching the feature word is called out from the image element library, that is, the image element of the body layer corresponding to the first image element that is called first; and so on, the expression can be obtained The image element of the first layer, the corresponding feature word should be "too delicious"; finally, it is judged that the input sentence has no subject, and the default is the first person, that is, the first image element corresponding to the first person called by the user in advance (as shown in Figure 2 The character portrait in the second picture from the left), add the personalized portrait corresponding to the character portrait, that is, add the image element of the portrait layer corresponding to the first image element.
同时，在上述实施例中，还可以包括：在输入时，即时输出显示所述输入的文字。所以即时输出显示的图像中，会有一个文字框，该文字框中的文字内容与输入平台的输入框中输入的文字同步。At the same time, in the above embodiment, it may further include: when inputting, immediately outputting and displaying the inputted text. Therefore, in the image displayed by the real-time output, there will be a text box, and the text content in the text box is synchronized with the text entered in the input box of the input platform.
接着，再点击一下图像元素输入按钮(如图3中的最左边的第一幅图)，系统即可从图像元素库中调取一新的图像元素(如图3中的从左边起的第二幅图)，通过输入平台输入文字“真给力”，系统会按照上述图2所示相同的方法生成如图3中的从左边起第四幅图，接着输入“最近上火，不敢吃辣的东西”，生成如图3中的从左边起第五幅图，同时输入的文字内容也会同步出现在新的图像的文字框内。Then, click the image element input button (the first picture on the far left as shown in Figure 3) again, and the system can call a new image element from the image element storehouse (the first picture from the left in Figure 3). Two pictures), enter the text "true to force" through the input platform, the system will generate the fourth picture from the left in Figure 3 according to the same method as shown in Figure 2 above, and then input "Recently got angry, dare not eat "Spicy stuff" to generate the fifth image from the left in Figure 3, and the input text content will also appear in the text box of the new image synchronously.
在上述实施例中，其中，上述步骤18可以包括：In the above embodiment, wherein, the above step 18 may include:
步骤181，按照所述第二特征词与第一特征词之间的语义关系，确定所述第二图像元素与所述第三图像元素之间的组合顺序；Step 181, according to the semantic relationship between the second feature word and the first feature word, determine the combination sequence between the second image element and the third image element;
步骤182，按照所述组合顺序，将所述第二图像元素对应的图像与所述第三图像元素对应的图像组合成新的图像。Step 182: Combine the image corresponding to the second image element and the image corresponding to the third image element into a new image according to the combination sequence.
进一步地，步骤182可以包括：Further, step 182 may include:
步骤1821，按照所述组合顺序，依次获得所述组合顺序中，与所述第二图像元素对应的第一显示区域，以及与所述第三图像元素对应的第二显示区域；Step 1821, according to the combination order, sequentially obtain the first display area corresponding to the second image element and the second display area corresponding to the third image element in the combination order;
步骤1822，按照所述第一显示区域确定的位置，将所述第二图像元素对应的图像显示在所述第一显示区域中，并按照所述第二显示区域确定的位置，将所述第三图像元素对应的图像显示在所述第二显示区域中；Step 1822: Display the image corresponding to the second image element in the first display area according to the position determined in the first display area, and display the image corresponding to the second image element in the first display area according to the position determined in the second display area. The images corresponding to the three image elements are displayed in the second display area;
步骤1823，将所有显示区域中显示的图像元素组合成所述新的图像。Step 1823, combine the image elements displayed in all display areas into the new image.
如：身体层对应的图像元素都固定在一个区域范围内。头像层对应的图像元素也固定出现身体层上方的一个范围内，从而达到身体与头部衔接的吻合。For example, the image elements corresponding to the body layer are all fixed within a range. The image elements corresponding to the avatar layer also appear fixedly in a range above the body layer, so as to achieve the matching between the body and the head.
每个身体层对应的图像元素的固定点都在图中有一个坐标值，每次生成图像时，头像层和表情层的图像元素会自动找到该身体素材的固定点坐标，并按坐标参数与之衔接。The fixed point of the image element corresponding to each body layer has a coordinate value in the figure. Every time an image is generated, the image elements of the avatar layer and the expression layer will automatically find the fixed point coordinates of the body material, and match them according to the coordinate parameters. the connection.
在上述所有实施例中，所述方法还可以进一步包括：In all the above-mentioned embodiments, the method may further include:
将即时输出显示的图像发送给网络端的服务器，所述即时输出显示的图像中具有与输入的文字同步显示的文字框，即输入的文字也即时输出显示，以达到图文并茂的效果。Send the image for real-time output and display to the server at the network end. The image for real-time output and display has a text box displayed synchronously with the input text, that is, the input text is also output and displayed in real time, so as to achieve the effect of both pictures and text.
优选的，将即时输出显示的图像发送给网络端的服务器的步骤包括：Preferably, the step of sending the image displayed by the instant output to the server on the network side includes:
将即时输出显示的图像以个性化封装方式，发送给网络端的服务器，如可以将即时输出显示的图像以礼物封装的方式通过网络端的服务器，发送给另一用户的终端设备，也可以以其它个性化封装方式进行发送，以提高用户的满意度和使用乐趣。Send the image displayed by the instant output to the server on the network side in a personalized package. For example, the image displayed on the instant output can be sent to the terminal device of another user through the server on the network side in the form of a gift package, or it can be packaged in other ways. Send it in a packaged way to improve user satisfaction and enjoyment.
具体地，如图4和图5所示，其中，图4是先选择礼物(如是一束花)，然后，将该选择的礼物与当前场景中的角色(生成的包括人物的个性化风格的新的图像)进行组合，得到一以虚拟礼物形式封装的新的图像；其中，该选择的礼物可以是根据输入的文字“花”从图像元素库中匹配到的图像元素，也可以是用户主动选择的一图像元素；图5与图4的区别在于，图5中，先将包括人物的个性化风格的新的图像作为当前场景中的角色，然后再选择礼物，再进行合成，形成虚拟礼物。当然，本发明的实施例并不限于上述图4和图5所示的方式，与当前场景中角色进行组合的礼物对应的图像元素还可以是如已经制作好的蛋糕图像元素，还可以是按照如上述方法生成的包括其它人物的个性化图像对应的图像元素。Specifically, as shown in Fig. 4 and Fig. 5, wherein, in Fig. 4, a gift (such as a bouquet of flowers) is first selected, and then the selected gift is combined with the character in the current scene (the generated personalized style including the character) new image) to get a new image packaged in the form of a virtual gift; wherein, the selected gift can be an image element matched from the image element library according to the input text "flower", or it can be the user's initiative An image element selected; the difference between Figure 5 and Figure 4 is that in Figure 5, the new image including the character's personalized style is first used as the character in the current scene, and then the gift is selected and synthesized to form a virtual gift . Certainly, the embodiment of the present invention is not limited to the manners shown in Fig. 4 and Fig. 5 above, and the image element corresponding to the gift combined with the characters in the current scene may also be a cake image element that has already been made, or it may be according to The image elements corresponding to the personalized images of other characters are included in the above-mentioned method.
优选地，在上述所有实施例中，所述图像元素库中的图像元素包括：第一人称相应的特征词对应的图像元素或者所述第一人称相应的特征词对应的图像元素的个性化图像元素；如在本地客户端的即进通讯平台中，可以获得包括用户本人头像对应的图像元素或者该用户本人头像对应的个性化图像元素，即以各种卡通形象为风格生成的用户本人头像的个性化图像元素。Preferably, in all the above-mentioned embodiments, the image elements in the image element library include: image elements corresponding to first-person corresponding feature words or personalized image elements corresponding to first-person corresponding feature words; For example, in the instant communication platform of the local client, you can obtain image elements corresponding to the user's avatar or personalized image elements corresponding to the user's avatar, that is, personalized images of the user's avatar generated in the style of various cartoon images element.
所述图像元素为：平面图像、动态图像和/或三维图像。The image elements are: plane images, dynamic images and/or three-dimensional images.
本发明的上述实施例，通过使用户提供人像照片，通过计算机处理，把照片中的人物转换成漫画中的人物。当用户输入文字或录入语音后，根据语义分析系统，从图像元素库中搜到与输入的文字中的特征词相应的图像元素，并按照各个特征词之间的语义关系，确定图像元素之间的组合顺序，并按照该组合顺序，生成一副完整的新的图像，从而实现了使用户在电脑上或手机上通过打字或说话就能生成与描述内容相符的图像，且文字同时出现在图像中的对话框内。然后把生成的图像通过网络发送给对方，从而进行交流，真正做到图文并茂。其中，图像元素可以包括人物动作，物品，背景，表情等。此外，用户还可以输入不同的人物名称更换画中的角色。用户可以自己创作素材。通过载入照片，对照片进行风格化处理后，成为图画中的一部分。用户还可以拥有即时通讯所拥有的其他功能。In the above-mentioned embodiment of the present invention, the characters in the photos are converted into the characters in the comics by making the user provide portrait photos, and through computer processing. After the user enters text or voice, according to the semantic analysis system, the image elements corresponding to the feature words in the input text are searched from the image element library, and the image elements are determined according to the semantic relationship between each feature word. Combination sequence, and according to the combination sequence, a complete new image is generated, so that the user can generate an image that matches the description by typing or speaking on the computer or mobile phone, and the text appears in the image at the same time in the dialog box. Then send the generated images to the other party through the network, so as to communicate, and truly achieve both pictures and texts. Wherein, the image elements may include character actions, items, backgrounds, expressions, and the like. In addition, users can also enter different character names to replace the characters in the painting. Users can create their own material. By loading a photo, stylize the photo and become part of the picture. Users can also have other functions that instant messaging has.
如图6所示，本发明的实施例还提供一种即时通讯装置，包括：As shown in Figure 6, an embodiment of the present invention also provides an instant messaging device, including:
调取模块41，用于从图像元素库中调取一第一图像元素；Calling module 41, used to call a first image element from the image element library;
输入模块42，用于通过所述即时通讯平台的输入平台获得输入的文字；The input module 42 is used to obtain the input text through the input platform of the instant messaging platform;
第一确定模块43，用于确定后一时刻输入的文字与前一时刻输入的文字组成的具有一确定语义的第一特征词；The first determination module 43 is used to determine the first feature word with a certain semantic meaning formed by the text input at the next moment and the text input at the previous moment;
第一匹配模块44，用于从所述图像元素库中获得与所述第一特征词相匹配的第二图像元素，其中，所述第二图像元素是所述第一图像元素的个性化图像元素；The first matching module 44 is configured to obtain a second image element matching the first feature word from the image element library, wherein the second image element is a personalized image of the first image element element;
输出模块45，用于将所述第二图像元素对应的图像即时输出显示。The output module 45 is configured to output and display the image corresponding to the second image element in real time.
该装置实施例同样通过将即时输入的文字即时进行语义分析，得到特征词，并从图像元素库中获得与该特征词匹配的图像元素，并即时输出该图像元素，从而实现图像随输入的文字即时显示的效果，且该图像是与输入的文字的语义相匹配的图像。The embodiment of the device also performs semantic analysis on the instant input text to obtain the feature word, and obtains the image element matching the feature word from the image element library, and outputs the image element in real time, thereby realizing that the image follows the input text. The effect is displayed in real time, and the image is an image that matches the semantics of the input text.
进一步地，如图7所示，在上述图6所示实施例的基础上，上述即时通讯装置还可以包括：Further, as shown in FIG. 7, on the basis of the above-mentioned embodiment shown in FIG. 6, the above-mentioned instant messaging device may further include:
第二确定模块46，用于在确定第一特征词后，根据即时输入的文字，再确定第二特征词；The second determination module 46 is used to determine the second characteristic word according to the text input immediately after determining the first characteristic word;
第二匹配模块47，所述图像元素库中获得与所述第二特征词相匹配的第三图像元素；The second matching module 47, the third image element matched with the second feature word is obtained in the image element library;
图像处理模块48，用于将所述第三图像元素对应的图像，与前一时刻输出显示的第二图像元素对应的图像，组合成一新的图像；An image processing module 48, configured to combine the image corresponding to the third image element and the image corresponding to the second image element output and displayed at the previous moment into a new image;
所述输出模块45进一步用于将所述新的图像即时输出显示。The output module 45 is further configured to output and display the new image immediately.
图像处理模块48具体用于，按照所述第二特征词与第一特征词之间的语义关系，确定所述第二图像元素与所述第三图像元素之间的组合顺序；并按照所述组合顺序，将所述第二图像元素对应的图像与所述第三图像元素对应的图像组合成新的图像。The image processing module 48 is specifically configured to, according to the semantic relationship between the second feature word and the first feature word, determine the combination sequence between the second image element and the third image element; and according to the Combining sequence, combining the image corresponding to the second image element and the image corresponding to the third image element into a new image.
进一步地，按照所述组合顺序，依次获得所述组合顺序中，与所述第二图像元素对应的第一显示区域，以及与所述第三图像元素对应的第二显示区域；并按照所述第一显示区域确定的位置，将所述第二图像元素对应的图像显示在所述第一显示区域中，并按照所述第二显示区域确定的位置，将所述第三图像元素对应的图像显示在所述第二显示区域中；并将所有显示区域中显示的图像元素组合成所述新的图像。Further, according to the combination sequence, the first display area corresponding to the second image element and the second display area corresponding to the third image element in the combination sequence are sequentially obtained; and according to the Display the image corresponding to the second image element in the first display area at the position determined in the first display area, and display the image corresponding to the third image element according to the position determined in the second display area displaying in the second display area; and combining image elements displayed in all display areas into the new image.
如：身体层对应的图像元素都固定在一个区域范围内。头像层对应的图像元素也固定出现身体层上方的一个范围内，从而达到身体与头部衔接的吻合。For example, the image elements corresponding to the body layer are all fixed within a range. The image elements corresponding to the avatar layer also appear fixedly in a range above the body layer, so as to achieve the matching between the body and the head.
每个身体层对应的图像元素的固定点都在图中有一个坐标值，每次生成图像时，头像层和表情层的图像元素会自动找到该身体素材的固定点坐标，并按坐标参数与之衔接。The fixed point of the image element corresponding to each body layer has a coordinate value in the figure. Every time an image is generated, the image elements of the avatar layer and the expression layer will automatically find the fixed point coordinates of the body material, and match them according to the coordinate parameters. the connection.
进一步地，在上述所有实施例中，即时通讯装置还可以包括：Further, in all the above-mentioned embodiments, the instant messaging device may further include:
网络模块，用于将即时输出显示的图像发送给网络端的服务器；和/或The network module is used to send the image displayed by the immediate output to the server on the network side; and/or
更新模块，用于对所述图像元素库的图像元素进行添加、修改或者删除。The update module is used to add, modify or delete the image elements in the image element library.
其中，所述即时输出显示的图像中具有与输入的文字同步显示的文字框，即输入的文字也即时输出显示，以达到图文并茂的效果；更新时，用户可以对图像元素进行DIY修正，包括各层图像元素的更改、位移、缩放、变换等。Wherein, the image displayed by the instant output has a text box displayed synchronously with the input text, that is, the input text is also output and displayed in real time, so as to achieve the effect of both pictures and text; when updating, the user can DIY correct the image elements, including various Change, displacement, scaling, transformation, etc. of layer image elements.
进一步地，网络模块可以将即时输出显示的图像以个性化封装方式，发送给网络端的服务器，如可以将即时输出显示的图像以礼物封装的方式通过网络端的服务器，发送给另一用户的终端设备，也可以以其它个性化封装方式进行发送，以提高用户的满意度和使用乐趣。Further, the network module can send the image displayed by the instant output to the server at the network end in a personalized packaging manner, for example, the image displayed on the instant output can be sent to the terminal device of another user through the server at the network end in the form of gift packaging , and can also be sent in other personalized packaging methods to improve user satisfaction and enjoyment.
另外，在上述所有实施例中，所述图像元素库中的图像元素包括：第一人称相应的特征词对应的图像元素或者所述第一人称相应的特征词对应的图像元素的个性化图像元素；如在本地客户端的即进通讯平台中，可以获得包括用户本人头像对应的图像元素或者该用户本人头像对应的个性化图像元素，即以各种卡通形象为风格生成的用户本人头像的个性化图像元素；所述图像元素为：平面图像、动态图像和/或三维图像。In addition, in all the above-mentioned embodiments, the image elements in the image element library include: image elements corresponding to the characteristic words corresponding to the first person or personalized image elements corresponding to the image elements corresponding to the characteristic words corresponding to the first person; In the instant communication platform of the local client, you can obtain the image elements corresponding to the user's avatar or the personalized image elements corresponding to the user's avatar, that is, the personalized image elements of the user's avatar generated in the style of various cartoon images ; The image elements are: plane images, dynamic images and/or three-dimensional images.
本发明的上述装置可以是一即时通讯聊天工具，如本发明的实施例对应的图聊工具，可应用于手机的通讯平台，微博平台，PC的通讯平台等。通过打字或语音录入可生成与文字或语音内容相符的漫画(即新的图像)，漫画中的主角是用户自己的形象，用户可DIY自己的形象，并可通过照片创作新的图像元素并应用到创作中去，还可通过画笔对漫画进行手绘，用户可根据提供的模版创作4格及多格漫画，用户可将生成出的漫画发送到即时聊天伙伴，可在图聊工具中共享聊天伙伴发来的图片，用户可进行群聊，即多个用户同时进行图片聊天，用户拥有仅文字聊天的选择。The above-mentioned device of the present invention may be an instant messaging chat tool, such as a picture chat tool corresponding to the embodiment of the present invention, which can be applied to a communication platform of a mobile phone, a microblog platform, a communication platform of a PC, and the like. Comics (that is, new images) that match the text or voice content can be generated by typing or voice input. The protagonist in the comics is the user's own image, and the user can DIY his own image, and can create new image elements through photos and apply them. When it comes to creation, comics can also be hand-painted with a brush. Users can create 4-frame and multi-frame comics according to the provided templates. Users can send the generated comics to instant chat partners, and can share chat partners in the picture chat tool With the pictures sent, users can chat in groups, that is, multiple users chat with pictures at the same time, and users have the option of text chat only.
如图8所示，本发明的实施例还提供一种终端设备60，包括：显示模块49，还包括：如上所述的即时通讯装置；其中，所述显示模块49用于显示新的图像。As shown in FIG. 8 , the embodiment of the present invention also provides a terminal device 60, including: a display module 49, and also includes: the instant messaging device as described above; wherein, the display module 49 is used to display a new image.
该终端设备可以是个人手持设备，如手机等，也可以是个人PC，也可以是其它任何智能设备。The terminal device may be a personal handheld device, such as a mobile phone, or a personal PC, or any other smart device.
如图9所示，本发明的实施例还提供一种即时通讯系统，包括：终端设备和服务器，其中，As shown in FIG. 9, an embodiment of the present invention also provides an instant messaging system, including: a terminal device and a server, wherein,
所述终端设备从位于所述服务器中的图像元素库中调取一第一图像元素，并通过所述即时通讯平台的输入平台获得输入的文字，并确定后一时刻输入的文字与前一时刻输入的文字组成的具有一确定语义的第一特征词，并将所述第一特征词传输给所述服务器；The terminal device retrieves a first image element from the image element library located in the server, and obtains the input text through the input platform of the instant messaging platform, and determines the difference between the input text at the next moment and the text at the previous moment. A first feature word with a certain semantic meaning formed by the input text, and transmitting the first feature word to the server;
所述服务器从所述图像元素库中获得与所述第一特征词相匹配的第二图像元素，其中，所述第二图像元素是所述第一图像元素的个性化图像元素，并将所述第二图像元素输出至所述终端设备；The server obtains a second image element matching the first feature word from the image element library, wherein the second image element is a personalized image element of the first image element, and the outputting the second image element to the terminal device;
所述终端设备将所述第二图像元素对应的图像即时输出显示。The terminal device outputs and displays the image corresponding to the second image element in real time.
其中，所述终端设备还用于在确定第一特征词后，根据即时输入的文字，再确定第二特征词，并将所述第二特征词传输给所述服务器；Wherein, the terminal device is further configured to determine the second characteristic word according to the immediately input text after determining the first characteristic word, and transmit the second characteristic word to the server;
所述服务器还用于从所述图像元素库中获得与所述第二特征词相匹配的第三图像元素，并将所述第三图像元素对应的图像，与前一时刻输出显示的第二图像元素对应的图像，组合成一新的图像，并将所述新的图像输出至所述终端设备；The server is further configured to obtain a third image element matching the second feature word from the image element library, and output and display the image corresponding to the third image element with the second image element displayed at the previous moment. Combining the images corresponding to the image elements into a new image, and outputting the new image to the terminal device;
所述终端设备将所述新的图像即时输出显示。The terminal device outputs and displays the new image immediately.
该系统中，服务器还进一步包括：用户管理模块，图像元素学习模块，以及语义分析模块，其中，用户管理模块实现对多个用户的管理，图像元素学习模块用于对用户在前一段时间内，对相应的图像元素的使用行为进行记录，并将使用最多的图像元素的查找地址进行记录，以便于查找时，能更快速地查找到该图像元素；语义分析模块，用于对用户输入的文字进行主义分析，并确定出相应的特征词，以便于能从图像元素库中匹配到与该特征词相对应的图像元素。In this system, the server further includes: a user management module, an image element learning module, and a semantic analysis module, wherein, the user management module realizes the management of multiple users, and the image element learning module is used to analyze the user's previous period of time, Record the use behavior of the corresponding image elements, and record the search address of the most used image elements, so that the image elements can be found more quickly when searching; the semantic analysis module is used to analyze the text entered by the user Carry out doctrine analysis, and determine the corresponding feature words, so that the image elements corresponding to the feature words can be matched from the image element library.
以上所述是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明所述原理的前提下，还可以作出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。The above description is a preferred embodiment of the present invention, it should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, some improvements and modifications can also be made, and these improvements and modifications can also be made. It should be regarded as the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210062120.5ACN102624648B (en) | 2012-03-09 | 2012-03-09 | Instant messaging method, device and system and terminal equipment |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210062120.5ACN102624648B (en) | 2012-03-09 | 2012-03-09 | Instant messaging method, device and system and terminal equipment |
| Publication Number | Publication Date |
|---|---|
| CN102624648A CN102624648A (en) | 2012-08-01 |
| CN102624648Btrue CN102624648B (en) | 2015-04-08 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210062120.5AExpired - Fee RelatedCN102624648B (en) | 2012-03-09 | 2012-03-09 | Instant messaging method, device and system and terminal equipment |
| Country | Link |
|---|---|
| CN (1) | CN102624648B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104468317B (en)* | 2013-09-16 | 2018-10-12 | 联想(北京)有限公司 | A kind of information processing method and the first electronic equipment |
| CN106020809B (en)* | 2016-05-15 | 2019-03-12 | 快创科技（大连）有限公司 | Online game literature generation system |
| CN106846040B (en)* | 2016-12-22 | 2021-11-09 | 武汉斗鱼网络科技有限公司 | Virtual gift display method and system in live broadcast room |
| WO2018119815A1 (en)* | 2016-12-29 | 2018-07-05 | 深圳前海达闼云端智能科技有限公司 | Image display method and device, and electronic device |
| CN109873751B (en)* | 2019-01-11 | 2020-10-09 | 珠海格力电器股份有限公司 | Group chat voice information processing method and device, storage medium and server |
| CN110490953B (en)* | 2019-07-25 | 2023-04-07 | 维沃移动通信有限公司 | Text-based image generation method, terminal device and medium |
| CN113268663B (en)* | 2021-05-20 | 2023-04-18 | 苏州鱼得水电气科技有限公司 | Download recommendation system and method based on big data |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101453427A (en)* | 2007-11-29 | 2009-06-10 | 悟空数位娱乐实业有限公司 | Animation playing method for real-time communication |
| CN102110304A (en)* | 2011-03-29 | 2011-06-29 | 华南理工大学 | Material-engine-based automatic cartoon generating method |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101453427A (en)* | 2007-11-29 | 2009-06-10 | 悟空数位娱乐实业有限公司 | Animation playing method for real-time communication |
| CN102110304A (en)* | 2011-03-29 | 2011-06-29 | 华南理工大学 | Material-engine-based automatic cartoon generating method |
| Publication number | Publication date |
|---|---|
| CN102624648A (en) | 2012-08-01 |
| Publication | Publication Date | Title |
|---|---|---|
| CN102624648B (en) | Instant messaging method, device and system and terminal equipment | |
| CN102662961B (en) | Method, apparatus and terminal unit for matching semantics with image | |
| US10116598B2 (en) | System and method for increasing clarity and expressiveness in network communications | |
| US9706040B2 (en) | System and method for facilitating communication via interaction with an avatar | |
| JP6306008B2 (en) | System and method for increasing clarity and expressiveness in network communications | |
| CN102110304B (en) | Material-engine-based automatic cartoon generating method | |
| US11165734B1 (en) | Messaging system share-to-chat | |
| WO2014161429A1 (en) | Methods for avatar configuration and realization, client terminal, server, and system | |
| CN102662568B (en) | Method and device for inputting picture | |
| WO2015122993A1 (en) | Methods and apparatuses for animated messaging between messaging participants represented by avatar | |
| US12430812B2 (en) | Text-guided cameo generation | |
| CN106228451A (en) | A kind of caricature chat system | |
| US20140300612A1 (en) | Methods for avatar configuration and realization, client terminal, server, and system | |
| CN112152901A (en) | Virtual image control method and device and electronic equipment | |
| US12254049B2 (en) | Searching augmented reality experiences using visual embeddings | |
| CN102801652A (en) | Method, client and system for adding contact persons through expression data | |
| US20240428481A1 (en) | Generating ground truths for generative ai applications | |
| US20250285351A1 (en) | Augmented reality try-on experience for friend | |
| KR20240091143A (en) | Method and system for generating voice messages with varying effects | |
| US20230127090A1 (en) | Voice note with face tracking | |
| US20250111628A1 (en) | Generating 3d models with texture | |
| US20240371106A1 (en) | Techniques for using 3-d avatars in augmented reality messaging | |
| Youn et al. | A study on UI design of social networking service messenger by using case analysis model | |
| CN102789503A (en) | Method, system and client for transforming image age in instant communication | |
| JP2004070685A (en) | Electronic device and receiving and reproducing method of e-mail with portrait |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20150408 |