CN110032561B - Form construction method and system based on semantics - Google Patents
Form construction method and system based on semantics Download PDFInfo
- Publication number
- CN110032561B CN110032561B CN201910079244.6A CN201910079244A CN110032561B CN 110032561 B CN110032561 B CN 110032561B CN 201910079244 A CN201910079244 A CN 201910079244A CN 110032561 B CN110032561 B CN 110032561B
- Authority
- CN
- China
- Prior art keywords
- analyzed
- controls
- text
- control
- appropriate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
A semantic-based form construction method and system are provided. The method comprises the following steps: receiving a form comprising elements to be analyzed and corresponding original controls; performing semantic analysis on the element to be analyzed and determining whether the element to be analyzed comprises at least one preset field; if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of the fields; if the original control is different from the appropriate control queried in the pre-configured table for each pre-set field, the original control is adjusted to the appropriate control in the table. In various embodiments of the present invention, the element to be analyzed is text, an image, audio or video.
Description
Technical Field
The present application relates generally to data acquisition, and more particularly to the construction of forms in data acquisition.
Background
Forms are an important tool in data acquisition. Form elements or form controls may include text boxes, multi-line text boxes, radio boxes, check boxes, drop down select boxes, file upload boxes, matrix select boxes, form boxes, time/date boxes, sliders, and the like for gathering data entered or selected by a user. The form elements may also include buttons, such as a submit button, a reset button, etc., for user interaction with a web page or APP, etc.
With advances in computer technology, elements in forms are becoming increasingly rich, and not only text, but images (such as product photos, starburst photos, landscapes, specific scenes, etc.), audio (such as conversations, music, etc.), even video (such as product introduction short videos, advertising videos, educational presentations, etc.), etc. may be incorporated into forms. Data collection for these rich elements is a necessary trend.
In data collection by questionnaire, the questionnaire data can also be obtained by using various form elements. In the prior art, there are a wide variety of questionnaire products. The system provides a practical online form tool, and forms such as questionnaire investigation, activity registration, opinion feedback, information registration, online order, examination evaluation and the like are quickly created, so that the data are automatically collected and the working time is saved.
However, in building a questionnaire, the controls are often easily misplaced. For example, in the case of multi-choice semantics, a single choice box is employed, directly resulting in inaccuracy of the acquired data. Also, when forms are built in web pages or various APPs, there are cases where the controls are selected incorrectly, resulting in errors in the data collected.
Accordingly, there is a need in the art for a method and system that can effectively correct misconnection controls. There is also a need for a method and system that can automatically recommend controls efficiently.
Disclosure of Invention
In order to solve the technical problems, the invention provides a form construction scheme based on semantics, which applies a semantic analysis technology, so that the wrong selection control can be effectively corrected, and the control can be automatically recommended in a high-efficiency manner.
According to an embodiment of the present invention, there is provided a semantic-based form construction method including: receiving a form comprising elements to be analyzed and corresponding original controls; performing semantic analysis on the element to be analyzed and determining whether the element to be analyzed comprises at least one preset field; if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of the fields; comparing the corresponding original control of each preset field with the proper control queried in the preset table for each preset field; if the original control of the preset field is different from the proper control, the original control is adjusted to the proper control in the form.
In one embodiment of the invention, the element to be analyzed comprises text.
In another embodiment of the invention, the element to be analyzed comprises an image.
In yet another embodiment of the invention, the element to be analyzed comprises audio.
In another embodiment of the invention, the element to be analyzed comprises video.
In an embodiment of the present invention, performing semantic analysis on the element to be analyzed includes converting the element to be analyzed into text if the element to be analyzed is not text, and performing semantic analysis.
In another embodiment of the present invention, performing semantic analysis on the element to be analyzed includes performing semantic analysis on the element to be analyzed using an artificial intelligence algorithm if the element to be analyzed is not text.
In one embodiment of the invention, adjusting the original control to the appropriate control in the form is automatically replacing the original control with the appropriate control.
In another embodiment of the invention, adjusting the original control to the appropriate control in the form includes displaying the appropriate control side-by-side with the original control.
In yet another embodiment of the present invention, adjusting the original control to the appropriate control in the form includes popup displaying the appropriate control for user selection replacement.
According to another embodiment of the present invention, there is provided a semantic-based form construction method including receiving a form including elements to be analyzed; performing semantic analysis on the element to be analyzed and determining whether the element to be analyzed comprises at least one preset field; if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of the fields; acquiring an appropriate control of each preset field; appropriate controls are automatically presented in the form.
In one embodiment of the invention, the element to be analyzed comprises text.
In another embodiment of the invention, the element to be analyzed comprises an image.
In yet another embodiment of the invention, the element to be analyzed comprises audio.
In another embodiment of the invention, the element to be analyzed comprises video.
In an embodiment of the present invention, performing semantic analysis on the element to be analyzed includes converting the element to be analyzed into text if the element to be analyzed is not text, and performing semantic analysis.
In another embodiment of the invention, performing semantic analysis on the element to be analyzed includes performing semantic analysis on the element to be analyzed using an artificial intelligence algorithm if the element to be analyzed is not text.
In one embodiment of the invention, if there are multiple appropriate controls, the multiple appropriate controls are displayed side-by-side.
In another embodiment of the invention, if there are multiple appropriate controls, the multiple appropriate controls are pop-up displayed for selection and arrangement by the user.
According to an embodiment of the present invention, there is provided a semantic-based form construction system including: the receiving module is used for receiving a form comprising elements to be analyzed and corresponding original controls; the analysis module performs semantic analysis on the element to be analyzed and determines whether the element to be analyzed comprises at least one preset field; and an adjustment module: if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of the fields; if the original control is different from the appropriate control queried in the pre-configured table for each pre-set field, the original control is adjusted to the appropriate control in the table.
In one embodiment of the invention, the element to be analyzed comprises text.
In another embodiment of the invention, the element to be analyzed comprises an image.
In yet another embodiment of the invention, the element to be analyzed comprises audio.
In another embodiment of the invention, the element to be analyzed comprises video.
In an embodiment of the present invention, the analyzing module performs semantic analysis on the element to be analyzed, including converting the element to be analyzed into text by the analyzing module if the element to be analyzed is not text, and performing semantic analysis.
In another embodiment of the invention, performing semantic analysis on the element to be analyzed includes performing semantic analysis on the element to be analyzed using an artificial intelligence algorithm if the element to be analyzed is not text.
In one embodiment of the invention, the adjustment module adjusting the original control to the appropriate control in the form includes the adjustment module automatically replacing the original control with the appropriate control.
In another embodiment of the invention, the adjustment module adjusting the original control to the appropriate control in the form includes the adjustment module displaying the appropriate control side-by-side with the original control.
In yet another embodiment of the present invention, the adjustment module adjusting the original control to the appropriate control in the form includes the adjustment module popup displaying the appropriate control for user selection replacement.
According to another embodiment of the present invention, there is provided a semantic-based form construction system including: the receiving module is used for receiving a form comprising elements to be analyzed; the analysis module performs semantic analysis on the element to be analyzed and determines whether the element to be analyzed comprises at least one preset field; the acquisition module is used for: if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of the fields; acquiring an appropriate control of each preset field; appropriate controls are automatically presented in the form.
In one embodiment of the invention, the element to be analyzed comprises text.
In another embodiment of the invention, the element to be analyzed comprises an image.
In yet another embodiment of the invention, the element to be analyzed comprises audio.
In another embodiment of the invention, the element to be analyzed comprises video.
In an embodiment of the present invention, the analyzing module performs semantic analysis on the element to be analyzed, including converting the element to be analyzed into text by the analyzing module if the element to be analyzed is not text, and performing semantic analysis.
In another embodiment of the present invention, the analyzing module performing semantic analysis on the element to be analyzed includes performing semantic analysis on the element to be analyzed using an artificial intelligence algorithm if the element to be analyzed is not text.
In one embodiment of the invention, if there are multiple appropriate controls, the acquisition module displays the multiple appropriate controls side by side.
In another embodiment of the present invention, if there are multiple appropriate controls, the acquisition module pops up and displays the multiple appropriate controls for selection and arrangement by the user.
The embodiment of the invention can actively help a user to correct the wrong selection by analyzing the semantics of the constituent elements, thereby improving the working efficiency and the productivity. In fact, the semantic analysis technology is incorporated into form construction and analysis by the technical scheme, so that fault tolerance construction of the form is allowed, user experience is improved, and data accuracy is improved.
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Drawings
The foregoing summary of the invention, as well as the following detailed description of the invention, will be better understood when read in conjunction with the accompanying drawings. It is to be noted that the drawings are merely examples of the claimed invention. In the drawings, like reference numbers indicate identical or similar elements.
FIG. 1 illustrates one example of a questionnaire construction tool interface;
FIG. 2 illustrates one example of an interface for semantic-based form fault tolerant construction according to one embodiment of the present invention;
FIG. 3 illustrates one example of an interface for semantic-based form recommendation construction according to one embodiment of the present invention;
FIG. 4 illustrates another example of an interface for semantic-based form recommendation construction according to an embodiment of the present invention;
FIG. 5 illustrates a flow diagram of a semantic based form construction method according to an embodiment of the present invention;
FIG. 6 shows a flow chart of a semantic based form construction method according to another embodiment of the present invention;
FIG. 7 shows a block diagram of a semantic based form building system according to an embodiment of the present invention;
FIG. 8 illustrates a block diagram of a semantic-based form construction system according to another embodiment of the present invention.
Detailed Description
In order to make the above objects, features and advantages of the present invention more comprehensible, embodiments accompanied with figures are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than as described herein, and therefore the present invention is not limited to the specific embodiments disclosed below.
The invention provides a form construction method and a form construction system based on semantics. Data collection for elements in a form will be described in this specification as a questionnaire, but those skilled in the art will appreciate that embodiments of the invention are applicable to forms of various forms.
Further, elements in the form may include text, images, audio, video, and so forth. In this description, text will be mainly given as an example, but it will be understood by those skilled in the art that embodiments of the present invention are applicable to various forms of elements.
Embodiments of the semantic-based form construction method and system of the present invention will be implemented in conjunction with semantic analysis. Semantic analysis refers to the mining and learning of text, pictures, etc. using various machine learning methods. The segmentation, phrase extraction, etc., involved in semantic analysis of text are known to those skilled in the art and only relevant conclusions are drawn here. Likewise, convolution training, deep learning, information extraction, and natural language conversion involved in semantic analysis of images are also known to those skilled in the art, and only relevant conclusions are drawn here. Similarly, the extraction of information and natural language conversion involved in semantic analysis for audio and video are not described in detail herein.
Form construction interface
Forms may be used in a variety of environments and in a variety of forms, such as spreadsheets, web forms attached to a browser, forms attached to an APP or applet, cloud forms, and the like.
FIG. 1 illustrates one example of a questionnaire construction tool interface. In the questionnaire construction tool interface shown in fig. 1, options can be added to the questionnaire by using various form elements. Examples of form elements are radio boxes (single choice), check boxes (multiple choice), drop down (choice) boxes, single line text boxes, multiple line text boxes, linear scale boxes, matrix radio boxes, matrix gap filling boxes, time/date boxes, and the like. In the questionnaire shown, initially added are "apples", "bananas" and "kiwi" with a single box.
FIG. 2 illustrates one example of an interface for semantic-based form fault tolerant construction according to one embodiment of the present invention. Semantic analysis may be provided through a variety of service forms, such as semantic analysis platforms, semantic analysis cloud services, and these service forms may be more specifically, for example, browsers, APPs, applets, clouds, and the like.
In the initial questionnaire shown in fig. 1, a question is entered: "please select at least one fruit you like. "at least" due to the existence of multi-choice semantics in the question, the results produced by the originally selected control box of FIG. 1 will no longer be accurate, as shown in FIG. 2 (a). In the interface example of the semantic-based form fault tolerant build of FIG. 2, the radio boxes will be able to be automatically replaced with check boxes, as shown in FIG. 2 (b). Thus, the original misplacement or inapplicable control in the form will be replaced, i.e. the form construction interface in this embodiment allows fault tolerant construction.
Likewise, when there are other multi-choice semantics, such as "at least one choice", "which places, factors, categories/types, links", "multiple/locations", "diversity/diversification", "diversification" (which are only a partial non-exhaustive example here), the misconvergence control may be automatically replaced with a corresponding appropriate control. Such replacement is not limited to the replacement of a radio box with a check box, but may be the replacement of a radio box with a drop-down box, the replacement of a drop-down box with a single line of text boxes or multiple lines of text boxes, or the replacement of a matrix radio box with a matrix filled box.
In addition, in other contexts other than Chinese (e.g., english), when there is multi-choice semantics, such as "at least", "a plurality of", "multiple", etc., the wrong choice control can be automatically replaced with a corresponding appropriate control as well. Those skilled in the art will appreciate that embodiments of the present invention are equally applicable in the context of French, german, spanish, russian, and other Europe-based languages, japanese, korean, and other Altai-based languages.
FIG. 3 illustrates one example of an interface for semantic-based form recommendation construction according to one embodiment of the present invention. In the questionnaire shown in fig. 3, the questions entered are: "does the lecture meet your needs? "in this context, the control may answer yes or no with a radio box (301). However, where satisfaction needs to be subdivided to determine fine-grained audience, a linear scale (302) may be selected. The linear scale table (302) subdivides satisfaction into 7 categories: satisfaction (smiling face), 5, 4, 3, 2, 1, dissatisfaction (crying face).
In this case, the original control can be adjusted when the judgment semantics of yes/no are detected. In this embodiment, the yes or no with single box and the linear scale will be displayed side by side for the user to select by themselves. Alternatively, the linear scale table may directly replace the radio box. Alternatively, the linear scale table may pop up for the user to confirm whether to replace the radio frame.
In another embodiment of the invention, there are a number of suitable controls available. There are a variety of ways in which these controls may be displayed. For example, they may be displayed side-by-side, in a list, in an ellipsis, etc. Alternatively, other display means may be employed to alert the user to the presence of various selections.
FIG. 4 illustrates another example of an interface for semantic-based form recommendation construction according to an embodiment of the present invention. The interface for the semantic-based form recommendation construction is similar to that of FIG. 1, except that: the form initially contains only the questions "please select at least one fruit you like" and "apple", "banana" and "kiwi" options (see fig. 4 (a)). Since there is a multi-choice semantic "at least" in this question, the appropriate control "check item" can be automatically presented (see fig. 4 (b)).
The form construction interface in the embodiment allows form construction recommendation based on semantics, and can improve user experience in a certain context environment and improve data accuracy.
Form construction method based on semantics
FIG. 5 shows a flow diagram of a semantic based form construction method according to an embodiment of the present invention.
At block 502, a form is received that includes elements to be analyzed and corresponding original controls. The elements to be analyzed may be text, images, audio, video, and so on. The received form may be a form entered by the user in real time, or may be a form previously established by the user.
At block 504, semantic analysis is performed for the element to be analyzed and it is determined whether the element to be analyzed includes at least one preset field.
In embodiments in which the element to be analyzed is text, performing semantic analysis on the text includes performing text processing on the text. In the prior art, examples of text processing techniques are: segmentation, term weighting, keyword/phrase extraction, syntactic analysis, and so forth. Specifically, the word segmentation method includes a word segmentation method based on character string matching, a full segmentation method based on a language model, a word segmentation method based on a deep learning method, and the like. Term weighting methods include unsupervised computing methods and supervised machine learning methods, among others. The keyword extraction method includes TF-IDF keyword extraction method, topic-model keyword extraction method, RAKE keyword extraction method, etc. The syntax analysis method is classified into phrase syntax analysis and dependency syntax analysis according to the syntax system, and has a rule-based method and a statistical-based method, respectively, and the like.
In the interface example of the semantic based form fault tolerant build of fig. 2, the question is "please select at least one fruit you like". Acquiring the semantic analysis results may include setting the extracted phrase or term to "at least" to acquire multi-choice semantics.
In the interface example of the semantic-based form recommendation construction of FIG. 3, the problem is: "does the lecture meet your needs? ". Acquiring the semantic analysis results may include setting the extracted phrase or word to "whether or not" to acquire decision semantics.
In an embodiment of the present invention, performing semantic analysis on the element to be analyzed includes converting the element to be analyzed into text and performing semantic analysis if the element to be analyzed is not text.
Further, in embodiments in which the element to be analyzed is an image, performing semantic analysis on the image includes performing image-to-text conversion on the image. Image text conversion is essentially a textual description of an image, i.e. descriptive text is automatically generated from an image. The textual description of the images facilitates data mining, analysis and retrieval by people from a vast array of images, combining techniques in the computer vision field and the natural language processing field. The image has the characteristics of multiple channels and high dimensionality and is affected by illumination, resolution, environment and noise. Natural language has structure, grammar is various and standard, vocabulary is flexible and changeable, and the establishment of corresponding relation between images and texts is very challenging. Textual descriptions of images often employ both search-based methods and language model-based methods. The method based on the search is to carry out semantic segmentation on the image and the text respectively, project the image and the text into the same space, establish a corresponding relation and find the text which is most matched with the image from a database. The language model-based method can generate a brand new sentence, namely, extracting objects, scenes and relations in the image, and then generating the sentence by adopting a template.
When descriptive characters of the image are obtained, text semantic analysis can be performed on the descriptive characters, and semantic analysis results can be obtained. For example, for a photograph of a star engaged in an activity, the descriptive text obtained is "star xxx engaged in xx charitable activity in xxxx year x month, dressing. Then in investigating the star support rate or heat, photos of different stars may be used as options, in conjunction with appropriate controls, in order to collect corresponding data. The application scene is also suitable for different commodities, different movie dramas, different hotels and the like.
Also, in embodiments in which the element to be analyzed is audio, performing semantic analysis on the audio includes performing audio-to-text conversion on the audio. When the corresponding text of the audio is obtained, text semantic analysis can be performed on the text, and a semantic analysis result can be obtained.
Still further, in embodiments in which the element to be analyzed is video, semantic analysis of the video includes text conversion of the video frames and audio, respectively. When the corresponding text is obtained, text semantic analysis can be performed on the text, and semantic analysis results can be obtained.
In another embodiment of the present invention, for embodiments where the element to be analyzed is an image, audio or video, the image, audio or video may be semantically analyzed by artificial intelligence algorithms without first performing text conversion on the image, audio or video. Taking an image as an example, the image semantic feature extraction can be realized through fusion of fuzzy logic, genetic algorithm and artificial neural network. Those skilled in the art will appreciate that, as artificial intelligence algorithms continue to evolve and optimize, semantic analysis of different elements to be analyzed and obtaining semantic analysis results may be efficiently performed by a variety of artificial intelligence algorithms.
At block 506, if the element to be analyzed includes at least one preset field, a preconfigured table listing a plurality of fields and appropriate controls for each field is queried for each of the at least one preset field.
In different application scenarios, the preset fields and corresponding controls may be different. For example, for multi-choice semantics of chinese environments, the preset fields may be selected as "at least", "at least one item", "which places, factors, categories/types, links", "multiple/locations", "diversity/diversification", "diversification", etc., and the corresponding controls may be check boxes, drop-down boxes, multi-line text boxes, matrix blank boxes, etc. The preset fields and corresponding controls may be placed in a preset table, which may be one-to-one, one-to-many, many-to-one, or even many-to-many.
For example, for the decision semantics of the chinese environment, the preset fields may be selected as "yes", "no", "like", "dislike", "satisfactory", "dissatisfied", "positive", "negative", etc., and the corresponding controls may be a single box, a linear scale, a matrix single box, etc. Also, when the preset fields and corresponding controls are placed in the preset table, their correspondence may be one-to-one, one-to-many, many-to-one, or even many-to-many.
The pre-configured table may be stored in a computer readable storage medium such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, a removable disk, a CD-ROM, a cloud storage, etc.
At block 508, the corresponding original control for each preset field is compared to the appropriate controls queried in the preset table for each preset field.
At block 510, if the original control of the preset field is different from the appropriate control, the original control is adjusted to the appropriate control in the form.
In an embodiment of the invention, adjusting the original control to the appropriate control in the form includes automatically replacing the original control with the appropriate control. For example, in the example interface of the semantic-based form fault tolerant build of FIG. 2, the preset field is "at least," the original control is a single box, and the appropriate control of the preset field "at least" in the pre-configured form is a check box, which is automatically replaced with a check box upon determining the multi-choice semantic.
In another embodiment of the invention, adjusting the original control to the appropriate control in the form includes displaying the appropriate control alongside the original control or in other manners of display. For example, in the example interface of the semantic-based form recommendation construction of fig. 3, the preset field is "no", the original control is a single box, and the proper control of the preset field "no" in the preset form is a single box or a linear scale, then the control single box is displayed side-by-side with the linear scale upon determining the decision semantic.
In yet another embodiment of the present invention, adjusting the original control to the appropriate control in the form includes popup displaying the appropriate control for user selection replacement. For example, in the example interface of the semantic-based form recommendation construction of fig. 3, when the proper control of the preset field "whether" in the preconfigured form is a single box or a linear scale, the linear scale may be pop-up displayed upon determining the decision semantics and prompt the user to select whether to replace the original control single box.
FIG. 6 shows a flow chart of a semantic based form construction method according to another embodiment of the present invention.
At block 601, a form including elements to be analyzed is received. The elements to be analyzed may include text, images, audio, video, and so forth. The received form may be a form entered by the user in real time, or may be a form previously established by the user.
At block 603, semantic analysis is performed for the element to be analyzed and it is determined whether the element to be analyzed includes at least one preset field.
In embodiments in which the element to be analyzed is text, performing semantic analysis on the text includes performing text processing on the text.
In an embodiment of the present invention, performing semantic analysis on the element to be analyzed includes converting the element to be analyzed into text and performing semantic analysis if the element to be analyzed is not text. If the element to be analyzed is not text, the element to be analyzed may be an image, audio or video, or the like.
In another embodiment of the present invention, for embodiments in which the element to be analyzed is an image, audio or video, etc., the image, audio or video may be semantically analyzed by an artificial intelligence algorithm without first performing text conversion on the image, audio or video.
At block 605, if the element to be analyzed includes at least one preset field, a preset table is queried for each preset field, wherein the preset table lists a plurality of fields and appropriate controls for the respective fields.
At block 607, the appropriate controls for each preset field are obtained.
At block 609, the appropriate controls are automatically presented in the form.
In one embodiment of the invention, when there are multiple appropriate controls, the controls may be displayed side-by-side. Alternatively, a plurality of appropriate controls may be pop-up displayed for selection and arrangement by the user.
The method embodiment of the invention can actively help a user to correct the wrong selection by analyzing the semantics of the constituent elements, thereby improving the working efficiency and the productivity. The method embodiment of the invention can automatically recommend proper selection to the user by analyzing the semantics of the constituent elements, thereby further improving the working efficiency and the productivity. In fact, the technical scheme of the invention brings the technologies of text semantic analysis, image semantic analysis, audio semantic analysis, video semantic analysis and the like into form construction and analysis, thereby allowing the form to carry out fault-tolerant construction or automatic recommendation construction, improving user experience and simultaneously improving data accuracy.
Form construction system based on semantics
FIG. 7 shows a block diagram of a semantic based form building system according to an embodiment of the present invention.
As shown in fig. 7, the semantic-based form construction system 700 may include: a receiving module 702, an analyzing module 704 and an adjusting module 706.
The receiving module 702 receives a form that includes elements to be analyzed and corresponding original controls. The elements to be analyzed may include text, images, audio, video, and so forth. The received form may be a form entered by the user in real time, or may be a form previously established by the user.
The analysis module 704 performs semantic analysis on the element to be analyzed and determines whether the element to be analyzed includes at least one preset field.
In embodiments in which the element to be analyzed is text, the analysis module 704 performs semantic analysis on the text including text processing of the text.
In one embodiment of the invention, the analysis module 704 performs semantic analysis on the element to be analyzed, including converting the element to be analyzed into text by the analysis module 704 and performing semantic analysis if the element to be analyzed is not text.
Further, in embodiments in which the element to be analyzed is an image, the analysis module 704 performs semantic analysis on the image including image-to-text conversion of the image. When descriptive text of an image is obtained, the analysis module 704 may perform text semantic analysis on the descriptive text and obtain a semantic analysis result.
Also, in embodiments in which the element to be analyzed is audio, the analysis module 704 performs semantic analysis on the audio including audio-to-text conversion of the audio. When the corresponding text of the audio is obtained, the analysis module 704 may perform text semantic analysis on the text and obtain a semantic analysis result.
Still further, in embodiments in which the element to be analyzed is video, the analysis module 704 performs semantic analysis on the video including text conversion of the video frames and audio, respectively. When a corresponding word is obtained, the analysis module 704 may perform text semantic analysis on the word and obtain a semantic analysis result.
In another embodiment of the invention, for embodiments in which the element to be analyzed comprises an image, audio, or video, the analysis module 704 may perform semantic analysis on the image, audio, or video by artificial intelligence algorithms without first performing text conversion on the image, audio, or video. Taking an image as an example, the image semantic feature extraction can be realized through fusion of fuzzy logic, genetic algorithm and artificial neural network. As will be appreciated by those skilled in the art, with the continued development and optimization of artificial intelligence algorithms, the analysis module performs semantic analysis on different elements to be analyzed and obtains semantic analysis results efficiently through various artificial intelligence algorithms.
If it is determined that the element to be analyzed includes at least one preset field, the adjustment module 706 queries a preset table listing a plurality of fields and appropriate controls for the respective fields for each preset field. In different application scenarios, the fields and corresponding appropriate controls may be different. The correspondence of fields placed in the preconfigured table and the corresponding appropriate controls may be one-to-one, one-to-many, many-to-one, or even many-to-many. The pre-configured table may be stored in a computer readable storage medium.
If the original control is different from the appropriate control queried in the preconfigured table for each preset field, the adjustment module 706 further adjusts the original control to the appropriate control in the table.
In one embodiment of the invention, the adjustment module 706 adjusting the original control to the appropriate control in the form includes the adjustment module 706 automatically replacing the original control with the appropriate control.
In another embodiment of the invention, the adjustment module 706 adjusting the original control to the appropriate control in the form includes the adjustment module 706 displaying the appropriate control side-by-side with the original control.
In yet another embodiment of the invention, the adjustment module 706 adjusting the original control to the appropriate control in the form includes the adjustment module 706 popup displaying the appropriate control for user selection replacement.
FIG. 8 illustrates a block diagram of a semantic-based form construction system according to another embodiment of the present invention.
As shown in fig. 8, a semantic-based form construction system 800 may include: a receiving module 802, an analyzing module 804, and an acquiring module 806.
The receiving module 802 receives a form including elements to be analyzed. The elements to be analyzed may include text, images, audio, video, and so forth. The received form may be a form entered by the user in real time, or may be a form previously established by the user.
The analysis module 804 performs semantic analysis on the element to be analyzed and determines whether the element to be analyzed includes at least one preset field.
In embodiments in which the element to be analyzed is text, the analysis module 804 performs semantic analysis on the text including text processing of the text.
In one embodiment of the present invention, the analyzing module 804 performs semantic analysis on the element to be analyzed, including converting the element to be analyzed into text by the analyzing module 804 and performing semantic analysis if the element to be analyzed is not text. If the element to be analyzed is not text, the element to be analyzed may be an image, audio or video, or the like.
In another embodiment of the invention, for embodiments in which the element to be analyzed is an image, audio, video, or the like, the analysis module 804 may perform semantic analysis on the image, audio, or video by artificial intelligence algorithms without first performing text conversion on the image, audio, or video.
If the element to be analyzed includes at least one preset field, the acquisition module 806 queries a preset table listing a plurality of fields and appropriate controls for the respective fields for each preset field.
The acquisition module 806 acquires the appropriate controls for each preset field and automatically presents the appropriate controls in the form.
In one embodiment of the invention, when there are multiple appropriate controls, the controls may be displayed side-by-side. Alternatively, a plurality of appropriate controls may be pop-up displayed for selection and arrangement by the user.
The system embodiment of the invention can actively help a user to correct wrong selection or automatically recommend proper selection to the user by analyzing the semantics of the constituent elements by each module forming the semantic-based form construction system, thereby improving the working efficiency and the productivity. In fact, the technical scheme of the invention brings the technologies of text semantic analysis, image semantic analysis, audio semantic analysis, video semantic analysis and the like into a form construction and analysis system, thereby allowing the form to carry out fault-tolerant construction or automatic recommendation construction, improving user experience and simultaneously improving data accuracy.
The various steps and modules of the above-described semantic-based form construction method and system may be implemented in hardware, software, or a combination thereof. If implemented in hardware, the various illustrative steps, modules, and circuits described in connection with the invention may be implemented or performed with a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic component, a hardware component, or any combination thereof. A general purpose processor may be a processor, microprocessor, controller, microcontroller, state machine, or the like. If implemented in software, the various illustrative steps, modules, described in connection with the invention may be stored on or transmitted as one or more instructions or code on a computer readable medium. Software modules implementing various operations of the invention may reside in storage media such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, a removable disk, a CD-ROM, cloud storage, etc. A storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium, as well as execute corresponding program modules to implement the various steps of the present invention. Moreover, software-based embodiments may be uploaded, downloaded, or accessed remotely via suitable communication means. Such suitable communication means include, for example, the internet, world wide web, intranet, software applications, cable (including fiber optic cable), magnetic communications, electromagnetic communications (including RF, microwave and infrared communications), electronic communications, or other such communication means.
It is also noted that the embodiments may be described as a process which is depicted as a flowchart, a flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. Additionally, the order of the operations may be rearranged.
The disclosed methods, apparatus, and systems should not be limited in any way. Rather, the invention encompasses all novel and non-obvious features and aspects of the various disclosed embodiments (both alone and in various combinations and subcombinations with one another). The disclosed methods, apparatus and systems are not limited to any specific aspect or feature or combination thereof, nor do any of the disclosed embodiments require that any one or more specific advantages be present or that certain or all technical problems be solved.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many modifications may be made by those of ordinary skill in the art without departing from the spirit of the present invention and the scope of the appended claims, which fall within the scope of the present invention.
Claims (26)
1. A form construction method based on semantics comprises the following steps:
receiving a form comprising elements to be analyzed and corresponding original controls;
performing semantic analysis on the element to be analyzed to determine whether the element to be analyzed comprises at least one preset field;
if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of each field, and the proper controls are controls for correcting the original controls of the element to be analyzed when the original controls of the preset fields are different from the proper controls;
comparing the corresponding original control of each preset field with the proper control queried in the preset table for each preset field; and
and if the original control of the preset field is different from the proper control, adjusting the original control into the proper control in the form.
2. The method of claim 1, wherein the element to be analyzed comprises text, an image, audio, or video.
3. The method of claim 1, wherein semantically analyzing the element to be analyzed comprises converting the element to be analyzed into text and semantically analyzing the text if the element to be analyzed is not text.
4. The method of claim 1, wherein semantically analyzing the element to be analyzed comprises semantically analyzing the element to be analyzed using an artificial intelligence algorithm if the element to be analyzed is not text.
5. The method of claim 1, wherein adjusting the original control to the appropriate control comprises automatically replacing the original control with the appropriate control.
6. The method of claim 1, wherein adjusting the original control to the appropriate control comprises displaying the appropriate control side-by-side with the original control.
7. The method of claim 1, wherein adjusting the original control to the appropriate control comprises popup displaying the appropriate control for user selection replacement.
8. A form construction method based on semantics comprises the following steps:
receiving a form comprising elements to be analyzed;
performing semantic analysis on the element to be analyzed and determining whether the element to be analyzed comprises at least one preset field;
if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of the fields, and the proper controls are controls automatically recommended according to the semantics of the element to be analyzed;
Acquiring an appropriate control of each preset field;
the appropriate controls are automatically presented in the form.
9. The method of claim 8, wherein the element to be analyzed comprises text, an image, audio, or video.
10. The method of claim 8, wherein performing semantic analysis on the element to be analyzed comprises converting the element to be analyzed into text and performing semantic analysis if the element to be analyzed is not text.
11. The method of claim 8, wherein semantically analyzing the element to be analyzed comprises semantically analyzing the element to be analyzed using an artificial intelligence algorithm if the element to be analyzed is not text.
12. The method of claim 8, wherein automatically presenting the appropriate control comprises displaying a plurality of the appropriate controls side-by-side if there are a plurality of the appropriate controls.
13. The method of claim 8, wherein automatically presenting the appropriate control comprises popup displaying a plurality of the appropriate controls for selection and arrangement by a user if the appropriate controls are plural.
14. A semantic-based form building system, comprising:
the receiving module is used for receiving a form comprising elements to be analyzed and corresponding original controls;
the analysis module performs semantic analysis on the element to be analyzed and determines whether the element to be analyzed comprises at least one preset field;
and an adjustment module:
if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of each field, and the proper controls are controls for correcting the original controls of the element to be analyzed when the original controls of the preset fields are different from the proper controls;
and if the original control is different from the proper control queried in the preset table for each preset field, adjusting the original control into the proper control in the table.
15. The system of claim 14, wherein the element to be analyzed comprises text, an image, audio, or video.
16. The system of claim 14, wherein the analysis module performing semantic analysis on the element to be analyzed comprises converting, by the analysis module, the element to be analyzed into text and performing semantic analysis if the element to be analyzed is not text.
17. The system of claim 14, wherein the analysis module performing semantic analysis on the element to be analyzed comprises performing semantic analysis on the element to be analyzed by the analysis module using an artificial intelligence algorithm if the element to be analyzed is not text.
18. The system of claim 14, wherein the adjustment module adjusting the original control to the appropriate control comprises the adjustment module automatically replacing the original control with the appropriate control.
19. The system of claim 14, wherein the adjustment module adjusting the original control to the appropriate control comprises the adjustment module displaying the appropriate control side-by-side with the original control.
20. The system of claim 14, wherein the adjustment module adjusting the original control to the appropriate control comprises the adjustment module popup displaying the appropriate control for user selection replacement.
21. A semantic-based form building system, comprising:
the receiving module is used for receiving a form comprising elements to be analyzed;
the analysis module performs semantic analysis on the element to be analyzed and determines whether the element to be analyzed comprises at least one preset field;
The acquisition module is used for:
if the element to be analyzed comprises at least one preset field, querying a preset table for each preset field, wherein the preset table lists a plurality of fields and proper controls of the fields, and the proper controls are controls automatically recommended according to the semantics of the element to be analyzed;
acquiring an appropriate control of each preset field;
the appropriate controls are automatically presented in the form.
22. The system of claim 21, wherein the element to be analyzed comprises text, an image, audio, or video.
23. The system of claim 21, wherein the analysis module performing semantic analysis on the element to be analyzed comprises converting, by the analysis module, the element to be analyzed into text and performing semantic analysis if the element to be analyzed is not text.
24. The system of claim 21, wherein the analysis module performing semantic analysis on the element to be analyzed comprises performing semantic analysis on the element to be analyzed by the analysis module using an artificial intelligence algorithm if the element to be analyzed is not text.
25. The system of claim 21, wherein the acquisition module automatically presenting the appropriate control in the form comprises displaying a plurality of the appropriate controls side-by-side by the acquisition module if there are a plurality of the appropriate controls.
26. The system of claim 21, wherein the acquisition module automatically presenting the appropriate control in the form comprises the acquisition module popup displaying a plurality of the appropriate controls for user selection and arrangement if there are a plurality of the appropriate controls.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910079244.6A CN110032561B (en) | 2019-01-28 | 2019-01-28 | Form construction method and system based on semantics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910079244.6A CN110032561B (en) | 2019-01-28 | 2019-01-28 | Form construction method and system based on semantics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110032561A CN110032561A (en) | 2019-07-19 |
| CN110032561B true CN110032561B (en) | 2023-07-18 |
Family
ID=67235599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910079244.6A Active CN110032561B (en) | 2019-01-28 | 2019-01-28 | Form construction method and system based on semantics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110032561B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112434514B (en) * | 2020-11-25 | 2022-06-21 | 重庆邮电大学 | Multi-granularity multi-channel neural network based semantic matching method and device and computer equipment |
| CN116149631B (en) * | 2023-01-05 | 2023-10-03 | 三峡高科信息技术有限责任公司 | Method for generating Web intelligent form based on natural language |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662340B2 (en) * | 2000-04-28 | 2003-12-09 | America Online, Incorporated | Client-side form filler that populates form fields based on analyzing visible field labels and visible display format hints without previous examination or mapping of the form |
| CN103869931A (en) * | 2012-12-10 | 2014-06-18 | 三星电子（中国）研发中心 | Method and device for controlling user interface through voice |
| CN104166462A (en) * | 2013-05-17 | 2014-11-26 | 北京搜狗科技发展有限公司 | Input method and system for characters |
| CN105022615A (en) * | 2014-04-21 | 2015-11-04 | 大唐软件技术股份有限公司 | Interface generating method and system |
| CN107943930A (en) * | 2017-11-22 | 2018-04-20 | 用友金融信息技术股份有限公司 | Dynamic list generation method, device, computer equipment and readable storage medium storing program for executing |
| CN108763391A (en) * | 2018-05-21 | 2018-11-06 | 天津字节跳动科技有限公司 | Questionnaire page surface treatment method and apparatus |
-
2019
- 2019-01-28 CN CN201910079244.6A patent/CN110032561B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662340B2 (en) * | 2000-04-28 | 2003-12-09 | America Online, Incorporated | Client-side form filler that populates form fields based on analyzing visible field labels and visible display format hints without previous examination or mapping of the form |
| CN103869931A (en) * | 2012-12-10 | 2014-06-18 | 三星电子（中国）研发中心 | Method and device for controlling user interface through voice |
| CN104166462A (en) * | 2013-05-17 | 2014-11-26 | 北京搜狗科技发展有限公司 | Input method and system for characters |
| CN105022615A (en) * | 2014-04-21 | 2015-11-04 | 大唐软件技术股份有限公司 | Interface generating method and system |
| CN107943930A (en) * | 2017-11-22 | 2018-04-20 | 用友金融信息技术股份有限公司 | Dynamic list generation method, device, computer equipment and readable storage medium storing program for executing |
| CN108763391A (en) * | 2018-05-21 | 2018-11-06 | 天津字节跳动科技有限公司 | Questionnaire page surface treatment method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110032561A (en) | 2019-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446135B (en) | Multimedia data label generation method and device | |
| CN110750959B (en) | Text information processing method, model training method and related device | |
| CN110362671B (en) | Topic recommendation method, device and storage medium | |
| KR102034346B1 (en) | Method and Device for Detecting Slang Based on Learning | |
| CN103052953A (en) | Information processing device, method of processing information, and program | |
| CN111651497B (en) | User tag mining method and device, storage medium and electronic equipment | |
| CN108924651B (en) | Teaching video intelligent playing system based on training operation recognition | |
| US10685012B2 (en) | Generating feature embeddings from a co-occurrence matrix | |
| US20160117301A1 (en) | Annotation sharing system and method | |
| CN110377789A (en) | For by text summaries and the associated system and method for content media | |
| US11392791B2 (en) | Generating training data for natural language processing | |
| CN113010711B (en) | Method and system for automatically generating movie poster based on deep learning | |
| CN110032561B (en) | Form construction method and system based on semantics | |
| Tuna et al. | Topic based segmentation of classroom videos | |
| CN111614986A (en) | Bullet screen generation method, system, equipment and storage medium based on online education | |
| US20100311020A1 (en) | Teaching material auto expanding method and learning material expanding system using the same, and machine readable medium thereof | |
| CN111144079A (en) | Method and device for intelligently acquiring learning resources, printer and storage medium | |
| Zhu | An educational approach to machine learning with mobile applications | |
| US20170287346A1 (en) | System and methods to create multi-faceted index for instructional videos | |
| CN116049557A (en) | Educational resource recommendation method based on multi-mode pre-training model | |
| CN113779345B (en) | Teaching material generation method and device, computer equipment and storage medium | |
| CN107430824B (en) | Semi-automatic system and method for evaluating responses | |
| Ciurez et al. | Automatic categorization of educational videos according to learning styles | |
| CN116306506A (en) | Intelligent mail template method based on content identification | |
| Sokolová et al. | An introduction to detection of hate speech and offensive language in Slovak |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201015 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. Effective date of registration: 20201015 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman, British Islands Applicant before: Advanced innovation technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |