CN114969258A - Table processing method and device - Google Patents
Table processing method and device Download PDFInfo
- Publication number
- CN114969258A CN114969258A CN202210591758.1A CN202210591758A CN114969258A CN 114969258 A CN114969258 A CN 114969258A CN 202210591758 A CN202210591758 A CN 202210591758A CN 114969258 A CN114969258 A CN 114969258A
- Authority
- CN
- China
- Prior art keywords
- cells
- function
- structural elements
- network
- text
- 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.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 15
- 230000006870 function Effects 0.000 claims abstract description 125
- 238000000034 method Methods 0.000 claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 38
- 239000013598 vector Substances 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 24
- 230000015654 memory Effects 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000003058 natural language processing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 239000003795 chemical substances by application Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000003915 cell function Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000010230 functional analysis Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000008852 wen-xin Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/177—Editing, e.g. inserting or deleting of tables; using ruled lines
- G06F40/18—Editing, e.g. inserting or deleting of tables; using ruled lines of spreadsheets
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
Abstract
The disclosure provides a form processing method and a form processing device, relates to the technical field of computers, and particularly relates to the technical field of artificial intelligence including computer vision, natural language processing and deep learning. The specific implementation mode comprises the following steps: determining element characteristics of cells in the table, wherein the element characteristics comprise characteristics of structural elements and characteristics of text elements; inputting the element characteristics of the cells in the table into a function determination network to obtain the function characteristics of the cells in the table; and inputting the functional characteristics of the cells in the table into the classifier to obtain the functional categories of the cells in the table. The method and the device have the advantage that the characteristics of the structural elements and the text elements of the table are used for participating in prediction, and the function of accurately determining the cells is facilitated.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to the field of artificial intelligence technologies including computer vision, natural language processing, and deep learning, and in particular, to a method and an apparatus for processing a table.
Background
In the real world, a great deal of information exists in paper-based tables or electronic tables, and for computers, each cell in the tables is only a character string, and the function of each cell in the tables is usually interpreted manually and input into the computer, so that the machine can understand the tables. And then the information in the table is inquired, added, deleted and the like.
The automatic functional analysis of the table cells is a method using programming or artificial intelligence, which can reduce the cost of manually analyzing and storing the functions of each cell in the table.
Disclosure of Invention
A method and a device for processing a table, an electronic device and a storage medium are provided.
According to a first aspect, there is provided a table processing method, including: determining element characteristics of cells in the table, wherein the element characteristics comprise characteristics of structural elements and characteristics of text elements; inputting the element characteristics of the cells in the table into a function determination network to obtain the function characteristics of the cells in the table; and inputting the functional characteristics of the cells in the table into the classifier to obtain the functional categories of the cells in the table.
According to a second aspect, there is provided a method of training a function determination network, wherein the method comprises: acquiring element characteristics of cells in a form sample, wherein the element characteristics comprise the characteristics of structural elements and the characteristics of text elements; inputting the element characteristics of the cells in the table sample into a function determination network to be trained to obtain the function characteristics of the cells in the table sample; inputting the functional characteristics of the cells in the table sample into a classifier to obtain the functional categories of the cells in the table sample; and training the function determination network to be trained by using the function types and the function type labels of the cells in the table sample to obtain the trained function determination network.
According to a third aspect, there is provided a table processing apparatus comprising: a determining unit configured to determine element characteristics of cells in the table, wherein the element characteristics include characteristics of structural elements and characteristics of text elements; the input unit is configured to input the element characteristics of the cells in the table into the function determination network to obtain the function characteristics of the cells in the table; and the classification unit is configured to input the functional characteristics of the cells in the table into the classifier to obtain the functional categories of the cells in the table.
According to a fourth aspect, there is provided an apparatus for training a function determination network, wherein the apparatus comprises: the obtaining unit is configured to obtain element characteristics of cells in the table sample, wherein the element characteristics comprise characteristics of structural elements and characteristics of text elements; the forward unit is configured to input the element characteristics of the cells in the table sample into a function determination network to be trained to obtain the function characteristics of the cells in the table sample; the output unit is configured to input the functional characteristics of the cells in the table sample into the classifier to obtain the functional categories of the cells in the table sample; and the training unit is configured to train the function determination network to be trained by using the function types and the function type labels of the cells in the table sample to obtain the trained function determination network.
According to a fifth aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of any of the embodiments of the method of any of the above aspects.
According to a sixth aspect, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any of the embodiments of the method according to any aspect.
According to a seventh aspect, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method according to any embodiment of the method of any aspect.
According to the scheme disclosed by the invention, the characteristics of the structural elements and the text elements of the table are utilized to participate in prediction, so that the function of the cell can be accurately determined.
Drawings
Other features, objects and advantages of the disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which some embodiments of the present disclosure may be applied;
FIG. 2 is a flow diagram for one embodiment of a method of processing a form according to the present disclosure;
FIG. 3 is a schematic diagram of cell numbers for various cells of a table processing method according to the present disclosure;
FIG. 4 is a flow diagram of one embodiment of a training method of a function determination network according to the present disclosure;
FIG. 5 is a schematic block diagram of one embodiment of a table processing apparatus according to the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing a method of processing a table according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, necessary security measures are taken, and the customs of the public order is not violated.
It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates an exemplary system architecture 100 of an embodiment of a processing method of a form or a processing apparatus of a form to which the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various communication client applications, such as a video application, a live application, an instant messaging tool, a mailbox client, social platform software, and the like, may be installed on the terminal devices 101, 102, and 103.
Here, the terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices having a display screen, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server providing various services, such as a background server providing support for the terminal devices 101, 102, 103. The background server may analyze and perform other processing on the received data such as the table, and feed back a processing result (e.g., a function type of a cell in the table) to the terminal device.
It should be noted that the processing method of the table provided by the embodiment of the present disclosure may be executed by the server 105 or the terminal devices 101, 102, and 103, and accordingly, the processing apparatus of the table may be disposed in the server 105 or the terminal devices 101, 102, and 103.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method of processing a form according to the present disclosure is shown. The processing method of the table comprises the following steps:
In this embodiment, an execution subject (for example, the server or the terminal device shown in fig. 1) on which the processing method of the table is executed may determine, for a cell in the table, an element (token) feature of the cell. The table in the present embodiment may be a document table including text.
In practice, an element may be an element of a related structure, i.e. a structural element, such as a row position. Furthermore, an element may also be an element related to text, i.e. a text element, such as text in a cell. The element feature is a parameter capable of indicating characteristics of an element, and may specifically include a structural element feature, and may also include a text element feature.
The element may obtain the element feature after the element is subjected to the preset processing, for example, the preset processing may be to search a vector table indicating a correspondence between the element and the element feature.
In this embodiment, the execution body may input the feature of the cell in the table into the function determination network to obtain the feature of the function. The functional characteristic may indicate a function of a cell in the table. The functional characteristic may be output from the function determination network, or may be a result of performing a specified process on the output of the function determination network, where the specified process may be, for example, a process using a preset model or formula.
The function determination network is used to predict the function of the cell in the table, the output of which is a functional feature indicating the function.
The function determination network is a deep neural network. In particular, the deep neural network may be a variety of networks with language processing functions, such as bert (Bidirectional Encoder representation from Transformer).
In this embodiment, the execution agent may input the functional features of the cells in the table into a classifier, and obtain the functional categories of the cells in the table output from the classifier. The functional categories of the cells may include at least two of: a header (which may include a row header, a column header), a value (value), and a mixed cell. The value here is the value corresponding to the header. The mixed cell refers to a cell containing a certain amount of content (the amount of content is greater than a preset threshold value), such as a cell containing a remark item, which is not a header nor a value.
In practice, the classifiers can be various, such as a normalized exponential function soft-max classifier, or a Support Vector Machines (SVM).
The method provided by the embodiment of the disclosure can comprehensively extract the table information based on the characteristics of the structural elements and the text elements of the table, is favorable for comprehensively and accurately analyzing the table content, and thus realizes the function of accurately determining the cells.
In some optional implementations of any embodiment of the present application, determining the element characteristics of the cells in the table includes: vectorizing the text elements and the structural elements of the cells in the table to obtain the features of the text elements and the features of the structural elements; and adding the characteristics of the text elements and the characteristics of the structural elements to obtain the element characteristics of the cells in the table.
In this embodiment, the execution body may vectorize the text element and the structure in the table, and take the vectorization result as the feature of the text element and the feature of the structure element. The element features of the cells may be vector-summed features of both text elements and structural elements.
In practice, the execution body described above may vectorize the text element in various ways. For example, a vector corresponding to the text is looked up in a vector table (word embedding table) of the text. The vector table indicates a correspondence between the text element and a vector of the text element. Alternatively, the execution agent may input the text into a preset vectorization model, and output a vector from the model as a vectorization result.
The execution body may vectorize the structural elements in various ways. For example, the execution agent may look up a vector corresponding to the structural element in a vector table of the structure. The vector table indicates a correspondence between the structural elements and vectors of the structural elements. Alternatively, the execution agent may input the structural element into a specified vectorization model, and output a vector from the model as a vectorization result.
The added features in these implementations may be the features of the structural elements and the features of the text elements of each cell, and may also be the features of the structural elements and the features of the text elements arranged in sequence (in the order of the cells) among the plurality of cells.
The implementation modes can fuse the text features and the structural features through vectorization and vector addition, so that more comprehensive table features are input to the function determination network.
In some optional implementations of any of the embodiments above, the text element includes a word-cutting result of the text within the cell; the structural elements include row positions, column positions, or cell numbers.
In these implementations, one text element may be a word segmentation (word segmentation) result. A structural element may be a row position, a column position, or a cell number. Further, the structural element may also be merged cell information indicating whether the cell is a merged cell.
The cell sequence number refers to the sorting of the cells in the table, and the same cell sequence number is adopted for merging the cells. The structural element may include a row position and a column position of the cell, for example, the row position and the column position may be 2 and 5, indicating that the cell is in the 2 nd row and the 5 th column.
As shown in fig. 3, the left side of the figure is a table, and the right side shows the cell numbers of the cells in the table.
These implementations may extract comprehensive information from the table by fusing the textual information, the rank information, and the sort information of the cells.
In some optional implementations of any of the embodiments above, the function determination network comprises a linguistic network and a feed-forward neural network; inputting the element characteristics of the cells in the table into the function determination network to obtain the function characteristics of the cells in the table, wherein the function characteristics comprise the following steps: inputting the element characteristics of the cells in the table into a language network to obtain a language processing result vector of the element characteristics; and inputting the language processing result vector into a feedforward neural network to obtain the functional characteristics of the cell.
In these alternative implementations, the execution subject may process the element features of the cells by using a language network. The element feature herein may include a structural element feature and a text element feature.
The language network may be a deep neural network with language processing capabilities. For example, the deep neural network may be bert, or wenxin (semantic understanding techniques and platforms).
In practice, the classifier may be in a model with the function determination network, and both the table processing method and the training steps in the present disclosure may be performed on the model. In addition, the step of determining the elemental characteristics of the cells in the table may also be implemented in the model.
The execution subject can further process the language network by using a feed-forward neural network (FFN) to obtain a feature more suitable for judging the function type, namely the function feature.
These implementations may utilize a linguistic network and a feed-forward neural network to generate features suitable for determining a functional class.
With further reference to FIG. 4, a flow 400 of one embodiment of a method of training a function to determine a network is shown. The process 400 includes the following steps:
In this embodiment, an execution subject (for example, a server or a terminal device shown in fig. 1) on which the processing method of the table runs may determine the loss value of the function determination network by using the function class of the cell output from the classifier, the function class label of the cell in the table sample, and the loss function. And training the function determination network to be trained by using the loss value. The resulting trained function determination network may be used to implement the table processing methods of the present disclosure.
In practice, the function determination network to be trained may be a pre-trained language network, such as pre-trained ernie.
In the embodiment, the structural element features and the text element features are extracted from the table, so that more comprehensive information extraction is realized, and a model capable of accurately judging the cell function is trained.
Optionally, the training objectives include features of a convergence function determination network and optimization structure elements; the generating step of the feature of the structural element includes: randomly initializing the structural elements of the cells into vectors with the same dimensionality as the characteristics of the text elements, and taking the vectors as the characteristics of the structural elements; the method further comprises the following steps: and optimizing the characteristics of the structural elements of the cells by using the functional categories and the functional category labels of the table samples to obtain an optimization result, wherein the optimization result is used for generating a vectorization tool for determining the characteristics of the structural elements.
Specifically, any electronic device may randomly initialize the structural element, where the initialization is limited to the condition that the initialization result is the same as the dimension of the feature of the text element. In the training process, the execution main body utilizes the function type and the function type label output by the classifier, so that the function determination network can be converged, the function determination network has the capability of determining the cell function, and the characteristics of the structural elements can be optimized and modified. In addition, the execution subject may further optimize the features of the text elements by using the function categories and the function category labels output by the classifier, that is, the training target may further include features that optimize the text structure elements. The optimization results from optimizing the features of the structural elements may be used to generate a vector table of the structure described above. The optimization results from optimizing the characteristics of the text elements may be used to generate the vector table of text described above.
The implementation modes can optimize the characteristics of the structural elements while converging the function determination network, and the optimization result can be used in prediction by using the function determination network, so that more accurate characteristics of the structural elements are obtained, and the accuracy of network prediction is improved.
With further reference to fig. 5, as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of a device for processing a table, which corresponds to the method embodiment shown in fig. 2, and which may include the same or corresponding features or effects as the method embodiment shown in fig. 2, in addition to the features described below. The device can be applied to various electronic equipment in particular.
As shown in fig. 5, the processing apparatus 500 of the table of the present embodiment includes: a determination unit 501, an input unit 502 and a classification unit 503. The determining unit 501 is configured to determine element features of cells in the table, where the element features include features of structural elements and features of text elements; an input unit 502 configured to input the element characteristics of the cells in the table into the function determination network, resulting in the function characteristics of the cells in the table; a classification unit 503 configured to input the functional features of the cells in the table into the classifier, resulting in functional categories of the cells in the table.
In this embodiment, specific processing of the determining unit 501, the input unit 502, and the classifying unit 503 of the table processing apparatus 500 and the technical effects thereof can refer to the related descriptions of step 201, step 202, and step 203 in the corresponding embodiment of fig. 2, which are not repeated herein.
In some optional implementations of the embodiment, the determining unit is further configured to perform determining the element characteristics of the cells in the table as follows: vectorizing the text elements and the structural elements of the cells in the table to obtain the features of the text elements and the features of the structural elements; and adding the characteristics of the text elements and the characteristics of the structural elements to obtain the element characteristics of the cells in the table.
In some optional implementations of this embodiment, the text element includes a word-cutting result of the text within the cell; the structural elements include row positions, column positions, or cell numbers.
In some optional implementations of this embodiment, the function determination network includes a language network and a feed-forward neural network; an input unit further configured to perform inputting the element characteristics of the cells in the table into the function determination network, resulting in the function characteristics of the cells in the table, as follows: inputting the element characteristics of the cells in the table into a language network to obtain a language processing result vector of the element characteristics; and inputting the language processing result vector into a feedforward neural network to obtain the functional characteristics of the cell.
As an implementation of the method shown in fig. 4, the present disclosure provides an embodiment of an apparatus for training a function determination network, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 4, and besides the features described below, the embodiment of the apparatus may further include the same or corresponding features or effects as the embodiment of the method shown in fig. 4. The device can be applied to various electronic equipment.
The apparatus for determining a network by a training function of the present embodiment includes: the device comprises an acquisition unit, a forward unit, an input unit and a training unit. The obtaining unit is configured to obtain element characteristics of cells in the table sample, wherein the element characteristics comprise characteristics of structural elements and characteristics of text elements; the forward unit is configured to input the element characteristics of the cells in the table sample into a function determination network to be trained to obtain the function characteristics of the cells in the table sample; the output unit is configured to input the functional characteristics of the cells in the table sample into the classifier to obtain the functional categories of the cells in the table sample; and the training unit is configured to train the function determination network to be trained by using the function type and the function type labels of the cells in the table sample to obtain the trained function determination network.
In this embodiment, specific processes of the obtaining unit, the forward unit, the input unit, and the training unit of the device for determining a network by the training function and technical effects brought by the specific processes may respectively refer to relevant descriptions of step 401, step 402, step 403, and step 404 in the corresponding embodiment of fig. 4, and are not described herein again.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
As shown in fig. 6, is a block diagram of an electronic device of a method of processing a table according to an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing some of the necessary operations (e.g., as an array of servers, a group of blade servers, or a multi-processor system). In fig. 6, one processor 601 is taken as an example.
The memory 602 is a non-transitory computer readable storage medium provided by the present disclosure. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of processing the table provided by the present disclosure. The non-transitory computer-readable storage medium of the present disclosure stores computer instructions for causing a computer to execute a method of processing a table provided by the present disclosure.
The memory 602, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the processing method of the table in the embodiment of the present disclosure (for example, the determination unit 501, the input unit 502, and the classification unit 503 shown in fig. 5). The processor 601 executes various functional applications of the server and data processing, i.e., a processing method of the table in the above method embodiment, by running the non-transitory software programs, instructions, and modules stored in the memory 602.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the processing electronics of the table, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 optionally includes memory located remotely from the processor 601, which may be connected to the processing electronics of the table via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the form processing method may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected by a bus or other means, and fig. 6 illustrates the connection by a bus as an example.
The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the processing electronics of the form, such as a touch screen, keypad, mouse, track pad, touch pad, pointer stick, one or more mouse buttons, track ball, joystick, or other input device. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server may be a cloud Server, which is also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service extensibility in a traditional physical host and a VPS service ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server incorporating a blockchain.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a determination unit, an input unit, and a classification unit. Where the names of these cells do not in some cases constitute a limitation on the cell itself, for example, a determination cell may also be described as a "cell that determines an element characteristic of a cell in a table".
As another aspect, the present disclosure also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: determining element characteristics of cells in the table, wherein the element characteristics comprise characteristics of structural elements and characteristics of text elements; inputting the element characteristics of the cells in the table into a function determination network to obtain the function characteristics of the cells in the table; and inputting the functional characteristics of the cells in the table into the classifier to obtain the functional categories of the cells in the table.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept as defined above. For example, the above features and the technical features disclosed in the present disclosure (but not limited to) having similar functions are replaced with each other to form the technical solution.
Claims (15)
1. A method of processing a form, the method comprising:
determining element characteristics of cells in a table, wherein the element characteristics comprise characteristics of structural elements and characteristics of text elements;
inputting the element characteristics of the cells in the table into a function determination network to obtain the function characteristics of the cells in the table;
and inputting the functional characteristics of the cells in the table into a classifier to obtain the functional categories of the cells in the table.
2. The method of claim 1, wherein the determining the elemental characteristics of the cells in the table comprises:
vectorizing the text elements and the structural elements of the cells in the table to obtain the features of the text elements and the features of the structural elements;
and adding the characteristics of the text elements and the characteristics of the structural elements to obtain the element characteristics of the cells in the table.
3. The method of claim 1 or 2, wherein a text element comprises a word-cut result of text within a cell; the structural elements include row positions, column positions, or cell numbers.
4. The method of claim 1, wherein the function determination network comprises a linguistic network and a feed-forward neural network;
the inputting the element characteristics of the cells in the table into the function determination network to obtain the function characteristics of the cells in the table includes:
for the element characteristics of the cells in the table, inputting the element characteristics into the language network to obtain a language processing result vector of the element characteristics;
and inputting the language processing result vector into the feedforward neural network to obtain the functional characteristics of the cell.
5. A method of training a function determination network, wherein the method comprises:
acquiring element characteristics of cells in a table sample, wherein the element characteristics comprise characteristics of structural elements and characteristics of text elements;
inputting the element characteristics of the cells in the table sample into a function determination network to be trained to obtain the function characteristics of the cells in the table sample;
inputting the functional characteristics of the cells in the table sample into a classifier to obtain the functional categories of the cells in the table sample;
and training the function determination network to be trained by using the function types and the function type labels of the cells in the table sample to obtain the trained function determination network.
6. The method of claim 5, wherein the training objectives comprise features of a convergence function determination network and optimization structure elements;
the step of determining the characteristics of the structural elements comprises:
randomly initializing the structural elements of the cells into vectors with the same dimension as 9 of the features of the text elements, and taking the vectors as the features of the structural elements;
the method further comprises the following steps:
and optimizing the characteristics of the structural elements of the cells by using the function types and the function type labels of the table samples to obtain an optimization result, wherein the optimization result is used for generating a vectorization tool, and the vectorization tool is used for determining the characteristics of the structural elements.
7. An apparatus for processing a form, the apparatus comprising:
a determining unit configured to determine element features of cells in a table, wherein the element features include features of structural elements and features of text elements;
the input unit is configured to input the element characteristics of the cells in the table into the function determination network to obtain the function characteristics of the cells in the table;
and the classification unit is configured to input the functional characteristics of the cells in the table into the classifier to obtain the functional categories of the cells in the table.
8. The apparatus of claim 7, wherein the determining unit is further configured to perform the determining the element characteristics of the cells in the table as follows:
vectorizing the text elements and the structural elements of the cells in the table to obtain the features of the text elements and the features of the structural elements;
and adding the characteristics of the text elements and the characteristics of the structural elements to obtain the element characteristics of the cells in the table.
9. The apparatus of claim 7 or 8, wherein a text element comprises a word-cutting result of text within a cell; the structural elements include row positions, column positions, or cell numbers.
10. The apparatus of claim 7, wherein the function determination network comprises a linguistic network and a feed-forward neural network;
the input unit is further configured to perform the step of inputting the element characteristics of the cells in the table into the function determination network to obtain the function characteristics of the cells in the table as follows:
for the element characteristics of the cells in the table, inputting the element characteristics into the language network to obtain a language processing result vector of the element characteristics;
and inputting the language processing result vector into the feedforward neural network to obtain the functional characteristics of the cell.
11. An apparatus for training a function determination network, wherein the apparatus comprises:
the obtaining unit is configured to obtain element characteristics of cells in the table sample, wherein the element characteristics comprise characteristics of structural elements and characteristics of text elements;
a forward unit configured to input the element features of the cells in the table sample into a function determination network to be trained, so as to obtain the function features of the cells in the table sample;
the output unit is configured to input the functional characteristics of the cells in the table sample into the classifier to obtain the functional categories of the cells in the table sample;
and the training unit is configured to train the function determination network to be trained by using the function types and the function type labels of the cells in the table sample to obtain the trained function determination network.
12. The apparatus of claim 11, wherein the training objectives comprise features of a convergence function determination network and optimization structure elements;
the step of determining the characteristics of the structural elements comprises:
randomly initializing the structural elements of the cells into vectors with the same dimensionality as the characteristics of the text elements, and taking the vectors as the characteristics of the structural elements;
the device further comprises:
and the optimization unit is configured to optimize the characteristics of the structural elements of the cell by using the function categories and the function category labels of the table samples to obtain an optimization result, wherein the optimization result is used for generating a vectorization tool, and the vectorization tool is used for determining the characteristics of the structural elements.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.
15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210591758.1A CN114969258A (en) | 2022-05-27 | 2022-05-27 | Table processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210591758.1A CN114969258A (en) | 2022-05-27 | 2022-05-27 | Table processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114969258A true CN114969258A (en) | 2022-08-30 |
Family
ID=82958202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210591758.1A Pending CN114969258A (en) | 2022-05-27 | 2022-05-27 | Table processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114969258A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113486177A (en) * | 2021-07-12 | 2021-10-08 | 贵州电网有限责任公司 | Electric power field table column labeling method based on text classification |
| CN113553326A (en) * | 2021-06-21 | 2021-10-26 | 深圳市金蝶天燕云计算股份有限公司 | Spreadsheet data processing method, device, computer equipment and storage medium |
| CN113723278A (en) * | 2021-08-27 | 2021-11-30 | 上海云从汇临人工智能科技有限公司 | Training method and device of form information extraction model |
| US20210406452A1 (en) * | 2020-06-30 | 2021-12-30 | Siemens Aktiengesellschaft | Computer-implemented method and apparatus for automatically annotating columns of a table with semantic types |
| CN113901216A (en) * | 2021-10-08 | 2022-01-07 | 北京百度网讯科技有限公司 | Data annotation method, table information extraction method, device and electronic equipment |
| CN113989822A (en) * | 2021-12-24 | 2022-01-28 | 中奥智能工业研究院(南京)有限公司 | Picture table content extraction method based on computer vision and natural language processing |
-
2022
- 2022-05-27 CN CN202210591758.1A patent/CN114969258A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210406452A1 (en) * | 2020-06-30 | 2021-12-30 | Siemens Aktiengesellschaft | Computer-implemented method and apparatus for automatically annotating columns of a table with semantic types |
| CN113553326A (en) * | 2021-06-21 | 2021-10-26 | 深圳市金蝶天燕云计算股份有限公司 | Spreadsheet data processing method, device, computer equipment and storage medium |
| CN113486177A (en) * | 2021-07-12 | 2021-10-08 | 贵州电网有限责任公司 | Electric power field table column labeling method based on text classification |
| CN113723278A (en) * | 2021-08-27 | 2021-11-30 | 上海云从汇临人工智能科技有限公司 | Training method and device of form information extraction model |
| CN113901216A (en) * | 2021-10-08 | 2022-01-07 | 北京百度网讯科技有限公司 | Data annotation method, table information extraction method, device and electronic equipment |
| CN113989822A (en) * | 2021-12-24 | 2022-01-28 | 中奥智能工业研究院(南京)有限公司 | Picture table content extraction method based on computer vision and natural language processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112560912B (en) | Classification model training method and device, electronic equipment and storage medium | |
| CN111523326B (en) | Entity chain finger method, device, equipment and storage medium | |
| CN111428507B (en) | Entity chain finger method, device, equipment and storage medium | |
| CN111507104B (en) | Method and device for establishing label labeling model, electronic equipment and readable storage medium | |
| CN111191428B (en) | Comment information processing method and device, computer equipment and medium | |
| CN111967262A (en) | Method and device for determining entity tag | |
| CN111428514A (en) | Semantic matching method, device, equipment and storage medium | |
| CN110705460A (en) | Image category identification method and device | |
| CN111522944A (en) | Method, apparatus, device and storage medium for outputting information | |
| CN111104514A (en) | Method and device for training document label model | |
| CN111667056A (en) | Method and apparatus for searching model structure | |
| CN110543558B (en) | Question matching method, device, equipment and medium | |
| CN111611990A (en) | Method and device for identifying table in image | |
| CN111782785B (en) | Automatic question and answer method, device, equipment and storage medium | |
| CN112507090A (en) | Method, apparatus, device and storage medium for outputting information | |
| CN111127191A (en) | Risk assessment method and device | |
| CN112380847A (en) | Interest point processing method and device, electronic equipment and storage medium | |
| CN112529180A (en) | Method and apparatus for model distillation | |
| CN112507702A (en) | Text information extraction method and device, electronic equipment and storage medium | |
| CN111858905A (en) | Model training method, information identification method, device, electronic equipment and storage medium | |
| CN111523019B (en) | Method, apparatus, device and storage medium for outputting information | |
| CN111783427A (en) | Method, device, equipment and storage medium for training model and outputting information | |
| CN113342946B (en) | Model training method and device for customer service robot, electronic equipment and medium | |
| CN113157829A (en) | Method and device for comparing interest point names, electronic equipment and storage medium | |
| CN111385188A (en) | Recommendation method and device for dialog elements, electronic equipment and medium |
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 |