CN109284480B - Service document processing method, device and server - Google Patents
Service document processing method, device and server Download PDFInfo
- Publication number
- CN109284480B CN109284480B CN201810840526.9A CN201810840526A CN109284480B CN 109284480 B CN109284480 B CN 109284480B CN 201810840526 A CN201810840526 A CN 201810840526A CN 109284480 B CN109284480 B CN 109284480B
- Authority
- CN
- China
- Prior art keywords
- block
- sub
- semantic
- business
- blocks
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 25
- 238000000926 separation method Methods 0.000 claims abstract description 129
- 230000009471 action Effects 0.000 claims abstract description 99
- 238000000034 method Methods 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 8
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000001072 colon Anatomy 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/117—Tagging; Marking up; Designating a block; Setting of attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/258—Heading extraction; Automatic titling; Numbering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The specification discloses a business document processing method, a device and a server, comprising: identifying a first type separation identifier in the business semantic block, wherein the first type separation identifier separates the business semantic block into a plurality of semantic sub-blocks; and identifying a program action sub-block from the plurality of semantic sub-blocks based on the first type separation identification, and using an operation object sub-block corresponding to the program action sub-block.
Description
Technical Field
The present disclosure relates to the field of computers, and in particular, to a method, an apparatus, and a server for processing a service document.
Background
Many scenarios require the business knowledge, expert experience, etc. to be saved to form a business knowledge document. When the same business needs to be processed later, the business is executed according to fixed steps in the business knowledge document. With the development of artificial intelligence, it is desirable that a computer be able to understand business knowledge documents and automatically perform fixed steps in the business knowledge documents. To enable a computer to understand business knowledge, currently, business knowledge documents are converted into machine steps by programmers or programmed script descriptions are learned by experts. In the artificial intelligence field, the semantics of the business knowledge document are understood through pure algorithms.
Disclosure of Invention
The embodiment of the specification provides a business document processing method, a business document processing device and a server.
In a first aspect, an embodiment of the present disclosure provides a business document processing method, including:
identifying a first type separation identifier in a business semantic block, wherein the first type separation identifier separates the business semantic block into a plurality of semantic sub-blocks, and the business semantic block belongs to the business document;
and identifying a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation identification.
In a second aspect, embodiments of the present disclosure provide a business document processing apparatus, including:
the identification unit is used for identifying a first type separation identification in a business semantic block, wherein the first type separation identification separates the business semantic block into a plurality of semantic sub-blocks, and the business semantic block belongs to the business document;
the semantic identification unit is used for identifying a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation identification.
In a third aspect, embodiments of the present description provide a server comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of the first aspects when the program is executed.
One or more technical solutions provided in the embodiments of the present disclosure at least have the following technical effects or advantages:
according to the business document processing method, the business document processing device and the server, the first type separation mark separates the business semantic block into a plurality of semantic sub-blocks, and the program action sub-block and the operation object sub-block corresponding to the program action sub-block are identified from the plurality of semantic sub-blocks based on the first type separation mark. Therefore, the first type separation mark enables the machine to identify which parts in the business document are program actions to be executed and which parts are operation objects corresponding to the executed program actions, so that the machine can accurately understand the business document, and steps in the business document can be automatically executed, and the method is more accurate and efficient.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present specification, the drawings that are needed in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present specification, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of a scenario in which a business document processing method is implemented in the present specification;
FIG. 2 is a flowchart of a business document processing method provided in the first aspect of the embodiments of the present disclosure;
FIG. 3 is a schematic diagram of a specific implementation of a business document processing method in the first aspect in the embodiment of the present disclosure;
FIG. 4 is a schematic structural view of an identification code distribution device according to a second aspect of the embodiments of the present disclosure;
fig. 5 is a schematic structural diagram of a server according to a third aspect of the embodiments of the present disclosure.
Detailed Description
In order to better understand the technical solutions described above, the technical solutions of the embodiments of the present specification are described in detail below through the accompanying drawings and the specific embodiments, and it should be understood that the specific features of the embodiments of the present specification and the specific features of the embodiments of the present specification are detailed descriptions of the technical solutions of the embodiments of the present specification, and not limit the technical solutions of the present specification, and the technical features of the embodiments of the present specification may be combined without conflict.
Referring to fig. 1, fig. 1 is a schematic view of a scenario in which a business document processing method is implemented in the present specification: the local device 100, the local device 100 is provided with a business document processing system 101, which is used for automatically understanding and executing steps in a business document.
In some implementations, the home device 100 needs to communicate with more than one peer device 200. The service processing system 201 on the peer device 200 is configured to respond to a service request generated by the local device 100 executing a step in a service document, and feed back a response result to the local device 100. In particular, the peer device 200 may be specifically another server for providing services. For example, the peer device 200 may be: and the search server is used for responding to the search related request initiated in the process of executing the business document by the local terminal equipment 100. The opposite terminal device 200 may be a data input platform, and is configured to respond to a data input request initiated during the process of executing a business document by the local terminal device 100, so as to complete data input in the data input platform. It should be noted that, the specific type of the peer device 200 varies according to the specific content of the service document, and the embodiment of the present disclosure does not exemplify the type of the peer device 200.
Of course, there are also scenarios where the home terminal device 100 does not need to communicate with the peer terminal device 200, and the checking of the home terminal device 100 itself or the stored content on the home terminal device 100 is done based on the steps in the business document being understood and automatically performed by the business document processing system 101. For example, the analysis process of a fault on the local terminal device 100 is completed; for example, detection of the program content stored on the local device 100 is completed.
Many scenes need to save business knowledge, expert experience and the like in a document mode to form a business document. When the same business needs to be processed later, the steps in the business document are followed. With the development of artificial intelligence, it is desirable that a computer be able to understand a business document and automatically execute steps in the business document. For example, automatically performing based on a business document: an item on-line inspection item, a fault analysis process, etc. Through the first type separation mark in the business document, the machine can accurately understand which parts in the business document are program actions to be executed and which parts are operation objects corresponding to the program actions, so that the machine can accurately understand the business document and can more efficiently and accurately automatically execute the steps in the business document.
In a first aspect, an embodiment of the present disclosure provides a business document processing method, which is applied to a home terminal apparatus 100. Referring to fig. 2, the business document processing method includes the following steps S202 to S204:
s202: a first type of separation identifier in the business semantic block is identified, the first type of separation identifier separating the business semantic block into a plurality of semantic sub-blocks.
The business semantic block belongs to a business document, and the language of the business document can be a document formed by Chinese, english and other user readable languages. The business document is composed of more than one business content item, and the business content item is composed of more than one semantic sub-block.
In the present description embodiment, the business semantic blocks are determined from the business document. In an alternative embodiment, the business semantic blocks are obtained from the business document by:
step 02: and reading the business document, wherein the business document is divided into N business content items based on a preset format identifier, and N is an integer greater than or equal to 1.
In the embodiment of the present specification, the N service content items may have an execution sequence, or may be executed independently without being sequenced.
In an alternative embodiment, the preset format identifier may be an item number for the service content item, and the N service content items each have an item number. The embodiments of the present disclosure are not limited to the form of item numbers, and in particular implementations, item numbers may be numeric numbers, alphabetic numbers, or combination numbers. For example, the business document may be in the following style, but is not limited to the following style:
"XX Automation Process
1. Business content item a
2. Business content item B
3. Business content item C'
In another alternative embodiment, the preset format identifier may be a paragraph identifier for the service content item, so that the N service content items are each paragraphs. For example, paragraph identification may be: the k characters are indented. For example, two characters are indented, one character is indented, and so on.
Step 04: n business content items of the business document are determined based on the preset format identification.
In step 04, the current preset format identifier and the next preset format identifier may be identified, and the content between the current preset format identifier and the next preset format identifier is determined to be the service content item. And if the next preset format identifier is not identified, determining the content after the current preset format identifier as a service content item. Thus, N business content items of the business document are determined.
Step 06: more than one business semantic block is identified from the N business content items based on the second type of separation identification.
In the present description embodiment, the second type of separation mark is different from the first type of separation mark. There are no second type separation identities in the service content item, and there are also one or more second type separation identities.
In a specific implementation, the second type of separation mark includes a first portion and a second portion, and there may be no sequence between the first portion and the second portion. The first part of the second type separation mark belongs to a semantic punctuation mark in the business document, and the second part of the second type separation mark is a first specific separation mark which is different from the semantic punctuation mark. For example, a first specific separation sign is adjacent after the semantic punctuation mark, and then the separation sign is a second type separation mark in the business content item.
In the illustrated embodiment, adjacent business semantic blocks in a business content item are separated by semantic punctuation marks. The semantic punctuation is specifically a chinese punctuation, such as: periods of periods. ", comma", exclamation mark "-! ", semicolon"; ", colon": "Chinese sentence-breaking symbol.
In an alternative embodiment, the following steps are performed on N service content items respectively, and service semantic blocks are identified from each service content item respectively by the following implementation procedure:
analyzing whether a second type separation mark exists in the business content item; identifying the business content item, if present, as a plurality of business semantic blocks separated based on a second type separation identity; otherwise, it is determined that the service content item includes a single service semantic block. Specifically, if P-1 second type separation identifiers exist in the service content item, the service content item is contained with P service semantic blocks separated by the P-1 second type separation identifiers, and P is an integer greater than 1.
For example, the service content item is "input ΔΔ needs to apply for patent title in website search field, ΔΔ clicks button search". The patent titles of the 'patent titles requiring DeltaDeltaA' and the 'click button search' input in the website search column are adjacent business semantic blocks in the same business content item, and the adjacent business semantic blocks are separated by commas, adding first specific separation symbols delta adjacent to the commas as second type separation marks.
In the specific implementation process, analyzing whether semantic punctuation marks are in the business content items; if the semantic punctuation mark exists in the business content item, judging whether a first specific separation mark adjacent to the semantic punctuation mark exists, and if the first specific separation mark adjacent to the semantic punctuation mark exists, determining that the semantic punctuation mark and the adjacent first specific separation mark form a second type separation mark, namely: the presence of a second type of separation identity in the service content item is analyzed.
Through the steps 02-06, the business content item can be accurately identified from the business document, and the business semantic block can be accurately identified from the business content item on the basis, so that the accuracy of machine understanding of the business document is improved.
Further, the embodiment of the present specification also provides the following implementation procedure: if the second type separation mark exists in the business content item, discarding semantic punctuation marks adjacent to the first specific separator in the second type separation mark of the business content item when the business content item is executed, so that the business content item does not influence the reading and understanding of a user, and meanwhile, a machine algorithm can accurately understand the business content item.
Specifically, the first specific separation symbol may be (), { }, $, @, etc., and in an alternative implementation manner of the embodiment of the present specification, the first specific separation symbol is more than two consecutive space symbols. Thus, the reading and understanding of the business document by the user are not affected at all. For example, the first specific separation symbol can be two continuous space symbols after the semantic punctuation mark, so that the separation can be realized by distinguishing the first specific separation symbol from the independent space symbol, and the influence on the reading of the business document by the user is avoided to the greatest extent.
S204: based on the first type separation identification, a program action sub-block and an operation object sub-block corresponding to the program action sub-block are identified from the plurality of semantic sub-blocks.
In the embodiment of the present specification, the first type of separation mark is specifically: a second specific separator that is different from the semantic punctuation in the business document. The second specific separator may be (), { }, $, @, etc., and in an alternative embodiment of the present disclosure, the first specific separator symbol is two or more consecutive space symbols, so as not to affect the user's reading understanding of the business document.
In particular, the first specific separator and the second specific separator may be the same symbol, for example, two or more continuous space symbols.
In the embodiment of the present specification, the program action sub-block is specifically used for: and inputting an operation object in the target dialog box and/or performing touch operation on the operation object. The operation object is a network link or a virtual operation area corresponding to the program action sub-block. Specifically, the program action sub-block may be a program action sub-block for inputting a network link in a target dialog box, which is an in-website input box or a browser address input box. The program action sub-block may be a program action sub-block for performing touch operation on a virtual operation area, and the virtual operation area may be a virtual button.
In the implementation process, the first type separation identifier may not exist in the business semantic block, and one or more first type separation identifiers may also exist.
For example, the first type separation identifier does not exist in the service semantic block, which may be the case that the program action of the service semantic block does not need a corresponding operation object, for example, the browser is opened to be a program action sub-block without a corresponding operation object, and the first type separation identifier is not required to be set in the service semantic block. If the service semantic block does not have the first type separation identifier, the service semantic block is directly understood and executed without executing steps S202-S204.
For the case that one or more first type separation identifiers exist in the business semantic blocks, identifying a program action sub-block and an operation object sub-block corresponding to the program action sub-block from a plurality of semantic sub-blocks based on the first type separation identifiers, wherein the method comprises the following steps:
identifying M semantic sub-blocks from the service semantic blocks based on first type separation identifications in the service semantic blocks, wherein the service semantic blocks are separated into M semantic sub-blocks based on M-1 first type separation identifications, and M is an integer greater than 1; determining a semantic sub-block in a first preset position in the M semantic sub-blocks as a program action semantic sub-block; and determining the semantic sub-block in a second preset position in the M semantic sub-blocks as an operation object corresponding to the program action semantic sub-block, wherein the second preset position is different from the first preset position.
Specifically, the first preset position is one side of the first type separation mark, and the second preset position is the other side of the first type separation mark. In a specific implementation process, one program action sub-block in the service semantic block may correspond to one or more operation objects. The plurality of program action sub-blocks may correspond to one operation object.
In an alternative embodiment, the program action sub-blocks are in one-to-one correspondence with the operation objects, and the implementation process of step S204 is specifically as follows:
Identifying two semantic sub-blocks separated by a first type separation identifier from the business semantic block based on the first type separation identifier in the business semantic block; identifying the semantic subblocks positioned on the first side of the first type separation mark as program action subblocks; and identifying the semantic sub-blocks of which the two semantic sub-blocks are positioned on the second side of the first type separation mark as operation objects corresponding to the program action sub-blocks.
Specifically, the first side of the first type separation mark is the adjacent position before the first type separation mark; correspondingly, the second side of the second type of separation mark may be an adjacent position after the first type of separation mark. Then: and identifying the semantic sub-block positioned before the first type separation mark as a program action sub-block, and identifying the semantic sub-block positioned after the first type separation mark as an operation object corresponding to the program action sub-block.
For example, the business semantic block inputs delta http in the browser address bar: the// www2. Sooppat. Com ", separated into semantic sub-blocks based on two consecutive space symbols: "enter in browser address bar" and "http:// www2. Sooppat. Com". The input of the browser address bar is identified as a program action sub-block, and the input of the http:// www2.Soopat. Com is identified as an object of the program action sub-block in the browser address bar.
For example, a business semantic block "click button ΔΔ search" is separated into semantic sub-blocks based on two consecutive space symbols: "click button" and "search". The clicking button is identified as a program action sub-block, and the searching is identified as a virtual operation area corresponding to the program action clicking button.
Further, after the program action sub-block and the operation object sub-block corresponding to the program action sub-block are identified, the implementation process of the automatic execution service semantic block is further included, and the following explanation is made on the process of automatically executing the service semantic block according to different scenes:
if the execution service semantic block is applied to a scenario related to the peer device, the implementation procedure is as follows: executing the program action represented by the program action sub-block on the operation object in the operation object sub-block to generate a service request sent to the opposite terminal equipment; and obtaining a response result of the opposite terminal equipment to the service request. If the next service semantic block exists, after a response result of the opposite terminal equipment to the service request is obtained, automatically executing the next service semantic block; and circulating until the business document is finished.
If the execution service semantic block is a scene irrelevant to the opposite terminal equipment, the implementation process is as follows: executing the program action represented by the program action sub-block on the operation object in the operation object sub-block to finish the checking action of the storage content on the local terminal equipment or the local terminal electronic equipment to obtain a checking result; understanding and automatically executing the next business semantic block to obtain a next checking result; and circulating until the business document is finished.
It should be noted that, the business document may further include a business semantic block that does not conform to the operation object sub-block corresponding to the program action sub-block, so in order to further accurately execute the business semantic block, the following implementation process may further include:
identifying whether a judgment prompt sub-block exists in a plurality of semantic sub-blocks of the business semantic block; if the judgment prompt sub-block exists, determining semantic sub-blocks adjacent to the judgment prompt sub-block as judgment result sub-blocks; if the judgment prompt sub-block does not exist, step S202 is performed to identify a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation identification.
In an alternative embodiment, it may be determined whether it is a judgment hint sub-block based on semantic recognition:
comparing the identified semantic subblocks with characters in a preset set, and if the semantic subblocks are the same as the characters in the preset set, taking the semantic subblocks as judgment prompt subblocks. For example, the "if", "if" and so on semantic sub-blocks may be determined as judgment hint sub-blocks.
After determining the semantic sub-block adjacent to the judgment hint sub-block as the judgment result sub-block, the method further comprises: determining the next adjacent semantic sub-block with the judgment result sub-block as a business execution sub-block corresponding to the judgment result sub-block; and executing the business content corresponding to the business execution sub-block when the judging result of the specific content meets the condition of the judging result sub-block representation.
Specifically, the judgment result of the specific content may be: from the response results for the peer device or from the inspection results for the local device.
Specifically, the judgment result sub-block is a sub-block adjacent to the judgment prompt sub-block, and the service execution sub-block is a sub-block adjacent to the judgment result sub-block. For example, "if the ΔΔ search result is equal to zero, ΔΔ refers to the patent platform submitting a patent application" judging prompt sub-block is "if", adjacent to which is a judging result sub-block "search result is equal to zero", adjacent to which is a business execution sub-block "to the patent platform submitting a patent application". If the search result is equal to zero, then the business content of the submitted patent application to the patent platform is executed.
Next, a process for implementing patent automation application based on the technical scheme provided in the embodiment of the present specification is given with reference to fig. 3:
first, the business document is as follows:
"patent Automation application Process
1. Opening a browser
2. Inputting DeltaDeltahttp:// www2. Sooptat.com in browser address bar
3. Inputting patent titles needing to be applied for delta in a website search column, and searching for delta by delta clicking a button delta SooPAT
4. If the ΔΔ search result is equal to zero, ΔΔ submits the patent application to the patent platform
Patent application flow to patent platform
41. Opening a browser
42. Inputting DeltaDeltahttp:// siehdq=AQxRG-0000 & query in browser address bar
43. Beginning to enter patent "
The user submits a patent application with patent title of 'patent title', and triggers the business document processing system 101 of the local terminal device 100 to read the business document of 'patent automation application flow', and identify the business content item 1: "open browser", program actions for opening the browser are automatically executed.
Next, the business document processing system 101 recognizes the business content item 2: "at browser Address column input delta Δhttp: the program action is identified by the 'input in browser address bar', the 'http:// ww2.Soopat. Com' is identified as the corresponding network link to be input in browser address bar, the search server 210 receives the request of entering the website carrying the 'http:// ww2.Soopat. Com', and feeds back the corresponding website page of the network link 'http:// ww2.Soopat. Com' to the local terminal device 100.
Next, the business document processing system 101 identifies business content item 3: the method comprises the steps of identifying a patent title required to be applied for by delta in a website search field, clicking a button delta SooPAT search by delta, identifying the patent title required to be applied for by delta in the website search field as a service semantic block, and identifying the button clicking the button delta SooPAT search as the service semantic block. Next, "inputting in the web site search field" of the "patent title requiring application for Δ" is identified as a program action, "inputting in the web site search field of the" patent title requiring application "is identified as an operation object corresponding to the" inputting in the web site search field "of the program action," clicking a "button" in the button Δ sonopat search "is identified as a program action, and" sonopat search "is identified as a virtual operation area corresponding to the clicking button program action. Such that the search server 210 receives a search request carrying a patent title "xxxx" of a desired application, searches patent websites 300 for patent applications whose patent title contains "xxxx" based on the search engine 211, and feeds back the search result to the home terminal apparatus 100.
Next, the business document processing system 101 identifies business content item 4: "if the ΔΔ search result is equal to zero, ΔΔ submits a patent application to the patent platform. Identifying a judgment prompt subblock "if", determining whether the search result fed back by the search server 210 satisfies "search result equals zero", and if so, executing the program action of the identified service execution subblock: "submit patent application to patent platform".
Then, the process jumps to "to patent platform submit patent application procedure", and the business document processing system 101 identifies the business content item 41: "open browser" and perform the program action of opening the browser.
Next, the business document processing system 101 identifies the business content item 42: "at browser Address column input delta Δhttp: the patent platform 220 receives the request to enter the website, and feeds back the website page with the network link of 'http:// siehdq=aqxrg-0000 & query' to the local terminal device 100.
Finally, the business document processing system 101 identifies the business content item 43: the "begin entering patent" enters a patent application entitled "patent title" to a patent filed by a user based on a patent filing system 221 in the patent platform. Thus, the patent automation application process is completed.
In a second aspect, embodiments of the present disclosure provide a business document processing apparatus, as shown in fig. 4, including:
an identifier identifying unit 401, configured to identify a first type separation identifier in a service semantic block, where the first type separation identifier separates the service semantic block into a plurality of semantic sub-blocks, and the service semantic block belongs to a service document;
the semantic identification unit 402 is configured to identify a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation identifier.
In an alternative embodiment, the apparatus further comprises:
the execution unit is used for executing the program action represented by the program action sub-block on the operation object in the operation object sub-block and generating a service request sent to the opposite terminal equipment;
the result acquisition unit is used for acquiring a response result of the opposite terminal equipment to the service request.
In an alternative embodiment, the apparatus further comprises:
the prompt recognition unit is used for recognizing whether judgment prompt sub-blocks exist in the semantic sub-blocks or not;
the judging sub-block determining unit is used for determining the semantic sub-block adjacent to the judging prompt sub-block as a judging result sub-block if the recognition result of the prompting recognition unit is that the semantic sub-block exists; and if the recognition result of the prompt recognition unit is that the recognition result does not exist, executing the step of recognizing the program action sub-block and the operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation mark.
In an alternative embodiment, the apparatus further comprises:
an execution sub-block determining unit, configured to determine a semantic sub-block next adjacent to the judgment result sub-block as a service execution sub-block corresponding to the judgment result sub-block;
and the service execution unit is used for executing the service content corresponding to the service execution sub-block when the judging result of the specific content meets the condition of the judging result sub-block representation.
In an alternative embodiment, the semantic recognition unit 402 is specifically configured to:
based on first type separation identifications in the business semantic blocks, M semantic sub-blocks are identified from the business semantic blocks, the business semantic blocks are separated into M semantic sub-blocks based on M-1 first type separation identifications, and M is an integer greater than 1;
determining a semantic sub-block in a first preset position in the M semantic sub-blocks as a program action semantic sub-block;
and determining the semantic sub-block in a second preset position in the M semantic sub-blocks as an operation object corresponding to the program action semantic sub-block, wherein the second preset position is different from the first preset position.
In an alternative embodiment, the semantic recognition unit 402 is specifically configured to:
identifying two semantic sub-blocks separated by a first type separation identifier from the business semantic block based on the first type separation identifier in the business semantic block;
Identifying the semantic subblocks positioned on the first side of the first type separation mark as program action subblocks;
and identifying the semantic sub-blocks of which the two semantic sub-blocks are positioned on the second side of the first type separation mark as operation objects corresponding to the program action sub-blocks.
In an alternative embodiment, the apparatus further comprises:
the reading unit is used for reading the business document, wherein the business document is divided into N business content items based on a preset format identifier, and N is an integer greater than or equal to 1;
the content item determining unit is used for determining N business content items of the business document based on the preset format identification;
and the semantic block identification unit is used for identifying more than one business semantic block from the N business content items based on the second type separation identification.
In an alternative embodiment, the semantic block identification unit is specifically configured to perform the following steps on the business content item:
analyzing whether a second type separation mark exists in the business content item;
identifying the business content item, if present, as a plurality of business semantic blocks separated based on a second type separation identity; otherwise, it is determined that the service content item includes a single service semantic block.
In an alternative embodiment, the second type of separation mark comprises: a first portion and a second portion;
The first part belongs to a semantic punctuation mark in the business document, and the second part is a first specific separation symbol different from the semantic punctuation mark.
In an alternative embodiment, the apparatus further comprises:
and discarding the semantic punctuation marks adjacent to the first specific separator in the second type separator identifier when executing the service content item, if any.
In an alternative embodiment, the program action sub-block is specifically configured to:
inputting an operation object in a target dialog, and/or
And performing touch operation on the operation object.
In an alternative embodiment, the first type of separation mark is specifically: a second specific separator that is different from the semantic punctuation in the business document.
In a third aspect, based on the same inventive concept as the business document processing method in the foregoing embodiment, the present disclosure further provides a server, as shown in fig. 5, including a memory 504, a processor 502, and a computer program stored in the memory 504 and capable of running on the processor 502, where the processor 502 implements the steps described in any possible implementation manner of the foregoing business document processing method when executing the program.
Where in FIG. 5 a bus architecture (represented by bus 500), bus 500 may include any number of interconnected buses and bridges, with bus 500 linking together various circuits, including one or more processors, represented by processor 502, and memory, represented by memory 504. Bus 500 may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., as are well known in the art and, therefore, will not be described further herein. Bus interface 506 provides an interface between bus 500 and receiver 501 and transmitter 503. The receiver 501 and the transmitter 503 may be the same element, i.e. a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 502 is responsible for managing the bus 500 and general processing, while the memory 504 may be used to store data used by the processor 502 in performing operations.
In a fourth aspect, based on the same inventive concept as the business document processing method in the foregoing embodiment, the present specification further provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps described in any possible implementation manner of the foregoing business document processing method.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous
The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present description have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the disclosure.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present specification without departing from the spirit or scope of the specification. Thus, if such modifications and variations of the present specification fall within the scope of the claims and the equivalents thereof, the present specification is also intended to include such modifications and variations.
Claims (19)
1. A business document processing method, comprising:
identifying a first type separation identifier in a business semantic block, wherein the first type separation identifier separates the business semantic block into a plurality of semantic sub-blocks, the first type separation identifier is a second specific separator which is different from a semantic punctuation mark in the business document, the business semantic block belongs to the business document, and the second specific separator is a symbol in the business semantic block which does not influence reading and understanding of a user on the business document;
for the case that one or more first type separation identifiers exist in a business semantic block, identifying a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation identifiers, wherein the method comprises the following steps: m semantic sub-blocks are identified from the service semantic block based on first type separation identifications in the service semantic block, the service semantic block is separated into M semantic sub-blocks based on M-1 first type separation identifications, and M is an integer greater than 1; determining a semantic sub-block in a first preset position in the M semantic sub-blocks as a program action semantic sub-block; determining a semantic sub-block in a second preset position in the M semantic sub-blocks as an operation object corresponding to the program action semantic sub-block, wherein the second preset position is different from the first preset position;
And executing the program action characterized by the program action sub-block on the operation object in the operation object sub-block so as to automatically execute the steps in the business document.
2. The business document processing method of claim 1, further comprising, after said identifying a program action sub-block and an operation object sub-block corresponding to said program action sub-block from said plurality of semantic sub-blocks:
executing the program action represented by the program action sub-block on the operation object in the operation object sub-block to generate a service request sent to the opposite terminal equipment;
and obtaining a response result of the opposite terminal equipment to the service request.
3. The business document processing method of claim 1, further comprising, before said identifying a program action sub-block and an operation object sub-block corresponding to said program action sub-block from said plurality of semantic sub-blocks:
identifying whether a judgment prompt sub-block exists in the plurality of semantic sub-blocks;
if the judgment prompt sub-block exists, determining the semantic sub-block adjacent to the judgment prompt sub-block as a judgment result sub-block;
and if not, executing the step of identifying a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation mark.
4. The business document processing method of claim 3, wherein after said determining the semantic sub-block adjacent to the judgment-hint sub-block as a judgment result sub-block, further comprising:
determining the next adjacent semantic sub-block with the judging result sub-block as a service execution sub-block corresponding to the judging result sub-block;
and executing the business content corresponding to the business execution sub-block when the judging result of the specific content meets the condition represented by the judging result sub-block.
5. The business document processing method of claim 1, wherein the identifying a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation identifier, further comprises:
identifying two semantic sub-blocks separated by the first type separation mark from the service semantic block based on the first type separation mark in the service semantic block, wherein program action sub-blocks in the service semantic block are in one-to-one correspondence with operation objects;
identifying a semantic sub-block positioned on the first side of the first type separation mark in the two semantic sub-blocks as a program action sub-block;
And identifying the semantic sub-blocks of which the two semantic sub-blocks are positioned at the second side of the first type separation mark as operation objects corresponding to the program action sub-blocks, wherein the second side is different from the first side.
6. The business document processing method of any of claims 1-5, further comprising, prior to said identifying the first type of separation identity in the business semantic block:
reading a business document, wherein the business document is divided into N business content items based on a preset format identifier, and N is an integer greater than or equal to 1;
determining N business content items of the business document based on the preset format identifier;
more than one business semantic block is identified from the N business content items based on a second type of separation identification.
7. The business document processing method of claim 6, wherein the step of identifying more than one business semantic block from the N business content items based on the second type separation identification comprises: the following steps are performed on the business content item:
analyzing whether the second type separation mark exists in the business content item;
identifying the business content item, if present, as a plurality of the business semantic blocks separated based on the second type separation identity; otherwise, determining that the business content item comprises a single business semantic block.
8. The business document processing method of claim 7, wherein the second type separation mark comprises: a first portion and a second portion;
the first part belongs to a semantic punctuation mark in the business document, and the second part is a first specific separation symbol different from the semantic punctuation mark.
9. The business document processing method of claim 8, further comprising, after said analyzing whether said second type separation identity is present in said business content item:
and discarding semantic punctuation marks adjacent to the first specific separation symbol in the second type separation mark when executing the business content item if the first specific separation symbol exists.
10. A business document processing apparatus, comprising:
the identification unit is used for identifying a first type separation identification in a business semantic block, wherein the first type separation identification divides the business semantic block into a plurality of semantic sub-blocks, the first type separation identification is a second specific separator which is different from a semantic punctuation mark in the business document, the business semantic block belongs to the business document, and the second specific separator is a symbol which does not influence reading and understanding of a user on the business document in the business semantic block;
The semantic identification unit is configured to identify a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation identifier, where one or more first type separation identifiers exist in the service semantic block, and the semantic identification unit includes: m semantic sub-blocks are identified from the service semantic block based on first type separation identifications in the service semantic block, the service semantic block is separated into M semantic sub-blocks based on M-1 first type separation identifications, and M is an integer greater than 1; determining a semantic sub-block in a first preset position in the M semantic sub-blocks as a program action semantic sub-block; determining a semantic sub-block in a second preset position in the M semantic sub-blocks as an operation object corresponding to the program action semantic sub-block, wherein the second preset position is different from the first preset position;
and executing the program action characterized by the program action sub-block on the operation object in the operation object sub-block so as to automatically execute the steps in the business document.
11. The business document processing device of claim 10, further comprising:
The execution unit is used for executing the program action represented by the program action sub-block on the operation object in the operation object sub-block and generating a service request sent to the opposite terminal equipment;
and the result acquisition unit is used for acquiring a response result of the opposite terminal equipment to the service request.
12. The business document processing device of claim 10, further comprising:
the prompt recognition unit is used for recognizing whether judgment prompt sub-blocks exist in the semantic sub-blocks or not;
a judging sub-block determining unit, configured to determine, if the recognition result of the prompt recognition unit is that there is a semantic sub-block adjacent to the judging prompt sub-block as a judging result sub-block; and if the recognition result of the prompt recognition unit is that the first type separation identifier does not exist, executing the step of recognizing a program action sub-block and an operation object sub-block corresponding to the program action sub-block from the plurality of semantic sub-blocks based on the first type separation identifier.
13. The business document processing device of claim 12, further comprising:
an execution sub-block determining unit, configured to determine a semantic sub-block next adjacent to the judgment result sub-block as a service execution sub-block corresponding to the judgment result sub-block;
And the service execution unit is used for executing the service content corresponding to the service execution sub-block when the judging result of the specific content meets the condition represented by the judging result sub-block.
14. The business document processing device of claim 10, wherein the semantic recognition unit is further specifically configured to:
identifying two semantic sub-blocks separated by the first type separation mark from the service semantic block based on the first type separation mark in the service semantic block, wherein program action sub-blocks in the service semantic block are in one-to-one correspondence with operation objects;
identifying a semantic sub-block positioned on the first side of the first type separation mark in the two semantic sub-blocks as a program action sub-block;
and identifying the semantic sub-blocks of which the two semantic sub-blocks are positioned at the second side of the first type separation mark as operation objects corresponding to the program action sub-blocks.
15. The business document processing apparatus of any of claims 10-14, further comprising:
the reading unit is used for reading the business document, wherein the business document is divided into N business content items based on a preset format identifier, and N is an integer greater than or equal to 1;
A content item determining unit, configured to determine N service content items of the service document based on the preset format identifier;
and the semantic block identification unit is used for identifying more than one business semantic block from the N business content items based on the second type separation identification.
16. The business document processing device of claim 15, wherein said semantic block identification unit is specifically configured to perform the following steps on said business content item:
analyzing whether the second type separation mark exists in the business content item;
identifying the business content item, if present, as a plurality of the business semantic blocks separated based on the second type separation identity; otherwise, determining that the business content item comprises a single business semantic block.
17. The business document processing device of claim 16, wherein the second type of separation mark comprises: a first portion and a second portion;
the first part belongs to a semantic punctuation mark in the business document, and the second part is a first specific separation symbol different from the semantic punctuation mark.
18. The business document processing device of claim 17, further comprising:
And the discarding unit is used for discarding semantic punctuation marks adjacent to the first specific separation symbol in the second type separation mark when the business content item is executed if the semantic punctuation marks exist.
19. A server comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1-9 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810840526.9A CN109284480B (en) | 2018-07-27 | 2018-07-27 | Service document processing method, device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810840526.9A CN109284480B (en) | 2018-07-27 | 2018-07-27 | Service document processing method, device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109284480A CN109284480A (en) | 2019-01-29 |
| CN109284480B true CN109284480B (en) | 2024-01-16 |
Family
ID=65182848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810840526.9A Active CN109284480B (en) | 2018-07-27 | 2018-07-27 | Service document processing method, device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109284480B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070114B (en) * | 2019-04-03 | 2020-11-10 | 奇安信科技集团股份有限公司 | Multi-specification fusion processing method and device, computer equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9710829B1 (en) * | 2013-06-19 | 2017-07-18 | Intuit Inc. | Methods, systems, and articles of manufacture for analyzing social media with trained intelligent systems to enhance direct marketing opportunities |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040194009A1 (en) * | 2003-03-27 | 2004-09-30 | Lacomb Christina | Automated understanding, extraction and structured reformatting of information in electronic files |
| US7689037B2 (en) * | 2004-10-22 | 2010-03-30 | Xerox Corporation | System and method for identifying and labeling fields of text associated with scanned business documents |
| GB2443447A (en) * | 2006-10-30 | 2008-05-07 | Hewlett Packard Development Co | A method of constructing an output document by adding data from a variable data document to a template document |
| AU2010300317C1 (en) * | 2009-10-02 | 2016-09-01 | Aravind Musuluri | System and method for block segmenting, identifying and indexing visual elements, and searching documents |
| US9633332B2 (en) * | 2010-07-13 | 2017-04-25 | Hewlett Packard Enterprise Development Lp | Generating machine-understandable representations of content |
| US9690770B2 (en) * | 2011-05-31 | 2017-06-27 | Oracle International Corporation | Analysis of documents using rules |
| US20150149461A1 (en) * | 2013-11-24 | 2015-05-28 | Interstack, Inc | System and method for analyzing unstructured data on applications, devices or networks |
-
2018
- 2018-07-27 CN CN201810840526.9A patent/CN109284480B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9710829B1 (en) * | 2013-06-19 | 2017-07-18 | Intuit Inc. | Methods, systems, and articles of manufacture for analyzing social media with trained intelligent systems to enhance direct marketing opportunities |
Non-Patent Citations (1)
| Title |
|---|
| 智能答疑系统的设计及探讨;李丽华;《怀化学院学报》;20060530(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109284480A (en) | 2019-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107291783B (en) | Semantic matching method and intelligent equipment | |
| US10923120B2 (en) | Human-machine interaction method and apparatus based on artificial intelligence | |
| CN110096599B (en) | Knowledge graph generation method and device | |
| CN112035599A (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| CN114757176A (en) | Method for obtaining target intention recognition model and intention recognition method | |
| CN109285024B (en) | Online feature determination method and device, electronic equipment and storage medium | |
| CN114492601A (en) | Resource classification model training method and device, electronic equipment and storage medium | |
| CN113836303A (en) | Text type identification method and device, computer equipment and medium | |
| CN114647713A (en) | Knowledge graph question-answering method, device and storage medium based on virtual confrontation | |
| CN111078855A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN111126058A (en) | Text information automatic extraction method and device, readable storage medium and electronic equipment | |
| CN109284480B (en) | Service document processing method, device and server | |
| CN114637726A (en) | Data processing method, device and storage medium | |
| CN111368066A (en) | Method, device and computer readable storage medium for acquiring dialogue abstract | |
| CN106407332B (en) | Search method and device based on artificial intelligence | |
| CN116383234A (en) | Search statement generation method and device, computer equipment and storage medium | |
| CN110489740A (en) | Semantic analytic method and Related product | |
| CN111597453B (en) | User image drawing method, device, computer equipment and computer readable storage medium | |
| CN112115362B (en) | Programming information recommendation method and device based on similar code recognition | |
| CN114676705A (en) | Dialogue relation processing method, computer and readable storage medium | |
| CN113704422A (en) | Text recommendation method and device, computer equipment and storage medium | |
| CN111859148A (en) | Theme extraction method, device and equipment and computer readable storage medium | |
| CN113704623A (en) | Data recommendation method, device, equipment and storage medium | |
| CN108268623B (en) | Text extraction method, device, equipment and medium | |
| CN110941765A (en) | Search intention identification method, information search method and device and electronic equipment |
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: 20200923 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200923 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman 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. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |