CN112330214A - Contract review method and device and readable storage medium - Google Patents
Contract review method and device and readable storage medium Download PDFInfo
- Publication number
- CN112330214A CN112330214A CN202011347815.9A CN202011347815A CN112330214A CN 112330214 A CN112330214 A CN 112330214A CN 202011347815 A CN202011347815 A CN 202011347815A CN 112330214 A CN112330214 A CN 112330214A
- Authority
- CN
- China
- Prior art keywords
- clause
- contract
- type
- risk
- 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
- 238000012552 review Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000013145 classification model Methods 0.000 claims abstract description 48
- 238000012549 training Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000012790 confirmation Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000012937 correction Methods 0.000 abstract description 3
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000001915 proofreading effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Technology Law (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a contract review method, a contract review device and a readable storage medium, which are characterized by firstly identifying text information of a target contract, then identifying a contract type of the target contract and a clause type of each clause of the target contract by utilizing a text classification model based on the text information of the target contract, finding a matched clause template in a sample database according to the contract type of the target contract and the clause type of each clause, carrying out clause content comparison, and outputting a risk level of each clause according to a comparison result. Namely, the target contract text is automatically identified, then a text classification model is used for searching a clause template matched with the type of the clause of the target contract in a sample database, automatic comparison analysis is carried out, and the risk point in the contract text is output, so that automatic examination and correction are carried out on the contract, and the efficiency of contract review is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a contract review method, a contract review device and a readable storage medium.
Background
At present, legal workers face a great deal of drafting and modifying of contracts, and in order to reduce risks in the contracts, the contracts need to be manually reviewed, which consumes a great deal of labor and time. In order to improve the efficiency of review, the automatic review and proofreading of the contract can improve the efficiency of the contract review, particularly for contract texts with more clauses.
Disclosure of Invention
The invention aims to provide a contract review method for automatically reviewing and checking contracts.
To achieve the above object, the present invention provides a contract review method, comprising:
identifying text information of the target contract;
based on the text information of the target contract, identifying the contract type of the target contract and the clause type of each clause of the target contract by using a text classification model, finding a matched clause template in a sample database according to the contract type of the target contract and the clause type of each clause, comparing the clause contents, and outputting the risk level of each clause according to the comparison result.
Optionally, in the contract review method, the step of finding a matching clause template in the sample database to compare the clause contents, and outputting the risk level of each clause according to the comparison result includes:
acquiring a clause template matched with the contract type and the clause type of each clause from the sample database;
comparing the similarity of the word feature vectors of each clause with the matched clause template;
and outputting the risk grade of each clause according to the similarity obtained by comparison and the risk grade of the matched clause template.
Optionally, in the contract review method, the sample database includes a plurality of clause templates matching with the contract type and the clause type of each clause, and the step of finding the matching clause template in the sample database to compare the clause contents and output the risk level of each clause according to the comparison result includes:
acquiring a plurality of clause templates matched with the contract type and the clause type of each clause from the sample database;
comparing the similarity of the word feature vectors of each clause with the similarity of a plurality of matched clause templates to confirm the clause template with the maximum similarity with each clause;
and outputting the risk grade of each clause according to the maximum similarity obtained by comparison and the risk grade of the clause template with the maximum similarity.
Optionally, in the contract review method, the clause template in the sample database includes: a positive example in which there is no risk or a degree of risk below a first threshold, and/or a negative example in which there is a risk or a degree of risk above a second threshold;
if the similarity of the clause and the positive example is higher, the risk level of the clause is lower, and if the similarity of the clause and the negative example is higher, the risk level of the clause is higher.
Optionally, in the contract review method, the text classification model is obtained by training contract samples in advance.
Optionally, in the contract review method, the step of training the same to obtain the text classification model includes:
marking the text paragraphs of each contract sample in the sample database to mark the contract type, the clause type and the risk level of each text paragraph;
and training the text paragraphs marked with the same type, the clause type and the risk level by using a neural network model to obtain the text classification model.
Optionally, in the contract review method, the contract review method further includes: and saving the clauses of the target contract to the sample database so as to update the text classification model by using a new sample of the sample database.
Optionally, in the contract review method, the contract review method further includes:
outputting the comparison result by using a text clause output model;
the output comparison result comprises:
displaying a difference between the target contract and the matching clause template;
displaying the favored parties of the target contract; and/or
The terms at risk and standard template terms matching the terms at risk are noted.
Optionally, in the contract review method, the contract review method further includes:
generating a risk report to be sent to the client for confirmation by the client, according to the risk level of each of the terms, and,
and after the client confirms, saving the risk report.
Optionally, in the contract review method, the method includes:
the text recognition module is used for recognizing the text information of the target contract;
and the comparison module is used for identifying the contract type of the target contract and the clause type of each clause of the target contract by using a text classification model based on the text information of the target contract, finding a matched clause template in a sample database according to the contract type of the target contract and the clause type of each clause, comparing the clause contents, and outputting the risk level of each clause according to a comparison result.
Optionally, in the contract review method, the step of the comparison module finding a matched clause template in the sample database to compare the clause contents, and outputting the risk level of each clause according to the comparison result includes:
acquiring a clause template matched with the contract type and the clause type of each clause from the sample database;
comparing the similarity of the word feature vectors of each clause with the matched clause template;
and outputting the risk grade of each clause according to the similarity obtained by comparison and the risk grade of the matched clause template.
Optionally, in the contract review method, the sample database includes a plurality of clause templates matching with the contract types and the clause types of the clauses, and the step of the comparison module finding the matching clause template in the sample database to perform clause content comparison and outputting the risk level of the clauses according to the comparison result includes:
acquiring a plurality of clause templates matched with the contract type and the clause type of each clause from the sample database;
comparing the similarity of the word feature vectors of each clause with the similarity of a plurality of matched clause templates to confirm the clause template with the maximum similarity with each clause;
and outputting the risk grade of each clause according to the maximum similarity obtained by comparison and the risk grade of the clause template with the maximum similarity.
Optionally, in the contract review method, the clause template in the sample database includes: a positive example in which there is no risk or a degree of risk below a first threshold, and/or a negative example in which there is a risk or a degree of risk above a second threshold;
if the similarity of the clause and the positive example is higher, the risk level of the clause is lower, and if the similarity of the clause and the negative example is higher, the risk level of the clause is higher.
Optionally, in the contract review method, the text classification model is obtained by training contract samples in advance.
Optionally, in the contract review method, the step of training the same to obtain the text classification model includes:
marking the text paragraphs of each contract sample in the sample database to mark the contract type, the clause type and the risk level of each text paragraph;
and training the text paragraphs marked with the same type, the clause type and the risk level by using a neural network model to obtain the text classification model.
Optionally, in the contract reviewing method, the contract reviewing apparatus further includes: and the storage module is used for storing the clauses of the target contract to the sample database so as to update the text classification model by using a new sample of the sample database.
Optionally, in the contract reviewing method, the contract reviewing device further includes an output module, and the output module is configured to output the comparison result by using a text clause output model;
the output comparison result comprises:
displaying a difference between the target contract and the matching clause template;
displaying the favored parties of the target contract; and/or
The terms at risk and standard template terms matching the terms at risk are noted.
Optionally, in the contract review method, the comparison module is further configured to generate a risk report according to the risk level of each clause, and send the risk report to the client for the client to confirm.
The present invention also provides a readable storage medium having stored therein a computer program which, when executed by a processor, implements a contract review method as described above.
In summary, the contract review method, apparatus and readable storage medium provided by the present invention include: identifying text information of the target contract; based on the text information of the target contract, identifying the contract type of the target contract and the clause type of each clause of the target contract by using a text classification model, finding a matched clause template in a sample database according to the contract type of the target contract and the clause type of each clause, comparing the clause contents, and outputting the risk level of each clause according to the comparison result. Namely, the target contract text is automatically identified, then a text classification model is used for searching a clause template matched with the type of the clause of the target contract in a sample database, automatic comparison analysis is carried out, and the risk point in the contract text is output, so that automatic examination and correction are carried out on the contract, and the efficiency of contract review is improved.
Drawings
FIG. 1 is a flow chart of a contract review method provided by an embodiment of the present invention;
FIG. 2 is a block diagram of a contract review apparatus provided by an embodiment of the present invention;
wherein the reference numerals are as follows:
11-a text recognition module; 12-an alignment module; 13-an output module; 14-memory module.
Detailed Description
The contract review method, apparatus, and readable storage medium according to the present invention are further described in detail with reference to the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention. Further, the structures illustrated in the drawings are often part of actual structures. In particular, the drawings may have different emphasis points and may sometimes be scaled differently.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
As shown in fig. 1, the present embodiment provides a contract review method, which includes the steps of:
s11, recognizing text information of the target contract;
s12, based on the text information of the target contract, using a text classification model to identify the contract type of the target contract and the clause type of each clause of the target contract, and according to the contract type of the target contract and the clause type of each clause, finding a matched clause template in a sample database to compare the clause contents, and outputting the risk level of each clause according to the comparison result.
The contract review method provided by the embodiment firstly automatically identifies the target contract text, then searches the clause template matched with the type of the clause of the target contract in the sample database by using the text classification model, performs automatic comparison analysis, and outputs the risk point in the contract text, so that automatic examination and check are performed on the contract, and the efficiency of contract review is improved.
The above steps are described in further detail below.
In step S11, the text presentation of the target contract may be a Word version, a PDF version, a PPT version, a TXT version, or a picture version. The textual information for various versions of the contract can be identified through a character recognition model.
When the text information of the target contract is identified, the target contract can be compared with contract texts of different historical versions, and whether the content in the target contract is consistent with the content of the original contract (the contract of any historical version) or not is judged through comparison, so that the target contract text is prevented from being tampered. The target contract and the original contract can be in the same format or different formats (such as one or more of Word, PDF, PPT, TXT, etc.).
Specifically, the following method can be used to compare the target contract with the original contract:
acquiring an image of a target contract and an electronic document of an original contract;
identifying each line of character area in the image of the target contract based on a pre-trained area identification model, wherein the area identification model is a neural network-based model;
recognizing character contents in each row of character areas based on a pre-trained character recognition model to obtain recognized characters, wherein the character recognition model is a neural network-based model; acquiring position information of the recognized character;
generating an electronic document of the target contract according to the position information and the recognized characters; comparing the contents of the electronic document of the target contract and the electronic document of the original contract; and
and judging whether the target contract and the original contract have difference points or not according to the comparison result, and positioning the difference points according to the position information of the difference points.
Thus, the comparison between the target contract and the original contract is completed through the above steps, and if there is a difference, it indicates that the target contract may be tampered, and then the located difference is verified, and then step S12 is performed.
In step S12, when the text classification model is used to find a matching clause template in the sample database for comparing the clause contents, and the risk level of each clause is output according to the comparison result, the following steps may be specifically adopted:
acquiring a clause template matched with the contract type and the clause type of each clause from the sample database; comparing the similarity of the word feature vectors of each clause with the matched clause template; and outputting the risk grade of each clause according to the similarity obtained by comparison and the risk grade of the matched clause template.
In addition, preferably, at the stage of establishing the sample database, a plurality of clause templates with the same contract type and clause type are collected and stored in the sample database, so that when the text classification model trained by the sample database is used for comparing clauses, the sample database includes a plurality of clause templates matched with the contract type and the clause type of each clause. On this basis, in step S12, when the text classification model is used to find a matching clause template in the sample database for comparing the clauses and the contents, and the risk level of each clause is output according to the comparison result, the following steps may be specifically adopted:
acquiring a plurality of clause templates matched with the contract type and the clause type of each clause from the sample database; comparing the similarity of the word feature vectors of each clause with the similarity of a plurality of matched clause templates to confirm the clause template with the maximum similarity with each clause; and outputting the risk grade of each clause according to the maximum similarity obtained by comparison and the risk grade of the clause template with the maximum similarity.
Wherein the text classification model is obtained by training contract samples in advance. The contract sample is a contract sample in the sample database. Specifically, the text classification model can be obtained by training a combined sample by the following steps:
marking the text paragraphs of each contract sample in the sample database to mark the contract type, the clause type and the risk level of each text paragraph shown in the table 1; and training the text paragraphs marked with the same type, the clause type and the risk level by using a neural network model to obtain the text classification model.
Thus, after the text information of the target contract is identified, the contract type of the target contract, the clause type of each clause and the risk degree of each clause can be identified by using the text classification model.
In this embodiment, the presentation of the risk level may be diversified, for example, with identifiers a, b, c, d to distinguish different levels, or with textual content high, low, etc.
TABLE 1
| Type of contract | Clause type | Content providing method and apparatus | Risk rating |
| WWW | www | AAAA | aaa |
| XXX | xxx | BBBB | bbb |
| YYY | yyy | CCCCC | ccc |
| ZZZ | zzz | DDDDDD | ddd |
| 。。。 | 。。。 | 。。。 | 。。。 |
In some other embodiments, after the contract type, the clause type, and the risk level of each text paragraph are marked, the neural network model is used to train the same type to obtain a first classification model (also called a contract type identification model), the neural network model is used to train the same type to obtain a second classification model (also called a clause classification model), then the first classification model is used to identify the contract type of the target contract, the second classification model is used to identify the clause type of each clause of the target contract, further, the character matching identification model is used to find a matched clause template in the sample database according to the contract type of the target contract and the clause type of each clause to perform clause content comparison, and the risk level of each clause is output according to the comparison result.
From the above description, the text classification model may be a general classification model, and may also include several sub-classification models, and the specific presentation form of the text classification model does not form a limitation of the present application, and only needs to identify the contract type of the target contract, the clause type of each clause, and the risk level of each clause by using the model.
In addition, during sample training, samples in the sample database can be classified according to the risk degree of the clause and divided into a positive sample and a negative sample, and if the clause text in the contract text has no risk or the risk degree is lower than a first threshold value, the clause text can be used as the positive sample of the clause type and stored in the sample database; if the clause text in the contract text has a counter example with risk or with risk degree higher than a second threshold value, the clause text can be stored in the sample database as a regular example of the clause type. In this way, in step S12, when the degree of similarity to the positive example is higher, the risk level of the clause is lower, and when the degree of similarity to the negative example is higher, the risk level of the clause is higher.
Further, the terms of the target contract may also be saved to the sample database to update the text classification model with a new sample of the sample database.
Optionally, in step S12, in addition to outputting the risk level of each of the terms according to the comparison result, a risk report may be generated and sent to the client according to the risk level of each of the terms, so that the client can confirm the risk report, and the risk report is saved after the client confirms the risk report.
In addition, the contract review method provided by the embodiment may further include: outputting the comparison result by using a text clause output model; the output comparison result comprises: displaying a difference between the target contract and the matching clause template; displaying the favorable side of the target contract (whether the term is biased toward itself, the opponent or a neutral term); and/or noting the terms at risk and standard template terms matching the terms at risk.
That is, in this embodiment, the comparison result in step S12 can be presented in various forms, and the above-mentioned exemplary lists do not constitute a limitation to the present application. For example, the comparison result may also annotate the terms with risks, that is, add an annotation column, annotate the establishment of the modification of the terms and the reason description, or output a version modified according to the term template and the risk degree.
The embodiment of the present invention further provides a contract review device, including:
the text recognition module 11 is used for recognizing text information of the target contract;
a comparison module 12, configured to identify, based on the text information of the target contract, a contract type of the target contract and a clause type of each clause of the target contract by using a text classification model, find a matched clause template in a sample database according to the contract type of the target contract and the clause type of each clause, perform clause content comparison, and output a risk level of each clause according to a comparison result.
The steps of the comparison module 12 finding a matched clause template in the sample database to compare the clause contents, and outputting the risk level of each clause according to the comparison result include: acquiring a clause template matched with the contract type and the clause type of each clause from the sample database; comparing the similarity of the word feature vectors of each clause with the matched clause template; and outputting the risk grade of each clause according to the similarity obtained by comparison and the risk grade of the matched clause template.
Further, the step of the sample database including a plurality of clause templates matching with the contract type and the clause type of each clause, the step of the comparison module 12 finding the matching clause template in the sample database to compare the clause contents, and outputting the risk level of each clause according to the comparison result includes: acquiring a plurality of clause templates matched with the contract type and the clause type of each clause from the sample database; comparing the similarity of the word feature vectors of each clause with the similarity of a plurality of matched clause templates to confirm the clause template with the maximum similarity with each clause; and outputting the risk grade of each clause according to the maximum similarity obtained by comparison and the risk grade of the clause template with the maximum similarity.
The detailed description of the clause template and the text classification model has been made in the foregoing section, and will not be repeated herein. In addition to outputting the risk level of each of the terms according to the comparison result, optionally, the comparison module 12 is further configured to generate a risk report according to the risk level of each of the terms, and send the risk report to the client for the client to confirm.
In addition, corresponding to the contract review method provided by the present embodiment, the contract review apparatus further includes an output module 13, where the output module 13 is configured to output the comparison result by using a text clause output model; the output comparison result comprises: displaying a difference between the target contract and the matching clause template; displaying the favored parties of the target contract; and/or, noting the terms at risk and standard template terms matching the terms at risk, and so on.
The contract review apparatus may further include: a storage module 14, configured to save terms of the target contract to the sample database, so as to update the text classification model with a new sample of the sample database. Additionally, risk reports confirmed by the client may also be stored.
In summary, each module in the contract review apparatus provided in this embodiment is respectively used to implement each step of the contract review method provided in this embodiment, and therefore, for specific description of functions that can be implemented by each module, reference may be made to the related description of the corresponding step of the contract review method described above, and repeated details are not repeated. In addition, the contract reviewing device can achieve the same technical effects as the contract reviewing method, and further description is omitted here.
It is understood that, in the contract reviewing apparatus, the text recognition module 11, the comparison module 12, the output module 13, and the storage module 14 may be combined and implemented in one apparatus, or any one of the modules may be divided into a plurality of sub-modules, or at least part of functions of one or more of the text recognition module 11, the comparison module 12, the output module 13, and the storage module 14 may be combined with at least part of functions of other modules and implemented in one functional module. According to an embodiment of the present invention, in the contract review apparatus, at least one of the text recognition module 11, the comparison module 12, the output module 13 and the storage module 14 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented in an appropriate combination of three implementations of software, hardware and firmware.
As is apparent from the above description, the contract review method according to the embodiment of the present invention is applicable to the contract review apparatus according to the embodiment of the present invention. In addition, the contract review apparatus can be configured on an electronic device, wherein the electronic device can be a personal computer, a mobile terminal and the like, and the mobile terminal can be a mobile phone, a tablet computer and other hardware devices with various operating systems. The electronic device comprises a processor and a memory for storing a computer program; the computer program, when executed by the processor, implements the contract review method provided by the present embodiment.
In the electronic device, the Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory.
Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
The present embodiment also provides a readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the contract review method provided by the present embodiment.
The readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device, such as, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, and any suitable combination of the foregoing. The computer programs described herein may be downloaded from a readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives the computer program from the network and forwards the computer program for storage in a readable storage medium in the respective computing/processing device. Computer programs for carrying out operations of the present invention may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer program may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), can execute computer-readable program instructions to implement various aspects of the present invention by utilizing state information of a computer program to personalize the electronic circuitry.
To sum up, the contract review method, apparatus and readable storage medium provided by the present invention first identify the text information of the target contract, then identify the contract type of the target contract and the clause type of each clause of the target contract based on the text information of the target contract by using the text classification model, and find the matched clause template in the sample database for comparing the clause contents according to the contract type of the target contract and the clause type of each clause, and output the risk level of each clause according to the comparison result. Namely, the target contract text is automatically identified, then a text classification model is used for searching a clause template matched with the type of the clause of the target contract in a sample database, automatic comparison analysis is carried out, and the risk point in the contract text is output, so that automatic examination and correction are carried out on the contract, and the efficiency of contract review is improved.
The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.
Claims (19)
1. A method of contract review, comprising:
identifying text information of the target contract;
based on the text information of the target contract, identifying the contract type of the target contract and the clause type of each clause of the target contract by using a text classification model, finding a matched clause template in a sample database according to the contract type of the target contract and the clause type of each clause, comparing the clause contents, and outputting the risk level of each clause according to the comparison result.
2. The method of contract review of claim 1, wherein the step of finding matching clause templates in the sample database for clause content comparison and outputting the risk level of each clause according to the comparison result comprises:
acquiring a clause template matched with the contract type and the clause type of each clause from the sample database;
comparing the similarity of the word feature vectors of each clause with the matched clause template;
and outputting the risk grade of each clause according to the similarity obtained by comparison and the risk grade of the matched clause template.
3. The method of contract review of claim 1, wherein the sample database includes a plurality of clause templates matching the contract type and the clause type of each clause, and the step of finding the matching clause template in the sample database for clause content comparison and outputting the risk level of each clause according to the comparison result comprises:
acquiring a plurality of clause templates matched with the contract type and the clause type of each clause from the sample database;
comparing the similarity of the word feature vectors of each clause with the similarity of a plurality of matched clause templates to confirm the clause template with the maximum similarity with each clause;
and outputting the risk grade of each clause according to the maximum similarity obtained by comparison and the risk grade of the clause template with the maximum similarity.
4. The contract review method of claim 2 or 3, wherein the clause templates in the sample database include: a positive example in which there is no risk or a degree of risk below a first threshold, and/or a negative example in which there is a risk or a degree of risk above a second threshold;
if the similarity of the clause and the positive example is higher, the risk level of the clause is lower, and if the similarity of the clause and the negative example is higher, the risk level of the clause is higher.
5. The contract review method of claim 1, wherein the text classification model is derived by training contract samples in advance.
6. The method of contract review of claim 5, wherein the step of training a sample to derive the text classification model comprises:
marking the text paragraphs of each contract sample in the sample database to mark the contract type, the clause type and the risk level of each text paragraph;
and training the text paragraphs marked with the same type, the clause type and the risk level by using a neural network model to obtain the text classification model.
7. The contract review method of claim 6, further comprising: and saving the clauses of the target contract to the sample database so as to update the text classification model by using a new sample of the sample database.
8. The contract review method of claim 1, further comprising:
outputting the comparison result by using a text clause output model;
the output comparison result comprises:
displaying a difference between the target contract and the matching clause template;
displaying the favored parties of the target contract; and/or
The terms at risk and standard template terms matching the terms at risk are noted.
9. The contract review method of claim 1, further comprising:
generating a risk report to be sent to the client for confirmation by the client, according to the risk level of each of the terms, and,
and after the client confirms, saving the risk report.
10. A contract review apparatus, comprising:
the text recognition module is used for recognizing the text information of the target contract;
and the comparison module is used for identifying the contract type of the target contract and the clause type of each clause of the target contract by using a text classification model based on the text information of the target contract, finding a matched clause template in a sample database according to the contract type of the target contract and the clause type of each clause, comparing the clause contents, and outputting the risk level of each clause according to a comparison result.
11. The contract review apparatus of claim 10, wherein the comparing module finds a matching clause template in the sample database for comparing the contents of the clauses and outputting the risk level of each clause according to the comparison result comprises:
acquiring a clause template matched with the contract type and the clause type of each clause from the sample database;
comparing the similarity of the word feature vectors of each clause with the matched clause template;
and outputting the risk grade of each clause according to the similarity obtained by comparison and the risk grade of the matched clause template.
12. The contract review apparatus of claim 10, wherein the sample database includes a plurality of clause templates matching the contract type and the clause type of each clause, and the step of the comparison module finding the matching clause template in the sample database for comparing the clause contents and outputting the risk level of each clause according to the comparison result includes:
acquiring a plurality of clause templates matched with the contract type and the clause type of each clause from the sample database;
comparing the similarity of the word feature vectors of each clause with the similarity of a plurality of matched clause templates to confirm the clause template with the maximum similarity with each clause;
and outputting the risk grade of each clause according to the maximum similarity obtained by comparison and the risk grade of the clause template with the maximum similarity.
13. The contract review apparatus of claim 11 or 12, wherein the clause templates in the sample database include: a positive example in which there is no risk or a degree of risk below a first threshold, and/or a negative example in which there is a risk or a degree of risk above a second threshold;
if the similarity of the clause and the positive example is higher, the risk level of the clause is lower, and if the similarity of the clause and the negative example is higher, the risk level of the clause is higher.
14. The contract review apparatus of claim 13, wherein the text classification model is derived by training contract samples in advance.
15. The contract review apparatus of claim 14, wherein training a sample to obtain the text classification model comprises:
marking the text paragraphs of each contract sample in the sample database to mark the contract type, the clause type and the risk level of each text paragraph;
and training the text paragraphs marked with the same type, the clause type and the risk level by using a neural network model to obtain the text classification model.
16. The contract review apparatus of claim 15, wherein the contract review apparatus further comprises: and the storage module is used for storing the clauses of the target contract to the sample database so as to update the text classification model by using a new sample of the sample database.
17. The contract review apparatus of claim 10, further comprising an output module for outputting the comparison results using a text clause output model;
the output comparison result comprises:
displaying a difference between the target contract and the matching clause template;
displaying the favored parties of the target contract; and/or
The terms at risk and standard template terms matching the terms at risk are noted.
18. The contract review apparatus of claim 10, wherein the comparison module is further configured to generate a risk report to the client for the client to confirm according to the risk level of each of the terms.
19. A readable storage medium, having stored therein a computer program which, when executed by a processor, implements the contract review method of any of claims 1-9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011347815.9A CN112330214A (en) | 2020-11-26 | 2020-11-26 | Contract review method and device and readable storage medium |
| PCT/CN2021/132929 WO2022111548A1 (en) | 2020-11-26 | 2021-11-24 | Contract review method and apparatus, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011347815.9A CN112330214A (en) | 2020-11-26 | 2020-11-26 | Contract review method and device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112330214A true CN112330214A (en) | 2021-02-05 |
Family
ID=74307972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011347815.9A Pending CN112330214A (en) | 2020-11-26 | 2020-11-26 | Contract review method and device and readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112330214A (en) |
| WO (1) | WO2022111548A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112926299A (en) * | 2021-03-29 | 2021-06-08 | 杭州天谷信息科技有限公司 | Text comparison method, contract review method and audit system |
| CN112950017A (en) * | 2021-02-26 | 2021-06-11 | 云账户技术(天津)有限公司 | Contract risk identification method and device and electronic equipment |
| CN113326684B (en) * | 2021-08-03 | 2021-11-09 | 江苏金恒信息科技股份有限公司 | Contract signing management method, system and device |
| WO2022111548A1 (en) * | 2020-11-26 | 2022-06-02 | 杭州睿胜软件有限公司 | Contract review method and apparatus, and readable storage medium |
| CN116384387A (en) * | 2023-01-04 | 2023-07-04 | 深圳擎盾信息科技有限公司 | Automatic combination and examination method and device |
| CN116976683A (en) * | 2023-09-25 | 2023-10-31 | 江铃汽车股份有限公司 | Automatic auditing method, system, storage medium and device for contract clauses |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152843B (en) * | 2022-11-22 | 2024-01-12 | 南京擎盾信息科技有限公司 | Category identification method, device and storage medium for contract template to be filled-in content |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918635A (en) * | 2017-12-12 | 2019-06-21 | 中兴通讯股份有限公司 | A kind of contract text risk checking method, device, equipment and storage medium |
| CN110163478A (en) * | 2019-04-18 | 2019-08-23 | 平安科技（深圳）有限公司 | A kind of the risk checking method and device of contract terms |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112330214A (en) * | 2020-11-26 | 2021-02-05 | 杭州睿胜软件有限公司 | Contract review method and device and readable storage medium |
-
2020
- 2020-11-26 CN CN202011347815.9A patent/CN112330214A/en active Pending
-
2021
- 2021-11-24 WO PCT/CN2021/132929 patent/WO2022111548A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918635A (en) * | 2017-12-12 | 2019-06-21 | 中兴通讯股份有限公司 | A kind of contract text risk checking method, device, equipment and storage medium |
| CN110163478A (en) * | 2019-04-18 | 2019-08-23 | 平安科技（深圳）有限公司 | A kind of the risk checking method and device of contract terms |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022111548A1 (en) * | 2020-11-26 | 2022-06-02 | 杭州睿胜软件有限公司 | Contract review method and apparatus, and readable storage medium |
| CN112950017A (en) * | 2021-02-26 | 2021-06-11 | 云账户技术(天津)有限公司 | Contract risk identification method and device and electronic equipment |
| CN112926299A (en) * | 2021-03-29 | 2021-06-08 | 杭州天谷信息科技有限公司 | Text comparison method, contract review method and audit system |
| CN112926299B (en) * | 2021-03-29 | 2024-04-09 | 杭州天谷信息科技有限公司 | Text comparison method, contract review method and auditing system |
| CN113326684B (en) * | 2021-08-03 | 2021-11-09 | 江苏金恒信息科技股份有限公司 | Contract signing management method, system and device |
| CN116384387A (en) * | 2023-01-04 | 2023-07-04 | 深圳擎盾信息科技有限公司 | Automatic combination and examination method and device |
| CN116976683A (en) * | 2023-09-25 | 2023-10-31 | 江铃汽车股份有限公司 | Automatic auditing method, system, storage medium and device for contract clauses |
| CN116976683B (en) * | 2023-09-25 | 2024-02-27 | 江铃汽车股份有限公司 | Automatic auditing method, system, storage medium and device for contract clauses |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022111548A1 (en) | 2022-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112330214A (en) | Contract review method and device and readable storage medium | |
| CN109446885B (en) | Text-based component identification method, system, device and storage medium | |
| CN109872162B (en) | Wind control classification and identification method and system for processing user complaint information | |
| CN112417885A (en) | Answer generation method and device based on artificial intelligence, computer equipment and medium | |
| JP2020030408A (en) | Method, apparatus, device and medium for identifying key phrase in audio | |
| CN108664471B (en) | Character recognition error correction method, device, equipment and computer readable storage medium | |
| CN112163424A (en) | Data labeling method, device, equipment and medium | |
| CN112416778A (en) | Test case recommendation method and device and electronic equipment | |
| CN116860949B (en) | Question-answering processing method, device, system, computing equipment and computer storage medium | |
| CN111553150A (en) | Method, system, device and storage medium for analyzing and configuring automatic API (application program interface) document | |
| CN109446299B (en) | Method and system for searching e-mail content based on event recognition | |
| CN111667923B (en) | Data matching method and device, computer readable medium and electronic equipment | |
| CN113935710A (en) | Contract auditing method and device, electronic equipment and storage medium | |
| CN110532449B (en) | Method, device, equipment and storage medium for processing service document | |
| CN112650858A (en) | Method and device for acquiring emergency assistance information, computer equipment and medium | |
| CN111325031A (en) | Resume parsing method and device | |
| CN113837113A (en) | Document verification method, device, equipment and medium based on artificial intelligence | |
| CN110738056A (en) | Method and apparatus for generating information | |
| CN112669850A (en) | Voice quality detection method and device, computer equipment and storage medium | |
| CN112256877A (en) | Resume screening method, device, equipment and storage medium combining RPA and AI | |
| CN111177387A (en) | User list information processing method, electronic device and computer readable storage medium | |
| CN110705258A (en) | Text entity identification method and device | |
| US20230110931A1 (en) | Method and Apparatus for Data Structuring of Text | |
| CN114154480A (en) | Information extraction method, device, equipment and storage medium | |
| CN113656545A (en) | Intelligent interviewing method and device, computer equipment and storage 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 |