WO2021042521A1 - Procédé de génération automatique de contrat, dispositif informatique et support de stockage informatique non volatil - Google Patents

Procédé de génération automatique de contrat, dispositif informatique et support de stockage informatique non volatil Download PDF

Info

Publication number
WO2021042521A1
WO2021042521A1 PCT/CN2019/117088 CN2019117088W WO2021042521A1 WO 2021042521 A1 WO2021042521 A1 WO 2021042521A1 CN 2019117088 W CN2019117088 W CN 2019117088W WO 2021042521 A1 WO2021042521 A1 WO 2021042521A1
Authority
WO
WIPO (PCT)
Prior art keywords
contract
template
target
warning information
generated
Prior art date
Application number
PCT/CN2019/117088
Other languages
English (en)
Chinese (zh)
Inventor
王巍
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2021042521A1 publication Critical patent/WO2021042521A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/90335—Query processing
    • G06F16/90344—Query processing by using string matching techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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

Definitions

  • This application relates to the technical field of base frame operation and maintenance, and in particular to a method for automatically generating contracts, computer equipment, and computer non-volatile storage media.
  • the embodiments of the present application provide a method for automatically generating a contract, a computer device, and a computer non-volatile storage medium to solve the problem of low contract production efficiency in the prior art.
  • a method for automatically generating a contract includes obtaining a contract generation request, the contract generation request carrying basic information of the contract to be generated, and the basic information includes the contract.
  • Name and type of contract business retrieve a contract template according to the basic information of the contract to be generated, the contract template including multiple contract element filling fields; obtain the contract element value entered by the user in the multiple contract element filling fields; Generate a target contract according to the contract template and the contract element values; compare the risk of the target contract with the pre-stored contract template in the database to obtain the risk warning information of the target contract; output the risk warning information containing the risk warning information Target contract.
  • a device for automatically generating a contract comprising: a first obtaining unit for obtaining a contract generation request, the contract generation request carrying basic information of the contract to be generated ,
  • the basic information includes the name of the contract and the type of the contract business;
  • the retrieval unit is configured to retrieve a contract template according to the basic information of the contract to be generated, the contract template includes a plurality of contract element filling fields;
  • the second acquisition unit Used to obtain the contract element values entered by the user in the multiple contract element filling fields;
  • a generating unit used to generate a target contract based on the contract template and the contract element values;
  • a comparison unit used to compare the target Perform risk comparison between the contract and the pre-stored contract template in the database to obtain the risk warning information of the target contract;
  • the output unit is used to output the target contract containing the risk warning information.
  • a computer non-volatile storage medium includes a stored program, and when the program runs, the device where the storage medium is located is controlled to execute the above contract. Automatically generate methods.
  • a computer device including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor executes all When the computer program is described, the steps of the above-mentioned automatic contract generation method are realized.
  • the contract template is retrieved from the basic information of the contract to be generated, and the target contract is generated by the contract element values entered by the user in the filling field; the target contract is compared with the contract template pre-stored in the database for risk comparison, Obtain the risk prompt information of the target contract; generate the target contract containing the risk prompt information, improve the efficiency of contract generation, and at the same time make the user understand the risks of the contract at a glance.
  • Fig. 1 is a flowchart of an optional automatic contract generation method provided by an embodiment of the present application
  • Fig. 2 is a schematic diagram of an optional automatic contract generation device provided by an embodiment of the present application.
  • Fig. 3 is a schematic diagram of an optional computer device provided by an embodiment of the present application.
  • first, second, third, etc. may be used to describe terminals in the embodiments of the present application, these terminals should not be limited to these terms. These terms are only used to distinguish terminals from each other.
  • the first terminal may also be referred to as the second terminal, and similarly, the second terminal may also be referred to as the first terminal.
  • the word “if” as used herein can be interpreted as “when” or “when” or “in response to determination” or “in response to detection”.
  • the phrase “if determined” or “if detected (statement or event)” can be interpreted as “when determined” or “in response to determination” or “when detected (statement or event) )” or “in response to detection (statement or event)”.
  • Fig. 1 is a flowchart of a method for automatically generating a contract according to an embodiment of the present application. As shown in Fig. 1, the method includes:
  • Step S101 Obtain a contract generation request.
  • the contract generation request carries basic information of the contract to be generated.
  • the basic information includes the name of the contract and the type of contract business.
  • the name of the contract can be, for example, a capital increase contract, a shareholder contract, an equity transfer contract, a house lease contract, a house purchase contract, a bond transfer agreement, etc.;
  • the type of business includes any one of banking, trust, securities, and fund business.
  • the user can select the required business type and the name of the required contract on the preset webpage.
  • a contract template is retrieved according to the basic information of the contract to be generated.
  • the contract template includes multiple contract element filling fields. Understandably, the "filled field" refers to an editable and filled area pre-inserted into the contract template.
  • Step S103 Obtain the contract element values entered by the user in the multiple contract element filling fields.
  • the elements of the contract can be the subject matter of the contract, the quantity of the contract, the price or remuneration agreed in the contract, the time limit, place and method of performance of the contract, liability for breach of contract, and measures to resolve disputes.
  • the filling fields of contract elements include the name of the borrower, the nature of the borrower, the purpose of the loan, the term of the loan, whether there is a guarantee, the method of lending, and the method of dispute resolution.
  • the filled field can be filled or edited in various ways such as text filling, number filling, and selection of preset fields. For example, for the loan period, the user can directly edit and enter 30 years, or click to select the preset 30 years, thereby speeding up the efficiency of contract generation.
  • Step S104 Generate a target contract according to the contract template and contract element values.
  • the contract element filling field is provided with a preset identification. Through the identification, the server can directly associate the contract element value with the corresponding contract element filling field, thereby ensuring the accuracy of the generated target contract.
  • Step S105 Perform risk comparison between the target contract and the pre-stored contract template in the database to obtain risk warning information of the target contract.
  • Step S106 Output the target contract containing risk warning information.
  • the contract template is retrieved from the basic information of the contract to be generated, and the target contract is generated through the contract element values entered by the user in the filling field; the target contract is compared with the pre-stored contract template in the database to obtain the target The risk warning information of the contract; generate the target contract containing the risk warning information to improve the efficiency of contract generation, and at the same time make the user know the risks of the contract at a glance.
  • calling the contract template according to the basic information of the contract to be generated includes: calling a contract template set according to the type of business of the contract to be generated.
  • the contract template set includes multiple contract templates, where each contract template corresponds to one The contract name is associated; a contract template matching the contract name of the contract to be generated is obtained from the contract template collection; multiple contract elements in the contract template are output to fill in the field.
  • the server will parse the contract name and the type of the contract business in the basic information, and initially filter the contract template set according to the type of business, and then match the contract name in the contract template set obtained by the preliminary screening to determine the required contract template.
  • calling the contract template according to the basic information of the contract to be generated including: extracting keywords from the basic information, and searching for multiple contract samples in an online search engine according to the keywords; de-duplicating the multiple contract samples;
  • the contract template generation model is trained based on the multiple contract samples after deduplication processing; the contract template output by the trained contract template generation model is obtained, and the contract template includes multiple contract element filling fields.
  • multiple contract samples can be deduplicated by using a local sensitive hash (simHash) algorithm, and a small part of the string in the contract sample is extracted with the same rule to represent the entire contract sample. If a small part of the string has a high degree of coincidence, then The repeatability of the entire contract sample is also high. Understandably, for similar texts, the corresponding simHash strings are also similar, that is, the similarity of the simHash signature values of the two texts intuitively reflects the similarity of the original text, which brings the possibility of text deduplication. After the text to be deduplicated is mapped by the simHash algorithm, the 01 string will be obtained.
  • the 01 strings of the two texts are only different from 0 and 1 in a few positions, most of the other positions are completely the same. Then the similarity between the two texts is extremely high. Therefore, by calculating the number of positions where 0 or 1 is different between two 01 strings, the value obtained can be used to characterize the similarity between two texts.
  • the contract template generation model is obtained by supervised training of the existing convolutional neural network structure using machine learning methods and contract samples.
  • the contract template generation model is a model composed of a recurrent neural network.
  • a network model such as a convolutional neural network or an adversarial network may also be used. By learning the features of the contract's constituent elements and semantic relationship classification in the contract sample, the model can generate the required contract template.
  • compare the risk of the target contract with the pre-stored contract template in the database to obtain the risk warning information of the target contract including:
  • the target contract retrieve a contract template consistent with the business type and contract name of the target contract.
  • the clause text in the contract template is associated with the corresponding risk warning information;
  • the target contract is divided into multiple sub-segment texts, and Calculate the semantic similarity score of each sub-segment text and the clause text in the contract template through the similarity calculation model; use the risk warning information corresponding to the clause text with the highest semantic similarity score as the risk warning information of the sub-segment text; take the risk warning
  • the information is marked on the corresponding sub-paragraph text of the target contract.
  • the similarity calculation model is used to determine whether two texts are similar texts. Specifically, the similarity calculation model can determine whether it is similar text based on the similarity parameter by obtaining the similarity parameter between two texts.
  • the similarity parameter includes at least one of Jaccard coefficient, edit distance, and semantic distance.
  • the Jaccard coefficient is used to compare the similarity and difference between the limited sample sets. Specifically, the text to be compared can be segmented to obtain two phrase sets, and then the text similarity is obtained based on the two phrase sets.
  • Edit distance refers to Levinstein distance, which can be used as a measure of similarity between two texts.
  • the edit distance between them is the minimum number of operations required to convert one of the strings to the other.
  • the operations here are limited to three types: insertion and deletion of a character Or replace.
  • Semantic distance is a measure of the similarity between two texts from a semantic perspective
  • the Word2Vec method can be used to calculate the semantic distance between two texts, by transforming the text to be compared into a semantic representation form, and then passing various distances
  • the representation method calculates the semantic distance between two texts.
  • the risk warning information includes the legal terms on which the risk is based and risk correction suggestions. This allows the user to modify the target contract after seeing the risk warning information.
  • the method further includes: extracting keywords in the risk warning information, and obtaining the risk level according to the keywords; marking the target contract according to the risk level and its corresponding marking color for convenience
  • the user makes modifications according to the marked target contract, and the modification method includes at least one of re-editing, deleting, replacing, and word order adjustment.
  • the extracted keyword is "about", which is a forbidden word in the contract, and it is marked in red to facilitate the user to modify this word, eliminate the imprecise vocabulary of the contract, and make the target contract more Standard and accurate.
  • the method further includes: in response to the user's review completion instruction, obtaining the seal identifier in the contract template according to the contract template called by the target contract; calling the seal system Interface to obtain the seal information corresponding to the seal identification; determine the seal location corresponding to the seal information in the target contract according to the seal location information in the contract template; stamp the seal information to the corresponding seal location in the target contract After that, output the target contract.
  • the server can call the corresponding seal information according to the seal identification in the contract template, and then add the seal information to the corresponding position of the target contract according to the coordinate value of the seal in the contract template. In this way, effective contracts can be generated quickly and effectively, and the efficiency of contract production can be improved.
  • the embodiment of the present application provides a device for automatically generating a contract, which is used to execute the above-mentioned method for automatically generating a contract.
  • the device includes: a first acquiring unit 10, a calling unit 20, and a second acquiring unit 30 , The generation unit 40, the comparison unit 50, and the output unit 60.
  • the first obtaining unit 10 is configured to obtain a contract generation request.
  • the contract generation request carries basic information of the contract to be generated.
  • the basic information includes the name of the contract and the type of contract business.
  • the name of the contract can be, for example, a capital increase contract, a shareholder contract, an equity transfer contract, a house lease contract, a house purchase contract, a bond transfer agreement, etc.;
  • the type of business includes any one of banking, trust, securities, and fund business.
  • the user can select the required business type and the name of the required contract on the preset webpage.
  • the retrieval unit 20 is configured to retrieve a contract template according to the basic information of the contract to be generated, and the contract template includes multiple contract element filling fields. Understandably, the "filled field" refers to an editable and filled area pre-inserted into the contract template.
  • the second obtaining unit 30 is configured to obtain the contract element values input by the user in the multiple contract element filling fields.
  • the elements of the contract can be the subject matter of the contract, the quantity of the contract, the price or remuneration agreed in the contract, the time limit, place and method of performance of the contract, liability for breach of contract, measures to resolve disputes, etc.
  • the filling fields of contract elements include the name of the borrower, the nature of the borrower, the purpose of the loan, the term of the loan, whether there is a guarantee, the method of lending, and the method of dispute resolution.
  • the filled field can be filled or edited in various ways such as text filling, number filling, and selection of preset fields. For example, for the loan period, the user can directly edit and enter 30 years, or click to select the preset 30 years, thereby speeding up the efficiency of contract generation.
  • the generating unit 40 is used to generate the target contract according to the contract template and contract element values.
  • the contract element filling field is provided with a preset identification. Through the identification, the server can directly associate the contract element value with the corresponding contract element filling field, thereby ensuring the accuracy of the generated target contract.
  • the comparison unit 50 is used to compare the risk of the target contract with the pre-stored contract template in the database to obtain the risk warning information of the target contract.
  • the output unit 60 is used to output the target contract containing risk warning information.
  • the contract template is retrieved from the basic information of the contract to be generated, and the target contract is generated through the contract element values entered by the user in the filling field; the target contract is compared with the pre-stored contract template in the database to obtain the target The risk warning information of the contract; generate the target contract containing the risk warning information to improve the efficiency of contract generation, and at the same time make the user know the risks of the contract at a glance.
  • calling the contract template according to the basic information of the contract to be generated includes: calling a contract template set according to the type of business of the contract to be generated.
  • the contract template set includes multiple contract templates, where each contract template corresponds to one The contract name is associated; a contract template matching the contract name of the contract to be generated is obtained from the contract template collection; multiple contract elements in the contract template are output to fill in the field.
  • the server will parse the contract name and the type of contract business in the basic information, and initially filter the contract template set according to the type of business, and then match the contract name in the contract template set obtained by the preliminary screening to determine the required contract template.
  • the retrieval unit 20 includes a retrieval subunit, a first acquisition subunit, and an output subunit.
  • the retrieval subunit is used to retrieve a collection of contract templates according to the type of business of the contract to be generated.
  • the collection of contract templates includes multiple contract templates, where each contract template is associated with a corresponding contract name; the first acquisition subunit, It is used to obtain a contract template matching the contract name of the contract to be generated from the contract template collection; the output subunit is used to output multiple contract elements in the contract template to fill the fields.
  • the invocation subunit is used to extract keywords from the basic information, and search multiple contract samples in the web search engine according to the keywords; de-duplicate the multiple contract samples;
  • the contract sample trains the contract template generation model; the contract template output by the trained contract template generation model is obtained.
  • the contract template includes multiple contract element filling fields.
  • multiple contract samples can be deduplicated by using a local sensitive hash algorithm, and a small part of the string in the contract sample is extracted with the same rule to represent the entire contract sample. If a small part of the string has a high degree of overlap, then the entire contract sample The repeatability is also very high. Understandably, for similar texts, the corresponding simHash strings are also similar, that is, the similarity of the simHash signature values of the two texts intuitively reflects the similarity of the original text, which brings the possibility of text deduplication. After the text to be deduplicated is mapped by the simHash algorithm, the 01 string will be obtained.
  • the 01 strings of the two texts are only different from 0 and 1 in a few positions, most of the other positions are completely the same. Then the similarity between the two texts is extremely high. Therefore, by calculating the number of positions where 0 or 1 is different between two 01 strings, the value obtained can be used to characterize the similarity between two texts.
  • the contract template generation model is obtained by supervised training of the existing convolutional neural network structure using machine learning methods and contract samples.
  • the contract template generation model is a model composed of a recurrent neural network.
  • a network model such as a convolutional neural network or an adversarial network may also be used. By learning the features of the contract's constituent elements and semantic relationship classification in the contract sample, the model can generate the required contract template.
  • the comparison unit 50 includes a second retrieval subunit, a segmentation subunit, a confirmation subunit, and a labeling subunit.
  • the second retrieval subunit is used to retrieve the contract template consistent with the business type and contract name of the target contract according to the basic information of the target contract.
  • the clause text in the contract template is associated with the corresponding risk warning information;
  • the unit is used to divide the target contract into multiple sub-segment texts, and calculate the semantic similarity score of each sub-segment text and the clause text in the contract template through the similarity calculation model; confirm the sub-unit, which is used to score the highest semantic similarity
  • the risk warning information corresponding to the clause text of the clause is used as the risk warning information of the sub-segment text; the labeling subunit is used to mark the risk warning information on the corresponding sub-segment text of the target contract.
  • the similarity calculation model is used to determine whether two texts are similar texts. Specifically, the similarity calculation model can determine whether it is similar text based on the similarity parameter by obtaining the similarity parameter between two texts.
  • the similarity parameter includes at least one of Jaccard coefficient, edit distance, and semantic distance.
  • the Jaccard coefficient is used to compare the similarity and difference between the limited sample sets. Specifically, the text to be compared can be segmented to obtain two phrase sets, and then the text similarity is obtained based on the two phrase sets.
  • Edit distance refers to Levinstein distance, which can be used as a measure of similarity between two texts.
  • the edit distance between them is the minimum number of operations required to convert one of the strings to the other.
  • the operations here are limited to three types: insertion and deletion of a character Or replace.
  • Semantic distance is a measure of the similarity between two texts from a semantic perspective
  • the Word2Vec method can be used to calculate the semantic distance between two texts, by transforming the text to be compared into a semantic representation form, and then passing various distances
  • the representation method calculates the semantic distance between two texts.
  • the risk warning information includes the legal terms on which the risk is based and risk correction suggestions. This allows the user to modify the target contract after seeing the risk warning information.
  • the device further includes an extraction unit and a labeling unit.
  • the extraction unit is used to extract the keywords in the risk notification information, and the risk level is obtained according to the keywords; the labeling unit is used to mark the target contract according to the risk level and its corresponding color, so that the user can modify the target contract after the mark ,
  • the modification method includes at least one of re-editing, deleting, replacing, and word order adjustment.
  • the extracted keyword is "about", which is a forbidden word in the contract, and it is marked in red to facilitate the user to modify this word, eliminate the imprecise vocabulary of the contract, and make the target contract more Standard and accurate.
  • the device further includes a third acquiring unit, a calling unit, a determining unit, and a second output unit.
  • the third obtaining unit is used to obtain the seal identifier in the contract template according to the contract template called by the target contract in response to the user's review completion instruction; the calling unit is used to call the interface of the seal system to obtain the corresponding seal identifier The seal information; the determining unit is used to determine the seal location corresponding to the seal information in the target contract according to the seal location information in the contract template; the second output unit is used to add the seal information to the target contract After the corresponding stamp position, output the target contract.
  • the server can call the corresponding seal information according to the seal identification in the contract template, and then add the seal information to the corresponding position of the target contract according to the coordinate value of the seal in the contract template. In this way, effective contracts can be generated quickly and effectively, and the efficiency of contract production can be improved.
  • the embodiment of the present application provides a computer non-volatile storage medium.
  • the storage medium includes a stored program.
  • the device where the storage medium is located is controlled to perform the following steps: obtain a contract generation request, which carries the contract to be generated
  • the basic information includes the contract name and the type of contract business
  • the contract template is retrieved according to the basic information of the contract to be generated, and the contract template includes multiple contract element filling fields; obtaining the contract elements entered by the user in the multiple contract element filling fields Value; Generate the target contract according to the contract template and contract element values; compare the target contract with the pre-stored contract template in the database to obtain the risk warning information of the target contract; output the target contract containing the risk warning information.
  • the device where the storage medium is located is controlled to execute the call of the contract template according to the basic information of the contract to be generated, including:
  • the contract template collection includes multiple contract templates, where each contract template is associated with a corresponding contract name; from the contract template collection, a contract with the contract to be generated is obtained Contract template with matching name; output multiple contract elements in the contract template to fill in the field.
  • the device where the storage medium is located is controlled to execute the call of the contract template according to the basic information of the contract to be generated, including:
  • the contract template generation model is obtained by supervised training of the existing convolutional neural network structure by using machine learning methods and contract samples; the contract template output by the trained contract template generation model is obtained.
  • the device where the storage medium is located is controlled to perform a risk comparison between the target contract and the pre-stored contract template in the database to obtain the risk alert information of the target contract, including: calling the target contract based on the basic information of the target contract The contract template whose business belongs to the same type and contract name.
  • the clause text in the contract template is associated with the corresponding risk warning information; the target contract is divided into multiple sub-segment texts, and the similarity calculation model is used to calculate each sub-segment text and The semantic similarity score of the clause text in the contract template; the risk warning information corresponding to the clause text with the highest semantic similarity score is used as the risk warning information of the sub-segment text; the risk warning information is marked on the corresponding sub-segment text of the target contract .
  • the device where the storage medium is controlled, after executing the target contract that outputs the risk warning information, further executes the following steps: extracting keywords in the risk warning information, and obtaining the risk level according to the keywords; according to the risk level and The corresponding marking color marks the target contract to facilitate users to modify the marked target contract.
  • the modification method includes at least one of re-editing, deleting, replacing, and word order adjustment.
  • the device where the storage medium is controlled further executes the following steps after executing the target contract containing risk warning information:
  • Fig. 3 is a schematic diagram of a computer device provided by an embodiment of the present application.
  • the computer device 100 of this embodiment includes: a processor 101, a memory 102, and a computer program 103 stored in the memory 102 and running on the processor 101.
  • the processor 101 executes the computer program 103 when the computer program 103 is executed.
  • the automatic contract generation method in the example is not repeated here to avoid repetition.
  • the computer program is executed by the processor 101, the function of each model/unit in the automatic contract generation device in the embodiment is realized. In order to avoid repetition, it will not be repeated here.
  • the computer device 100 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the computer device may include, but is not limited to, a processor 101 and a memory 102.
  • FIG. 3 is only an example of the computer device 100 and does not constitute a limitation on the computer device 100. It may include more or less components than those shown in the figure, or a combination of certain components, or different components.
  • computer equipment may also include input and output devices, network access devices, buses, and so on.
  • the so-called processor 101 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the memory 102 may be an internal storage unit of the computer device 100, such as a hard disk or a memory of the computer device 100.
  • the memory 102 may also be an external storage device of the computer device 100, such as a plug-in hard disk equipped on the computer device 100, a smart memory card (Smart Media Card, SMC), a Secure Digital (SD) card, and a flash memory card (Flash). Card) and so on.
  • the memory 102 may also include both an internal storage unit of the computer device 100 and an external storage device.
  • the memory 102 is used to store computer programs and other programs and data required by the computer equipment.
  • the memory 102 can also be used to temporarily store data that has been output or will be output.
  • the disclosed system, device, and method may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined. Or it can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional units.
  • the above-mentioned integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium.
  • the above-mentioned software functional unit is stored in a storage medium and includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (Processor) execute the method described in each embodiment of the present application. Part of the steps.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Strategic Management (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Educational Administration (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

La présente invention concerne un procédé de génération automatique de contrat, un dispositif informatique et un support de stockage informatique non volatil associés au domaine technique du fonctionnement et de la maintenance d'un cadre de base. Le procédé comprend les étapes consistant à : acquérir une demande de génération de contrat, la demande de génération de contrat contenant des informations de base d'un contrat à générer, et les informations de base comprenant le nom du contrat et le type d'un service du contrat (S101) ; récupérer un modèle de contrat en fonction des informations de base du contrat à générer, le modèle de contrat comprenant de multiples domaines de renseignement d'élément de contrat (S102) ; acquérir des valeurs d'élément de contrat entrées par un utilisateur dans les multiples domaines de renseignement d'élément de contrat (S103) ; générer un contrat cible en fonction du modèle de contrat et des valeurs d'élément de contrat (S104) ; effectuer une comparaison de risque entre le contrat cible et un modèle de contrat pré-stocké dans une base de données pour obtenir des informations d'avertissement de risque du contrat cible (S105) ; et délivrer le contrat cible contenant les informations d'avertissement de risque (S106). Par conséquent, le procédé permet de résoudre le problème lié à la faible efficacité de création de contrat de l'état de la technique.
PCT/CN2019/117088 2019-09-04 2019-11-11 Procédé de génération automatique de contrat, dispositif informatique et support de stockage informatique non volatil WO2021042521A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910830509.1 2019-09-04
CN201910830509.1A CN110765770A (zh) 2019-09-04 2019-09-04 一种合同自动生成方法及装置

Publications (1)

Publication Number Publication Date
WO2021042521A1 true WO2021042521A1 (fr) 2021-03-11

Family

ID=69329227

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/117088 WO2021042521A1 (fr) 2019-09-04 2019-11-11 Procédé de génération automatique de contrat, dispositif informatique et support de stockage informatique non volatil

Country Status (2)

Country Link
CN (1) CN110765770A (fr)
WO (1) WO2021042521A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114169306A (zh) * 2021-12-13 2022-03-11 平安养老保险股份有限公司 一种生成电子回执单的方法、装置、设备及可读存储介质
CN115809652A (zh) * 2023-01-28 2023-03-17 北京蓝色星际科技股份有限公司 自动合成红头文件的方法及装置
CN116384382A (zh) * 2023-01-04 2023-07-04 深圳擎盾信息科技有限公司 一种基于多轮交互的自动化长篇合同要素识别方法及装置

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111882419B (zh) * 2020-05-25 2022-02-08 马上消费金融股份有限公司 质检文件的方法、装置及服务器
CN111931475A (zh) * 2020-06-28 2020-11-13 重庆锐云科技有限公司 动态认购书生成方法、系统、计算机设备及存储介质
CN111797608B (zh) * 2020-06-29 2023-08-22 中国工商银行股份有限公司 信用数据核对方法及装置
CN111932412A (zh) * 2020-09-04 2020-11-13 汪宏杰 合同起草及修订方法、装置、存储介质及设备
CN112308742A (zh) * 2020-09-24 2021-02-02 五八到家有限公司 合同生成方法、装置及系统
CN112329427B (zh) * 2020-11-26 2023-08-08 北京百度网讯科技有限公司 短信样本的获取方法和装置
CN112800761A (zh) * 2020-12-25 2021-05-14 讯飞智元信息科技有限公司 信息回填方法及其相关电子设备、存储介质
CN112686639B (zh) * 2021-01-05 2022-11-08 河北冀联人力资源服务集团有限公司 一种基于深度学习的劳动合同确定的方法和系统
CN112686646B (zh) * 2021-01-31 2023-09-22 重庆渝高科技产业(集团)股份有限公司 一种合同线上填报管理方法及系统
CN113191456A (zh) * 2021-05-26 2021-07-30 平安信托有限责任公司 基于文本识别技术的单证生成方法、装置、设备及介质
CN113326684B (zh) * 2021-08-03 2021-11-09 江苏金恒信息科技股份有限公司 一种合同签约管理方法、系统及装置
CN114610681A (zh) * 2022-03-16 2022-06-10 阿里巴巴（中国）有限公司 信息录入方法以及装置
CN114493551B (zh) * 2022-03-28 2022-07-05 中国光大银行股份有限公司 一种合同的生成方法及装置、电子设备、存储介质
CN115169291B (zh) * 2022-07-14 2023-05-12 中国建筑西南设计研究院有限公司 文本转换方法、装置、终端设备和计算机可读存储介质
CN116127937A (zh) * 2022-09-09 2023-05-16 广州市花都区人民医院 适用于医院业务的合同全生命周期管理方法、装置
CN116757886B (zh) * 2023-08-16 2023-11-28 南京尘与土信息技术有限公司 数据分析方法及分析装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103106593A (zh) * 2013-02-21 2013-05-15 广州宝钢南方贸易有限公司 一种合同制作和评审装置
US9514117B2 (en) * 2007-02-28 2016-12-06 Docusign, Inc. System and method for document tagging templates
CN109523225A (zh) * 2018-10-12 2019-03-26 平安科技（深圳）有限公司 一种合同管理方法、系统及终端设备
CN110083809A (zh) * 2019-03-16 2019-08-02 平安城市建设科技(深圳)有限公司 合同条款相似度计算方法、装置、设备及可读存储介质
CN110168665A (zh) * 2016-12-20 2019-08-23 谷歌有限责任公司 使用机器学习技术生成模板文档

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5692206A (en) * 1994-11-30 1997-11-25 Taco Bell Corporation Method and apparatus for automating the generation of a legal document
CN108509401B (zh) * 2018-03-05 2022-01-28 平安普惠企业管理有限公司 合同生成方法、装置、计算机设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9514117B2 (en) * 2007-02-28 2016-12-06 Docusign, Inc. System and method for document tagging templates
CN103106593A (zh) * 2013-02-21 2013-05-15 广州宝钢南方贸易有限公司 一种合同制作和评审装置
CN110168665A (zh) * 2016-12-20 2019-08-23 谷歌有限责任公司 使用机器学习技术生成模板文档
CN109523225A (zh) * 2018-10-12 2019-03-26 平安科技（深圳）有限公司 一种合同管理方法、系统及终端设备
CN110083809A (zh) * 2019-03-16 2019-08-02 平安城市建设科技(深圳)有限公司 合同条款相似度计算方法、装置、设备及可读存储介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114169306A (zh) * 2021-12-13 2022-03-11 平安养老保险股份有限公司 一种生成电子回执单的方法、装置、设备及可读存储介质
CN116384382A (zh) * 2023-01-04 2023-07-04 深圳擎盾信息科技有限公司 一种基于多轮交互的自动化长篇合同要素识别方法及装置
CN116384382B (zh) * 2023-01-04 2024-03-22 深圳擎盾信息科技有限公司 一种基于多轮交互的自动化长篇合同要素识别方法及装置
CN115809652A (zh) * 2023-01-28 2023-03-17 北京蓝色星际科技股份有限公司 自动合成红头文件的方法及装置

Also Published As

Publication number Publication date
CN110765770A (zh) 2020-02-07

Similar Documents

Publication Publication Date Title
WO2021042521A1 (fr) Procédé de génération automatique de contrat, dispositif informatique et support de stockage informatique non volatil
CN110163478B (zh) 一种合同条款的风险审查方法及装置
US10521508B2 (en) Natural language processing for extracting conveyance graphs
CN108388559B (zh) 地理空间应用下的命名实体识别方法及系统、计算机程序
WO2022048211A1 (fr) Procédé et appareil de génération de répertoire de document, dispositif électronique et support de stockage lisible
US20200110795A1 (en) Facilitating auto-completion of electronic forms with hierarchical entity data models
TW202113577A (zh) 用於機器語言模型建立之技術
WO2021051867A1 (fr) Procédé et appareil d'identification d'informations d'actif, dispositif informatique et support de stockage
US11232300B2 (en) System and method for automatic detection and verification of optical character recognition data
US10489645B2 (en) System and method for automatic detection and verification of optical character recognition data
TW202020691A (zh) 特徵詞的確定方法、裝置和伺服器
WO2021175009A1 (fr) Procédé et appareil de construction de graphe d'événement d'alerte précoce, dispositif et support de stockage
TWI682287B (zh) 知識圖譜產生裝置、方法及其電腦程式產品
US20150117721A1 (en) Coordinate-Based Document Processing and Data Entry System and Method
WO2021196825A1 (fr) Procédé et appareil de génération de résumé, dispositif électronique et support
CN110162754B (zh) 一种岗位描述文档的生成方法及设备
CN109800354B (zh) 一种基于区块链存储的简历修改意图识别方法及系统
CN111651552B (zh) 结构化信息确定方法、装置和电子设备
CN109933803B (zh) 一种成语信息展示方法、展示装置、电子设备及存储介质
CN114462616A (zh) 用于防止敏感数据在线公开的机器学习模型
CN111553556A (zh) 业务数据分析方法、装置、计算机设备及存储介质
US11461801B2 (en) Detecting and resolving semantic misalignments between digital messages and external digital content
US10963686B2 (en) Semantic normalization in document digitization
CN113255369B (zh) 文本相似度分析的方法、装置及存储介质
CN110941952A (zh) 一种完善审计分析模型的方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19944429

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19944429

Country of ref document: EP

Kind code of ref document: A1