CN115422904A - Contract management method and device based on knowledge graph classification - Google Patents
Contract management method and device based on knowledge graph classification Download PDFInfo
- Publication number
- CN115422904A CN115422904A CN202211115419.2A CN202211115419A CN115422904A CN 115422904 A CN115422904 A CN 115422904A CN 202211115419 A CN202211115419 A CN 202211115419A CN 115422904 A CN115422904 A CN 115422904A
- Authority
- CN
- China
- Prior art keywords
- contract
- target
- standard
- information
- library
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
- G06Q50/188—Electronic negotiation
Abstract
The invention provides a contract management method and a device based on knowledge graph classification, wherein the method comprises the following steps: acquiring first target information corresponding to a target contract, wherein the target contract is any contract to be submitted, and the first target information comprises service category information corresponding to the target contract; recommending the content of the target contract based on a contract content recommendation model according to the first target information of the target contract to obtain contract recommendation content, wherein the contract recommendation content comprises a target contract standard normal form and/or a target contract body example and/or a target contract standard clause; and generating the target contract according to the contract recommendation content. Therefore, the invention can quickly and accurately find the contract template matched with the current service in a large number of contract template libraries, thereby effectively improving the contract undertaking quality.
Description
Technical Field
The invention relates to the technical field of contract management, in particular to a contract management method and device based on knowledge graph classification.
Background
The contract is set up among natural persons, legal persons and other organizations of equal subjects, it is a protocol for standardizing the capital and financial resources transfer system under the market economic condition, for enterprises (such as power enterprises), with the continuous enlargement of the enterprise scale, the subordinate subsidiaries thereof are continuously increased, the related business faces are also wider and wider, a large number of contracts are generated in the operation and production, and the contracts are used as important business certificates of the external information of the enterprises, and are core information resources and important assets of the enterprises, so that for the power enterprises, the management of the contracts is particularly important, the contracts of the power enterprises can be managed, and the operation management efficiency of the power enterprises is improved.
Currently, for an electric power enterprise, for a certain service, contract contractors can manually select a relevant contract template to complete contract signing of the service. However, practice has found that due to the complexity of the power service, the requirement for contract contractors by manually selecting a contract template associated with the power service is high, and the manually selected contract template may not match the current power service, resulting in a low contract acceptance quality.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a contract management method and device based on knowledge graph classification, which can quickly and accurately find out a contract template matched with the current service in a large number of contract template libraries, thereby effectively improving the contract undertaking quality.
In order to solve the technical problem, the first aspect of the present invention discloses a contract management method based on knowledge graph classification, which includes:
acquiring first target information corresponding to a target contract, wherein the target contract is any contract to be submitted, and the first target information comprises service category information corresponding to the target contract;
recommending the content of the target contract based on a contract content recommendation model according to the first target information of the target contract to obtain contract recommendation content, wherein the contract recommendation content comprises a target contract standard normal form and/or a target contract body example and/or a target contract standard clause;
and generating the target contract according to the contract recommendation content.
As an optional implementation manner, in the first aspect of the present invention, the recommending, according to the first target information of the target contract, the content of the target contract based on a contract content recommendation model to obtain a contract recommended content includes:
determining a service line corresponding to the target contract according to the first target information of the target contract;
under the business line, screening a target contract standard model from a contract standard model library based on a contract content recommendation model, and/or screening a target contract body example from a contract body example library, and/or screening a target contract standard clause from a contract standard clause library to obtain contract recommendation content;
the number of the target contract standard clauses, the target contract body examples and the target contract standard clauses can be 1 or more, each contract standard paradigm in the contract standard paradigm library is composed of contract elements for completing the classification of the knowledge graph, each contract body example in the contract body example library is composed of contract elements for completing the classification of the knowledge graph, and each contract standard clause in the contract standard clause library is composed of contract elements for completing the classification of the knowledge graph.
As an optional implementation manner, in the first aspect of the present invention, the screening, under the business line, a target contract standard norm from a contract standard norm library and/or a target contract standard example from a contract standard example library and/or a target contract standard term from a contract standard term library based on a contract content recommendation model includes:
acquiring second target information under the service line, wherein the second target information comprises at least one piece of sub information, and the sub information comprises first historical time information of each contract standard template selected by an undertaking department of the target contract and second historical time information of each contract standard template selected by an undertaking person of the target contract;
and/or the presence of a gas in the gas,
the sub-information comprises third history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract and fourth history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract;
and/or the presence of a gas in the atmosphere,
the sub-information comprises fifth historical time information of each contract standard term in the contract standard term library selected by the contractor of the target contract and sixth historical time information of each contract standard term in the contract standard term library selected by the contractor of the target contract;
determining a weighting factor corresponding to each sub-information in the second target information;
calculating according to the sub-information and a weighting factor corresponding to each sub-information based on a contract content recommendation model to obtain a calculation result, wherein the calculation result comprises a score of each contract standard norm in the contract standard library and/or a score of each contract body case in the contract body case library and/or a score of each contract standard clause in the contract standard clause library;
and determining a target contract standard norm and/or a target contract body example and/or a target contract standard clause according to the calculation result.
As an optional implementation manner, in the first aspect of the present invention, the determining, according to the calculation result, a target contract standard norm and/or a target contract body example and/or a target contract standard clause includes:
determining all contract standard norms with scores of the contract standard norms in the contract standard norms library which are more than or equal to a preset score threshold value in the calculation result as the target contract norms;
and/or the presence of a gas in the gas,
determining all contract body examples of which the scores of the contract body examples in the contract body example library are greater than or equal to a preset score threshold value in the calculation result as the target contract body examples;
and/or the presence of a gas in the atmosphere,
determining all contract standard terms in the contract standard term library in the calculation result with scores larger than or equal to a preset score threshold as the target contract terms.
As an optional implementation manner, in the first aspect of the present invention, in the contract element library for completing the classification of the knowledge graph, a plurality of contract elements of the same category form a tree-shaped association system, where the tree-shaped association system includes a plurality of levels, and the relationship between the plurality of contract elements of the same category is determined by the plurality of levels;
and, the method further comprises:
receiving feedback information which is input by a certain user and is related to a certain contract element;
according to the feedback information, self-learning is carried out through a word expansion algorithm to obtain expansion words corresponding to the contract elements;
and importing the expansion words corresponding to the contract elements into the contract element library.
As an alternative implementation, in the first aspect of the present invention, the method further includes:
acquiring a contract examination rule corresponding to the target contract, wherein the contract examination rule is a rule formed by calling data under a business line corresponding to the target contract;
according to the contract examination rule, examining the target contract based on a contract verification model to obtain a contract examination result;
judging whether the examination result is abnormal or not;
and when the judgment result is yes, generating first prompt information, wherein the first prompt information is used for prompting to adjust the content of the target contract.
As an alternative implementation, in the first aspect of the present invention, the method further includes:
acquiring target risk cases related to the target contract from the risk case base according to the first target information of the target contract, wherein all the risk cases in the risk case base consist of contract elements for completing knowledge graph classification;
comparing the target contract with the target risk case to obtain a comparison result;
and generating corresponding warning information according to different comparison results.
The second aspect of the invention discloses a contract management device based on knowledge graph classification, which comprises:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring first target information corresponding to a target contract, the target contract is any contract to be submitted, and the first target information comprises service category information corresponding to the target contract;
the recommending module is used for recommending the content of the target contract based on a contract content recommending model according to the first target information of the target contract to obtain contract recommending content, and the contract recommending content comprises a target contract standard norm and/or a target contract body example and/or a target contract standard clause;
and the contract generation module is used for generating the target contract according to the contract recommendation content.
As an optional implementation manner, in the second aspect of the present invention, the recommending module recommends, according to the first target information of the target contract, the content of the target contract based on the contract content recommending model, and a specific manner of obtaining the contract recommended content is:
determining a service line corresponding to the target contract according to the first target information of the target contract;
under the business line, screening a target contract standard model from a contract standard model library and/or screening a target contract body example from a contract body example library and/or screening a target contract standard clause from the contract standard clause library based on a contract content recommendation model to obtain contract recommendation content;
the number of the target contract standard clauses, the target contract body examples and the target contract standard clauses can be 1 or more, each contract standard paradigm in the contract standard paradigm library is composed of contract elements for completing the classification of the knowledge graph, each contract body example in the contract body example library is composed of contract elements for completing the classification of the knowledge graph, and each contract standard clause in the contract standard clause library is composed of contract elements for completing the classification of the knowledge graph.
As an optional implementation manner, in the second aspect of the present invention, the recommendation module, under the business line, based on the contract content recommendation model, screens the target contract standard template from the contract standard template library and/or screens the target contract body examples from the contract body example library and/or screens the target contract standard terms from the contract standard terms library in a specific manner:
acquiring second target information under the service line, wherein the second target information comprises at least one piece of sub-information, and the sub-information comprises first historical time information of each contract standard model in a contract standard model library selected by an undertaking department of the target contract and second historical time information of each contract standard model in the contract standard model library selected by an undertaking department of the target contract;
and/or the presence of a gas in the atmosphere,
the sub-information comprises third history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract and fourth history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract;
and/or the presence of a gas in the atmosphere,
the sub-information comprises fifth historical time information of each contract standard term in the contract standard term library selected by the contractor of the target contract and sixth historical time information of each contract standard term in the contract standard term library selected by the contractor of the target contract;
determining a weighting factor corresponding to each sub-information in the second target information;
calculating according to the sub-information and a weighting factor corresponding to each sub-information based on a contract content recommendation model to obtain a calculation result, wherein the calculation result comprises a score of each contract standard template in the contract standard template library and/or a score of each contract body example in the contract body template library and/or a score of each contract standard clause in the contract standard clause library;
and determining a target contract standard norm and/or a target contract body example and/or a target contract standard clause according to the calculation result.
As an optional implementation manner, in the second aspect of the present invention, the specific manner of determining the target contract standard norm and/or the target contract body examples and/or the target contract standard clauses by the recommending module according to the calculation result is:
determining all contract standard norms with scores of the contract standard norms in the contract standard norms library which are more than or equal to a preset score threshold value in the calculation result as the target contract norms;
and/or the presence of a gas in the gas,
determining all contract body examples with the scores of the contract body examples in the contract body example library in the calculation result being greater than or equal to a preset score threshold value as the target contract body example;
and/or the presence of a gas in the gas,
determining all contract standard terms in the contract standard term library in the calculation result with scores larger than or equal to a preset score threshold as the target contract terms.
As an optional implementation manner, in the second aspect of the present invention, in the contract element library for completing the classification of the knowledge graph, a plurality of contract elements of the same category form a tree-shaped association system, wherein the tree-shaped association system comprises a plurality of levels, and the relationship between the plurality of contract elements of the same category is determined through the plurality of levels;
and, the apparatus further comprises:
the receiving module is used for receiving feedback information which is input by a certain user and is related to a certain contract element;
the expansion module is used for self-learning through a word expansion algorithm according to the feedback information to obtain an expansion word corresponding to the contract element;
and the importing module is used for importing the expansion words corresponding to the contract elements into the contract element library.
As an optional implementation manner, in the second aspect of the present invention, the obtaining module is further configured to obtain a contract inspection rule corresponding to the target contract, where the contract inspection rule is a rule formed by retrieving data under a business line corresponding to the target contract;
and, the apparatus further comprises:
the examination module is used for examining the target contract based on a contract verification model according to the contract examination rule to obtain a contract examination result;
the judging module is used for judging whether the examination result is abnormal or not;
and the prompting module is used for generating first prompting information when the judgment result of the judging module is yes, wherein the first prompting information is used for prompting the adjustment of the content of the target contract.
As an optional implementation manner, in the second aspect of the present invention, the obtaining module is further configured to obtain, from the risk case library, a target risk case related to the target contract according to the first target information of the target contract, where all risk cases in the risk case library are composed of contract elements that complete classification of a knowledge graph;
and, the apparatus further comprises:
the comparison module is used for comparing the target contract with the target risk case to obtain a comparison result;
and the prompt module is also used for generating corresponding warning information according to different comparison results.
The third aspect of the invention discloses a contract management device based on knowledge graph classification, which comprises:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program codes stored in the memory to execute part or all of the steps of the contract management method based on the knowledge-graph classification disclosed by the first aspect of the invention.
In a fourth aspect, the present invention discloses a computer storage medium storing computer instructions for performing some or all of the steps of the method for contract management based on knowledge-graph classification disclosed in the first aspect of the present invention when the computer instructions are invoked.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, first target information corresponding to a target contract is obtained, wherein the target contract is a contract to be held, and the first target information comprises service category information corresponding to the target contract; recommending the content of the target contract based on a contract content recommendation model according to the first target information of the target contract to obtain contract recommended content, wherein the contract recommended content comprises a target contract standard normal form and/or a target contract body example and/or a target contract standard clause; and generating the target contract according to the contract recommendation content. Therefore, the method and the device can automatically recommend the content of the target contract based on the contract content recommendation model according to the information such as the service category of the target contract to be submitted, recommend the information such as the target contract standard model essay, the target contract body example and the target contract standard clause corresponding to the target contract in a large amount of contract template libraries, and can quickly and accurately find the contract template matched with the current service through the operation, thereby effectively improving the submission quality of the contract.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a contract management method based on knowledge-graph classification according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram of another method for contract management based on knowledge-graph classification according to the embodiment of the invention;
FIG. 3 is a schematic structural diagram of a contract management apparatus based on knowledge-graph classification according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of another contract management apparatus based on knowledge-graph classification according to the embodiment of the present invention;
fig. 5 is a schematic structural diagram of another contract management apparatus based on knowledge-graph classification according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, product, or apparatus that comprises a list of steps or elements is not limited to those listed but may alternatively include other steps or elements not listed or inherent to such process, method, product, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The embodiment of the invention discloses a contract management method and a device based on knowledge graph classification, which can automatically recommend the content of a target contract based on a contract content recommendation model according to the information such as the service category of the target contract to be submitted, recommend the information such as target contract standard template, target contract body example and target contract standard clause corresponding to the target contract in a large amount of contract template libraries, and can quickly and accurately find a contract template matched with the current service through the operation, thereby effectively improving the submission quality of the contract. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a method for contract management based on knowledge-graph classification according to an embodiment of the present invention. As shown in FIG. 1, the method for contract management based on knowledge-graph classification may include the following operations:
101. the method comprises the steps of obtaining first target information corresponding to a target contract, wherein the target contract is any contract to be held, and the first target information comprises service category information corresponding to the target contract.
In this embodiment of the present invention, the first target information of the target contract further includes information about a company (e.g., a subsidiary company, a branch company), an undertaking department, and an undertaking staff, to which the contract undertaking of the target contract belongs, and may further include other information related to the target contract, which is not limited in this embodiment of the present invention.
In the embodiment of the invention, the business category information corresponding to the target contract is the business category corresponding to the target contract, a business architecture system can be constructed according to each business responsibility and division, and the business category information corresponding to the target activity can be obtained according to the constructed business architecture system. For example, for an electric power enterprise, an electric power business architecture system is constructed according to each business duty and division of the electric power enterprise, business category information corresponding to a target contract can be obtained according to the constructed electric power business architecture system,
102. and recommending the content of the target contract based on a contract content recommendation model according to the first target information of the target contract to obtain contract recommended content, wherein the contract recommended content comprises a target contract standard norm and/or a target contract body example and/or a target contract standard clause.
In the embodiment of the invention, the contract recommendation content comprises a target contract standard normal sentence and/or a target contract body example and/or a target contract standard clause, wherein the target contract standard normal sentence is a contract standard normal sentence which is selected from a contract standard normal library and is matched with the target contract, and the contract standard normal sentence is a contract text which is made by companies or branches and sub-official and is used by all departments and subordinate units of a unit in priority and cannot change the clause thereof; the target contract embodiment is a contract embodiment matched with the target contract and selected from a contract embodiment library, and the contract embodiment refers to a related title list composed of main terms of the contract, such as the target, the price, the quality, the fulfillment period and the like; the target contract standard clause is selected from a contract standard clause library and matched with the target contract, and the contract standard clause refers to the main clauses of the contract, such as target, price, quality, fulfillment period and the like.
In the embodiment of the invention, the contract content recommendation model identifies and analyzes the demand information and the contract requirements of the target contract based on the cloud computing technology and the artificial intelligence algorithm, calculates the matching degree of each contract content to be recommended by combining the data in the database, and recommends the contract recommendation content corresponding to the target contract according to the matching degree.
Further, in the operation of determining the contract recommendation content, the contract content recommendation model may first calculate a matching degree between each contract content to be recommended and the target contract;
comparing the matching degree of each contract content to be recommended with a matching degree threshold value, and screening out initial contract content to be recommended;
and determining contract recommended content corresponding to the target contract according to all the contract contents to be recommended.
103. And generating a target contract according to the contract recommendation content.
In the embodiment of the invention, the target contract can be generated according to the recommended target contract standard model; the target contract can also be generated according to the recommended target contract body example; the target contract may also be generated according to recommended target contract standard terms; the target contract can be generated according to the recommended target contract standard norms and the target contract body examples; the target contract can be generated according to the recommended target contract body examples and the target contract standard clauses; the target contract can also be generated according to the recommended target contract standard norm and target contract body examples and target contract standard clauses.
Therefore, the contract management method based on knowledge graph classification described by the embodiment of the invention can automatically recommend the content of the target contract based on the contract content recommendation model according to the service category and other information of the target contract to be underwritten, recommend the information of the target contract standard model essay, the target contract body example, the target contract standard clause and the like corresponding to the target contract in a large amount of contract template libraries, and can quickly and accurately find the contract template matched with the current service through the operation, thereby effectively improving the underwriting quality of the contract.
Example two
Referring to fig. 2, fig. 2 is a schematic flow chart of another method for contract management based on knowledge-graph classification according to an embodiment of the present invention. As shown in FIG. 2, the contract management method based on knowledge-graph classification can comprise the following operations:
201. the method comprises the steps of obtaining first target information corresponding to a target contract, wherein the target contract is any contract to be underwritten, and the first target information comprises service category information corresponding to the target contract.
202. And determining a business line corresponding to the target contract according to the first target information of the target contract.
203. Under the business line, a target contract standard model is screened from a contract standard model library based on a contract content recommendation model, and/or a target contract body example is screened from a contract body example library and/or a target contract standard clause is screened from a contract standard clause library to obtain contract recommendation content.
In the embodiment of the invention, the contract management system classifies all related services to obtain a plurality of service lines corresponding to different services, each service line is provided with a contract standard model and/or contract body examples and/or contract standard clauses related to the services, and when the service line of a target contract is determined, the contract standard model and/or contract body examples and/or contract standard clauses under the related service line can be pertinently recommended, so that more appropriate contract contents can be recommended.
In the embodiment of the present invention, the number of the target contract standard clause and the target contract body examples and the target contract standard clause may be 1 or more, each contract standard paradigm in the contract standard library is composed of contract elements for completing classification of a knowledge graph, each contract body example in the contract body library is composed of contract elements for completing classification of a knowledge graph, and each contract standard clause in the contract standard clause library is composed of contract elements for completing classification of a knowledge graph.
In an optional embodiment, the screening, under the business line, the target contract standard norm from the contract standard norm library and/or the target contract body examples from the contract body example library and/or the target contract standard terms from the contract standard terms library based on the contract content recommendation model includes:
acquiring second target information under the service line, wherein the second target information comprises at least one piece of sub information, and the sub information comprises first historical time information of each contract standard model in a contract standard model library selected by an undertaking department of the target contract and second historical time information of each contract standard model in the contract standard model library selected by the undertaking person of the target contract;
and/or the presence of a gas in the gas,
the sub-information comprises third history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract and fourth history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract;
and/or the presence of a gas in the gas,
the sub-information comprises fifth historical time information of each contract standard clause in the contract standard clause library selected by the contractor of the target contract and sixth historical time information of each contract standard clause in the contract standard clause library selected by the contractor of the target contract;
determining a weighting factor corresponding to each sub-information in the second target information;
calculating according to the sub-information and the weighting factor corresponding to each sub-information based on a contract content recommendation model to obtain a calculation result, wherein the calculation result comprises the score of each contract standard template in the contract standard template library and/or the score of each contract body example in the contract body example library and/or the score of each contract standard clause in the contract standard clause library;
and determining the target contract standard norm and/or target contract examples and/or target contract standard clauses according to the calculation result.
Therefore, in the optional embodiment, the target contract standard model, the target contract body example and the target contract standard clause can be obtained by obtaining the plurality of pieces of sub information under the business line corresponding to the target contract and according to the scoring results of the weighting factors corresponding to the plurality of pieces of sub information, and the accuracy of determining the contract recommended content can be improved through the above manner.
In another optional embodiment, the determining the target contract standard norm and/or the target contract body example and/or the target contract standard clause according to the calculation result comprises:
determining all contract standard norms with scores of the contract standard norms in the contract standard norm library which are more than or equal to a preset score threshold value in the calculation result as the target contract norms;
and/or the presence of a gas in the gas,
determining all contract body examples of which the scores of the contract body examples in the contract body example library are greater than or equal to a preset score threshold value in the calculation result as the target contract body example;
and/or the presence of a gas in the atmosphere,
and determining all contract standard terms with scores of contract standard terms in the contract standard term library larger than or equal to a preset score threshold value in the calculation result as the target contract terms.
It can be seen that this alternative embodiment can further improve the accuracy of determining the contract recommended content by confirming the target contract standard norm, the target contract body examples and the target contract standard clauses with the result that the score is greater than or equal to the corresponding score threshold.
In a further alternative embodiment, in the contract element library for completing the classification of the knowledge graph, a plurality of contract elements of the same category form a tree-shaped association system, wherein the tree-shaped association system comprises a plurality of levels, and the relationship among the plurality of contract elements of the same category is determined through a plurality of the levels;
and, the method further comprises:
receiving feedback information which is input by a certain user and is related to a certain contract element;
according to the feedback information, self-learning is carried out through a word expansion algorithm to obtain an expansion word corresponding to the contract element;
and importing the expansion words corresponding to the contract elements into the contract element library.
In this alternative embodiment, a plurality of contract elements of the same category form a tree-shaped association system, which may be three levels, for example, the first level contract element may be a term title, the second level contract element may be an examination element, and the third level contract element may be a contract byte, and a plurality of levels may be further refined according to actual requirements, for example, the plurality of levels may be further ranked according to financial elements, legal elements, and professional elements.
In this optional embodiment, the obtaining way of the feedback information related to a certain contract element may be obtained from a database of the contract management system itself, or may be obtained from another external database related to the contract element managed by the contract, which is not limited in the embodiment of the present invention.
Therefore, the optional embodiment can enable the contract elements in the contract element library to self-learn through the input feedback information, can realize the expansion of the contract elements, and can improve the efficiency of handling the contract by expanding the more abundant contract elements.
204. And generating a target contract according to the contract recommendation content.
In the embodiment of the present invention, for other descriptions of steps 201 to 204, please refer to the detailed description of steps 101 to 103 in the first embodiment, which is not repeated herein.
Therefore, by implementing the contract management method based on knowledge graph classification described in the embodiment of the invention, the service line corresponding to the target contract can be determined according to the service category and other information of the target contract to be underwritten, the contract content recommendation model screens out the information of the target contract standard template, the target contract body example, the target contract standard clause and the like which are more matched with the target contract under the determined service line, and the contract template matched with the current service can be further quickly and accurately found through the operation, so that the underwriting quality of the contract is further improved.
In yet another optional embodiment, the method may further comprise:
acquiring a contract examination rule corresponding to the target contract, wherein the contract examination rule is a rule formed by calling data under a business line corresponding to the target contract;
according to the contract examination rule, examining the target contract based on a contract verification model to obtain a contract examination result;
judging whether the examination result is abnormal or not;
and when the judgment result is yes, generating first prompt information, wherein the first prompt information is used for prompting the adjustment of the content of the target contract.
Therefore, the optional embodiment can acquire the contract examination rules which are accurately matched with the target contract, and the examination of the target contract is realized through the contract examination rules, so that the examination efficiency of the contract can be improved, and the error rate of contract examination can be reduced.
In yet another optional embodiment, the method may further comprise:
acquiring target risk cases related to the target contract from the risk case base according to the first target information of the target contract, wherein all the risk cases in the risk case base consist of contract elements for completing knowledge graph classification;
comparing the target contract with the target risk case to obtain a comparison result;
and generating corresponding warning information according to different comparison results.
Therefore, the optional embodiment can acquire the target risk cases which are exactly matched with the target contracts, and by comparing the risk cases with the target contracts, the risks in the target contracts can be known in time, and the possibility of risks occurring in the contracts is reduced.
EXAMPLE III
Referring to fig. 3, fig. 3 is a schematic structural diagram of a contract management apparatus based on knowledge-graph classification according to an embodiment of the present invention. As shown in fig. 3, the apparatus may include:
an obtaining module 301, configured to obtain first target information corresponding to a target contract, where the target contract is a contract to be held, and the first target information includes service category information corresponding to the target contract;
the recommending module 302 is configured to recommend the content of the target contract based on a contract content recommending model according to the first target information of the target contract, so as to obtain contract recommending content, where the contract recommending content includes a target contract standard model essay and/or a target contract physical example and/or a target contract standard clause;
the contract generating module 303 is configured to generate the target contract according to the contract recommended content.
Therefore, the contract management device based on the knowledge graph classification can automatically recommend the content of the target contract based on the contract content recommendation model according to the information such as the service category of the target contract to be submitted, recommend the information such as the target contract standard model, the target contract body example and the target contract standard clause corresponding to the target contract in a large number of contract template libraries, and quickly and accurately find the contract template matched with the current service through the operation, so that the submission quality of the contract is effectively improved.
In an optional embodiment, the recommending module 302 recommends the content of the target contract based on the contract content recommending model according to the first target information of the target contract, and the specific manner of obtaining the contract recommended content is as follows:
determining a service line corresponding to the target contract according to the first target information of the target contract;
under the business line, screening a target contract standard model from a contract standard model library based on a contract content recommendation model, and/or screening a target contract body example from a contract body example library, and/or screening a target contract standard clause from a contract standard clause library to obtain contract recommendation content;
the number of the target contract standard clauses and the target contract body examples and the target contract standard clauses can be 1 or more, each contract standard paradigm in the contract standard library is composed of contract elements for completing the classification of the knowledge graph, each contract body example in the contract body library is composed of contract elements for completing the classification of the knowledge graph, and each contract standard clause in the contract standard clause library is composed of contract elements for completing the classification of the knowledge graph.
It can be seen that, by implementing the contract management device based on knowledge graph classification described in the embodiment of the present invention, the service line corresponding to the target contract can be determined according to the service category and other information of the target contract to be underwritten, the contract content recommendation model screens out the information of the target contract standard template, the target contract body example, the target contract standard clause and the like which are more matched with the target contract under the determined service line, and the contract template matched with the current service can be further quickly and accurately found through the above operations, so as to further improve the underwriting quality of the contract.
In another alternative embodiment, the recommendation module 302 screens the target contract standard norm from the contract standard norm library and/or the target contract body examples from the contract body example library and/or the target contract standard terms from the contract standard terms library based on the contract content recommendation model under the business line in the specific manner:
acquiring second target information under the service line, wherein the second target information comprises at least one piece of sub information, and the sub information comprises first historical time information of each contract standard model in a contract standard model library selected by an undertaking department of the target contract and second historical time information of each contract standard model in the contract standard model library selected by the undertaking person of the target contract;
and/or the presence of a gas in the atmosphere,
the sub-information comprises third history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract and fourth history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract;
and/or the presence of a gas in the atmosphere,
the sub-information comprises fifth historical time information of each contract standard clause in the contract standard clause library selected by the contractor of the target contract and sixth historical time information of each contract standard clause in the contract standard clause library selected by the contractor of the target contract;
determining a weighting factor corresponding to each sub-information in the second target information;
calculating according to the sub-information and the weighting factor corresponding to each sub-information based on a contract content recommendation model to obtain a calculation result, wherein the calculation result comprises the score of each contract standard template in the contract standard template library and/or the score of each contract body example in the contract body example library and/or the score of each contract standard clause in the contract standard clause library;
and determining a target contract standard norm and/or a target contract body example and/or a target contract standard clause according to the calculation result.
Therefore, in the optional embodiment, the target contract standard model, the target contract body example and the target contract standard clause can be obtained by obtaining the plurality of pieces of sub information under the business line corresponding to the target contract and according to the calculation results of the weighting factors corresponding to the plurality of pieces of sub information, and the accuracy of determining the contract recommended content can be improved through the above manner.
In another optional embodiment, the recommending module 302 determines the specific manner of the target contract standard norm and/or the target contract physical examples and/or the target contract standard clauses according to the calculation result as follows:
determining all contract standard norms with scores of the contract standard norms in the contract standard norm library which are more than or equal to a preset score threshold value in the calculation result as the target contract norms;
and/or the presence of a gas in the gas,
determining all contract body examples with the scores of the contract body examples in the contract body example library in the calculation result being more than or equal to a preset score threshold value as the target contract body example;
and/or the presence of a gas in the atmosphere,
and determining all contract standard terms with scores of contract standard terms in the contract standard term library larger than or equal to a preset score threshold value in the calculation result as the target contract terms.
It can be seen that this alternative embodiment can further improve the accuracy of determining the contract recommendation content by confirming the target contract standard norms, target contract examples and target contract standard clauses with the result that the score is greater than or equal to the corresponding score threshold.
In yet another alternative embodiment, as shown in fig. 4, in the contract element library for completing the classification of the knowledge graph, a plurality of contract elements of the same category form a tree-shaped association system, wherein the tree-shaped association system comprises a plurality of levels, and the relationship between the plurality of contract elements of the same category is determined through a plurality of the levels;
and, the apparatus further comprises:
a receiving module 304, configured to receive feedback information related to a contract element, which is input by a certain user;
the expansion module 305 is configured to perform self-learning through a word expansion algorithm according to the feedback information to obtain an expansion word corresponding to the contract element;
an importing module 306, configured to import the expansion word corresponding to the contract element into the contract element library.
Therefore, the optional embodiment can enable the contract elements in the contract element library to self-learn through the input feedback information, can realize the expansion of the contract elements, and can improve the efficiency of handling the contract by expanding the more abundant contract elements.
In yet another optional embodiment, as shown in fig. 4, the obtaining module 301 is further configured to obtain a contract inspection rule corresponding to the target contract, where the contract inspection rule is a rule formed by retrieving data under a business line corresponding to the target contract;
and, the apparatus further comprises:
the examination module 307 is configured to examine the target contract based on the contract verification model according to the contract examination rule to obtain a contract examination result;
a determining module 308, configured to determine whether the examination result is abnormal;
a prompting module 309, configured to generate first prompting information when the determination result of the determining module 308 is yes, where the first prompting information is used to prompt to adjust the content of the target contract.
Therefore, the optional embodiment can acquire the contract examination rules which are accurately matched with the target contract, and the examination of the target contract is realized through the contract examination rules, so that the examination efficiency of the contract can be improved, and the error rate of the contract examination can be reduced.
In yet another alternative embodiment, as shown in fig. 4, the obtaining module 301 is further configured to obtain a target risk case related to the target contract from the risk case base according to the first target information of the target contract, where all risk cases in the risk case base are composed of contract elements that complete classification of a knowledge graph;
and, the apparatus further comprises:
a comparing module 309, configured to compare the target contract with the target risk case to obtain a comparison result;
the prompting module 309 is further configured to generate corresponding warning information according to different comparison results.
Therefore, the optional embodiment can acquire the target risk cases which are exactly matched with the target contract, and by comparing the risk cases with the target contract, the risk in the target contract can be known in time, and the possibility of occurrence of risk of the contract is reduced.
Example four
Referring to fig. 5, fig. 5 is a schematic structural diagram of another contract management apparatus based on knowledge-graph classification according to an embodiment of the present invention. As shown in fig. 5, the apparatus may include:
a memory 401 storing executable program code;
a processor 402 coupled with the memory 401;
the processor 402 calls executable program code stored in the memory 401 for performing the steps in the method for contract management based on knowledge-graph classification described in embodiment one or embodiment two.
EXAMPLE five
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the contract management method based on knowledge graph classification described in the first embodiment or the second embodiment.
EXAMPLE six
The embodiment of the invention discloses a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, wherein the computer program is operable to make a computer execute the steps of the contract management method based on knowledge-graph classification described in the first embodiment or the second embodiment.
The above-described embodiments of the apparatus are merely illustrative, and the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above detailed description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, wherein the storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc-Read-Only Memory (CD-ROM) or other Memory capable of storing data, a magnetic tape, or any other computer-readable medium capable of storing data.
Finally, it should be noted that: the contract management method and apparatus based on knowledge graph classification disclosed in the embodiments of the present invention are only disclosed as preferred embodiments of the present invention, and are only used for illustrating the technical solution of the present invention, not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for contract management based on knowledge-graph classification, the method comprising:
acquiring first target information corresponding to a target contract, wherein the target contract is any contract to be submitted, and the first target information comprises service category information corresponding to the target contract;
recommending the content of the target contract based on a contract content recommendation model according to the first target information of the target contract to obtain contract recommendation content, wherein the contract recommendation content comprises a target contract standard normal form and/or a target contract body example and/or a target contract standard clause;
and generating the target contract according to the contract recommendation content.
2. The method for contract management based on knowledge-graph classification as claimed in claim 1, wherein the recommending the content of the target contract based on a contract content recommendation model according to the first target information of the target contract to obtain a contract recommended content comprises:
determining a service line corresponding to the target contract according to the first target information of the target contract;
under the business line, screening a target contract standard model from a contract standard model library based on a contract content recommendation model, and/or screening a target contract body example from a contract body example library, and/or screening a target contract standard clause from a contract standard clause library to obtain contract recommendation content;
the number of the target contract standard clauses, the target contract body examples and the target contract standard clauses can be 1 or more, each contract standard paradigm in the contract standard paradigm library is composed of contract elements for completing the classification of the knowledge graph, each contract body example in the contract body example library is composed of contract elements for completing the classification of the knowledge graph, and each contract standard clause in the contract standard clause library is composed of contract elements for completing the classification of the knowledge graph.
3. The method for contract management based on knowledge-graph classification according to claim 2, wherein the screening of the target contract standard normal sentence from the contract standard normal library and/or the screening of the target contract body examples from the contract body example library and/or the screening of the target contract body standard terms from the contract body standard terms library under the business line based on the contract content recommendation model comprises:
acquiring second target information under the service line, wherein the second target information comprises at least one piece of sub-information, and the sub-information comprises first historical time information of each contract standard model in a contract standard model library selected by an undertaking department of the target contract and second historical time information of each contract standard model in the contract standard model library selected by an undertaking department of the target contract;
and/or the presence of a gas in the gas,
the sub-information comprises third history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract and fourth history frequency information of each contract body example in the contract body example library selected by the undertaking department of the target contract;
and/or the presence of a gas in the gas,
the sub-information comprises fifth historical time information of each contract standard clause in the contractor selection contract standard clause library of the target contract and sixth historical time information of each contract standard clause in the contractor selection contract standard clause library of the target contract;
determining a weighting factor corresponding to each sub-information in the second target information;
calculating according to the sub-information and a weighting factor corresponding to each sub-information based on a contract content recommendation model to obtain a calculation result, wherein the calculation result comprises a score of each contract standard norm in the contract standard library and/or a score of each contract body case in the contract body case library and/or a score of each contract standard clause in the contract standard clause library;
and determining a target contract standard norm and/or a target contract body example and/or a target contract standard clause according to the calculation result.
4. The method for contract management based on knowledge-graph classification as claimed in claim 3, wherein the determining of the target contract standard norm and/or target contract examples and/or target contract standard clauses according to the calculation result comprises:
determining all contract standard norms with scores of the contract standard norms in the contract standard norm library which are greater than or equal to a preset score threshold value in the calculation result as the target contract norms;
and/or the presence of a gas in the gas,
determining all contract body examples with the scores of the contract body examples in the contract body example library in the calculation result being greater than or equal to a preset score threshold value as the target contract body example;
and/or the presence of a gas in the atmosphere,
determining all contract standard terms in the contract standard term library in the calculation result with scores larger than or equal to a preset score threshold as the target contract terms.
5. The contract management method based on the knowledge-graph classification as claimed in any one of claims 2-4, characterized in that in the contract element library for completing the knowledge-graph classification, a plurality of contract elements of the same category form a tree-shaped association system, wherein the tree-shaped association system comprises a plurality of levels, and the relationship between the plurality of contract elements of the same category is determined by the plurality of levels;
and, the method further comprises:
receiving feedback information which is input by a certain user and is related to a certain contract element;
according to the feedback information, self-learning is carried out through a word expansion algorithm to obtain expansion words corresponding to the contract elements;
and importing the expansion words corresponding to the contract elements into the contract element library.
6. The method for contract management based on knowledge-graph classification of claim 5, wherein the method further comprises:
acquiring a contract examination rule corresponding to the target contract, wherein the contract examination rule is a rule formed by calling data under a business line corresponding to the target contract;
according to the contract examination rule, examining the target contract based on a contract verification model to obtain a contract examination result;
judging whether the examination result is abnormal or not;
and when the judgment result is yes, generating first prompt information, wherein the first prompt information is used for prompting to adjust the content of the target contract.
7. The method for contract management based on knowledge-graph classification of claim 6, wherein the method further comprises:
acquiring a target risk case related to the target contract from the risk case library according to the first target information of the target contract, wherein all risk cases in the risk case library consist of contract elements for completing knowledge graph classification;
comparing the target contract with the target risk case to obtain a comparison result;
and generating corresponding warning information according to different comparison results.
8. A contract management apparatus based on knowledge-graph classification, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring first target information corresponding to a target contract, the target contract is any contract to be submitted, and the first target information comprises service category information corresponding to the target contract;
the recommendation module is used for recommending the content of the target contract based on a contract content recommendation model according to the first target information of the target contract to obtain contract recommendation content, wherein the contract recommendation content comprises a target contract standard norm and/or a target contract body example and/or a target contract standard clause;
and the contract generation module is used for generating the target contract according to the contract recommendation content.
9. A contract management apparatus based on knowledge-graph classification, the apparatus comprising:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to perform some or all of the steps of the method of contract management based on knowledge-graph classification of any one of claims 1-7.
10. A computer storage medium storing computer instructions which, when invoked, perform some or all of the steps in a method for contract management based on knowledgegraph taxonomy as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211115419.2A CN115422904A (en) | 2022-09-14 | 2022-09-14 | Contract management method and device based on knowledge graph classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211115419.2A CN115422904A (en) | 2022-09-14 | 2022-09-14 | Contract management method and device based on knowledge graph classification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115422904A true CN115422904A (en) | 2022-12-02 |
Family
ID=84203002
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211115419.2A Pending CN115422904A (en) | 2022-09-14 | 2022-09-14 | Contract management method and device based on knowledge graph classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115422904A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230059494A1 (en) * | 2021-08-19 | 2023-02-23 | Digital Asset Capital, Inc. | Semantic map generation from natural-language text documents |
-
2022
- 2022-09-14 CN CN202211115419.2A patent/CN115422904A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230059494A1 (en) * | 2021-08-19 | 2023-02-23 | Digital Asset Capital, Inc. | Semantic map generation from natural-language text documents |
| US20230056987A1 (en) * | 2021-08-19 | 2023-02-23 | Digital Asset Capital, Inc. | Semantic map generation using hierarchical clause structure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7783545B2 (en) | Automated coaching for a financial modeling and counseling system | |
| CN111192144A (en) | Financial data prediction method, device, equipment and storage medium | |
| US11657402B2 (en) | Dynamic claims submission system | |
| CN114547475B (en) | Resource recommendation method, device and system | |
| CN113742492A (en) | Insurance scheme generation method and device, electronic equipment and storage medium | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN115422904A (en) | Contract management method and device based on knowledge graph classification | |
| JP6978582B2 (en) | Forecasting business support device and forecasting business support method | |
| CN114281932A (en) | Method, device and equipment for training work order quality inspection model and storage medium | |
| US20210027319A1 (en) | Method and system for collecting and analyzing data to generate performance forecasts for assets | |
| CN113361959A (en) | Method and device for calculating maturity of centralized operation of banking business | |
| CN112860672A (en) | Method and device for determining label weight | |
| CN111353728A (en) | Risk analysis method and system | |
| US11645449B1 (en) | Computing system for data annotation | |
| CN115660451A (en) | Supplier risk early warning method, device, equipment and medium based on RPA | |
| CN113450208A (en) | Loan risk change early warning and model training method and device | |
| CN111026705B (en) | Building engineering file management method, system and terminal equipment | |
| CN113743752A (en) | Data processing method and device | |
| CN113743435A (en) | Business data classification model training method and device, and business data classification method and device | |
| JP2020038570A (en) | Estimation device, system, method and program, and learning apparatus and method | |
| CN113987186B (en) | Method and device for generating marketing scheme based on knowledge graph | |
| WO2023144949A1 (en) | Risk countermeasure assistance device, learning device, risk countermeasure assistance method, learning method, and program | |
| US20240020327A1 (en) | Lossless summarization | |
| US20230342693A1 (en) | Methods and apparatus for natural language processing and governance | |
| WO2023195117A1 (en) | Group generating device, group generating method, and non-transitory computer-readable 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 |