CN114943217A - Contract risk identification method, device, equipment and storage medium - Google Patents
Contract risk identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114943217A CN114943217A CN202210602862.6A CN202210602862A CN114943217A CN 114943217 A CN114943217 A CN 114943217A CN 202210602862 A CN202210602862 A CN 202210602862A CN 114943217 A CN114943217 A CN 114943217A
- Authority
- CN
- China
- Prior art keywords
- risk
- contract
- sentences
- business
- concern
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012163 sequencing technique Methods 0.000 claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 239000013598 vector Substances 0.000 claims description 44
- 230000011218 segmentation Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000012790 confirmation Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 230000002457 bidirectional effect Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 230000000306 recurrent effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 239000013307 optical fiber Substances 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
- G06Q50/188—Electronic negotiation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Technology Law (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a contract risk identification method, a contract risk identification device, contract risk identification equipment and a storage medium. The method comprises the following steps: dividing the contract to be processed to generate a plurality of contract sentences; receiving business concern risk information input by a user; expanding the service attention risk information in a preset mode; confirming contract sentences suspected of paying attention to risks in a multi-dimensional mode from a plurality of contract sentences based on the expanded business attention risk information by a preset algorithm; calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk sequencing model; and sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the highest risk from the contract sentences suspected of paying attention to the risk. When the technical scheme of the embodiment of the invention identifies the contract risk, the invention can deal with changeable contract risk scenes, has better expansibility and generalization capability and improves the risk identification accuracy.
Description
Technical Field
The embodiment of the invention relates to the field of computer software, in particular to a contract risk identification method, a contract risk identification device, contract risk identification equipment and a storage medium.
Background
One of the important items of the contracts for the parties of the contracts is contract risk identification, and the contract risk often causes some abnormal loss of the parties of the contracts or the parties of the contracts, and even causes more serious loss of the parties of the contracts due to contract fraud. In the prior art, contract risk identification is usually identified through keyword identification or semantic vector matching, the former is judged through risk keywords, but risk identification accuracy is low and identification is easy to miss, and the latter is automatic risk identification according to word vectors and word weights, so that risk identification accuracy is low, and the problem of contract risk identification cannot be efficiently and accurately solved.
Disclosure of Invention
The embodiment of the invention provides a contract risk identification method, a contract risk identification device, contract risk identification equipment and a storage medium, and can improve the efficiency and accuracy of contract risk identification.
According to an aspect of the present invention, an embodiment of the present invention provides a contract risk identification method, including:
dividing the contract to be processed to generate a plurality of contract sentences;
receiving business concern risk information input by a user;
expanding the service attention risk information in a preset mode;
confirming contract sentences suspected of paying attention to risks in a multi-dimensional mode from a plurality of contract sentences based on the expanded business attention risk information by a preset algorithm;
calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk sequencing model;
and sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the highest risk from the contract sentences suspected of paying attention to the risk.
According to another aspect of the present invention, there is provided a contract risk identifying apparatus including:
the contract processing module is used for carrying out segmentation processing on the contract to be processed so as to generate a plurality of contract sentences;
the risk expansion module is used for receiving business concern risk information input by a user; expanding the service attention risk information in a preset mode;
the suspected risk confirmation module is used for confirming the contract sentences suspected of concerning the risk in a multi-dimensional mode from the plurality of contract sentences according to the expanded business attention risk information by a preset algorithm;
the similarity calculation module is used for calculating the similarity between the business concern risk information and each suspected concern risk contract sentence by using a risk sequencing model;
and the risk confirmation module is used for sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the maximum risk from the contract sentences suspected of paying attention to the risk.
According to another aspect of the present invention, there is provided a computer apparatus comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a contract risk identification method according to any of the embodiments of the invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement a contract risk identification method according to any one of the embodiments of the present invention when executed.
According to the contract risk identification method provided by the embodiment of the invention, a to-be-processed contract is divided to generate a plurality of contract sentences; receiving business concern risk information input by a user; expanding the service attention risk information in a preset mode; confirming contract sentences suspected of paying attention to risks in a multi-dimensional mode from a plurality of contract sentences based on the expanded business attention risk information by a preset algorithm; calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk sequencing model; and sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the highest risk from the contract sentences suspected of paying attention to the risk. As an efficient contract risk identification matching mechanism, the embodiment of the application solves the technical problems that in the prior art, when contract risk identification is carried out, the risk identification accuracy is too low and the identification contract risk range is lower, can deal with changeable contract risk scenes, has good expansibility and generalization capability, improves the accuracy of the risk identification accuracy to the maximum extent, and improves the efficiency of the contract risk identification. It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
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 description of the embodiments will be briefly introduced 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 to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a contract risk identification method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a further contract risk identification method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a contract risk identification apparatus according to an embodiment of the present invention;
fig. 4 is a block diagram of a computer device 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.
Example one
Fig. 1 is a schematic diagram of a contract risk identification method according to an embodiment of the present invention, where the embodiment is applicable to a case of determining contract risk, and the method may be executed by a contract risk identification apparatus, where the apparatus may be implemented by software and/or hardware, and may be generally integrated in a computer device. As shown in fig. 1, the method comprises the steps of:
step S101, the contract to be processed is divided to generate a plurality of contract sentences.
In the embodiment of the invention, the input contract to be processed is obtained, and the contract content in the contract to be processed is divided to generate a plurality of divided contract sentences.
Optionally, the dividing the contract to be processed to generate a plurality of contract sentences includes: sentence segmentation is carried out on the contract to be processed according to the sentence segmentation rule, and a contract sentence set is generated; performing word segmentation on the contract clauses according to a word segmentation rule to generate contract clauses; and obtaining a dictionary to train word vectors to generate a word vector model.
The segmentation rule of the clauses can be any one of the segmentation rules of the clauses; for example, the segmentation may be performed using a segmentation rule of a special sentence segmenter. The segmentation rule of the word segmentation can also be any segmentation rule of the word segmentation; the word vector training can be any word vector training method, and illustratively, an open-source Chinese encyclopedia can be collected to train a word vector model. The embodiment of the present invention is not limited thereto.
In the embodiment of the invention, the clause segmentation is carried out on the contract to be processed through the clause segmentation rule to generate a contract clause set, then the clause of the contract is segmented according to the segmentation rule of the clause to generate the contract clause of the contract clause, and a word vector model is trained through a dictionary.
Step S102, receiving business concern risk information input by a user; and expanding the business concern risk information in a preset mode.
The business concern risk information may be a risk statement associated with a business in a contract, and the preset mode may be a preset risk expansion mode.
In the embodiment of the invention, the business concern risk information input by a user is received, and a preset risk expansion mode is obtained to expand the business concern risk information. Optionally, the expanding the service attention risk information in a preset mode includes: performing word segmentation on the business concern risk information according to a word segmentation rule to generate risk words; calculating the keyword score of each risk participle according to the word frequency and the inverse document frequency of each risk participle in the risk participles; sorting the keyword scores of all risk participles, and extracting a plurality of risk keywords of the business concern risk information; and inputting a plurality of risk keywords of the business concern risk information into a word vector model to obtain the most similar synonyms corresponding to the risk keywords, further replacing all the risk keywords with the synonyms, and expanding the business concern risk information.
In the embodiment of the invention, the business concern risk information is segmented into risk segments, the word frequency and the inverse document frequency of each risk segment in the risk segments are counted, the word frequency and the inverse document frequency of each risk segment are multiplied, and the product is used as the keyword score of the risk segment. Then, the keyword scores of all risk participles are sequenced from top to bottom, and a plurality of risk keywords with the keyword scores in a preset ranking are screened out; and acquiring the most similar synonyms corresponding to the risk keywords by using the screened multiple risk keyword input word vector models, further replacing all the risk keywords with the corresponding synonyms, and expanding the business attention risk information.
Illustratively, the business concern risk information is segmented, the word frequency and the inverse document frequency of each risk segmented word are calculated, the product of the word frequency and the inverse document frequency of each risk segmented word is used as the score of a keyword, n risk keywords with the scores before n names are screened out, the n risk keywords are input into a word vector model to obtain the most similar synonym corresponding to each risk keyword, all the risk keywords are replaced by the synonyms, and the business concern risk information is expanded to n.
Optionally, in another embodiment of the present invention, the expanding the business concern risk information in a preset mode further includes: inquiring a historical service risk database according to the service attention risk information, and determining the similarity between the service attention risk information and the stored historical service risk; sequencing similarity of the business concern risk information and the stored historical business risk, and determining the historical business risk similar to the business concern risk information; and expanding the business concern risk information according to the similar historical business risk.
The historical business risk database is used for storing historical business risks, and can be any one of non-relational data and relational databases. The historical business risk may be business risk information for the occurrence of a risk in the contract.
In the embodiment of the invention, after a user inputs business concern risk information, the business concern risk information is inquired in a historical business risk database according to the business concern risk information, the historical business risk database generates stored historical business risks according to the inquiry of the business concern risk information, similarity analysis is carried out on the business concern risk information and the stored historical business risks, the similarity between the business concern risk information and each stored historical business risk is generated, then the business concern risk information and each stored historical business risk are sequenced from top to bottom according to the similarity between the business concern risk information and the stored historical business risks, the historical business risks with the similarity positioned in a preset ranking are screened out as similar historical business risks, the similar historical business risks are used as business concern risk information, and the business concern risk information is expanded.
Illustratively, business concern risk information is input into a historical business risk database to be inquired, n historical business risks are inquired, the similarity between each historical business risk and the business concern risk information is calculated, the n historical business risks are sorted according to the similarity size relation from top to bottom, m historical business risks before m are selected as similar historical business risks, and m business concern risk information is expanded.
And S103, confirming contract sentences suspected of paying attention to risks in a multi-dimensional mode from a plurality of contract sentences according to the expanded business attention risk information by a preset algorithm.
Optionally, the multidimensional confirmation of the contract sentences suspected of paying attention to the risk based on the expanded business attention risk information from the plurality of contract sentences by using a preset algorithm includes:
respectively calculating the word frequency of the contract participles and the risk participles in a plurality of contract clauses to obtain the word frequency of the contract participles and the word frequency of the risk participles, and further respectively determining the contract participle weight and the risk participle weight according to the word frequency of the contract participles and the word frequency of the risk participles;
calculating the word frequency similarity of the contract to be processed and the business attention risk information according to the contract word frequency and risk word frequency and the contract word weight and risk word weight;
and respectively counting contract participles and risk participles to determine a contract participle set and a risk participle set, and performing similarity calculation according to the contract participle set and the risk participle set to obtain the intersection set similarity of the contract to be processed and the business concern risk.
In the embodiment of the invention, the word frequency of contract participles and risk participles in a plurality of contract clauses is calculated, the word frequency of the contract participles and the word frequency of the risk participles are determined, then the contract participle weight and the risk participle weight of the contract participles and the risk participles in the contract clauses are determined, the word frequency similarity of a contract to be processed and the business attention risk information is calculated according to the contract participle word frequency, the risk participle word frequency, the contract participle weight and the risk participle weight, and the calculation modes of word frequency IDF (qi) and risk participle weight Score (Q, d) in the word frequency similarity are as follows:
wherein N is the number of all contract sentences, df i The number of sentences containing participles; q, d are two sentences whose similarity degrees are to be calculated, and k1 and b are adjustment factors, which may be set to k 1-2, b-0.75, and f i For word segmentation at q i Frequency of occurrence in document d, dl being the current sentence length, dl avg Is the average sentence length.
Further, all contract participles and risk participles are counted to determine a contract participle set and a risk participle set, co-occurrence words of the risk participles and the contract participles are calculated, and the proportion occupied by the co-occurrence words in all words is determined as the intersection set similarity degree Jaccard (A, B) of the contract to be processed and the business concern risk. Jaccard (A, B) is calculated as follows:
wherein A, B represents risk participle set and contract participle set.
Optionally, the multidimensional determination of the contract sentences suspected of paying attention to the risk based on the expanded business attention risk information in multiple contract sentences by using a preset algorithm further includes: respectively acquiring word vectors and word weights of the business concern risk information and the contract sentences according to the word vector model; and obtaining corresponding sentence vectors of the business concern risk information and the contract sentences through a weighting mode according to the business concern risk information and the word vectors and the word weights of the contract sentences, and further performing similarity calculation according to the business concern risk information and the sentence vectors of the contract sentences to obtain the semantic similarity of the contract to be processed and the business concern risk information.
In the embodiment of the invention, the word vector and the word weight of the business concern risk information and the contract sentence are respectively obtained through a word vector model, the business concern risk information and the word vector and the word weight of the contract sentence are weighted and documented to correspond to the business concern risk information and the sentence vector of the contract sentence, and then the similarity calculation is carried out on the business concern risk information and the sentence vector of the contract sentence, and the semantic similarity of the contract to be processed and the business concern risk information is calculated. The calculation method of the semantic similarity cos (a, b) is as follows:
the a and b are sentence vectors of the business concern risk item and the contract sentence respectively, and the sentence vectors can be obtained through word vectors and IDF (qi) formula weighting representation.
Optionally, the multidimensional determination of the contract sentences suspected of paying attention to the risk based on the expanded business attention risk information in multiple contract sentences by using a preset algorithm further includes:
and confirming the contract sentences suspected of concerning risks in a multi-dimension mode from the multiple contract sentences according to the word frequency similarity, the union set similarity and the semantic similarity of the contract to be processed and the business attention risk information.
Optionally, preliminarily determining the contract sentences suspected of concerning the risk respectively according to the word frequency similarity, the union set similarity and the semantic similarity of the business concerning risk information, and then combining and de-duplicating all preliminarily determined contract sentences suspected of concerning the risk to determine the contract sentences suspected of concerning the risk. Further, in order to reduce the calculation difficulty, the preliminarily confirmed contract sentences suspected of being concerned with risks can be sorted first, and the higher-ranked contract sentences can be reserved.
Exemplarily, 30 suspected risk-focusing contract sentences are preliminarily determined according to the word frequency similarity, the intersection set similarity and the semantic similarity of the business risk-focusing information, then the 30 suspected risk-focusing contract sentences determined according to the similarity are sequenced, then 90 preliminarily determined suspected risk-focusing contract sentences are merged and deduplicated, and finally the 30 deduplicated suspected risk-focusing contract sentences are reserved as the finally determined suspected risk-focusing contract sentences.
And step S104, calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk ranking model.
The risk ranking model is used for calculating the similarity between the business concern risk information and each contract sentence suspected to concern the risk. The risk ranking model may include, but is not limited to, at least one of a bi-directional recurrent neural network, a convolutional neural network model, a recurrent neural network, and a structural recurrent neural network.
Specifically, before calculating the similarity between the business concern risk information and each suspected concern risk contract sentence by using a risk ranking model, the method further includes:
acquiring sample service attention risk information, and establishing a service attention risk training set and a service attention risk testing set of the sample service attention risk information according to the sample service attention risk information. And a sample contract sentence suspected of concern risk is obtained, and a sample contract sentence training set of the suspected concern risk of the sample contract sentence suspected of concern risk and a sample contract sentence test set of the suspected concern risk of the sample contract sentence suspected of concern risk are established according to the sample contract sentence suspected of concern risk.
And inputting the sample business concern risk information in the business concern risk training set and the sample contract sentences suspected of concern risk in the suspected concern risk training set into a neural network model, training the neural network model, and generating a risk ranking model. Specifically, sample business concern risk information in a business concern risk training set and sample contract sentences suspected of concern risks in a sample contract sentence training set are input into a neural network model to generate training similarity; and determining a training error according to the generated training similarity and the expected similarity corresponding to the sample service attention risk information and the sample contract sentence suspected of attention risk, and further adjusting parameters of the neural network model according to the training error to obtain a risk ranking model.
Furthermore, similarity between the business attention risk information and each suspected attention risk contract sentence is calculated through a risk sequencing model.
And S105, sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the maximum risk from the contract sentences suspected of paying attention to the risk.
According to the contract risk identification method provided by the embodiment of the invention, a plurality of contract sentences are generated by segmenting the contract to be processed; receiving business concern risk information input by a user; expanding the service attention risk information in a preset mode; confirming contract sentences suspected of paying attention to risks in a multi-dimensional mode from a plurality of contract sentences based on the expanded business attention risk information by a preset algorithm; calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk sequencing model; and sequencing the suspected risk-paying-attention contract sentences according to the similarity so as to determine the contract sentence with the maximum risk from the suspected risk-paying-attention contract sentences. As an efficient contract risk identification matching mechanism, the embodiment of the application solves the technical problems that in the prior art, when contract risk identification is carried out, the risk identification accuracy is too low and the identification contract risk range is lower, can deal with changeable contract risk scenes, has good expansibility and generalization capability, improves the accuracy of the risk identification accuracy to the maximum extent, and improves the efficiency of the contract risk identification.
Example two
Fig. 2 is a schematic flow chart of another contract risk identification method provided in the embodiment of the present invention, and the embodiment of the present invention optimizes based on the above optional embodiments, and provides a specific optional implementation manner for calculating the similarity between the business concern risk information and each contract sentence suspected of concern risk according to a risk ranking model. Specifically, as shown in fig. 2, the method includes the following steps:
step S201, performing segmentation processing on the contract to be processed to generate a plurality of contract sentences.
And step S202, receiving business concern risk information input by a user.
And step S203, expanding the business concern risk information in a preset mode.
And S204, confirming the contract sentences suspected of paying attention to the risks in a multi-dimensional mode from the multiple contract sentences by a preset algorithm based on the expanded business attention risk information.
Step S205, inputting the business concern risk information and the suspected concern risk contract sentence into a risk ranking model to calculate the matching degree between the business concern risk information and the suspected concern risk contract sentence, so as to obtain the similarity between the business concern risk information and the suspected concern risk contract sentence.
Optionally, the similarity between the business concern risk information and the contract sentence suspected of concern risk is calculated through a risk ranking model, and then the degree of the risk is ranked according to the degree of the similarity score. The business concern risk information is used as an input a of a risk ranking model, and a contract sentence suspected of concern risk is used as an input b.
For example, the business concern risk information may be "evacuation needs to restore the original site", and the ranking of the degree of risk may be: 1. when the first party withdraws from the ground, the ground and facilities must not be damaged, so that the ground and facilities are lost, and the first party is responsible for restoring the ground to the original state, and the similarity score is 0.998;
2. after the contract expires, if the two parties do not agree on the contract, the party a needs to remove and restore the articles in the rental lot within 7 days from the expiration date of the contract, 0.985 (similarity score);
optionally, the step of calculating the similarity between the business concern risk information and the suspected concern risk contract sentence through the risk ranking model is as follows:
(1) the risk sequencing model firstly realizes the vectorization of contract sentences of business concern risk information and suspected concern risks through a word embedding layer;
(2) respectively carrying out bidirectional sequence coding on the obtained two vectors through a bidirectional cyclic neural networkFirst pass the forgetting gate weight W f And deviation b f For the current state x t And history status h t-1 Is calculated to pass
Compressing to 0-1 to obtain the forgetting probability of the history information, namely formula (1); similarly, the input probability of the current time information is obtained through the formula (2); obtaining the output probability of the current time information through a formula (5); passing candidate memory cell weight W of current time c And deviation b c For the current state x t And historical status h t-1 Is calculated to pass
Obtaining the state of the candidate memory cell at the current moment
Namely, formula (3); by probability of forgetting f t And input probability i t Synthesizing the current time candidate memory cell states
And historical memory cell status
Obtaining the state c of the memory cell at the current time t I.e., equation (4); finally through the output probability o t And tanh function versus memory cell state c at the current time t Calculating and outputting the historical state h of the current moment t Formula (6); wherein
Respectively outputting the historical state h of each time step after being coded by the bidirectional recurrent neural network t I.e. equations (8), (9);
f t ＝sigmoid(W f *[h t-1 ，x t ]+b f ) (1)
i t ＝sigmoid(W i *[h t-1 ，x t ]+b i ) (2)
o t ＝sigmoid(W o *[h t-1 ，x t ]+b o ) (5)
h t ＝o t *tan h(C t ) (6)
(3) then, the deep interaction between the two vectors is realized through a self-attention layer mechanism, and the input vector is calculated through a formula (10)
Relative to the vector at time i
Importance at time j, i.e. e ij (ii) a By passing
Is calculated to obtain
In the whole
Attention score in (1)
That is, equation (11), and similarly, from equation (12)
In the whole
Attention score in sequence coding process
In the process, contribution expressions of the two to each other are introduced;
(4) finally, splicing the interactive results to obtain m a And m b I.e., equations (13) and (14); coding the obtained product by a bidirectional cyclic neural network again to obtain
And
equations (15) and (16); obtaining p after maximum pooling and average pooling dimensionality reduction a And p b I.e. maleFormulae (17) and (18); finally pass full connection layer weight W ffn And bias b ffn Calculating to obtain similarity between the two, namely a formula (19);
similar＝softmax(W ffn *[p a ，p b ]+b ffn ) (19)
(5) and sequencing based on the similarity of the business concern risk information and the suspected contract risk sentences to obtain the contract sentence with the maximum risk, namely the corresponding contract risk.
And S206, sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the maximum risk from the contract sentences suspected of paying attention to the risk.
According to the contract risk identification method provided by the embodiment of the invention, a to-be-processed contract is divided to generate a plurality of contract sentences; receiving business concern risk information input by a user; expanding the service attention risk information in a preset mode; confirming the suspected risk-concerning contract sentences from the plurality of contract sentences in a multi-dimension mode based on the expanded business risk-concerning information; calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk sequencing model; and sequencing the suspected risk-paying-attention contract sentences according to the similarity so as to determine the contract sentence with the maximum risk from the suspected risk-paying-attention contract sentences. As an efficient contract risk identification matching mechanism, the method solves the technical problems that in the prior art, when contract risk identification is carried out, risk identification accuracy is too low and contract risk range is low, changeable contract risk scenes can be dealt with, good expansibility and generalization capability are achieved, accuracy of risk identification accuracy is improved to the maximum degree, and requirements on newly added training data are low while efficiency of contract risk identification is improved.
EXAMPLE III
Fig. 3 is a schematic diagram of a contract risk identification apparatus according to a fourth embodiment of the present invention, as shown in fig. 3, the apparatus includes: a contract processing module 310, a risk expansion module 320, a suspected risk confirmation module 330, a similarity calculation module 340, and a risk confirmation module 350, wherein:
a contract processing module 310, configured to perform segmentation processing on the to-be-processed contract to generate a plurality of contract sentences;
a risk expansion module 320, configured to receive business concern risk information input by a user; expanding the service attention risk information in a preset mode;
a suspected risk confirmation module 330, configured to confirm a contract sentence suspected of concern risk in multiple dimensions from multiple contract sentences by using a preset algorithm based on the expanded business concern risk information;
the similarity calculation module 340 is configured to calculate a similarity between the business concern risk information and each suspected concern contract sentence by using a risk ranking model;
and a risk confirming module 350, configured to sort the contract sentences suspected of paying attention to the risk according to the similarity, so as to determine a contract sentence with the highest risk from the contract sentences suspected of paying attention to the risk.
The contract risk identification device provided by the embodiment of the invention generates a plurality of contract sentences by dividing the contract to be processed; receiving business concern risk information input by a user; expanding the service attention risk information in a preset mode; confirming contract sentences suspected of paying attention to risks in a multi-dimensional mode from a plurality of contract sentences based on the expanded business attention risk information by a preset algorithm; calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk sequencing model; and sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the highest risk from the contract sentences suspected of paying attention to the risk. As an efficient contract risk identification matching mechanism, the embodiment of the application solves the technical problems that in the prior art, when contract risk identification is carried out, the risk identification accuracy is too low and the identification contract risk range is lower, can deal with changeable contract risk scenes, has good expansibility and generalization capability, improves the accuracy of the risk identification accuracy to the maximum extent, and improves the efficiency of the contract risk identification.
Optionally, the contract processing module 310 is specifically configured to: sentence segmentation is carried out on the contract to be processed according to the sentence segmentation rule, and a contract sentence set is generated;
performing word segmentation on the contract clauses according to a word segmentation rule to generate contract clauses;
and obtaining a dictionary to train word vectors to generate a word vector model.
Optionally, the risk expansion module 320 is specifically configured to: performing word segmentation on the business concern risk information according to a word segmentation rule to generate risk words;
calculating the keyword score of each risk participle according to the word frequency and the inverse document frequency of each risk participle in the risk participles; sorting the keyword scores of all risk participles, and extracting a plurality of risk keywords of the business concern risk information;
and inputting a plurality of risk keywords of the business concern risk information into a word vector model to obtain the most similar synonyms corresponding to the risk keywords, further replacing all the risk keywords with the synonyms, and expanding the business concern risk information.
Optionally, the risk expansion module 320 is further specifically configured to:
inquiring a historical service risk database according to the service attention risk information, and determining the similarity between the service attention risk information and the stored historical service risk;
sequencing similarity of the business concern risk information and the stored historical business risk, and determining the historical business risk similar to the business concern risk information;
and expanding the business concern risk information according to the similar historical business risk.
Optionally, the suspected risk confirmation module 330 is specifically configured to: respectively calculating the word frequency of the contract participles and the risk participles in a plurality of contract clauses to obtain the word frequency of the contract participles and the word frequency of the risk participles, and further respectively determining the contract participle weight and the risk participle weight according to the word frequency of the contract participles and the word frequency of the risk participles;
calculating the word frequency similarity of the contract to be processed and the business attention risk information according to the contract word frequency and risk word frequency and the contract word weight and risk word weight;
and respectively counting contract participles and risk participles to determine a contract participle set and a risk participle set, and performing similarity calculation according to the contract participle set and the risk participle set to obtain the intersection set similarity of the contract to be processed and the business concern risk.
Further, the suspected risk confirmation module 330 is further specifically configured to: respectively acquiring word vectors and word weights of the business concern risk information and the contract sentences according to the word vector model;
and obtaining corresponding sentence vectors of the business concern risk information and the contract sentences through a weighting mode according to the business concern risk information and the word vectors and the word weights of the contract sentences, and further performing similarity calculation according to the business concern risk information and the sentence vectors of the contract sentences to obtain semantic similarity of the contract to be processed and the business concern risk information.
Further, the suspected risk confirmation module 330 is further specifically configured to: and confirming the contract sentences suspected of concerning risks in a multi-dimension mode from the multiple contract sentences according to the word frequency similarity, the union set similarity and the semantic similarity of the contract to be processed and the business attention risk information.
Optionally, the similarity calculation module 340 is specifically configured to:
and inputting the business concern risk information and the suspected concern risk contract sentences into a risk sorting model respectively to calculate the matching degree of the business concern risk information and the suspected concern risk contract sentences, so as to obtain the similarity of the business concern risk information and the suspected concern risk contract sentences.
Since the contract risk identification apparatus described above is an apparatus capable of executing the contract risk identification method in the embodiment of the present invention, based on the contract risk identification method described in the embodiment of the present invention, a person skilled in the art can understand the specific implementation of the contract risk identification apparatus of the embodiment and various variations thereof, and therefore, how the contract risk identification apparatus implements the contract risk identification method in the embodiment of the present invention is not described in detail here. The device used by those skilled in the art to implement the contract risk identification method in the embodiment of the present invention is within the scope of the protection of the present application.
Example four
FIG. 4 shows a schematic block diagram of a computer device 10 that may be used to implement an embodiment of the invention. Computer devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The computer device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the computer device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM)12, a Random Access Memory (RAM)13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM)12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the computer device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.
A number of components in the computer device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the computer device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. Processor 11 performs the various methods and processes described above, such as the contract risk identification method.
In some embodiments, the contract risk identification method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the computer device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the contract risk identification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the contract risk identification method in any other suitable manner (e.g., by way of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the Internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
EXAMPLE five
Embodiment 5 of the present invention further provides a computer storage medium storing a computer program, which when executed by a computer processor is configured to execute the contract risk identification method according to any one of the above embodiments of the present invention: dividing the contract to be processed to generate a plurality of contract sentences; receiving business concern risk information input by a user; expanding the business concern risk information in a preset mode; confirming the suspected risk-concerning contract sentences from the plurality of contract sentences in a multi-dimension mode based on the expanded business risk-concerning information; calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk sequencing model; and sequencing the suspected risk-paying-attention contract sentences according to the similarity so as to determine the contract sentence with the maximum risk from the suspected risk-paying-attention contract sentences.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM, or flash Memory), an optical fiber, a portable compact disc Read Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. A contract risk identification method, comprising:
dividing the contract to be processed to generate a plurality of contract sentences;
receiving business concern risk information input by a user;
expanding the service attention risk information in a preset mode;
confirming contract sentences suspected of paying attention to risks in a multi-dimensional mode from a plurality of contract sentences based on the expanded business attention risk information by a preset algorithm;
calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk sequencing model;
and sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the highest risk from the contract sentences suspected of paying attention to the risk.
2. The method of claim 1, wherein the processing the contract for processing for segmentation to generate a plurality of contract sentences comprises:
sentence segmentation is carried out on the contract to be processed according to the sentence segmentation rule, and a contract sentence set is generated;
performing word segmentation on the contract clauses according to a word segmentation rule to generate contract clauses;
and obtaining a dictionary to train word vectors to generate a word vector model.
3. The method according to claim 1, wherein the expanding the business concern risk information in a preset mode comprises:
performing word segmentation on the business concern risk information according to a word segmentation rule to generate risk words;
calculating the keyword score of each risk participle according to the word frequency and the inverse document frequency of each risk participle in the risk participles; sorting the keyword scores of all risk participles, and extracting a plurality of risk keywords of the business concern risk information;
and inputting a plurality of risk keywords of the business concern risk information into a word vector model to obtain the most similar synonyms corresponding to the risk keywords, further replacing all the risk keywords with the synonyms, and expanding the business concern risk information.
4. The method according to claim 1, wherein the expanding the business concern risk information in a preset mode further comprises:
inquiring a historical service risk database according to the service attention risk information, and determining the similarity between the service attention risk information and the stored historical service risk;
sequencing similarity of the business concern risk information and the stored historical business risk, and determining the historical business risk similar to the business concern risk information;
and expanding the business concern risk information according to the similar historical business risk.
5. The method of claim 2, wherein the step of identifying the contract sentences suspected of being concerned with risks in a multi-dimensional manner from the plurality of contract sentences based on the expanded business concern risk information by using a preset algorithm comprises:
respectively calculating the word frequency of the contract participles and the risk participles in a plurality of contract clauses to obtain the word frequency of the contract participles and the word frequency of the risk participles, and further respectively determining the contract participle weight and the risk participle weight according to the word frequency of the contract participles and the word frequency of the risk participles;
calculating the word frequency similarity of the contract to be processed and the business attention risk information according to the contract word frequency and risk word frequency and the contract word weight and risk word weight;
and respectively counting contract participles and risk participles to determine a contract participle set and a risk participle set, and performing similarity calculation according to the contract participle set and the risk participle set to obtain the intersection set similarity of the contract to be processed and the business concern risk.
6. The method of claim 2, wherein the multidimensional confirmation of the contract sentences suspected of being concerned with risks is performed from a plurality of contract sentences based on the expanded business concern risk information by a preset algorithm, and further comprising:
respectively acquiring word vectors and word weights of the business concern risk information and the contract sentences according to the word vector model;
and obtaining corresponding sentence vectors of the business concern risk information and the contract sentences through a weighting mode according to the business concern risk information and the word vectors and the word weights of the contract sentences, and further performing similarity calculation according to the business concern risk information and the sentence vectors of the contract sentences to obtain the semantic similarity of the contract to be processed and the business concern risk information.
7. The method of claim 1, wherein the multidimensional confirmation of the contract sentences suspected of being concerned with risks is performed from a plurality of contract sentences based on the expanded business concern risk information by a preset algorithm, and further comprising:
and confirming the contract sentences suspected of concerning risks in a multi-dimension mode from the multiple contract sentences according to the word frequency similarity, the union set similarity and the semantic similarity of the contract to be processed and the business attention risk information.
8. The method of claim 1, wherein the using a risk ranking model to calculate similarity between the business concern risk information and each suspected concern contract sentence using a risk ranking model comprises: and inputting the business concern risk information and the suspected concern risk contract sentences into a risk sorting model respectively to calculate the matching degree of the business concern risk information and the suspected concern risk contract sentences, so as to obtain the similarity of the business concern risk information and the suspected concern risk contract sentences.
9. A contract risk identification apparatus, comprising:
the contract processing module is used for carrying out segmentation processing on the contract to be processed so as to generate a plurality of contract sentences;
the risk expansion module is used for receiving business concern risk information input by a user; expanding the business concern risk information in a preset mode;
the suspected risk confirmation module is used for confirming the contract sentences suspected of concerning the risk in a multi-dimensional mode from the plurality of contract sentences according to the expanded business attention risk information by a preset algorithm;
the similarity calculation module is used for calculating the similarity between the business concern risk information and each suspected concern contract sentence by using a risk ranking model;
and the risk confirmation module is used for sequencing the contract sentences suspected of paying attention to the risk according to the similarity so as to determine the contract sentence with the maximum risk from the contract sentences suspected of paying attention to the risk.
10. A computer device, characterized in that the computer device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the contract risk identification method of any one of claims 1-8.
11. A computer storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing a processor to implement, when executed, the contract risk identification method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210602862.6A CN114943217A (en) | 2022-05-30 | 2022-05-30 | Contract risk identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210602862.6A CN114943217A (en) | 2022-05-30 | 2022-05-30 | Contract risk identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114943217A true CN114943217A (en) | 2022-08-26 |
Family
ID=82909825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210602862.6A Pending CN114943217A (en) | 2022-05-30 | 2022-05-30 | Contract risk identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114943217A (en) |
-
2022
- 2022-05-30 CN CN202210602862.6A patent/CN114943217A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112506864A (en) | File retrieval method and device, electronic equipment and readable storage medium | |
| CN114037059A (en) | Pre-training model, model generation method, data processing method and data processing device | |
| CN116467461A (en) | Data processing method, device, equipment and medium applied to power distribution network | |
| CN115470313A (en) | Information retrieval and model training method, device, equipment and storage medium | |
| CN114647727A (en) | Model training method, device and equipment applied to entity information recognition | |
| CN113392920B (en) | Method, apparatus, device, medium, and program product for generating cheating prediction model | |
| CN112699237B (en) | Label determination method, device and storage medium | |
| CN114625834A (en) | Enterprise industry information determination method and device and electronic equipment | |
| CN112906368B (en) | Industry text increment method, related device and computer program product | |
| CN117971698A (en) | Test case generation method and device, electronic equipment and storage medium | |
| CN114048315A (en) | Method and device for determining document tag, electronic equipment and storage medium | |
| CN117745482A (en) | Method, device, equipment and medium for determining contract clause | |
| CN113590774A (en) | Event query method, device and storage medium | |
| CN115248890A (en) | User interest portrait generation method and device, electronic equipment and storage medium | |
| CN112925912A (en) | Text processing method, and synonymous text recall method and device | |
| CN112560425A (en) | Template generation method and device, electronic equipment and storage medium | |
| CN114036921A (en) | Policy information matching method and device | |
| CN117271884A (en) | Method, device, electronic equipment and storage medium for determining recommended content | |
| CN116881432A (en) | Text pushing method, text pushing device, electronic equipment and storage medium | |
| CN114741433B (en) | Community mining method, device, equipment and storage medium | |
| US11580309B1 (en) | Predictive time series data object machine learning system | |
| CN115618875A (en) | Public opinion scoring method, system and storage medium based on named entity recognition | |
| CN114841172A (en) | Knowledge distillation method, apparatus and program product for text matching double tower model | |
| CN114138976A (en) | Data processing and model training method and device, electronic equipment and storage medium | |
| CN115292506A (en) | Knowledge graph ontology construction method and device applied to office field |
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 |