CN112184498A - Contract scoring method and device, computer equipment and storage medium - Google Patents
Contract scoring method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112184498A CN112184498A CN202011055598.6A CN202011055598A CN112184498A CN 112184498 A CN112184498 A CN 112184498A CN 202011055598 A CN202011055598 A CN 202011055598A CN 112184498 A CN112184498 A CN 112184498A
- Authority
- CN
- China
- Prior art keywords
- contract
- target
- model
- scoring
- type
- 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
- 238000013077 scoring method Methods 0.000 title abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims description 74
- 238000003062 neural network model Methods 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000009193 crawling Effects 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 239000002131 composite material Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Abstract
The application relates to the technical field of artificial intelligence, and provides a contract scoring method, a contract scoring device, computer equipment and a storage medium, wherein a target contract to be scored is obtained, and the type of the target contract is obtained; according to the type of the target contract, matching a target model parameter set corresponding to the type in a database; correspondingly updating the model parameters in the contract scoring model according to the target model parameter set to obtain a target contract scoring model; extracting text features of the target contract; inputting the text features of the target contract into the target contract scoring model, and outputting the score of the target contract. According to the method and the device, the target contract scoring model with the optimal model parameters is adapted according to the type of the contract, so that the score output by the target contract scoring model is more accurate, and the scoring efficiency is high.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a contract scoring method, apparatus, computer device, and storage medium.
Background
In traditional contract scoring, manual scoring and computer fuzzy scoring are typically used:
and (3) manual appraising: the method has the advantages that the accuracy is high when the administrator scores manually, but the workload of the administrator is increased for a long time, the efficiency problem is increasingly obvious, and the characteristic of high efficiency of a computer is not utilized.
Computer fuzzy scoring: and selecting important key information from the elements according to the scores, and scoring the synthetic quality by using a fuzzy calculation mode. Although the efficiency is guaranteed, the common computer is not trained, so that the common computer is difficult to accurately evaluate all aspects of the same, and the scoring accuracy is low.
Disclosure of Invention
The main purpose of the present application is to provide a method, an apparatus, a computer device and a storage medium for contract scoring, aiming to overcome the current defects of low efficiency and inaccurate scoring for the contract scoring.
To achieve the above object, the present application provides a contract scoring method, comprising the steps of:
acquiring a target contract to be scored, and acquiring the type of the target contract;
according to the type of the target contract, matching a target model parameter set corresponding to the type in a database; the database is pre-stored with the corresponding relation between the contract type and the model parameter set, wherein the model parameter set is the collection of each model parameter in the contract scoring model;
correspondingly updating the model parameters in the contract scoring model according to the target model parameter set to obtain a target contract scoring model;
extracting text features of the target contract;
inputting the text features of the target contract into the target contract scoring model, and outputting the score of the target contract.
Further, the step of obtaining the target contract to be scored and obtaining the type of the target contract comprises:
acquiring contract samples, and classifying the contract samples according to the types of the contract samples to obtain a plurality of types of contract training samples; the contract training sample comprises a contract training text and a corresponding standard score;
extracting text features of the contract training texts included in the same type of contract training samples;
inputting the text features into a neural network model for training until the difference value between the score output by the neural network model and the standard score corresponding to the contract training text is smaller than a preset value, and finishing the training of the neural network model to obtain a corresponding contract score model under the type;
constructing model parameters of the contract scoring model corresponding to the type as a model parameter set;
and establishing a corresponding relation between the type of the contract training sample and the model parameter set, and storing the corresponding relation in the database.
Further, the step of obtaining a contract sample includes:
performing incremental crawling on a contract evaluation text in the Internet through a preset crawler script;
judging whether the contract evaluation text comprises a corresponding standard score or not; if yes, using the contract evaluation text as the contract sample; and if not, deleting the contract evaluation text.
Further, the text features comprise the text overall features of the target contract and the similarity of the target contract and a standard contract;
the step of extracting the text features of the target contract comprises the following steps:
acquiring a corresponding standard contract according to the type of the target contract;
comparing the format of the target contract with that of the standard contract, and extracting the integral text features of the target contract;
carrying out similarity calculation on each single sentence in the target contract and the corresponding single sentence in the standard contract;
and calculating the similarity between the target contract and the standard contract according to the similarity corresponding to each single sentence.
Further, the scores of the target contract comprise corresponding scores in a plurality of dimensions;
after the step of inputting the text features of the target contract into the target contract scoring model and outputting the score of the target contract, the method comprises the following steps:
creating a blank layer;
constructing a circular area in the blank map layer, drawing a plurality of dividing lines pointing to arcs by taking the circle center of the circular area as a starting point, and equally dividing the circular area into a plurality of fan-shaped areas; wherein the number of the segmentation lines is the same as the number of the scored dimensions;
marking scales of scores on the dividing lines respectively, and marking the scores corresponding to the multiple dimensions on the dividing lines respectively according to the scales to obtain marking points on each dividing line; wherein, the score corresponding to one dimension is only marked on one segmentation line;
and connecting the mark points on the adjacent dividing lines, and deleting all the dividing lines to obtain the radar map corresponding to the score of the target contract.
Further, the step of obtaining the target contract to be scored and obtaining the type of the target contract comprises:
receiving instruction content input by a user at a pre-configured desktop application program;
prompting the user whether to save the instruction content;
if a storage command sent by the user is received, storing the instruction content into an instruction list;
prompting the user whether to execute the instruction content;
and if a confirmation execution command sent by the user is received, executing the instruction content to execute the step of acquiring the target contract to be scored and acquiring the type of the target contract.
The application also provides a contract scoring device, including:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring a target contract to be scored and acquiring the type of the target contract;
the matching unit is used for matching a target model parameter set corresponding to the type in a database according to the type of the target contract; the database is pre-stored with the corresponding relation between the contract type and the model parameter set, wherein the model parameter set is the collection of each model parameter in the contract scoring model;
the updating unit is used for correspondingly updating the model parameters in the contract scoring model according to the target model parameter set to obtain a target contract scoring model;
a first extraction unit, configured to extract a text feature of the target contract;
and the scoring unit is used for inputting the text characteristics of the target contract into the target contract scoring model and outputting the score of the target contract.
Further, the apparatus further comprises:
the second acquisition unit is used for acquiring contract samples and classifying the contract samples according to the types of the contract samples to obtain a plurality of types of contract training samples; the contract training sample comprises a contract training text and a corresponding standard score;
the second extraction unit is used for extracting the text features of the contract training texts included in the same type of contract training samples;
the training unit is used for inputting the text features into a neural network model for training until the difference value between the score output by the neural network model and the standard score corresponding to the contract training text is smaller than a preset value, completing the training of the neural network model and obtaining a corresponding contract score model under the type;
the composition unit is used for composing the model parameters of the contract scoring model corresponding to the type into a model parameter set;
and the storage unit is used for establishing a corresponding relation between the type of the contract training sample and the model parameter set and storing the corresponding relation in the database.
The present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of any of the above.
The contract scoring method, the contract scoring device, the computer equipment and the storage medium acquire a target contract to be scored and acquire the type of the target contract; according to the type of the target contract, matching a target model parameter set corresponding to the type in a database; correspondingly updating the model parameters in the contract scoring model according to the target model parameter set to obtain a target contract scoring model; extracting text features of the target contract; inputting the text features of the target contract into the target contract scoring model, and outputting the score of the target contract. According to the method and the device, the target contract scoring model with the optimal model parameters is adapted according to the type of the contract, so that the score output by the target contract scoring model is more accurate, and the scoring efficiency is high.
Drawings
FIG. 1 is a schematic diagram illustrating the method steps for contract scoring in one embodiment of the present application;
FIG. 2 is a block diagram of an apparatus for contract scoring according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, in an embodiment of the present application, a method for contract scoring is provided, including the steps of:
step S1, obtaining a target contract to be scored and obtaining the type of the target contract;
step S2, according to the type of the target contract, matching a target model parameter set corresponding to the type in a database; the database is pre-stored with the corresponding relation between the contract type and the model parameter set, wherein the model parameter set is the collection of each model parameter in the contract scoring model;
step S3, according to the target model parameter set, correspondingly updating the model parameters in the contract scoring model to obtain a target contract scoring model;
step S4, extracting text features of the target contract;
and step S5, inputting the text features of the target contract into the target contract scoring model, and outputting the score of the target contract.
In the embodiment, the method is applied to the technical field of smart cities to promote the construction of the smart cities. The method is particularly used for scoring contracts, and the contracts comprise various types of contracts such as insurance contracts and labor contracts.
As described in the above step S1, the target contract to be scored is typically a new contract document made by the business personnel, and the contract made by the business personnel needs to be scored in order to supervise the business capability of the business personnel. Due to different business fields of business personnel, the types of contracts made corresponding to the business personnel are different. In the present embodiment, the model parameters of the contract scoring model for subsequent contract scoring are different for different types of contracts. Therefore, the type of the target contract needs to be acquired.
As described in step S2, for each type of contract, the corresponding neural network model is trained in advance to obtain the optimal model parameters of the neural network model for that type, and the optimal model parameters constitute the model parameter set and are stored in the database. When the contracts are evaluated, the target model parameter sets corresponding to the types can be matched in the database only according to the types of the target contracts. The model parameters included in the target model parameter set are the optimal model parameters of a contract scoring model for scoring the target contract.
As stated in step S3, correspondingly updating the model parameters in the contract scoring model according to the target model parameter set, so as to obtain a target contract scoring model; the model parameters in the target model parameter set are the current optimal model parameters, and the optimal model parameters are updated to the contract scoring model to obtain the target contract scoring model, so that the obtained target contract scoring model is in the optimal scoring state, and the accuracy of model output scoring is improved.
As described in the above steps S4-S5, the text features of the target contract are extracted and input into the scoring model of the target contract, so that the score of the target contract can be output. The target contract scoring model is the best scoring model corresponding to the current type of target contract, and has high accuracy and high confidence when the scoring is output.
In the embodiment, the target contract scoring model obtained by training a large amount of training data is used for scoring the target contract, so that the scoring efficiency is high, the accuracy of output scoring is higher through data training, and the defects of low efficiency and inaccurate scoring in the conventional process of scoring the same contract are overcome.
In an embodiment, the step S1 of obtaining the target contract to be scored and obtaining the type of the target contract is preceded by:
step S11, acquiring contract samples, and classifying the contract samples according to the types of the contract samples to obtain contract training samples of multiple types; the contract training sample comprises a contract training text and a corresponding standard score;
step S12, extracting the text features of the contract training texts included in the same type of contract training samples;
step S13, inputting the text features into a neural network model for training until the difference between the score output by the neural network model and the standard score corresponding to the contract training text is smaller than a preset value, completing the training of the neural network model, and obtaining a corresponding contract score model under the type;
step S14, the model parameters of the contract scoring model corresponding to the type are used as a model parameter set;
and step S15, establishing a corresponding relation between the type of the contract training sample and the model parameter set, and storing the corresponding relation in the database.
In this embodiment, when training the contract scoring model, training is performed based on a large number of contract training samples to improve the accuracy of the output score of the contract scoring model.
During training, in order to obtain the optimal model parameters of the contract scoring model corresponding to each contract type, when constructing a contract training sample, classifying the contract sample according to the type of the contract sample to obtain a plurality of types of contract training samples. Further, training is carried out independently for each type of contract training sample, and text features of contract training texts included in the same type of contract training sample are extracted; inputting the text features into a neural network model for training until the difference value between the score output by the neural network model and the standard score corresponding to the contract training text is smaller than a preset value, completing the training of the neural network model, obtaining the optimal model parameter of the contract scoring model corresponding to the type, forming the optimal model parameter into the model parameter set, establishing the corresponding relation between the type of the contract training sample and the model parameter set, storing the model parameter set in the database, and facilitating the direct calling of the model parameter set from the database when subsequently scoring the contract so as to update the contract scoring model to the optimal state.
In this embodiment, the step S11 of obtaining the contract sample includes:
performing incremental crawling on a contract evaluation text in the Internet through a preset crawler script; programming an incremental crawler script for automatically performing incremental crawling on Internet related contract evaluation text data every day by using a programming language (Java or Python), and utilizing the incremental crawler script
Judging whether the contract evaluation text comprises a corresponding standard score or not; if yes, using the contract evaluation text as the contract sample; and if not, deleting the contract evaluation text.
In one embodiment, the text features comprise the text overall features of the target contract and the similarity of the target contract and a standard contract;
the step S4 of extracting the text feature of the target contract includes:
a. acquiring a corresponding standard contract according to the type of the target contract; in the present embodiment, for each type of target contract, there is a corresponding standard contract.
b. Comparing the format of the target contract with that of the standard contract, and extracting the integral text features of the target contract; the text integral characteristic refers to the similarity of the formats of the target contract and the standard contract. Such as paragraph ordering, font, etc. If the overall format difference between the target contract and the standard contract is large, the corresponding similarity is low.
c. Carrying out similarity calculation on each single sentence in the target contract and the corresponding single sentence in the standard contract; specifically, each single sentence in the target contract is converted into a first sentence vector, the corresponding single sentence in the standard contract is converted into a second sentence vector, and the distance between the first sentence vector and the second sentence vector is calculated to obtain the similarity between each single sentence in the target contract and the corresponding single sentence in the standard contract.
d. And calculating the similarity between the target contract and the standard contract according to the similarity corresponding to each single sentence. In this embodiment, the similarity corresponding to the above-mentioned single sentence is subjected to aggregation operation or weighted calculation, so as to obtain the similarity between the target contract and the standard contract.
In one embodiment, the scores for the target contract comprise corresponding scores in a plurality of dimensions;
after the step S5 of inputting the text features of the target contract into the target contract scoring model and outputting the score of the target contract, the method includes:
step S6, creating a blank layer;
step S7, constructing a circular area in the blank map layer, drawing a plurality of dividing lines pointing to arcs by taking the circle center of the circular area as a starting point, and equally dividing the circular area into a plurality of fan-shaped areas; wherein the number of the segmentation lines is the same as the number of the scored dimensions;
step S8, marking the scale of the score on the dividing lines respectively, and marking the scores corresponding to the multiple dimensions on the dividing lines respectively according to the scale to obtain the mark points on each dividing line; wherein, the score corresponding to one dimension is only marked on one segmentation line;
and step S9, connecting the mark points on the adjacent dividing lines, and deleting all the dividing lines to obtain the radar map corresponding to the score of the target contract.
In this embodiment, the scores of the target contract include scores corresponding to six dimensions, which are a composite score, a procedure compliance, a term compliance, a composite risk, a performance status, and a risk detail item. The scores output by the target contract scoring model are scores of six dimensions, and in order to display the scores of the six dimensions, the scores of the six dimensions are displayed in a radar map mode according to the mode, so that the scores are visually displayed, and the visual display effect of the same real situation is improved.
In an embodiment, the step S1 of obtaining the target contract to be scored and obtaining the type of the target contract is preceded by:
receiving instruction content input by a user at a pre-configured desktop application program;
prompting the user whether to save the instruction content;
if a storage command sent by the user is received, storing the instruction content into an instruction list;
prompting the user whether to execute the instruction content;
and if a confirmation execution command sent by the user is received, executing the instruction content to execute the step of acquiring the target contract to be scored and acquiring the type of the target contract.
In this embodiment, a desktop application is pre-programmed, and the application can perform browser automation operation services, and after a user inputs instruction content, the browser performs corresponding operations such as automatic clicking, automatic inputting, automatic opening, and automatic closing. For example, a user inputs login EOA in an input field, inputs contract attachment names to be searched and downloaded, specifies a storage path, then clicks to confirm, the browser is automatically opened and corresponding whole-course operation is carried out, the user can leave the keyboard and the mouse by both hands after clicking to confirm, the settings can be stored afterwards, input instruction content is reduced, and working efficiency is improved.
The desktop application program can also set a computer network IP address of an administrator, periodically and periodically send a mail circulation prompt to the administrator, the prompt content is filed, uploaded and recorded for the contract, and meanwhile, related filling content such as contract name and path is set in the mail content, and then automatic uploading is performed, which is not described herein again.
Referring to fig. 2, an embodiment of the present application further provides a contract scoring apparatus, including:
the first acquisition unit 10 is used for acquiring a target contract to be scored and acquiring the type of the target contract;
a matching unit 20, configured to match, according to the type of the target contract, a target model parameter set corresponding to the type in a database; the database is pre-stored with the corresponding relation between the contract type and the model parameter set, wherein the model parameter set is the collection of each model parameter in the contract scoring model;
the updating unit 30 is configured to correspondingly update the model parameters in the contract scoring model according to the target model parameter set, so as to obtain a target contract scoring model;
a first extraction unit 40, configured to extract a text feature of the target contract;
and the scoring unit 50 is used for inputting the text characteristics of the target contract into the target contract scoring model and outputting the score of the target contract.
In one embodiment, the apparatus further comprises:
the second acquisition unit is used for acquiring contract samples and classifying the contract samples according to the types of the contract samples to obtain a plurality of types of contract training samples; the contract training sample comprises a contract training text and a corresponding standard score;
the second extraction unit is used for extracting the text features of the contract training texts included in the same type of contract training samples;
the training unit is used for inputting the text features into a neural network model for training until the difference value between the score output by the neural network model and the standard score corresponding to the contract training text is smaller than a preset value, completing the training of the neural network model and obtaining a corresponding contract score model under the type;
the composition unit is used for composing the model parameters of the contract scoring model corresponding to the type into a model parameter set;
and the storage unit is used for establishing a corresponding relation between the type of the contract training sample and the model parameter set and storing the corresponding relation in the database.
In an embodiment, the second obtaining unit is specifically configured to:
performing incremental crawling on a contract evaluation text in the Internet through a preset crawler script;
judging whether the contract evaluation text comprises a corresponding standard score or not; if yes, using the contract evaluation text as the contract sample; and if not, deleting the contract evaluation text.
In one embodiment, the text features comprise the text overall features of the target contract and the similarity of the target contract and a standard contract;
the first extraction unit 40 is configured to:
acquiring a corresponding standard contract according to the type of the target contract;
comparing the format of the target contract with that of the standard contract, and extracting the integral text features of the target contract;
carrying out similarity calculation on each single sentence in the target contract and the corresponding single sentence in the standard contract;
and calculating the similarity between the target contract and the standard contract according to the similarity corresponding to each single sentence.
In one embodiment, the scores for the target contract comprise corresponding scores in a plurality of dimensions;
the device, still include:
the creating unit is used for creating a blank layer;
the construction unit is used for constructing a circular area in the blank map layer, drawing a plurality of dividing lines pointing to arcs by taking the circle center of the circular area as a starting point, and equally dividing the circular area into a plurality of fan-shaped areas; wherein the number of the segmentation lines is the same as the number of the scored dimensions;
the marking unit is used for marking the scales of the scores on the dividing lines respectively and marking the scores corresponding to the multiple dimensions on the dividing lines respectively according to the scales to obtain mark points on each dividing line; wherein, the score corresponding to one dimension is only marked on one segmentation line;
and the connecting unit is used for connecting the mark points on the adjacent dividing lines and deleting all the dividing lines to obtain the radar map corresponding to the score of the target contract.
In one embodiment, the apparatus further comprises:
the receiving unit is used for receiving instruction contents input by a user in a pre-configured desktop application program;
the first prompting unit is used for prompting the user whether to store the instruction content;
the storage unit is used for storing the instruction content into an instruction list if a storage command sent by the user is received;
the second prompting unit is used for prompting whether the user executes the instruction content or not;
and the execution unit is used for executing the instruction content if receiving a confirmation execution command sent by the user, so as to acquire a target contract to be scored through the first acquisition unit 10 and acquire the type of the target contract.
In this embodiment, please refer to the method described in the above embodiment for the specific implementation of each unit in the above apparatus embodiment, which is not described herein again.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing contract data and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a method of contract scoring.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method of contract scoring. It is to be understood that the computer-readable storage medium in the present embodiment may be a volatile-readable storage medium or a non-volatile-readable storage medium.
In summary, for the contract scoring method, apparatus, computer device and storage medium provided in the embodiments of the present application, a target contract to be scored is obtained, and a type of the target contract is obtained; according to the type of the target contract, matching a target model parameter set corresponding to the type in a database; correspondingly updating the model parameters in the contract scoring model according to the target model parameter set to obtain a target contract scoring model; extracting text features of the target contract; inputting the text features of the target contract into the target contract scoring model, and outputting the score of the target contract. According to the method and the device, the target contract scoring model with the optimal model parameters is adapted according to the type of the contract, so that the score output by the target contract scoring model is more accurate, and the scoring efficiency is high.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only for the preferred embodiment of the present application and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.
Claims (10)
1. A method of contract scoring, comprising the steps of:
acquiring a target contract to be scored, and acquiring the type of the target contract;
according to the type of the target contract, matching a target model parameter set corresponding to the type in a database; the database is pre-stored with the corresponding relation between the contract type and the model parameter set, wherein the model parameter set is the collection of each model parameter in the contract scoring model;
correspondingly updating the model parameters in the contract scoring model according to the target model parameter set to obtain a target contract scoring model;
extracting text features of the target contract;
inputting the text features of the target contract into the target contract scoring model, and outputting the score of the target contract.
2. The method of contract scoring according to claim 1, wherein said step of obtaining a target contract to be scored and obtaining a type of the target contract is preceded by the steps of:
acquiring contract samples, and classifying the contract samples according to the types of the contract samples to obtain a plurality of types of contract training samples; the contract training sample comprises a contract training text and a corresponding standard score;
extracting text features of the contract training texts included in the same type of contract training samples;
inputting the text features into a neural network model for training until the difference value between the score output by the neural network model and the standard score corresponding to the contract training text is smaller than a preset value, and finishing the training of the neural network model to obtain a corresponding contract score model under the type;
constructing model parameters of the contract scoring model corresponding to the type as a model parameter set;
and establishing a corresponding relation between the type of the contract training sample and the model parameter set, and storing the corresponding relation in the database.
3. The method of contract scoring according to claim 2, wherein said step of obtaining a sample of contracts comprises:
performing incremental crawling on a contract evaluation text in the Internet through a preset crawler script;
judging whether the contract evaluation text comprises a corresponding standard score or not; if yes, using the contract evaluation text as the contract sample; and if not, deleting the contract evaluation text.
4. The method of contract scoring according to claim 1, wherein said textual features include textual overall features of said target contract and a similarity of said target contract to a standard contract;
the step of extracting the text features of the target contract comprises the following steps:
acquiring a corresponding standard contract according to the type of the target contract;
comparing the format of the target contract with that of the standard contract, and extracting the integral text features of the target contract;
carrying out similarity calculation on each single sentence in the target contract and the corresponding single sentence in the standard contract;
and calculating the similarity between the target contract and the standard contract according to the similarity corresponding to each single sentence.
5. The method of contract scoring according to claim 1, wherein the score for the target contract comprises scores corresponding in a plurality of dimensions;
after the step of inputting the text features of the target contract into the target contract scoring model and outputting the score of the target contract, the method comprises the following steps:
creating a blank layer;
constructing a circular area in the blank map layer, drawing a plurality of dividing lines pointing to arcs by taking the circle center of the circular area as a starting point, and equally dividing the circular area into a plurality of fan-shaped areas; wherein the number of the segmentation lines is the same as the number of the scored dimensions;
marking scales of scores on the dividing lines respectively, and marking the scores corresponding to the multiple dimensions on the dividing lines respectively according to the scales to obtain marking points on each dividing line; wherein, the score corresponding to one dimension is only marked on one segmentation line;
and connecting the mark points on the adjacent dividing lines, and deleting all the dividing lines to obtain the radar map corresponding to the score of the target contract.
6. The method of contract scoring according to claim 1, wherein said step of obtaining a target contract to be scored and obtaining a type of the target contract is preceded by the steps of:
receiving instruction content input by a user at a pre-configured desktop application program;
prompting the user whether to save the instruction content;
if a storage command sent by the user is received, storing the instruction content into an instruction list;
prompting the user whether to execute the instruction content;
and if a confirmation execution command sent by the user is received, executing the instruction content to execute the step of acquiring the target contract to be scored and acquiring the type of the target contract.
7. An apparatus for contract scoring, comprising:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring a target contract to be scored and acquiring the type of the target contract;
the matching unit is used for matching a target model parameter set corresponding to the type in a database according to the type of the target contract; the database is pre-stored with the corresponding relation between the contract type and the model parameter set, wherein the model parameter set is the collection of each model parameter in the contract scoring model;
the updating unit is used for correspondingly updating the model parameters in the contract scoring model according to the target model parameter set to obtain a target contract scoring model;
a first extraction unit, configured to extract a text feature of the target contract;
and the scoring unit is used for inputting the text characteristics of the target contract into the target contract scoring model and outputting the score of the target contract.
8. The apparatus for contract scoring according to claim 7, further comprising:
the second acquisition unit is used for acquiring contract samples and classifying the contract samples according to the types of the contract samples to obtain a plurality of types of contract training samples; the contract training sample comprises a contract training text and a corresponding standard score;
the second extraction unit is used for extracting the text features of the contract training texts included in the same type of contract training samples;
the training unit is used for inputting the text features into a neural network model for training until the difference value between the score output by the neural network model and the standard score corresponding to the contract training text is smaller than a preset value, completing the training of the neural network model and obtaining a corresponding contract score model under the type;
the composition unit is used for composing the model parameters of the contract scoring model corresponding to the type into a model parameter set;
and the storage unit is used for establishing a corresponding relation between the type of the contract training sample and the model parameter set and storing the corresponding relation in the database.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011055598.6A CN112184498A (en) | 2020-09-29 | 2020-09-29 | Contract scoring method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011055598.6A CN112184498A (en) | 2020-09-29 | 2020-09-29 | Contract scoring method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112184498A true CN112184498A (en) | 2021-01-05 |
Family
ID=73946996
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011055598.6A Pending CN112184498A (en) | 2020-09-29 | 2020-09-29 | Contract scoring method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112184498A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033178A (en) * | 2021-03-04 | 2021-06-25 | 海创汇科技创业发展有限公司 | Text evaluation method and device for business plan and computer |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140108072A1 (en) * | 2012-10-17 | 2014-04-17 | Bank Of America | Vendor Contract Assessment Tool |
| CN109657227A (en) * | 2018-10-08 | 2019-04-19 | 平安科技（深圳）有限公司 | Contract feasibility determination method, equipment, storage medium and device |
| CN109918635A (en) * | 2017-12-12 | 2019-06-21 | 中兴通讯股份有限公司 | A kind of contract text risk checking method, device, equipment and storage medium |
| CN110059924A (en) * | 2019-03-13 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Checking method, device, equipment and the computer readable storage medium of contract terms |
| CN110110320A (en) * | 2019-03-12 | 2019-08-09 | 平安科技（深圳）有限公司 | Automatic treaty review method, apparatus, medium and electronic equipment |
| CN110163380A (en) * | 2018-04-28 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Data analysing method, model training method, device, equipment and storage medium |
| CN110716767A (en) * | 2018-07-13 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Model component calling and generating method, device and storage medium |
-
2020
- 2020-09-29 CN CN202011055598.6A patent/CN112184498A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140108072A1 (en) * | 2012-10-17 | 2014-04-17 | Bank Of America | Vendor Contract Assessment Tool |
| CN109918635A (en) * | 2017-12-12 | 2019-06-21 | 中兴通讯股份有限公司 | A kind of contract text risk checking method, device, equipment and storage medium |
| CN110163380A (en) * | 2018-04-28 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Data analysing method, model training method, device, equipment and storage medium |
| CN110716767A (en) * | 2018-07-13 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Model component calling and generating method, device and storage medium |
| CN109657227A (en) * | 2018-10-08 | 2019-04-19 | 平安科技（深圳）有限公司 | Contract feasibility determination method, equipment, storage medium and device |
| CN110110320A (en) * | 2019-03-12 | 2019-08-09 | 平安科技（深圳）有限公司 | Automatic treaty review method, apparatus, medium and electronic equipment |
| CN110059924A (en) * | 2019-03-13 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Checking method, device, equipment and the computer readable storage medium of contract terms |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033178A (en) * | 2021-03-04 | 2021-06-25 | 海创汇科技创业发展有限公司 | Text evaluation method and device for business plan and computer |
| CN113033178B (en) * | 2021-03-04 | 2023-09-12 | 海创汇科技创业发展有限公司 | Text evaluation method, device and computer for business planning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110457431B (en) | Knowledge graph-based question and answer method and device, computer equipment and storage medium | |
| CN110765015B (en) | Method for testing tested application and electronic equipment | |
| CN112163424A (en) | Data labeling method, device, equipment and medium | |
| CN110377218B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN101452443B (en) | Recording medium for recording logical structure model creation assistance program, logical structure model creation assistance device and logical structure model creation assistance method | |
| JP7128919B2 (en) | Skill term evaluation method and device, electronic device, computer readable medium | |
| CN109614371B (en) | Method, device, computer equipment and storage medium for storing information | |
| CN111914159A (en) | Information recommendation method and terminal | |
| CN112184498A (en) | Contract scoring method and device, computer equipment and storage medium | |
| CN115659226A (en) | Data processing system for acquiring APP label | |
| CN113590737B (en) | Event data processing method, device, equipment and medium based on knowledge graph | |
| CN115935344A (en) | Abnormal equipment identification method and device and electronic equipment | |
| CN112836041A (en) | Personnel relationship analysis method, device, equipment and storage medium | |
| CN110750984B (en) | Command line character string processing method, terminal, device and readable storage medium | |
| JP2017111500A (en) | Character recognizing apparatus, and program | |
| CN115098663A (en) | Method and system for accurately portraying job seeker | |
| CN113656705B (en) | Course recommendation method, device, equipment and storage medium based on artificial intelligence | |
| CN110569401A (en) | paper marking method and device, computer equipment and storage medium | |
| CN112507129B (en) | Content change processing method of power distribution network operation file and related equipment | |
| CN113033178A (en) | Text evaluation method and device for business plan and computer | |
| CN106815592B (en) | Text data processing method and device and wrong word recognition methods and device | |
| JP2021068067A (en) | Mapping rule generation support device and method | |
| CN113849644A (en) | Text classification model configuration method and device, computer equipment and storage medium | |
| CN111881664A (en) | Information extraction method, device, equipment and medium combining RPA and AI | |
| CN112632246A (en) | Robot dialogue method and device based on deep learning and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210105 |