Transaction contract dispute processing method and device and computer program product

Abstract

The invention discloses a transaction contract dispute processing method, a transaction contract dispute processing device and a computer program product. Relates to the financial science and technology field or other related fields, and the method comprises the steps: obtaining a transaction contract dispute request, determining M evaluation objects according to the transaction contract dispute request, obtaining the dimension data of the M evaluation objects, and obtaining M groups of dimension data, each group of dimension data comprising N pieces of dimension data; for one evaluation object, determining a weight coefficient of each dimension data associated with the evaluation object, and determining a time decay parameter of the evaluation object; inputting the N pieces of dimension data associated with the weight coefficient of the evaluation object and the time decay parameter into a score prediction model to obtain an evaluation score; and selecting Y target evaluation objects based on the M evaluation scores. Through application of the method and the device, the problem of low efficiency during transaction contract event processing caused by low matching accuracy during selection of the evaluation object for evaluating the transaction contract event in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other related fields, and specifically, to a method, device and computer program product for handling transaction contract disputes. Background Art

[0002] In recent years, with the development of the digital economy, blockchain technology, as a representative of distributed ledger technology, has shown broad application prospects in many fields such as finance, e-commerce, and supply chain management due to its unique characteristics of decentralization, data immutability, and high security. As an important part of blockchain technology, smart contracts provide a way to automatically execute contract terms without the intervention of a third party. When the preset conditions are met, smart contracts can automatically execute the corresponding operations, greatly improving the efficiency and transparency of contract execution.

[0003] However, the widespread use of smart contracts has also brought new challenges, especially in terms of transaction security and information authenticity. Although blockchain technology is powerful, it cannot completely isolate abnormal transaction behaviors. For example, in financial transactions, problems such as deviations in the execution of smart contracts are common. These disputes not only affect the interests of individuals or companies, but may also have an impact on the trust and stability of the entire blockchain ecosystem. In addition, the design and execution of smart contracts themselves are not foolproof. Due to the ambiguity of contract terms or programming errors, smart contract disputes often occur. The disputes often focus on key issues such as the validity of the contract and whether the execution results are consistent with the original intentions of both parties.

[0004] To solve the above problems, an underlying technology aimed at resolving cross-chain smart contract disputes is proposed, namely the OATH (Open Attestation of Hashes and Transactions) blockchain protocol. Although the OATH blockchain provides an innovative dispute resolution framework, the existing implementation still faces some limitations. First, the credit rating of consensus validators is mostly based on static data evaluation, which may not reflect the actual reputation of the validator in real time in a dynamically changing market environment, affecting the fairness and efficiency of dispute resolution. Second, when dealing with complex disputes, the smart contract adjustment mechanism of OATH is relatively fixed and cannot be flexibly adjusted according to the specific complexity of the case, resulting in deficiencies in resource utilization and execution efficiency.

[0005] In the related art, there is a problem of low matching accuracy when selecting evaluation objects for evaluating transaction contract events, which leads to low efficiency in processing transaction contract events. No effective solution has been proposed yet. Summary of the invention

[0006] The main purpose of this application is to provide a method, device and computer program product for handling transaction contract disputes, so as to solve the problem in the related art that the matching accuracy is low when selecting the evaluation object for evaluating the transaction contract event, resulting in low efficiency in handling the transaction contract event.

[0007] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for handling transaction contract disputes is provided. The method includes: obtaining a transaction contract dispute request, determining M evaluation objects according to the transaction contract dispute request, and obtaining dimension data of the M evaluation objects to obtain M groups of dimension data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimension data includes N dimension data, M and N are positive integers; for an evaluation object, determine the weight coefficient of each dimension data associated with the evaluation object, and determine the time decay parameter of the evaluation object, wherein the time decay parameter is used to characterize the state of the evaluation object when evaluating the transaction contract event; for an evaluation object, input the N dimension data of the evaluation object associated with the weight coefficient and the time decay parameter into the scoring prediction model to obtain an evaluation score; select Y target evaluation objects based on the M evaluation scores, wherein after the Y target evaluation objects process the transaction contract event, the evaluation processing result is obtained, and Y is a positive integer.

[0008] Furthermore, obtaining dimensional data of M evaluation objects to obtain M groups of dimensional data includes: obtaining a preset data dictionary, wherein the preset data dictionary contains the association relationship between multiple dimensional data and initial dimensional data; for one evaluation object, obtaining N initial dimensional data of the evaluation object, wherein the N initial dimensional data include multiple digital form data and multiple text form data; performing data conversion processing on the N initial dimensional data using the preset data dictionary to obtain first processed dimensional data, and performing deduplication processing on the first processed dimensional data using a filtering statement to obtain a group of dimensional data of the evaluation object.

[0009] Furthermore, determining the weight coefficient of each dimensional data associated with the evaluation object includes: performing feature recognition on the transaction contract dispute request to obtain evaluation type information, wherein the evaluation type information includes at least one of the following: financial type, legal type, and supply chain type; for an evaluation object, obtaining the initial weight coefficients of N dimensional data of the evaluation object to obtain N initial weight coefficients; inputting the N initial weight coefficients and the evaluation type information into a machine learning algorithm, and using the machine learning algorithm to adjust the N initial weight coefficients based on the evaluation type information to obtain N weight coefficients.

[0010] Furthermore, determining the time decay parameter of the evaluation object includes: determining the evaluation type parameter according to the evaluation type information of the transaction contract dispute request; for an evaluation object, screening out target dimension data from the N dimension data of the evaluation object, wherein the target dimension data characterizes the review preference of the evaluation object in a preset time period; adjusting the decay coefficient using the target dimension data, calculating the product of the decay coefficient and the time period of the preset time period to obtain a first product, wherein the decay coefficient is used to characterize the evaluation ability of the evaluation object; performing power calculation on the first product to obtain an initial decay parameter, calculating the product of the initial decay parameter and the evaluation type parameter to obtain a time decay parameter.

[0011] Furthermore, in the case where the rating prediction model is a random forest model, N dimensional data of the evaluation object associated with weight coefficients and a time decay parameter are input into the rating prediction model to obtain an evaluation score, including: performing feature engineering processing on the N dimensional data associated with weight coefficients and the time decay parameter to obtain N+1 evaluation features; using each evaluation feature to construct a decision tree to obtain N+1 decision trees; performing regression processing on each decision tree until each decision tree meets the recursive conditions to obtain N+1 processed spanning trees; performing data conversion on the N+1 processed spanning trees to obtain N+1 initial scores, calculating the mean of the N+1 initial scores, and obtaining the evaluation score of the evaluation object.

[0012] Furthermore, selecting Y target evaluation objects based on the M evaluation scores includes: obtaining the blockchain associated with the transaction contract when the transaction contract event calls the transaction contract, and obtaining K protocol parameters associated with the blockchain, wherein the K protocol parameters include at least a block quantity parameter, a recommended quantity parameter, and a transaction fee parameter, and K is a positive integer; determining the blockchain coefficient of each protocol parameter according to the transaction contract event, and calculating the K protocol parameters using the K blockchain coefficients to obtain a fitness parameter; obtaining a review list, determining the evaluation object requirements from the review list according to the fitness parameters, and selecting Y target evaluation objects from the M evaluation objects according to the evaluation object requirements, wherein the evaluation object requirements include the number of evaluation objects and the review time limit.

[0013] Furthermore, in the case where the K protocol parameters are a block number parameter, a suggested amount parameter and a transaction fee parameter, the K protocol parameters are calculated using K blockchain coefficients to obtain the fitness parameter, including: calculating the inverse of the block number parameter to obtain a first calculation parameter, calculating the product of the first calculation parameter and the blockchain coefficient of the block number parameter to obtain a first parameter product; calculating the product of the suggested amount parameter and the blockchain coefficient of the suggested amount parameter to obtain a second parameter product, calculating the product of the transaction fee parameter and the blockchain coefficient of the transaction fee parameter to obtain a third parameter product; calculating the sum of the first parameter product and the second parameter product to obtain an initial fitness parameter, and calculating the difference between the initial fitness parameter and the third parameter product to obtain the fitness parameter.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a processing device for a transaction contract dispute is provided. The device includes: an acquisition unit, which is used to acquire a transaction contract dispute request, determine M evaluation objects according to the transaction contract dispute request, and acquire dimension data of the M evaluation objects to obtain M groups of dimension data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimension data includes N dimension data, M and N are positive integers; a determination unit, which is used to determine the weight coefficient of each dimension data associated with the evaluation object for an evaluation object, and determine the time decay parameter of the evaluation object, wherein the time decay parameter is used to characterize the state of the evaluation object when evaluating the transaction contract event; an input unit, which is used to input the N dimension data of the evaluation object associated with the weight coefficient and the time decay parameter into a scoring prediction model for an evaluation object to obtain an evaluation score; a selection unit, which is used to select Y target evaluation objects based on the M evaluation scores, wherein after the Y target evaluation objects process the transaction contract event, an evaluation processing result is obtained, and Y is a positive integer.

[0015] According to another aspect of an embodiment of the present invention, a computer storage medium is provided. The computer storage medium is used to store a program, wherein when the program is run, the device where the computer storage medium is located is controlled to execute a method for handling transaction contract disputes.

[0016] According to another aspect of an embodiment of the present invention, there is also provided an electronic device comprising one or more processors and a memory; the memory stores computer-readable instructions, and the processor is used to execute the computer-readable instructions, wherein when the computer-readable instructions are executed, a method for handling transaction contract disputes is executed.

[0017] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, a method for handling transaction contract disputes is performed.

[0018] Through this application, the following steps are adopted: obtaining a transaction contract dispute request, determining M evaluation objects according to the transaction contract dispute request, and obtaining dimension data of the M evaluation objects to obtain M groups of dimension data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimension data includes N dimension data, where M and N are positive integers; for an evaluation object, determining a weight coefficient of each dimension data associated with the evaluation object, and determining a time decay parameter of the evaluation object, wherein the time decay parameter is used to characterize the state of the evaluation object when evaluating the transaction contract event; for an evaluation object, inputting the N dimension data of the evaluation object associated with the weight coefficient and the time decay parameter A scoring prediction model is provided to obtain an evaluation score; Y target evaluation objects are selected based on the M evaluation scores, wherein an evaluation processing result is obtained after the Y target evaluation objects process the transaction contract event, and Y is a positive integer. This solves the problem in the related art that the matching accuracy is low when selecting the evaluation object for evaluating the transaction contract event, resulting in low efficiency in processing the transaction contract event. By acquiring the dimensional data of the evaluation object, multiple groups of dimensional data are obtained, and the weight coefficient and time decay parameter of each dimensional data associated with the evaluation object are determined. The dimensional data associated with the evaluation object with the weight coefficient and the time decay parameter are input into the scoring prediction model to obtain the evaluation score, and the target evaluation object is selected based on the evaluation score, thereby achieving the effect of accurately and quickly selecting the evaluation object. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 is a flow chart of a method for handling transaction contract disputes provided in accordance with an embodiment of the present application;

[0021] Figure 2 It is a schematic diagram of an optional method for handling transaction contract disputes provided in an embodiment of the present application;

[0022] Figure 3 is a schematic diagram of a system for handling transaction contract disputes provided according to an embodiment of the present application;

[0023] Figure 4 is a schematic diagram of a transaction contract dispute processing device provided according to an embodiment of the present application;

[0024] Figure 5 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0029] It should be noted that the collected information used in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse to use it.

[0030] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a method for handling transaction contract disputes provided in an embodiment of the present application, such as Figure 1As shown, the method comprises the following steps:

[0031] Step S101, obtaining a transaction contract dispute request, determining M evaluation objects according to the transaction contract dispute request, and obtaining dimensional data of the M evaluation objects to obtain M groups of dimensional data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimensional data includes N dimensional data, where M and N are positive integers.

[0032] Specifically, when two customers use smart contracts to conduct transactions, if one customer finds that the contract terms generated by the smart contract have ambiguity, time limit issues or programming errors, resulting in the execution results based on the above contract being different from the original intentions of both parties, a transaction contract event is generated at this time, and the above transaction contract event can be evaluated by selecting one or more evaluation objects. When selecting the evaluation object, first, multiple candidate evaluation objects can be determined using the transaction contract dispute request generated by the transaction contract event, and then the relevant information of each evaluation object is obtained, that is, a set of dimensional data for each evaluation object is obtained.

[0033] Step S102, for an evaluation object, determine the weight coefficient of each dimension data associated with the evaluation object, and determine the time decay parameter of the evaluation object, wherein the time decay parameter is used to characterize the state of the evaluation object when evaluating a transaction contract event.

[0034] Specifically, since the attributes of transaction contract events may be different, the weight data of each dimensional data associated with each evaluation object may be different. Therefore, it is necessary to adjust the weight coefficient of the dimensional data associated with each evaluation object. At the same time, it is also necessary to determine the state of each evaluation object when evaluating the above transaction contract events, that is, to obtain the time decay parameter.

[0035] Step S103: for an evaluation object, N dimension data of the evaluation object associated with weight coefficients and a time decay parameter are input into a scoring prediction model to obtain an evaluation score.

[0036] Specifically, the rating prediction model can be a random forest model. After determining the weight coefficient of the dimensional data, all dimensional data associated with the weight coefficient and the time decay parameter of each evaluation object can be input into the rating prediction model. The model processes the dimensional data and the time decay parameter to obtain multiple evaluation scores.

[0037] Step S104: select Y target evaluation objects based on the M evaluation scores, wherein after the Y target evaluation objects process the transaction contract event, an evaluation processing result is obtained, and Y is a positive integer.

[0038] Specifically, after obtaining the evaluation score of each candidate evaluation object, the evaluation objects can be sorted in descending order according to these evaluation scores, and then one or more target evaluation objects can be selected from the sorting according to the evaluation object requirements. After these evaluation objects have processed the above events, the evaluation processing results are fed back to the two parties of the transaction contract event.

[0039] The method for handling transaction contract disputes provided in the embodiment of the present application obtains a transaction contract dispute request, determines M evaluation objects according to the transaction contract dispute request, and obtains dimensional data of the M evaluation objects to obtain M groups of dimensional data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimensional data includes N dimensional data, where M and N are positive integers; for one evaluation object, a weight coefficient of each dimensional data associated with the evaluation object is determined, and a time decay parameter of the evaluation object is determined, wherein the time decay parameter is used to characterize the state of the evaluation object when evaluating the transaction contract event; for one evaluation object, the N dimensional data of the evaluation object associated with the weight coefficient and the time decay parameter are combined; Subtract parameters from the input into the scoring prediction model to obtain an evaluation score; select Y target evaluation objects based on the M evaluation scores, wherein after the Y target evaluation objects process the transaction contract event, an evaluation processing result is obtained, and Y is a positive integer, which solves the problem of low matching accuracy in selecting evaluation objects for evaluating transaction contract events in the related technology, resulting in low efficiency in processing transaction contract events. By acquiring the dimensional data of the evaluation object, multiple groups of dimensional data are obtained, and the weight coefficient and time decay parameter of each dimensional data associated with the evaluation object are determined. The dimensional data of the evaluation object associated with the weight coefficient and the time decay parameter are input into the scoring prediction model to obtain the evaluation score, and the target evaluation object is selected based on the evaluation score, thereby achieving the effect of accurately and quickly selecting the evaluation object.

[0040] In order to improve the efficiency of data processing, optionally, in the method for handling transaction contract disputes provided in an embodiment of the present application, dimensional data of M evaluation objects are obtained, and obtaining M groups of dimensional data includes: obtaining a preset data dictionary, wherein the preset data dictionary contains the association relationship between multiple dimensional data and initial dimensional data; for one evaluation object, obtaining N initial dimensional data of the evaluation object, wherein the N initial dimensional data include multiple digital form data and multiple text form data; performing data conversion processing on the N initial dimensional data using the preset data dictionary to obtain first processed dimensional data, and performing deduplication processing on the first processed dimensional data using a filtering statement to obtain a group of dimensional data of the evaluation object.

[0041] Specifically, the preset data dictionary can be in the form of a key-value pair, where the key is the initial dimensional data and the value is the corresponding dimensional data. In order to determine the dimensional data of the evaluation object, the initial dimensional data of each evaluation object can be obtained, where the initial dimensional data can be multiple digital data and multiple text data, such as gender, age, nationality, educational background, skills, community activity participation, voting accuracy, voting response speed data, etc. In order to help the scoring prediction model better identify dimensional data, the above data can be processed through a preset data dictionary containing the association relationship between multiple dimensional data and the initial dimensional data. For example, if the initial dimensional data contains If the data contains "Bachelor's degree" and "Master's degree" in text form, and the preset data dictionary maps "Bachelor's degree" to 1 and "Master's degree" to 2, after the initial dimensional data is converted, these text-based data can be converted into corresponding digital dimensional data; if the initial dimensional data contains community activity participation status "100 hours" and "300 hours" in digital form, and the preset data dictionary maps "100 hours" to 4 and "300 hours" to 6, after the initial dimensional data is converted, these initial dimensional data in digital form can be converted into corresponding digital dimensional data, thereby obtaining the first processed dimensional data.

[0042] Furthermore, in order to ensure the uniqueness of each dimension data and eliminate duplicate data items, a filter statement can be used to deduplicate these data. For example, a deduplication function in a programming language or a DISTINCT keyword in a database query statement can be used to process them, so as to obtain a set of dimension data. This embodiment converts the original, possibly duplicated, and diverse initial dimension data into a set of standardized, deduplicated data sets that can be used for further analysis, thereby not only improving the efficiency of data processing, but also providing a more accurate and reliable basis for subsequent data analysis.

[0043] In order to more accurately screen out suitable evaluation objects, optionally, in the method for handling transaction contract disputes provided in an embodiment of the present application, determining the weight coefficient of each dimensional data associated with the evaluation object includes: performing feature recognition on the transaction contract dispute request to obtain evaluation type information, wherein the evaluation type information includes at least one of the following: financial type, legal type, and supply chain type; for an evaluation object, obtaining the initial weight coefficients of N dimensional data of the evaluation object to obtain N initial weight coefficients; inputting the N initial weight coefficients and the evaluation type information into a machine learning algorithm, and using the machine learning algorithm to adjust the N initial weight coefficients based on the evaluation type information to obtain N weight coefficients.

[0044] Specifically, since the direction of a transaction contract event can be of multiple types, different transaction contract events may have different requirements for the evaluation object. In order to screen out suitable evaluation objects, different weight coefficients may be assigned to the dimensional data of the evaluation object. First, the transaction contract dispute request may be feature identified to obtain the evaluation type information of the event. After obtaining the initial weight coefficient of each dimensional data, the initial weight coefficient and the evaluation type information are input into the machine learning algorithm. The machine learning algorithm is used to adjust the initial weight coefficient based on the evaluation type information to obtain a weight coefficient that reflects the impact of different evaluation types on the weight. For example, for the evaluation of legal type transaction contract events, it may be necessary to increase the weight coefficient of the dimensional data related to contract compliance, wherein the initial weight coefficient may be determined by historical data analysis or predefined rules. By adjusting the weight coefficient, this embodiment can more accurately evaluate the transaction contract dispute request and provide a reference for resolving disputes.

[0045] In order to determine the assessment ability of the assessment object, optionally, in the method for handling transaction contract disputes provided in the embodiment of the present application, determining the time decay parameter of the assessment object includes: determining the assessment type parameter according to the assessment type information of the transaction contract dispute request; for an assessment object, screening out target dimension data from the N dimension data of the assessment object, wherein the target dimension data characterizes the review preference of the assessment object in a preset time period; adjusting the attenuation coefficient using the target dimension data, calculating the product of the attenuation coefficient and the time period of the preset time period to obtain a first product, wherein the attenuation coefficient is used to characterize the assessment ability of the assessment object; performing power calculation on the first product to obtain an initial attenuation parameter, calculating the product of the initial attenuation parameter and the assessment type parameter to obtain a time decay parameter.

[0046] Specifically, because recent behaviors can better reflect the current state of the evaluation object, and the importance of more distant historical behaviors gradually decreases over time, in addition to adjusting the weight coefficient of each dimension data, it is also necessary to determine the time decay parameter used to characterize the state of the evaluation object when evaluating the transaction contract event. First, the target dimension data can be screened out from multiple dimension data. This data can characterize the review preference of the evaluation object within a preset time period. By analyzing this data, we can better understand the direct manifestation of the review preference and behavioral characteristics of the evaluation object within the preset time period.

[0047] Furthermore, these target dimension data can be used to adjust the attenuation coefficient used to characterize the evaluation ability of the evaluation object. By adjusting the attenuation coefficient, the change in the evaluation ability of the evaluation object in different time periods can be more accurately reflected. Then, the product of the attenuation coefficient and the time period of the preset time period is calculated to obtain the first product, that is, the influence of the attenuation coefficient is combined with the time period, which can provide a quantitative indicator to measure the change of the evaluation ability of the evaluation object over time.

[0048] Finally, the first product is exponentially calculated to adapt to different evaluation requirements and scenarios, and then the initial attenuation parameter is obtained, wherein the initial attenuation parameter can further refine the evaluation ability of the evaluation object to make it more in line with the actual situation. Then the product of the initial attenuation parameter and the evaluation type parameter is calculated to obtain the time attenuation parameter. It can be calculated by the following formula: P = Y × e (-kt) , where Y represents the evaluation type parameter, k represents the decay coefficient, and the time decay parameter P is a key parameter that comprehensively considers the evaluation ability, time period, and evaluation type of the evaluation object. By calculating the time decay parameter, this embodiment can not only consider the changes in the evaluation ability of the evaluation object in different time periods, but also provide a more accurate and comprehensive reference for the final evaluation score in combination with the characteristics and requirements of the evaluation type.

[0049] Optionally, in the method for handling transaction contract disputes provided in an embodiment of the present application, when the scoring prediction model is a random forest model, N dimensional data of the evaluation object associated with weight coefficients and time decay parameters are input into the scoring prediction model to obtain an evaluation score, including: performing feature engineering processing on the N dimensional data associated with weight coefficients and time decay parameters to obtain N+1 evaluation features; using each evaluation feature to construct a decision tree to obtain N+1 decision trees; performing regression processing on each decision tree until each decision tree meets the recursive condition to obtain N+1 processed spanning trees; performing data conversion on the N+1 processed spanning trees to obtain N+1 initial scores, calculating the mean of the N+1 initial scores, and obtaining the evaluation score of the evaluation object.

[0050] Specifically, before using the scoring prediction model to determine the score of each evaluation object, it is necessary to consider not only the numerical value of each dimensional data, but also the correlation between them and the contribution weight of each dimension to the final result. Therefore, it is necessary to perform feature engineering on the given multiple dimensional data associated with weight coefficients and time decay parameters, and then obtain multiple dimensional features and a time decay feature. Then, these evaluation features can be used to build a decision tree model. Each decision tree model corresponds to an evaluation feature, and each node represents a feature test, each branch represents the result of the test, and each leaf node represents the final decision or prediction result. Finally, each decision tree model is regressed until the recursive condition is met, such as reaching the minimum number of node splits or the maximum tree depth, and the corresponding processed spanning tree is obtained.

[0051] Furthermore, data conversion is performed on the generated trees after the above processing, and their results are converted into initial scores. The initial scores are then averaged to obtain the evaluation score of the evaluation object. This embodiment constructs effective decision trees, and then obtains a more comprehensive and accurate evaluation score based on these decision trees, which can more accurately judge the overall performance of the evaluation object.

[0052] The target evaluation object can be determined based on the evaluation score. Optionally, in the method for handling transaction contract disputes provided in the embodiment of the present application, selecting Y target evaluation objects based on M evaluation scores includes: obtaining the blockchain associated with the transaction contract when the transaction contract event calls the transaction contract, and obtaining K protocol parameters associated with the blockchain, wherein the K protocol parameters include at least a block quantity parameter, a recommended quantity parameter, and a transaction fee parameter, and K is a positive integer; determining the blockchain coefficient of each protocol parameter based on the transaction contract event, and calculating the K protocol parameters using the K blockchain coefficients to obtain a fitness parameter; obtaining a review list, determining the evaluation object requirements from the review list based on the fitness parameters, and selecting Y target evaluation objects from the M evaluation objects based on the evaluation object requirements, wherein the evaluation object requirements include the number of evaluation objects and the review time limit.

[0053] Specifically, after calculating the evaluation scores using the rating prediction model, the evaluation objects can be selected based on these evaluation scores. First, relevant information can be extracted from the transaction contract event, and then the blockchain related to the event can be determined, and then multiple protocol parameters of the blockchain can be obtained. For example, the protocol parameters can be the block size (that is, the block number parameter), the transaction volume per second (that is, the recommended volume parameter), and the transaction fee provided when calling the smart contract (that is, the transaction fee parameter).

[0054] Furthermore, the protocol parameters of the above blockchain and the corresponding blockchain coefficients are used for calculation to obtain fitness parameters. According to the fitness parameters, the specific requirements of the evaluation object can be determined from the review list, where these requirements may include the number of evaluation objects to be evaluated and the time limit for completing the review. Finally, one or more target evaluation objects are selected from the candidate evaluation objects according to the above evaluation object requirements. This embodiment ensures that the transaction contract event is effectively and comprehensively evaluated by selecting the target evaluation object using the evaluation score, thereby improving the accuracy and efficiency of the evaluation.

[0055] Optionally, in the method for handling transaction contract disputes provided in an embodiment of the present application, when the K protocol parameters are a block quantity parameter, a recommended quantity parameter and a transaction fee parameter, the K protocol parameters are calculated using K blockchain coefficients to obtain the fitness parameter, including: calculating the inverse of the block quantity parameter to obtain a first calculation parameter, calculating the product of the first calculation parameter and the blockchain coefficient of the block quantity parameter to obtain a first parameter product; calculating the product of the recommended quantity parameter and the blockchain coefficient of the recommended quantity parameter to obtain a second parameter product, calculating the product of the transaction fee parameter and the blockchain coefficient of the transaction fee parameter to obtain a third parameter product; calculating the sum of the first parameter product and the second parameter product to obtain an initial fitness parameter, and calculating the difference between the initial fitness parameter and the third parameter product to obtain the fitness parameter.

[0056] Specifically, in order to determine the target evaluation object, a selection can be made based on the fitness parameter, which can be calculated by the following formula: Fitness parameter = w1*(1 / block number parameter)+w2*recommended amount parameter-w3*transaction fee parameter, where w1, w2, and w3 represent the blockchain coefficient of the block number parameter, the blockchain coefficient of the recommended amount parameter, and the blockchain coefficient of the transaction fee parameter, respectively.

[0057] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0058] This embodiment also provides a method for handling transaction contract disputes, and the method is applied to a system for handling transaction contract disputes. Figure 2 is a schematic diagram of an optional method for handling transaction contract disputes provided in an embodiment of the present application. Figure 3 is a schematic diagram of a system for handling transaction contract disputes provided in accordance with an embodiment of the present application, such as Figure 2 , Figure 3As shown, the system includes contract execution parties, smart contracts and a transaction evaluation system, and the transaction evaluation system includes a data processing module, a dynamic weight allocation module, a time decay module, an evaluation calculation module and an adjustment module.

[0059] When the parties involved in the smart contract execution, Client A and Client B, conduct a financial product transaction through the smart contract, the smart contract calls the API interface of the transaction evaluation system during the writing process. Therefore, the called smart contract is monitored during all subsequent execution processes of the smart contract.

[0060] When client A believes that he has completed the transaction by calling the smart contract, but client B believes that he has not received the transaction confirmation, the transaction contract event generated at this time sends a notification to client A and client B, and generates a transaction contract dispute request, and stores the disputed smart contract and the basic information of both parties of the smart contract on the blockchain, which triggers the dispute assessment. Based on the data processing module, the dimension data of multiple candidate assessment objects are obtained from the blockchain, and the DISTINCT keyword is used to remove duplicates, so as to obtain a set of dimension data.

[0061] Furthermore, the weight distribution module is used to determine the weight coefficient of each dimension data associated with the evaluation object through a machine learning algorithm. For example, if the evaluation type information of the above event is financial type, the weight coefficient of the skill (related to finance) characteristics of the evaluation object can be adjusted; and the time decay module is used through the formula P = Y × e (-kt) Calculate the time decay parameters and input these data into the evaluation calculation module to calculate the evaluation score.

[0062] After the evaluation calculation module obtains multiple dimensional data associated with weight coefficients and time decay parameters, the dimensional data associated with weight coefficients and time decay parameters are input into the random forest algorithm to obtain the evaluation score. The evaluation score is then sent to the adjustment module to select the evaluation object. At this time, the particle swarm optimization algorithm can be used to determine the number of evaluation objects and the review time limit, and then multiple target evaluation objects are selected. After these target evaluation objects process the transaction contract event, the evaluation processing results are obtained and stored on the blockchain. The system feeds back to the calling customer, and the evaluation of this transaction contract event is completed.

[0063] This embodiment obtains dimensional data of the evaluation object to obtain multiple groups of dimensional data, determines the weight coefficient and time decay parameter of each dimensional data associated with the evaluation object, inputs the dimensional data with weight coefficient and time decay parameter associated with the evaluation object into a scoring prediction model to obtain an evaluation score, and selects a target evaluation object based on the evaluation score, thereby achieving the effect of accurately and quickly selecting the evaluation object.

[0064] The embodiment of the present application also provides a transaction contract dispute processing device. It should be noted that the transaction contract dispute processing device of the embodiment of the present application can be used to execute the transaction contract dispute processing method provided in the embodiment of the present application. The transaction contract dispute processing device provided in the embodiment of the present application is introduced below.

[0065] Figure 4 is a schematic diagram of a transaction contract dispute processing device provided according to an embodiment of the present application, such as Figure 4 As shown, the device includes: an acquisition unit 40, a determination unit 41, an input unit 42, and a selection unit 43.

[0066] The acquisition unit 40 is used to acquire a transaction contract dispute request, determine M evaluation objects according to the transaction contract dispute request, and acquire dimension data of the M evaluation objects to obtain M groups of dimension data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimension data includes N dimension data, where M and N are positive integers;

[0067] A determination unit 41 is used to determine, for an evaluation object, a weight coefficient of each dimension data associated with the evaluation object, and determine a time decay parameter of the evaluation object, wherein the time decay parameter is used to characterize the state of the evaluation object when evaluating a transaction contract event;

[0068] An input unit 42 is used to input N dimension data of an evaluation object associated with weight coefficients and a time decay parameter into a scoring prediction model to obtain an evaluation score for an evaluation object;

[0069] The selection unit 43 is used to select Y target evaluation objects based on the M evaluation scores, wherein after the Y target evaluation objects process the transaction contract event, an evaluation processing result is obtained, and Y is a positive integer.

[0070] The transaction contract dispute processing device provided in the embodiment of the present application obtains a transaction contract dispute request through an acquisition unit 40, determines M evaluation objects according to the transaction contract dispute request, and obtains dimensional data of the M evaluation objects to obtain M groups of dimensional data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimensional data includes N dimensional data, where M and N are positive integers; the determination unit 41 determines, for one evaluation object, a weight coefficient of each dimensional data associated with the evaluation object, and determines a time decay parameter of the evaluation object, wherein the time decay parameter is used to characterize the state of the evaluation object when evaluating the transaction contract event; the input unit 42 inputs, for one evaluation object, the number of dimensions of the N dimensions associated with the evaluation object with the weight coefficient. and time decay parameters are input into the scoring prediction model to obtain an evaluation score; the selection unit 43 selects Y target evaluation objects based on the M evaluation scores, wherein after the Y target evaluation objects process the transaction contract event, an evaluation processing result is obtained, and Y is a positive integer, which solves the problem of low matching accuracy when selecting evaluation objects for evaluating transaction contract events in the related art, resulting in low efficiency in processing transaction contract events. By acquiring the dimensional data of the evaluation object, multiple groups of dimensional data are obtained, and the weight coefficient and time decay parameter of each dimensional data associated with the evaluation object are determined, and the dimensional data of the evaluation object associated with the weight coefficient and the time decay parameter are input into the scoring prediction model to obtain the evaluation score, and the target evaluation object is selected based on the evaluation score, thereby achieving the effect of accurately and quickly selecting the evaluation object.

[0071] Optionally, in the transaction contract dispute processing device provided in the embodiment of the present application, the acquisition unit 40 includes: a first acquisition module, used to acquire a preset data dictionary, wherein the preset data dictionary contains the association relationship between multiple dimensional data and initial dimensional data; a second acquisition module, used to acquire N initial dimensional data of an evaluation object for an evaluation object, wherein the N initial dimensional data include multiple digital form data and multiple text form data; a first processing module, used to perform data conversion processing on the N initial dimensional data using the preset data dictionary to obtain first processed dimensional data, and perform deduplication processing on the first processed dimensional data using a filtering statement to obtain a set of dimensional data of the evaluation object.

[0072] Optionally, in the transaction contract dispute processing device provided in the embodiment of the present application, the determination unit 41 includes: an identification module, used to perform feature identification on the transaction contract dispute request to obtain evaluation type information, wherein the evaluation type information includes at least one of the following: financial type, legal type and supply chain type; a third acquisition module, used to obtain, for an evaluation object, the initial weight coefficients of N dimensional data of the evaluation object, and obtain N initial weight coefficients; an input module, used to input the N initial weight coefficients and the evaluation type information into a machine learning algorithm, and use the machine learning algorithm to adjust the N initial weight coefficients based on the evaluation type information to obtain N weight coefficients.

[0073] Optionally, in the transaction contract dispute processing device provided in the embodiment of the present application, the determination unit 41 includes: a first determination module, used to determine the evaluation type parameter according to the evaluation type information of the transaction contract dispute request; a screening module, used to screen out target dimension data from N dimensional data of an evaluation object for an evaluation object, wherein the target dimension data characterizes the review preference of the evaluation object in a preset time period; an adjustment module, used to adjust the attenuation coefficient using the target dimension data, calculate the product of the attenuation coefficient and the time period of the preset time period, and obtain a first product, wherein the attenuation coefficient is used to characterize the evaluation ability of the evaluation object; a first calculation module, used to perform power calculation on the first product to obtain an initial attenuation parameter, calculate the product of the initial attenuation parameter and the evaluation type parameter, and obtain a time attenuation parameter.

[0074] Optionally, in the transaction contract dispute processing device provided in the embodiment of the present application, the input unit 42 includes: a second processing module, which is used to perform feature engineering processing on N dimensional data associated with weight coefficients and time decay parameters to obtain N+1 evaluation features; a construction module, which is used to construct a decision tree using each evaluation feature to obtain N+1 decision trees; a third processing module, which is used to perform regression processing on each decision tree until each decision tree meets the recursive condition to obtain N+1 processed spanning trees; a conversion module, which is used to perform data conversion on the N+1 processed spanning trees to obtain N+1 initial scores, calculate the mean of the N+1 initial scores, and obtain the evaluation score of the evaluation object.

[0075] Optionally, in the transaction contract dispute processing device provided in the embodiment of the present application, the selection unit 43 includes: a fourth acquisition module, used to obtain the blockchain associated with the transaction contract when the transaction contract event calls the transaction contract, and obtain K protocol parameters associated with the blockchain, wherein the K protocol parameters include at least a block quantity parameter, a recommended quantity parameter and a transaction fee parameter, and K is a positive integer; a second determination module, used to determine the blockchain coefficient of each protocol parameter according to the transaction contract event, and use the K blockchain coefficients to calculate the K protocol parameters to obtain a fitness parameter; a fifth acquisition module, used to obtain a review list, determine the evaluation object requirements from the review list according to the fitness parameters, and select Y target evaluation objects from the M evaluation objects according to the evaluation object requirements, wherein the evaluation object requirements include the number of evaluation objects and the review time limit.

[0076] Optionally, in the transaction contract dispute processing device provided in the embodiment of the present application, the selection unit 43 includes: a second calculation module, used to calculate the inverse of the block quantity parameter to obtain a first calculation parameter, and calculate the product of the first calculation parameter and the blockchain coefficient of the block quantity parameter to obtain the first parameter product; a third calculation module, used to calculate the product of the recommended quantity parameter and the blockchain coefficient of the recommended quantity parameter to obtain the second parameter product, and calculate the product of the transaction fee parameter and the blockchain coefficient of the transaction fee parameter to obtain the third parameter product; a fourth calculation module, used to calculate the sum of the first parameter product and the second parameter product to obtain an initial fitness parameter, and calculate the difference between the initial fitness parameter and the product of the third parameter to obtain a fitness parameter.

[0077] The above-mentioned transaction contract dispute processing device includes a processor and a memory. The above-mentioned acquisition unit 40, determination unit 41, input unit 42, selection unit 43, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0078] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters are adjusted to solve the problem of low matching accuracy when selecting an evaluation object for evaluating a transaction contract event in the related art, resulting in low efficiency in processing the transaction contract event.

[0079] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0080] An embodiment of the present invention provides a computer storage medium, which is used to store a program. When the program is running, the device where the computer storage medium is located is controlled to execute a method for handling transaction contract disputes.

[0081] Figure 5 is a schematic diagram of an electronic device provided according to an embodiment of the present application, such as Figure 5 As shown, an embodiment of the present invention provides an electronic device, the electronic device 50 includes a processor, a memory, and a program stored in the memory and executable on the processor, the processor is used to execute computer-readable instructions, wherein the computer-readable instructions execute a method for handling transaction contract disputes when they are executed. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0082] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of a method for handling transaction contract disputes in various embodiments of the present application.

[0083] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0084] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0088] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0089] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0091] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for handling transaction contract disputes, characterized in that: include: Obtaining a transaction contract dispute request, determining M evaluation objects according to the transaction contract dispute request, and obtaining dimension data of the M evaluation objects to obtain M groups of dimension data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimension data includes N dimension data, where M and N are positive integers; For an evaluation object, determine the weight coefficient of each dimension data associated with the evaluation object, and determine the time decay parameter of the evaluation object, wherein the time decay parameter is used to characterize the state of the evaluation object when evaluating the transaction contract event; For an evaluation object, N dimension data of the evaluation object associated with weight coefficients and a time decay parameter are input into a scoring prediction model to obtain an evaluation score; Based on the M evaluation scores, Y target evaluation objects are selected, wherein after the Y target evaluation objects process the transaction contract event, an evaluation processing result is obtained, and Y is a positive integer.

2. The method according to claim 1, characterized in that The dimensional data of the M evaluation objects are obtained, and the M groups of dimensional data include: Acquire a preset data dictionary, wherein the preset data dictionary includes associations between multiple dimensional data and initial dimensional data; For an evaluation object, obtaining N initial dimension data of the evaluation object, wherein the N initial dimension data includes a plurality of digital form data and a plurality of text form data; The preset data dictionary is used to perform data conversion processing on the N initial dimensional data to obtain first processed dimensional data, and a filter statement is used to perform deduplication processing on the first processed dimensional data to obtain a set of dimensional data of the evaluation object.

3. The method according to claim 1, characterized in that Determining the weight coefficient of each dimension data associated with the evaluation object includes: Performing feature recognition on the transaction contract dispute request to obtain assessment type information, wherein the assessment type information includes at least one of the following: financial type, legal type, and supply chain type; For an evaluation object, obtaining initial weight coefficients of N dimensional data of the evaluation object to obtain N initial weight coefficients; The N initial weight coefficients and the evaluation type information are input into a machine learning algorithm, and the N initial weight coefficients are adjusted based on the evaluation type information using the machine learning algorithm to obtain N weight coefficients.

4. The method according to claim 1, characterized in that: Determining the time decay parameter of the evaluation object includes: Determine an assessment type parameter according to the assessment type information of the transaction contract dispute request; For an evaluation object, target dimension data is screened out from the N dimension data of the evaluation object, wherein the target dimension data represents the review preference of the evaluation object in a preset time period; Using the target dimension data to adjust the attenuation coefficient, calculating the product of the attenuation coefficient and the time period of the preset time period to obtain a first product, wherein the attenuation coefficient is used to characterize the evaluation ability of the evaluation object; The first product is subjected to power calculation to obtain an initial attenuation parameter, and the product of the initial attenuation parameter and the evaluation type parameter is calculated to obtain the time attenuation parameter.

5. The method according to claim 1, characterized in that In the case where the rating prediction model is a random forest model, N dimensional data of the evaluation object associated with weight coefficients and a time decay parameter are input into the rating prediction model to obtain an evaluation score including: Performing feature engineering processing on the N dimensional data associated with weight coefficients and time decay parameters to obtain N+1 evaluation features; Use each evaluation feature to build a decision tree and get N+1 decision trees; Perform regression processing on each decision tree until each decision tree meets the recursive condition and obtains N+1 processed spanning trees; Data conversion is performed on the N+1 processed spanning trees to obtain N+1 initial scores, and the average of the N+1 initial scores is calculated to obtain the evaluation score of the evaluation object.

6. The method according to claim 1, characterized in that Based on the M evaluation scores, Y target evaluation objects are selected, including: Obtain the blockchain associated with the transaction contract event when calling the transaction contract, and obtain K protocol parameters associated with the blockchain, wherein the K protocol parameters at least include a block quantity parameter, a recommended quantity parameter, and a transaction fee parameter, and K is a positive integer; Determine the blockchain coefficient of each protocol parameter according to the transaction contract event, and calculate the K protocol parameters using the K blockchain coefficients to obtain a fitness parameter; Obtain a review list, determine evaluation object requirements from the review list according to a fitness parameter, and select the Y target evaluation objects from the M evaluation objects according to the evaluation object requirements, wherein the evaluation object requirements include the number of evaluation objects and a review time limit.

7. The method according to claim 6, characterized in that In the case where the K protocol parameters are the block quantity parameter, the recommended amount parameter, and the transaction fee parameter, the K protocol parameters are calculated using K blockchain coefficients to obtain the fitness parameters including: Calculating the inverse of the block number parameter to obtain a first calculation parameter, and calculating the product of the first calculation parameter and the blockchain coefficient of the block number parameter to obtain a first parameter product; Calculating the product of the suggested amount parameter and the blockchain coefficient of the suggested amount parameter to obtain a second parameter product, and calculating the product of the transaction fee parameter and the blockchain coefficient of the transaction fee parameter to obtain a third parameter product; The sum of the first parameter product and the second parameter product is calculated to obtain an initial fitness parameter, and the difference between the initial fitness parameter and the third parameter product is calculated to obtain the fitness parameter.

8. A device for handling transaction contract disputes, characterized in that: include: an acquisition unit, configured to acquire a transaction contract dispute request, determine M evaluation objects according to the transaction contract dispute request, and acquire dimension data of the M evaluation objects to obtain M groups of dimension data, wherein the transaction contract dispute request is an evaluation request generated based on a transaction contract event, each evaluation object is used to evaluate the nature of the transaction contract event, and each group of dimension data includes N dimension data, where M and N are positive integers; A determination unit, configured to determine, for an evaluation object, a weight coefficient of each dimension data associated with the evaluation object, and determine a time decay parameter of the evaluation object, wherein the time decay parameter is used to characterize a state of the evaluation object when evaluating the transaction contract event; An input unit, for inputting, for an evaluation object, N dimension data associated with weight coefficients and a time decay parameter of the evaluation object into a scoring prediction model to obtain an evaluation score; A selection unit is used to select Y target evaluation objects based on M evaluation scores, wherein after the Y target evaluation objects process the transaction contract event, an evaluation processing result is obtained, and Y is a positive integer.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for handling transaction contract disputes described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The invention comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for handling transaction contract disputes as described in any one of claims 1 to 7.

Images