Transaction dispute processing method and device

Abstract

The embodiment of the invention discloses a transaction dispute processing method and device. According to the method, a user identity verification scheme suitable for the intelligent service robot is provided, the scheme introduces a multi-mode interaction technology to guide two transaction parties to perform efficient communication, an appropriate solution is recommended based on interaction data, and finally a satisfactory consensus is achieved. Through the scheme, on the premise of ensuring fair participation of the two parties, the two transaction parties can be effectively promoted to reach a consensus for processing transaction disputes. The transaction dispute processing device provided by the embodiment of the specification also has the above beneficial effects.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a transaction dispute resolution method and device. Background Art

[0002] With the rapid increase in the number of online transactions, various transaction disputes will arise during online transactions. Currently, the handling of transaction disputes often relies on manual review, that is, users report the target transaction, and then the reviewer on the review side reviews it. Such a review mechanism is not only highly dependent on expert experience, but also time-consuming and inefficient, resulting in long waiting times for users and low user satisfaction. Summary of the invention

[0003] One or more embodiments of the present specification provide a transaction dispute handling method and apparatus, which can automatically handle transaction disputes with extremely high efficiency.

[0004] In a first aspect, a transaction dispute handling method is provided, which is applicable to an intelligent service robot, and the method comprises:

[0005] In response to a user's reporting operation on a target transaction, verifying whether there is a transaction dispute in the target transaction;

[0006] In response to a transaction dispute existing in the target transaction, generating a candidate solution for the target transaction;

[0007] A multimodal online negotiation channel is provided for both parties of the target transaction, and during the negotiation process between the two parties, the intentions of the two parties are analyzed to provide the candidate solutions that meet the preferences of the two parties, so as to encourage the two parties to reach a consensus.

[0008] As an optional implementation manner of the method of the first aspect, in response to a user's reporting operation on a target transaction, verifying whether there is a transaction dispute in the target transaction specifically includes:

[0009] Based on the reported information, a preliminary judgment result is obtained as to whether there is a transaction dispute in the target transaction;

[0010] In response to the preliminary judgment result that there is a transaction dispute in the target transaction, intelligent interactions are performed with both parties of the target transaction respectively, and a final judgment result of whether there is a transaction dispute in the target transaction is obtained based on information collected during the interaction process.

[0011] Specifically, based on the reported information, a preliminary judgment result is obtained as to whether there is a transaction dispute in the target transaction, including:

[0012] extracting key information related to the transaction dispute from the reporting information and the target transaction;

[0013] Based on the key information, a preliminary judgment result is obtained as to whether there is any transaction dispute in the target transaction.

[0014] Specifically, in response to the preliminary judgment result that the target transaction has a transaction dispute, intelligent interactions are performed with both parties of the target transaction, and based on the information collected during the interaction, a final judgment result of whether the target transaction has a transaction dispute is obtained, which specifically includes:

[0015] In the process of intelligently interacting with the transaction parties of the target transaction, respectively, collecting credential information and interaction data provided by the transaction parties;

[0016] Determining the behavioral characteristics of the transaction parties based on the interaction data;

[0017] A final judgment result of whether there is a transaction dispute in the target transaction is obtained according to the behavioral characteristics of the transaction parties and the credential information.

[0018] As an optional implementation manner of the method of the first aspect, in response to a transaction dispute existing in the target transaction, generating a candidate solution for the target transaction specifically includes:

[0019] According to the preset decision logic, the transaction disputes of the target transaction are matched by rules, and according to the rule matching results, one or more solutions are selected from a pre-built solution set to form the selected solution.

[0020] As an optional implementation manner of the method of the first aspect, in response to a transaction dispute existing in the target transaction, generating a candidate solution for the target transaction specifically includes:

[0021] In a pre-built knowledge base, the transaction dispute of the target transaction is matched with the historical cases in the knowledge base, and the candidate solution is determined based on the matching result.

[0022] As an optional implementation manner of the method of the first aspect, the method further includes:

[0023] In response to the consistent selection of the candidate solution by both parties of the target transaction, a transaction dispute resolution agreement is generated.

[0024] As an optional implementation manner of the method of the first aspect, the method further includes:

[0025] Collecting processing data of the intelligent service robot in the process of handling transaction disputes;

[0026] Collect user feedback data on the transaction dispute handling process and results;

[0027] The intelligent service robot is optimized according to the processing data and the feedback data.

[0028] In a second aspect, a transaction dispute handling device is provided, which is applicable to an intelligent service robot, and the device comprises:

[0029] A data acquisition module configured to acquire reporting information submitted by a user regarding a target transaction;

[0030] a determination module, configured to verify whether there is a transaction dispute in the target transaction in response to a user's reporting operation on the target transaction;

[0031] a solution suggestion module, in response to a transaction dispute existing in the target transaction, generating a candidate solution for the target transaction;

[0032] The consensus guidance and execution module is configured to provide a multimodal online negotiation channel for the two parties of the target transaction, and during the negotiation process between the two parties, analyze the intentions of the two parties, and provide the candidate solutions that meet the preferences of the two parties, so as to encourage the two parties to reach a consensus.

[0033] As an optional implementation of the device of the second aspect, the determination module includes a reporting information processing and judgment module and a two-way confirmation module;

[0034] The reporting information processing and judgment module is configured to obtain a preliminary judgment result on whether there is a transaction dispute in the target transaction according to the reporting information;

[0035] The two-way confirmation module is configured to, in response to the preliminary judgment result that the target transaction has a transaction dispute, intelligently interact with the two parties of the target transaction respectively, and obtain a final judgment result of whether the target transaction has a transaction dispute based on information collected during the interaction process.

[0036] As an optional implementation manner of the device described in the second aspect, the consensus guidance and execution module is also used to generate a transaction dispute resolution agreement in response to the consistent selection of the candidate solution by the two parties to the target transaction.

[0037] As an optional implementation manner of the device according to the second aspect, the device further includes a user experience optimization module, and the user experience optimization module is configured as follows:

[0038] Collecting processing data of the intelligent service robot in the process of handling transaction disputes;

[0039] Collect user feedback data on the transaction dispute handling process and results;

[0040] The intelligent service robot is optimized according to the processing data and the feedback data.

[0041] In a third aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned transaction dispute resolution method is implemented.

[0042] In a fourth aspect, an electronic device is provided, including:

[0043] One or more processors; and a memory associated with the one or more processors, the memory being used to store program instructions, and the program instructions, when read and executed by the one or more processors, execute the above-mentioned transaction dispute handling method.

[0044] The beneficial effect of the user identity verification method described in one or more embodiments of this specification is that the method provides a user identity verification solution suitable for intelligent service robots, which introduces multi-modal interaction technology to guide the transaction parties to communicate efficiently, and recommend appropriate solutions based on interaction data, and finally reach a satisfactory consensus. Through this solution, it is possible to effectively promote the transaction parties to reach a consensus on handling transaction disputes under the premise of ensuring fair participation of both parties.

[0045] The user identity verification device described in the embodiments of this specification also has the above-mentioned beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 It is a flow chart of a transaction dispute handling method provided for one or more embodiments of this specification.

[0048] Figure 2 A schematic diagram of the structure of a transaction dispute resolution device provided in one or more embodiments of this specification.

[0049] Figure 3 A schematic diagram of the structure of a determination module provided for one or more embodiments of this specification.

[0050] Figure 4 A schematic diagram of the workflow of a two-way confirmation module provided in one or more embodiments of this specification.

[0051] Figure 5 A schematic diagram of the workflow of a solution suggestion module provided for one or more embodiments of this specification.

[0052] Figure 6 One or more embodiments of this specification provide a workflow diagram of a consensus guidance and execution module.

[0053] Figure 7 A schematic diagram of the structure of an electronic device provided for one or more embodiments of this specification. DETAILED DESCRIPTION

[0054] First of all, it should be noted that the terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise.

[0055] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Therefore, it should be recognized by those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0056] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0057] In the digital age, the number of online transactions has increased rapidly, among which there are many online disputes and even online fraud, which have brought significant risks and losses to enterprises and users. The traditional online dispute handling process often relies on cumbersome manual review, which is not only time-consuming and inefficient, but also relies on expert experience, and user satisfaction is not high.

[0058] In view of this, one or more embodiments of this specification propose a transaction dispute handling method and device, which can automatically and efficiently handle transaction disputes. This solution can be used as an auxiliary tool for manual review and combined with manual review to improve the efficiency of handling transaction disputes.

[0059] The transaction dispute handling method and device described in one or more embodiments of this specification will be further described in detail below in conjunction with the drawings and specific embodiments of the specification, but this detailed description does not constitute a limitation on the embodiments of this specification.

[0060] Please refer to Figure 1 , Figure 1 This is a flow chart of a transaction dispute handling method proposed in one or more embodiments of this specification, which is applicable to an intelligent service robot. Figure 1 As shown, the method specifically includes steps S100 to S104.

[0061] S100: In response to a user's reporting operation on a target transaction, verify whether there is any transaction dispute in the target transaction.

[0062] When a user reports a target transaction, the first thing to do is to verify whether the target transaction actually involves a transaction dispute. Take fraud disputes as an example. When one user reports another party for fraud, on the one hand, the victim needs to be protected and fraud prevention must be prevented; on the other hand, it is also necessary to avoid falsely accusing innocent parties. It is extremely challenging to distinguish between a normal commodity transaction dispute and real fraud. This requires not only an in-depth understanding of each transaction, but also a mediation process that ensures transparency and fairness.

[0063] Based on the above purpose, in some implementations, the following methods can be used to verify the authenticity of transaction disputes:

[0064] S1000: Based on the reported information, a preliminary judgment result of whether the target transaction has a transaction dispute is obtained. Specifically, natural language processing can be used to analyze the content of the reported information to identify potential fraudulent behavior. It can extract key information from the original text of the reported information submitted by the user, and can also extract the time of the transaction event, the account involved, the transaction characteristics, etc., and convert this information into structured data for further analysis. Then, based on the key information and these structured data, combined with specific transaction dispute judgment logic rules, or combined with a pre-trained transaction dispute identification model, a preliminary judgment result of whether the target transaction has a transaction dispute is obtained.

[0065] For example, NLP can be used to perform sentiment analysis and keyword extraction on the original text of the report information to determine whether the text contains fraud characteristics and patterns, and then combine the time of the transaction event, the accounts involved, the transaction characteristics, etc. to make preliminary judgments and filtering of fraud.

[0066] S1002: In response to a preliminary judgment result that a transaction dispute exists in the target transaction, intelligent interactions are performed with both parties of the target transaction, and a final judgment result of whether a transaction dispute exists in the target transaction is obtained based on information collected during the interaction process.

[0067] This step S1002 is a two-way confirmation process, that is, the intelligent service robot needs to interact intelligently with both parties of the transaction, that is, the reporting party and the reported party, to verify the factual details and specific circumstances of the reported target transaction. By conducting two-way confirmation with both parties of the transaction, it is ensured that each party has the opportunity to express their own views and evidence, thereby verifying the authenticity of the report and providing necessary information support for subsequent solutions.

[0068] Specifically, intelligent service robots can use natural language understanding and generation technology to have natural and smooth conversations with users. At the same time, they provide users with a way to upload evidence (such as transaction records, screenshots of conversations, etc.) to collect specific information about the report or the target transaction, and ensure the integrity and traceability of the information. For example, intelligent service robots can collect information such as the reason for the report, transaction vouchers, and transaction process from the reporter to determine whether it constitutes fraud. Intelligent service robots can also inform the reported party of the report, and then collect information such as the reported party's operating conditions, business model, and whether the reported party recognizes that there is a dispute in the transaction.

[0069] In some implementations, the behavioral characteristics of the transaction parties in the interaction, such as reaction time and question avoidance, can also be analyzed. These data may be helpful in judging the situation. For example, NLP algorithms and speech recognition algorithms can be used to determine whether the user is lying. Alternatively, it can be determined whether there is fraud based on whether the user chooses to answer certain questions. If the reported party refuses to answer some transaction-related questions, it is more likely that the target transaction involves fraud or business risk.

[0070] Through the above-mentioned two-way confirmation process, we can ensure that we have sufficient information before formulating a solution, reduce misjudgments caused by incomplete information, and avoid affecting the accuracy of the judgment of the authenticity of the dispute based on the report of only one party.

[0071] In addition, the information collected during the two-way confirmation process will also be confirmed in combination with actual data and information. For example, the information provided by both parties in the two-way confirmation process can be automatically matched and compared by an intelligent customer service robot to identify inconsistencies and suspicious points, and then verified in combination with the actual data of the transaction. The verification mechanism can increase the accuracy of the processing results, thereby enhancing users' trust in the system. It ensures that both parties to the transaction can participate in the confirmation process, increase the fairness and transparency of the system processing, and reduce user complaints caused by unfair processing.

[0072] On the other hand, during the two-way confirmation process, effective communication can also help both parties to the transaction understand each other's position, which may lead to preliminary reconciliation or safety education in the process.

[0073] S102: In response to a transaction dispute existing in the target transaction, generating a candidate solution for the target transaction.

[0074] This step S102 is the next step after confirming that there is a transaction dispute in the target transaction. In this step S102, the expert knowledge base and built-in decision logic can be used to recommend appropriate solutions. These solutions include but are not limited to refunds, account restrictions, evidence, user education or other actions.

[0075] The above decision logic can be implemented through rule matching, that is, matching the relevant information of the target transaction with rules, and selecting one or more solutions from the pre-built solution set according to the matching conditions satisfied by the target transaction to form a candidate solution. For example, if the target transaction is judged to meet the fraud conditions through rule matching, and the reported party agrees to refund, then the candidate solution is determined to be refunding the reported party and removing the account control of the reported party.

[0076] The above-mentioned expert knowledge base may include information such as laws and regulations, historical cases, industry practices, and expert experience.

[0077] In some implementations, the transaction disputes of the target transaction may be matched with historical cases in the expert knowledge base, and after similar historical cases are found, candidate solutions for the target transaction may be constructed based on the solutions of the historical cases.

[0078] In some implementations, historical cases in the expert knowledge base can also be used to train a machine learning model, which can be used to match relevant information of the target transaction with pre-built solutions to generate a recommended list of solutions. Based on the priority of each solution in the recommended list, the candidate solutions can be determined.

[0079] Preferably, the above-mentioned decision logic and machine learning model can be used in combination to complement each other. That is, for transaction disputes that are not covered by the matching rules of the decision logic, the machine learning model can be used to assist in selecting candidate solutions.

[0080] In addition, the above-mentioned decision-making logic and machine learning models can be used in combination to decide on multiple solutions and form a solution set. This can minimize risks and prevent potential losses and legal disputes by increasing the diversity of solutions.

[0081] S104: Provide a multimodal online negotiation channel for both parties of the target transaction, and during the negotiation process between the two parties, analyze the intentions of the two parties and provide candidate solutions that meet the preferences of the two parties, so as to encourage the two parties to reach a consensus.

[0082] The above-mentioned multimodal online negotiation channels can support communication methods including but not limited to video, text, and voice, so that the two parties to the transaction can interact directly online, making communication more intuitive and efficient.

[0083] In the online negotiation channel, users can use a variety of interactive methods to achieve consensus guidance under the guidance of intelligent robot services. Specifically, the intelligent service robot can collect the content of online communication between the two parties to the transaction, and then identify the user's intention through the intention analysis algorithm, so as to select candidate solutions that are more in line with the user's preferences and recommend them to the two parties to the transaction.

[0084] The recommendation form of the candidate solutions can be adaptively set according to the needs, and this embodiment does not limit this. For example, graphic options about candidate solutions can be generated during the video conference mediation process to facilitate the transaction parties to choose a solution that satisfies both parties after negotiation. If the solution is confirmed by the transaction parties, it means that the two parties have reached a consensus.

[0085] In some implementations, after the transaction parties reach a consensus on a solution, the intelligent service robot can generate a corresponding transaction dispute resolution agreement for both parties to sign and confirm.

[0086] Specifically, these transaction dispute resolution agreements can be generated based on pre-built agreement templates. After the two parties to the transaction reach a consensus, they can select an agreement template that matches the transaction dispute. After filling in the information of the two parties to the transaction in the template, they can obtain the transaction dispute resolution agreement.

[0087] In some embodiments, the transaction dispute handling method may further include an intelligent service robot optimization solution. Specifically, the processing data of the intelligent service robot in the process of handling transaction disputes may be collected, and the user's feedback data on the transaction dispute handling process and the handling results may be collected, and the intelligent service robot may be optimized based on the processing data and feedback data.

[0088] For example, you can evaluate the user's behavior patterns when using the system, such as which functions are frequently used and which steps cause users to exit or abandon the operation, and optimize the service process. You can also set up a mechanism to encourage users to provide feedback after the interaction, such as a rating system, questionnaire or direct text feedback, and optimize the corresponding process or function through user feedback information.

[0089] Through user experience optimization solutions, intelligent service robots can not only provide users with instant transaction dispute resolution services, but also improve themselves based on users' actual experience to provide higher quality services.

[0090] The above is the transaction dispute handling method described in this embodiment. From the above content, it can be seen that the method introduces multi-modal interaction technology to guide the transaction parties to communicate efficiently, and recommend appropriate solutions based on interaction data, and finally reach a satisfactory consensus. Through this solution, it is possible to effectively promote the transaction parties to reach a consensus on handling transaction disputes while ensuring fair participation of both parties.

[0091] Corresponding to the above transaction dispute handling method, this embodiment also provides a transaction dispute handling device, which is suitable for an intelligent service robot. Figure 2 , Figure 2 FIG. 1 is a schematic diagram of a transaction dispute handling device proposed in one or more embodiments of this specification. Figure 2 As shown, the device comprises:

[0092] The data acquisition module 201 is configured to acquire reporting information submitted by a user regarding a target transaction.

[0093] The determination module 202 is configured to verify whether there is a transaction dispute in the target transaction in response to a user's reporting operation on the target transaction.

[0094] The solution suggestion module 203 generates a candidate solution for the target transaction in response to a transaction dispute existing in the target transaction.

[0095] The consensus guidance and execution module 204 is configured to provide a multimodal online negotiation channel for the two parties of the target transaction, and during the negotiation process between the two parties, analyze the intentions of the two parties and provide candidate solutions that meet the preferences of the two parties to encourage the two parties to reach a consensus.

[0096] Regarding the above-mentioned data acquisition module 201, the module mainly responds to the user's report request and collects specific information about the target transaction from the user, such as transaction voucher screenshots, transaction time, transaction content and other information.

[0097] With respect to the above-mentioned determination module 202, the module is specifically used to obtain a preliminary judgment result of whether there is a transaction dispute in the target transaction based on the reported information. When the preliminary judgment result is that there is a transaction dispute in the target transaction, the determination module 202 performs intelligent interaction with the transaction parties of the target transaction respectively, and obtains a final judgment result of whether there is a transaction dispute in the target transaction based on the information collected during the interaction process.

[0098] Please refer to Figure 3 , Figure 3The specific structure diagram of the determination module 202 is shown.

[0099] The determination module 202 may specifically include a reporting information processing and judgment module 2021. The reporting information processing and judgment module 2021 is used to obtain a preliminary judgment result on whether there is a transaction dispute in the target transaction based on the reporting information. Specifically, the reporting information processing and judgment module 2021 can use natural language processing to analyze the content of the reporting information and identify potential fraudulent behavior. It can extract key information from the original text of the reporting information submitted by the user, and can also extract the time of occurrence, the accounts involved, the transaction characteristics, etc. in the transaction event, and convert this information into structured data for further analysis. Then, based on the key information and these structured data, combined with specific transaction dispute judgment logic rules, or combined with a pre-trained transaction dispute identification model, a preliminary judgment result on whether there is a transaction dispute in the target transaction is obtained.

[0100] For example, NLP can be used to perform sentiment analysis and keyword extraction on the original text of the report information to determine whether the text contains fraud characteristics and patterns, and then combine the time of the transaction event, the accounts involved, the transaction characteristics, etc. to make preliminary judgments and filtering of fraud.

[0101] The determination module 202 may further include a two-way confirmation module 2022. The two-way confirmation module 2022 is mainly used to respond to the preliminary judgment result that the target transaction has a transaction dispute, and to perform intelligent interaction with the transaction parties of the target transaction respectively, and obtain a final judgment result of whether the target transaction has a transaction dispute based on the information collected during the interaction process.

[0102] Please refer to Figure 4 , Figure 4 The workflow of the two-way confirmation module 2022 is schematically shown. Figure 4 As shown, the two-way confirmation module 2022 provides intelligent interaction services, and during the intelligent interaction process, collects credentials and compares information, and finally makes decisions based on the interaction behaviors with both parties to the transaction to determine the authenticity of the transaction dispute.

[0103] Specifically, the two-way confirmation module 2022 needs to intelligently interact with both parties of the transaction, that is, the reporting party and the reported party, to verify the factual details and specific circumstances of the reported target transaction. By conducting two-way confirmation with both parties of the transaction, it is ensured that each party has the opportunity to express their own views and evidence, thereby verifying the authenticity of the report and providing necessary information support for subsequent solutions.

[0104] The two-way confirmation module 2022 can use natural language understanding and generation technology to conduct natural and smooth conversations with users. At the same time, it provides users with a way to upload credentials (such as transaction records, screenshots of conversations, etc.) to collect specific information about the report or the target transaction, and ensure the integrity and traceability of the information. For example, the intelligent service robot can collect information such as the reason for the report, transaction vouchers, and transaction process from the reporter to determine whether it constitutes fraud. The intelligent service robot can also inform the reported party of the report, and then collect information such as the reported party's business situation, business model, and whether it recognizes that there is a dispute in the transaction.

[0105] The two-way confirmation module 222 can also analyze the behavioral characteristics of the transaction parties in the interaction, such as reaction time and question avoidance. These data may be helpful in judging the situation. For example, NLP algorithms and speech recognition algorithms can be used to determine whether the user is lying. Alternatively, it can be determined whether there is fraud based on whether the user chooses to answer some questions. If the reported party refuses to answer some transaction-related questions, it is more likely that the target transaction has fraud or business risk behavior.

[0106] In addition, the information collected by the two-way confirmation module 2022 during the two-way confirmation process will also be confirmed in combination with actual data and information. For example, the information provided by the two parties to the transaction during the two-way confirmation process can be automatically matched and compared by an intelligent customer service robot to identify inconsistencies and suspicious points, and then verified in combination with the actual data of the transaction. Through the verification mechanism, the accuracy of the processing results can be increased, thereby enhancing the user's trust in the system. Ensure that both parties to the transaction can participate in the confirmation process, increase the fairness and transparency of the system processing, and reduce user complaints caused by unfair processing.

[0107] On the other hand, during the two-way confirmation process, the two-way confirmation module 2022 can also assist the transaction parties in understanding each other's positions through effective communication, which may facilitate a preliminary settlement or conduct safety education in the process.

[0108] Regarding the above-mentioned solution suggestion module 203, this module is triggered after confirming that there is a transaction dispute in the target transaction. The workflow of the solution suggestion module 203 is as follows: Figure 5 As shown, in the solution suggestion module 203, the expert knowledge base and built-in decision logic can be used to recommend appropriate solutions. These solutions include but are not limited to refunds, account restrictions, evidence, user education or other actions.

[0109] The above decision logic can be implemented through rule matching, that is, matching the relevant information of the target transaction with rules, and selecting one or more solutions from the pre-built solution set according to the matching conditions satisfied by the target transaction to form a candidate solution. For example, if the target transaction is judged to meet the fraud conditions through rule matching, and the reported party agrees to refund, then the candidate solution is determined to be refunding the reported party and removing the account control of the reported party.

[0110] The above-mentioned expert knowledge base may include information such as laws and regulations, historical cases, industry practices, and expert experience.

[0111] In some implementations, the solution suggestion module 203 may match the transaction dispute of the target transaction with historical cases in the expert knowledge base, and after finding similar historical cases, construct candidate solutions for the target transaction based on the solutions of the historical cases.

[0112] In some implementations, the solution suggestion module 203 may also use historical cases in the expert knowledge base to train a machine learning model, and the machine learning model may be used to match the relevant information of the target transaction with the pre-built solutions, thereby generating a recommended list of solutions. Based on the priority of each solution in the recommended list, the candidate solutions mentioned above may be determined.

[0113] Preferably, the solution suggestion module 203 can also make comprehensive use of the above-mentioned decision logic and machine learning model for complementation, that is, for transaction disputes that are not covered by the matching rules of the decision logic, the machine learning model can be used to assist in selecting candidate solutions.

[0114] In addition, the solution suggestion module 203 can also make comprehensive use of the above-mentioned decision logic and machine learning model to decide on multiple solutions to form a solution set, thereby minimizing risks and preventing potential losses and legal disputes by increasing the diversity of solutions.

[0115] For the above consensus guidance and execution module 204, please refer to Figure 6 , Figure 6 The figure shows the workflow of the consensus guidance and execution module 204. The consensus guidance and execution module 204 provides a multi-modal interaction channel for both parties of the transaction, and guides both parties of the transaction to reach a consensus through the built-in strategy process and solution recommendation process during the interaction between the two parties of the transaction.

[0116] Specifically, the multimodal online negotiation channel provided by the consensus guidance and execution module 204 can support communication methods including but not limited to video, text and voice, so that the two parties to the transaction can interact directly online, making communication more intuitive and efficient.

[0117] In the online negotiation channel, users can use a variety of interactive methods to achieve consensus guidance under the guidance of intelligent robot services. Specifically, the intelligent service robot can collect the content of online communication between the two parties to the transaction, and then identify the user's intention through the intention analysis algorithm, so as to select candidate solutions that are more in line with the user's preferences and recommend them to the two parties to the transaction.

[0118] The recommendation form of the candidate solutions can be adaptively set according to the needs, and this embodiment does not limit this. For example, graphic options about candidate solutions can be generated during the video conference mediation process to facilitate the transaction parties to choose a solution that satisfies both parties after negotiation. If the solution is confirmed by the transaction parties, it means that the two parties have reached a consensus.

[0119] In some implementations, after both parties to the transaction reach a consensus on a solution, the consensus guidance and execution module 204 may also generate a corresponding transaction dispute resolution agreement for both parties to sign and confirm.

[0120] Specifically, these transaction dispute resolution agreements can be generated based on pre-built agreement templates. After the two parties to the transaction reach a consensus, they can select an agreement template that matches the transaction dispute. After filling in the information of the two parties to the transaction in the template, they can obtain the transaction dispute resolution agreement.

[0121] Please continue to refer to Figure 2 In some implementations, the transaction dispute handling device may further include a user experience optimization module 205. Specifically, the user experience optimization module 205 may collect processing data of the intelligent service robot in the process of handling transaction disputes, collect user feedback data on the transaction dispute handling process and processing results, and optimize the intelligent service robot based on the processing data and feedback data.

[0122] For example, the user experience optimization module 205 can evaluate the user's behavior patterns during the use of the system, such as which functions are frequently used and which steps cause users to exit or abandon the operation, and optimize the service process. A mechanism can also be established to encourage users to provide feedback after the interaction, such as a rating system, questionnaire or direct text feedback, and optimize the corresponding process or function through user feedback information.

[0123] For the above-mentioned transaction dispute handling device, taking a module as an example of a software functional unit, the data acquisition module 201 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above-mentioned computing instance may be one or more. For example, the data acquisition module 201 may include code running on multiple hosts / virtual machines / containers. The multiple hosts / virtual machines / containers used to run the code may be distributed in the same region (region) or in different regions. Furthermore, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including one data center or multiple data centers with close geographical locations. Among them, usually a region may include multiple AZs.

[0124] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Usually, a VPC is set up in a region. For cross-region communication between two VPCs in the same region and between VPCs in different regions, a communication gateway needs to be set up in each VPC to achieve interconnection between VPCs through the communication gateway.

[0125] As an example of a hardware functional unit, the data acquisition module 201 may include at least one computing device, such as a server, etc. Alternatively, the data acquisition module 201 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0126] The multiple computing devices included in the data acquisition module 201 can be distributed in the same region or in different regions. The multiple computing devices included in the data acquisition module 201 can be distributed in the same AZ or in different AZs. Similarly, the multiple computing devices included in the data acquisition module 201 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0127] In other embodiments, the data acquisition module 201 can be used to execute any step in the transaction dispute handling method described above, the determination module 202 can be used to execute any step in the transaction dispute handling method described above, the solution suggestion module 203 can be used to execute any step in the transaction dispute handling method described above, the consensus guidance and execution module 204 can be used to execute any step in the transaction dispute handling method described above, and the user experience optimization module 205 can be used to execute any step in the transaction dispute handling method described above. The steps that the data acquisition module 201, the determination module 202, the solution suggestion module 203, the consensus guidance and execution module 204, and the user experience optimization module 205 are responsible for implementing can be specified as needed, and the data acquisition module 201, the determination module 202, the solution suggestion module 203, the consensus guidance and execution module 204, and the user experience optimization module 205 respectively implement different steps in the transaction dispute handling method described above to realize all the functions of the transaction dispute handling device described above.

[0128] In this implementation, the transaction dispute handling apparatus may also be applied to computing devices such as computers and servers, or to a computing device cluster including at least one computing device, to implement the transaction dispute handling function.

[0129] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned transaction dispute resolution method is implemented.

[0130] Computer-readable storage media include permanent and non-permanent, removable and non-removable media that can store information by any method or technology. 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 disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmitting 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.

[0131] This embodiment also provides an electronic device, including:

[0132] One or more processors; and a memory associated with the one or more processors, the memory being used to store program instructions, which, when read and executed by the one or more processors, implement the above-mentioned transaction dispute handling method.

[0133] Please refer to Figure 7 , Figure 7 A structural schematic diagram of the above-mentioned electronic device is shown. The electronic device includes a bus 701, a processor 702, a memory 703 and a communication interface 604. The memory 703 stores a computer program, and when the computer program runs on the processor 702, the processor 702 executes the specific steps in the above-mentioned transaction dispute handling method. It should be understood that the present application does not limit the number of processors and memories in the electronic device.

[0134] The bus 701 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus 701 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 The bus 701 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 701 may include a path for transmitting information between various components of the terminal device (for example, the processor 702, the memory 703 and the communication interface 704).

[0135] The processor 702 may include any one or more of a processor such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0136] The memory 703 may include a volatile memory, such as a random access memory (RAM). The memory 703 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0137] The communication interface 704 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the electronic device and other devices or a communication network.

[0138] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0139] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0140] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0141] It should be noted that the above examples are only specific embodiments of the present invention. Obviously, the present invention is not limited to the above examples, and there are many similar variations. All variations directly derived or associated from the contents disclosed by the technicians in this field should fall within the protection scope of the present invention.

Claims

1. A transaction dispute handling method, applicable to an intelligent service robot, comprising: In response to a user's reporting operation on a target transaction, verifying whether there is a transaction dispute in the target transaction; In response to a transaction dispute existing in the target transaction, generating a candidate solution for the target transaction; A multimodal online negotiation channel is provided for both parties of the target transaction, and during the negotiation process between the two parties, the intentions of the two parties are analyzed to provide the candidate solutions that meet the preferences of the two parties, so as to encourage the two parties to reach a consensus.

2. The method according to claim 1, in response to a user's reporting operation on a target transaction, verifying whether there is a transaction dispute in the target transaction, specifically comprising: Based on the reported information, a preliminary judgment result is obtained as to whether there is a transaction dispute in the target transaction; In response to the preliminary judgment result that there is a transaction dispute in the target transaction, intelligent interactions are performed with both parties of the target transaction respectively, and a final judgment result of whether there is a transaction dispute in the target transaction is obtained based on information collected during the interaction process.

3. According to the method of claim 2, obtaining a preliminary judgment result of whether the target transaction involves a transaction dispute based on the reporting information, specifically comprising: extracting key information related to the transaction dispute from the reporting information and the target transaction; Based on the key information, a preliminary judgment result is obtained as to whether there is any transaction dispute in the target transaction.

4. The method according to claim 2, in response to the preliminary judgment result that the target transaction has a transaction dispute, intelligently interacting with both parties of the target transaction, and obtaining a final judgment result of whether the target transaction has a transaction dispute based on information collected during the interaction, specifically comprising: In the process of intelligently interacting with the transaction parties of the target transaction, respectively, collecting credential information and interaction data provided by the transaction parties; Determining the behavioral characteristics of the transaction parties based on the interaction data; A final judgment result of whether there is a transaction dispute in the target transaction is obtained according to the behavioral characteristics of the transaction parties and the credential information.

5. The method according to claim 1, in response to the target transaction having a transaction dispute, generating a candidate solution for the target transaction, specifically comprising: According to the preset decision logic, the transaction disputes of the target transaction are matched by rules, and according to the rule matching results, one or more solutions are selected from a pre-built solution set to form the selected solution.

6. The method according to claim 1, in response to the target transaction having a transaction dispute, generating a candidate solution for the target transaction, specifically comprising: In a pre-built knowledge base, the transaction dispute of the target transaction is matched with the historical cases in the knowledge base, and the candidate solution is determined based on the matching result.

7. The method according to claim 1, further comprising: In response to the consistent selection of the candidate solution by both parties of the target transaction, a transaction dispute resolution agreement is generated.

8. The method according to claim 1, further comprising: Collecting processing data of the intelligent service robot in the process of handling transaction disputes; Collect user feedback data on the transaction dispute handling process and results; The intelligent service robot is optimized according to the processing data and the feedback data.

9. A transaction dispute handling device, applicable to an intelligent service robot, comprising: A data acquisition module configured to acquire reporting information submitted by a user regarding a target transaction; a determination module, configured to verify whether there is a transaction dispute in the target transaction in response to a user's reporting operation on the target transaction; a solution suggestion module, in response to a transaction dispute existing in the target transaction, generating a candidate solution for the target transaction; The consensus guidance and execution module is configured to provide a multimodal online negotiation channel for the two parties of the target transaction, and during the negotiation process between the two parties, analyze the intentions of the two parties, and provide the candidate solutions that meet the preferences of the two parties, so as to encourage the two parties to reach a consensus.

10. The device according to claim 9, wherein the determination module comprises a reporting information processing and judgment module and a two-way confirmation module; The reporting information processing and judgment module is configured to obtain a preliminary judgment result on whether there is a transaction dispute in the target transaction according to the reporting information; The two-way confirmation module is configured to, in response to the preliminary judgment result that the target transaction has a transaction dispute, intelligently interact with the two parties of the target transaction respectively, and obtain a final judgment result of whether the target transaction has a transaction dispute based on information collected during the interaction process.

11. According to the device of claim 9, the consensus guidance and execution module is also used to generate a transaction dispute resolution agreement in response to the consistent selection of the candidate solution by the two parties to the target transaction.

12. The device according to claim 9, further comprising a user experience optimization module, wherein the user experience optimization module is configured to: Collecting processing data of the intelligent service robot in the process of handling transaction disputes; Collect user feedback data on the transaction dispute handling process and results; The intelligent service robot is optimized according to the processing data and the feedback data.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 8.

14. An electronic device comprising: one or more processors; And a memory associated with the one or more processors, the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, the method according to any one of claims 1 to 8 is executed.

Images