Conversation processing method and system, computing device and storage medium

Abstract

The embodiment of the invention provides a dialogue processing method and system, computing equipment and a storage medium, and the method comprises the steps: receiving a question processing request which carries the question information of a to-be-processed question; determining a target problem processing end corresponding to the to-be-processed problem according to the problem information, generating first dialogue data corresponding to the to-be-processed problem, and sending the first dialogue data to the target problem processing end, the first dialogue data is used for guiding the target problem processing end to process the to-be-processed problem; and receiving second dialogue data returned by the target problem processing end for the first dialogue data, and determining a problem processing scheme corresponding to the to-be-processed problem according to the first dialogue data and the second dialogue data.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of artificial intelligence technology, and in particular to a dialogue processing method and system, a computing device, and a storage medium. Background Art

[0002] Currently, when e-commerce platform customer service handles user issues, they often encounter disputes between merchants and users. They need to analyze the user's shopping and after-sales process to identify the existing problems and solutions, and then communicate with both the merchant and the user to resolve the dispute. However, negotiations between platform customer service and merchants are often complex and time-consuming. First, they need to find a merchant customer service representative who can handle the dispute, and then communicate and negotiate a solution with the merchant customer service representative. The entire negotiation process consumes the platform customer service's energy, and the efficiency of handling dispute issues is low. As a result, user issues take a long time to resolve, affecting the user experience. Summary of the Invention

[0003] In view of this, embodiments of this specification provide a method for processing a conversation. One or more embodiments of this specification also relate to a conversation processing apparatus, a conversation processing system, a computing device, a computer-readable storage medium, and a computer program product to address technical deficiencies in the prior art.

[0004] According to a first aspect of an embodiment of this specification, a conversation processing method is provided, including: receiving a problem handling request, wherein the problem handling request carries problem information of a problem to be handled; Determining a target problem processing terminal corresponding to the problem to be processed based on the problem information, generating first dialogue data corresponding to the problem to be processed, and sending the first dialogue data to the target problem processing terminal, wherein the first dialogue data is used to guide the target problem processing terminal to process the problem to be processed; Receive second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine a problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

[0005] According to a second aspect of the embodiments of this specification, a conversation processing device is provided, including: A receiving module is configured to receive a problem handling request, wherein the problem handling request carries problem information of a problem to be handled; a generation module configured to determine a target problem processing terminal corresponding to the problem to be processed based on the problem information, generate first dialogue data corresponding to the problem to be processed, and send the first dialogue data to the target problem processing terminal, wherein the first dialogue data is used to guide the target problem processing terminal to process the problem to be processed; The determination module is configured to receive the second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine the problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

[0006] According to a third aspect of the embodiments of this specification, a dialogue processing system is provided, including an intelligent decision-making unit, wherein: The intelligent decision-making unit is used to receive a problem processing request, wherein the problem processing request carries problem information of the problem to be processed; determine the target problem processing end corresponding to the problem to be processed based on the problem information, generate first dialogue data corresponding to the problem to be processed, and send the first dialogue data to the target problem processing end, wherein the first dialogue data is used to guide the target problem processing end to process the problem to be processed; receive second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine the problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

[0007] According to a fourth aspect of the embodiments of this specification, a computing device is provided, including: memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the above-mentioned dialogue processing method are implemented.

[0008] According to a fifth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores a computer program / instruction, and when the computer program / instruction is executed by a processor, the steps of the above-mentioned dialogue processing method are implemented.

[0009] According to a sixth aspect of the embodiments of this specification, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the above-mentioned dialogue processing method when executed by a processor.

[0010] An embodiment of the present specification provides a dialogue processing method, including: receiving a problem processing request, wherein the problem processing request carries problem information of a problem to be processed; determining a target problem processing end corresponding to the problem to be processed based on the problem information, generating first dialogue data corresponding to the problem to be processed, and sending the first dialogue data to the target problem processing end, wherein the first dialogue data is used to guide the target problem processing end to process the problem to be processed; receiving second dialogue data returned by the target problem processing end in response to the first dialogue data, and determining a problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

[0011] In the above method, after receiving the problem handling request, the target problem processing end corresponding to the problem to be handled can be determined according to the problem information of the problem to be handled carried in the problem handling request, and the first dialogue data corresponding to the problem to be handled can be generated, and the first dialogue data can be sent to the target problem processing end, and the first dialogue data can be used to guide the target problem processing end to handle the problem to be handled, and the second dialogue data returned by the target problem processing end for the first dialogue data can be received. According to the first dialogue data and the second dialogue data, the problem handling solution for the problem to be handled is determined, and by entrusting the negotiation of the problem handling solution to the intelligent agent, and enabling the intelligent agent to generate the first dialogue data to guide the target problem processing end to handle the problem to be handled, the problem can be solved, the labor cost can be reduced, and the problem solving efficiency can be improved, thereby ensuring the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a schematic diagram of an application scenario of a conversation processing method provided by an embodiment of this specification; Figure 2 This is a flow chart of a conversation processing method provided by one embodiment of this specification; Figure 3 This is a schematic diagram of a display interface displayed by an e-commerce platform to a human customer service representative of a conversation processing method provided in one embodiment of this specification; Figure 4 This is a schematic diagram of a display interface showing a negotiation process in a dialogue processing method provided by an embodiment of this specification; Figure 5 This is a technical link diagram of a conversation processing method provided by an embodiment of this specification; Figure 6 This is a flowchart of a process of a conversation processing method provided by one embodiment of this specification; Figure 7 This is a structural diagram of a conversation processing device provided by one embodiment of this specification; Figure 8This is a structural block diagram of a computing device provided by one embodiment of this specification. DETAILED DESCRIPTION

[0013] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0014] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0015] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0016] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0017] First, the terms involved in one or more embodiments of this specification are explained.

[0018] Agent: A concept widely used in artificial intelligence and computer science, it refers to an entity that can perceive its environment and influence it by performing actions. Agents can be software programs, robots, or other types of automated systems. They are typically designed to solve specific problems or complete specific tasks and can operate in a variety of environments, such as the internet, the physical world, or simulations.

[0019] In this specification, a conversation processing method is provided. This specification also involves a conversation processing device, a conversation processing system, a computing device, a computer-readable storage medium, and a computer program product, which are described in detail one by one in the following embodiments.

[0020] See also Figure 1 , Figure 1 A schematic diagram of an application scenario of a conversation processing method provided according to an embodiment of this specification is shown. The conversation processing method includes the following steps.

[0021] A problem handling request is received, wherein the problem handling request carries problem information of a problem to be handled.

[0022] Determine the target problem processing end corresponding to the problem to be processed based on the problem information, generate first dialogue data corresponding to the problem to be processed, and send the first dialogue data to the target problem processing end, wherein the first dialogue data is used to guide the target problem processing end to process the problem to be processed.

[0023] Receive second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine a problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

[0024] like Figure 1 As shown, Figure 1 It includes a terminal device 102 and an intelligent decision-making unit 104.

[0025] During specific implementation, the platform manual customer service of the e-commerce platform initiates a problem processing request to the intelligent decision-making unit 104 through the terminal side device 102. The intelligent decision-making unit 104 determines the target problem processing end corresponding to the problem to be processed based on the problem information of the problem to be processed carried in the problem processing request, and generates first dialogue data corresponding to the problem to be processed, and sends the first dialogue data to the target problem processing end, uses the first dialogue data to guide the target problem processing end to process the problem to be processed, and receives the second dialogue data returned by the target problem processing end for the first dialogue data. According to the first dialogue data and the second dialogue data, the problem processing solution for the problem to be processed is determined, and the intelligent decision-making unit 104 can send the problem processing solution to the terminal side device 102. The terminal side device 102 can display the problem processing solution to the platform manual customer service, and the platform manual customer service decides whether to send the problem processing solution to the platform user later, or the intelligent decision-making unit 104 can also directly send the problem processing solution to the platform user. By entrusting the negotiation of problem-solving solutions to the intelligent decision-making unit and enabling the intelligent decision-making unit to generate first dialogue data to guide the target problem processing end to handle the pending problems, the problem can be solved, labor costs can be reduced, and problem-solving efficiency can be improved, thereby ensuring user experience.

[0026] The end-side device 102 may include a browser, an application (APP), or a web application such as an H5 (Hypertext Markup Language 5) application, a lightweight application (also known as a mini-program, a type of lightweight application), or a cloud application. The end-side device may be developed based on a software development kit (SDK) for the corresponding service provided by the server, such as a real-time communication (RTC) SDK. The end-side device may be deployed in an electronic device and may rely on the device or certain apps in the device to operate. The electronic device may have a display and support information browsing, such as a personal mobile terminal such as a mobile phone, tablet computer, or personal computer. Various other types of applications may also be configured in the electronic device, such as human-computer interaction applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0027] See also Figure 2 , Figure 2 A flowchart of a conversation processing method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0028] Step 202: Receive a problem handling request, wherein the problem handling request carries problem information of a problem to be handled.

[0029] Specifically, the dialogue processing method provided in the embodiments of this specification can be applied to e-commerce platforms, and specifically can be applied to negotiation tasks between platform customer service and merchant customer service of the e-commerce platform.

[0030] Among them, the problem handling request can be understood as a custodial negotiation request initiated by the platform's manual customer service of the e-commerce platform. The pending problem can be understood as a dispute between the platform users of the e-commerce platform and the platform merchants of the e-commerce platform. Platform merchants sell goods on the e-commerce platform, and platform users purchase goods from platform merchants through the e-commerce platform. When platform users and platform merchants have a dispute over a commodity transaction, platform users can usually seek help from the platform customer service to intervene. After understanding the dispute, the platform customer service can negotiate with the merchant customer service to obtain a solution to the problem. The problem information of the pending problem can be understood as the problem information of the dispute problem. This problem information may include product information, merchant information, user problems, user demands, negotiation progress between users and merchants, negotiation scenarios, and negotiation goals.

[0031] Specifically, e-commerce platforms can use intelligent decision-making units as negotiation robots to negotiate and resolve pending issues. The intelligent decision-making units can receive problem-solving requests initiated by the platform's human customer service representatives and determine the problem information contained in the problem-solving requests. The intelligent decision-making units can be referred to as intelligent agents.

[0032] In actual applications, platform users of the e-commerce platform can initiate a dispute resolution request to the e-commerce platform. After receiving the dispute resolution request, the e-commerce platform can obtain relevant information of the pending dispute corresponding to the dispute resolution request. The e-commerce platform can display the platform users' demands and problems and the current negotiation progress between the platform users and platform merchants to the platform's manual customer service based on the relevant information. The platform's manual customer service can click on the display interface to initiate a managed negotiation to the intelligent decision-making unit based on the relevant order information and product information of the pending dispute, thereby initiating a problem resolution request to the intelligent decision-making unit.

[0033] See also Figure 3 , Figure 3 A schematic diagram of a display interface displayed by an e-commerce platform to a human customer service representative in a dialogue processing method according to an embodiment of this specification is shown. Figure 3As shown, the display interface can display to the platform's manual customer service the information of the product in dispute (including product name, product image, etc.), merchant information, user issues and demands (such as "It broke after less than 3 days of use, quality problems, requesting a return" (which may include user descriptions and pictures, etc.), the latest negotiation progress (such as "The merchant has not yet provided an effective solution / The merchant refuses to refund only, and no effective solution has yet been provided") and the negotiation time corresponding to the latest negotiation progress, the negotiation method selection control (such as "manual negotiation or managed negotiation"), the negotiation scenario (such as "Large item has defects and is not convenient for return, negotiate a discount compensation"), the negotiation target (such as "Partial compensation of XX yuan"), and the negotiation managed control. The product information, merchant information, user issues and demands, the latest negotiation progress, the negotiation scenario, and the negotiation target can be automatically summarized by the e-commerce platform based on the relevant information of the pending dispute, or can be manually input or selected by the platform's manual customer service, and this embodiment of the specification is not limited to this. The platform's manual customer service can select "Managed Negotiation" as the negotiation method selection control on the display interface and click the managed negotiation control. In response to the click operation (i.e., the problem handling instruction), the e-commerce platform generates a problem handling request carrying the problem information of the pending problem and sends it to the intelligent decision-making unit.

[0034] Step 204: Determine the target problem processing end corresponding to the problem to be processed based on the problem information, generate first dialogue data corresponding to the problem to be processed, and send the first dialogue data to the target problem processing end, wherein the first dialogue data is used to guide the target problem processing end to process the problem to be processed.

[0035] The target problem processing terminal can be understood as the merchant customer service for processing the pending problem. The first dialogue data can be dialogue data generated by the intelligent decision-making unit based on the problem information to guide the merchant customer service to provide a solution to the pending problem.

[0036] Specifically, the intelligent decision-making unit can determine the merchant customer service for handling the pending problem based on the problem information, generate dialogue data to guide the merchant customer service to provide a solution to the pending problem, and send the dialogue data to the merchant customer service.

[0037] In a specific implementation, determining the target problem processing end corresponding to the problem to be processed according to the problem information includes: Determining the problem object corresponding to the problem to be processed according to the problem object information corresponding to the problem to be processed included in the problem information; Determine a target problem processing end corresponding to the problem to be processed from a plurality of problem processing ends corresponding to the problem object.

[0038] Among them, the problem object can be understood as the platform merchant corresponding to the problem to be processed, that is, the merchant who has a dispute with the platform user. The problem object information can be understood as the merchant information contained in the problem information. The multiple problem processing terminals corresponding to the problem object can be understood as the multiple merchant customer service of the platform merchant.

[0039] Specifically, the intelligent decision-making unit can determine the platform merchant corresponding to the pending issue based on the merchant information included in the problem information, and select the target merchant customer service from multiple merchant customer service of the platform merchant for subsequent dispute negotiation.

[0040] In addition, the e-commerce platform may determine the platform merchant and the target merchant customer service and then send them to the intelligent decision-making unit, which then negotiates with the target merchant customer service.

[0041] In summary, the intelligent decision-making unit can automatically identify platform merchants and find the target merchant customer service among the platform merchants for subsequent dispute negotiations, realizing automated negotiations and thus reducing labor costs.

[0042] Furthermore, determining a target problem processing end corresponding to the problem to be processed from a plurality of problem processing ends corresponding to the problem object includes: Determining a target problem processing end corresponding to the problem to be processed according to priority information of each problem processing end among multiple problem processing ends corresponding to the problem object; and / or A target problem processing end corresponding to the problem to be processed is determined according to historical conversation information of each problem processing end among multiple problem processing ends corresponding to the problem object.

[0043] Priority information can be used to describe the willingness to negotiate and the efficiency of problem-solving among multiple merchant customer service representatives on the platform. A merchant customer service representative with a higher priority may have a stronger willingness to negotiate or be more efficient in handling disputes arising within a historical time period. This priority information can be obtained by labeling each merchant customer service representative based on historical communication patterns during the e-commerce platform's historical communication process. Historical conversation information can be understood as historical conversation data between platform customer service representatives and merchant customer service representatives.

[0044] Specifically, based on the priority information of each problem processing terminal among multiple problem processing terminals, a problem processing terminal with a higher priority can be determined as the target problem processing terminal; and / or, based on the historical conversation information of each problem processing terminal among multiple problem processing terminals, a problem processing terminal with a historical conversation number greater than a preset conversation number can be determined as the target problem processing terminal.

[0045] In addition, the target processing end can also be determined based on the platform docking group corresponding to the problem object. In actual applications, platform merchants usually set up platform docking groups, and the merchant customer service in the platform docking group communicates specifically with the platform customer service. Then, the intelligent decision-making unit can also determine the target problem processing end from the platform docking group. Alternatively, the intelligent decision-making unit can also determine the order processing customer service of the commodity transaction order corresponding to the problem to be processed, and determine the order processing customer service as the target problem processing end. Alternatively, the intelligent decision-making unit can also randomly select the target problem processing end from multiple problem processing ends of the problem object. This embodiment of the specification does not limit this.

[0046] In summary, by combining any one or more of the above strategies with the target problem processing end, it is convenient for the subsequent intelligent decision-making unit and the target problem processing end to negotiate and communicate, ensuring the efficiency of subsequent negotiations, so that the problems to be processed can be solved as soon as possible.

[0047] In a specific implementation, generating the first dialogue data corresponding to the problem to be processed includes: Generate a reference problem solution corresponding to the problem to be processed based on the problem information of the problem to be processed and the user information of the problem initiator corresponding to the problem to be processed; The reference problem processing solution is determined as the first dialogue data corresponding to the problem to be processed.

[0048] The reference problem solution can be understood as a suggested solution provided by the intelligent decision-making unit. The user who initiated the problem to be processed can be understood as the platform user who initiated the problem to be processed. User information can include the platform user's desired negotiation goal, etc.

[0049] Specifically, the intelligent decision-making unit can generate a suggested solution corresponding to the problem to be processed based on the problem information of the problem to be processed and the user information of the platform user who initiated the problem to be processed, and send the suggested solution as the first dialogue data to the target problem processing end to guide the target problem processing end to process it.

[0050] In practical applications, the negotiation dialogue between the intelligent decision-making unit and the target problem-solving end can proceed according to a process involving greeting, explaining the platform user's problem and demands, providing a suggested solution, guiding the target problem-solving end to propose other reasonable solutions, guiding the target problem-solving end to propose a solution, and finally guiding the target problem-solving end to confirm the final solution, striving to achieve the negotiation goal. The intelligent decision-making unit can intervene in the negotiation model, with the negotiation model outputting relevant response instructions. The first dialogue data output by the intelligent decision-making unit typically includes: 1. Guiding merchants to proactively provide solutions to the problem, increasing information transparency; 2. Providing suggested solutions, based on the e-commerce platform's historical data and dispute resolution experience, to provide reasonable suggestions to platform merchants and platform users; 3. Guiding other reasonable solutions, building on existing foundations to explore more possibilities and seek win-win situations; 4. Providing bargaining chips, introducing new variables or preferential conditions when appropriate, to promote negotiation progress; 5. Answering questions and promptly responding to questions from both platform merchants and platform users to eliminate misunderstandings and ensure smooth communication.

[0051] In summary, by providing suggestions through the intelligent decision-making unit, the negotiated solution of pending issues can be promoted as soon as possible, and the processing efficiency of pending issues can be further improved.

[0052] Step 206: Receive the second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine a problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

[0053] Specifically, after the intelligent decision-making unit sends the first dialogue data to the target problem processing end, it can receive the second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine the problem processing solution based on the first dialogue data and the second dialogue data.

[0054] Then, after obtaining the problem-solving solution, the problem-solving solution can be sent to the platform user. If the platform user agrees, the pending problem can be solved according to the problem-solving solution. If the platform user disagrees, the above process can be repeated to negotiate with the platform merchant again.

[0055] In a specific implementation, the receiving of the second dialogue data returned by the target problem processing end in response to the first dialogue data, and determining a problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data, includes: receiving second dialogue data returned by the target question processing end in response to the first dialogue data; generating next first dialogue data for the second dialogue data according to the question to be processed, the first dialogue data, and the second dialogue data, and sending the next first dialogue data to the target question processing end; Receive the next second dialogue data returned by the target problem processing end for the next first dialogue data, and continue to execute the step of generating the next first dialogue data for the second dialogue data based on the problem to be processed, the first dialogue data, and the second dialogue data, until a problem processing solution corresponding to the problem to be processed is obtained based on the first dialogue data and the second dialogue data.

[0056] Specifically, the intelligent decision-making unit and the target problem processing end can engage in multiple rounds of interactive dialogue to negotiate. The first dialogue data and the second dialogue data can represent one round of interactive dialogue, and the next first dialogue data and the next second dialogue data can represent the second round of interactive dialogue. It is understood that the first dialogue data refers to the dialogue data sent by the intelligent decision-making unit to the target problem processing end, and the second dialogue data refers to the dialogue data sent by the target problem processing end to the intelligent decision-making unit. In these multiple rounds of interactive dialogue, the problem resolution solution corresponding to the pending problem can be determined based on the first dialogue data and the second dialogue data of each round of interactive dialogue.

[0057] In practical applications, the problem-solving solution may be a suggested solution provided by the intelligent decision-making unit and agreed to by the target problem-solving end. Alternatively, the problem-solving solution may be a problem-solving solution reached through gradual negotiation between the intelligent decision-making unit and the target problem-solving end.

[0058] In summary, through multiple rounds of interactive dialogue, solution negotiation is achieved, and finally a solution to the problem is obtained, which further promotes the resolution of pending issues.

[0059] Furthermore, the generating, based on the problem to be processed, the first dialogue data, and the second dialogue data, the next first dialogue data for the second dialogue data includes: Performing sentiment analysis on the second conversation data to obtain a sentiment analysis result; Generate next first dialogue data for the second dialogue data according to the sentiment analysis result, the question to be processed, the first dialogue data, and the second dialogue data.

[0060] Specifically, the intelligent decision-making unit can perform sentiment analysis on the second dialogue data returned by the target problem processing end in each round, obtain the sentiment analysis results, and adjust the negotiation method according to the sentiment analysis results when generating the next round of first dialogue data for the second dialogue data.

[0061] During specific implementation, a sentiment analysis model may be used to perform sentiment analysis on the second conversation data. The sentiment analysis model may be a machine learning model, a deep learning model, etc., which is not limited in the embodiments of this specification.

[0062] In actual applications, when the target problem processing end responds to the first dialogue data sent by the intelligent decision-making unit, the intelligent decision-making unit will respond in a timely manner. If the target problem processing end does not respond for a long time, the first dialogue data can be generated to urge it to reply. If the sentiment analysis result of the second dialogue data replied by the target problem processing end shows that it is emotionally excited, the first dialogue data can be generated to soothe it. In addition, the intelligent decision-making unit can adjust the negotiation method according to the response attitude of the target problem processing end. If the sentiment analysis result shows that the target problem processing end is in a mild mood, the intelligent decision-making unit can more actively urge the target problem processing end to provide more problem-solving solutions; if the sentiment analysis result shows that the target problem processing end is emotionally excited, a moderate negotiation method can be adopted to avoid escalation of conflicts.

[0063] In summary, by enabling the intelligent decision-making unit to flexibly adjust the negotiation strategy according to the response attitude of the platform merchants, the negotiation goals can be further achieved.

[0064] Furthermore, for the first conversation data output by the intelligent decision-making unit, before sending the first conversation data to the target problem processing end, the e-commerce platform can perform risk detection on the first conversation data and obtain risk detection results. If it is determined that there is a risk in the first conversation data based on the risk monitoring results, the e-commerce platform will stop sending the first conversation data to the target problem processing end to achieve risk control and avoid public opinion risks.

[0065] Furthermore, during the negotiation process between the intelligent decision-making unit and the target problem processing end, the e-commerce platform can display the negotiation process between the intelligent decision-making unit and the target problem processing end to the platform's manual customer service through a display interface, and the platform's manual customer service will conduct manual monitoring. The platform's manual customer service can adjust the negotiation target or terminate the negotiation process at any time on the display interface.

[0066] See also Figure 4 , Figure 4 A schematic diagram of a display interface showing a negotiation process in a dialogue processing method provided according to an embodiment of this specification is shown. Figure 4 As shown, the display interface can display the negotiation process between the intelligent decision-making unit and the target problem processing end, and display adjustment controls and manual negotiation controls. The platform's manual customer service clicks the adjustment control, and the e-commerce platform can display the problem information of the pending problem on the display interface (that is, display the above Figure 3 ), at this time, the platform's manual customer service can adjust the negotiation target contained in the problem information. The platform's manual customer service clicks the manual negotiation control to terminate the managed negotiation process between the intelligent decision-making unit and the target problem processing end, and the platform's manual customer service will subsequently conduct manual negotiation.

[0067] In practical applications, see Figure 5 , Figure 5 FIG. 1 shows a technical link diagram of a conversation processing method provided according to an embodiment of this specification. Figure 5 As shown, the platform customer service of the e-commerce platform can trigger the hosting negotiation, the negotiation layer triggers the negotiation task, and the negotiation is executed after diversion. In the intelligent agent module, the intelligent agent initialization is executed, including the creation of intelligent agent instances, negotiation context information (i.e., problem information) and driving subsequent execution. The intelligent agent (i.e., intelligent decision-making unit) can make solution decisions, including negotiation decisions, negotiation context information updates and outputs, and in the solution decision process, call the dialogue arrangement algorithm to perform intent recognition, solution recognition, speech decision and negotiation end recognition. The intelligent decision-making unit can output the dialogue data by calling the above algorithm and send it to the merchant customer service, and the merchant customer service can perform dialogue data For replies, card operations or operations that have not been replied for a long time, the intelligent decision-making unit can also execute negotiation decisions in the executor execution and output the negotiation execution results. The executor module can perform negotiation execution during the negotiation process, including executing greetings, cards, and speech sending, ending negotiations, etc. The basic capability module can send messages, receive messages, transfer event monitoring, card push and card operation callbacks, etc. during the negotiation process. When the merchant customer service has not replied for a long time, the negotiation timeout detection module can perform negotiation timeout detection, so that the intelligent decision-making unit can execute urging operations, etc., and finally end after obtaining the negotiation result between the intelligent decision-making unit and the merchant customer service.

[0068] In the above method, after the intelligent decision-making unit receives the problem processing request, it can determine the target problem processing end corresponding to the problem to be processed based on the problem information of the problem to be processed carried in the problem processing request, and generate first dialogue data corresponding to the problem to be processed, send the first dialogue data to the target problem processing end, use the first dialogue data to guide the target problem processing end to process the problem to be processed, and receive the second dialogue data returned by the target problem processing end for the first dialogue data, determine the problem processing solution for the problem to be processed based on the first dialogue data and the second dialogue data, and entrust the negotiation of the problem processing solution to the intelligent decision-making unit, and enable the intelligent decision-making unit to generate the first dialogue data to guide the target problem processing end to process the problem to be processed, so as to achieve the solution of the problem, reduce labor costs, improve problem solving efficiency, and thus ensure user experience.

[0069] The following combined Figure 6 , taking the application of the dialogue processing method provided in this specification in customer service negotiation as an example, the dialogue processing method is further explained. Figure 6 A flowchart of a process of a dialogue processing method provided by an embodiment of this specification is shown, which specifically includes the following steps.

[0070] Step 602: The platform's manual customer service initiates a hosting negotiation with the intelligent agent.

[0071] Step 604: The agent determines the merchant’s customer service.

[0072] Step 606: The intelligent agent negotiates with the merchant’s customer service and obtains negotiation results.

[0073] Step 608: Display the negotiation process between the intelligent agent and the merchant’s customer service to the platform’s manual customer service.

[0074] In this method, the platform's customer service initiates a managed negotiation with the agent. Based on the problem information, the agent identifies the merchant's customer service representative and negotiates with them on behalf of the platform's customer service representative. The agent then displays the negotiation results to the platform's customer service representative, allowing them to adjust negotiation goals or intervene in the negotiation process in a timely manner. This resolves the problem, reduces labor costs, improves problem-solving efficiency, and ensures a positive user experience.

[0075] Corresponding to the above method embodiment, this specification also provides a dialogue processing device embodiment, Figure 7 FIG1 shows a structural diagram of a conversation processing device provided by an embodiment of this specification. Figure 7 As shown, the device includes: The receiving module 702 is configured to receive a problem handling request, wherein the problem handling request carries problem information of a problem to be handled; A generating module 704 is configured to determine a target problem processing terminal corresponding to the problem to be processed based on the problem information, generate first dialogue data corresponding to the problem to be processed, and send the first dialogue data to the target problem processing terminal, wherein the first dialogue data is used to guide the target problem processing terminal to process the problem to be processed; The determination module 706 is configured to receive the second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine the problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

[0076] In an optional embodiment, the generating module 704 is further configured to: Determining the problem object corresponding to the problem to be processed according to the problem object information corresponding to the problem to be processed included in the problem information; Determine a target problem processing end corresponding to the problem to be processed from a plurality of problem processing ends corresponding to the problem object.

[0077] In an optional embodiment, the generating module 704 is further configured to: Determining a target problem processing end corresponding to the problem to be processed according to priority information of each problem processing end among multiple problem processing ends corresponding to the problem object; and / or A target problem processing end corresponding to the problem to be processed is determined according to historical conversation information of each problem processing end among multiple problem processing ends corresponding to the problem object.

[0078] In an optional embodiment, the determining module 706 is further configured to: receiving second dialogue data returned by the target question processing end in response to the first dialogue data; generating next first dialogue data for the second dialogue data according to the question to be processed, the first dialogue data, and the second dialogue data, and sending the next first dialogue data to the target question processing end; Receive the next second dialogue data returned by the target problem processing end for the next first dialogue data, and continue to execute the step of generating the next first dialogue data for the second dialogue data based on the problem to be processed, the first dialogue data, and the second dialogue data, until a problem processing solution corresponding to the problem to be processed is obtained based on the first dialogue data and the second dialogue data.

[0079] In an optional embodiment, the determining module 706 is further configured to: Performing sentiment analysis on the second conversation data to obtain a sentiment analysis result; Generate next first dialogue data for the second dialogue data according to the sentiment analysis result, the question to be processed, the first dialogue data, and the second dialogue data.

[0080] In an optional embodiment, the generating module 704 is further configured to: Generate a reference problem solution corresponding to the problem to be processed based on the problem information of the problem to be processed and the user information of the problem initiator corresponding to the problem to be processed; The reference problem processing solution is determined as the first dialogue data corresponding to the problem to be processed.

[0081] In the above-mentioned device, after the intelligent decision-making unit receives the problem processing request, it can determine the target problem processing end corresponding to the problem to be processed based on the problem information of the problem to be processed carried in the problem processing request, and generate first dialogue data corresponding to the problem to be processed, send the first dialogue data to the target problem processing end, use the first dialogue data to guide the target problem processing end to process the problem to be processed, and receive the second dialogue data returned by the target problem processing end for the first dialogue data, determine the problem processing solution for the problem to be processed based on the first dialogue data and the second dialogue data, and entrust the negotiation of the problem processing solution to the intelligent decision-making unit, and enable the intelligent decision-making unit to generate the first dialogue data to guide the target problem processing end to process the problem to be processed, so as to achieve the solution of the problem, reduce labor costs, improve problem solving efficiency, and thus ensure user experience.

[0082] The above is a schematic diagram of a conversation processing device according to this embodiment. It should be noted that the technical solution of this conversation processing device and the technical solution of the conversation processing method described above are based on the same concept. For details not described in detail in the technical solution of the conversation processing device, please refer to the description of the technical solution of the conversation processing method described above.

[0083] Corresponding to the above method embodiment, the embodiment of this specification also provides a dialogue processing system, including an intelligent decision-making unit, wherein: The intelligent decision-making unit is used to receive a problem processing request, wherein the problem processing request carries problem information of the problem to be processed; determine the target problem processing end corresponding to the problem to be processed based on the problem information, generate first dialogue data corresponding to the problem to be processed, and send the first dialogue data to the target problem processing end, wherein the first dialogue data is used to guide the target problem processing end to process the problem to be processed; receive second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine the problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

[0084] In an optional embodiment, the system further comprises an information determination unit, wherein: The information determination unit is used to receive problem information of the problem to be processed, and in response to the problem processing instruction for the problem to be processed, generate a problem processing request carrying the problem information of the problem to be processed, and send the problem processing request to the intelligent decision-making unit.

[0085] In an optional embodiment, the system further comprises a dialogue detection unit, wherein: The dialogue detection unit is used to perform risk detection on the first dialogue data generated by the intelligent decision-making unit to obtain a risk detection result, and when it is determined that the first dialogue data is risky according to the risk detection result, send a dialogue stop instruction to the intelligent decision-making unit, wherein the dialogue stop instruction is used to cause the intelligent decision-making unit to stop sending the first dialogue data to the target problem processing end.

[0086] The above is a schematic diagram of a dialog processing system according to this embodiment. It should be noted that the technical solution of this dialog processing system and the technical solution of the dialog processing method described above are based on the same concept. For details not described in detail in the technical solution of the dialog processing system, please refer to the description of the technical solution of the dialog processing method described above.

[0087] Figure 8 8 shows a block diagram of a computing device 800 according to one embodiment of the present disclosure. Components of the computing device 800 include, but are not limited to, a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0088] The computing device 800 also includes an access device 840 that enables the computing device 800 to communicate via one or more networks 860. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 840 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0089] In one embodiment of the present application, the above components of the computing device 800 and Figure 8Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 8 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0090] Computing device 800 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or personal computer (PC). Computing device 800 can also be a mobile or stationary server.

[0091] The processor 820 is configured to execute the following computer program / instruction, which implements the steps of the above-mentioned dialogue processing method when executed by the processor.

[0092] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the computing device embodiment is generally similar to the conversation processing method embodiment, so its description is relatively simple. For relevant parts, refer to the description of the conversation processing method embodiment.

[0093] An embodiment of the present specification further provides a computer-readable storage medium storing a computer program / instruction, which implements the steps of the above-mentioned dialogue processing method when executed by a processor.

[0094] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the computer-readable storage medium embodiment is generally similar to the conversation processing method embodiment, so its description is relatively simple. For relevant parts, refer to the description of the conversation processing method embodiment.

[0095] An embodiment of the present specification further provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned dialogue processing method when executed by a processor.

[0096] The above is a schematic diagram of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the aforementioned conversation processing method are based on the same concept. For details not described in detail in the technical solution of the computer program product, please refer to the description of the technical solution of the aforementioned conversation processing method.

[0097] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0098] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium may be appropriately increased or decreased based on the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0099] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0100] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A conversation processing method, comprising: receiving a problem handling request, wherein the problem handling request carries problem information of a problem to be handled; Determining a target problem processing terminal corresponding to the problem to be processed based on the problem information, generating first dialogue data corresponding to the problem to be processed, and sending the first dialogue data to the target problem processing terminal, wherein the first dialogue data is used to guide the target problem processing terminal to process the problem to be processed; Receive second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine a problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

2. The method according to claim 1, wherein determining the target problem processing end corresponding to the problem to be processed according to the problem information comprises: Determining the problem object corresponding to the problem to be processed according to the problem object information corresponding to the problem to be processed included in the problem information; Determine a target problem processing end corresponding to the problem to be processed from a plurality of problem processing ends corresponding to the problem object.

3. The method according to claim 2, wherein determining a target problem processing terminal corresponding to the problem to be processed from a plurality of problem processing terminals corresponding to the problem object comprises: Determining a target problem processing end corresponding to the problem to be processed according to priority information of each problem processing end among multiple problem processing ends corresponding to the problem object; and / or A target problem processing end corresponding to the problem to be processed is determined according to historical conversation information of each problem processing end among multiple problem processing ends corresponding to the problem object.

4. The method according to claim 1, wherein receiving the second dialogue data returned by the target problem processing end in response to the first dialogue data, and determining a problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data, comprises: receiving second dialogue data returned by the target question processing end in response to the first dialogue data; generating next first dialogue data for the second dialogue data according to the question to be processed, the first dialogue data, and the second dialogue data, and sending the next first dialogue data to the target question processing end; Receive the next second dialogue data returned by the target problem processing end for the next first dialogue data, and continue to execute the step of generating the next first dialogue data for the second dialogue data based on the problem to be processed, the first dialogue data, and the second dialogue data, until a problem processing solution corresponding to the problem to be processed is obtained based on the first dialogue data and the second dialogue data.

5. The method according to claim 4, wherein generating the next first dialogue data for the second dialogue data based on the to-be-processed question, the first dialogue data, and the second dialogue data comprises: Performing sentiment analysis on the second conversation data to obtain a sentiment analysis result; Generate next first dialogue data for the second dialogue data according to the sentiment analysis result, the question to be processed, the first dialogue data, and the second dialogue data.

6. The method according to any one of claims 1 to 5, wherein generating first dialogue data corresponding to the question to be processed comprises: Generate a reference problem solution corresponding to the problem to be processed based on the problem information of the problem to be processed and the user information of the problem initiator corresponding to the problem to be processed; The reference problem processing solution is determined as the first dialogue data corresponding to the problem to be processed.

7. A dialogue processing system, comprising an intelligent decision-making unit, wherein: The intelligent decision-making unit is used to receive a problem processing request, wherein the problem processing request carries problem information of the problem to be processed; determine the target problem processing end corresponding to the problem to be processed based on the problem information, generate first dialogue data corresponding to the problem to be processed, and send the first dialogue data to the target problem processing end, wherein the first dialogue data is used to guide the target problem processing end to process the problem to be processed; receive second dialogue data returned by the target problem processing end in response to the first dialogue data, and determine the problem processing solution corresponding to the problem to be processed based on the first dialogue data and the second dialogue data.

8. The system according to claim 7, further comprising an information determination unit, wherein: The information determination unit is used to receive problem information of the problem to be processed, and in response to the problem processing instruction for the problem to be processed, generate a problem processing request carrying the problem information of the problem to be processed, and send the problem processing request to the intelligent decision-making unit.

9. The system according to claim 7, further comprising a conversation detection unit, wherein The dialogue detection unit is used to perform risk detection on the first dialogue data generated by the intelligent decision-making unit to obtain a risk detection result, and when it is determined that the first dialogue data is risky according to the risk detection result, send a dialogue stop instruction to the intelligent decision-making unit, wherein the dialogue stop instruction is used to cause the intelligent decision-making unit to stop sending the first dialogue data to the target problem processing end.

10. A computing device comprising: memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

11. A computer-readable storage medium storing a computer program / instruction, wherein the computer program / instruction is executed by a processor to implement the steps of the method according to any one of claims 1 to 6.

12. A computer program product comprising a computer program / instruction, which implements the steps of the method according to any one of claims 1 to 6 when executed by a processor.

Images