Data processing method and system, computing device and storage medium

Abstract

The embodiment of the invention provides a data processing method and system, computing equipment and a storage medium, and the data processing method comprises the steps: obtaining interactive dialogue data related to a target object in response to a consultation request for the target object; on the basis of an appeal confirmation model, performing appeal recognition on the target object according to the interactive dialogue data to obtain a target appeal corresponding to the target object; and under the condition of determining that the target appeal meets the appeal processing condition, inputting the target appeal and object information of the target object into an appeal processing model, and processing the target appeal based on the appeal processing model.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of artificial intelligence, and particularly relate to a data processing method and system, a computing device, and a storage medium. BACKGROUND

[0002] Currently, users can make online purchases through e-commerce platforms. When a user encounters a problem, the user can consult through a service portal. Usually, the user's appeal needs to be confirmed through dialogue with the user. The dialogue usually includes a series of processes such as greeting the user, waiting for the user to describe the problem encountered, and confirming the user's appeal. A lot of time is wasted in confirming the user's appeal through dialogue with the user, and after confirming the appeal, the artificial customer service still needs to handle the appeal for the user through corresponding operations, resulting in a waste of a large amount of labor cost. In the case of needing to handle more user appeals, the response to the user will be slower, affecting the user's consultation experience. SUMMARY

[0003] Therefore, the embodiments of the present specification provide a data processing method. One or more embodiments of the present specification also relate to a data processing apparatus, a data processing system, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects in the prior art.

[0004] According to a first aspect of the embodiments of the present specification, a data processing method is provided, including: In response to a consultation request for a target object, obtaining interaction dialogue data related to the target object; Based on an appeal confirmation model, performing appeal identification on the target object according to the interaction dialogue data to obtain a target appeal corresponding to the target object; In a case where it is determined that the target appeal meets an appeal processing condition, inputting the target appeal and object information of the target object to an appeal processing model, and processing the target appeal based on the appeal processing model.

[0005] According to a second aspect of the embodiments of the present specification, a data processing apparatus is provided, including: An obtaining module configured to, in response to a consultation request for a target object, obtain interaction dialogue data related to the target object; An identification module configured to, based on an appeal confirmation model, perform appeal identification on the target object according to the interaction dialogue data to obtain a target appeal corresponding to the target object; A processing module configured to, in a case where it is determined that the target appeal meets an appeal processing condition, input the target appeal and object information of the target object to an appeal processing model, and process the target appeal based on the appeal processing model.

[0006] According to a third aspect of the embodiments of the present specification, a data processing system is provided, comprising a first intelligent decision unit and a second intelligent decision unit, wherein, The first intelligent decision unit is configured to perform complaint identification on the target object to obtain a target complaint corresponding to the target object in a case where the user complaint cannot be obtained from the interactive dialogue data, and send the target complaint and object information of the target object to the second intelligent decision unit in a case where it is determined that the target complaint meets complaint processing conditions, wherein the interactive dialogue data is interactive dialogue data related to the target object obtained in response to a consultation request for the target object. The second intelligent decision unit is configured to process the target complaint.

[0007] According to a fourth aspect of the embodiments of the present specification, a computing device is provided, comprising: a memory and a processor; The memory is configured to store computer programs / instructions, and the processor is configured to execute the computer programs / instructions, which realize the steps of the above data processing method when executed by the processor.

[0008] According to a fifth aspect of the embodiments of the present specification, a computer readable storage medium is provided, which stores computer programs / instructions, which realize the steps of the above data processing method when executed by the processor.

[0009] According to a sixth aspect of the embodiments of the present specification, a computer program product is provided, comprising computer programs / instructions, which realize the steps of the above data processing method when executed by the processor.

[0010] One embodiment of the present specification provides a data processing method, comprising: obtaining interactive dialogue data related to a target object in response to a consultation request for the target object; performing complaint identification on the target object based on a complaint confirmation model according to the interactive dialogue data to obtain a target complaint corresponding to the target object; and inputting the target complaint and object information of the target object to a complaint processing model and processing the target complaint based on the complaint processing model in a case where it is determined that the target complaint meets complaint processing conditions.

[0011] In the method, after receiving the consultation request for the target object, the interaction dialogue data related to the target object can be acquired, the target object is subjected to appeal identification based on the appeal confirmation model, the target appeal corresponding to the target object is obtained, and the target appeal and the object information related to the target object are input into the appeal processing model in a case where it is determined that the target appeal meets the appeal processing condition, and the target appeal is processed based on the appeal processing model. By using the appeal confirmation model and the appeal processing model, the appeal of the user to the target object is confirmed and processed respectively, without the need for manual customer service and the user to have a dialogue and processing, so as to reduce the waste of human cost. The consultation request of the user is processed based on the two models, so as to ensure the speed and efficiency of responding to the consultation request and further improve the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 FIG. 1 is a schematic diagram of an application scenario of a data processing method according to an embodiment of the present specification; Figure 2 FIG. 2 is a flowchart of a data processing method according to an embodiment of the present specification; Figure 3 FIG. 3 is a flowchart of determining a target appeal in a data processing method according to an embodiment of the present specification; Figure 4 FIG. 4 is a technical architecture diagram of a data processing method according to an embodiment of the present specification; Figure 5 FIG. 5 is a process flowchart of a data processing method according to an embodiment of the present specification; Figure 6 FIG. 6 is a structural diagram of a data processing device according to an embodiment of the present specification; Figure 7 FIG. 7 is a structural diagram of a data processing system according to an embodiment of the present specification; Figure 8 FIG. 8 is a structural block diagram of a computing device according to an embodiment of the present specification. DETAILED DESCRIPTION

[0013] In the following description, many specific details are set forth in order to provide a thorough understanding of the present specification. However, the present specification can be practiced in many different ways beyond the specific embodiments described herein, and it is understood that persons having ordinary skill in the art can make similar modifications without departing from the scope of the present specification.

[0014] The terminology used in the one or more embodiments of the present specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the present specification. As used in the one or more embodiments of the present specification and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "and / or," as used in the one or more embodiments of the present specification, are used to mean

[0015] It will be understood that, although the terms first, second, etc. can be used herein to describe various information, these terms are not intended to denote

[0016] In addition, it should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the one or more embodiments of the present specification are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0017] First, the nomenclature involved in the one or more embodiments of the present specification is explained.

[0018] Agent: Agent is a widely used concept in the field of artificial intelligence and computer science, which refers to an entity that can perceive its environment and affect it by performing actions. Agent can be a software program, a robot or other types of automated system. They are usually designed to solve specific problems or complete specific tasks, and can run in various environments, such as the Internet, the physical world or simulated environments.

[0019] In the present specification, a data processing method is provided, and the present specification also relates to a data processing device, a data 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] Reference is made to Figure 1 , Figure 1An application scenario diagram of a data processing method according to one embodiment of the present specification is shown, which comprises the following steps.

[0021] In response to the consultation request for the target object, the interaction dialogue data related to the target object is obtained.

[0022] Based on the appeal confirmation model, the appeal of the target object is identified according to the interaction dialogue data, and the target appeal corresponding to the target object is obtained.

[0023] In the case where it is determined that the target appeal meets the appeal processing condition, the target appeal and the object information of the target object are input to the appeal processing model, and the target appeal is processed based on the appeal processing model.

[0024] As Figure 1 shown, Figure 1 The end-side device 102 and the cloud-side device 104 are included.

[0025] In specific implementation, the user enters the customer service consultation page of the e-commerce platform in the end-side device 102, the end-side device 102 sends a consultation request to the cloud-side device 104 of the e-commerce platform, the customer service robot of the workbench of the e-commerce platform can interact with the user in the customer service consultation page to obtain the interaction dialogue data for the target object, the cloud-side device 104 of the e-commerce platform can obtain the interaction dialogue data, identify the appeal of the target object according to the interaction dialogue data by using the appeal confirmation model, determine the target appeal corresponding to the target object, and in the case where it is determined that the target appeal meets the appeal processing condition, process the target appeal according to the object information of the target object by using the appeal processing model. The speed and efficiency of the consultation request response are guaranteed, and the user experience is further improved.

[0026] The terminal-side device 102 can include a browser, an APP (Application), or a web application such as an H5 (Hyper Text Markup Language 5) application, or a light application (also known as a small program, a lightweight application), or a cloud application, etc. The terminal-side device can be developed based on a software development kit (SDK) of a corresponding service provided by the server-side, such as based on a real-time communication (RTC) SDK, etc. The terminal-side device can be deployed in an electronic device, and needs to be run in dependence of the device or some APP in the device, etc. The electronic device can have a display screen and support information browsing, etc., and can be a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications can also be configured in the electronic device, for example, human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant communication tools, mailbox clients, social platform software, etc.

[0027] The cloud-side device 104 can be understood as a server providing various services, including a physical server, a cloud server, for example, a server providing communication services for multiple clients, for example, a server for background training supporting a model used on a client, for example, a server processing data sent by a client, etc. It should be noted that the cloud-side device 104 can be implemented as a distributed server cluster composed of multiple servers, or as a single server. The cloud-side device 104 can also be a server of a distributed system, or a server combined with a blockchain. The cloud-side device 104 can also be a cloud server of cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, etc. basic cloud computing services, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0028] It should be noted that the data processing method provided in the embodiments of the present specification can be executed by the cloud-side device 104, or can be executed by the terminal-side device 102; in other embodiments, the data processing method provided in the embodiments of the present specification can also be executed by the terminal-side device 102 and the cloud-side device 104 together.

[0029] Referring to Figure 2 , Figure 2 A flowchart of a data processing method according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0030] Step 202: in response to the consultation request for the target object, obtaining interaction dialogue data related to the target object.

[0031] Specifically, the data processing method provided by the embodiments of the present specification can be applied to an e-commerce platform. Specifically, the data processing method can process questions raised by users of the e-commerce platform for created commodity purchase orders. For example, a user purchases a certain commodity on the e-commerce platform, and the consultation questions and after-sales questions for the commodity can be processed according to the data processing method. Alternatively, the data processing method provided by the embodiments of the present specification can also be applied to other service platforms, such as an education platform. A user can purchase an education course through the education platform. Then, the user's questions related to the purchased education course can also be processed according to the data processing method. For example, it can also be applied to sports software. A user can purchase a sports course and sports equipment in the sports software. Then, the user's questions related to the purchased sports course and sports equipment can be processed according to the data processing method. The embodiments of the present specification do not limit the application scenarios of the data processing method. It can be understood that the data processing method provided by the embodiments of the present specification can be applied to various service platforms that provide transaction services. Further, the solicitation knowledge, related restrictions and boundary conditions provided in different fields can be reused for the identification of solicitation in the field. The embodiments of the present specification do not limit this.

[0032] For ease of understanding, the embodiments of the present specification take the application of the data processing method to the e-commerce platform as an example for illustration.

[0033] The target object can be understood as an object that needs to be consulted, such as a target order and a target account. The target order can be understood as a commodity purchase order that needs to be consulted. The target account can be understood as an account of a user in an e-commerce platform. The target appeal related to the target account can be, for example, how to unbind a member, how to open a member, and the like. The consultation request for the target object can be understood as a consultation request for the target object sent by a purchase user of the target object through a client. In actual application, the consultation request can be generated when the user enters the customer service consultation page of the target object in the e-commerce platform. The interaction dialogue data related to the target object can be understood as the interaction dialogue data between the user and the customer service for the related problems of the target object after the user enters the customer service consultation page of the target object, or can also include the interaction dialogue data between the user and the customer service for the related problems of the target object in a historical time period. For example, the user sends a consultation request for the target object through the client on February 15, and the user and the customer service communicate for the target object. Therefore, the interaction dialogue data between the user and the customer service can be obtained. Alternatively, the user and the customer service communicate for the target object on February 15, and the user sends a consultation request for the target object through the client again on February 17. Therefore, the interaction dialogue data between the user and the customer service for the target object on February 15 can be obtained. Alternatively, the interaction dialogue data related to the target object can also be interaction dialogue feature data. It can be understood that the customer service mentioned in the embodiments of the present specification can be a manual customer service or a customer service robot, and the embodiments of the present specification do not limit the same.

[0034] Based on this, the user can log in to the e-commerce platform through the client, enter the customer service consultation page of the target object in the e-commerce platform, and generate a consultation request for the target object to the e-commerce platform through the client. The e-commerce platform receives the consultation request for the target object and obtains the interaction dialogue data related to the target object. In actual implementation, after the e-commerce platform receives the consultation request for the target object, the e-commerce platform can interact with the user in the customer service consultation page based on the manual customer service or the customer service robot, so as to obtain the interaction dialogue data related to the target object. Alternatively, the e-commerce platform can obtain the interaction dialogue data related to the target object in a historical time period from the database of the e-commerce platform after receiving the consultation request for the target object. Specifically, in the case that the target object is a target order, the interaction dialogue data corresponding to the order number of the target order can be obtained from the database of the e-commerce platform according to the order number.

[0035] In actual application, the user of the target object can consult or seek help from the workbench for problem solving in the e-commerce platform through the telephone or the customer service consultation page. The workbench can interact with the user based on the manual customer service or the customer service robot, so as to obtain the target appeal of the user for the target object.

[0036] Step 204: based on the appeal confirmation model, performing appeal identification on the target object according to the interactive dialogue data, to obtain a target appeal corresponding to the target object.

[0037] Specifically, after obtaining the interactive dialogue data related to the target object, the appeal confirmation model can be used to perform appeal identification on the target object according to the interactive dialogue data, to obtain a target appeal corresponding to the target object.

[0038] Further, after obtaining the interactive dialogue data related to the target object, it can be determined whether the user appeal can be directly obtained from the interactive dialogue data. If not, appeal identification can be performed on the target object based on the appeal confirmation model according to the interactive dialogue data, to obtain a target appeal corresponding to the target object.

[0039] The appeal confirmation model can be understood as an intelligent agent for performing appeal identification on the interactive dialogue data. It can be a virtual person, a robot, a natural language processing model, a machine learning model obtained after training on an appeal confirmation task, a deep learning model, etc., which are not limited in the embodiments of the present specification. Therefore, in the case where the user appeal cannot be obtained from the interactive dialogue data, an intelligent agent hosting process for appeal confirmation can be entered, in which the appeal identification is performed on the target object based on the intelligent agent. Alternatively, after obtaining the interactive dialogue data related to the target object, the intelligent agent hosting process for appeal confirmation can be directly entered, in which the appeal identification is performed on the target object based on the intelligent agent.

[0040] The target appeal corresponding to the target object can be understood as the appeal of the user of the target object to the target object, i.e., the user appeal. For example, if the interactive dialogue data contains "I want a refund" proposed by the user, then the target appeal of the user to the target object can be directly determined as a refund appeal from the interactive dialogue data.

[0041] In practical applications, referring to Figure 3 , Figure 3 Fig. 1 shows a flowchart for determining a target appeal in a data processing method according to an embodiment of the present specification, as shown in Figure 3As shown, the user of the target object can enter the customer service consultation page (i.e., the user enters the line), and a multi-round dialogue interaction is performed between the customer service robot and the user to obtain interactive dialogue data between the user and the customer service robot. If the customer service robot can directly obtain the target appeal in the interactive dialogue data or detects that the user has a strong appeal to enter the manual customer service, the manual stage can be entered. In the manual stage, the customer service robot can be used for hosting, the target appeal obtained is secondly confirmed, and in the case that the target appeal recognition is determined to be inaccurate, the appeal confirmation hosting stage can be entered, that is, the target appeal of the target object is further inquired from the user based on the appeal confirmation model. If the target appeal cannot be directly obtained in the interactive dialogue data, the appeal confirmation hosting stage can be entered, that is, the target appeal of the target object is further inquired from the user based on the appeal confirmation model. When judging whether the target appeal can be recognized from the interactive dialogue data, whether the order scene, the reference question and the target appeal are determined according to the interactive dialogue data. In the case that the order scene, the reference question and the target appeal can be obtained from the interactive dialogue data, the target appeal can be directly obtained from the interactive dialogue data; in the case that the order scene, the reference question and the target appeal do not exist in the interactive dialogue data, it is indicated that the target appeal cannot be directly obtained from the interactive dialogue data. The order scene can be a pre-sale scene, an after-sale scene, a return scene, a refund scene, etc., and the reference question can be a question pre-configured according to the order scene, such as the reference question "Can this be refunded?". If the reference question exists in the interactive dialogue data, that is, the user inquires about the reference question, it is determined that the target appeal of the user is refund. After the target appeal is determined, the target appeal that meets the access appeal enters the hosting, and in the case that the target appeal meets the appeal processing condition, the service hosting stage is entered, and the target appeal is processed in the service hosting stage. Further, in the appeal confirmation hosting stage, that is, in the stage of appeal recognition based on the appeal confirmation model, if the target appeal still cannot be confirmed or there is a problem in the subsequent service hosting process, the manual customer service can intervene in the appeal confirmation hosting stage, instruct to exit the appeal confirmation hosting stage, and transfer the interactive dialogue data to a skill group for solving such problems for processing by the manual customer service or the customer service robot.

[0042] In specific implementation, the appeal confirmation model is used to identify the target appeal of the target object according to the interactive dialogue data, and the target appeal corresponding to the target object is obtained. In the case that the user appeal cannot be obtained from the interactive dialogue data, the appeal confirmation model is used to identify the target appeal of the target object according to the interactive dialogue data, and the target appeal corresponding to the target object is obtained. In a case where the user demand cannot be obtained from the interactive dialogue data, the target object is subjected to demand identification based on a demand confirmation model and the interactive dialogue data, to obtain a target demand corresponding to the target object. The interactive dialogue data is subjected to semantic analysis, to obtain a semantic analysis result. In a case where the user demand cannot be obtained from the interactive dialogue data according to the semantic analysis result, the target object is subjected to demand identification based on a demand confirmation model and the interactive dialogue data, to obtain a target demand corresponding to the target object.

[0043] Specifically, after obtaining the interactive dialogue data, the interactive dialogue data can be subjected to semantic analysis, to obtain a semantic analysis result. In a case where the user demand cannot be obtained from the interactive dialogue data according to the semantic analysis result, the next round of interactive dialogue between the user and the target object can be subjected to demand identification based on a demand confirmation model and the interactive dialogue data of the next round of interactive dialogue, to obtain a target demand corresponding to the target object.

[0044] In actual application, when the interactive dialogue data is subjected to semantic analysis, the interactive dialogue data can be subjected to semantic analysis based on a language analysis rule. For example, the meaning of the interactive dialogue data can be understood by using the syntactic structure, part-of-speech tagging, and lexical semantic information specified in the language analysis rule, to obtain a semantic analysis result. Alternatively, the co-occurrence frequency of words in the interactive dialogue data and other statistical features can be calculated by using data in a large-scale corpus, and the semantic relationship between the words in the interactive dialogue data can be inferred according to these statistical features, to obtain a semantic analysis result. Alternatively, the semantic analysis of the interactive dialogue data can be implemented based on a semantic analysis model. The semantic analysis model can be a natural language processing model, a machine learning model, or a deep learning model trained based on a training data set of a semantic analysis task, and the present specification does not limit the same.

[0045] In addition, when the interactive dialogue data is subjected to semantic analysis, it can also be determined whether the interactive dialogue data contains a preset demand keyword according to the preset demand keyword. If not, it indicates that the user demand cannot be obtained from the interactive dialogue data. The preset demand keyword can be determined according to actual project requirements. In the field of e-commerce platforms, the preset demand keyword can include return, refund, and exchange.

[0046] In summary, by first performing simple appeal judgment on the interactive dialogue data related to the target object, in the case where the user appeal cannot be directly obtained from the interactive dialogue data, the appeal confirmation hosting stage can be entered, and the appeal confirmation model is used to perform secondary appeal confirmation on the target object, to realize automatic confirmation of the target appeal based on the agent, to reduce the labor cost while ensuring the accuracy of the determined target appeal, and to further ensure the consultation experience of the user.

[0047] In a specific implementation, the appeal confirmation model is used to perform appeal identification on the target object based on the interactive dialogue data, to obtain the target appeal corresponding to the target object, including: The appeal confirmation model is used to obtain the object information of the target object based on the interactive dialogue data. The appeal confirmation guiding dialogue data is generated based on the object information of the target object and the interactive dialogue data, and the appeal confirmation guiding dialogue data is sent to the target user who initiates the consultation request. The consultation dialogue data returned by the target user based on the appeal confirmation guiding dialogue data is received, and appeal identification is performed on the appeal confirmation guiding dialogue data and the consultation dialogue data, to obtain the target appeal corresponding to the target object.

[0048] In the case where the target object is a target order, the object information of the target object can include but is not limited to an order number, an order creation time, an order payment state, an order payment method, buyer information (i.e., user information), seller information, order current state information, product information of a product corresponding to the target object, logistics information, after-sales service information, etc. The appeal confirmation guiding dialogue data can be understood as dialogue data generated by the appeal confirmation model and used to guide the user to speak the target appeal for the target object. The consultation dialogue data can be understood as dialogue data replied by the target user of the target object based on the appeal confirmation guiding dialogue data.

[0049] Specifically, the appeal confirmation model can obtain the object information of the target object based on the interactive dialogue data, and generate the appeal confirmation guiding dialogue data based on the object information of the target object and the interactive dialogue data, and send the appeal confirmation guiding dialogue data to the client of the target user who initiates the consultation request, to guide the target user to speak his own appeal. The consultation dialogue data replied by the target user based on the appeal confirmation guiding dialogue data is received, and appeal identification is performed on the appeal confirmation guiding dialogue data and the consultation dialogue data, to obtain the target appeal corresponding to the target object.

[0050] In actual applications, the demand confirmation model and the target user can have multiple rounds of interactive dialogue. Specifically, the demand confirmation model sends demand confirmation guidance dialogue data to the target user, the target user responds to the consultation dialogue data, and the demand confirmation model continues to generate the next round of demand confirmation guidance dialogue data based on the consultation dialogue data. The target user continues to respond to the next round of consultation dialogue data until the target demand can be obtained from the demand confirmation guidance dialogue data and the consultation dialogue data. Furthermore, if the dialogue rounds reach the preset round threshold and the target demand cannot be confirmed, or if other exit rules are met, the demand confirmation hosting process can be exited and transferred to manual customer service for processing.

[0051] In summary, by conducting interactive dialogues with target users based on the demand confirmation model, secondary confirmation of the target demand can be achieved, which reduces labor costs and facilitates subsequent processing of the target demand.

[0052] Step 206 : When it is determined that the target demand meets the demand processing conditions, the target demand and the object information of the target object are input into a demand processing model, and the target demand is processed based on the demand processing model.

[0053] Specifically, after determining the user's target demand for the target object, if it is determined that the target demand meets the demand processing conditions, the target demand and the object information of the target object can be input into the demand processing model, and the target demand can be processed according to the object information of the target object based on the demand processing model.

[0054] Among them, the claim processing conditions can be understood as the conditions for judging whether the target claim can be processed. The claim processing conditions can be determined according to the actual needs of the project. The claim processing conditions can be pre-configured according to the project. For example, in the case where the target claim is a refund claim, the claim processing conditions can be "the user level of the target user meets the preset level threshold, and the target object is within the refund period", etc. Then, when the user level of the target user of the target object meets the preset level threshold, and the target object is within the refund period, it can be determined that the target claim corresponding to the target object meets the claim processing conditions. The claim processing model can be understood as an intelligent agent used to process the target claim, which can be a virtual person, a robot, a machine learning model obtained after training for the claim processing task, a deep learning model, etc. For example, in the case where the target claim is a refund claim, a refund can be processed for the target object based on the claim processing model. In the case where the target object is a target order, the object information of the target object can be understood as the order information of the target order. In the case where the target object is a target account, the object information of the target object can be understood as the account information of the target account.

[0055] Based on this, in the case where it is determined that the target appeal can be processed according to the pre-configured appeal processing condition, the target appeal and the object information of the target object can be input to the appeal processing model, at this time, the service acceptance hosting phase can be entered, and the target appeal is processed according to the object information of the target object based on the appeal processing model.

[0056] In actual application, referring to Figure 4 , Figure 4 A technical architecture diagram of a data processing method provided according to one embodiment of the present specification is shown, as shown in Figure 4 The target user can enter the agent service through the intelligent customer service robot of the customer service consultation page, the interactive dialogue data and the like can be routed to the router, the online service can be dispatched by the dispatcher, and the customer service and the speech expression can be locked, the hosting admission, hosting creation, speech chat message notification, speech sending and hosting exit can be performed by calling the knowledge base, the hosting intelligent agent can perform hosting instance management, memory management and tool calling, and can also call the algorithm intelligent agent component, call the large model decision and model routing, and the hosting intelligent agent can perform scheme execution of the service scheme based on the hosting decision of one interactive dialogue. The target user and the intelligent customer service robot perform interactive dialogue to obtain interactive dialogue data related to the target object, and enter the artificial dispatching to determine whether the target appeal can be directly obtained from the interactive dialogue data through routing judgment. If the target appeal cannot be directly obtained, it means that the virtual person confirmation rule is hit, and the target object and the interactive dialogue data are routed to the skill group under centralized supervision for centralized hosting, that is, the appeal confirmation phase is entered. In the hosting process, the appeal confirmation model (i.e., the customer service robot) can be called for decision and interactive dialogue with the target user. At this time, the artificial customer service can monitor the interactive dialogue between the customer service robot and the target user. During the interactive dialogue between the customer service robot and the target user, the customer service robot can perform secondary appeal confirmation according to the interactive dialogue data, and after confirming the target appeal corresponding to the target object, the target appeal and the target object are transferred to another actual acceptance intelligent agent (i.e., the appeal processing model) for scheme acceptance, that is, the target appeal is processed, and the service acceptance hosting phase is entered. In the actual hosting process, in the case where the target appeal is changed or needs to be re-confirmed, the target object can be transferred to the appeal confirmation phase again for appeal confirmation by the appeal confirmation model in the form of dialogue with the target user.

[0057] Specifically, the inputting the target appeal and the object information of the target object to the appeal processing model in the case where it is determined that the target appeal satisfies the appeal processing condition comprises: determining the object information of the target object; In a case where it is determined according to the object information that the target appeal meets an appeal processing condition, inputting the target appeal and the object information of the target object to an appeal processing model, wherein the appeal processing condition is preconfigured according to an appeal type of the target appeal.

[0058] The appeal type can include a refund type, an exchange type, a return type, etc., and the appeal processing condition can include an appeal processing condition corresponding to each appeal type. For example, the appeal processing condition of a refund appeal can be different from the appeal processing condition of an exchange appeal. Specifically, the appeal processing condition of a refund appeal can be that the target object is within a refund period of 7 days, and the appeal processing condition of an exchange appeal can be that the target object is within an exchange period of 40 days.

[0059] Specifically, the object information of the target object can be determined. In a case where it is determined according to the object information that the target appeal meets an appeal processing condition, the target appeal and the object information of the target object are input to an appeal processing model.

[0060] In summary, by preconfiguring the appeal processing condition according to the appeal type, it is convenient to determine whether the target appeal meets the appeal processing condition, so as to determine whether the target object can be transferred to the service hosting stage for processing of the target appeal, thereby further ensuring the appeal processing efficiency.

[0061] Further, in a case where it is determined that the target appeal meets an appeal processing condition, the target appeal and the object information of the target object are input to an appeal processing model, and the target appeal is processed based on the appeal processing model. In a case where it is determined that the target appeal meets an appeal processing condition, the appeal type of the target appeal is determined, and an appeal processing model corresponding to the appeal type is determined. The target appeal and the object information of the target object are input to the appeal processing model, and the target appeal is processed based on the appeal processing model.

[0062] The appeal processing model can include appeal processing models corresponding to multiple appeal types. For example, the appeal processing model can include a pre-sale appeal processing model and an after-sale appeal processing model. The pre-sale appeal processing model can be used to process pre-sale appeals, such as a product link query appeal, a product size consultation appeal, etc. The after-sale appeal processing model can be used to process after-sale appeals, such as a return appeal, an exchange appeal, etc.

[0063] Specifically, in a case where it is determined that the target appeal meets an appeal processing condition, the appeal type of the target appeal can be determined, so as to determine an appeal processing model corresponding to the appeal type. Then, the target appeal can be processed based on the appeal processing model corresponding to the appeal type.

[0064] In summary, by assigning the target appeal to the appeal processing model corresponding to the appeal type, efficient processing of the target appeal is achieved.

[0065] In addition, after inputting the target appeal and the object information of the target object into the appeal processing model, the method further includes: In a case where it is determined that the target appeal is changed, the processing of the target appeal is stopped, and the changed target appeal is determined; The changed target appeal is input into the appeal confirmation model, and the changed target appeal is re-identified based on the appeal confirmation model.

[0066] Specifically, in the service hosting stage, the appeal processing model can also interact with the target user in the processing process of the target appeal to process the target appeal. In a case where the target user proposes to change the target appeal, the appeal processing model can stop processing the target appeal, determine the changed target appeal according to the current interactive dialogue, and send the changed target appeal, the current interactive dialogue and the target object to the appeal confirmation model again, and transfer to the appeal confirmation model to re-identify the changed target appeal, so as to ensure accurate identification of the changed target appeal.

[0067] Further, after determining the changed target appeal, the method further includes: determining the changed appeal type of the changed target appeal, and determining the changed appeal processing model corresponding to the changed appeal type; inputting the changed target appeal and the object information of the target object into the changed appeal processing model, and processing the target appeal based on the changed appeal processing model.

[0068] The changed appeal type can be understood as the appeal type of the changed target appeal, and the changed appeal processing model can be understood as the appeal processing model corresponding to the appeal type of the changed target appeal.

[0069] Specifically, after determining the changed target appeal, the appeal type of the changed target appeal can be determined, and the appeal processing model corresponding to the appeal type can be determined, and the changed target appeal can be processed directly based on the appeal processing model.

[0070] In actual application, the virtual person confirms that it can exist as an intelligent agent for claim confirmation on the workbench (i.e., a claim confirmation model), and can exist as multiple intelligent agents for claim confirmation on the customer service consultation page (i.e., a pre-sale claim confirmation model and an after-sale claim confirmation model). After the target user enters the customer service consultation page, the intention of the target user can be identified based on the interactive dialogue data between the target user, and the target object corresponding to the target user can be routed to the corresponding intelligent agent (the pre-sale claim confirmation model or the after-sale claim confirmation model). According to the default rule, the target object can be routed to the after-sale claim confirmation model. In the decision-making process, the after-sale claim confirmation model can identify the target user's ear problem based on the interactive dialogue data, recall of pre-sale and after-sale knowledge, and entity recall, clarify the problem, and finally give the identified knowledge, so as to confirm the target claim according to the identified knowledge. After the claim confirmation model on the customer service consultation page determines the target claim, an instruction can be generated for the workbench, and the workbench can determine whether to transfer to the pre-sale claim processing model or the after-sale claim processing model for processing the target claim according to the configured processing condition (i.e., a claim processing condition). If the pre-sale claim processing model or the after-sale claim processing model identifies that the target claim has changed during the service process, the virtual person confirmation stage can be transferred to, and the claim confirmation model can be used to continue claim confirmation.

[0071] In summary, in the above method, after receiving a consultation request for a target object, interactive dialogue data related to the target object can be obtained. In the case where the user claim cannot be confirmed from the interactive dialogue data, the target object can be identified based on a claim confirmation model to obtain a target claim corresponding to the target object. In the case where the target claim meets a claim processing condition, the target claim and object information related to the target object can be input to a claim processing model, and the target claim can be processed based on the claim processing model. By using the claim confirmation model and the claim processing model, the user's claim for the target object can be confirmed and processed respectively, without the need for manual customer service and user dialogue and processing, reducing the waste of human cost. The consultation request of the user is processed based on the two models, ensuring the speed and efficiency of responding to the consultation request, and further improving the user experience.

[0072] The following describes the data processing method in combination with the accompanying Figure 5 The data processing method provided in the specification is taken as an example of application in an e-commerce platform. Wherein, Figure 5 A flowchart of a processing process of a data processing method provided in an embodiment of the specification is shown, which specifically includes the following steps.

[0073] Step 502: The target user initiates a consultation request for a target order.

[0074] Step 504: The target user and the customer service robot carry out an interactive dialogue.

[0075] Step 506: Claim confirmation hosting.

[0076] In the claim confirmation hosting stage, the pre-sale claim confirmation agent or the after-sale claim confirmation agent can confirm the target order based on the current interactive dialogue data. The workbench can make decisions in the claim confirmation hosting stage, which can include claim confirmed, claim clarification, claim clarified, dialogue sending, and sending playing, to realize the confirmation of the target claim and the interactive dialogue with the target user. The workbench can determine whether the target claim can be confirmed and enter the subsequent hosting access based on the decision result.

[0077] Step 508: Determine the target claim and execute the subsequent hosting access.

[0078] After determining the target claim, it is handed over to the subsequent service hosting stage.

[0079] Step 510: Determine whether it can continue to host, if not, execute step 512, if yes, execute step 514.

[0080] Specifically, it can be determined whether the target claim meets the claim processing condition, if yes, it is determined that it can continue to host, if not, it is determined that it cannot continue to host.

[0081] Step 512: Artificial hosting.

[0082] Step 514: Execute claim confirmation post-hosting.

[0083] Step 516: Start playing the solution.

[0084] Specifically, the target claim can be processed according to the preset processing rule, and the solution playing is started, which can be the operation of the target claim or the inquiry dialogue sending to the target user, etc.

[0085] Step 518: Enter the pre-sale hosting agent or the after-sale hosting agent.

[0086] Step 520: Solution post-process.

[0087] Specifically, the processing method given in the previous interactive dialogue data can be explained and further questioned and answered based on the further interactive dialogue data between the user and the given processing solution, the emotion recognition result can be obtained according to the emotion recognition of all the interactive dialogue data between the user and the given processing solution, and the soothing dialogue can be sent to the user in the case where the user's emotion is determined to be excited according to the emotion recognition result.

[0088] Step 522: in the case of determining the target appeal change, shift to the appeal confirmation hosting stage to re-determine the target appeal.

[0089] In the above method, after receiving the consultation request for the target order, the interactive dialogue data related to the target order can be acquired. In the case where the user appeal cannot be confirmed from the interactive dialogue data, the target order can be subjected to appeal identification based on the appeal confirmation model to obtain the target appeal corresponding to the target order. In the case where it is determined that the target appeal meets the appeal processing condition, the target appeal and the order information related to the target order are input into the appeal processing model, and the target appeal is processed based on the appeal processing model. By using the appeal confirmation model and the appeal processing model, the appeal of the user to the target order is confirmed and processed respectively, without the need for manual customer service and user dialogue and processing, reducing the waste of human cost. The consultation request of the user is processed based on the two models of the appeal confirmation model and the appeal processing model, ensuring the speed and efficiency of responding to the consultation request, and further improving the user experience.

[0090] Corresponding to the above method embodiments, the present specification also provides data processing device embodiments, Figure 6 A structural schematic diagram of a data processing device provided by one embodiment of the present specification is shown. As shown in the figure, Figure 6 The device comprises: The acquisition module 602 is configured to acquire interactive dialogue data related to the target object in response to a consultation request for the target object. The identification module 604 is configured to perform appeal identification on the target object based on the appeal confirmation model according to the interactive dialogue data, and obtain the target appeal corresponding to the target object. The processing module 606 is configured to input the target appeal and the object information of the target object into the appeal processing model in the case where it is determined that the target appeal meets the appeal processing condition, and process the target appeal based on the appeal processing model.

[0091] In an optional embodiment, the identification module 604 is further configured to: In the case where the user appeal cannot be acquired from the interactive dialogue data, perform appeal identification on the target object based on the appeal confirmation model according to the interactive dialogue data, and obtain the target appeal corresponding to the target object.

[0092] In an optional embodiment, the identification module 604 is further configured to: Perform semantic analysis on the interactive dialogue data to obtain a semantic analysis result. In a case where it is determined according to the semantic analysis result that the user demand cannot be acquired from the interactive dialogue data, a demand recognition is performed on the target object according to the interactive dialogue data based on a demand confirmation model, and a target demand corresponding to the target object is acquired.

[0093] In an optional embodiment, the identification module 604 is further configured to: acquire object information of the target object according to the interactive dialogue data based on the demand confirmation model; generate demand confirmation guide dialogue data according to the object information of the target object and the interactive dialogue data, and send the demand confirmation guide dialogue data to the target user who initiates the consultation request; receive consultation dialogue data returned by the target user based on the demand confirmation guide dialogue data, perform demand recognition on the demand confirmation guide dialogue data and the consultation dialogue data, and acquire a target demand corresponding to the target object.

[0094] In an optional embodiment, the processing module 606 is further configured to: determine object information of the target object; in a case where it is determined according to the object information that the target demand satisfies a demand processing condition, input the target demand and the object information of the target object into a demand processing model, wherein the demand processing condition is preconfigured according to a demand type of the target demand.

[0095] In an optional embodiment, the processing module 606 is further configured to: in a case where it is determined that the target demand satisfies a demand processing condition, determine a demand type of the target demand and determine a demand processing model corresponding to the demand type; input the target demand and the object information of the target object into the demand processing model, and process the target demand based on the demand processing model.

[0096] In an optional embodiment, the processing module 606 is further configured to: in a case where it is determined that the target demand is changed, stop processing the target demand, and determine a changed target demand; input the changed target demand into the demand confirmation model, and re-identify the changed target demand based on the demand confirmation model.

[0097] In an optional embodiment, the processing module 606 is further configured to: determine a changed appeal type of the changed target appeal, and determine a changed appeal processing model corresponding to the changed appeal type; input the changed target appeal and object information of the target object into the changed appeal processing model, and process the target appeal based on the changed appeal processing model.

[0098] In the device, after receiving the consultation request for the target object, the interactive dialogue data related to the target object can be obtained. In a case where the user appeal cannot be confirmed from the interactive dialogue data, the interactive dialogue data is subjected to appeal identification based on the appeal confirmation model to obtain the target appeal corresponding to the target object. In a case where it is determined that the target appeal meets the appeal processing condition, the target appeal and the object information related to the target object are input into the appeal processing model, and the target appeal is processed based on the appeal processing model. By using the appeal confirmation model and the appeal processing model, the appeal of the user to the target object is confirmed and processed respectively, without the need for manual customer service and user dialogue and processing, reducing the waste of human cost. The consultation request of the user is processed based on the two models, ensuring the speed and efficiency of responding to the consultation request, and further improving the user experience.

[0099] The above is a schematic scheme of the data processing device of the embodiment. It should be noted that the technical scheme of the data processing device belongs to the same concept as the technical scheme of the data processing method described above. The details of the technical scheme of the data processing device that are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0100] Corresponding to the method embodiments described above, the present specification also provides data processing system embodiments, Figure 7 A structural schematic diagram of a data processing system provided by an embodiment of the present specification is shown. As shown in the figure, Figure 7 The system includes a first intelligent decision unit 702 and a second intelligent decision unit 704, wherein, The first intelligent decision unit 702 is configured to, in a case where a user appeal cannot be obtained from interactive dialogue data, identify the appeal of a target object to obtain a target appeal corresponding to the target object, and in a case where it is determined that the target appeal meets an appeal processing condition, send the target appeal and object information of the target object to the second intelligent decision unit. The interactive dialogue data is interactive dialogue data related to the target object obtained in response to a consultation request for the target object. The second intelligent decision unit 704 is configured to process the target appeal.

[0101] The first intelligent decision unit can be understood as an intelligent agent for confirming the appeal, and can refer to the appeal confirmation model in the data processing method. The second intelligent decision unit can be understood as an intelligent agent for processing the appeal, and can refer to the appeal processing model in the data processing method.

[0102] Specifically, after receiving the consultation request for the target object, the interactive dialogue data related to the target object can be obtained. In the case where the user appeal cannot be confirmed from the interactive dialogue data, the first intelligent decision unit can be used to identify the appeal of the target object, obtain the target appeal corresponding to the target object, and in the case where it is determined that the target appeal meets the appeal processing condition, the target appeal and the object information related to the target object are transferred to the second intelligent decision unit, and the target appeal is processed based on the second intelligent decision unit. Specifically, the second intelligent decision unit can enter the pre-sale appeal management or the post-sale appeal management according to the type of the target appeal. In addition, the second intelligent decision unit can transfer the target appeal and the related information of the target appeal to the first intelligent decision unit for re-appeal identification in the case where the target appeal is changed.

[0103] By using the first intelligent decision unit and the second intelligent decision unit, the appeal of the target object by the user is confirmed and processed respectively, without the need for manual customer service and user dialogue and processing, reducing the waste of human cost. The consultation request of the user is processed based on the two intelligent agents, ensuring the speed and efficiency of responding to the consultation request, and further improving the user experience.

[0104] The above is a schematic scheme of a data processing system of the embodiment. It should be noted that the technical scheme of the data processing system belongs to the same concept as the technical scheme of the data processing method described above. The details of the technical scheme of the data processing system that are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0105] Figure 8 A structural block diagram of a computing device 800 according to one embodiment of the present specification is shown. The 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 through a bus 830, and a database 850 is used to save data.

[0106] 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 combinations of such networks, such as the Internet. The access device 840 can include one or more of any type of network interface (for example, a network interface card (NIC)) 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, or the like.

[0107] In one embodiment of the present application, the above-mentioned components of the computing device 800, as well as other components not shown in FIG. 8, can be connected to each other by a bus. It should be understood that Figure 8 the computing device structure diagram shown is only for the purpose of example, and is not a limitation on the scope of the present application. Those skilled in the art can add or replace other components as needed. Figure 8 the computing device structure diagram shown is only for the purpose of example, and is not a limitation on the scope of the present application. Those skilled in the art can add or replace other components as needed.

[0108] The computing device 800 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (for example, a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, and the like), a mobile phone (for example, a smartphone), a wearable computing device (for example, a smart watch, smart glasses, and the like), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 800 can also be a mobile or stationary server.

[0109] The processor 820 is configured to execute instructions from a computer program or instructions, which when executed by the processor, implement the steps of the above-mentioned data processing method.

[0110] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts among the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, the computing device embodiment is described simply because it is basically similar to the data processing method embodiment, and the relevant part can be referred to the description of the data processing method embodiment.

[0111] An embodiment of the specification further provides a computer readable storage medium storing computer programs / instructions, which are executed by a processor to implement the steps of the above data processing method.

[0112] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts among the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, the computer readable storage medium embodiment is described simply because it is basically similar to the data processing method embodiment, and the relevant part can be referred to the description of the data processing method embodiment.

[0113] An embodiment of the specification further provides a computer program product including computer programs / instructions, which are executed by a processor to implement the steps of the above data processing method.

[0114] The above is a schematic scheme of the computer program product of the embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the above data processing method belong to the same concept, and the details of the technical scheme of the computer program product which are not described in detail can be referred to the description of the technical scheme of the data processing method.

[0115] The above describes specific embodiments of the specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps in a claim can be performed in an order different than the order in which the acts or steps are recited, and still accomplish the desired results. Also, the process depicted in the accompanying figures does not necessarily require the particular order shown, or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0116] The computer readable medium can include any entity or apparatus capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, software distribution medium, etc. It should be noted that the computer readable medium can include appropriate additions or subtractions according to the requirements of patent practice. For example, according to the patent practice in some regions, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0117] It should be noted that, for the foregoing method embodiments, in order to facilitate description, they are all described as a combination of a series of actions, but those skilled in the art should know that the embodiments of the present specification are not limited by the order of the described actions, because according to the embodiments of the present specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of the present specification.

[0118] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0119] The preferred embodiments of the present specification disclosed above are only used to help explain the present specification. The alternative embodiments do not describe all the details and limit the invention to the specific embodiments described. Obviously, according to the content of the embodiments of the present specification, many modifications and changes can be made. The present specification selects and describes these embodiments in order to better explain the principles and practical applications of the embodiments of the present specification, so that those skilled in the art can well understand and use the present specification. The present specification is limited by the claims and their entire scope and equivalents.

Claims

1. A data processing method, comprising: In response to a consultation request for a target object, obtaining interactive dialogue data related to the target object; Based on the demand confirmation model, the demand of the target object is identified according to the interactive dialogue data to obtain the target demand corresponding to the target object; When it is determined that the target demand meets the demand processing condition, the target demand and the object information of the target object are input into a demand processing model, and the target demand is processed based on the demand processing model.

2. The method according to claim 1, wherein the step of identifying the demands of the target object based on the interactive dialogue data based on the demand confirmation model to obtain the target demand corresponding to the target object comprises: In the case where the user demand cannot be obtained from the interactive dialogue data, based on the demand confirmation model, the demand of the target object is identified according to the interactive dialogue data to obtain the target demand corresponding to the target object; In the case where the user demand cannot be obtained from the interactive dialogue data, based on the demand confirmation model, the demand of the target object is identified according to the interactive dialogue data to obtain the target demand corresponding to the target object, including: Performing semantic analysis on the interactive dialogue data to obtain a semantic analysis result; When it is determined that the user demand cannot be obtained from the interactive dialogue data according to the semantic analysis result, the demand of the target object is identified based on the interactive dialogue data based on the demand confirmation model to obtain the target demand corresponding to the target object.

3. The method according to claim 1 or 2, wherein the step of identifying the demands of the target object based on the interactive dialogue data based on the demand confirmation model to obtain the target demand corresponding to the target object comprises: Based on the demand confirmation model, and according to the interactive dialogue data, obtaining object information of the target object; generating demand confirmation guiding dialogue data according to the object information of the target object and the interactive dialogue data, and sending the demand confirmation guiding dialogue data to the target user who initiated the consultation request; Receive the consultation dialogue data returned by the target user based on the demand confirmation guiding dialogue data, perform demand identification on the demand confirmation guiding dialogue data and the consultation dialogue data, and obtain the target demand corresponding to the target object.

4. The method according to claim 1, wherein, when determining that the target demand satisfies a demand processing condition, inputting the target demand and the object information of the target object into a demand processing model comprises: Determining object information of the target object; When it is determined according to the object information that the target demand satisfies a demand processing condition, the target demand and the object information of the target object are input into a demand processing model, wherein the demand processing condition is pre-configured according to the demand type of the target demand.

5. The method according to claim 1, wherein, when determining that the target demand satisfies a demand processing condition, inputting the target demand and the object information of the target object into a demand processing model, and processing the target demand based on the demand processing model, comprises: When it is determined that the target demand meets the demand processing conditions, determining the demand type of the target demand and determining the demand processing model corresponding to the demand type; The target demand and the object information of the target object are input into the demand processing model, and the target demand is processed based on the demand processing model.

6. The method according to any one of claims 1-2, 4-5, further comprising: after inputting the target demand and the target object information into the demand processing model; When it is determined that the target demand has been changed, stopping processing the target demand and determining the changed target demand; The changed target demand is input into the demand confirmation model, and the changed target demand is re-identified based on the demand confirmation model.

7. The method according to claim 6, further comprising: Determine the change request type of the changed target request, and determine the change request processing model corresponding to the change request type; The changed target requirement and the object information of the target object are input into the change requirement processing model, and the target requirement is processed based on the change requirement processing model.

8. A data processing system comprising a first intelligent decision-making unit and a second intelligent decision-making unit, wherein: The first intelligent decision-making unit is configured to, if unable to obtain the user demand from the interactive dialogue data, perform demand identification on the target object, obtain a target demand corresponding to the target object, and, if determining that the target demand satisfies a demand processing condition, send the target demand and the object information of the target object to the second intelligent decision-making unit, wherein the interactive dialogue data is interactive dialogue data related to the target object obtained in response to a consultation request for the target object; The second intelligent decision-making unit is used to process the target demand.

9. 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 7 are implemented.

10. A computer-readable storage medium storing a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program / instruction, which implements the steps of the method according to any one of claims 1 to 7 when executed by a processor.

Images