Data processing method, computing device, storage medium and computer program product

Abstract

The embodiment of the invention provides a data processing method, computing equipment, a storage medium and a computer program product, and the data processing method comprises the steps: obtaining a target problem for a target order in response to an order consultation request for the target order; and according to the target question and order summary information of the target order, determining a target answer corresponding to the target question, the order summary information being generated according to a historical processing event corresponding to the target order. The target problem is specifically solved according to the order summary information, a lot of time is not needed to query and integrate the order information related to the target order, the response speed of the target problem is improved, the problem solving efficiency of the target problem is further ensured, and the interaction experience of a user who puts forward the target problem is ensured.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of artificial intelligence technology, and in particular to data processing methods, computing devices, storage media, and computer program products. Background Art

[0002] With the development of network technology, people have gradually shifted from offline shopping to online shopping through e-commerce platforms. However, when purchasing goods through e-commerce platforms, they cannot see the actual goods, or need to make after-sales operations such as refunds and returns on the e-commerce platform, so they usually need to consult customer service on the e-commerce platform. In order to ensure that customer service can respond to and solve user questions in a timely manner, it is usually necessary to access the context related to the user's questions. However, due to the huge amount of information involved in e-commerce platforms and the fact that relevant information is usually distributed across different systems and platforms, it is difficult for customer service to quickly obtain a complete picture of user information and orders. It takes extra time to query and integrate relevant information, which reduces the customer service's response speed to user questions, affects the efficiency of problem solving, and leads to a poor user experience. Therefore, an effective technical solution is urgently needed to solve the above problems. Summary of the Invention

[0003] In view of this, the embodiments of this specification provide two data processing methods. One or more embodiments of this specification also involve two data processing devices, a data 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, there is provided a data processing method, including: In response to an order inquiry request for a target order, obtaining a target question for the target order; A target answer corresponding to the target question is determined according to the target question and order summary information of the target order, wherein the order summary information is generated according to historical processing events corresponding to the target order.

[0005] According to a second aspect of the embodiments of this specification, there is provided a data processing device, including: an acquisition module, configured to acquire a target question for a target order in response to an order inquiry request for the target order; The determination module is configured to determine a target answer corresponding to the target question based on the target question and order summary information of the target order, wherein the order summary information is generated based on historical processing events corresponding to the target order.

[0006] According to a third aspect of the embodiments of this specification, another data processing method is provided, which is applied to a server, including: In response to an order inquiry request for a target order sent by a client, obtaining a target question for the target order; According to the target question and the order summary information of the target order, a target answer corresponding to the target question is determined, and the target answer is sent to the client, wherein the order summary information is generated according to the historical processing events corresponding to the target order.

[0007] According to a fourth aspect of the embodiments of this specification, another data processing device is provided, which is applied to a server, including: an acquisition module configured to, in response to an order inquiry request for a target order sent by a client, acquire a target question for the target order; A determination module is configured to determine a target answer corresponding to the target question based on the target question and order summary information of the target order, and send the target answer to the client, wherein the order summary information is generated based on historical processing events corresponding to the target order.

[0008] According to a fifth aspect of the embodiments of this specification, a data processing system is provided, including an intelligent decision-making unit and a data storage platform, wherein: The intelligent decision-making unit is configured to, in response to an order inquiry request for a target order sent by a client, obtain order summary information of the target order from the data storage platform, wherein the order summary information is generated based on historical processing events corresponding to the target order; The intelligent decision-making unit is further used to receive a target question for the target order sent by the client, determine a target answer corresponding to the target question based on the target question and the order summary information, and send the target answer to the client.

[0009] According to a sixth aspect of the embodiments of this specification, there is provided a computing device, 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 data processing method are implemented.

[0010] According to a seventh 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 data processing method are implemented.

[0011] According to an eighth 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 data processing method when executed by a processor.

[0012] One embodiment of the present specification provides a data processing method, comprising: obtaining a target question for a target order in response to an order consultation request for the target order; and determining a target answer corresponding to the target question based on the target question and order summary information of the target order, wherein the order summary information is generated based on historical processing events corresponding to the target order.

[0013] In the above method, in response to the user's order consultation request for the target order, the user's target question for the target order can be obtained, and the target answer to the target question can be determined based on the target question and the order summary information of the target order. The order summary information of the target order is generated based on the historical processing events corresponding to the target order, so that the target problem can be solved in a targeted manner according to the order summary information, without spending a lot of time to query and integrate the order information related to the target order, thereby improving the response speed to the target problem, further ensuring the problem-solving efficiency of the target problem, and ensuring the interactive experience of the user who raised the target question. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a schematic diagram of an application scenario of a data processing method provided by an embodiment of this specification; Figure 2 is a flow chart of a data processing method provided by one embodiment of this specification; Figure 3 This is a flowchart of a data processing method provided by one embodiment of this specification; Figure 4 This is a schematic diagram of the structure of a data processing device provided by one embodiment of this specification; Figure 5 is a flow chart of another data processing method provided by one embodiment of this specification; Figure 6 is a structural diagram of another data processing device provided by an embodiment of this specification; Figure 7 This is a schematic diagram of the structure of a data processing system provided by one embodiment of this specification; Figure 8 This is a structural block diagram of a computing device provided by one embodiment of this specification. DETAILED DESCRIPTION

[0015] 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.

[0016] 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.

[0017] 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".

[0018] 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.

[0019] First, the terms involved in one or more embodiments of this specification are explained.

[0020] 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.

[0021] In actual applications, e-commerce platforms usually require a large number of customer service representatives to handle user questions. For example, they need to answer questions about compensation for logistics delays, help with communication difficulties with merchants after a refund request is rejected, and inquiries about the progress of ongoing issues. When handling these issues, customer service representatives usually need certain contextual information to quickly locate user requests. However, the amount of information involved in each link of the entire product chain on e-commerce platforms is huge and scattered. It is extremely difficult for customer service representatives to understand the full picture of the orders related to the user's questions. They often need to consult in detail and browse different platforms to understand the order information related to the question. This can easily cause users to lose patience and give up on customer service consultations, making it difficult for users to get their questions resolved, affecting the user experience. Therefore, an effective technical solution is urgently needed to solve the above problems.

[0022] In this specification, two data processing methods are provided. This specification also involves two data processing devices, 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.

[0023] See also Figure 1 , Figure 1 A schematic diagram of an application scenario of a data processing method provided according to an embodiment of this specification is shown. The data processing method includes the following steps.

[0024] In response to an order inquiry request for a target order, obtaining a target question for the target order; A target answer corresponding to the target question is determined according to the target question and order summary information of the target order, wherein the order summary information is generated according to historical processing events corresponding to the target order.

[0025] like Figure 1 As shown, Figure 1 It includes a terminal side device 102 and a cloud side device 104.

[0026] During specific implementation, the user enters the customer service consultation page of the e-commerce platform in the terminal device 102 and sends the order link of the target order. The terminal device 102 generates an order consultation request for the target order and sends it to the cloud device 104. The user enters the target question in the customer service consultation page, and the terminal device 102 sends the target question to the cloud device 104. The cloud device 104 receives the target question for the target order and determines the target answer corresponding to the target question based on the target question and the order summary information of the target order. The order summary information can be generated by the cloud device 104 according to the historical processing events corresponding to the target order. Furthermore, the order summary information can be generated by the cloud device 104 according to the historical processing events corresponding to the target order after receiving the order consultation request, and the target answer is sent to the terminal device 102. The terminal device 102 can display the target answer to the user on the customer service consultation page.

[0027] 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.

[0028] Cloud-side devices 104 can be understood as servers that provide various services, including physical servers and cloud servers. For example, these servers provide communication services to multiple clients, servers that support backend training for models used by clients, and servers that process data sent by clients. It should be noted that cloud-side devices 104 can be implemented as a distributed server cluster consisting of multiple servers or as a single server. Cloud-side devices 104 can also be servers in a distributed system or servers integrated with blockchain. Cloud-side devices 104 can also be cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, or intelligent cloud computing servers or intelligent cloud hosts equipped with artificial intelligence technology.

[0029] It is worth noting that the data processing method provided in the embodiments of this specification can be executed by the cloud-side device 104 or by the end-side device 102; in other embodiments, the data processing method provided in the embodiments of this specification can also be executed jointly by the end-side device 102 and the cloud-side device 104.

[0030] See also Figure 2 , Figure 2 A flow chart of a data processing method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0031] Step 202: In response to an order inquiry request for a target order, a target question for the target order is obtained.

[0032] Specifically, the data processing method provided in the embodiments of this specification can be applied to e-commerce platforms. Specifically, the data processing method can process questions raised by users of the e-commerce platform. For example, when a user purchases a product on the e-commerce platform, consulting questions, after-sales questions, etc. about the product can be processed according to the data processing method. Alternatively, the data processing method provided in the embodiments of this specification can also be applied to other service platforms, such as an education platform, where users can purchase education courses through the education platform, and then the user's related questions about the purchased education courses can also be processed according to the data processing method. For example, it can also be applied to sports software, where users can purchase sports courses and sports equipment in the sports software, and then the user's related questions about the purchased sports courses and sports equipment can be processed according to the data processing method. The embodiments of this specification do not limit the application scenarios of the data processing method. It can be understood that the data processing method provided in the embodiments of this specification can be applied to various service platforms that provide transaction services.

[0033] For ease of understanding, the embodiments of this specification are described using the application of the data processing method to an e-commerce platform as an example.

[0034] The target order can be understood as a purchase order for a product requiring consultation, and the order consultation request can be understood as a consultation request for the target order sent by a user through a client. In practical applications, the order consultation request can be generated by a user accessing the customer service consultation page for the target order on an e-commerce platform. The target question can be a question entered by a user on the customer service consultation page of the e-commerce platform.

[0035] Based on this, the user can log in to the e-commerce platform through the client and enter the customer service consultation page of the target order in the e-commerce platform. At this time, the e-commerce platform receives the order consultation request for the target order and obtains the user's target question for the target order.

[0036] In a specific implementation, after responding to the order inquiry request for the target order, the method further includes: Obtain historical processing events corresponding to the target order; Generate order summary information of the target order according to the historical processing events.

[0037] Among them, historical processing events can be understood as processing events for the target order within a historical time period. Historical processing events can serve as historical trajectory information for the target order. Historical processing events can include logistics processing events, refund processing events, customer service consultation events, and event data related to these processing events. Order summary information can be understood as summary information of historical processing events for the target order. It is understandable that the number of words in the order summary information is smaller than the number of words in the historical processing events. It is understandable that there can be multiple historical processing events corresponding to the target order.

[0038] Specifically, after responding to the order consultation request for the target order and before obtaining the target problem for the target order, the historical processing events corresponding to the target order can be obtained, and order summary information of the target order can be generated based on the historical processing events.

[0039] In actual applications, the historical processing events of the target order can be part of the trajectory information contained in the target order, which includes the order information, logistics information, refund information, consultation chat records between users and merchants, conversation records between users and customer service robots, and the current service progress of the target order. Specifically, historical processing events for a target order may include order- and user-related information. Order-related information may include order-related information, logistics-related information, user-related information, and order service trajectory data. Order-related information may include main order information, sub-order information, and freight insurance information. Main order information may include the main order number, main order management unit, transaction type, seller information, buyer information, seller store, payment time, order status, etc. Sub-order information may include the sub-order number, product information, purchase quantity, actual product price, insurance information, and shipping status. Freight insurance information may include freight insurance premium, freight insurance coverage, insurance company, effective date, and policy status. Logistics-related information may include shipping package information, return package information, exchange package information, buyer receipt information, and seller return information. Shipping package information, return package information, and exchange package information may all include the order number, product title, product purchase quantity, actual product price, logistics order number, logistics company, logistics mode, shipping information, and receiving information. User-related information may include user ID, user nickname, user name, user level, and user membership status. Service track data may include update time, channel information, object information, and update content, and may specifically include chat records, service progress, logistics tracks, refund messages, and service progress messages for the target order and each customer service representative. Service progress may, for example, be the return service progress or exchange service progress for the target order. Information in the user dimension may include human-to-human conversations (i.e., conversations between the user and manual customer service), human-to-machine conversations (i.e., conversations between the user and a customer service robot), orders, refunds, logistics, appeals, complaints, disputes, dispute appeals, compensation, service progress, and other information related to the user who initiated the order consultation request. It is understandable that in the embodiments of this specification, the historical processing events of the target order obtained may be a series of processing events that the target order has experienced since the target order was created. The specific information to be obtained can be determined based on actual needs, and the embodiments of this specification do not limit this.

[0040] Furthermore, when obtaining the historical processing event corresponding to the target order, it can be obtained from the database, and the database can be used to store all order data of the orders created in the e-commerce platform.

[0041] In a specific implementation, generating the order summary information of the target order according to the historical processing event includes: Sorting the historical processing events according to a preset sorting rule to obtain order processing information of the target order; The order processing information is summarized to obtain order summary information of the target order.

[0042] Among them, the preset sorting rules can be understood as the rules for sorting the historical processing events of the target order, the order processing information can be understood as the historical processing track information of the target order obtained after sorting the historical processing events, and the order summary information can be understood as the information summarizing the historical processing track information of the target order. The order summary information may include key information extracted from the historical processing track information, which can describe what processing the target order has undergone within the historical time period, what its current status is, etc. In actual applications, the order summary information can be, for example, "11 days ago, the user said that there was a problem with the quality of the product and hoped to return the product and refund, and the merchant agreed. 2 hours ago, the user expressed his inquiry about the whereabouts of the money, and the platform showed the user that the money had been returned to the original account, and the user expressed satisfaction with the platform's solution."

[0043] Specifically, multiple historical processing events corresponding to the target order can be sorted according to preset sorting rules to obtain historical processing trajectory information of the target order, and key information of the historical processing trajectory information can be extracted and summarized to obtain order summary information of the target order.

[0044] In summary, by sorting historical processing events, we can sort and summarize historical processing events and arrange historical processing events into an effective structure, which is convenient for extracting key information from the order processing information obtained after sorting, ensuring In a specific implementation, the historical processing events are sorted according to a preset sorting rule to obtain the order processing information of the target order, including: sorting the historical processing events according to their priority information to obtain order processing information of the target order; or The historical processing events are sorted according to the processing time of the historical processing events to obtain the order processing information of the target order.

[0045] In one embodiment, the preset sorting rule can be a rule for sorting by the priority of historical processing events, or a rule for sorting by the processing time of historical processing events. It is understandable that the preset sorting rule can be set according to actual needs, and the embodiments of this specification do not limit this. The priority information of historical processing events can be pre-configured, and the priority can be used to indicate the importance of historical processing events. For example, the priority of a product exchange event can be greater than the priority of a shipment event. In other words, in actual applications, the importance of a product exchange event for a product related to a target order can be greater than the importance of a shipment event. In other words, in actual applications, after a user purchases a product and creates a target order, the shipment of the product is an inevitable event, while the user's exchange of the product is an accidental event. The probability of a product exchange event is less than the probability of a shipment event. Therefore, when the historical processing events of the target order include a product exchange event, it may indicate that there is a problem with the product in the target order or that there may be a dispute between the user and the product seller. Therefore, the product exchange event is more important, and the priority of the product exchange event can be set higher than the priority of the shipment event, so that the product exchange event can be sorted in a higher position during sorting. The processing time of historical processing events can be understood as the occurrence time of the historical processing events. For example, a user purchases a product on March 11, the product is shipped on March 12, the user receives the product on March 15, and initiates a return application on March 17. Then, the processing time of the shipping event of the target order in which the user purchased the product is March 12, the processing time of the receipt event is March 15, and the processing time of the return event is March 17. Then, the historical processing events of the target order can be sorted according to the occurrence time, so as to obtain the trajectory information of the processing process of the target order.

[0046] Specifically, in one embodiment of the present specification, priority information of each historical processing event among multiple historical processing events can be obtained, and the multiple historical processing events can be arranged in positive order according to the priority information of each historical processing event, that is, the multiple historical processing events are sorted in order from high to low priority to obtain order processing information of the target order.

[0047] In another embodiment of the present specification, the processing time of each of multiple historical processing events can be obtained, and the multiple historical processing events can be sorted in ascending order or descending order according to the processing time of each historical processing event, that is, the multiple historical processing events can be sorted in order from far to near or from near to far according to the processing time to obtain the order processing information of the target order.

[0048] In practical applications, after obtaining the historical processing events of the target order, the historical processing events can be sorted by different time and modules to obtain standardized and unified processing track information as order processing information. The following shows the order processing information of a target order.

[0049] "Logistics track XX year XX month XX day X hour X minute X second (i.e. the current time of this status) Object information: Package type: Shipping package; Logistics company: XX; Logistics order number: XXX; Update content: Logistics status: Order has been placed; Logistics status details: The product has been ordered; Logistics track XX year XX month XX day X hour X minute X second Object information: Package type: Shipping package; Logistics company: XX; Logistics order number: XXX; Update content: Logistics status: shipped; Logistics status details: waiting for collection; Refund message XX year XX month XX day X hour X minute X second Object information: Sub-order number: XX; Refund type: Refund only; Refund reason: The courier has not been delivered; Goods status: Not received; Refund amount: XX yuan; Update content: Action type: Apply for refund; Action role: User; Action description: Initiated a refund request; Goods status: Not received; Reason: The express delivery has not been delivered; Amount: XX yuan; Chat records between users and customer service robots at XX year XX month XX day X hour X minute X second Subject information: Session number: XX Update content: specific chat content records (the specific chat content records here may include chat time, chat object, chat content and chat end status); Refund message XX year XX month XX day X hour X minute X second Object information: Sub-order number: XX; Refund type: Refund only; Refund reason: The courier has not been delivered; Goods status: Not received; Refund amount: XX yuan Update content: Action type: Agree; Action role: Seller; Action description: The merchant agrees to this after-sales service application.

[0050] Refund message XX year XX month XX day X hour X minute X second Object information: Sub-order number: XX; Refund type: Refund only; Refund reason: The courier has not yet delivered; Goods status: Not received; Refund amount: XX yuan; Update content: Action type: Refund successful; Action role: Seller; Action description: The merchant proactively agrees to refund the buyer XX yuan.

[0051] In summary, by sorting historical processing events according to processing time or priority information, the historical processing events of the target order can be sorted out, making the order processing information that can be used for reference when summarizing by extracting key information clearer, and facilitating a comprehensive and concise summary of subsequent order summary information.

[0052] Furthermore, summarizing the order processing information to obtain order summary information of the target order includes: Inputting the order processing information and the preset prompt word into an information summary model to obtain order summary information of the target order output by the information summary model; Among them, the preset prompt words include task description information, task processing use cases and model output restrictions. The task description information is used to guide the information summary model to summarize the order processing information, the task processing use cases are used to enable the information summary model to summarize the order processing information according to the task processing use cases, and the model output restrictions are used to limit the order summary information output by the information summary model.

[0053] In practical applications, the information summary model can be a natural language processing model, or other machine learning models, deep learning models, etc. that have been trained for information summarization tasks, and the embodiments of this specification do not limit this. The task description information can be, for example, "Please summarize the following content in a short sentence based on the order information of the given target order and the changes that occur over time. It is necessary to use concise content to describe the user's recent problems and corresponding demands from the user's perspective, and describe the solutions provided by the merchant and the platform. Multiple demands can be described in segments." The task processing use case can be an example of the order summary information output by the information summary model, such as "Example: Situation description: 11 days ago, it was used to indicate that there was a problem with the quality of the product and the merchant agreed to return the product and refund. The merchant agreed. 2 hours ago, the user asked about the whereabouts of the money, and the platform showed the user that the money had been returned to the original account. The user was satisfied with the platform's solution." The model output restriction conditions can be the format requirements and restriction conditions for the order summary information output by the information summary model. The format requirements can be, for example, "Description of the situation: XXXX." The restriction conditions can be, for example, "1. There is no need to reveal the specific product name, only to refer to it as a general term for the product; 2. If there are certain problems with the product, please only select the existing problems from the following: product quality problems, product out of stock, product shortage, product does not match the description, product size does not match, and do not describe the specific problems; 3. It is only necessary to summarize the information of this order and the changes that have occurred over the timeline. There is no need to make any speculations or other information that does not exist; 4. The sequence of events and the subject cannot be logically confusing, and the language logic must be consistent; 5. The timeline information of each situation must be stated, and the time must be indicated in the form of "xx days ago", "xx hours ago" or "xx minutes ago", and only information within 14 days must be output; 6. Do not use descriptions such as "later", "soon after", "then" that cannot clearly state the time; 7. Do not describe that the user's order package has been confirmed to be received; 8. Use the method of "the user applied for xxx due to xxx, and the seller accepted / does not accept" to describe it; 9. Do not output that the user has completed the order payment; 10. If the current information has a new status change, it needs to be described; 11. Keep it as concise as possible.

[0054] Based on this, after generating the order processing information, the preset prompt words corresponding to the information summary task can be determined, and the order processing information and the preset prompt words can be input into the information summary model to obtain the order summary information of the target order output by the information summary model.

[0055] In addition, a preset prompt word may be generated according to the order processing information and a preset prompt word template, and the preset prompt word may be input into the information summary model to obtain order summary information.

[0056] In actual applications, the order summary information may also include the user's demand for the target order predicted by the information summary model based on the order processing information and preset prompt words.

[0057] In summary, after obtaining the identical and standardized order processing information, the order processing information and the preset prompt words can be input into the information summary model, and the target order can be summarized through the information summary model to obtain order summary information. Since the order processing information input into the information summary model is sorted in a certain order, the input is clearer for the information summary model, which facilitates the subsequent extraction of key information from the order processing information for order summary, and can obtain the order summary information of the target order more quickly and efficiently. The obtained order summary information not only retains most of the information of the target order, but also reduces the time for customer service to view historical records before solving the target problem, greatly improving the customer service's ability to handle the target problem and reducing the cost of customer service to solve the target problem.

[0058] Step 204: Determine a target answer corresponding to the target question based on the target question and the order summary information of the target order, wherein the order summary information is generated based on historical processing events corresponding to the target order.

[0059] The target answer corresponding to the target question may be the answer to the target question that is replied to the user.

[0060] Specifically, after receiving the user's target question regarding the target order, a target answer corresponding to the target question can be determined based on the target question and the order summary information. Furthermore, the target answer corresponding to the target question can be obtained from the order summary information based on the target question. In specific implementations, the user's needs can be determined based on the target question, and the target answer used to address the needs can be obtained from the order summary information.

[0061] In actual applications, after generating the order summary information of the target order according to the historical processing event, the method further includes: Storing the order summary information in a data storage platform; Before determining a target answer corresponding to the target question based on the target question and the order summary information of the target order, the method further includes: The order summary information of the target order is obtained from the data storage platform.

[0062] The data storage platform can be understood as a database for storing order summary information output by the information summary model.

[0063] Specifically, after the information summary model outputs the order summary information, the order summary information can be stored in the data storage platform. After receiving the target question for the target order, the order summary information of the target order is obtained from the data storage platform, and the target answer corresponding to the target question is determined based on the target question and the order summary information.

[0064] In actual applications, when storing order summary information in a data storage platform, the order number and order summary information of the target order and their corresponding relationship can be stored in the data storage platform. Then, when a target question for the target order is received, the order summary information of the target order can be obtained from the data storage platform according to the order number of the target order.

[0065] In summary, by storing the order summary information output by the information summary model in the data storage platform, it is convenient to obtain the order summary information from the data storage platform in a timely manner when receiving the target question for the target order in the future, thereby further improving the response speed and processing efficiency of the target question.

[0066] Then, in one embodiment of this specification, the method further includes: In response to a processing completion instruction for the target order, the order summary information of the target order stored in the data storage platform is deleted.

[0067] Among them, the processing completion instruction for the target order can be an instruction sent by the customer service of the e-commerce platform after the target problem is processed. The processing completion instruction is used to indicate that the relevant problems of the target order have been solved, and the data storage platform no longer needs to store the order summary information of the target order, thereby realizing memory cleaning of the data storage platform.

[0068] Specifically, in response to a processing completion instruction sent by the customer service when the target issue is processed, the order summary information of the target order stored in the data storage platform is deleted.

[0069] In addition, the storage time of the order summary information in the data storage platform can also be monitored. When it is determined that the storage time reaches a preset time threshold, the order summary information in the data storage platform is deleted. For example, when the storage time reaches 10 days or 15 days, the order summary information in the data storage platform is deleted. In actual applications, the storage time of the order summary information can be monitored by a timer, and this embodiment of the specification does not limit this. Further, the preset time threshold can be determined based on the order information of the target order or the historical problem processing time. For example, if the free return period of the target order's goods is 30 days, then the preset time interval can be set to be greater than the free return period, such as 35 days, etc. Or, if the processing time of historical problems similar to the target problem of the target order in the historical time period of the e-commerce platform is 20 days, then the preset time interval can be set to 20 days, 25 days or 18 days, etc. This embodiment of the specification does not limit the setting of the preset time interval, and it can be set and dynamically adjusted according to actual needs.

[0070] In summary, by determining the target problem solution or regularly deleting the order summary information stored in the data storage platform, the memory of the data storage platform can be cleaned up in a timely manner, avoiding the memory occupation of the data storage platform caused by a large amount of subsequent order summary information.

[0071] In practical applications, determining a target answer corresponding to the target question based on the target question and the order summary information of the target order includes: Based on the intelligent decision-making unit, a target answer corresponding to the target question is determined according to the target question and the order summary information of the target order.

[0072] Among them, the intelligent decision-making unit can be understood as an intelligent entity, such as a customer service robot on an e-commerce platform.

[0073] Specifically, the customer service robot of the e-commerce platform can determine the target answer corresponding to the target question based on the target question and order summary information, and send the target answer to the user who initiated the order consultation request, thereby realizing an interactive dialogue between the customer service robot and the user, and further realizing the solution of the target problem and other problems of the target order. In addition, it is also possible to determine the target answer corresponding to the target question based on the target question and order summary information based on manual customer service, and send the target answer to the user who initiated the order consultation request. This embodiment of the present specification does not limit this. Moreover, it is understandable that the customer service mentioned in the embodiments of the present specification can be a customer service robot or a manual customer service.

[0074] To sum up, in the above method, in response to the user's order consultation request for the target order, the user's target question for the target order can be obtained, and the target answer to the target question can be determined based on the target question and the order summary information of the target order. The order summary information of the target order is generated based on the historical processing events corresponding to the target order, so that the target problem can be solved in a targeted manner according to the order summary information, without spending a lot of time querying and integrating order information related to the target order, thereby improving the response speed to the target problem, further ensuring the problem-solving efficiency of the target problem, and ensuring the interactive experience of the user who raises the target question.

[0075] The following combined Figure 3 , taking the application of the data processing method provided in this specification in e-commerce customer service as an example, the data processing method is further explained. Figure 3 A flowchart of a data processing method provided in one embodiment of this specification is shown, which specifically includes the following steps.

[0076] Step 302: The customer service robot receives an order consultation request for a target order sent by a user client.

[0077] Specifically, the user client can enter the customer service consultation page (i.e., enter the line) on the e-commerce platform with an order link of the target order.

[0078] Step 304: The customer service robot sends the order consultation request to the data storage platform.

[0079] Specifically, the customer service robot triggers a function to send the order consultation request to the data storage platform.

[0080] Step 306: The data storage platform obtains historical processing events corresponding to the target order from the database.

[0081] Specifically, the data storage platform can obtain all trajectory information (i.e., historical processing events) of the target order and the user of the target order from the database.

[0082] Step 308: The data storage platform sorts the historical processing events according to the preset sorting rules to obtain the order processing information of the target order.

[0083] Specifically, the data storage platform can arrange and combine all trajectory information according to time and module to obtain arranged order processing information.

[0084] Step 310: The data storage platform inputs the order processing information and the preset prompt words into the information summary model to obtain order summary information of the target order.

[0085] Specifically, the data storage platform can input the order processing information and the preset prompt words into the information summary model, and return the order summary information of the target order, which includes the user's possible demands for the target order.

[0086] Step 312: The customer service robot receives the target question for the target order sent by the user client.

[0087] Step 314: The customer service robot obtains order summary information of the target order from the data storage platform.

[0088] Step 316: The customer service robot determines the target answer corresponding to the target question based on the target question and the order summary information.

[0089] Specifically, the customer service robot can determine a solution to the target question based on the order summary information output by the information summary model and the target question raised by the user, and use the solution as the target answer corresponding to the target question.

[0090] Step 318: The customer service robot sends the target answer to the user client.

[0091] In summary, this method can effectively summarize the historical order experiences of users on e-commerce platforms, including the problems they encountered with their target orders, their corresponding requests, and the solutions provided by merchants and platforms. This solves the problem of manual customer service or customer service robots providing irrelevant answers to questions about their target orders after entering the e-commerce platform, increasing user interaction willingness and reducing further manpower costs. After the user enters the customer service consultation page, various trajectory data before the user enters the line is obtained, including logistics, refunds, buyer-seller chat records, and user click records. This information is then arranged into a certain structure in chronological order, and a standard prompt word is generated from this structure. This information is then used to obtain the problems encountered by the user with the order, their corresponding requests, and the solutions provided by merchants and platforms from the information summary model.

[0092] Corresponding to the above method embodiment, this specification also provides a data processing device embodiment, Figure 4 FIG1 shows a schematic diagram of the structure of a data processing device provided by an embodiment of this specification. Figure 4 As shown, the device includes: An acquisition module 402 is configured to acquire a target question for a target order in response to an order inquiry request for the target order; The determination module 404 is configured to determine a target answer corresponding to the target question based on the target question and order summary information of the target order, wherein the order summary information is generated based on historical processing events corresponding to the target order.

[0093] In an optional embodiment, the acquisition module 402 is further configured to: Obtain historical processing events corresponding to the target order; Generate order summary information of the target order according to the historical processing events.

[0094] In an optional embodiment, the acquisition module 402 is further configured to: Sorting the historical processing events according to a preset sorting rule to obtain order processing information of the target order; The order processing information is summarized to obtain order summary information of the target order.

[0095] In an optional embodiment, the acquisition module 402 is further configured to: sorting the historical processing events according to their priority information to obtain order processing information of the target order; or The historical processing events are sorted according to the processing time of the historical processing events to obtain the order processing information of the target order.

[0096] In an optional embodiment, the acquisition module 402 is further configured to: Inputting the order processing information and the preset prompt word into an information summary model to obtain order summary information of the target order output by the information summary model; Among them, the preset prompt words include task description information, task processing use cases and model output restrictions. The task description information is used to guide the information summary model to summarize the order processing information, the task processing use cases are used to enable the information summary model to summarize the order processing information according to the task processing use cases, and the model output restrictions are used to limit the order summary information output by the information summary model.

[0097] In an optional embodiment, the determining module 404 is further configured to: Storing the order summary information in a data storage platform; The order summary information of the target order is obtained from the data storage platform.

[0098] In an optional embodiment, the apparatus further includes a deletion module configured to: In response to a processing completion instruction for the target order, the order summary information of the target order stored in the data storage platform is deleted.

[0099] In the above-mentioned device, in response to the user's order consultation request for the target order, the user's target question for the target order can be obtained, and the target answer to the target question can be determined based on the target question and the order summary information of the target order. The order summary information of the target order is generated based on the historical processing events corresponding to the target order, so that the target problem can be solved in a targeted manner according to the order summary information, without spending a lot of time to query and integrate the order information related to the target order, thereby improving the response speed to the target problem, further ensuring the problem-solving efficiency of the target problem, and ensuring the interactive experience of the user who raised the target question.

[0100] The above is a schematic diagram of a data processing device according to this embodiment. It should be noted that the technical solution of the data processing device and the technical solution of the above-mentioned data processing method are based on the same concept. For details not described in detail in the technical solution of the data processing device, please refer to the description of the technical solution of the above-mentioned data processing method.

[0101] Corresponding to the above method embodiment, this specification also provides another data processing method, which is applied to the server. Figure 5 A flowchart of another data processing method provided according to an embodiment of this specification is shown, which specifically includes the following steps.

[0102] Step 502: Responding to an order inquiry request for a target order sent by a client, obtaining a target question for the target order; Step 504: Determine a target answer corresponding to the target question based on the target question and the order summary information of the target order, and send the target answer to the client, wherein the order summary information is generated based on the historical processing events corresponding to the target order.

[0103] Here, the client can be understood as the user client that initiates an order consultation request.

[0104] Specifically, after receiving the user's order consultation request for the target order sent by the client, the server can pre-acquire the historical processing events corresponding to the target order before receiving the target question for the target order, and generate order summary information of the target order based on the historical processing events. Then, after receiving the target question for the target order, the server can directly obtain the order summary information of the target order, determine the target answer to the target question based on the order summary information and the target question, and send the target answer to the client, so as to achieve targeted solution to the target problem according to the order summary information, without spending a lot of time to query and integrate relevant information after receiving the target question, thereby improving the response speed to the target problem, further ensuring the problem-solving efficiency of the target problem, and ensuring the interactive experience of the user who raised the target question.

[0105] The above is a schematic scheme of a data processing method of this embodiment. It should be noted that the technical scheme of this data processing method and the technical scheme of the above data processing method are of the same concept. For details not described in detail in the technical scheme of the data processing method, please refer to the description of the technical scheme of the above data processing method.

[0106] Corresponding to the above method embodiment, this specification also provides another data processing device, which is applied to the server. Figure 6 FIG. 1 shows a schematic structural diagram of another data processing device provided according to an embodiment of the present specification. Figure 6 As shown, the device includes: An acquisition module 602 is configured to, in response to an order inquiry request for a target order sent by a client, acquire a target issue for the target order; Determination module 604 is configured to determine the target answer corresponding to the target question based on the target question and the order summary information of the target order, and send the target answer to the client, wherein the order summary information is generated based on the historical processing events corresponding to the target order.

[0107] In the above-mentioned device, after receiving the user's order consultation request for the target order, before receiving the target question for the target order, the historical processing event corresponding to the target order can be obtained in advance, and the order summary information of the target order can be generated based on the historical processing event. Then, after receiving the target question for the target order, the order summary information of the target order can be directly obtained, and the target answer to the target question can be determined based on the order summary information and the target question, so as to achieve targeted solution of the target problem based on the order summary information. There is no need to spend a lot of time to query and integrate relevant information after receiving the target question, which improves the response speed to the target problem, further ensures the problem-solving efficiency of the target problem, and ensures the interactive experience of the user who raises the target question.

[0108] The above is a schematic diagram of a data processing device according to this embodiment. It should be noted that the technical solution of the data processing device and the technical solution of the above-mentioned data processing method are based on the same concept. For details not described in detail in the technical solution of the data processing device, please refer to the description of the technical solution of the above-mentioned data processing method.

[0109] Corresponding to the above method embodiment, this specification also provides a data processing system, Figure 7 FIG. 1 shows a schematic diagram of a data processing system according to an embodiment of the present invention. Figure 7 As shown, the system includes an intelligent decision-making unit 702 and a data storage platform 704, wherein: The intelligent decision-making unit 702 is configured to, in response to an order inquiry request for a target order sent by a client, obtain order summary information of the target order from the data storage platform 704, wherein the order summary information is generated based on historical processing events corresponding to the target order; The intelligent decision-making unit 702 is further configured to receive a target question for the target order sent by the client, determine a target answer corresponding to the target question based on the target question and the order summary information, and send the target answer to the client.

[0110] In the above system, after receiving the user's order consultation request for the target order, before receiving the target question for the target order, the historical processing event corresponding to the target order can be obtained in advance, and the order summary information of the target order can be generated based on the historical processing event. Then, after receiving the target question for the target order, the order summary information of the target order can be directly obtained, and the target answer to the target question can be determined based on the order summary information and the target question, so as to achieve targeted solution to the target problem based on the order summary information. There is no need to spend a lot of time querying and integrating relevant information after receiving the target question, which improves the response speed to the target problem, further ensures the problem-solving efficiency of the target problem, and ensures the interactive experience of the user who raises the target question.

[0111] The above is a schematic diagram of a data processing system according to this embodiment. It should be noted that the technical solution of the data processing system and the technical solution of the above-mentioned data processing method are based on the same concept. For details not described in detail in the technical solution of the data processing system, please refer to the description of the technical solution of the above-mentioned data processing method.

[0112] 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.

[0113] 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.

[0114] In one embodiment of the present application, the above components of the computing device 800 and Figure 8 Other 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.

[0115] 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.

[0116] The processor 820 is configured to execute the following computer program / instructions, which implement the steps of the above-mentioned data processing method when executed by the processor.

[0117] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the computing device embodiment is generally similar to the data processing method embodiment, so the description is relatively simple. For relevant parts, refer to the description of the data processing method embodiment.

[0118] 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 data processing method when executed by a processor.

[0119] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from the other embodiments. In particular, the computer-readable storage medium embodiment is generally similar to the data processing method embodiment, so its description is relatively simple. For relevant portions, refer to the description of the data processing method embodiment.

[0120] An embodiment of the present specification further provides a computer program product, comprising a computer program / instruction, which implements the steps of the above-mentioned data processing method when executed by a processor.

[0121] The above is a schematic solution of a computer program product of this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the above-mentioned data 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 above-mentioned data processing method.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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 data processing method, comprising: In response to an order inquiry request for a target order, obtaining a target question for the target order; A target answer corresponding to the target question is determined according to the target question and order summary information of the target order, wherein the order summary information is generated according to historical processing events corresponding to the target order.

2. The method according to claim 1, further comprising: Obtain historical processing events corresponding to the target order; Generate order summary information of the target order according to the historical processing events.

3. The method according to claim 2, wherein generating order summary information of the target order based on the historical processing event comprises: Sorting the historical processing events according to a preset sorting rule to obtain order processing information of the target order; The order processing information is summarized to obtain order summary information of the target order.

4. The method according to claim 3, wherein the step of sorting the historical processing events according to a preset sorting rule to obtain the order processing information of the target order comprises: sorting the historical processing events according to their priority information to obtain order processing information of the target order; or The historical processing events are sorted according to the processing time of the historical processing events to obtain the order processing information of the target order.

5. The method according to claim 3, wherein summarizing the order processing information to obtain order summary information of the target order comprises: Inputting the order processing information and the preset prompt word into an information summary model to obtain order summary information of the target order output by the information summary model; Among them, the preset prompt words include task description information, task processing use cases and model output restrictions. The task description information is used to guide the information summary model to summarize the order processing information, the task processing use cases are used to enable the information summary model to summarize the order processing information according to the task processing use cases, and the model output restrictions are used to limit the order summary information output by the information summary model.

6. The method according to any one of claims 2 to 5, further comprising: after generating order summary information of the target order according to the historical processing event; Storing the order summary information in a data storage platform; Before determining a target answer corresponding to the target question based on the target question and the order summary information of the target order, the method further includes: The order summary information of the target order is obtained from the data storage platform.

7. The method according to claim 6, further comprising: In response to a processing completion instruction for the target order, the order summary information of the target order stored in the data storage platform is deleted.

8. A data processing method, applied to a server, comprising: In response to an order inquiry request for a target order sent by a client, obtaining a target question for the target order; According to the target question and the order summary information of the target order, a target answer corresponding to the target question is determined, and the target answer is sent to the client, wherein the order summary information is generated according to the historical processing events corresponding to the target order.

9. A data processing system comprising an intelligent decision-making unit and a data storage platform, wherein: The intelligent decision-making unit is configured to, in response to an order inquiry request for a target order sent by a client, obtain order summary information of the target order from the data storage platform, wherein the order summary information is generated based on historical processing events corresponding to the target order; The intelligent decision-making unit is further used to receive a target question for the target order sent by the client, determine a target answer corresponding to the target question based on the target question and the order summary information, and send the target answer to the client.

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 8 are implemented.

11. 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 8.

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 8 when executed by a processor.

Images