Text processing methods, apparatus and electronic devices

Abstract

This application provides a text processing method, apparatus, and electronic device. The text processing method includes: receiving a question text sent by a target user to a current merchant; determining the target user's intent based on the question text; if the current merchant has pre-configured multiple group answers for the target user's intent, obtaining the target user's corresponding target user tag, and determining the target group answer corresponding to the target user tag as the answer to reply to the question text from among the multiple group answers; and sending the target group answer to the target user. This application, by pre-configuring group answers for different user tags under different user intents, allows the return of the corresponding group answer based on the target user's target user tag when the received question text contains the target user's intent. This enables the response to the target user's question text to be considered from the target user's perspective, providing a more accurate and precise answer, thereby improving the user experience.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more particularly to a text processing method, apparatus, and electronic device. Background Technology

[0002] In e-commerce, it's common for users to ask merchants questions, such as inquiries about product information before purchase, logistics progress during shipping, and after-sales issues after receiving the goods. To improve service efficiency, merchants typically configure answer text on the server side for each question, allowing for a quick response when a user asks a question.

[0003] However, in related technologies, only the question text is considered when configuring the answer text, which results in the inability to provide users with accurate answers, thereby reducing the user experience. Summary of the Invention

[0004] This application provides a text processing method, apparatus, and electronic device to address the problem of inaccurate configuration answers.

[0005] The first aspect of this application provides a text processing method, including: receiving a question text sent by a target user to a current merchant; determining the target user's intent based on the question text; if the current merchant has pre-configured multiple group answers for the target user's intent, obtaining the target user tag corresponding to the target user, and determining the target group answer corresponding to the target user tag as the answer to the question text from among the multiple group answers; and sending the target group answer to the target user.

[0006] A second aspect of this application provides a text processing apparatus, comprising:

[0007] The receiving module is used to receive question texts sent by target users regarding the current merchant;

[0008] The determination module is used to determine the target user's intent based on the question text;

[0009] The processing module is used to obtain the target user tag corresponding to the target user if the current merchant has pre-configured multiple group answers for the target user's intent, and determine the target group answer corresponding to the target user tag as the answer to the reply question text among the multiple group answers;

[0010] The sending module is used to send answers from the target audience to the target users.

[0011] A third aspect of this application provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the text processing method of the first aspect.

[0012] A fourth aspect of this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the text processing method of the first aspect.

[0013] This application embodiment is applied to a consultation scenario in the e-commerce field. The provided text processing method includes: receiving a question text sent by a target user to a current merchant; determining the target user's intent based on the question text; if the current merchant has pre-configured multiple group answers for the target user's intent, obtaining the target user's corresponding target user tag, and determining the target group answer corresponding to the target user tag as the answer to the question text from among the multiple group answers; and sending the target group answer to the target user. This application embodiment, by pre-configuring group answers for different user tags under different user intents, allows the return of the corresponding group answer based on the target user's target user tag when the received question text contains the target user's intent. This enables the response to the target user's question text to be considered from the target user's perspective, providing a more accurate and precise answer, thereby improving the user experience. Attached Figure Description

[0014] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0015] Figure 1 A schematic diagram illustrating a text processing method provided for an exemplary embodiment of this application;

[0016] Figure 2 A flowchart illustrating the steps of a text processing method provided in an exemplary embodiment of this application;

[0017] Figure 3 A schematic diagram illustrating a text processing method provided for an exemplary embodiment of this application;

[0018] Figure 4 A flowchart illustrating the steps of another text processing method provided in an exemplary embodiment of this application;

[0019] Figure 5 A schematic diagram illustrating the acquisition of target user tags as an exemplary embodiment of this application;

[0020] Figure 6 A structural block diagram of a text processing apparatus provided for an exemplary embodiment of this application;

[0021] Figure 7This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] The text processing method provided in this application is applied to consultation scenarios in the e-commerce field. The server side is configured with an intelligent customer service system to automatically respond to user inquiries, saving costs for merchants while resolving user issues. Merchants can typically customize the answers for their own stores or products, improving the accuracy of answer configuration. However, currently, there is no capability to configure answers from the user's perspective. For example, there is currently no way to configure different answers based on different user attributes and the relationship between users and merchants, thus hindering the creation of more user-friendly and tailored intelligent services to provide a better user experience.

[0024] Furthermore, related technologies consider the scenario when configuring answers. For example, by building a data-driven intelligent algorithm model, accumulating massive amounts of real-world data through serving a large number of users, and performing high-dimensional machine learning and deep training to feed back into the algorithm model, the response logic of human customer service can be simulated, improving the semantic understanding and question-and-answer capabilities of the customer service robot. However, these methods mainly focus on configuring answers around scenario positioning and semantic understanding, and cannot provide users with accurate answers or a better user experience.

[0025] In e-commerce consultation scenarios, the aforementioned technologies suffer from the inability to provide users with accurate answers. This application's embodiment provides a text processing method that includes: receiving a question text sent by a target user to a current merchant; determining the target user's intent based on the question text; if the current merchant has pre-configured multiple group answers for the target user's intent, obtaining the target user's corresponding target user tag, and determining the target group answer corresponding to the target user tag as the answer to the question text from among the multiple group answers; and sending the target group answer to the target user. This application embodiment, by pre-configuring group answers for different user tags under different user intents, allows the return of the corresponding group answer based on the target user's target user tag when the received question text contains the target user's intent. This enables the response to the target user's question text to be considered from the target user's perspective, providing a more accurate and precise answer, thereby improving the user experience.

[0026] In this embodiment, the text processing method can be implemented using a cloud computing system. Furthermore, the server executing the text processing method can be a cloud server, leveraging the advantages of cloud resources to run various text processing methods; alternatively, the text processing method can also be applied to conventional servers or server arrays, etc., without limitation.

[0027] In addition, refer to Figure 1 This illustration demonstrates an application scenario of an embodiment of this application. In this scenario, a merchant sends a configured audience answer to a server via a merchant terminal, and a target user sends a question text to the server via a user terminal. The server then returns the audience answer to the target user based on the configured audience answer. For example, a merchant opens a virtual store on a current platform to sell goods. Users purchase these goods online through the platform and need to ask questions to inquire about product information. Typically, the product information inquired about by users has standardized answers, such as product size, color, and usage. To save costs, the merchant configures corresponding answers for different questions on the current platform. When a user asks a question, the merchant can use these answers to automatically respond. This embodiment of the application proposes pre-configuring audience answers for different user tags based on different user intentions. When the received question text contains the intention of the target user, the corresponding audience answer can be returned based on the target user's target user tags. This allows the response to the target user's question text to be considered from the target user's perspective, providing more accurate and precise answers and thus improving the user experience.

[0028] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0029] Figure 2A flowchart illustrating the steps of a text processing method provided for an exemplary embodiment of this application. Figure 2 The text processing method shown includes the following steps:

[0030] S201, Receive the question text sent by the target user regarding the current merchant.

[0031] In e-commerce scenarios, each merchant will have a corresponding virtual store. Each virtual store includes many products, which users can purchase online and receive in-store.

[0032] In this embodiment of the application, the target user is the buyer. The question text can be a question from the target user regarding a specific product of the current merchant (in the current store).

[0033] For example, the virtual stores of merchants are currently mainly used to sell skincare products, such as skincare sets of series A, skincare sets of series B, skincare toners of series C, and skincare creams of series D. Question texts are such as "What skin type is your skincare set suitable for?" or "What skin type is this skincare toner of series C suitable for?"

[0034] In this embodiment of the application, the question text can be any inquiry text entered by the target user in response to the current merchant.

[0035] S202, Based on the question text, determine the target user's intent.

[0036] The target user intent corresponding to the question text can be determined through semantic analysis or through keyword extraction. This application does not limit the specific methods used.

[0037] For example, if the question text is "What skin type is our skincare set suitable for?", the target user intent is "to inquire about a set suitable for their skin type". If the question text is "What skin type is this C-series toner suitable for?", the target user intent is "the skin type suitable for the C-series toner".

[0038] Furthermore, if the question text is "What skin tone is this C series skin care water suitable for?", the target user intent is "The skin tone that the C series skin care water is suitable for". If the question text is "How many milliliters is this C series skin care water?", the target user intent is "The specifications of the C series skin care water".

[0039] In this embodiment of the application, the question text expressing the same intent can be in multiple forms, and the server can determine that it is a unified target user intent. For example, question text a1 is "This skin care water is from the C series, what skin type can it be used on?", question text a2 is "Can I use this skin care water, the one from the C series, for my skin type?", and question text a3 is "Please help me take a look, what skin type can the C series skin care water be used on? I want to know." Then, the target user intent determined by the server for question text a1, question text a2 and question text a3 is "the skin type suitable for the C series skin care water".

[0040] S203, if the current merchant has pre-configured multiple group answers for the target user's intent, then obtain the target user tag corresponding to the target user, and determine the target group answer corresponding to the target user tag as the answer to the reply question text among the multiple group answers.

[0041] In this system, each target user intent corresponds to multiple audience-specific answers. These audience-specific answers are configured by the merchant based on the target user intent, and each answer has a corresponding user tag. Therefore, after determining the target user intent, we can first determine if there are audience-specific answers for that intent. If so, we obtain the target user tag, and then, based on the target user tag, determine the corresponding target audience answer from among the multiple audience-specific answers for that intent. This target audience answer is then used to reply to the target user's question text.

[0042] For example, refer to Figure 3 The target user "I" inputs the question text "What skin type is this C series skincare toner suitable for?" into store X. The target user sends the question text to the server. The server determines the target user's intent "What skin type is the C series skincare toner suitable for?" based on the question text, and then determines the corresponding answer for the target user's intent from a pre-configured knowledge base. Figure 3 The target user intent "C series skincare toner is suitable for which skin type?" corresponds to three user groups: ①, ②, and ③. Each user group has a corresponding user tag: ① corresponds to the user tag "dry skin", ② to the user tag "oily skin", and ③ to the user tag "combination skin". Furthermore, when a user group's intent is determined to have a corresponding user group, the target user's target user tag is obtained. Figure 3 If the target user's tag is "dry skin", then the answer ① corresponding to the user tag "dry skin" will be sent to the target user, which will be "Dear, this is not suitable for dry skin. The D series toner is more suitable for dry skin". The target user will then display the answer ① to the target user.

[0043] Furthermore, in this embodiment, the target user can have multi-faceted user tags, which refer to the user tags of the target user under the target user's intent. For example, the target user's user tags may include "skin type is dry," "skin tone is fair," "price range is 200 to 400 yuan," and "size is 160 ml to 260 ml." Wherein, if the target user's intent is to inquire about skin type, the target user tag is "skin type is dry." If the target user's intent is to inquire about skin tone, the target user tag is "skin tone is fair." If the target user's intent is to inquire about price, the target user tag is "price range is 200 to 400 yuan." If the target user's intent is to inquire about volume, the target user tag is "size is 160 ml to 260 ml."

[0044] In this embodiment, there is a correspondence between user intent, user tags, and audience answers. Specifically, it can be determined according to the merchant's configuration. The merchant can configure multiple sets of user tags based on a user intent. Each set of user tags can include at least one user tag, and each set of user tags corresponds to an audience answer.

[0045] For example, if a user's intent is "What skin type is the C series toner suitable for?", and a group of users is tagged with "dry skin and fair skin", then the corresponding answer could be "Dear, this is not suitable for dry skin. The D series toner is more suitable for dry skin and also for fair skin."

[0046] In this embodiment, the correspondence between user intent, user tags, and audience answers can be freely configured according to the needs of the merchant. The purpose is to take into account the perspective of the target user, provide the target user with more accurate and detailed answers, and improve the target user experience.

[0047] S204, Send the answers to the target audience to the target users.

[0048] Reference Figure 3 The system sends the answers corresponding to the target user's tags to the target user as the target audience's answers, so that the target audience's answers are displayed to the target users.

[0049] This application embodiment is applied to a consultation scenario in the e-commerce field. The provided text processing method includes: receiving a question text sent by a target user to a current merchant; determining the target user's intent based on the question text; if the current merchant has pre-configured multiple group answers for the target user's intent, obtaining the target user's corresponding target user tag, and determining the target group answer corresponding to the target user tag as the answer to the question text from among the multiple group answers; and sending the target group answer to the target user. This application embodiment, by pre-configuring group answers for different user tags under different user intents, allows the return of the corresponding group answer based on the target user's target user tag when the received question text contains the target user's intent. This enables the response to the target user's question text to be considered from the target user's perspective, providing a more accurate and precise answer, thereby improving the user experience.

[0050] Figure 4 A flowchart illustrating the steps of another text processing method provided for an exemplary embodiment of this application. Figure 4 As shown, the specific steps include:

[0051] S401 receives the answers from the merchant for each user intent, configured for different user tags and corresponding audiences.

[0052] Among them, user intent corresponds to multiple user tags, and user tags correspond to the answers of different groups of people.

[0053] In one optional embodiment, the merchant can configure multiple user intents for each product in the store, each user intent is configured with different user tags, and each user tag corresponds to a specific audience answer. The configured correspondence between user intents, audience answers, and user tags is then stored in a preset configuration library. Subsequently, when the server receives a question text sent by a target user, it can determine the target user intent corresponding to the question text, search for a target intent identical to the target user intent in the configured target user intents, determine that the target user intent has multiple corresponding audience answers, obtain the target user tag of the target user, and determine the corresponding target audience answer from the multiple audience answers based on the target user tag.

[0054] Referring to Table 1, the correspondence between user intent, target audience, and user tags for the current merchant's configuration of the C-series skincare water is illustrated exemplarily.

[0055] Table 1

[0056]

[0057] Table 1 shows the correspondence between user intent, user tags, and audience responses. Specifically, when user tags are the same, different user intents can result in different audience responses. For example, if the user intent is "C series toner is suitable for skin type" and the user tags are "dry skin, fair skin," the response would be: "Dear, this is not suitable for dry skin. The D series toner is more suitable for dry skin, and also more suitable for fair skin." If the user intent is "C series toner is suitable for skin tone" and the user tags are "dry skin, fair skin," the response would be: "Dear, this is suitable for fair skin, but not for dry skin. The D series toner is more suitable for dry skin, and also more suitable for fair skin."

[0058] In one optional embodiment, the current merchant can configure multiple types of configuration answers for different user intents, such as at least one of the following: general answers, related object answers, keyword answers, and audience answers. General answers are configured for the current merchant's store, related object answers are configured for the current product, keyword answers are configured for keywords in the question text, and audience answers are configured for the user. When configuring the corresponding configuration answers, the current merchant can configure the priority of the corresponding configuration answers.

[0059] For example, referring to Table 2, it can be seen that the configuration answer types for the current merchant's user intent configuration of "suitable for skin type" for this product are "audience answer," "general answer," and "related object answer." The configuration answer types for the user intent configuration of "suitable for skin tone" for this product are "keyword answer," "general answer," and "related object answer," with each type of configuration answer having a corresponding priority. In actual configuration, the current merchant can configure according to their needs.

[0060] Table 2

[0061]

[0062] In this embodiment, merchants can configure the answers according to their needs, thereby making the configuration of answers more flexible. In addition, the configuration of answers for different groups of people can provide more precise and detailed services to users.

[0063] S402 stores the correspondence between user intent, audience answers, and user tags.

[0064] In this embodiment of the application, the correspondence between the user intent, the audience answer, and the user tag configured by the merchant is stored in a preset configuration knowledge base for use.

[0065] S403, Receive the question text sent by the target user regarding the current merchant.

[0066] S404, Based on the question text, determine the target user's intent.

[0067] S405, Determine the pre-configured answer for the current merchant's intent regarding the target user.

[0068] The configuration answers include at least one of the following categories: general answers, related object answers, keyword answers, and audience answers, as well as the priority of each category of configuration answers.

[0069] For example, referring to Table 2, if the target user intent is "C series skin care water is suitable for skin type", then based on the target user intent, the pre-configured answers for the target user intent are determined to be "target audience answer", "general answer", and "related object answer". If the target user intent is "C series skin care water is suitable for skin tone", then based on the target user intent, the pre-configured answers for the target user intent are determined to be "keyword answer", "general answer", and "related object answer".

[0070] S406 If the configured answer includes the audience answer, and the audience answer has a higher priority than other configured answers, then obtain the target user tag corresponding to the target user, and determine the target audience answer corresponding to the target user tag as the answer to the reply question text among multiple audience answers.

[0071] Specifically, it determines whether the configured answer includes the audience answer and whether the audience answer has a higher priority than other configured answers. If so, it obtains the target user tag corresponding to the target user and determines the target audience answer corresponding to the target user tag as the answer to the reply question text among multiple audience answers.

[0072] Referring to Table 2, if the target user's intent is "C series skin care water is suitable for skin type", then the target user's intent includes "audience answer", and "audience answer" has the highest priority. In this case, the target user's corresponding target user tag is obtained, and among multiple audience answers, the target audience answer corresponding to the target user tag is determined as the answer to the reply question text.

[0073] Furthermore, if it is determined that the configured answer includes the audience answer, but the audience answer has a lower priority than other configured answers, then the configured answer with the highest priority is sent to the target user. For example, if the highest priority is the "keyword answer", then the keyword answer is sent to the target user.

[0074] In one optional embodiment, obtaining the target user tag corresponding to the target user includes: obtaining the target user's user data at the current merchant; and analyzing and processing the user data to obtain the target user tag.

[0075] The target user tags include user attribute tags and relationship tags. The target user tags are obtained by analyzing and processing user data, including: when the user data includes the target user's historical conversation information and / or historical order information under the current merchant, the user data is analyzed and processed to obtain user attribute tags; and / or when the user data includes the relationship between the target user and the current merchant, the user data is analyzed and processed to obtain relationship tags.

[0076] In this embodiment, the user tag is determined by the target user's user data at the current merchant, and the user data consists of data related to the usage permissions granted by the target user to the current merchant. The user data includes at least one of the following: historical conversation information, historical order information, and the association relationship between the target user and the current merchant.

[0077] For example, the relationship between the target user and the current merchant includes: the target user is a new or old customer of the current merchant; the target user is a member or not a member of the current merchant; the target user is a fan or not a fan of the current merchant; and the target user has recently purchased goods from the current merchant or has not purchased any goods from the current merchant.

[0078] Analyzing historical conversations and / or order information can yield user attribute tags, such as user preferences and personal characteristics. For example, for skincare product stores, preferences include price range and product size. Personal characteristics include skin type, skin texture, or skin tone. For clothing stores, preferences include color and style. Personal characteristics include height, weight, and body type.

[0079] In addition, the relationship between target users and current merchants is analyzed and processed to obtain relationship tags, such as members, old customers / new customers, fans, or recent purchases.

[0080] Specifically, when configuring answers, merchants can tailor the content to different user attribute tags and use different wording depending on the relationship tags. For example, when the target user tags include the user attribute tag "dry skin" and the relationship tag "returning customer," the corresponding answer could be, "Welcome back to our store! This product isn't suitable for dry skin; the D series toner is better for dry skin." When the target user tags include the user attribute tag "dry skin" and the relationship tag "new customer," the corresponding answer could be, "Welcome back to our store! This product isn't suitable for dry skin; the D series toner is better for dry skin. New customer gifts are available when you purchase this product!"

[0081] This application can use different wording to reply to target users based on the association tags, so as to give target users different preferential policies and different Q&A experiences.

[0082] In this embodiment, user tags are determined based on the target user's user data at the current merchant, which can prevent user data from being used across merchants and improve the security of user data.

[0083] In addition, user tags can be pre-mined from user data, and then the user identifier (login account), user tags, and the current merchant can be stored. During use, the corresponding user tag can be found based on the user identifier and the current merchant.

[0084] In one optional embodiment, if the target user is a new user of the current merchant, then obtaining the target user tag corresponding to the target user includes: providing the target user with query information for determining the user attribute tag; and receiving the user attribute tag replied by the target user.

[0085] If a target user visits the current merchant's store for the first time, it can be determined that the target user is a new user of the current merchant. If the target user is a new user, there is no user data for the target user in the current merchant. In this embodiment, user attribute tags are obtained by sending an inquiry message to the target user.

[0086] Furthermore, the query information is generated based on the target user's intent. For example, if the target user's intent is "what skin type is the C series skincare lotion suitable for", then the query information could be "What is your skin type?" If the target user's intent is "what skin tone is the C series skincare lotion suitable for", then the query information could be "What is your skin tone?"

[0087] For example, refer to Figure 5 The query information is sent by the server to the target user using a machine-based customer service model. It is displayed on the target user's side so that the target user can input their own tags based on the query information. The query information may also include answers related to the question text. For example... Figure 5 As shown, the inquiry information may include: the relevant answer (product description: Dear customer, this product is suitable for women with dry and fair skin, aged 25 and above, 160ml), the question (What is your skin type?), and a list of skin types (combination, oily, and dry) for the target user to choose from. The skin type selected by the target user is the target user's user attribute tag.

[0088] In the embodiments of this application, user tags of target users can be obtained through various methods, thereby enabling more accurate service to target users.

[0089] S407, send the answers to the target audience to the target users.

[0090] S408: If the priority of the audience answer is lower than that of other configured answers or the configured answers do not include the audience answer, then send the other configured answer with the highest priority to the target user.

[0091] Specifically, it determines whether the configured answer includes the audience answer and whether the audience answer has a higher priority than other configured answers. If not, it obtains the target user tag corresponding to the target user and determines the target audience answer corresponding to the target user tag as the answer to the reply question text among multiple audience answers.

[0092] Furthermore, if the merchant has not pre-configured audience answers for a specific target user, other configured answers can be sent to the target user to resolve the issue raised in the problem text. Moreover, if the merchant's current configured audience answers have a low priority, other high-priority configured answers can be sent to the target user to resolve the issue raised in the problem text.

[0093] This application embodiment can be applied to question-and-answer systems in the e-commerce field, making it easier for merchants to configure answers that are precise for specific groups of people in scenarios where user tags need to be considered, thereby providing more detailed user services and improving user consultation satisfaction.

[0094] Furthermore, the embodiments of this application mainly involve mining user data generated by target users in the current merchant, and then, from the perspective of question and answer answer configuration, enabling merchants to configure different answers for different user tags of buyers. While ensuring that user data is not abused, this improves the flexibility and accuracy of merchants in configuring answers, and also increases merchants' satisfaction with using the question and answer system in this intelligent dialogue scenario.

[0095] Finally, in the question-and-answer scenario of the intelligent customer service field, the embodiments of this application provide the ability to create accurate profiles based on the user group, which can tailor more detailed answers to the user and provide merchants with more detailed answers, thereby improving user satisfaction.

[0096] This application is applied to a consultation scenario in the e-commerce field. It receives a question text from a target user regarding a current merchant; determines the target user's intent based on the question text; if the current merchant has pre-configured multiple group answers for the target user's intent, target user tags can be obtained through user data mining or by questioning the target user; and the answer corresponding to the target user's tag is determined from the multiple group answers as the answer to the question text; the target group answer is then sent to the target user, enabling a more accurate and precise answer from the target user's perspective when responding to their question text, thereby improving the user experience.

[0097] In the embodiments of this application, reference is made to Figure 6In addition to providing a text processing method, a text processing apparatus 60 is also provided, which includes:

[0098] Receiver module 61 is used to receive the question text sent by the target user regarding the current merchant;

[0099] Module 62 is used to determine the target user's intent based on the question text;

[0100] Processing module 63 is used to obtain the target user tag corresponding to the target user if the current merchant has pre-configured multiple group answers for the target user's intent, and determine the target group answer corresponding to the target user tag as the answer to the reply question text among the multiple group answers;

[0101] The sending module 64 is used to send answers from the target audience to the target users.

[0102] In one optional embodiment, the processing module 63 is specifically used to: obtain the target user's user data at the current merchant; analyze and process the user data to obtain the target user's tag.

[0103] In one optional embodiment, the target user tag includes: user attribute tag and association relationship tag. When the processing module 63 analyzes and processes the user data to obtain the target user tag, it is specifically used to: analyze and process the user data to obtain the user attribute tag when the user data includes the target user's historical dialogue information and / or historical order information under the current merchant; and / or analyze and process the user data to obtain the association relationship tag when the user data includes: the association relationship between the target user and the current merchant.

[0104] In one optional embodiment, if the target user is a new user of the current merchant, the processing module 63 is specifically used to: provide the target user with query information for determining user attribute tags; and receive the user attribute tags replied by the target user.

[0105] In one optional embodiment, the processing module 63 is specifically used to: determine the configuration answers pre-configured by the current merchant for the target user's intent, the configuration answers including at least one of the following: general answers, associated object answers, keyword answers, and audience answers, and the priority of each type of configuration answer; if the configuration answers include audience answers, and the priority of the audience answers is higher than other configuration answers, then obtain the target user tag corresponding to the target user.

[0106] In an optional embodiment, the sending module 64 is further configured to: if the priority of the crowd answer is lower than that of other configured answers or the configured answers do not include the crowd answer, then send the other configured answers with the highest priority to the target user.

[0107] In one optional embodiment, the system further includes a configuration module (not shown), which, before receiving the question text sent by the target user for the current merchant, further includes: receiving the audience answers configured by the current merchant for each user intent for different user tags, wherein the user intent corresponds to multiple user tags, and the user tags correspond to audience answers; and saving the correspondence between user intent, audience answers, and user tags.

[0108] The text processing device provided in this application embodiment pre-configures group answers for different user tags under different user intentions. When the received question text has the intention of the target user, it can return the corresponding group answer according to the target user's target user tag. This allows the device to consider the target user's perspective when replying to the target user's question text, providing the target user with more accurate and precise answers, thereby improving the user experience.

[0109] Furthermore, in some of the processes described in the above embodiments and accompanying drawings, multiple operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The sequence numbers are merely used to distinguish different operations, and the sequence numbers themselves do not represent any execution order. Additionally, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0110] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an example embodiment of this application. Figure 7 As shown, the electronic device 70 includes a processor 71 and a memory 72 communicatively connected to the processor 71, the memory 72 storing computer execution instructions.

[0111] The processor executes computer execution instructions stored in the memory to implement the text processing method provided in any of the above method embodiments. The specific functions and technical effects to be achieved will not be elaborated here.

[0112] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the text processing method provided in any of the above method embodiments.

[0113] This application also provides a computer program product, which includes: a computer program stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the text processing method provided in any of the above method embodiments.

[0114] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0117] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0119] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0120] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A text processing method, characterized in that, include: Receive question texts from target users regarding the current merchant; Based on the question text, determine the target user's intent; If the current merchant has pre-configured multiple group answers for the target user's intent, then the target user tag corresponding to the target user is obtained, and the corresponding target person answer is determined from the multiple group answers corresponding to the target user's intent based on the target user tag. The target group answer corresponding to the target user tag is determined to be the answer to reply to the question text. Send the answers from the target group to the target users; If the current merchant has pre-configured multiple group answers for the target user's intent, then the target user's corresponding target user tag is obtained, including: Determine the pre-configured answers that the current merchant has configured for the target user's intent. The configuration answers include at least one of the following categories: general answers, related object answers, keyword answers, and audience answers, as well as the priority of each category of configuration answers. If the configured answer includes the answer for the target audience, and the answer for the target audience has a higher priority than other configured answers, then the target user tag corresponding to the target user is obtained.

2. The text processing method according to claim 1, characterized in that, The step of obtaining the target user tag corresponding to the target user includes: Obtain the target user's user data at the current merchant; The target user data is analyzed and processed to obtain the target user tags.

3. The text processing method according to claim 2, characterized in that, The target user tags include: user attribute tags and association relationship tags. The process of analyzing and processing the user data to obtain the target user tags includes: When the user data includes the target user's historical conversation information and / or historical order information under the current merchant, the user data is analyzed and processed to obtain the user attribute tags; And / or, the user data includes: in the case of the association relationship between the target user and the current merchant, the user data is analyzed and processed to obtain the association relationship tag.

4. The text processing method according to claim 1, characterized in that, If the target user is a new user of the current merchant, then obtaining the target user tag corresponding to the target user includes: Provide the target user with query information to determine the user attribute tags. Receive the user attribute tags in response from the target user.

5. The text processing method according to claim 1, characterized in that, Also includes: If the priority of the answer for the target user group is lower than that of other configured answers, or if the configured answers do not include the answer for the target user group, then the other configured answers with the highest priority are sent to the target user.

6. The text processing method according to any one of claims 1 to 4, characterized in that, Before receiving the question text sent by the user regarding the current merchant, the process also includes: Receive the audience answers configured by the current merchant for each user intent and for different user tags, wherein the user intent corresponds to multiple user tags, and the user tags correspond to the audience answers; Save the correspondence between the user intent, the group's answers, and the user tags.

7. A text processing device, characterized in that, include: The receiving module is used to receive question texts sent by target users regarding the current merchant; The determination module is used to determine the target user's intent based on the question text; The processing module is configured to, if the current merchant has pre-configured multiple group answers for the target user's intent, obtain the target user tag corresponding to the target user, and determine the target group answer corresponding to the target user tag as the answer to reply to the question text from the multiple group answers corresponding to the target user's intent based on the target user tag; The sending module is used to send the answers of the target group to the target user; The processing module is specifically used to determine the configuration answer pre-configured by the current merchant for the target user's intent. The configuration answer includes at least one of the following: general answer, associated object answer, keyword answer, and audience answer, as well as the priority corresponding to each type of configuration answer. If the configured answer includes the answer for the target audience, and the answer for the target audience has a higher priority than other configured answers, then the target user tag corresponding to the target user is obtained.

8. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the text processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing computer-executable instructions, characterized in that, When the computer executes the instructions, they are used by the processor to implement the text processing method according to any one of claims 1 to 6.

Images