Shopping guide dialogue interaction method and device, storage medium and computer equipment

By identifying the types and flow points of user inquiries and utilizing pre-defined scenario flowcharts and response cards, the problems of inquiry response and guidance in sales guide dialogue interactions were solved, achieving timely, comprehensive, and accurate information feedback and improving the user experience.

CN118964582APending Publication Date: 2024-11-15GUANGZHOU PINWEI SOFTWARE CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411200538.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

In existing technologies, the interactive dialogue between sales guides cannot provide users with timely, comprehensive, and accurate responses and guidance for their inquiries. Especially when faced with a large variety of products and complex consumer needs, human sales guides find it difficult to fully and accurately grasp all product information.

Method used

By identifying the information type and flow nodes of user inquiries, and utilizing pre-defined scenario flowcharts and response cards within the flow nodes, timely, comprehensive, and accurate response information is generated, guiding users to engage in further in-depth communication.

Benefits of technology

It improves the relevance and timeliness of dialogue interaction, ensures the comprehensiveness and professionalism of response information, meets users' potential needs, and enhances user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118964582A_ABST
    Figure CN118964582A_ABST
Patent Text Reader

Abstract

According to the shopping guide dialogue interaction method and device, the storage medium and the computer equipment provided by the invention, when the inquiry information input by the user on the interaction interface is received, the information type of the inquiry information and the corresponding transfer node can be determined firstly, so that the actual demand of the inquiry information can be reflected through the transfer node; then, a reply card corresponding to the inquiry information can be determined based on the transfer node, information assembly is performed on the reply card according to a node reply template of the transfer node, and reply information is generated, so that comprehensiveness and specialty of the reply information are ensured; meanwhile, the next circulation node can be obtained according to the preset scene flow chart to serve as the target node, the guide inquiry information of the target node is obtained to meet the potential requirements of the user, and finally the reply information and the guide inquiry information can be sequentially returned to the interactive interface to guide the user to further communicate deeply. Therefore, by means of the method, comprehensive and accurate inquiry reply and guidance can be provided for the user in time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a shopping guide dialogue interaction method, device, storage medium and computer equipment. Background Art

[0002] With the rapid development of e-commerce, the number of various commodities on e-commerce platforms is huge. In the face of overloaded commodity information, in order to improve the user shopping experience and increase user stickiness, shopping guide dialogue interaction came into being. Shopping guide dialogue interaction can help users make purchase decisions by responding to customer inquiries, displaying commodities, answering questions, etc., so as to improve the sales conversion rate on e-commerce platforms.

[0003] However, traditional shopping guide dialogue interactions rely on direct communication between human shopping guides and users. Although they can provide a certain degree of personalized services, faced with the increasingly large variety of goods and complex consumer needs, human shopping guides find it difficult to fully and accurately grasp all product information, and are unable to provide users with relatively comprehensive and accurate inquiry responses and inquiry guidance in a timely manner. Summary of the invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect that the shopping guide dialogue interaction in the prior art cannot provide users with relatively comprehensive and accurate inquiry responses and inquiry guidance in a timely manner.

[0005] The present application provides a shopping guide dialogue interaction method, the method comprising:

[0006] When receiving inquiry information input by the user in the interactive interface, determining the information type of the inquiry information and determining the flow node corresponding to the information type;

[0007] Determine at least one reply card corresponding to the inquiry information based on the flow node, and assemble information on each reply card according to the node reply template of the flow node to generate reply information;

[0008] According to a preset scenario flow chart, the next flow node of the flow node is determined as the target node, and the guidance inquiry information of the target node is obtained, and the reply information and the guidance inquiry information are returned to the interactive interface in sequence.

[0009] Optionally, determining the information type of the inquiry information includes:

[0010] Determine a business scenario corresponding to the inquiry information, and perform type analysis on the inquiry information based on the business scenario to obtain an information type of the inquiry information.

[0011] Optionally, determining the flow node corresponding to the information type includes:

[0012] Acquire information parameters of the information type, and determine multiple flow nodes corresponding to the business scenario, and trigger parameters corresponding to each flow node;

[0013] The information parameters are matched with the trigger parameters respectively, and the flow node corresponding to the information type is determined from the flow nodes according to the matching result.

[0014] Optionally, determining at least one reply card corresponding to the inquiry information based on the flow node includes:

[0015] Segmenting the query information to obtain a plurality of phrases, and performing keyword screening on each phrase to obtain at least one target phrase;

[0016] The inquiry object in the inquiry information is read, and a reply card corresponding to each target phrase is generated in the flow node based on the inquiry object.

[0017] Optionally, assembling information of each reply card according to a preset node reply template to generate reply information includes:

[0018] Determine a node reply template of the flow node and a parameter type corresponding to each reply card; wherein the node reply template is composed of reply modules of multiple parameter types;

[0019] Filter out the reply modules corresponding to the parameter type of each reply card from various reply modules, and lay out and assemble the filtered reply modules to generate an information reply template;

[0020] Fill the parameters in each reply card into the information reply template to obtain the reply information.

[0021] Optionally, the determining, according to a preset scenario flow chart, a next flow node of the flow node as a target node includes:

[0022] Determine the business scenario corresponding to the inquiry information, and the scenario branch corresponding to the business scenario in the preset scenario flow chart; the scenario branch is obtained by directed connection of multiple flow nodes;

[0023] Determine the node position of the flow node of the query information in the scene branch, and obtain the next flow node that is directed connected to the node position as the target node.

[0024] Optionally, the process of constructing the scenario flow chart includes:

[0025] Obtain historical shopping guide conversations for multiple business scenarios;

[0026] Perform scenario analysis on each historical shopping guide dialogue, and decompose each historical shopping guide dialogue into nodes according to the analysis results to obtain multiple flow nodes, and generate scenario branches corresponding to each business scenario based on each flow node;

[0027] Determine the directional relationship between the flow nodes in each scene branch, and connect the flow nodes in a directed manner according to each directional relationship to generate a scene flow chart.

[0028] The present application also provides a shopping guide dialogue interaction device, including:

[0029] A node determination module, configured to determine, when receiving inquiry information input by a user on an interactive interface, an information type of the inquiry information and a flow node corresponding to the information type;

[0030] A reply generation module, used to determine at least one reply card corresponding to the inquiry information based on the flow node, and assemble information on each reply card according to the node reply template of the flow node to generate reply information;

[0031] The inquiry guidance module is used to determine the next flow node of the flow node as the target node according to the preset scenario flow chart, obtain the guidance inquiry information of the target node, and return the reply information and the guidance inquiry information to the interactive interface in sequence.

[0032] The present application also provides a storage medium, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the shopping guide dialogue interaction method as described in any one of the above embodiments.

[0033] The present application also provides a computer device, comprising: one or more processors, and a memory;

[0034] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the shopping guide dialogue interaction method described in any one of the above embodiments are performed.

[0035] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0036] The shopping guide dialogue interaction method, device, storage medium and computer equipment provided by the present application, when receiving the inquiry information input by the user in the interactive interface, can first determine the information type of the inquiry information, and determine the flow node corresponding to the information type, so that the actual needs of the inquiry information can be reflected through the flow node to improve the pertinence and timeliness of the subsequent dialogue interaction; then, at least one reply card corresponding to the inquiry information can be determined based on the flow node, and the information of each reply card can be assembled according to the node reply template of the flow node to generate reply information, so as to ensure the comprehensiveness and professionalism of the reply information, and can also generate reply information that meets the user's needs in a very short time, further improving the timeliness of the reply; at the same time, the next flow node of the flow node can be determined according to the preset scenario flow chart as the target node, and the guide inquiry information of the target node can be obtained to meet the user's potential needs, and finally the reply information and the guide inquiry information can be returned to the interactive interface in turn, guiding the user to further deepen the communication and improve the user experience. Therefore, the present application can use the pre-set scenario flow chart and the reply card in each flow node to provide users with more comprehensive and accurate inquiry replies and inquiry guidance in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 A flowchart of a shopping guide dialogue interaction method provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of a process of generating a reply message provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of a process flow diagram for constructing a scenario flow diagram provided in an embodiment of the present application;

[0041] Figure 4 A schematic diagram of the structure of a shopping guide dialogue interaction device provided in an embodiment of the present application;

[0042] Figure 5 A schematic diagram of the internal flow of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] Traditional shopping guide dialogue interactions rely on direct communication between human shopping guides and users. Although they can provide a certain degree of personalized services, faced with the increasingly large variety of goods and complex consumer demands, human shopping guides find it difficult to fully and accurately grasp all product information, and are unable to provide users with relatively comprehensive and accurate inquiry responses and inquiry guidance in a timely manner.

[0045] Based on this, this application proposes the following technical solutions, see below for details:

[0046] In one embodiment, Figure 1 As shown, Figure 1 A flowchart of a shopping guide dialogue interaction method provided in an embodiment of the present application; the present application provides a shopping guide dialogue interaction method, which specifically includes the following:

[0047] S110: When receiving inquiry information input by the user in the interactive interface, determining the information type of the inquiry information and determining the flow node corresponding to the information type.

[0048] In this step, when the user needs to inquire about the relevant information of the goods in the e-commerce platform, the corresponding inquiry information can be directly input into the interactive interface of the computer device. After the computer device receives the inquiry information input by the user, it can first determine the information type of the inquiry information, and then determine the flow node corresponding to the information type, so that the actual demand for the inquiry information can be reflected through the flow node, so as to improve the pertinence and timeliness of subsequent dialogue interaction.

[0049] Among them, information type refers to the category to which the specific content of the inquiry information belongs, such as size information, material information, color information, price information, promotion information, logistics information, etc.; and flow node refers to a series of logical units divided according to information type for processing specific types of inquiry information, such as attribute nodes, price nodes, promotion nodes and logistics nodes.

[0050] It should be noted that each flow node of the present application corresponds to one or more types of information. For example, when the flow node is an attribute node, the corresponding information type may include information on product attributes such as size information, material information, and color information; and the flow node is configured with corresponding processing logic and response templates. Therefore, when the computer determines the corresponding flow node based on the query information, it can respond to the user's query information quickly and accurately based on the flow node.

[0051] S120: Determine at least one reply card corresponding to the inquiry information based on the flow node, and assemble information on each reply card according to the node reply template of the flow node to generate reply information.

[0052] In this step, after determining the flow node of the inquiry information through step S110, the computer device can determine at least one reply card corresponding to the inquiry information based on the flow node, and then assemble the information of each reply card according to the node reply template of the flow node to generate reply information, thereby ensuring the comprehensiveness and professionalism of the reply information, and generating reply information that meets user needs in a very short time, further improving the timeliness of information feedback.

[0053] It is understandable that, since the corresponding processing logic and response template are pre-configured in the flow node, the computer device can perform logical processing on the response template in the flow node according to the query information, and then obtain at least one reply card corresponding to the query information. Among them, the reply card here refers to a component that displays a commodity information parameter, which contains a direct answer to the query question, such as multi-angle pictures of the commodity, performance data of the commodity, promotional information of the commodity and other information parameters. In this application, each reply card can correspond to any information type in the flow node.

[0054] For example, when the user inputs a query to learn about the attribute information of a product, the computer device can obtain a response template pre-stored in the flow node, and then generate a reply card corresponding to each attribute of the product based on the response template, such as reply cards corresponding to attributes such as product size, product color, and product material; if the user inputs a query to learn about the size of the product, the computer device can only generate a reply card corresponding to the product size, thereby improving the timeliness and accuracy of the shopping guide dialogue interaction.

[0055] It should be noted that the node reply template of this application refers to the content reply directly displayed to the user, which is set with the goal of being concise and accurate. Based on this, the computer device can assemble information on each reply card according to the node reply template and generate reply information corresponding to the inquiry information, so that the user can read the core content of the reply information at a glance.

[0056] S130: Determine the next flow node of the flow node according to the preset scenario flow chart as the target node, obtain the guidance inquiry information of the target node, and return the reply information and the guidance inquiry information to the interactive interface in sequence.

[0057] In this step, after generating the reply information corresponding to the inquiry information through step S120, the computer device can also determine the next flow node of the flow node according to the preset scenario flow chart as the target node, and then obtain the guiding inquiry information of the target node to meet the user's potential needs. Finally, the reply information and the guiding inquiry information can be returned to the interactive interface in sequence to guide the user to further deepen the communication and improve the user experience.

[0058] The scenario flow chart refers to a graphical tool pre-stored in a computer device for describing and planning various information scenarios and their flow paths that may be encountered during the interactive shopping guide dialogue process. It contains multiple flow nodes and arrows connecting these flow nodes to indicate the flow relationship between each flow node. Therefore, through the scenario flow chart, the computer device can predict the user's next inquiry direction through the flow relationship between each flow node, so as to guide the user to further deepen the communication.

[0059] It is understandable that the target node in the present application may be one or more. If there is one target node, the computer device may directly obtain the guidance query information of the target node and return it to the interactive interface; if there are multiple target nodes, the computer device may obtain the guidance query information of each target node and summarize it to form the final guidance query information and return it to the interactive interface to meet various questions or needs that the user may raise.

[0060] For example, if a user enters a query about a product in the interactive interface, "Introduce the brand of this product", the computer device can first return the corresponding reply information based on the query information, then obtain the corresponding target node's guidance query information and return it after summarizing. The guidance query information finally returned can be returned in the form of a guidance title and at least one guidance sub-question, where each guidance sub-question corresponds to a guidance query information of a target node. The guidance title here can be "Other questions about this product", and the guidance sub-questions can include "What is the evaluation of this product", "Who is the applicable population of this product", and "Introduce the attribute details of this product".

[0061] In addition, when the computer device returns the guidance inquiry information to the interactive interface, the guidance inquiry information of each target node can be displayed in the form of text clicks, that is, each guidance sub-question under the guidance title, so that the user can inquire about the information by directly clicking the corresponding guidance sub-question, thereby providing a smoother, more efficient and personalized interactive experience.

[0062] Furthermore, when returning the guidance inquiry information of some target nodes, the computer device can also return it in the form of options. For example, when the user's inquiry information is "recommend some suitable clothes", after returning the reply information of the clothes recommendation, the computer device can further generate guidance inquiry information, which includes price range options, color options, etc., wherein the price range options may include less than 70 yuan, 70 to 150 yuan, and more than 150 yuan, and the color options may include black, white, gray, and beige. This application does not limit the specific options of the guidance inquiry information. Therefore, the user can directly select options in the guidance inquiry information returned by the interactive interface, so that the computer device can provide the user with more detailed clothing recommendation information.

[0063] In the above embodiment, when receiving the inquiry information input by the user in the interactive interface, the information type of the inquiry information can be determined first, and the flow node corresponding to the information type can be determined, so that the actual needs of the inquiry information can be reflected through the flow node to improve the pertinence and timeliness of the subsequent dialogue interaction; then at least one reply card corresponding to the inquiry information can be determined based on the flow node, and the information of each reply card can be assembled according to the node reply template of the flow node to generate reply information, so as to ensure the comprehensiveness and professionalism of the reply information, and to generate reply information that meets the user's needs in a very short time, further improving the timeliness of the reply; at the same time, the next flow node of the flow node can be determined according to the preset scenario flow chart as the target node, and the guided inquiry information of the target node can be obtained to meet the user's potential needs, and finally the reply information and the guided inquiry information can be returned to the interactive interface in turn, guiding the user to further deepen the communication and improve the user experience. Therefore, the present application can use the pre-set scenario flow chart and the reply card in each flow node to provide users with more comprehensive and accurate inquiry replies and inquiry guidance in a timely manner.

[0064] In one embodiment, determining the information type of the inquiry information in step S110 may include:

[0065] S111: Determine the business scenario corresponding to the inquiry information, and perform type analysis on the inquiry information based on the business scenario to obtain the information type of the inquiry information.

[0066] In this embodiment, when determining the information type of the inquiry information, the computer device can first determine the business scenario corresponding to the inquiry information, and then perform type analysis on the inquiry information based on the business scenario, so as to obtain the information type corresponding to the inquiry information, thereby locking the inquiry direction of the inquiry information, and further improving the accuracy of the subsequently generated reply information.

[0067] Among them, the business scenario refers to a business field or task background pointed to by the inquiry information, such as business scenarios such as understanding products, checking orders, and product after-sales. The information type refers to the category divided according to the content, structure or purpose of the inquiry information in each business scenario. For example, in the business scenario of understanding products, its information type may include size information, material information, color information, price information, promotion information, etc. In the business scenario, the information type usually corresponds to the user's specific needs or question types.

[0068] Specifically, when determining the business scenario corresponding to the query information, the computer device can first extract the key information in the query information, match the key information with the predefined business scenario, and then determine the business scenario that the query information best matches based on the matching results and the contextual information in the interactive interface. The computer device can then further perform type analysis on the query information under the business scenario, and classify it into predefined information types based on the characteristics of the query information in the analysis results. When classifying the information type of the query information, the computer device can apply a series of classification rules or algorithms, which may include keyword matching, semantic analysis, machine learning and other technologies, which are not limited here.

[0069] In one embodiment, determining the flow node corresponding to the information type in step S110 may include:

[0070] S112: Obtain information parameters of the information type, and determine multiple flow nodes corresponding to the business scenario, and trigger parameters corresponding to each flow node.

[0071] S113: Match the information parameters with the trigger parameters respectively, and determine the flow node corresponding to the information type from the flow nodes according to the matching results.

[0072] In this embodiment, when determining the flow node corresponding to an information type, the computer device can first obtain the information parameters of the information type, and determine multiple flow nodes corresponding to the business scenario, and the trigger parameters corresponding to each flow node. The computer device can then match the information parameters with each trigger parameter respectively, and determine the flow node corresponding to the information type from each flow node based on the matching results, so as to reflect the actual needs of the inquiry information through the flow node.

[0073] It can be understood that the business scenario is obtained by connecting multiple flow nodes in a directed manner. Each flow node represents a processing link of an information type in the business scenario, and the processing order of each flow node is progressive. For example, in the business scenario of product comparison, its directed connected flow nodes can be product addition, dimension selection, and data comparison respectively.

[0074] Specifically, the information parameters of the information type in this application refer to parameters that can define or represent the essential attributes of the information, and each flow node is pre-set with corresponding trigger parameters for its processing object. Therefore, when the computer device determines the flow node corresponding to the information type, it can match the information parameters with each trigger parameter respectively, and use the flow node with the same matching result as the flow node corresponding to the information type, and then use the flow node for subsequent information processing to improve accuracy.

[0075] In one embodiment, determining at least one reply card corresponding to the inquiry information based on the flow node in step S120 may include:

[0076] S121: Segment the query information to obtain multiple phrases, and perform keyword screening on each phrase to obtain at least one target phrase.

[0077] S122: Read the inquiry object in the inquiry information, and generate a reply card corresponding to each target phrase in the flow node based on the inquiry object.

[0078] In this embodiment, when the computer device determines at least one reply card corresponding to the inquiry information, it can first segment the inquiry information to obtain multiple phrases, and then perform keyword screening on each phrase to obtain at least one target phrase; then the computer device can read the inquiry object in the inquiry information, and generate a reply card corresponding to each target phrase in the flow node based on the inquiry object, and the reply card contains all relevant parameters in the reply information.

[0079] Specifically, the computer device can perform semantic analysis on the query information, and segment the query information according to the analysis result, so that the query information can be discretized into multiple phrases, and then keyword screening is performed on each phrase based on the pre-stored keyword form, so as to obtain all target phrases in the keyword form. Then, the computer device can read the query object that the user needs to inquire about through the query information, and then obtain the relevant data corresponding to the query object from the e-commerce platform, and generate a reply card corresponding to each target phrase in the flow node based on these relevant data.

[0080] For example, when a user's inquiry question is "Introduce the price and material of clothes", the computer device can perform word segmentation and keyword extraction to obtain the two target phrases "price" and "material", and then obtain the price information and material information of the corresponding products from the e-commerce platform, and generate the corresponding reply card in the flow node.

[0081] Furthermore, when the user inputs the inquiry object to be queried in the interactive interface, the user can directly enter the corresponding product information in the interactive interface so that the computer device obtains the corresponding product from the e-commerce platform as the inquiry object, or the user can select and click on the product in the interactive interface so that the computer device uses it as the inquiry object. There is no limitation here.

[0082] In one embodiment, Figure 2 As shown, Figure 2 A schematic diagram of a process of generating a reply message provided in an embodiment of the present application; Figure 2 In step S120, information of each reply card is assembled according to a preset node reply template to generate reply information, which may include:

[0083] S121: Determine a node reply template of a flow node and a parameter type corresponding to each reply card; wherein the node reply template is composed of reply modules of multiple parameter types.

[0084] S122: Filter out the reply modules corresponding to the parameter type of each reply card from various reply modules, and lay out and assemble the filtered reply modules to generate an information reply template.

[0085] S123: Fill the parameters in each reply card into the information reply template to obtain the reply information.

[0086] In this embodiment, when generating reply information, the computer device may first determine the node reply template of the flow node and the parameter type corresponding to each reply card. Since the node reply template is composed of reply modules of multiple parameter types, the computer device may filter out the reply modules corresponding to the parameter type of each reply card from each reply module, and lay out and assemble the filtered reply modules to generate an information reply template; finally, the computer device may fill the parameters in each reply card into the information reply template to obtain reply information.

[0087] It is understandable that each flow node may include multiple parameter types, such as a property node may include size parameters, material parameters, and color parameters. The present application may pre-set a reply template corresponding to each parameter type contained in the flow node, and then constitute a node reply template of the flow node. In this way, after the computer device generates each reply card corresponding to the inquiry question, it may first select the corresponding reply module from the node reply template according to the parameter type of each reply card for layout assembly, and obtain an information reply template for returning to the interactive interface, and then use the parameters in each reply card to replace the variables in each reply module in the information reply template to obtain the reply information. Therefore, through the reply information, the user can read the key content in the reply information at a glance.

[0088] In one embodiment, determining the next flow node of the flow node as the target node according to the preset scenario flow chart in step S130 may include:

[0089] S131: Determine the business scenario corresponding to the inquiry information and the scenario branch corresponding to the business scenario in the preset scenario flow chart; the scenario branch is obtained by directed connection of multiple flow nodes.

[0090] S132: Determine the node position of the flow node of the query information in the scene branch, and obtain the next flow node that is directed connected to the node position as the target node.

[0091] In this embodiment, when determining the next flow node of the flow node of the inquiry information, the computer device may first determine the business scenario corresponding to the inquiry information and the scene branch corresponding to the business scenario in the preset scene flow chart; wherein the scene branch is obtained by direct connection of multiple flow nodes. Based on this, after determining the node position of the flow node of the inquiry information in the scene branch, the computer device may obtain the next flow node that is directed connected to the node position and use it as the target node.

[0092] It is understandable that the scenario flow chart is composed of scenario branches of multiple business scenarios, and the scenario branches are obtained by directed connection of multiple flow nodes. Since there may be overlapping flow nodes in different business scenarios, the computer device can first determine the business scenario corresponding to the inquiry scenario, and then extract its corresponding scenario branch in the scenario flow chart. In this way, after determining the node position of the flow node of the inquiry information, the computer device can directly obtain the next flow node on the scenario branch according to the flow relationship of the flow node, and use it as the target node to avoid mistakenly selecting the next flow node of other business scenarios with overlapping flow nodes.

[0093] In one embodiment, Figure 3 As shown, Figure 3A schematic diagram of a process flow diagram for constructing a scenario flow diagram provided in an embodiment of the present application; Figure 3 In step S130, the process of constructing the scene flow chart may include:

[0094] S133: Obtain historical shopping guide dialogues of multiple business scenarios.

[0095] S134: Scenario analysis is performed on each historical shopping guide dialogue, and nodes are decomposed for each historical shopping guide dialogue according to the analysis results to obtain multiple flow nodes, and scenario branches corresponding to each business scenario are generated based on each flow node.

[0096] S135: Determine the directional relationship between the flow nodes in each scene branch, and connect the flow nodes in a directed manner according to each directional relationship to generate a scene flow chart.

[0097] In this embodiment, when constructing a scenario flow chart, the computer device can first obtain historical shopping guide conversations of multiple business scenarios in the historical time period in the e-commerce platform, and then perform scenario analysis on each historical shopping guide conversation, and perform node decomposition on each historical shopping guide conversation according to the analysis results to obtain multiple flow nodes; then, the computer device can generate a scenario branch corresponding to each business scenario based on each flow node, and determine the directional relationship between the flow nodes in each scenario branch, so as to perform directed connection on each flow node according to each directional relationship to generate a scenario flow chart.

[0098] It is understandable that when the computer device obtains historical shopping guide conversations, it can cover all business scenarios to ensure the comprehensiveness of the scenario flowchart. In each business scenario, the computer device can obtain historical shopping guide conversations of different types of users in the business scenario. Since different types of users have different shopping needs and conversation styles, the computer device can balance the data by obtaining historical shopping guide conversations of different types of users, and then analyze their common problems, improve the accuracy of the historical shopping guide conversation node disassembly, and improve the versatility of the scenario flowchart.

[0099] The shopping guide dialogue interaction device provided in an embodiment of the present application is described below. The shopping guide dialogue interaction device described below and the shopping guide dialogue interaction method described above can be referenced to each other.

[0100] In one embodiment, Figure 4 As shown, Figure 4 A schematic diagram of the structure of a shopping guide dialogue interaction device provided in an embodiment of the present application; the present application also provides a shopping guide dialogue interaction device, including

[0101] The node determination module 210 is used to determine the information type of the inquiry information and the flow node corresponding to the information type when receiving the inquiry information input by the user in the interactive interface.

[0102] The reply generation module 220 is used to determine at least one reply card corresponding to the inquiry information based on the flow node, and assemble information on each reply card according to the node reply template of the flow node to generate reply information.

[0103] The inquiry guidance module 230 is used to determine the next flow node of the flow node as the target node according to the preset scenario flowchart, obtain the guidance inquiry information of the target node, and return the reply information and the guidance inquiry information to the interactive interface in sequence.

[0104] In the above embodiment, when receiving the inquiry information input by the user in the interactive interface, the information type of the inquiry information can be determined first, and the flow node corresponding to the information type can be determined, so that the actual needs of the inquiry information can be reflected through the flow node to improve the pertinence and timeliness of the subsequent dialogue interaction; then at least one reply card corresponding to the inquiry information can be determined based on the flow node, and the information of each reply card can be assembled according to the node reply template of the flow node to generate reply information, so as to ensure the comprehensiveness and professionalism of the reply information, and to generate reply information that meets the user's needs in a very short time, further improving the timeliness of the reply; at the same time, the next flow node of the flow node can be determined according to the preset scenario flow chart as the target node, and the guided inquiry information of the target node can be obtained to meet the user's potential needs, and finally the reply information and the guided inquiry information can be returned to the interactive interface in turn, guiding the user to further deepen the communication and improve the user experience. Therefore, the present application can use the pre-set scenario flow chart and the reply card in each flow node to provide users with more comprehensive and accurate inquiry replies and inquiry guidance in a timely manner.

[0105] In one embodiment, the node determination module 210 may include:

[0106] The type parsing submodule is used to determine the business scenario corresponding to the inquiry information, and perform type parsing on the inquiry information based on the business scenario to obtain the information type of the inquiry information.

[0107] In one embodiment, the node determination module 210 may further include:

[0108] The parameter determination submodule is used to obtain information parameters of the information type, and determine multiple flow nodes corresponding to the business scenario, and the trigger parameters corresponding to each flow node.

[0109] The parameter matching submodule is used to match the information parameters with each trigger parameter respectively, and determine the flow node corresponding to the information type from each flow node according to the matching result.

[0110] In one embodiment, the reply generation module 220 may include:

[0111] The information segmentation submodule is used to segment the query information to obtain multiple phrases, and perform keyword screening on each phrase to obtain at least one target phrase.

[0112] The card generation submodule is used to read the inquiry object in the inquiry information and generate a reply card corresponding to each target phrase in the flow node based on the inquiry object.

[0113] In one embodiment, the reply generation module 220 may further include:

[0114] The template determination submodule is used to determine the node reply template of the flow node and the parameter type corresponding to each reply card; wherein the node reply template is composed of reply modules of multiple parameter types.

[0115] The template assembly submodule is used to filter out the reply modules corresponding to the parameter type of each reply card from various reply modules, and to lay out and assemble the filtered reply modules to generate an information reply template.

[0116] The information generation submodule is used to fill the parameters in each reply card into the information reply template to obtain the reply information.

[0117] In one embodiment, the inquiry guiding module 230 may include:

[0118] The scenario determination submodule is used to determine the business scenario corresponding to the inquiry information and the scenario branch corresponding to the business scenario in the preset scenario flow chart; the scenario branch is obtained by directed connection of multiple flow nodes.

[0119] The node determination submodule is used to determine the node position of the flow node of the query information in the scene branch, and obtain the next flow node that is directed connected to the node position as the target node.

[0120] In one embodiment, the inquiry guiding module 230 may further include:

[0121] The data acquisition submodule is used to obtain historical shopping guide conversations for multiple business scenarios.

[0122] The branch generation submodule is used to perform scenario analysis on each historical shopping guide dialogue, and to decompose each historical shopping guide dialogue into nodes according to the analysis results to obtain multiple flow nodes, and to generate scenario branches corresponding to each business scenario based on each flow node.

[0123] The flowchart generation submodule is used to determine the directional relationship between the flow nodes in each scene branch, and to connect the flow nodes in a directed manner according to each directional relationship to generate a scene flowchart.

[0124] In one embodiment, the present application further provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the shopping guide dialogue interaction method as described in any one of the above embodiments.

[0125] In one embodiment, the present application further provides a computer device having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the shopping guide dialogue interaction method as described in any one of the above embodiments.

[0126] Indicatively, if Figure 5 As shown, Figure 5 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 300 may be provided as a server. Figure 5 The computer device 300 includes a processing component 302, which further includes one or more processors, and a memory resource represented by a memory 301, for storing instructions executable by the processing component 302, such as an application. The application stored in the memory 301 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 302 is configured to execute instructions to perform the shopping guide dialogue interaction method of any of the above embodiments.

[0127] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.

[0128] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0129] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0130] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.

[0131] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A shopping guide dialogue interaction method, characterized in that: The method comprises: When receiving inquiry information input by the user in the interactive interface, determining the information type of the inquiry information and determining the flow node corresponding to the information type; Determine at least one reply card corresponding to the inquiry information based on the flow node, and assemble information on each reply card according to the node reply template of the flow node to generate reply information; According to a preset scenario flow chart, the next flow node of the flow node is determined as the target node, and the guidance inquiry information of the target node is obtained, and the reply information and the guidance inquiry information are returned to the interactive interface in sequence.

2. The shopping guide dialogue interaction method according to claim 1, characterized in that: The determining of the information type of the inquiry information includes: Determine a business scenario corresponding to the inquiry information, and perform type analysis on the inquiry information based on the business scenario to obtain an information type of the inquiry information.

3. The shopping guide dialogue interaction method according to claim 2, characterized in that: The determining of the flow node corresponding to the information type includes: Acquire information parameters of the information type, and determine multiple flow nodes corresponding to the business scenario, and trigger parameters corresponding to each flow node; The information parameters are matched with the trigger parameters respectively, and the flow node corresponding to the information type is determined from the flow nodes according to the matching result.

4. The shopping guide dialogue interaction method according to claim 1, characterized in that: Determining at least one reply card corresponding to the inquiry information based on the flow node includes: Segmenting the query information to obtain a plurality of phrases, and performing keyword screening on each phrase to obtain at least one target phrase; The inquiry object in the inquiry information is read, and a reply card corresponding to each target phrase is generated in the flow node based on the inquiry object.

5. The shopping guide dialogue interaction method according to claim 1, characterized in that: The step of assembling information of each reply card according to a preset node reply template to generate reply information includes: Determine a node reply template of the flow node and a parameter type corresponding to each reply card; wherein the node reply template is composed of reply modules of multiple parameter types; Filter out the reply modules corresponding to the parameter type of each reply card from various reply modules, and lay out and assemble the filtered reply modules to generate an information reply template; Fill the parameters in each reply card into the information reply template to obtain the reply information.

6. The shopping guide dialogue interaction method according to claim 1, characterized in that: The step of determining the next flow node of the flow node as the target node according to the preset scenario flow chart includes: Determine the business scenario corresponding to the inquiry information, and the scenario branch corresponding to the business scenario in the preset scenario flow chart; the scenario branch is obtained by directed connection of multiple flow nodes; Determine the node position of the flow node of the query information in the scene branch, and obtain the next flow node that is directed connected to the node position as the target node.

7. The shopping guide dialogue interaction method according to claim 1 or 6, characterized in that: The construction process of the scenario flow chart includes: Obtain historical shopping guide conversations for multiple business scenarios; Perform scenario analysis on each historical shopping guide dialogue, and decompose each historical shopping guide dialogue into nodes according to the analysis results to obtain multiple flow nodes, and generate scenario branches corresponding to each business scenario based on each flow node; Determine the directional relationship between the flow nodes in each scene branch, and connect the flow nodes in a directed manner according to each directional relationship to generate a scene flow chart.

8. A shopping guide dialogue interaction device, characterized in that: include: A node determination module, configured to determine, when receiving inquiry information input by a user on an interactive interface, an information type of the inquiry information and a flow node corresponding to the information type; A reply generation module, used to determine at least one reply card corresponding to the inquiry information based on the flow node, and assemble information on each reply card according to the node reply template of the flow node to generate reply information; The inquiry guidance module is used to determine the next flow node of the flow node as the target node according to the preset scenario flow chart, obtain the guidance inquiry information of the target node, and return the reply information and the guidance inquiry information to the interactive interface in sequence.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the shopping guide dialogue interaction method as described in any one of claims 1 to 7.

10. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the shopping guide dialogue interaction method as described in any one of claims 1 to 7 are performed.

Citation Information

Patent Citations

  • Dialogue method of intelligent customer service robot and knowledge base management system of intelligent customer service robot

    CN106484801A

  • Intelligent question-and-answer multi-round interactive method and system based on visual flowchart

    CN106776649A

  • Management method of intelligent interaction process and multi-round conversation method and device

    CN109635085A

  • Intelligent question and answer method, device and equipment and storage medium

    CN111143540A

  • Intelligent question and answer method and device and computer equipment

    CN112052324A