Intelligent agent construction method and device, equipment, storage medium and program product

Abstract

The invention provides an agent construction method and device, electronic equipment, a computer readable storage medium and a computer program product, and relates to the field of artificial intelligence, in particular to the technical fields of man-machine interaction, intelligent robots, natural language processing and the like. The method comprises the following steps: determining a to-be-promoted object and promotion introduction parameters according to a received information promotion request, and labeling the promotion introduction parameters to obtain each target promotion label; filling the promotion introduction parameters of the to-be-promoted object into a preset general promotion dialogue template according to the promotion labels, and generating a target promotion dialogue template; wherein the promotion dialogue template comprises a plurality of dialogue nodes distributed according to a logic level; and based on the target promotion dialogue template, generating a target agent used for carrying out promotion introduction on the to-be-promoted object. According to the method, a flexible reply strategy is provided, and the man-machine interaction quality and efficiency are improved.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, specifically to the technical fields of human-computer interaction, intelligent robots, and natural language processing, and in particular to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for constructing an intelligent agent. Background Technology

[0002] Brand intelligence agents are an innovative concept that combines artificial intelligence (AI) technology with brand management. They apply AI to brand building, marketing, customer relationship management, and other fields, aiming to enhance brand influence and operational efficiency through intelligent means. Utilizing technologies such as natural language processing, machine learning, and data analysis, brand intelligence agents not only help brands communicate better with their target users but also automate tasks, thereby increasing brand value and market competitiveness. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for constructing intelligent agents, which can improve the quality and efficiency of human-computer interaction.

[0004] In a first aspect, embodiments of this disclosure propose an intelligent agent construction method, comprising: determining the target to be promoted and promotion introduction parameters based on a received information promotion request, and tagging the promotion introduction parameters to obtain target promotion tags; filling the promotion introduction parameters of the target to be promoted into a preset general promotion dialogue template according to each promotion tag to generate a target promotion dialogue template; wherein the promotion dialogue template contains multiple dialogue nodes distributed in a logical hierarchy; and generating a target intelligent agent for promoting the target to be promoted based on the target promotion dialogue template.

[0005] Secondly, this disclosure proposes an information promotion method, including: acquiring target users who are identified as interested in the target to be promoted; determining target dialogue nodes according to the target promotion dialogue template; and returning corresponding promotion introduction parameters to the target users according to the target dialogue nodes.

[0006] Thirdly, this disclosure proposes an intelligent agent construction device, comprising: a tagging module configured to determine the target to be promoted and promotional introduction parameters based on a received information promotion request, and to tag the promotional introduction parameters to obtain target promotional tags; a template generation module configured to fill the promotional introduction parameters of the target to be promoted into a preset general promotional dialogue template according to each promotional tag, and generate a target promotional dialogue template; wherein the promotional dialogue template contains multiple dialogue nodes distributed in a logical hierarchy; and an intelligent agent construction module configured to generate a target intelligent agent for promoting the target to be promoted based on the target promotional dialogue template.

[0007] Fourthly, embodiments of this disclosure provide an information promotion device, comprising: a user acquisition module configured to acquire target users identified as interested in the object to be promoted; a node determination module configured to determine target dialogue nodes based on a target promotion dialogue template; and a parameter return module configured to return corresponding promotion introduction parameters to the target users according to the target dialogue nodes.

[0008] Fifthly, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to implement the method described in either the first or second aspect.

[0009] In a sixth aspect, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions that enable a computer to perform the method as described in either the first or second aspect.

[0010] In a seventh aspect, embodiments of this disclosure provide a computer program product including a computer program that, when executed by a processor, can implement the method as described in either the first or second aspect.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is an exemplary system architecture to which this disclosure can be applied; Figure 2 A flowchart of an agent construction method provided in this disclosure embodiment; Figure 3 A flowchart of another intelligent agent construction method provided in this disclosure embodiment; Figure 4 A flowchart illustrating an information promotion method provided in this embodiment of the disclosure; Figure 5 A flowchart for determining a target dialogue node based on a target promotion dialogue template is provided in this embodiment of the disclosure; Figure 6 Another flowchart for determining a target dialogue node based on a target promotion dialogue template provided in this disclosure embodiment; Figure 7 This is a schematic diagram illustrating a target promotion dialogue template for constructing a target intelligent agent in an application scenario, as provided in an embodiment of this disclosure. Figure 8 A structural block diagram of an intelligent agent construction device provided in an embodiment of this disclosure; Figure 9 A structural block diagram of an information promotion device provided in this disclosure embodiment; Figure 10 This is a schematic diagram of the structure of an electronic device suitable for executing an intelligent agent construction method, provided as an embodiment of the present disclosure. Detailed Implementation

[0013] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding; these should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description. It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0014] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0015] Figure 1 An exemplary system architecture 100 is shown, in which embodiments of the intelligent agent construction methods, apparatuses, electronic devices, and computer-readable storage media of this disclosure can be applied.

[0016] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0017] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications for enabling information communication between the terminal devices 101, 102, and 103 and server 105 can be installed. These applications include web browsers, search engines, and instant messaging applications.

[0018] Terminal devices 101, 102, and 103 and server 105 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with displays, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the aforementioned electronic devices, and can be implemented as multiple software programs or software modules, or as a single software program or software module; no specific limitation is made here. When server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When server 105 is software, it can be implemented as multiple software programs or software modules, or as a single software program or software module; no specific limitation is made here.

[0019] Terminal devices 101, 102, 103 and server 105 can provide various services through built-in applications. Taking server 105 as an example, which can provide a web browser-type application that can build an intelligent agent based on information promotion information, server 105 can achieve the following effects when running the web browser-type application: First, it determines the target to be promoted and the promotion introduction parameters according to the received information promotion request, and performs tagging processing on the promotion introduction parameters to obtain each target promotion tag. Then, it fills the promotion introduction parameters of the target to be promoted into a preset general promotion dialogue template according to each promotion tag to generate a target promotion dialogue template. The promotion dialogue template contains multiple dialogue nodes distributed in a logical hierarchy. Finally, it generates a target intelligent agent for promoting the target to be promoted based on the target promotion dialogue template.

[0020] For terminal devices 101, 102, and 103, taking a web browser application that can provide information promotion to users by an intelligent agent built on server 105 as an example, when terminal devices 101, 102, and 103 run the web browser application, the following effects can be achieved: First, the target users who are identified as interested in the target of promotion are obtained; then, the target dialogue node is determined according to the target promotion dialogue template; finally, the corresponding promotion introduction parameters are returned to the target users according to the target dialogue node.

[0021] It should be noted that the information promotion request, the target audience, the promotion introduction parameters, and the promotion dialogue template can be obtained from the terminal devices 101, 102, and 103 via the network 104, or they can be pre-stored locally on the server 105 through various means. Therefore, when the server 105 detects that this data is already stored locally (for example, when it starts processing previously retained agent building and generation tasks), it can choose to directly retrieve this data from the local storage. In this case, the exemplary system architecture 100 may not include the terminal devices 101, 102, and 103 and the network 104.

[0022] Since constructing intelligent agents based on information promotion requires significant computing resources and strong computing power, the intelligent agent construction methods provided in the subsequent embodiments of this disclosure are generally executed by a server 105 with strong computing power and abundant computing resources. Correspondingly, the intelligent agent construction device is also generally located within the server 105. However, it should also be noted that when terminal devices 101, 102, and 103 also possess sufficient computing power and resources, they can also perform the aforementioned calculations performed by the server 105 through web browser applications installed on them, thereby outputting the same results as the server 105. Especially when multiple terminal devices with different computing capabilities exist simultaneously, but a web browser application determines that its terminal device has strong computing power and abundant remaining computing resources, it can allow the terminal device to perform the aforementioned calculations, thereby appropriately reducing the computing pressure on the server 105. Accordingly, the intelligent agent construction device can also be located within terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also exclude the server 105 and the network 104.

[0023] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0024] Please refer to Figure 2 , Figure 2 A flowchart of an agent construction method provided in this disclosure embodiment, wherein process 200 includes the following steps: Step 201: Determine the target audience and promotion parameters based on the received information promotion request, and tag the promotion parameters to obtain promotion tags for each target.

[0025] In this embodiment, when the executing entity (e.g.) Figure 1 When the server (105) receives an information promotion request, it determines the object to be promoted and the promotion introduction parameters. Specifically, the executing entity can receive the information promotion request in various ways (such as submitting a form on the front end, text input, etc.). The information promotion request is an intelligent agent construction request sent to the executing entity when a user wants to promote an object. Then, based on the information promotion request, the executing entity obtains the corresponding object to be promoted and the promotion introduction parameters. The promotion introduction parameters are used to describe the characteristics and functions of the object to be promoted, and the promotion introduction parameters can be of different data types, such as characters, images, videos, audio, etc.

[0026] In this embodiment, the executing entity tags the promotional parameters to obtain target promotional tags. Specifically, the executing entity can associate promotional parameters with specific tags through manual or automatic tagging. For example, the promotional parameter "red" can be tagged with "color," and the promotional parameter "circle" can be tagged with "shape," etc. Alternatively, the executing entity can first tag the promotional parameters automatically, and the user can manually adjust the tags of the automatically tagged promotional parameters.

[0027] Step 202: Fill in the promotion introduction parameters of the target object into the preset general promotion dialogue template according to each promotion tag, and generate the target promotion dialogue template.

[0028] In this embodiment, the executing entity fills in the promotion introduction parameters of the target object obtained in step 201 into a preset general promotion dialogue template according to each promotion tag, thereby generating a target promotion dialogue template. The promotion dialogue template contains multiple dialogue nodes distributed in a logical hierarchy. Some dialogue nodes in the general promotion dialogue template have empty slots for filling in promotion introduction parameters. The promotion introduction parameters are then filled into the dialogue nodes with empty slots to generate the target promotion dialogue template.

[0029] In this embodiment, the promotional parameters can be filled into empty dialog nodes in the following ways: The empty dialog nodes can be matched with the target promotional tags of the promotional parameters, and then the promotional parameters can be filled into the matched dialog nodes; the promotional parameters can be manually filled into the corresponding empty dialog nodes; or the promotional parameters can be filled into the matched dialog nodes first, and then the user can manually adjust the promotional parameters filled into the dialog nodes.

[0030] Step 203: Based on the target promotion dialogue template, generate a target intelligent agent for promoting and introducing the target audience.

[0031] In this embodiment, the executing entity generates a target intelligent agent for promoting and introducing the target object based on the target promotion dialogue template generated in step 202. The target intelligent agent refers to an entity that can autonomously perceive the environment, make inferences and decisions based on different dialogue scenarios, and promote and introduce the target object through multi-turn dialogue interaction.

[0032] The intelligent agent construction method provided in this disclosure generates a target promotion dialogue template based on the target object to be promoted and promotion introduction parameters, and generates a target intelligent agent for promoting the target object based on the target promotion dialogue template. This provides a more flexible response strategy during human-computer interaction, improving the quality and efficiency of human-computer interaction.

[0033] Please refer to Figure 3 , Figure 3 A flowchart of another intelligent agent construction method provided in this disclosure embodiment, wherein process 300 includes the following steps: Step 301: Determine the target audience and promotion parameters based on the received information promotion request, and tag the promotion parameters to obtain promotion tags for each target.

[0034] In this embodiment, the execution subject (e.g.) Figure 1 The server 105 shown can determine the target to be promoted based on the information promotion request and obtain the promotion introduction parameters of the target to be promoted from a preset information disclosure channel. The information promotion request includes the target to be promoted. After determining the target to be promoted, the executing entity obtains the promotion introduction parameters of the target to be promoted from the preset information disclosure channel. The preset information disclosure channel can be an official website with the target to be promoted, a comprehensive search platform database, or a transaction platform database, etc., and is not limited here.

[0035] The implementing entity can perform positional tagging on promotional parameters according to their location within the promotional content of the object to be promoted, resulting in target promotional tags associated with different promotional locations. Specifically, the promotional parameters of the object to be promoted can first be divided into different components, and then each promotional parameter can be associated with its corresponding component's tag through manual or automatic tagging to obtain target promotional tags. For example, when the object to be promoted is a car, different promotional locations such as "engine," "chassis," "body," and "electrical equipment" can be obtained according to the car's structure. Therefore, the target promotional tag for the promotional parameters "number of cylinders" and "displacement" is "engine," the target promotional tag for the promotional parameters "braking performance" and "drive method" is "chassis," the target promotional tag for the promotional parameters "size" and "body material" is "body," and the target promotional tag for the promotional parameters "safety system" and "battery capacity" is "electrical equipment."

[0036] The implementing entity can also tag the promotional parameters according to their corresponding data types to obtain target promotional tags associated with different types of data. Specifically, since promotional parameters can be of different data types, such as characters, images, videos, and audio, the promotional parameters can be manually or automatically labeled to associate them with tags associated with different types of data, thus obtaining target promotional tags.

[0037] The implementing entity can also automatically label the promotion introduction parameters according to different classification standards, and users can manually adjust the promotion labels of the automatically labeled promotion introduction parameters.

[0038] Step 302: Determine the dialog node to be filled in the template slot of the general promotion dialog template, which is used to fill the promotion introduction parameters according to the preset tags, and obtain the slot tag corresponding to the template slot of the dialog node to be filled.

[0039] In this embodiment, the executing entity can determine the dialogue nodes to be filled in the general promotion dialogue template. These dialogue nodes to be filled include template slots for filling promotion introduction parameters according to preset tags, and obtain the preset tags corresponding to the template slots of the dialogue nodes to be filled as slot tags.

[0040] Step 303: Determine the target promotion tag that matches the slot tag, and fill in the promotion introduction parameters corresponding to the target promotion tag into the template slot to generate the target promotion dialogue template.

[0041] In this embodiment, for each dialogue node to be populated in the general promotion dialogue template, the executing entity matches each target promotion tag with the slot tag corresponding to the dialogue node to be populated, obtains the target promotion tag that matches the slot tag, and fills the promotion introduction parameter corresponding to the target promotion tag into the template slot. When all dialogue nodes to be populated in the general promotion dialogue template have been filled with promotion introduction parameters, the current general promotion dialogue template is used as the target promotion dialogue template. The target promotion dialogue template is a dialogue system tree formed according to logical levels and different selection branches.

[0042] In this embodiment, the dialogue nodes in the promotional dialogue template include: static nodes, dynamic nodes, and response nodes. Static nodes do not contain template slots for filling promotional introduction parameters according to preset tags. Dynamic nodes contain at least one template slot for filling promotional introduction parameters according to preset tags. Response nodes are used to generate response content to the upper-level static or dynamic nodes. Response nodes are categorized by scenario type as: silent proactive response nodes, static response nodes, and dynamic response nodes. Silent proactive response nodes refer to response nodes initiated by the executing entity in a silent state. Static response nodes generate response content based on static nodes, and dynamic response nodes generate response content based on dynamic nodes.

[0043] Step 304: Based on the target promotion dialogue template, generate a target intelligent agent for promoting and introducing the target audience.

[0044] In this embodiment, the specific operation of step 304 has been described. Figure 2 Step 203 in the illustrated embodiment is described in detail and will not be repeated here.

[0045] In some optional implementations of this embodiment, when the executing entity determines that the information promotion request contains a promotion emphasis instruction corresponding to the object to be promoted, it can associate the promotion introduction parameter corresponding to the promotion emphasis instruction with the key promotion tag. Here, the promotion emphasis instruction refers to the instruction on the introduction information of the object to be promoted that the user wants to focus on promoting when constructing the target intelligent agent, and the key promotion tag is the part of the target promotion tag that corresponds to the promotion emphasis instruction.

[0046] The intelligent agent construction method provided in this disclosure first associates promotional introduction parameters of the object to be promoted with promotional tags according to different division methods. Then, it matches the target promotional tags corresponding to each promotional introduction parameter with the slot tags of the template slots in the general promotional dialogue template. The promotional introduction parameters of the object to be promoted are filled into the matched template slots to generate a target promotional dialogue template. Finally, a target intelligent agent for promoting the object to be promoted is generated based on the target promotional dialogue template. This target intelligent agent can provide more flexible response strategies in the human-computer interaction process. Through multi-turn dialogue, it increases the user's speaking rate and improves the quality and efficiency of human-computer interaction.

[0047] Please refer to Figure 4 , Figure 4 A flowchart of an information promotion method provided in this disclosure embodiment is applied to a target intelligent agent obtained according to the intelligent agent construction method of process 200 or process 300, wherein process 400 includes the following steps: Step 401: Identify target users who are interested in the promotional content.

[0048] In this embodiment, the execution subject (e.g.) Figure 1 The server 105 shown acquires target users identified as interested in the object to be promoted through various methods. Specifically, when the executing entity detects that a user performs operations such as searching, browsing, or clicking on the object to be promoted, it determines that the user is interested in the object to be promoted and identifies the user as a target user; or, when the executing entity detects that a user asks a question about the object to be promoted, it determines that the user is interested in the object to be promoted and identifies the user as a target user.

[0049] Step 402: Determine the target dialogue node based on the target promotion dialogue template.

[0050] In this embodiment, after the executing entity obtains the target user, it determines the target promotion dialogue template corresponding to the target intelligent agent, and determines the target dialogue node according to the target promotion dialogue template. The target promotion dialogue template is a dialogue system tree formed by logical hierarchy and different selection branches. The target dialogue node is used to generate dialogue content to have a dialogue with the user.

[0051] Step 403: Return the corresponding promotional introduction parameters to the target user according to the target dialogue node.

[0052] In this embodiment, the executing entity returns the corresponding promotional parameters to the target user based on the target dialogue node. Specifically, after determining the target dialogue node, the executing entity generates a response containing the promotional parameters based on the target dialogue node and sends the response to the target user.

[0053] If a user remains silent for more than a preset period, the executing entity can initiate an interest query to the target user through a silent active response node. If no response is received from the target user within the preset period, the entity remains silent until a new query is received from the target user. The interest query is used to rekindle the target user's interest in engaging in dialogue with the target agent.

[0054] The specific implementation steps for the executing entity to initiate an interest inquiry to the target user through a silent proactive reply node are as follows: When the target user's last inquiry cannot match the dynamic dialogue node, the promotion introduction parameters associated with the key promotion tag are filled into the slot of the silent proactive reply node. The target user is then initiated an interest inquiry through the silent proactive reply node. This achieves the goal of attempting to push key promotion information of the target object to the target user in a silent state if the target user's last inquiry did not contain a specific inquiry about the promotion introduction parameters, in order to rekindle the target user's interest in the dialogue about the promoted object.

[0055] Another specific implementation step for the implementing entity to initiate an interest inquiry to the target user through a silent proactive reply node is as follows: First, generate a silent proactive reply node based on the target user's last inquiry and the last reply returned to the target user. Then, initiate an interest inquiry to the target user through the silent proactive reply node. This achieves the goal of initiating an interest inquiry to the target user in a silent state by combining the target user's last inquiry and the last reply returned to the target user, so as to remind the user to continue to pay attention to the target to be promoted.

[0056] In some optional implementations of this embodiment, the execution entity may execute step 402 according to steps 501-504. Please refer to [reference needed]. Figure 5 : Step 501: In response to the target user not initiating an active inquiry request, initiate an initial inquiry to the target user according to the target promotion dialogue template and obtain an initial inquiry response.

[0057] In this embodiment, when the executing entity determines that the target user has not initiated an active inquiry request, it initiates an initial inquiry to the target user according to the target promotion dialogue template and obtains an initial inquiry response. The target promotion dialogue template includes a static response node for initiating the initial inquiry. The response content corresponding to the static response node is sent to the user, and the initial inquiry response returned by the user is received.

[0058] Step 502: In response to the inability to determine the matching target dialogue node based on the keywords in the initial query response, determine the content to be clarified based on the initial query response.

[0059] In this embodiment, when the executing entity cannot determine the matching target dialogue node based on the keywords in the initial inquiry response, it determines the content to be clarified based on the initial inquiry response. Specifically, the executing entity obtains the keywords in the initial inquiry response through various methods, matches the keywords with the dialogue nodes in the target promotion dialogue template, and when no matching dialogue node can be found, it determines the content to be clarified based on the initial inquiry response. The content to be clarified refers to content in the initial inquiry response that is ambiguous in intent, lacks information, or has logical contradictions.

[0060] Step 503: Send a supplementary inquiry to the target user regarding the clarified content and receive a response to the supplementary inquiry.

[0061] In this embodiment, the executing entity initiates supplementary inquiries to the target user regarding the content to be clarified, and receives a response from the user. These supplementary inquiries can either directly ask for missing information in the content to be clarified, or they can guide the user to complete the information through options.

[0062] Step 504: Determine the target dialogue node based on the keywords contained in the initial query response and the supplementary query response.

[0063] In this embodiment, the executing entity determines the target dialogue node based on the keywords contained in the initial query response and the supplementary query response. Specifically, the executing entity merges the keywords contained in the initial query response and the supplementary query response, and determines the dialogue node that matches the keywords in the target promotion dialogue template based on the merged keywords. The matched dialogue node is then identified as the target dialogue node.

[0064] In some optional implementations of this embodiment, the execution subject may also execute step 402 according to steps 601-604. Please refer to [reference needed]. Figure 6 : Step 601: In response to the target user's proactive inquiry request, identify the target dialogue node that matches the keywords in the proactive inquiry request.

[0065] In this embodiment, when the executing entity determines that a target user has initiated a proactive inquiry request, it obtains the keywords in the proactive inquiry request and matches the keywords with the dialogue nodes in the target promotion dialogue template. The matched dialogue node is then identified as the target dialogue node. Here, a proactive inquiry request refers to an inquiry request initiated by the user regarding the target to be promoted, before the target agent initiates an initial inquiry to the target user.

[0066] Step 602: In response to the inability to determine the matching target dialogue node based on the keywords in the active inquiry request, determine the content to be clarified based on the active inquiry request.

[0067] In this embodiment, when the executing entity cannot determine the matching target dialogue node based on the keywords in the proactive inquiry request, it determines the content to be clarified based on the proactive inquiry request. Specifically, the executing entity obtains the keywords in the proactive inquiry request through various methods, matches the obtained keywords with the dialogue nodes in the target promotion dialogue template, and when no matching dialogue node is found, it determines the content to be clarified based on the proactive inquiry request. The content to be clarified refers to content in the proactive inquiry request that is ambiguous in intent, lacks information, or has logical contradictions.

[0068] Step 603: Send a supplementary inquiry to the target user regarding the clarified content and receive a response to the supplementary inquiry.

[0069] In this embodiment, the executing entity initiates supplementary inquiries to the target user regarding the content to be clarified, and receives a response from the user. These supplementary inquiries can either directly ask for missing information in the content to be clarified, or they can guide the user to complete the information through options.

[0070] Step 604: Determine the target dialogue node based on the keywords contained in the proactive inquiry request and the supplementary inquiry response.

[0071] In this embodiment, the executing entity determines the target dialogue node based on the keywords contained in the proactive inquiry request and the supplementary inquiry response. Specifically, the executing entity merges the keywords contained in the proactive inquiry request and the supplementary inquiry response, and determines the dialogue node that matches the keywords in the target promotion dialogue template based on the merged keywords. The matched dialogue node is then identified as the target dialogue node.

[0072] In this embodiment, process 500 and process 600 are specific implementations of step 402 in two different scenarios. Process 500 is a specific implementation of determining the target dialogue node based on the target promotion dialogue template when the target user has not initiated an active inquiry request. Process 600 is a specific implementation of determining the target dialogue node based on the target promotion dialogue template when the target user initiates an active inquiry request.

[0073] The information promotion method provided in this disclosure improves user engagement and dialogue rounds by acquiring target users identified as interested in the promoted object, determining target dialogue nodes based on a target promotion dialogue template, and returning corresponding promotional parameters to target users according to the target dialogue nodes. This utilizes a target intelligent agent to promptly respond to target users interested in the promoted object. Furthermore, this embodiment promptly clarifies user responses / inquiries when there is ambiguity, missing information, or logical contradictions, guiding users to complete the information. Even when users remain silent, the method can proactively initiate inquiries or send key promotional parameters of the promoted object to rekindle user interest. This allows for flexible adoption of various interaction strategies to adapt to different dialogue scenarios, enhancing the user's interactive experience.

[0074] To enhance understanding, this disclosure also provides a specific application scenario and a concrete target promotion dialogue template 700 for constructing a target intelligent agent. Please refer to [example template 700]. Figure 7 As shown.

[0075] In this implementation, when an advertiser places an ad, they send an information promotion request to the server. Based on the information promotion request, the target audience and promotion introduction parameters are determined, and a general promotion dialogue template is obtained. The promotion introduction parameters are filled into the dynamic node according to the target promotion tag. Then, based on the trigger node, dynamic node, and static node, multiple dialogue paths are created according to different dialogue scenarios (such as silence, clarification, etc.). Based on the dialogue paths, corresponding silent active response nodes, dynamic response nodes, and static response nodes are generated. Finally, the multiple dialogue paths are merged to generate the target promotion dialogue template.

[0076] Further reference Figure 8 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of an intelligent agent construction device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0077] like Figure 8 As shown, the intelligent agent construction device 800 of this embodiment may include: a tagging module 801, a template generation module 802, and an intelligent agent construction module 803.

[0078] The tagging module 801 is configured to determine the target of promotion and the promotion introduction parameters based on the received information promotion request, and to perform tagging processing on the promotion introduction parameters to obtain each target promotion tag.

[0079] The template generation module 802 is configured to fill the promotion introduction parameters of the object to be promoted into a preset general promotion dialogue template according to each promotion tag, and generate a target promotion dialogue template; wherein, the promotion dialogue template contains multiple dialogue nodes distributed in a logical hierarchy.

[0080] The agent building module 803 is configured to generate a target agent for promoting and introducing the target object based on the target promotion dialogue template.

[0081] For details on the tagging module 801, template generation module 802, and agent construction module 803, and the resulting technical effects, please refer to [the relevant documentation / references]. Figure 2 The relevant descriptions of steps 201-203 in the corresponding embodiments will not be repeated here.

[0082] In some optional implementations of this embodiment, the tagging module 801 includes: an introduction position division unit, configured to perform position division tagging processing on the promotion introduction parameters according to the introduction position of the object to be promoted, so as to obtain each target promotion tag associated with different introduction positions.

[0083] In some optional implementations of this embodiment, the tagging module 801 includes: a data type division unit, configured to tag the promotion introduction parameters according to the corresponding data type to obtain each target promotion tag associated with different types of data.

[0084] In some optional implementations of this embodiment, the tagging module 801 includes: a promotion object determination unit, configured to determine the object to be promoted based on the information promotion request; and a promotion introduction parameter acquisition unit, configured to acquire the promotion introduction parameters of the object to be promoted from a preset information disclosure channel.

[0085] In some optional implementations of this embodiment, the tagging module 801 further includes: a key tag association unit, configured to associate the promotion introduction parameters corresponding to the promotion emphasis indication with the key promotion tags in response to an information promotion request containing a promotion emphasis indication corresponding to the object to be promoted; wherein, the key promotion tags are the part of the target promotion tags that correspond to the promotion emphasis indication.

[0086] In some optional implementations of this embodiment, the template generation module 802 includes: a slot tag acquisition unit, configured to determine a dialog node to be filled in a template slot for filling promotion introduction parameters according to preset tags in a general promotion dialog template, and acquire the slot tag corresponding to the template slot of the dialog node to be filled; and a tag matching unit, configured to determine a target promotion tag that matches the slot tag, and fill the promotion introduction parameters corresponding to the target promotion tag into the template slot to generate a target promotion dialog template.

[0087] In some optional implementations of this embodiment, the dialogue nodes in the template generation module 802 include: static nodes, dynamic nodes, and reply nodes. The dynamic node contains at least one template slot for filling promotional introduction parameters according to preset tags, and the reply node is used to form reply content to the upper-level static node or dynamic node.

[0088] In some optional implementations of this embodiment, the reply nodes in the template generation module 802 include, according to the scenario type, silent active reply nodes, static reply nodes, and dynamic reply nodes.

[0089] In some optional implementations of this embodiment, the target promotion dialogue template in the agent construction device 800 is a dialogue system tree formed according to logical levels and different selection branches.

[0090] This embodiment exists as a device embodiment corresponding to the above method embodiment. The intelligent agent construction device provided in this embodiment first associates the promotion introduction parameters of the object to be promoted with promotion tags according to different classification standards. Then, it matches the target promotion tags corresponding to each promotion introduction parameter with the slot tags of the template slots in the general promotion dialogue template. The promotion introduction parameters of the object to be promoted are filled into the matched template slots to generate a target promotion dialogue template. Finally, a target intelligent agent for promoting the object to be promoted is generated based on the target promotion dialogue template. This target intelligent agent can provide more flexible response strategies during human-computer interaction, improving the quality and efficiency of human-computer interaction.

[0091] Further reference Figure 9 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of an information promotion device, which is similar to... Figure 4 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0092] like Figure 9 As shown, the information promotion device 900 of this embodiment may include: a user acquisition module 901, a node determination module 902, and a parameter return module 903.

[0093] User acquisition module 901 acquires target users who have been identified as interested in the promotional targets.

[0094] The node determination module 902 is configured to determine the target dialogue node based on the target promotion dialogue template.

[0095] The parameter return module 903 is configured to return the corresponding promotional parameters to the target user based on the target dialogue node.

[0096] For details regarding the user acquisition module 901, node determination module 902, and parameter return module 903, and the resulting technical effects, please refer to [the relevant documentation]. Figure 4 The relevant descriptions of steps 401-403 in the corresponding embodiments will not be repeated here.

[0097] In some optional implementations of this embodiment, the information promotion device 900 further includes: an inquiry initiation module 904, configured to initiate an inquiry of interest to the target user through a silent active reply node in response to the duration of the silent state exceeding a preset duration; and a silent maintenance module 905, configured to remain in a silent state until a new inquiry from the target user is received if no corresponding reply from the target user is received within a preset duration.

[0098] In some optional implementations of this embodiment, the query initiation module 904 includes: a silent reply node generation unit, configured to fill the promotion introduction parameters associated with the key promotion tag into the slot of the silent active reply node in response to the last query initiated by the target user not matching the dynamic dialogue node; and a first query initiation unit, configured to initiate an interest query to the target user through the silent active reply node.

[0099] In some optional implementations of this embodiment, the query initiation module 904 further includes: a silent node generation unit, configured to generate a silent active reply node based on the last query initiated by the target user and the last reply returned to the target user; and a second query initiation unit, configured to initiate an interest query to the target user through the silent active reply node.

[0100] In some optional implementations of this embodiment, the node determination module 902 includes: an initial inquiry response acquisition unit, configured to initiate an initial inquiry to the target user according to the target promotion dialogue template and obtain an initial inquiry response in response to the target user not initiating an active inquiry request; a first content to be clarified determination unit, configured to determine the content to be clarified based on the initial inquiry response in response to the inability to determine a matching target dialogue node based on the keywords in the initial inquiry response; a first supplementary inquiry response acquisition unit, configured to initiate a supplementary inquiry to the target user regarding the content to be clarified and obtain a supplementary inquiry response; and a first target node determination unit, configured to determine the target dialogue node based on the keywords contained in the initial inquiry response and the supplementary inquiry response.

[0101] In some optional implementations of this embodiment, the node determination module 902 includes: a target dialogue node matching unit, configured to determine a target dialogue node matching the keywords in the active inquiry request in response to a target user initiating an active inquiry request; a second content to be clarified determination unit, configured to determine the content to be clarified based on the active inquiry request in response to the inability to determine a matching target dialogue node based on the keywords in the active inquiry request; a second supplementary inquiry response acquisition unit, configured to initiate a supplementary inquiry to the target user regarding the content to be clarified and obtain a supplementary inquiry response; and a second target node determination unit, configured to determine the target dialogue node based on the keywords contained in the active inquiry request and the supplementary inquiry response.

[0102] This embodiment exists as a device embodiment corresponding to the method embodiment described above. The information promotion device provided in this embodiment acquires target users identified as interested in the promotional object, determines target dialogue nodes according to the target promotion dialogue template, and returns corresponding promotional introduction parameters to the target users according to the target dialogue nodes. By utilizing the target intelligent agent to respond promptly to target users interested in the promotional object, the user speaking rate and dialogue rounds are improved. Furthermore, this embodiment promptly performs clarification operations when user replies / inquiries are ambiguous, lack information, or have logical contradictions, guiding users to complete the information. When users remain silent, it actively initiates inquiries to rekindle users' interest in the promotional object, thereby flexibly adopting multiple interaction strategies to adapt to different dialogue scenarios and improving the user's interactive experience.

[0103] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the methods described in any of the above embodiments.

[0104] According to embodiments of this disclosure, this disclosure also provides a readable storage medium storing computer instructions that enable a computer to perform the methods described in any of the above embodiments when executed.

[0105] According to embodiments of this disclosure, this disclosure also provides a computer program product that, when executed by a processor, can implement the methods described in any of the above embodiments.

[0106] Figure 10A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0107] like Figure 10 As shown, device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1002 or a computer program loaded from storage unit 10010 into random access memory (RAM) 1003. The RAM 1003 may also store various programs and data required for the operation of device 1000. The computing unit 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Input / output (I / O) interface 1005 is also connected to bus 1004.

[0108] Multiple components in device 1000 are connected to I / O interface 1005, including: input unit 1006, such as keyboard, mouse, etc.; output unit 1009, such as various types of monitors, speakers, etc.; storage unit 1008, such as disk, optical disk, etc.; and communication unit 1009, such as network card, modem, wireless transceiver, etc. Communication unit 1009 allows device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0109] The computing unit 1001 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as the agent construction method. For example, in some embodiments, the agent construction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the methods described above by any other suitable means (e.g., by means of firmware).

[0110] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0114] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0115] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0116] According to the technical solution of this disclosure, a target promotion dialogue template is generated based on the target object and promotion introduction parameters. A target intelligent agent is then generated based on the target promotion dialogue template to promote the target object. This provides a more flexible response strategy during human-computer interaction, improving the quality and efficiency of the interaction. Furthermore, the target intelligent agent responds promptly to target users interested in the target object, increasing user engagement and dialogue rounds, thus enhancing the user's interactive experience.

[0117] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0118] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for constructing an intelligent agent, comprising: Based on the received information promotion request, determine the target to be promoted and the promotion introduction parameters, and perform tagging processing on the promotion introduction parameters to obtain each target promotion tag; The promotion introduction parameters of the object to be promoted are filled into a preset general promotion dialogue template according to the promotion tags to generate a target promotion dialogue template; wherein, the promotion dialogue template contains multiple dialogue nodes distributed in a logical hierarchy; Based on the target promotion dialogue template, a target intelligent agent is generated to promote and introduce the object to be promoted.

2. The method according to claim 1, wherein, The step of filling the promotion introduction parameters of the object to be promoted into a preset general promotion dialogue template according to the promotion tags, and generating a target promotion dialogue template includes: Determine the dialogue node to be filled in the template slot of the general promotion dialogue template, which is used to fill the promotion introduction parameters according to the preset tags, and obtain the slot tag corresponding to the template slot of the dialogue node to be filled. Identify the target promotion tag that matches the slot tag, and fill the promotion introduction parameters corresponding to the target promotion tag into the template slot to generate the target promotion dialogue template.

3. The method according to claim 1, wherein, The process of tagging the promotional introduction parameters to obtain target promotional tags includes: The promotion introduction parameters are tagged according to their position relative to the introduction of the object to be promoted, resulting in target promotion tags associated with different introduction positions.

4. The method according to claim 1, wherein, The process of tagging the promotional introduction parameters to obtain target promotional tags includes: The promotional introduction parameters are tagged according to their corresponding data types to obtain target promotional tags associated with different types of data.

5. The method according to claim 1, wherein, The step of determining the target audience and its promotional introduction parameters based on the information promotion request includes: The target audience for promotion is determined based on the information promotion request; The promotional introduction parameters of the target object are obtained from the preset information disclosure channels.

6. The method according to claim 5, further comprising: In response to the information promotion request containing a promotion emphasis indication corresponding to the object to be promoted, the promotion introduction parameter corresponding to the promotion emphasis indication is associated with the key promotion tag; wherein, the key promotion tag is a portion of the target promotion tags that corresponds to the promotion emphasis indication.

7. The method according to any one of claims 1-6, wherein, The dialogue nodes include: static nodes, dynamic nodes, and reply nodes. The dynamic nodes contain at least one template slot for filling promotional introduction parameters according to preset tags. The reply nodes are used to generate reply content to the upper-level static or dynamic nodes.

8. The method according to claim 7, wherein, The reply nodes are categorized by scenario type as follows: silent active reply nodes, static reply nodes, and dynamic reply nodes.

9. The method according to any one of claims 1-6, wherein, The target promotion dialogue template is a dialogue system tree formed by logical levels and different selected branches.

10. An information dissemination method, applied to a target intelligent agent obtained by the intelligent agent construction method according to any one of claims 1-9, comprising: Acquire target users who have been identified as interested in the promotional materials; Determine the target dialogue nodes based on the target promotion dialogue template; The corresponding promotional parameters are returned to the target user according to the target dialogue node.

11. The method of claim 10, further comprising: If the duration of silence exceeds a preset time, an interesting query is initiated to the target user through a silent active response node; If no response is received from the target user for the inquiry of interest within a preset time period, the system remains silent until a new inquiry is received from the target user.

12. The method according to claim 11, wherein, The step of initiating an interesting query to the target user through a silent active reply node includes: In response to the fact that the last inquiry initiated by the target user could not be matched with a dynamic dialogue node, the promotion introduction parameters associated with the key promotion tag were filled into the slot of the silent active reply node; The silent proactive reply node initiates an inquiry of interest to the target user.

13. The method according to claim 11, wherein, The step of initiating an interesting query to the target user through a silent active reply node includes: The silent proactive reply node is generated based on the last inquiry initiated by the target user and the last reply returned to the target user. The silent proactive reply node initiates an inquiry of interest to the target user.

14. The method of claim 10, wherein, The step of determining the target dialogue node based on the target promotion dialogue template includes: In response to the target user not initiating an active inquiry request, an initial inquiry is initiated to the target user according to the target promotion dialogue template, and an initial inquiry response is obtained; In response to the inability to determine a matching target dialogue node based on the keywords in the initial query response, the content to be clarified is determined based on the initial query response; A supplementary inquiry is sent to the target user regarding the content to be clarified, and a response to the supplementary inquiry is received. The target dialogue node is determined based on the keywords contained in the initial query response and the supplementary query response.

15. The method according to claim 10, wherein, The step of determining the target dialogue node based on the target promotion dialogue template includes: In response to a proactive inquiry request initiated by a target user, a target dialogue node matching the keywords in the proactive inquiry request is identified; In response to the inability to determine a matching target dialogue node based on the keywords in the proactive inquiry request, the content to be clarified is determined based on the proactive inquiry request; A supplementary inquiry is sent to the target user regarding the content to be clarified, and a response to the supplementary inquiry is received. The target dialogue node is determined based on the keywords contained in the proactive inquiry request and the supplementary inquiry response.

16. An intelligent agent construction device, comprising: The tagging module is configured to determine the target to be promoted and the promotion introduction parameters based on the received information promotion request, and to perform tagging processing on the promotion introduction parameters to obtain each target promotion tag; The template generation module is configured to fill the promotion introduction parameters of the object to be promoted into a preset general promotion dialogue template according to the promotion tags, and generate a target promotion dialogue template; wherein, the promotion dialogue template contains multiple dialogue nodes distributed in a logical hierarchy; The agent building module is configured to generate a target agent for promoting and introducing the object to be promoted, based on the target promotion dialogue template.

17. An information dissemination device, applied to a target intelligent agent obtained by the intelligent agent construction device according to claim 16, comprising: The user acquisition module is configured to acquire target users who are identified as interested in the promotional targets. The node determination module is configured to determine the target dialogue node based on the target promotion dialogue template; The parameter return module is configured to return the corresponding promotional introduction parameters to the target user based on the target dialogue node.

18. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-15.

19. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-15.

20. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-15.

Images