Collaborative application method and device of multi-mode intelligent interaction system and medium

Abstract

The invention discloses a collaborative application method and device of a multi-mode intelligent interaction system and a medium, belongs to the technical field of industrial internet, and is used for solving the technical problems that an existing digital transformation innovation experience center is difficult to meet diversified requirements of customers, the interaction mode is single, and the manual dependence degree is high. The method comprises the steps of performing full-contact data acquisition processing on key behavior tracks of enterprise users on various platforms through enterprise user IDs subjected to code scanning identification to obtain multi-dimensional behavior data; constructing and updating the portrait of the enterprise user to obtain the portrait of the enterprise user; carrying out matching processing on the enterprise user portrait and a content library; generating an exclusive two-dimensional code for code scanning processing of an enterprise user, and determining an enterprise diagnosis report; performing question and answer response control on agents in different areas in the digital transformation innovation experience center to obtain an intelligent interaction strategy; and based on the intelligent interaction strategy, generating a guide visiting route for guiding exhibition of the enterprise user.

Description

A collaborative application method, device and medium for a multimodal intelligent interaction system Technical Field

[0001] This application relates to the field of industrial internet technology, and in particular to a collaborative application method, device and medium for a multimodal intelligent interactive system. Background Technology

[0002] Digital transformation innovation experience centers serve as important windows and pathways for understanding, experiencing, and implementing digital transformation. However, how to further enhance the comprehensiveness, interactivity, and intelligence of these centers, and build a new service model that is "immersive, full-link, and highly convertible," has become a key issue that urgently needs to be addressed.

[0003] Currently, the innovation experience center faces three main pain points: First, the guided tour is inefficient, relying too heavily on human explanations, which makes it difficult to meet the diverse needs of customers; second, the interaction mode is monotonous, and traditional explanation methods cannot meet the personalized needs of customers, resulting in visitors only passively receiving information, lacking real-time interaction and in-depth data collection capabilities, thus causing a break in the conversion chain; finally, the equipment operation and maintenance collaboration is lagging behind, with equipment failures mainly relying on manual inspections and dedicated personnel for handling. In the event of a sudden accident and the absence of maintenance personnel, no one knows the solution and cannot achieve timely handling. Summary of the Invention

[0004] This application provides a collaborative application method, device, and medium for a multimodal intelligent interactive system to solve the following technical problem: existing digital transformation innovation experience centers are unable to meet the diverse needs of customers, have a single interaction mode, and rely heavily on manual intervention.

[0005] The embodiments of this application adopt the following technical solution: On the one hand, the embodiments of this application provide a collaborative application method for a multimodal intelligent interaction system, including: collecting and processing multi-touchpoint data on the key behavioral trajectories of enterprise users on various platforms through scanning and identifying enterprise user IDs, to obtain multi-dimensional behavioral data; constructing and updating the enterprise user profile based on the multi-dimensional behavioral data, to obtain an enterprise user profile; matching the enterprise user profile with a content library; generating a unique QR code for the enterprise user's scanning and processing, and determining an enterprise diagnostic report; controlling the intelligent agents in different areas of the digital transformation innovation experience center to answer questions based on the enterprise diagnostic report, to obtain an intelligent interaction strategy; and generating a guided tour route for guiding enterprise users to exhibit based on the intelligent interaction strategy.

[0006] This application's embodiments, through the collection and processing of multi-dimensional behavioral data from enterprise users, enable the system to construct personalized enterprise user profiles, thereby providing services that better meet user needs. Specifically, the construction and updating of enterprise user profiles helps enterprises better understand user behavior and optimize products and services. Then, matching these profiles with a content library allows for the rapid retrieval of information relevant to enterprise user needs, improving information retrieval efficiency. Furthermore, enterprise diagnostic reports provide customized suggestions and solutions, facilitating digital transformation. Simultaneously, based on these reports, the system can intelligently control the intelligent agent's question-and-answer responses, providing more accurate and relevant information. Moreover, intelligent interaction strategies can guide enterprise users through effective exhibition visits, enhancing their experience in the digital innovation experience center.

[0007] In one feasible implementation, by scanning the enterprise user ID after identification, full-touchpoint data collection and processing of the enterprise user's key behavioral trajectories on various platforms is performed to obtain multi-dimensional behavioral data. Specifically, this includes: scanning the enterprise user's QR code to obtain the enterprise user ID; identifying and marking the enterprise user's key behavioral trajectories on various platforms based on the enterprise user ID to obtain key behavioral type information; wherein, the key behavioral type information includes at least: browsing behavior, clicking behavior, searching behavior, and conversion behavior; performing execution action analysis at the execution layer on the key behavioral type information to obtain key behavioral action information; wherein, the key behavioral action information includes at least: section / column preference, dwell time, content interaction, and access path and frequency; based on the key behavioral type information and the key behavioral action information, the multi-dimensional behavioral data of the enterprise user under multiple behaviors is obtained.

[0008] In one feasible implementation, a profile of enterprise users is constructed and updated based on the multidimensional behavioral data to obtain an enterprise user profile. Specifically, this includes: using preset big data analysis and machine learning algorithms to identify features of interest preferences in the multidimensional behavioral data to obtain the enterprise user's enterprise interest preference features; identifying features of behavioral habits in the multidimensional behavioral data to obtain the enterprise user's enterprise behavioral habit features; identifying features of demand tendencies in the multidimensional behavioral data to obtain the enterprise user's enterprise demand tendency features; and performing real-time dynamic updates on the enterprise interest preference features, enterprise behavioral habit features, and enterprise demand tendency features based on enterprise user behavior to construct the enterprise user profile corresponding to the enterprise user behavior.

[0009] In one feasible implementation, the enterprise user profile is matched with the content library, specifically including: matching and associating the enterprise user profile with the content library to obtain an associated content library; and querying the associated content library based on the enterprise user's interest tags, historical preferences, and real-time behavior to determine personalized content that is highly relevant to the enterprise user's needs.

[0010] In one feasible implementation, a unique QR code is generated for the enterprise user to scan, and an enterprise diagnostic report is determined. Specifically, this includes: adaptively matching the visualization platform interface, recommended sections, and default settings in the digital transformation innovation experience center based on the enterprise user profile to obtain a unique QR code specific to the enterprise user; associating the personalized requirements and the enterprise user profile with the unique QR code; and performing personalized diagnosis and analysis on the enterprise user based on the unique QR code scanned by the enterprise user, retrieving and obtaining the enterprise diagnostic report.

[0011] In one feasible implementation, before performing question-and-answer response control on the intelligent agents in different areas of the digital transformation innovation experience center based on the enterprise diagnostic report to obtain an intelligent interaction strategy, the method further includes: activating the navigation control of the digital transformation innovation experience center based on the enterprise diagnostic report; and performing information interaction control on the enterprise user through a digital human interaction layer and based on the enterprise diagnostic report, thereby obtaining a digital human interaction strategy.

[0012] In one feasible implementation, based on the enterprise diagnostic report, intelligent agents in different areas of the digital transformation innovation experience center are subjected to question-and-answer response control to obtain an intelligent interaction strategy. Specifically, this includes: deploying intelligent agents with AI functions in different areas of the digital transformation innovation experience center; wherein the functions of the different areas include: diagnostic evaluation area, sample learning area, scenario experience area, package recommendation area, element guarantee area, industrial adaptation area, and talent training area; based on the intelligent agents and the corresponding associated enterprise diagnostic report, providing enterprise users with solution recommendations and in-depth content explanations for the functions of different areas, and obtaining the intelligent interaction strategy based on the enterprise demand information responded to by natural language processing.

[0013] In one feasible implementation, based on the intelligent interaction strategy, a guided tour route for enterprise users to visit the exhibition is generated. Specifically, this includes: obtaining a weight coefficient for each area function based on the degree of importance of the area functions that enterprise users are interested in according to the intelligent interaction strategy; controlling the route priority of different areas in the digital transformation innovation experience center according to the weight coefficients corresponding to each area function to obtain a route planning strategy; using an intelligent robot to guide the tour route through the route planning strategy, generating a guided tour route for enterprise users to visit the exhibition; and collecting real-time enterprise user behavior data; wherein the real-time enterprise user behavior data includes at least: dwell time, interaction frequency, question content, and evaluation feedback; and feeding back the real-time enterprise user behavior data in real time and updating it in the enterprise diagnostic report.

[0014] Secondly, embodiments of this application also provide a collaborative application device for a multimodal intelligent interaction system, the 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, enabling the at least one processor to execute a collaborative application method for a multimodal intelligent interaction system as described in any of the above embodiments.

[0015] Thirdly, embodiments of this application also provide a non-volatile computer storage medium, wherein the storage medium is a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium stores at least one program, each program including instructions, and when the instructions are executed by a terminal, the terminal executes a collaborative application method of a multimodal intelligent interaction system as described in any of the above embodiments.

[0016] This application provides a collaborative application method, device and medium for a multimodal intelligent interaction system. Compared with the prior art, the embodiments of this application have the following beneficial technical effects: 1. Personalized service: By collecting and processing multidimensional behavioral data of enterprise users, the system can build personalized enterprise user profiles, thereby providing services that are more in line with user needs.

[0017] 2. Efficient user profile management: The construction and updating of enterprise user profiles can help enterprises better understand user behavior and optimize products and services.

[0018] 3. Intelligent matching: Matching enterprise user profiles with the content library can quickly find information related to the needs of enterprise users, improving the efficiency of information retrieval.

[0019] 4. Convenient user interaction: By generating a unique QR code, enterprise users can easily interact with the system, simplifying the access process.

[0020] 5. Precise diagnostic reports: Enterprise diagnostic reports can provide enterprise users with customized suggestions and solutions, which can help enterprises carry out digital transformation.

[0021] 6. Intelligent Question-Answering Response: Based on enterprise diagnostic reports, the system can intelligently control the agent's question-answering response, providing more accurate and relevant information.

[0022] 7. Optimize user experience: Intelligent interaction strategies can guide enterprise users to conduct effective exhibition visits and improve the user experience in the digital innovation experience center.

[0023] 8. Improve resource utilization: Through intelligent interaction strategies, the resources of the exhibition center can be better utilized, reducing unnecessary waiting and ineffective visitor routes. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 is a flowchart of a collaborative application method of a multimodal intelligent interaction system provided by an embodiment of this application; Figure 2 is a framework diagram of a multimodal collaborative intelligent interaction system provided by an embodiment of this application; Figure 3 is a structural schematic diagram of a collaborative application device of a multimodal intelligent interaction system provided by an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0026] This application provides a collaborative application method for a multimodal intelligent interaction system. As shown in Figure 1, the collaborative application method for a multimodal intelligent interaction system specifically includes steps S101-S105: S101, using the enterprise user ID identified by scanning the code, performing full-touchpoint data collection and processing on the key behavioral trajectories of the enterprise user on various platforms to obtain multidimensional behavioral data.

[0027] Specifically, the first step is to scan the QR code of visiting enterprise users to obtain their enterprise user IDs.

[0028] Furthermore, based on the enterprise user ID, the key behavioral trajectories of enterprise users on various platforms are identified and labeled to obtain key behavior type information. This key behavior type information includes at least: browsing behavior, click behavior, search behavior, and conversion behavior.

[0029] Furthermore, the key behavior type information is analyzed at the execution level to obtain key behavior action information. This key behavior action information includes at least: section / column preferences, dwell time, content interaction, and access path and frequency.

[0030] Furthermore, based on key behavior type information and key behavior action information, multidimensional behavioral data of enterprise users under multiple behaviors are obtained.

[0031] In one embodiment, Figure 2 is a framework diagram of a multimodal collaborative intelligent interaction system provided by an embodiment of this application. As shown in Figure 2, it is necessary to first systematically collect diversified behavioral data of users across terminals (including but not limited to WeChat official accounts, official websites, etc.) through enterprise user IDs, deeply construct user profiles, and realize intelligent and accurate push of content and services. Among them, the collection of key behavior type information and key behavior action information of all touchpoints, that is, accurately recording the key behavioral trajectory of users on various platforms, mainly including: 1) Browsing behavior: specific pages visited, articles browsed, and the completeness of reading / viewing.

[0032] 2) Click behavior: Clicked buttons, links, recommendation slots, and interactive elements.

[0033] 3) Section / Column Preferences: Navigation columns actively selected by users, and specific functional areas that are frequently accessed.

[0034] 4) Duration of stay: The time invested in a single page, specific content, or the entire session, reflecting the depth of interest.

[0035] 5) Search behavior: Entered search keywords and clicked search results.

[0036] 6) Content interaction: Active participation behaviors such as liking, saving, and sharing.

[0037] 7) Conversion behaviors: Key conversion actions such as form submission, appointment, and registration.

[0038] 8) Access path and frequency: Jump paths between different terminals and the periodicity of access.

[0039] In one embodiment, as shown in Figure 2, in the intelligent interaction system: 1) Scanning terminal → Multimodal hub: can retrieve user data and match user information; 2) Multimodal hub → Intelligent execution layer: can accurately match cases, distribute data to intelligent agents, and coordinate various intelligent agents; 3) Intelligent execution layer → Data feedback loop: can intelligently guide the visitor route, intelligently participate in interactive activities, intelligently collect data, and intelligently answer questions; 4) Data feedback loop → Multimodal hub: can provide feedback and optimization. In the feedback and optimization step: enterprise data can be iterated to generate user profiles and equipment health assessment reports. Real-time frequency feedback, question content feedback, evaluation feedback, and other data are provided. Data can also be fed back in real time based on the enterprise's stay duration.

[0040] S102. Based on multi-dimensional behavioral data, construct and update the profile of enterprise users to obtain the enterprise user profile.

[0041] Specifically, it is also necessary to use pre-set big data analysis and machine learning algorithms to identify the characteristics of interest preferences in multi-dimensional behavioral data, thereby obtaining the enterprise user's enterprise interest preference characteristics.

[0042] Furthermore, feature recognition is performed on the behavioral habit content in the multidimensional behavioral data to obtain the enterprise user's enterprise behavioral habit characteristics.

[0043] Furthermore, feature identification is performed on the demand tendency content in the multidimensional behavioral data to obtain the enterprise demand tendency characteristics of enterprise users.

[0044] Furthermore, the enterprise's interest and preference characteristics, behavioral habits, and demand tendencies are dynamically updated in real time based on enterprise user behavior, and an enterprise user profile corresponding to the enterprise user behavior is constructed.

[0045] In one embodiment, based on aggregated multidimensional behavioral data, big data analytics and machine learning algorithms are used to structurally and taggedly depict user characteristics: In terms of interests and preferences, it is necessary to identify users' long-term preferences and real-time interest hotspots for different content themes, product categories, and service directions. In terms of behavioral habits, it is necessary to clarify users' active time periods, frequently used devices, and operating habits. In terms of demand tendencies, it is necessary to infer users' potential needs and pain points (e.g., through search term and dwell time content analysis). Finally, a dynamic update mechanism is established to ensure that user profiles can evolve in real-time or near real-time as user behavior changes, maintaining the timeliness and accuracy of the profiles.

[0046] S103. Match the enterprise user profile with the content library; generate a unique QR code for enterprise users to scan and process, and determine the enterprise diagnostic report.

[0047] Specifically, the enterprise user profiles are first matched and associated with the content library to obtain the associated content library.

[0048] Furthermore, based on enterprise users' interest tags, historical preferences, and real-time behavior, the relevant content library is queried and processed to identify personalized content that is highly relevant to the enterprise users' needs.

[0049] In one embodiment, as shown in Figure 2, personalized content recommendation is also required. This involves intelligently matching user profiles with the content library, and then pushing highly relevant content based on the user's interest tags, historical preferences, and real-time behavior to improve information acquisition efficiency and user experience.

[0050] Furthermore, based on the enterprise user profile, the visualization platform interface, recommended sections, and default settings in the Digital Transformation Innovation Experience Center are adaptively matched to generate a unique QR code for each enterprise user. Then, personalized content and the enterprise user profile are linked to the unique QR code.

[0051] In one embodiment, the platform interface, recommendation section priority, default settings, etc., also need to be adjusted based on user profiles to provide a more personalized experience that meets user habits and needs, and generate exclusive QR codes.

[0052] Furthermore, based on the unique QR code scanned by enterprise users, personalized diagnosis and explanation are performed on enterprise users, and enterprise diagnostic reports are retrieved and obtained.

[0053] In one embodiment, enterprise users scan a code at an offline experience center's scanning terminal, enabling full terminal and system integration, precise data capture, triggering the system to wake up the corresponding digital human, generating personalized diagnostic introductions and analyses, and finally retrieving the corresponding pre-stored enterprise diagnostic report.

[0054] S104. Based on the enterprise diagnostic report, the intelligent agents in different areas of the digital transformation innovation experience center are controlled through question-and-answer response to obtain intelligent interaction strategies.

[0055] Specifically, based on the enterprise diagnostic report, the navigation control of the digital transformation innovation experience center is activated.

[0056] Furthermore, through the digital human interaction layer and based on enterprise diagnostic reports, information interaction control is implemented for enterprise users via visual interfaces and voice interaction to obtain digital human interaction strategies. In other words, within the digital human interaction layer, customized diagnostic interpretations and solution recommendations can be provided through visual interfaces and voice interaction.

[0057] Furthermore, AI-enabled intelligent agents will be deployed in different areas of the Digital Transformation Innovation Experience Center. These different areas will include: a diagnostic assessment area, a demonstration and learning area, a scenario experience area, a package recommendation area, a resource support area, an industrial adaptation area, and a talent training area.

[0058] Furthermore, based on the intelligent agent and the corresponding enterprise diagnostic report, the system provides solution recommendations and in-depth content analysis for enterprise users under different regional functions, and obtains intelligent interaction strategies based on the enterprise demand information responded to by natural language processing.

[0059] In one embodiment, as shown in Figure 2, during intelligent execution, in the intelligent agent question-and-answer layer, AI intelligent agents are first deployed across the entire area. Based on the existing seven areas of the Digital Transformation Innovation Experience Center—diagnosis and assessment, learning from examples, scenario experience, package recommendation, element guarantee, industrial adaptation, and talent training—regional intelligent agents are deployed in each area, with each layer interconnected and focusing on key points. They can ask questions via voice and interact intelligently, providing in-depth answers and analysis to the recommended solutions. Natural Language Processing (NLP) responds to enterprise needs and collects user behavior data to send back to the backend, thereby obtaining intelligent interaction strategies.

[0060] S105. Based on intelligent interaction strategies, generate guided tour routes to guide enterprise users through the exhibition.

[0061] Specifically, the weighting coefficient for each regional function is obtained by combining the degree of importance of regional functions that enterprise users pay attention to in the intelligent interaction strategy.

[0062] Furthermore, based on the weight coefficients corresponding to the functions of each area, route priority control is applied to different areas within the Digital Transformation Innovation Experience Center to obtain a route planning strategy.

[0063] Furthermore, intelligent robots guide and control the tour route using route planning strategies, generating guided tour routes for enterprise users. Real-time enterprise user behavior data is also collected. This real-time enterprise user behavior data includes at least: dwell time, interaction frequency, questions asked, and feedback. In other words, at the robot execution layer, the mobile robot provides common tour explanations, guides the tour route in real time, and collects user behavior data (dwell time / interaction frequency / questions asked / feedback, etc.). Real-time enterprise user behavior data can also be fed back and updated in the enterprise diagnostic report in real time.

[0064] As a feasible implementation method, in the data-driven stage of the collaborative application system of the multimodal intelligent interaction system, interactive behavior data and environmental sensor data (temperature, humidity / energy consumption) can be uploaded to the central database in real time; while the data analysis module generates enterprise user profiles and equipment health assessment reports. At the same time, in the proactive operation and maintenance stage, (1) predictive operation and maintenance: the equipment operation and maintenance intelligent agent can provide early warning of power grid faults based on historical data and machine learning algorithms. (2) intelligent operation guidance: by constructing an operation and maintenance intelligent agent, the equipment operation instructions are displayed to the operation and maintenance personnel in the form of voice interaction.

[0065] As a feasible implementation method, the key components of the collaborative application system architecture of the multimodal intelligent interaction system mainly include: a multimodal fusion hub (coordinating data flows from digital humans, robots, and sensors), a distributed intelligent agent network (regionally deployed lightweight AI interaction units), and a closed-loop feedback engine (feeding user behavior data back to the platform to iterate on enterprise needs). Specifically, this application constructs a full-link service closed loop of "scan-to-wake → intelligent interaction → data-driven → proactive operation and maintenance"; achieves personalized guidance and real-time data collection through multimodal fusion (digital human + intelligent agent + robot + sensor); and improves equipment management efficiency and security based on environmental perception and predictive operation and maintenance.

[0066] Among them, this application also has the following features: (1) Improved conversion efficiency: Personalized service paths effectively improve the conversion rate of visiting enterprises to sign contracts. (2) Optimized operation and maintenance response: Predictive operation and maintenance models improve fault response efficiency, reduce downtime losses, and avoid reception accidents. (3) Breakthrough in interaction depth: Multimodal collaboration realizes the upgrade from one-way tour to two-way data collection, and the completeness of interactive data collection is high. (4) Forward security and prevention: Environmental sensors + operation and maintenance intelligent agents work together to provide early warning of potential equipment risks.

[0067] In addition, this application embodiment also provides a collaborative application device for a multimodal intelligent interaction system, as shown in Figure 3. The collaborative application device 300 of the multimodal intelligent interaction system specifically includes: at least one processor 301; and a memory 302 communicatively connected to at least one processor 301. The memory 302 stores instructions that can be executed by at least one processor 301, so that at least one processor 301 can execute: collecting and processing key behavioral trajectories of enterprise users on various platforms through scanning and identifying enterprise user IDs to obtain multidimensional behavioral data; constructing and updating enterprise user profiles based on multidimensional behavioral data to obtain enterprise user profiles; matching enterprise user profiles with content libraries; generating exclusive QR codes for enterprise user scanning and processing, and determining enterprise diagnostic reports; controlling intelligent agents in different areas of the digital transformation innovation experience center to answer questions and respond according to the enterprise diagnostic reports to obtain intelligent interaction strategies; and generating guided tour routes for guiding enterprise users to exhibit based on the intelligent interaction strategies.

[0068] By collecting and processing multidimensional behavioral data from enterprise users, the system can build personalized enterprise user profiles, thereby providing services that better meet user needs. In other words, the construction and updating of enterprise user profiles helps enterprises better understand user behavior and optimize products and services. Then, matching these user profiles with a content library allows for the rapid retrieval of information relevant to enterprise user needs, improving information retrieval efficiency. Furthermore, enterprise diagnostic reports provide customized suggestions and solutions, aiding in digital transformation. Based on these reports, the system can intelligently control the intelligent agent's question-and-answer responses, providing more accurate and relevant information. Moreover, intelligent interaction strategies can guide enterprise users through effective exhibition visits, enhancing their experience in the digital innovation experience center.

[0069] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0070] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0071] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0073] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0074] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0077] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0079] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of this specification.

Claims

1. A collaborative application method for a multimodal intelligent interaction system, characterized in that, The method includes: collecting and processing multi-dimensional behavioral data from all touchpoints of enterprise users' key behavioral trajectories on various platforms using the enterprise user ID identified by scanning a QR code; constructing and updating enterprise user profiles based on the multi-dimensional behavioral data; matching the enterprise user profiles with a content library; generating a unique QR code for enterprise user scanning and processing, and determining an enterprise diagnostic report; controlling the intelligent agents in different areas of the digital transformation innovation experience center to respond to questions based on the enterprise diagnostic report, and obtaining intelligent interaction strategies; and generating guided tour routes for enterprise users to visit exhibitions based on the intelligent interaction strategies.

2. The collaborative application method of a multimodal intelligent interaction system according to claim 1, characterized in that, By scanning the enterprise user ID, the system collects and processes key behavioral data from all touchpoints across various platforms to obtain multi-dimensional behavioral data. Specifically, this includes: scanning the enterprise user's QR code to obtain their ID; identifying and marking the enterprise user's key behavioral trajectories across various platforms based on their ID to obtain key behavioral type information; wherein the key behavioral type information includes at least browsing behavior, click behavior, search behavior, and conversion behavior; performing execution action analysis on the key behavioral type information at the execution layer to obtain key behavioral action information; wherein the key behavioral action information includes at least section / column preferences, dwell time, content interaction, and access path and frequency; and based on the key behavioral type information and the key behavioral action information, the system obtains the multi-dimensional behavioral data of the enterprise user under various behavioral patterns.

3. The collaborative application method of a multimodal intelligent interaction system according to claim 1, characterized in that, Based on the multidimensional behavioral data, a profile of enterprise users is constructed and updated to obtain an enterprise user profile. Specifically, this includes: using preset big data analysis and machine learning algorithms to identify features of interest and preference content in the multidimensional behavioral data to obtain the enterprise user's enterprise interest and preference features; identifying features of behavioral habits content in the multidimensional behavioral data to obtain the enterprise user's enterprise behavioral habit features; identifying features of demand tendencies content in the multidimensional behavioral data to obtain the enterprise user's enterprise demand tendencies; and performing real-time dynamic updates of the enterprise interest and preference features, enterprise behavioral habit features, and enterprise demand tendencies features based on enterprise user behavior to construct the enterprise user profile corresponding to the enterprise user behavior.

4. The collaborative application method of a multimodal intelligent interaction system according to claim 1, characterized in that, The matching process between the enterprise user profile and the content library specifically includes: matching and associating the enterprise user profile with the content library to obtain an associated content library; and querying the associated content library based on the enterprise user's interest tags, historical preferences, and real-time behavior to determine personalized content that is highly relevant to the enterprise user's needs.

5. The collaborative application method of a multimodal intelligent interaction system according to claim 4, characterized in that, Generating a unique QR code for enterprise users to scan and processing, and determining an enterprise diagnostic report, specifically includes: adaptively matching the visualization platform interface, recommended sections, and default settings in the digital transformation innovation experience center according to the enterprise user profile to obtain a unique QR code for the enterprise user; associating the personalized needs content and the enterprise user profile with the unique QR code; and performing personalized diagnosis and introduction analysis on the enterprise user based on the unique QR code after scanning, retrieving and obtaining the enterprise diagnostic report.

6. The collaborative application method of a multimodal intelligent interaction system according to claim 1, characterized in that, Before obtaining an intelligent interaction strategy by performing question-and-answer response control on the intelligent agents in different areas of the digital transformation innovation experience center based on the enterprise diagnostic report, the method further includes: activating the navigation control of the digital transformation innovation experience center based on the enterprise diagnostic report; and obtaining a digital human interaction strategy by performing information interaction control on the enterprise users through the digital human interaction layer and based on the enterprise diagnostic report, using a visual interface and voice interaction.

7. The collaborative application method of a multimodal intelligent interaction system according to claim 6, characterized in that, Based on the enterprise diagnostic report, intelligent agents in different areas of the Digital Transformation Innovation Experience Center are subjected to question-and-answer response control to obtain intelligent interaction strategies. Specifically, this includes deploying AI-enabled intelligent agents in different areas of the Digital Transformation Innovation Experience Center; wherein the functions of the different areas include: diagnostic evaluation area, sample learning area, scenario experience area, package recommendation area, element guarantee area, industrial adaptation area, and talent training area; based on the intelligent agents and the corresponding associated enterprise diagnostic report, the enterprise users are provided with solution recommendations and in-depth content explanations for the functions of different areas, and the intelligent interaction strategies are obtained based on the enterprise demand information responded to by natural language processing.

8. The collaborative application method of a multimodal intelligent interaction system according to claim 1, characterized in that, Based on the aforementioned intelligent interaction strategy, a guided tour route for enterprise users to visit the exhibition is generated. Specifically, this includes: obtaining a weight coefficient for each functional area based on the degree of importance of the enterprise users' focus on that area in the intelligent interaction strategy; controlling the route priority for different areas in the digital transformation innovation experience center according to the weight coefficients corresponding to each functional area, thus obtaining a route planning strategy; using an intelligent robot to guide the tour route through the route planning strategy, generating a guided tour route for enterprise users to visit the exhibition; and collecting real-time enterprise user behavior data; wherein the real-time enterprise user behavior data includes at least: dwell time, interaction frequency, question content, and evaluation feedback; and feeding back the real-time enterprise user behavior data in real time and updating it in the enterprise diagnostic report.

9. A collaborative application device for a multimodal intelligent interaction system, characterized in that, The 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 execute a collaborative application method of a multimodal intelligent interaction system according to any one of claims 1-8.

10. A non-volatile computer storage medium, characterized in that, The storage medium is a non-volatile computer-readable storage medium that stores at least one program, each program including instructions that, when executed by a terminal, cause the terminal to perform a collaborative application method of a multimodal intelligent interaction system according to any one of claims 1-8.

Images