A data processing method, electronic equipment, medium and product

Abstract

The application provides a data processing method, an electronic device, a medium and a product; wherein the method comprises: obtaining behavior data of a plurality of users in a target space; determining user distribution information based on the behavior data; the user distribution information indicates the behavior distribution of a plurality of users in different regions in the target space; determining a guiding strategy of a target user based on the user distribution information; the guiding strategy is used to guide the behavior trajectory of the target user in the target space; a plurality of users include the target user; the behavior trajectory of the user in the target space can be dynamically guided.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data processing method, electronic device, medium, and product. Background Technology

[0002] In related technologies, spatial guidance for groups is usually pre-set. For example, when a user's terminal device (such as a mobile phone) enters a specific space, the corresponding preset route is displayed, which cannot achieve dynamic guidance for users. Summary of the Invention

[0003] This application provides a data processing method, electronic device, medium, and product that can dynamically guide a user's behavior trajectory within a target space.

[0004] The technical solution of this application embodiment is implemented as follows: This application provides a data processing method, the method comprising: Acquire behavioral data of multiple users in a target space; User distribution information is determined based on the behavioral data; the user distribution information indicates the behavioral distribution of multiple users in different regions of the target space; A guidance strategy for the target user is determined based on the user distribution information; the guidance strategy is used to guide the behavioral trajectory of the target user in the target space; the multiple users include the target user.

[0005] The method in the above scheme further includes: The service rules for the target space are determined; the service rules indicate the triggering conditions for service information in the target space; the service information includes one or more of the following: product information; video information; route information; The target service for each user is generated based on the behavioral data and the service rules.

[0006] The method in the above scheme further includes: Obtain feedback information from each user regarding the target service; The service rules are adjusted based on the feedback information.

[0007] The method in the above scheme further includes: Based on the user distribution information, determine the group behavior patterns of multiple users; Target data is determined from the behavioral data based on the group behavior pattern; the frequency threshold of the target data is greater than a preset threshold; The service rules are adjusted based on the target data.

[0008] In the above scheme, the step of determining the guidance strategy for target users based on the user distribution information includes: The attention index of the target area is determined based on the user distribution information; the target area is the area in the target space that the target user is interested in. The guidance strategy is determined based on the attention index.

[0009] In the above scheme, determining the guidance strategy based on the attention index includes: If the attention index indicates that the attention level of the target area is lower than the attention threshold, an enhanced guidance strategy is generated; the guidance strategy includes the enhanced guidance strategy; the enhanced guidance strategy includes one or more of the following: Increase the display weight of the target area; Adjust the position of the target area; Displays recommended content associated with the target area.

[0010] In the above scheme, determining the guidance strategy based on the attention index includes: If the attention index indicates that the attention level of the target area is higher than the attention threshold, a traffic diversion and guidance strategy is generated; the guidance strategy includes the traffic diversion and guidance strategy; the traffic diversion and guidance strategy includes one or more of the following: Reduce the display weight of the target area; Guide the target user to move away from the target area.

[0011] A data processing apparatus, the apparatus comprising: The acquisition unit is used to acquire behavioral data of multiple users in the target space; A processing unit is configured to determine user distribution information based on the behavioral data; the user distribution information indicates the behavioral distribution of multiple users in different regions of the target space; The processing unit is used to determine a guidance strategy for a target user based on the user distribution information; the guidance strategy is used to guide the behavioral trajectory of the target user in the target space; the multiple users include the target user.

[0012] This application provides an electronic device, including: a processor and a memory for storing computer programs capable of running on the processor. When the processor runs the computer program, it executes the data processing method provided in the embodiments of this application.

[0013] This application provides a computer-readable storage medium storing a computer program or computer-executable instructions for implementing the data processing method provided in this application when executed by a processor.

[0014] This application provides a computer program product, including a computer program or computer executable instructions. When the computer program or computer executable instructions are executed by a processor, they implement the data processing method provided in this application.

[0015] The embodiments of this application have the following beneficial effects: This application obtains behavioral data of multiple users in a target space; determines user distribution information based on the behavioral data; the user distribution information indicates the behavioral distribution of multiple users in different areas of the target space; determines a guidance strategy for the target user based on the user distribution information; the guidance strategy is used to guide the behavioral trajectory of the target user in the target space; the multiple users include the target user; and it is possible to dynamically guide the behavioral trajectory of the user in the target space. Attached Figure Description

[0016] Figure 1 A flowchart illustrating a data processing method provided in an embodiment of this application; Figure 2 A flowchart illustrating a data processing method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0019] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0020] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0021] Unless otherwise defined, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the embodiments of this application is for the purpose of describing the embodiments of this application only and is not intended to limit this application.

[0022] In the implementation of this application, the collection and processing of relevant data should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of laws and regulations and the authorization of the personal information subject.

[0023] Figure 1 This is an optional flowchart illustrating the data processing method provided in the embodiments of this application. The following will be combined with... Figure 1 The steps shown are explained as follows: Figure 1 As shown, the method includes the following steps: Step S101: Obtain behavioral data of multiple users in the target space.

[0024] Understandably, behavioral data can include data related to the user's spatiotemporal state and interactive behavior. In this embodiment, the execution side is a cloud platform. Behavioral data can be collected through a terminal, such as a mobile phone / glasses with integrated augmented reality functionality, a virtual reality headset, a computer browser, or the touchscreen of a smart all-in-one device. The terminal may include the following functional modules: Sensing and Positioning Module: Utilizes the terminal's hardware sensors (such as GPS and inertial measurement unit) and operating system services to acquire and process real-time spatiotemporal status data of the user within the space.

[0025] Command generation and reporting module: Encapsulates the user's spatiotemporal state and interactive behavior (such as clicks and voice input) into a standardized data format and reports it to the cloud platform through a communication protocol.

[0026] Rendering and presentation module: Responsible for receiving data instructions from the cloud platform and accurately integrating digital content (such as enhanced display effects, heatmaps, and recommended routes) with the real world or virtual scenes before presenting it to the user.

[0027] The methods and scenarios for terminal data collection are shown in Table 1: Input method Scene describe Touch operation Mobile Phone / AR Glasses Common interactions, such as clicking, swiping, and map dragging. Voice input All terminals Supports question and answer, navigation, interrupt commands, etc. gaze VR headset Focusing on the area triggers AI interaction or selection Shake and other sensors Mobile phone light interaction Activate recommendations and refresh routes Emotion recognition (expandable) Based on camera / voice tone Personalized adjustments to the style and pace of the presentation Table 1 In practical applications, a cloud platform can include three core units: Data Access and Processing Unit: As the infrastructure for data processing, this unit is responsible for receiving and preprocessing the raw data reported by all terminals.

[0028] Artificial Intelligence Decision and Generation Unit: This unit is responsible for generating content and responding to users.

[0029] Evolution and Regulation Unit: This unit is responsible for monitoring, evaluating, and optimizing the entire platform.

[0030] Step S102: Determine user distribution information based on behavioral data; user distribution information indicates the behavioral distribution of multiple users in different areas of the target space.

[0031] Understandably, the data access and processing unit receives behavioral data uploaded by the terminal, the artificial intelligence decision-making and generation unit can generate target services for each user, and the evolution and control unit determines user distribution information and monitors the behavioral distribution of multiple users in different areas of the target space.

[0032] In practical applications, the cloud platform may include a pre-trained user behavior model. The user behavior model includes service rules for the target space. The service rules indicate the triggering conditions for service information in the target space. For example, if a user stays within the geofence of exhibit A for more than 3 seconds, the platform will proactively push answers to frequently asked questions about that exhibit to the user.

[0033] User behavior models can generate target services for each user based on service rules and behavioral data; for example, for museums, they can generate corresponding explanatory content; for live videos, they can generate snippets of highlights; and for vending machines, they can generate recommended combinations of products based on the items selected by the user.

[0034] The evolution and control unit periodically calculates the balance index of different regions based on user distribution information to quantify the concentration of user attention. For example, the ratio of the number of independent users who stayed in the i-th pre-divided spatial region within a preset time window T (e.g., 5 minutes) to the total number of independent users served by the system within that time window. This definition enables the balance index to smoothly and in real time reflect the distribution of user attention in recent times.

[0035] Step S103: Determine the guidance strategy for the target user based on user distribution information; the guidance strategy is used to guide the target user's behavioral trajectory in the target space; multiple users include the target user.

[0036] In practical applications, attention metrics for target areas can be determined based on user distribution information; the target area is the area in the target space that the target users pay attention to, and the guidance strategy for the target users can be determined based on the attention metrics of the target area.

[0037] Attention metrics can be understood as balance metrics. The calculated balance metrics can be compared with a preset attention threshold to generate guidance strategies that guide the user's behavior trajectory in the target space. For example, when the balance metrics of the area currently being paid attention to by the user are higher than the attention threshold, the user can be guided to move away from the target area.

[0038] As can be seen from the above, this application obtains behavioral data of multiple users in a target space; determines user distribution information based on the behavioral data; the user distribution information indicates the behavioral distribution of multiple users in different areas of the target space; determines a guidance strategy for the target user based on the user distribution information; the guidance strategy is used to guide the behavioral trajectory of the target user in the target space; the multiple users include the target user; and it is able to dynamically guide the behavioral trajectory of the user in the target space.

[0039] In some embodiments of this application, the method further includes: The service rules for the target space are defined; the service rules indicate the triggering conditions for service information in the target space; the service information includes one or more of the following: product information; video information; route information; The target service for each user is generated based on behavioral data and service rules.

[0040] In practical applications, the cloud platform may include a pre-trained user behavior model. The user behavior model includes service rules for the target space. The service rules indicate the triggering conditions for service information in the target space. For example, if a user stays within the geofence of exhibit A for more than 3 seconds, the platform will proactively push answers to frequently asked questions about that exhibit to the user.

[0041] User behavior models can discretize user behavior data into a series of events. Each event is converted into an independent token; for example, a location is represented as [LOC_ID_123], a stay exceeding 30 seconds is represented as [DWELL_30S+], and a photo interaction is represented as [INTERACT_PHOTO]. Thus, a complete user trajectory is converted into a token sequence, such as "[LOC_ID_101] [DWELL_60S+][LOC_ID_105] [INTERACT_QA]...". These token sequences are used as training data, with the training objective being to predict the next most likely and highest-value [LOC_ID_XXX] token, i.e., the target service, based on existing sequences. When generating the target service, the model outputs a completely new token sequence. Taking route information as an example, the system also includes a path validity verification module. This module checks the generated sequences against a preset spatial graph to ensure that the route is physically feasible and conflict-free, and removes invalid generated results.

[0042] In some embodiments of this application, the method further includes: Obtain feedback information from each user regarding the target service; Service rules are adjusted based on feedback information.

[0043] In practical applications, the content evaluation module in the evolution and regulation unit tracks relevant feedback information in real time, such as route completion rate, user bounce rate at which node, and user explicit ratings.

[0044] Route completion rate: Route completion rate = (number of unique users who completed the route / number of unique users who started the route) × 100%. This is a key "health" indicator that reflects the overall design quality of the route.

[0045] Bounce rate at a node: Bounce rate at node N = (Number of users who abandon the route at node N / Total number of users who reach node N) × 100%. This metric is a "microscope" for diagnosing route problems and can help the system understand "why the route completion rate is low".

[0046] Explicit user ratings: Explicit user ratings are a subjective, qualitative supplementary metric, referring to the system proactively inviting users to provide direct, quantitative evaluations of their experience. This feedback is not inferred from observing user behavior, but rather given directly by the user, such as: star ratings, likes / dislikes, Net Promoter Score (NPS), tag selection, or short reviews.

[0047] The comprehensive performance score aims to integrate multiple evaluation indicators into a single, quantifiable score, facilitating automated judgment and ranking by the system. Its calculation typically uses a weighted summation formula: Overall performance score (S_perf) = w1*(route completion rate) + w2*(1-average node bounce rate) + w3*(normalized average explicit score).

[0048] Here, w1, w2, and w3 are weight coefficients, and their sum is 1. For example, if user reputation is valued more, the weight of w3 can be increased; if route flow design is valued more, the weight of w2 can be increased.

[0049] Average Bounce Rate: This is the average bounce rate of all nodes on a route, reflecting the overall smoothness of the route. Subtracting it from 1 is to convert it into a positive indicator (i.e., the lower the bounce rate, the higher the score).

[0050] Normalized average explicit rating: Since users' explicit ratings (such as 1-5 stars) have different dimensions than other metrics (0-100%), they need to be normalized first (for example, mapping 5 stars to 100 points and 1 star to 20 points) before being weighted.

[0051] This formula allows the system to obtain a comprehensive, objective, and configurable quantitative evaluation of the AI-generated route.

[0052] Suppose the system generates a "recap video of a goal", the overall performance score of this service content is calculated as follows: (S_perf) = w1 * (normalized tactical insight score) + w2 * (normalized analysis depth score) + w3 * (normalized average explicit score).

[0053] If you want AI to generate professional and hardcore tactical analysis content, you can increase the weight of w1 (tactical insight score); If you want AI to generate exciting and fast-paced highlight reels; If you want AI to generate content that is most popular with the public, you can increase the weight of w3 (explicit rating).

[0054] The evolution and regulation unit analyzes performance scores. If the score is lower than a preset threshold, or if the analysis reveals specific defects (e.g., "node 5 has an excessively high bounce rate"), the system will transform this negative feedback information into new service rules.

[0055] The AI ​​decision-making and generation unit is used to fine-tune or guide the regeneration of its user behavior model; this closed-loop process of "creation-evaluation-feedback-recreation" continues, ensuring the continuous evolution of content quality.

[0056] In some embodiments of this application, the method further includes: Determine the group behavior patterns of multiple users based on user distribution information; Target data is determined from behavioral data based on group behavior patterns; the frequency threshold of the target data is greater than a preset threshold. Adjust service rules based on target data.

[0057] In practical applications, the user behavior analysis module in the cloud platform analyzes behavioral data. When the analysis finds that more than a preset threshold number of users trigger similar interaction events (e.g., asking the same or semantically similar questions) within a specific spatial area, the system identifies this as a high-confidence group interaction pattern. Based on this group behavior pattern, the platform filters high-value data, i.e., target data, from the behavioral data. Each complete piece of behavioral data is first quantitatively scored. This score is calculated by weighting multiple dimensions of indicators, such as: Exploration Level: Measures how well a user discovers "niche" nodes. The more non-popular nodes a user visits, or the longer they spend on these nodes, the higher the score.

[0058] Engagement: Measures the depth of user interaction with content. The more interactive behaviors a user triggers during the route, such as Q&A, displaying enhanced interactions, and sharing photos, the higher the score.

[0059] Satisfaction: Directly derived from users' explicit ratings (such as star ratings).

[0060] Smoothness: Measures the smoothness of user experience; a high score indicates a high route completion rate and fewer meaningless wanderings and backtracking.

[0061] For example, the evaluation index score in a free-viewing scenario could be: Tactical Insight Score: This score is awarded for anticipating or focusing on key off-the-ball movements. If a user focuses on the player who provides the crucial assist or makes a key off-the-ball run within 5-10 seconds before a goal, they will receive a very high Tactical Insight Score.

[0062] Analysis Depth Score: This score rewards users for their in-depth analysis of key moments. For example, if a user's trajectory sequence immediately follows a series of slow-motion replays and tactical perspective changes after a crucial event (foul, goal), the score will be high.

[0063] Narrative coherence score: This score is used to assess whether a viewing trajectory constitutes a logical "viewing story." For example, a trajectory that starts with a defender's interception, focuses on key passes and runs, and finally leads to a striker's shot would have a high coherence score.

[0064] These scores are used to calculate a final "total trajectory value score" using preset weights (which can be adjusted by the operator). When the total score of a trajectory exceeds a preset threshold, it is marked as a "high-value user trajectory". These trajectories can be used as training data to input into the user behavior model and adjust the service rules in user behavior.

[0065] For example, the training and tuning of a user behavior model can be achieved in the following ways: 1. Over the past week, the "Evolution and Regulation Unit" has collected tens of thousands of behavioral data and performance scores on AI-generated routes.

[0066] 2. The platform found that users generally rated routes that included "surprisingly unpopular nodes" higher.

[0067] 3. The platform system packages all these new high-scoring trajectory data and user feedback data into a new training dataset.

[0068] 4. During off-peak business hours (e.g., early morning), the system launches a background batch processing task. This task fine-tunes the existing user behavior model; in the process, the model learns new data patterns (such as how to better balance popular and unpopular nodes).

[0069] 5. After the adjustments are completed, the new model is deployed and goes online, replacing the old model.

[0070] 6. The "Evolution and Regulation Unit" detected that the "Recommended Route - Version 1.0" had an excessively high exit rate at node 5; it generated a new instruction: "Please generate a route similar to version 1.0, but which must avoid node 5." 7. The instruction is sent to the "AI Decision and Generation Unit". This unit calls the currently trained generative model and takes this new constraint as input (this can be technically achieved through Prompt Engineering or Conditional Generation).

[0071] 8. The model performs an inference calculation and outputs a new route sequence that meets the requirements.

[0072] In some embodiments of this application, determining the guidance strategy for target users based on user distribution information includes: The attention index of the target area is determined based on user distribution information; the target area is the area in the target space that the target users pay attention to. The guidance strategy is determined based on attention metrics.

[0073] In practical applications, the global experience balance analysis module in the evolution and regulation unit calculates the user distribution balance index S covering the entire space once at a preset time period (e.g., every minute) to quantify the current concentration of user attention.

[0074] The equilibrium index S can be calculated based on the Shannon entropy formula: S = ∑pilogpi, where pi is the probability that a user appeared in region i within a preset time period (pi = ui / utotal, the number of users staying in region i divided by the total number of users). Users are evenly distributed across regions in the space, with each region having a roughly equal probability pi. Concentration of users in a few regions results in extremely high probabilities pi in those regions, while pi in other regions approaches 0. In this case, the system's uncertainty is minimized, and the entropy S is very low. A higher S value indicates a more balanced user distribution and a healthier spatial ecosystem; a lower S value indicates more concentrated user attention and a higher risk of imbalance. This provides a precise decision-making basis for subsequent automated control.

[0075] If the attention index indicates that the attention level of a target area is below the attention threshold, that is, one or more areas identified as "niche but potentially popular", new information attraction cores can be created to guide user flow.

[0076] The implementation steps can be as follows: The system extracts relevant keywords (such as "bronze ware" and "Shang Dynasty") from the interactive knowledge base; then, it combines these keywords with a preset "personality template" (e.g., "a learned historian with a rigorous speaking style") and dynamically generates a complete personality setting text through prompt engineering; finally, it injects this setting text as context into a large language model (LLM) service, enabling it to interact with the user in real time and contextually based on this specific personality.

[0077] If the attention index indicates that the attention level of the target area is higher than the attention threshold, the visual saturation and intensity or brightness of the super hotspot area can be temporarily reduced, while the visual appeal of secondary hotspots or "unpopular" potential areas can be increased. The reduction magnitude d can be a function related to the degree to which S deviates from the threshold Sth, for example, d=k×(Sth) S), where k is a preset control coefficient, which ensures that the intensity of control is proportional to the severity of the problem.

[0078] In some embodiments of this application, the guidance strategy is determined based on attention metrics, including: If the attention index indicates that the attention level of the target area is below the attention threshold, an enhanced guidance strategy is generated; the guidance strategy includes an enhanced guidance strategy; the enhanced guidance strategy includes one or more of the following: Increase the display weight of the target area; Adjust the position of the target area; Displays recommended content associated with the target area.

[0079] In practical applications, taking live football matches as an example, the vast majority (usually over 90%) of viewers' attention will be overly focused on the "super hot spot" of the ball handler or the ball itself. Here, "different areas" are redefined as every "focusable entity i" on the field, including: player 1, player 2, ..., the ball, the head coach, the referee, specific tactical areas (such as the penalty area, the center circle), etc.

[0080] The meaning of the indicator pi: The ratio of the total time that all viewers’ attention (judged by the focus of the virtual camera or the user’s click) is directed to entity i within a very short time window (e.g., 3 seconds) to the total time that attention is directed to all entities.

[0081] Meaning of Indicator S: When the S value is extremely low, it means that almost all viewers' attention (pi) is focused on the "ball" or the "player with the ball," indicating a highly uneven distribution of attention. In a crucial counter-attack, 95% of attention is focused on the player with the ball for more than 5 seconds. The platform briefly highlights a key "cold spot" with a very soft halo or highlight outline. For example, if the system identifies a striker making a crucial offside run through the tactical analysis module, it will mark him with a light gold halo for 1-2 seconds. Tactical Arrows / Trajectory Lines: Semi-transparent, dynamic arrows are used on the screen to draw the positioning and movement route of a key defensive player, helping viewers understand their defensive intentions.

[0082] A small sub-window can also automatically pop up in a corner of the main screen. The content of this window is not random, but rather the "cold spot" information that the system determines is most valuable at that moment.

[0083] Alternatively, a data label might briefly appear next to a key player without the ball, such as "Key runner in this attack" or "Has shaken off the defender," using concise text to supplement visual guidance.

[0084] Once the attack or tactical round ends (e.g., the ball goes out of bounds, a shot is completed), the audience's attention will naturally shift from a highly focused state, and the S-value will rise again. Once the S-value returns to above the healthy threshold, all visual guidance halos, tactical arrows, intelligent sub-screens, and other interfering elements will automatically and smoothly disappear, completely returning the screen to the user without any distractions. See Table 2 for details. screen area content Main screen area Free-view 3D video stream / virtual scene Bottom toolbar View switching button + heatmap switch + AI recommendation Top right corner Activated AI personality avatar (click to interact) Top left corner Current recommended perspective tag ("High-energy offensive perspective") pop-up notification "Switch to AI-powered commentary replay?", "Hot spots detected, recommended redirection", etc. Table 2 In some embodiments of this application, the guidance strategy is determined based on attention metrics, including: If the attention index indicates that the attention level of the target area is higher than the attention threshold, a diversion and guidance strategy is generated; the guidance strategy includes a diversion and guidance strategy; the diversion and guidance strategy includes one or more of the following: Reduce the display weight of the target area; Guide target users to migrate from the target region.

[0085] In practical applications, taking cultural tourism scenarios as an example, when a user approaches a painting, the system, having learned from historical data, has identified "curiosity about the posture of the horse in the painting" as a high-frequency interaction pattern in that area. The platform will proactively push relevant questions to initiate in-depth exploration. Simultaneously, the mall operator can see through the backend that the system, detecting excessive crowding in the first-floor atrium ("balance index" S below the threshold), has automatically activated a temporary interactive game as an "emergent AI interaction point" in a relatively quiet second-floor area. This successfully guided some family customers to the second floor, optimizing the overall customer flow distribution in the mall.

[0086] Taking a smart vending machine scenario as an example, an office worker buys lunch from a vending machine in an office building. Here, the "target space" refers to the user interface of a single machine and the sales network formed by all the machines.

[0087] The user added a salad to their shopping cart. Based on analysis of historical data from this and surrounding devices, the system detected a very high probability that the user who purchased this salad would also buy sugar-free soda. A recommendation immediately popped up on the screen: "This salad and sugar-free soda is a popular healthy combination!", along with a discounted price for the combination.

[0088] The system detected that the click-through rate of a certain new product across the entire network was far below the average (a global "cold spot"). To boost sales and collect user feedback, the system triggered adjustments, automatically increasing the user interface weight of the new product on 10% of machines and adding a "New Product Try" label. If a best-selling product sells out on machine A, the system can also guide users to a nearby machine B with stock to complete the purchase, achieving supply and demand equilibrium at the network level. After analyzing tens of thousands of "successful transaction paths" across the entire network through its evolution and adjustment unit, the platform discovered that the combination of "coffee + chocolate croissant on a rainy day" had an extremely high purchase rate. Therefore, it automatically generated a dynamic package called "Rainy Day Little Joys" and automatically pinned this package to the top of machines in specific areas when the weather forecast indicates rain. The effectiveness of this package will be continuously tracked and evaluated and used for subsequent marketing strategy iterations.

[0089] refer to Figure 2 As shown, in a feasible scenario, the data processing method of this application embodiment can be implemented in the following way: When users explore and interact in physical or virtual spaces, every movement, click, and question they make is captured by the user experience device and reported to the cloud in real time as anonymous behavioral data (movement trajectory, dwell time, interaction details, etc.).

[0090] These data are ultimately compiled into three crucial dynamic databases: a spatial attention heatmap that visually reflects the distribution of current user attention; a user trajectory database that records the exploration paths of all users; and an interaction knowledge base that stores user questions and system answers.

[0091] The evolution and regulation unit continuously analyzes the three major databases and, based on the analysis results, initiates three intelligent processes at different levels and with different cycles in parallel.

[0092] First, the health of the entire spatial ecosystem is ensured by periodically calculating the balance degree S to determine whether user attention is excessively concentrated. Once S is found to be below the healthy threshold, the system will trigger a balance adjustment strategy. The instructions are divided into two parts: one part directly affects the user terminal, such as adjusting the visual weight of hotspots; the other part notifies the AI ​​decision-making and generation unit to instantiate an "emergent AI personality" in a less popular area to create new attractions and actively guide the flow of people.

[0093] Second, it delves into the interactive knowledge base to analyze high-frequency interaction patterns (AI decision-making and generation unit). When it discovers that a large number of users are asking the same question in a certain location, it generates a "proactive service rule" and deploys this newly learned "experience" to the "execution arm." In this way, when users trigger the same scenario again, the system can "predict" and proactively provide services.

[0094] Third, by analyzing high-value user trajectories, it identifies the most interesting and efficient exploration paths. It then issues instructions to the "execution arm" to "create new routes" and optimizes the model based on user feedback and target data.

[0095] Based on the same inventive concept as described above, Figure 3 This is a schematic diagram of a data processing device provided in an embodiment of the present invention. The device includes: Acquisition unit 301 is used to acquire behavioral data of multiple users in the target space; Processing unit 302 is used to determine user distribution information based on behavioral data; the user distribution information indicates the behavioral distribution of multiple users in different areas of the target space; Processing unit 302 is used to determine the guidance strategy for the target user based on user distribution information; the guidance strategy is used to guide the behavioral trajectory of the target user in the target space; multiple users include the target user.

[0096] In some embodiments of this application, processing unit 302 is used to determine service rules for a target space; the service rules indicate the triggering conditions for service information in the target space; the service information includes one or more of the following: product information; video information; route information; The target service for each user is generated based on behavioral data and service rules.

[0097] In some embodiments of this application, the acquisition unit 301 is used to acquire feedback information of each user on the target service; Processing unit 302 is used to adjust service rules based on feedback information.

[0098] In some embodiments of this application, processing unit 302 is used to determine the group behavior pattern of multiple users based on user distribution information; Target data is determined from behavioral data based on group behavior patterns; the frequency threshold of the target data is greater than a preset threshold. Adjust service rules based on target data.

[0099] In some embodiments of this application, the processing unit 302 is used to determine the attention index of the target area based on user distribution information; the target area is the area in the target space that the target user pays attention to. The guidance strategy is determined based on attention metrics.

[0100] In some embodiments of this application, processing unit 302 is configured to generate an enhanced guidance strategy if the attention index indicates that the attention of the target area is lower than the attention threshold; the guidance strategy includes an enhanced guidance strategy; the enhanced guidance strategy includes one or more of the following: Increase the display weight of the target area; Adjust the position of the target area; Displays recommended content associated with the target area.

[0101] In some embodiments of this application, processing unit 302 is configured to generate a traffic diversion strategy if the attention index indicates that the attention of the target area is higher than the attention threshold; the guidance strategy includes a traffic diversion strategy; the traffic diversion strategy includes one or more of the following: Reduce the display weight of the target area; Guide target users to migrate from the target region.

[0102] Based on the foregoing embodiments, embodiments of this application provide an electronic device. Figure 4 This is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention. The electronic device 400 includes at least one processor 401 and a memory 402. Optionally, the electronic device 400 may further include at least one communication interface 403. The various components in the electronic device 400 are coupled together through a bus system 404. It can be understood that the bus system 404 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 404 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 4 The general designated all buses as Bus System 404.

[0103] Based on the hardware implementation of the above program modules, the communication interface 403 is able to interact with other communication devices. The processor 401 is connected to the communication interface 403 to enable information interaction with other communication devices and to execute the methods provided by one or more of the above-mentioned technical solutions when running a computer program; Memory 402, the computer program is stored in memory 402.

[0104] Specifically, processor 401 is used to acquire behavioral data of multiple users in the target space; User distribution information is determined based on behavioral data; user distribution information indicates the behavioral distribution of multiple users in different regions of the target space; The guidance strategy for target users is determined based on user distribution information; the guidance strategy is used to guide the behavioral trajectory of target users in the target space; multiple users include target users.

[0105] In some embodiments of this application, processor 401 is configured to determine service rules for a target space; the service rules indicate the triggering conditions for service information in the target space; the service information includes one or more of the following: product information; video information; route information; The target service for each user is generated based on behavioral data and service rules.

[0106] In some embodiments of this application, processor 401 is used to obtain feedback information from each user regarding the target service; Service rules are adjusted based on feedback information.

[0107] In some embodiments of this application, processor 401 is used to determine the group behavior pattern of multiple users based on user distribution information; Target data is determined from behavioral data based on group behavior patterns; the frequency threshold of the target data is greater than a preset threshold. Adjust service rules based on target data.

[0108] In some embodiments of this application, processor 401 is used to determine the attention index of a target region based on user distribution information; the target region is the region in the target space that the target user pays attention to. The guidance strategy is determined based on attention metrics.

[0109] In some embodiments of this application, processor 401 is configured to generate an enhanced guidance strategy if the attention index indicates that the attention of the target area is lower than the attention threshold; the guidance strategy includes an enhanced guidance strategy; the enhanced guidance strategy includes one or more of the following: Increase the display weight of the target area; Adjust the position of the target area; Displays recommended content associated with the target area.

[0110] In some embodiments of this application, processor 401 is configured to generate a traffic diversion strategy if a attention index indicates that the attention level of a target area is higher than an attention threshold; the diversion strategy includes a traffic diversion strategy; the traffic diversion strategy includes one or more of the following: Reduce the display weight of the target area; Guide target users to migrate from the target region.

[0111] It is understood that memory 402 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Sync Link Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 402 described in this embodiment of the invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0112] The memory 402 in this embodiment of the invention is used to store various types of data to support the operation of the electronic device 400. Examples of such data include any computer program for operation on the electronic device 400, and programs implementing the methods of this embodiment of the invention may be included in the memory 402.

[0113] The methods disclosed in the above embodiments of the present invention can be applied to processor 401, or implemented by processor 401. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of the present invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in a memory. The processor reads information from the memory and, in conjunction with its hardware, completes the steps of the aforementioned method.

[0114] In an exemplary embodiment, the electronic device 400 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the methods described above.

[0115] This application provides a computer program product, which includes a computer program or computer-executable instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the electronic device to perform the data processing method described in this application.

[0116] This application provides a computer-readable storage medium storing computer-executable instructions or a computer program. When the computer-executable instructions or the computer program are executed by a processor, the processor will execute the data processing method provided in this application. For example, ... Figure 1 The data processing method is shown.

[0117] In some embodiments, the computer-readable storage medium may be a memory such as RAM, ROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0118] In some embodiments, computer-executable instructions may take the form of programs, software, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.

[0119] As an example, computer-executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple co-located files (e.g., files that store one or more modules, subroutines, or code sections).

[0120] As an example, computer-executable instructions can be deployed to execute on a single electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed across multiple locations and interconnected via a communication network.

[0121] In summary, this application acquires behavioral data of multiple users in a target space; determines user distribution information based on the behavioral data; the user distribution information indicates the behavioral distribution of multiple users in different areas of the target space; determines a guidance strategy for the target user based on the user distribution information; the guidance strategy is used to guide the behavioral trajectory of the target user in the target space; the multiple users include the target user; and it is able to dynamically guide the behavioral trajectory of the user within the target space.

[0122] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A data processing method, characterized in that, The method includes: Acquire behavioral data of multiple users in a target space; User distribution information is determined based on the behavioral data; the user distribution information indicates the behavioral distribution of multiple users in different regions of the target space; A guidance strategy for the target user is determined based on the user distribution information; the guidance strategy is used to guide the behavioral trajectory of the target user in the target space; the multiple users include the target user.

2. The method according to claim 1, characterized in that, The method further includes: The service rules for the target space are determined; the service rules indicate the triggering conditions for service information in the target space; the service information includes one or more of the following: product information; video information; route information; The target service for each user is generated based on the behavioral data and the service rules.

3. The method according to claim 2, characterized in that, The method further includes: Obtain feedback information from each user regarding the target service; The service rules are adjusted based on the feedback information.

4. The method according to claim 2, characterized in that, The method further includes: Based on the user distribution information, determine the group behavior patterns of multiple users; Target data is determined from the behavioral data based on the group behavior pattern; the frequency threshold of the target data is greater than a preset threshold; The service rules are adjusted based on the target data.

5. The method according to claim 1, characterized in that, The guidance strategy for determining target users based on the user distribution information includes: The attention index of the target area is determined based on the user distribution information; the target area is the area in the target space that the target user is interested in. The guidance strategy is determined based on the attention index.

6. The method according to claim 5, characterized in that, Determining the guidance strategy based on the attention index includes: If the attention index indicates that the attention level of the target area is lower than the attention threshold, an enhanced guidance strategy is generated; the guidance strategy includes the enhanced guidance strategy; the enhanced guidance strategy includes one or more of the following: Increase the display weight of the target area; Adjust the position of the target area; Displays recommended content associated with the target area.

7. The method according to claim 5, characterized in that, Determining the guidance strategy based on the attention index includes: If the attention index indicates that the attention level of the target area is higher than the attention threshold, a traffic diversion and guidance strategy is generated; the guidance strategy includes the traffic diversion and guidance strategy; the traffic diversion and guidance strategy includes one or more of the following: Reduce the display weight of the target area; Guide the target user to move away from the target area.

8. An electronic device, characterized in that, include: The processor and the memory used to store computer programs that can run on the processor. When the processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 7.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images