User intelligent analysis method and device based on multi-source data and electronic equipment

Abstract

The application discloses a user intelligent analysis method and device based on multi-source data and electronic equipment, and relates to the field of user analysis.The user intelligent analysis method comprises the following steps: step 1, deploying an image acquisition component and an information delivery component, and registering authorized interaction point data; step 2, obtaining a quantitative processing of the attention state of a certain user in an image acquisition area to the delivered information, and obtaining an attention coefficient of the user to the delivered information; step 3, calling historical interaction data of the user from a database, analyzing the past consumption behavior, preference of viewing the delivered information and interactive behavior of browsing the interaction point of the user, and obtaining a historical behavior coefficient; through obtaining and analyzing real-time data fused by image acquisition, user historical behavior data and group preference data, and recommending, recommended content more in line with the instant needs of the user is generated, the comprehensiveness and accuracy of the recommendation are improved in a multi-source data fusion manner, and the recommended result is more personalized and intelligent.

Description

Technical Field

[0001] This invention relates to the field of user analytics technology, specifically to user intelligent analytics methods, devices, and electronic equipment based on multi-source data. Background Technology

[0002] In the era of big data, using big data technology for intelligent user analysis has become the choice of various industries. Intelligent user analysis is also one of the most important application scenarios in the field of artificial intelligence. The analysis results are a visual representation of user data, which concisely and vividly describes a user's characteristics with a series of user information. Therefore, only by fully and accurately exploring user needs and correctly grasping the direction of iteration can businesses fully demonstrate their vitality and competitiveness.

[0003] However, existing user intelligence analysis solutions still have room for improvement in certain scenarios, such as:

[0004] 1. Traditional user-based intelligent analysis mainly relies on users' historical behavior data and lacks measures to capture users' current interests in real time. This may result in recommended content that does not match users' immediate needs. Furthermore, data from a single source is difficult to cope with the dynamic changes in users' interests and cannot integrate multiple data sources. As a result, the recommendation results are usually a simple continuation of past behaviors and lack innovation.

[0005] 2. The feedback mechanism of intelligent analysis is not flexible enough, making it difficult to respond to changes in users' actual operations and preferences in a timely manner. It is easy to repeatedly push information that users have already interacted with or are not interested in, resulting in a decline in user experience and obvious information redundancy. Summary of the Invention

[0006] (a) Technical problems to be solved

[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides a user intelligent analysis method, device and electronic device based on multi-source data, which can effectively solve the problems of the prior art.

[0008] (II) Technical Solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0010] This invention discloses a user intelligent analysis method based on multi-source data, comprising the following steps:

[0011] Step 1: Deploy image acquisition components and information delivery components, and register authorized interaction point data;

[0012] Step 2: Quantify the attention status of a user in the image acquisition area to the delivered information, and obtain the user's attention coefficient to the delivered information;

[0013] Step 3: Retrieve users' historical interaction data from the database, analyze users' past consumption behavior, preferences for viewing and receiving information, and interaction behavior at browsing points, and obtain historical behavior coefficients;

[0014] Step 4: Obtain historical interaction data of all user groups within the current image acquisition area, and calculate the group interaction preference trend coefficient through big data analysis;

[0015] Step 5: Using the group interaction trend coefficient as a reference for weighting several interaction points, comprehensively analyze the user's historical behavior coefficient, attention coefficient to the current information, and group interaction preference trend coefficient to output recommendation tags. The interaction points corresponding to the recommendation tags and users will then conduct two-way information push.

[0016] Step 6: Analyze the user's interaction operations and results in the current cycle in real time, and eliminate similar interaction points that have been completed.

[0017] Furthermore, in the quantification process of step 2, eye tracking and facial expression technology are combined to analyze whether the user is paying attention to a certain information. After confirming that the user is paying attention to a certain information, it is determined whether the dwell time reaches or exceeds a preset threshold. If the determination is yes, the result is used as a quantification reference.

[0018] Furthermore, in step 4, if there is no newly added interaction point information in the historical interaction data of the user group, historical information of similar interaction points is collected through the Internet, several samples are extracted and predicted through deep learning algorithms, and the predicted data is used as the group interaction preference trend coefficient of the newly added interaction point.

[0019] Furthermore, in step 5, during the two-way information push between the interaction point corresponding to the recommendation tag and the user, if either party refuses to push, the push will be stopped, and the push between the user and the interaction point with the same attribute or the interaction point with the user with the same attribute will be removed in the current cycle, and will be reset in the next cycle.

[0020] Furthermore, in step 6, during the real-time analysis of the user's interaction operations and results in the current period, the weight ratio of the user's behavior coefficient and the attention coefficient of the delivered information is adjusted through data feedback from the interaction points and image acquisition devices, and the recommendation tags are re-output in a preset period.

[0021] Furthermore, in step 6, during the process of removing similar interaction points that have already been completed, if it is detected that a user has completed the target operation of a certain interaction point, then that interaction point and interaction points whose similarity meets the preset threshold will be removed from the recommendation pool for the current period.

[0022] A user-intelligent analysis device based on multi-source data includes:

[0023] The management module is used to control the start and stop of each functional module and to issue control permissions.

[0024] The data storage terminal is used for cloud storage of collected and analyzed data, and supports reading from local storage media;

[0025] The image acquisition module is used to acquire surveillance images and display information in a specified area, and convert the acquired images into character data.

[0026] The attention analysis module is used to analyze image character data and obtain the attention coefficient of the target user for one or more interaction points;

[0027] The historical behavior analysis module is used to analyze users' past purchase records, content preferences, and interaction point usage records, calculate users' individual preferences, and output historical behavior coefficients;

[0028] The group trend analysis module is used to analyze the historical data of all users in the current area to obtain the actual group preference trend. For newly added interaction points, it collects Internet data and uses deep learning algorithms to obtain the predicted group preference trend. The actual group preference trend and the predicted group preference trend are analyzed together, and each interaction point is assigned a corresponding weight to output the final group preference trend.

[0029] The tag generation module is used to comprehensively analyze users' historical behavior coefficients, current attention coefficients, and group interaction preference trend coefficients to generate recommendation tags.

[0030] The push module is used to push information bidirectionally based on tag content. If the user or interaction point rejects the push during the push process, the combination will be excluded in the current period and reset in the next period.

[0031] The dynamic adjustment module analyzes the user's current actions and results, adjusts the coefficients dynamically, and regenerates recommendation tags at the end of each cycle, removing interaction points that have been completed and their similar interaction points.

[0032] Furthermore, the management module is interconnected with the data storage terminal, the image acquisition module, and the dynamic adjustment module via a wireless network; the image acquisition module is interconnected with the attention analysis module via a wireless network; the dynamic adjustment module is interconnected with the attention analysis module and the historical behavior analysis module via a wireless network; and the tag generation module is interconnected with the attention analysis module, the historical behavior analysis module, the group trend analysis module, and the push module via a wireless network.

[0033] An electronic device includes: one or more processors; a memory for storing one or more computer-executable instructions; when the one or more computer-executable instructions are executed by the one or more processors, the one or more processors implement a user intelligent analysis method based on multi-source data.

[0034] A computer-readable storage medium, wherein computer-executable instructions, when executed by a processor, implement a user-intelligent analysis method based on multi-source data.

[0035] (III) Beneficial Effects

[0036] Compared with known prior art, the technical solution provided by this invention has the following beneficial effects:

[0037] 1. By acquiring and analyzing real-time data from fused image acquisition, user historical behavior data, and group preference data, we can make recommendations. We can quantify the user's current interest status in real time and obtain the user's real-time attention to the information being delivered. This will generate recommended content that better meets the user's immediate needs. By combining the user's historical behavior, current attention, and group trends, we can analyze changes in the user's interests from multiple dimensions, improving the comprehensiveness and accuracy of recommendations. The multi-source data fusion method improves the comprehensiveness and accuracy of recommendations, making the recommendation results more personalized and intelligent.

[0038] 2. By analyzing user interaction results in real time, completed or irrelevant interaction points and similar items can be eliminated to avoid duplicate push notifications. When a party refuses to push, the push notification for the current period will be automatically stopped, thereby optimizing the user's push notification experience.

[0039] 3. Through real-time feedback from image acquisition devices and interaction points, the recommendation strategy can be dynamically adjusted. Based on the user's immediate behavior and interaction results, the recommendation tags can be adjusted in a timely manner, so that the user's latest interests are quickly reflected in the recommended content.

[0040] 4. By using big data analysis to obtain user group interaction preferences, and based on newly added interaction points, deep learning algorithms are used to predict the group's preference trend coefficients, making the analysis solution highly adaptable to new data points. This allows it to consider individual historical behavior while also making comprehensive recommendations based on group trends, making it particularly suitable for personalized recommendation needs in public scenarios. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0042] Figure 1 This is a flowchart illustrating the user intelligent analysis method based on multi-source data in this invention.

[0043] Figure 2 This is a schematic diagram of the framework of the user intelligent analysis device based on multi-source data in this invention;

[0044] Figure 3 This is a schematic diagram of the architecture of the user intelligent analysis method based on multi-source data in this invention.

[0045] The numbers in the diagram represent: 1. Management module; 2. Data storage terminal; 3. Image acquisition module; 4. Attention analysis module; 5. Historical behavior analysis module; 6. Group trend analysis module; 7. Tag generation module; 8. Push module; 9. Dynamic adjustment module. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0047] The present invention will be further described below with reference to embodiments.

[0048] Example

[0049] The user intelligent analysis method based on multi-source data in this embodiment, such as Figure 1 and Figure 3 As shown, it includes the following steps:

[0050] Step 1: Deploy image acquisition components (such as cameras) and information delivery components (such as displays and smart billboards), and register authorized interaction point data;

[0051] Step 2: Quantify the attention status of a user in the image acquisition area to the delivered information, and obtain the user's attention coefficient to the delivered information;

[0052] During the quantification process, eye tracking and facial expression technology are combined to analyze whether a user is paying attention to a certain information. After confirming that the user is paying attention to a certain information, it is determined whether the dwell time reaches or exceeds a preset threshold. If the determination is yes, the result is used as a quantification reference. It can acquire interaction behavior data in real time and provide basic data support for subsequent analysis, accurately identify the user's attention to specific information, and provide a basis for personalized recommendations.

[0053] Step 3: Retrieve users' historical interaction data from the database, analyze users' past consumption behavior, preferences for viewing and receiving information, and interaction behavior at browsing points, and obtain historical behavior coefficients; improve the accuracy and effectiveness of the recommendation system based on in-depth analysis of users' historical behavior;

[0054] Step 4: Obtain historical interaction data of all user groups within the current image acquisition area, and calculate the group interaction preference trend coefficient through big data analysis;

[0055] If no new interaction points are found in the historical interaction data of the user group, historical information on similar interaction points is collected from the Internet, and several samples are extracted and predicted using deep learning algorithms. The predicted data is used as the group interaction preference trend coefficient for the newly added interaction points. This determines the group preferences and optimizes the collective recommendation strategy. Even when faced with new interaction points, it can provide preliminary predictive support and avoid the problem of data sparsity.

[0056] Step 5: Using the group interaction trend coefficient as a reference for weighting several interaction points, the user's historical behavior coefficient, attention coefficient to the current information, and group interaction preference trend coefficient are comprehensively analyzed to output recommendation tags. The interaction points corresponding to the recommendation tags and users conduct two-way information push; this improves the accuracy and personalization of recommendations and enhances the user experience.

[0057] During the two-way information push between the interaction points corresponding to the recommendation tags and users, if either party refuses to push, the push will be stopped. In the current cycle, pushes for that user and interaction points with similar attributes or pushes for that interaction point and users with similar attributes will be removed, and the system will be reset in the next cycle. This flexibly adapts to changes in user needs, prevents user aversion, and improves system friendliness.

[0058] Step 6: Analyze the user's interaction operations and results in real time. During the real-time analysis of the user's interaction operations and results in the current period, adjust the weight ratio of the user's behavior coefficient and the attention coefficient of the delivered information through data feedback from interaction points and image acquisition devices, and re-output recommendation tags in a preset period; improve the dynamism and adaptability of the recommendation system, so that the recommended content always matches the user's current interests;

[0059] If a user has already completed a certain interaction point, and similar interaction points that meet the preset similarity threshold are detected during the process of removing similar interaction points that have already completed the target operation of a certain interaction point, then that interaction point and interaction points whose similarity meets the preset threshold will be removed from the recommendation pool of the current period. This avoids redundant recommendations and improves the efficiency of pushing effective information and user satisfaction.

[0060] Compared with existing technologies, it can improve user experience in multiple dimensions, including accurately capturing user interests, dynamically adjusting recommendations, integrating group preferences and individual behaviors, and reducing redundant information pushes. It effectively solves the problems of inaccurate interest capture, single data, and delayed feedback in traditional user intelligent analysis and recommendation schemes.

[0061] At other levels, this embodiment also provides a user intelligent analysis device based on multi-source data, such as... Figure 2 As shown, it includes:

[0062] Management module 1 is used to control the start and stop of each functional module and to issue control permissions;

[0063] Data storage terminal 2 is used for cloud storage of collected and analyzed data, and supports reading from local storage media;

[0064] Image acquisition module 3 is used to acquire surveillance images and project information in a designated area, and convert the acquired images into character data;

[0065] Attention analysis module 4 is used to analyze image character data and obtain the attention coefficient of the target user for one or more interaction points;

[0066] Module 5, the historical behavior analysis module, is used to analyze users’ past purchase records, content preferences and usage records of interaction points, calculate users’ individual preferences, and output historical behavior coefficients.

[0067] The group trend analysis module 6 is used to analyze the historical data of all users in the current area to obtain the actual group preference trend. For newly added interaction points, it collects Internet data and uses deep learning algorithms to obtain the predicted group preference trend. It combines the actual group preference trend and the predicted group preference trend for analysis, assigns corresponding weights to each interaction point, and outputs the final group preference trend.

[0068] The tag generation module 7 is used to comprehensively analyze users' historical behavior coefficients, current attention coefficients, and group interaction preference trend coefficients to generate recommended tags.

[0069] Push module 8 is used to push information bidirectionally based on tag content. If the user or interaction point rejects the push during the push process, the combination will be excluded in the current cycle and reset in the next cycle.

[0070] The dynamic adjustment module 9 is used to analyze the user's current operation and results, and make dynamic coefficient adjustments. At the end of each cycle, it regenerates recommendation tags and removes interaction points that have been completed and their similar interaction points.

[0071] As a preferred embodiment of this example, Figure 2 As shown, the management module 1 is interconnected with the data storage terminal 2, the image acquisition module 3, and the dynamic adjustment module 9 via a wireless network. The image acquisition module 3 is interconnected with the attention analysis module 4 via a wireless network. The dynamic adjustment module 9 is interconnected with the attention analysis module 4 and the historical behavior analysis module 5 via a wireless network. The tag generation module 7 is interconnected with the attention analysis module 4, the historical behavior analysis module 5, the group trend analysis module 6, and the push module 8 via a wireless network.

[0072] In this implementation, after the user intelligent analysis device based on multi-source data is installed, the administrator registers the authorized interaction points through the management module 1 and sends control commands to each module. The data storage terminal 2 records the current analysis and collection data in real time and stores it in the cloud. The image acquisition module 3 obtains the user's viewing status of the information, which is quantified into a specific attention coefficient by the attention analysis module 4. The historical behavior analysis module 5 identifies the user's historical behavior data, and the group trend analysis module 6 obtains the group preference trend coefficient of the current area. After comprehensive analysis, the tag generation module 7 generates recommended tags that are suitable for the user, and the push module 8 conducts two-way information push between the interaction points and the user. The dynamic adjustment module 9 removes the interaction points that have completed the interaction operation and their similar interaction points in real time within a preset period.

[0073] As a preferred embodiment of this invention, an electronic device is provided, comprising: one or more processors; and a memory for storing one or more computer-executed instructions; wherein when the one or more computer-executed instructions are executed by the one or more processors, the one or more processors implement a user intelligent analysis method based on multi-source data.

[0074] This embodiment also provides a computer-readable storage medium that enables a user-intelligent analysis method based on multi-source data when computer execution instructions are executed by a processor.

[0075] In summary, this invention quantifies the user's current interest status in real time, obtains the user's real-time attention to the information being delivered, and thus generates recommended content that better meets the user's immediate needs. By combining the user's historical behavior, current attention, and group trends, this invention can analyze changes in the user's interests from multiple dimensions, thereby improving the comprehensiveness and accuracy of recommendations.

[0076] Based on users' real-time behavior and interaction results, the recommendation tags are adjusted in a timely manner to ensure that users' latest interests are quickly reflected in the recommended content. The interaction preferences of user groups are obtained through big data analysis, especially for newly added interaction points. The group's preference trend coefficient is predicted through deep learning algorithms. It can not only take into account individual historical behavior, but also make comprehensive recommendations based on group trends, which is suitable for personalized recommendation needs in public scenarios.

[0077] By analyzing user interaction results in real time, this invention can eliminate completed or irrelevant interaction points and similar items, thus avoiding duplicate push notifications. At the same time, when a party refuses to push, this invention can automatically stop the push notifications in the current cycle, thereby optimizing the user's push notification experience.

[0078] Finally, this invention improves the comprehensiveness and accuracy of recommendations by fusing multi-source data, making the recommendations more personalized and intelligent.

[0079] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A user intelligent analysis method based on multi-source data, characterized in that, Includes the following steps: Step 1: Deploy image acquisition components and information delivery components, and register authorized interaction point data; Step 2: Quantify the attention status of a user in the image acquisition area to the delivered information, and obtain the user's attention coefficient to the delivered information; In the quantification process of step 2, eye tracking and facial expression technology are combined to analyze whether the user is paying attention to a certain information. After confirming that the user is paying attention to a certain information, it is determined whether the dwell time reaches or exceeds a preset threshold. If the determination is yes, the result of the user's attention dwell time reaching or exceeding the preset threshold is used as the user's quantification reference for the certain information. Step 3: Retrieve users' historical interaction data from the database, analyze users' past consumption behavior, preferences for viewing and receiving information, and interaction behavior at browsing points, and obtain historical behavior coefficients; Step 4: Obtain historical interaction data of all user groups within the current image acquisition area, and calculate the group interaction preference trend coefficient through big data analysis; Step 5: Using the group interaction trend coefficient as a reference for weighting several interaction points, comprehensively analyze the user's historical behavior coefficient, attention coefficient to the current information, and group interaction preference trend coefficient to output recommendation tags. The interaction points corresponding to the recommendation tags and users will then conduct two-way information push. In step 5, during the two-way information push between the interaction point corresponding to the recommendation tag and the user, if either party refuses to push, the push will be stopped, and the push between the user and the interaction point with the same attribute or the interaction point and the user with the same attribute will be removed in the current cycle. In the next cycle, it will be reset. Step 6: Analyze the user's interaction operations and results in the current cycle in real time, and eliminate similar interaction points that have been completed; In step 6, during the real-time analysis of the user's interaction operations and results in the current period, the weight ratio of the user's behavior coefficient and the attention coefficient of the delivered information is adjusted through data feedback from the interaction points and image acquisition devices, and the recommendation tags are re-output in a preset period.

2. The user intelligent analysis method based on multi-source data according to claim 1, characterized in that, If no new interaction point information is found in the historical interaction data of the user group in step 4, then historical information of similar interaction points is collected through the Internet, several samples are extracted and predicted using a deep learning algorithm, and the predicted data is used as the group interaction preference trend coefficient of the newly added interaction point.

3. The user intelligent analysis method based on multi-source data according to claim 1, characterized in that, In step 6, during the process of removing similar interaction points that have already been completed, if it is detected that a user has completed the target operation of a certain interaction point, then that interaction point and interaction points whose similarity meets the preset threshold will be removed from the recommendation pool for the current period.

4. A user intelligent analysis device based on multi-source data, the device being used to implement the user intelligent analysis method based on multi-source data as described in any one of claims 1-3, characterized in that, include: The management module (1) is used to control the start and stop of each functional module and to issue control permissions. Data storage terminal (2) is used to store the collected and analyzed data in the cloud and supports reading the local storage medium; The image acquisition module (3) is used to acquire monitoring images and project information in a specified area, and convert the acquired images into character data; The attention analysis module (4) is used to analyze image character data and obtain the attention coefficient of the target user to one or more interaction points; The historical behavior analysis module (5) is used to analyze the user's past purchase records, content preferences and interaction point usage records, calculate the user's individual preferences, and output historical behavior coefficients; The group trend analysis module (6) is used to analyze all historical data of users in the current area to obtain the actual group preference trend. For newly added interaction points, the module collects Internet data and uses deep learning algorithms to obtain the predicted group preference trend. The actual group preference trend and the predicted group preference trend are analyzed together. Each interaction point is assigned a corresponding weight and the final group preference trend is output. The tag generation module (7) is used to comprehensively analyze the user's historical behavior coefficient, current attention coefficient and group interaction preference trend coefficient to generate recommendation tags; The push module (8) is used to push bidirectionally based on the tag content. During the push process, if the user or interaction point refuses to push, the combination will be excluded in the current period and reset in the next period. The dynamic adjustment module (9) is used to analyze the user's current operation and results, and make dynamic coefficient adjustments. At the end of each cycle, the recommendation tags are regenerated and the interaction points that have been completed and their similar interaction points are removed.

5. The user intelligent analysis device based on multi-source data according to claim 4, characterized in that, The management module (1) is connected to the data storage terminal (2), the image acquisition module (3) and the dynamic adjustment module (9) via a wireless network. The image acquisition module (3) is connected to the attention analysis module (4) via a wireless network. The dynamic adjustment module (9) is connected to the attention analysis module (4) and the historical behavior analysis module (5) via a wireless network. The tag generation module (7) is connected to the attention analysis module (4), the historical behavior analysis module (5), the group trend analysis module (6) and the push module (8) via a wireless network.

6. An electronic device, characterized in that, include: One or more processors; Memory is used to store one or more instructions that a computer can execute. When the one or more computer execution instructions are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-3.

7. A computer-readable storage medium storing computer-executable instructions, characterized in that, When the computer execution instructions are executed by the processor, the method as described in any one of claims 1-3 is implemented.

Images