Targeted short message reaching method based on dynamic position tracking and crowd density analysis

Through dynamic location tracking and crowd density analysis, hot spots are identified and SMS sending priority is adjusted, which solves the problems of low accuracy of static location data and uneven resource allocation, and achieves efficient and accurate SMS reach, improving marketing effects and User experience.

CN119052736AActive Publication Date: 2024-11-29CHANGSHA DILU DIGITAL TECH

Patent Information

Application Number
CN202411500959.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-25
Publication Date
2024-11-29
Estimated Expiration
2044-10-25

AI Technical Summary

Technical Problem

The existing targeted SMS reach methods rely on static location data and cannot reflect user movement in real time, resulting in reduced accuracy and ignoring the differences in population density, resulting in uneven resource allocation and affecting marketing effects and user experience.

Method used

Dynamic location tracking algorithm is used to combine machine learning and GIS technology to monitor the movement trajectory of the crowd in real time, and identify hot spots through the crowd density priority allocation algorithm, automatically adjust the priority of SMS sending, integrate it into the intelligent SMS reach platform, and optimize the sending strategy.

Benefits of technology

It improves the accuracy and timeliness of SMS delivery, optimizes resource usage efficiency, enhances marketing effects and user experience, and reduces economic losses and brand image risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119052736A_ABST
    Figure CN119052736A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of data processing, and provides a targeted short message reaching method based on dynamic position tracking and crowd density analysis. The method comprises the steps of obtaining a dynamic position and crowd density information of a target area, and cleaning and preprocessing data; a dynamic position accurate tracking algorithm is combined with machine learning and a GIS technology to accurately position a crowd track; using a crowd density priority distribution algorithm to identify a hot spot area, and automatically distributing a short message sending priority; the algorithm is integrated to a short message sending system, an intelligent platform is formed, and a sending strategy is optimized. According to the invention, a real-time dynamic position tracking algorithm, GPS and signal tower information are combined, crowd distribution is measured, moving features are identified, and population types are distinguished. And the short message can be accurately sent by updating the data. Meanwhile, a density analysis algorithm and a big data technology are adopted, the regional density is calculated in real time, the short message priority is intelligently allocated, a sending strategy is dynamically adjusted, and the resource use efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a targeted SMS reaching method based on dynamic location tracking and crowd density analysis. Background Art

[0002] In today's era of information explosion, precision marketing and efficient notifications have become one of the key elements of business success. However, although the existing targeted SMS contact methods have met the basic needs of the market to a certain extent, their inherent limitations cannot be ignored. In particular, the application of static location tracking technology has become a bottleneck restricting its further development.

[0003] First, let's take a closer look at the limitations of static location tracking through examples. Most existing targeted SMS reach methods rely on users' static location data, which is often obtained once when users register or fill in information, and cannot reflect users' movements in real time. With the increasingly fast-paced and mobile lives of people, users' actual locations are changing almost every moment. This means that when a company sends text messages based on these static data, the target population may have left their original location, resulting in a significant reduction in the accuracy of the text message reach. This "time has passed" phenomenon not only affects the effective communication of marketing information, but may also cause users to be disgusted with the frequent receipt of irrelevant information, thereby damaging the company's brand image.

[0004] To illustrate this more intuitively, the embodiment can cite some statistical data. According to a report released by a well-known market research organization, due to the limitations of static location tracking, about 30% of targeted text messages are no longer in the preset area when the target group is sent, and this proportion is as high as more than 50% during holidays or special events. This lack of accuracy has undoubtedly brought huge economic losses and brand image risks to enterprises.

[0005] In addition, the traditional SMS sending method has another significant drawback - ignoring the difference in population density. When formulating SMS sending strategies, many companies do not consider the actual population density in the target area, but send them according to a fixed ratio or quantity. Although this approach simplifies the operation process, it brings serious problems of uneven resource allocation. In high-density areas, due to dense populations and fierce competition, a large number of SMS messages may cause users' mobile phones to be frequently disturbed, or even SMS overload; while in low-density areas, due to sparse populations and low attention, SMS sending may be regarded as a waste of resources and it is difficult to achieve the expected marketing effect. This phenomenon not only reduces the overall sending efficiency, but also seriously affects the user experience.

[0006] In order to overcome these limitations, the embodiments need to seek more advanced and accurate SMS reach methods. On the one hand, advanced positioning technology and big data analysis methods can be used to track the user's movement trajectory and location changes in real time to ensure accurate SMS reach; on the other hand, the SMS sending strategy and frequency can be flexibly adjusted according to the actual population density in the target area to achieve reasonable allocation and efficient use of resources. Only in this way can the embodiments stand out in this fiercely competitive market and win more user trust and market share. Summary of the invention

[0007] In view of the deficiencies in the prior art, the present invention discloses a targeted SMS reaching method based on dynamic location tracking and crowd density analysis, which is used to solve the above problems.

[0008] The present invention is achieved through the following technical solutions: The present invention provides a targeted SMS reaching method based on dynamic location tracking and crowd density analysis, comprising the following steps: Obtain dynamic location and crowd density information data of the target area through the data interface, clean and pre-process the data to ensure that the data is accurate and real-time; Based on dynamic location data, we use dynamic location precision tracking algorithms, combined with machine learning and GIS technology, to accurately locate the movement trajectory and stay location of people; Use crowd density priority allocation algorithm to identify hot spots and automatically assign SMS sending priorities based on the analysis results; Integrate location tracking and density analysis algorithms into the SMS sending system to form an intelligent SMS reach platform, optimize SMS sending strategies, and improve marketing or notification effects.

[0009] Furthermore, in the method, a density-based local outlier factor (LOF) algorithm is used to identify and clean noise data of dynamic location data and crowd density information in the target area.

[0010] Furthermore, in the method, the LOF outlier detection algorithm executes time, the K-means algorithm is upgraded, and the time dimension T is added to the algorithm, so that the K-means algorithm can classify the signaling data with time and space attributes, and the K-means clustering algorithm with the time dimension is used to select a set of trajectory sequence points of a certain user sorted in ascending order based on time; Define the intra-cluster distance D pt It is the sum of the absolute values ​​of the distance of the center point u in the p distance cluster and the difference between the time dimension Tp of p and the time dimension Tu of the center point u, as shown in the formula: In the formula It is a balance parameter for adjusting distance and time difference.

[0011] Furthermore, in the method, the dynamic position precision tracking algorithm is specifically: in is the state prediction vector at time k including position and velocity; is the state transfer matrix, which is used to predict the next position of the target; is the input control vector; is the control input matrix, is the process noise; State update equation: is the Kalman gain matrix, is the observation vector; is the observation matrix.

[0012] Furthermore, the method mentioned above adopts a dynamic location precision tracking algorithm, which is based on the dynamic location data of mobile devices, combined with multi-source data of GPS and signal tower positioning, to achieve real-time monitoring of the movement trajectory of people in the target area. In addition, the method uses Kalman filtering technology to predict and correct dynamic location data to ensure the accuracy and real-time tracking.

[0013] Furthermore, in this method, the crowd density priority allocation algorithm clearly distinguishes high-density areas from low-density areas by collecting crowd density information at various locations in the target area. In the process of calculating the allocation priority, the algorithm uses the utility function to optimize resource allocation, ensuring that resources are first tilted towards high-density areas, thereby maximizing utility.

[0014] Furthermore, in the method, the crowd density is calculated as: is the crowd density at position (x,y) at time t; N(x,y,t) is the number of people at position (x,y) at time t, and A is the unit area.

[0015] Furthermore, in the method, the priority allocation model uses a utility function U to measure the priority of resource allocation: in is the priority utility value of position (x, y) at time t; and is a weight factor used to adjust the impact of crowd density and distance on priority; It is the distance function from the position (x,y) to the center of the hotspot.

[0016] Furthermore, in the method, data preprocessing involves eliminating noise data, processing outliers and implementing data standardization; by applying positioning technologies such as GPS, Wi-Fi, and Bluetooth, the real-time location of users in a specified area can be tracked.

[0017] Furthermore, in the method, after the text message is sent, the system collects and analyzes user feedback data to evaluate the effectiveness of the text message reach, and automatically adjusts the strategy parameters based on the evaluation results to continuously optimize the effectiveness and efficiency of the text message reach.

[0018] The beneficial effects of the present invention are: The present invention uses a real-time dynamic location tracking algorithm, combined with the global positioning system (GPS) data of mobile devices and signal tower positioning information, to accurately determine the distribution of people in the target area. The algorithm has the ability to identify parameters such as movement speed, path selection, and length of stay, and can distinguish between permanent residents and floating population, thereby accurately identifying the target population. By continuously updating the location data, it ensures that the location information of the crowd is kept up to date when sending text messages, thereby improving the accuracy and timeliness of text message delivery.

[0019] The present invention also introduces a crowd density analysis algorithm and combines it with big data technology to calculate and determine high-density and low-density areas in the target area in real time. Based on the identification results of crowd density and hot spots, the priority of SMS sending is intelligently allocated to ensure that residents in high-density areas receive information first. In addition, the system can dynamically adjust the SMS sending strategy according to density changes, optimize the efficiency of SMS resource use, and enhance the effectiveness of SMS delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 This is a schematic diagram of the steps of a targeted SMS reaching method based on dynamic location tracking and crowd density analysis. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In one embodiment, referring to Figure 1 As shown, a targeted SMS reaching method based on dynamic location tracking and crowd density analysis is provided, including the following steps: Obtain dynamic location and crowd density information data of the target area through the data interface, clean and pre-process the data to ensure that the data is accurate and real-time; Based on dynamic location data, we use dynamic location precision tracking algorithms, combined with machine learning and GIS technology, to accurately locate the movement trajectory and stay location of people; Use crowd density priority allocation algorithm to identify hot spots and automatically assign SMS sending priorities based on the analysis results; Integrate location tracking and density analysis algorithms into the SMS sending system to form an intelligent SMS reach platform, optimize SMS sending strategies, and improve marketing or notification effects.

[0024] In one embodiment, in today's era of information explosion, data collection and preprocessing are not only the cornerstone of data analysis, but also the key link to achieve precision marketing, efficient management and emergency response. Through the powerful data interface of mobile operators, the embodiment can have insight into the dynamic location data and crowd density information in the target area like having a perspective eye. This process is like fishing for precious pearls in a vast ocean of data, and every step needs to be cautious and meticulous.

[0025] Data cleaning and preprocessing, the implementation example uses advanced algorithms and technologies to strictly screen each piece of data to ensure that the data input into the system is like carefully selected pearls, crystal clear and impeccable. In addition, the conversion of location coordinates is also a crucial step, which can make the seemingly chaotic data points present a clear and orderly trajectory on the map. The calculation of crowd density is to scientifically evaluate the distribution of people in the target area through precise mathematical models and big data analysis technology, providing strong support for subsequent decision-making.

[0026] The development and application of dynamic location tracking algorithms have pushed this process to a new level. Based on the collected dynamic location data, the embodiment uses the power of machine learning and geographic information system (GIS) technology to develop a real-time location tracking algorithm. Through dynamic updates and continuous optimization of the algorithm, the embodiment ensures that the system can keep up with the times, track the location changes of the target population in real time, and provide more timely and accurate information support for subsequent decision-making.

[0027] Crowd density analysis and priority allocation are important means for the embodiment to achieve precision marketing and efficient management. The embodiment can accurately identify hot spots and potential high-value people by performing in-depth calculations and detailed analysis of the crowd density at different locations in the target area. Based on these analysis results, the system of the embodiment will automatically assign SMS sending priorities to ensure that people in high-density areas can receive important information first. This intelligent priority allocation mechanism not only improves the efficiency and accuracy of information reach, but also greatly improves user experience and satisfaction.

[0028] Finally, the embodiment seamlessly integrates dynamic location tracking and crowd density analysis algorithms into the SMS sending system, forming a powerful and easy-to-use intelligent SMS reach platform. This platform can intelligently optimize SMS sending strategies based on real-time location and density data to achieve accurate and efficient targeted SMS reach. Whether it is marketing promotion or emergency notification, the embodiment can quickly and accurately deliver information to the target group, thereby greatly improving the effectiveness and influence of marketing or notification.

[0029] In this embodiment, due to factors such as deviation or random errors, the data set may be filled with a large amount of noise data. These noise data have a significant interference and impact on the coherence of the user's trajectory, and traditional cleaning methods are not ideal in dealing with such problems. The outlier detection algorithm performs well in identifying noise data, so it is worth considering using the outlier detection algorithm to detect and clean noise data.

[0030] This embodiment selects the density-based LOF (Local Outlier Factor) outlier detection algorithm to identify and clean such noise data. In practical applications, the density-based LOF algorithm performs well and has strong adaptability. However, when executing the LOF algorithm, the time complexity of the algorithm reaches the square level because of the need to calculate the distance between each data point and other data points. In view of the large amount of signaling data, the execution time of the algorithm may be too long, so the detection process needs to be optimized urgently.

[0031] In order to use the traditional clustering algorithm to pre-detect data and reduce the data size, thereby shortening the execution time of the subsequent LOF outlier detection algorithm, this embodiment needs to improve the K-means algorithm so that it can process signaling data with a time dimension. The time dimension T is introduced into the clustering-based outlier detection algorithm, so that the improved K-means algorithm can effectively classify signaling data with spatiotemporal attributes. By using the K-means clustering algorithm with the introduction of the time dimension, a set of trajectory sequence points of a user sorted in ascending order based on time is selected to ensure that the points in the cluster are continuous in time, and each cluster contains data points with maximum and minimum timestamps.

[0032] In this embodiment, the intra-cluster distance D is defined pt It is the sum of the absolute values ​​of the distance of the center point u in the p distance cluster and the difference between the time dimension Tp of p and the time dimension Tu of the center point u, as shown in the formula.

[0033] In the formula It is a balance parameter for adjusting distance and time difference to avoid the time difference having a greater impact on the final result or having no effect.

[0034] The dynamic location precision tracking algorithm (DLPTA) involved in this embodiment can realize the accurate crowd positioning function. The algorithm relies on the dynamic location data generated by mobile devices and uses multiple data sources such as the global positioning system (GPS) and signal tower positioning to monitor the movement trajectory of people in the target area in real time.

[0035] The core of DLPTA in this embodiment is to apply Kalman filtering technology to predict and correct dynamic position data to ensure the accuracy of tracking and real-time response. By analyzing parameters such as speed, acceleration, and dwell time, DLPTA can distinguish between permanent and floating populations, thereby providing more accurate crowd positioning services.

[0036] in is the state prediction vector (including position, speed, etc.) at time k. is the state transfer matrix (used to predict the next target position), is the input control vector (such as movement acceleration, etc.). is the control input matrix, is the process noise.

[0037] The state update equation of this embodiment is: is the Kalman gain matrix, is the observation vector (eg GPS data). is the observation matrix.

[0038] In this embodiment, the crowd density priority allocation algorithm (CDPA) adopts an intelligent priority allocation mechanism. CDPA clearly distinguishes high-density areas from low-density areas by collecting crowd density information (such as the number of devices per unit area) at each location in the target area. In the process of determining the priority, the algorithm introduces a utility function to optimize resource allocation and ensure that SMS messages are sent to high-density areas first, thereby maximizing utility.

[0039] Crowd density calculation: is the crowd density at position (x,y) at time t. N(x,y,t) is the number of people at position (x,y) at time t, and A is the unit area.

[0040] Priority allocation model: Use the utility function U to measure the priority of resource allocation: in is the priority utility value of position (x, y) at time t. and is a weighting factor used to adjust the impact of crowd density and distance on priority. It is the distance function from the position (x,y) to the center of the hotspot.

[0041] In today's information age, data preprocessing has become the cornerstone of data analysis and decision-making. The data preprocessing process mentioned in this embodiment is not limited to simple data cleaning, but covers multiple key links such as deep removal of noise data, fine processing of outliers, and implementation of strict data standardization. This process is like panning for gold in the vast ocean of data. Through careful screening and polishing, we ensure that every piece of data can accurately reflect the true face of the real world.

[0042] In this example, we use advanced algorithms and models to deeply analyze the collected raw data, accurately identify and remove noise data caused by equipment failure, human error or environmental factors. This process is like a precise microscope, helping us reveal the truth behind the data and ensure the accuracy of the analysis results.

[0043] This embodiment uses a combination of statistical methods and machine learning technology to finely process outliers. For outliers that are obviously deviated from the normal range, we make necessary corrections or elimination; and for outliers that may have special significance, we conduct in-depth mining and analysis in order to discover the valuable information contained therein.

[0044] Data standardization is an indispensable step in data preprocessing. It converts data into a unified measurement scale, eliminates the dimensional differences between different data sources, and enables effective comparison and analysis of data. In this embodiment, we have developed a scientific and reasonable standardization scheme based on the actual distribution of data and business needs to ensure the comparability and consistency of data.

[0045] After completing the data preprocessing, we used GPS, Wi-Fi, Bluetooth and other positioning technologies to build an efficient and accurate real-time location tracking system. This system is like an invisible network that covers every corner of the designated area and can capture and track users' dynamic location information in real time. This location information not only provides merchants with valuable user behavior data, but also provides important decision-making support for urban planning, traffic management and other fields.

[0046] Once the SMS is sent, our system quickly enters the feedback data collection and analysis phase. This process is like a keen detective, capturing key indicators such as user replies, click-through rates, and conversion rates to comprehensively evaluate the effectiveness of SMS reach. Based on these evaluation results, we use advanced algorithms and models to automatically adjust strategy parameters, such as sending time, content optimization, and target audience screening, to optimize the effectiveness and efficiency of SMS reach. This process is like a wise commander, adjusting tactical layout in a timely manner according to changes in the battlefield situation to ensure that every attack achieves the best results.

[0047] This embodiment builds a comprehensive, efficient and accurate SMS marketing system through sophisticated data preprocessing, efficient real-time location tracking, and intelligent feedback data analysis and strategy adjustment. This system not only improves the effectiveness and efficiency of SMS reach, but also brings more commercial value and user satisfaction to merchants. In future development, we will continue to optimize this system and introduce more advanced technologies and concepts to cope with the increasingly complex and changing market environment.

[0048] In summary, the present invention uses a real-time dynamic location tracking algorithm, combined with the global positioning system (GPS) data of mobile devices and signal tower positioning information, to accurately measure the distribution of people in the target area. The algorithm has the ability to identify parameters such as movement speed, path selection, and length of stay, and can distinguish between permanent residents and floating population, thereby accurately identifying the target population. By continuously updating the location data, it is ensured that the location information of the crowd is kept up to date when sending text messages, thereby improving the accuracy and timeliness of text message delivery.

[0049] The present invention also introduces a crowd density analysis algorithm and combines it with big data technology to calculate and determine high-density and low-density areas in the target area in real time. Based on the identification results of crowd density and hot spots, the priority of SMS sending is intelligently allocated to ensure that residents in high-density areas receive information first. In addition, the system can dynamically adjust the SMS sending strategy according to density changes, optimize the efficiency of SMS resource use, and enhance the effectiveness of SMS delivery.

[0050] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A targeted SMS reaching method based on dynamic location tracking and crowd density analysis, characterized in that: The following steps are involved: Obtain dynamic location and crowd density information data of the target area through the data interface, clean and pre-process the data to ensure that the data is accurate and real-time; Based on dynamic location data, we use dynamic location precision tracking algorithms, combined with machine learning and GIS technology, to accurately locate the movement trajectory and stay location of people; Use crowd density priority allocation algorithm to identify hot spots and automatically assign SMS sending priorities based on the analysis results; Integrate location tracking and density analysis algorithms into the SMS sending system to form an intelligent SMS reach platform, optimize SMS sending strategies, and improve marketing or notification effects.

2. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 1 is characterized in that: In the method, a density-based LOF outlier detection algorithm is used to detect and clean noise data in the target area dynamic position and crowd density information data.

3. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 2 is characterized in that: In the method, the LOF outlier detection algorithm is executed in time, the K-means algorithm is upgraded, and the time dimension T is added to the algorithm, so that the K-means algorithm can classify the signaling data with time and space attributes, and the K-means clustering algorithm with the time dimension is used to select a set of trajectory sequence points of a certain user sorted in ascending order based on time; Define the intra-cluster distance D pt It is the sum of the absolute values ​​of the distance of the center point u in the p distance cluster and the difference between the time dimension Tp of p and the time dimension Tu of the center point u, as shown in the formula: In the formula It is a balance parameter for adjusting distance and time difference.

4. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 1 is characterized in that: In the method, the dynamic position accurate tracking algorithm is specifically: in is the state prediction vector at time k including position and velocity; is the state transfer matrix, which is used to predict the next position of the target; is the input control vector; is the control input matrix, is the process noise; State update equation: is the Kalman gain matrix, is the observation vector; is the observation matrix.

5. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 4 is characterized in that: The method uses a dynamic location precision tracking algorithm based on the dynamic location data of the mobile device, locates multi-source data through GPS and signal towers, tracks the movement trajectory of people in the target area in real time, and uses Kalman filtering technology to predict and correct the dynamic location data to ensure the accuracy and real-time performance of tracking.

6. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 1 is characterized in that: In the method, the crowd density priority allocation algorithm distinguishes between high-density areas and low-density areas by collecting crowd density data at different locations in the target area. When calculating the priority, the utility function is introduced to optimize resource allocation to ensure that SMS messages are sent preferentially to high-density areas to achieve maximum utility.

7. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 6 is characterized in that: In the method, the crowd density is calculated as: is the crowd density at position (x,y) at time t; N(x,y,t) is the number of people at position (x,y) at time t, and A is the unit area.

8. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 6 is characterized in that: In the method, the priority allocation model uses the utility function U to measure the priority of resource allocation: in is the priority utility value of position (x, y) at time t; and is a weight factor used to adjust the impact of crowd density and distance on priority; It is the distance function from the position (x,y) to the center of the hotspot.

9. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 1 is characterized in that: In the method, data preprocessing includes removing noise data, processing outliers and standardizing data; Use GPS, Wi-Fi, and Bluetooth positioning technologies to track the real-time location of users in the target area.

10. The targeted SMS reaching method based on dynamic location tracking and crowd density analysis according to claim 1 is characterized in that: In the method, after the SMS is sent, the system collects and analyzes user feedback data to evaluate the effect of the SMS reach, and automatically adjusts the strategy parameters based on the evaluation results to continuously optimize the effect and efficiency of the SMS reach.

Citation Information

Patent Citations

  • Short message sending processing method, device and system

    CN103813278A

  • System and method for precisely issuing emergency warning short message based on human flow density

    CN108133438A

  • A system and method for guide tour routes in scenic spot

    CN109509119A

  • Method for analyzing and extracting moving track of user based on mobile phone signaling

    CN112765120A

  • Information pushing method and device

    CN114741595A

Cited By

  • LOF algorithm-based work order abnormal information detection method

    CN120067844A

  • A Work Order Abnormal Information Detection Method Based on LOF Algorithm

    CN120067844B