Human-computer interaction method and system for self-service ticket buying based on artificial intelligence
By dynamically adjusting the k value and distance measurement weights in the local outlier factor algorithm, the abnormality detection process of the self-service ticket purchase system is optimized, the problem of inaccurate risk assessment results is solved, and accurate abnormality detection and real-time risk control are achieved. Improves the sensitivity and accuracy of the system.
Patent Information
- Application Number
- CN202411137000.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-19
AI Technical Summary
In the existing self-service ticket purchase system, the local outlier factor algorithm is improperly selected k value during abnormal detection, resulting in inaccurate risk assessment results, too low or too high sensitivity, high false alarm rate, affecting user experience.
By dynamically adjusting the k value in the local outlier factor algorithm, combining the proportion of historical and current abnormal data and data similarity, optimizing the abnormal detection process, using the initial k value to update the rules and distance measurement weight calculations, ensuring that the evaluation indicators are optimal. This will achieve accurate abnormal data detection.
It improves the sensitivity and accuracy of abnormal ticket detection, ensures accurate abnormal detection and real-time risk control of user ticket purchase behavior, and effectively prevents potential abnormal ticket purchase behavior.
Smart Images

Figure CN119089348A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology. More specifically, the present invention relates to a self-service ticket purchase human-computer interaction method and system based on artificial intelligence. Background Art
[0002] Artificial intelligence relies on natural language processing, machine learning, computer vision, intelligent dialogue systems, and dynamic pricing in the human-computer interaction of self-service ticket purchases, enabling the system to understand user voice and text input, analyze user behavior, provide personalized recommendations and real-time pricing, and improve security and user experience through identity authentication and sentiment analysis. Together, these technologies optimize the intelligence and efficiency of the ticket purchase process. In the self-service ticket purchase system, user ticket purchase risk assessment uses artificial intelligence algorithms, such as the local outlier factor (LOF) algorithm and the isolation forest algorithm, to analyze ticket purchase behavior and identify potential fraud, violations, or other abnormal behaviors. The realization of this function not only relies on advanced algorithms and technologies, but also requires comprehensive consideration of user experience and business needs. The system needs to accurately detect abnormal behaviors while minimizing the false alarm rate to avoid interfering with the normal user's ticket purchase experience. This requires that the system must have strong data processing and analysis capabilities and be able to flexibly adapt to different scenarios and needs during the design and implementation process.
[0003] For example, when using the local outlier factor algorithm to assess the risk of user ticket purchases, since the local outlier factor algorithm is an unsupervised outlier detection method and a density-based outlier detection method, it often needs to set a k value when performing anomaly detection. Therefore, the k value has a great impact on the anomaly detection of each user's ticket purchase data. When the k value is too large, the local outlier factor algorithm has low sensitivity, which may cause risk data to be misjudged as normal data; when the k value is too small, the local outlier factor algorithm has high sensitivity, which may cause false alarms for normal data, thereby causing inaccurate risk assessment results for users' ticket purchases. Summary of the invention
[0004] In order to solve the problem of inaccurate risk assessment results for user ticket purchases raised in the above background technology, the present invention provides solutions in the following aspects.
[0005] In a first aspect, the present invention provides a self-service ticket purchase human-computer interaction method based on artificial intelligence, comprising:
[0006] Obtain the ticket purchase data of different users in the current time period; use the local outlier factor algorithm to perform anomaly detection on the ticket purchase data of each user to obtain suspected abnormal data and suspected normal data of each ticket purchase data; wherein the k nearest neighbor value in the local outlier factor algorithm is the initial k value;
[0007] Calculate the evaluation index of suspected normal data, the evaluation index is positively correlated with the classification validity and data similarity; the classification validity characterizes the difference between the current suspected abnormal data and the abnormal data in the historical time period; in response to the evaluation index being lower than the set threshold, update the initial value until the updated evaluation index is higher than the set threshold, stop updating, and obtain the updated optimal value; wherein the update rule is: when the proportion of suspected abnormal data is lower than the proportion of abnormal data in the historical time period, take the product of the last k value and the classification validity as the current updated k value; when the proportion of suspected abnormal data is higher than or equal to the proportion of abnormal data in the historical time period, take the ratio of the last k value to the classification validity as the current updated k value;
[0008] Based on the optimal value, anomaly detection is performed on the ticket purchasing data of each user to obtain the final abnormal data of each ticket purchasing data, and the abnormal ticket purchasing behavior of the user corresponding to the final abnormal data is promptly prevented.
[0009] The above scheme achieves accurate abnormal data detection by optimizing the k value in the local outlier factor algorithm, enabling it to adaptively adjust in different time periods, thereby improving the problem of inaccurate risk assessment results for user ticket purchases.
[0010] Furthermore, the initial k value is:
[0011]
[0012] In the formula, A′ represents the total number of ticket purchase data in the current time period, A represents the total number of ticket purchase data in the historical time period, and B represents the total number of abnormal data in the historical time period. Indicates the proportion of abnormal data in the historical time period.
[0013] The above scheme multiplies the proportion of abnormal data in the historical time period by the total number of ticket purchase data in the current time period, and obtains the initial value of k through historical experience, so that the detection algorithm can adapt to data fluctuations in different time periods, ensuring that the anomaly detection algorithm remains effective when the data scale changes, thereby improving the sensitivity and accuracy of anomaly detection.
[0014] Furthermore, the data similarity is:
[0015] S n,n+1 =α×d n,n+1 +(1-α)×y n,n+1 ;
[0016] In the formula, S n,n+1 Indicates the data similarity between the nth data and the n+1th data in the suspected normal data, d n,n+1 Indicates the Manhattan distance between the nth data and the n+1th data in the suspected normal data, y n,n+1It represents the cosine similarity between the nth data and the n+1th data in the suspected normal data, and α represents the distance measurement weight.
[0017] The above technical solution combines Manhattan distance and cosine similarity, and dynamically adjusts the weights of the two according to the sparsity of data distribution. When the data is sparsely distributed, it relies more on cosine similarity, thereby improving the accuracy and robustness of the similarity calculation, and effectively responding to the needs of anomaly detection under different data distributions.
[0018] Furthermore, the calculation formula of the distance metric weight α is:
[0019]
[0020] In the formula, C represents the total number of suspected normal data, r represents the total number of characteristic parameters in the ticket purchase data, and d n,n+1 G represents the Manhattan distance between the nth data and the n+1th data in the suspected normal data. i,j represents the jth characteristic parameter of the i-th data in the suspected normal data, G i+1,j Represents the ,th characteristic parameter of the i+1th data in the suspected normal data.
[0021] The above technical solution dynamically calculates the distance metric weight α by comprehensively considering the overall distribution characteristics of suspected normal data and the differences in each characteristic parameter, thereby accurately reflecting the actual similarity between the data. This method can effectively adapt to the complexity of data characteristics.
[0022] Furthermore, the classification validity is:
[0023]
[0024] Where H represents the classification validity, A′ represents the total number of ticket purchase data in the current time period; B′ represents the total number of suspected abnormal data in the current time period, A represents the total number of ticket purchase data in the historical time period, B represents the total number of abnormal data in the historical time period, and e is the base of the natural logarithm function.
[0025] The above technical solution quantifies the difference in the proportion of abnormal data between the current time period and the historical time period by calculating the classification effectiveness. The impact of the difference is controlled by the exponential function to ensure that the classification effectiveness is close to 1 when the abnormal proportion does not change much, thereby providing stability during dynamic adjustment and sensitively reflecting the abnormality when there is a significant difference, thereby improving the adaptability and accuracy of the detection algorithm.
[0026] Furthermore, the evaluation index is:
[0027]
[0028] In the formula, U represents the evaluation index, H represents the classification effectiveness, Sn,n+1 represents the data similarity between the nth data and the n+1th data in the suspected normal data, and C represents the total number of suspected normal data.
[0029] The above method effectively combines the influence of historical abnormal data and the similarity of current data, providing a balanced evaluation criterion that helps to ensure the classification accuracy and stability of detection during the optimization process.
[0030] Furthermore, the ticket purchase data includes multiple characteristic parameters, which are: ticket purchase time, ticket purchase frequency, ticket purchase total price, account login frequency, and average flight interval of air tickets.
[0031] Furthermore, it also includes: preprocessing the ticket purchase data, and the preprocessing process includes: data normalization, missing value filling and data smoothing.
[0032] In a second aspect, the present invention provides an artificial intelligence-based self-service ticket purchase human-computer interaction system, comprising a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, any one of the artificial intelligence-based self-service ticket purchase human-computer interaction methods described above is implemented.
[0033] The beneficial effects of the present invention are:
[0034] The present invention optimizes the anomaly detection process by dynamically adjusting the k value in the local outlier factor algorithm, combining the historical and current abnormal data proportions and data similarity, and improves the sensitivity and accuracy of the detection algorithm. By continuously updating and optimizing the k value, the evaluation index is ensured to be optimal, thereby achieving accurate anomaly detection and real-time risk control of user ticket purchase behavior, solving the problem of inaccurate risk assessment results of user ticket purchases, and effectively preventing potential abnormal ticket purchase behavior. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:
[0036] Figure 1 is a flowchart schematically showing a human-computer interaction method for self-service ticket purchase based on artificial intelligence according to an embodiment of the present invention;
[0037] Figure 2 It is a structural block diagram schematically showing a human-computer interaction system for self-service ticket purchase based on artificial intelligence according to an embodiment of the present invention. DETAILED DESCRIPTION
[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 those skilled in the art without creative work are within the scope of protection of the present invention.
[0039] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
[0040] An embodiment of a self-service ticket purchasing human-computer interaction method based on artificial intelligence.
[0041] like Figure 1 As shown, a flowchart of a self-service ticket purchase human-computer interaction method based on artificial intelligence in an embodiment of the present invention includes:
[0042] S1: Get the ticket purchase data of different users in the current time period.
[0043] In one embodiment, the ticket purchase data of different users in the current time period can be obtained by calling the application programming interface of the ticket purchase platform. Of course, user behavior tracking tools can also be used to record, such as using Google Analytics tools to obtain the ticket purchase data of different users; and the ticket purchase data includes multiple characteristic parameters, which are: ticket purchase time, ticket purchase frequency, ticket purchase total price, account login frequency, and average interval between flight tickets.
[0044] Among them, the time of ticket purchase can reveal whether the user's ticket purchasing habits are consistent with their historical behavior patterns. For example, late-night ticket purchases may indicate account abuse or abnormal user behavior; frequent ticket purchases may suggest that the user is engaged in reselling tickets or trying to take advantage of ticket price fluctuations, and there is a risk of account theft; high total ticket purchase prices may be related to fraudulent behavior, such as using stolen credit cards to purchase tickets. In addition, if a user usually purchases large-value tickets but suddenly starts purchasing small-value tickets, this may also indicate that there is an abnormality in the account. Too frequent account logins may indicate that the account has been stolen or there are abnormal access attempts. At the same time, booking multiple flights in a short period of time, especially when the flight departure times are too close or the flight arrival time conflicts with the departure time of subsequent flights, resulting in a short or even negative average flight interval, may also be related to fraud, evasion of supervision, or abnormal personal behavior.
[0045] Specifically, it also includes preprocessing of ticket purchase data, and the preprocessing process is: data normalization, missing value filling and data smoothing. Data normalization is used to convert data of different ranges to a unified scale so that each feature is in the same range; missing value filling is used to fill the missing values in the data set to ensure data integrity; data smoothing is used to reduce noise and irregular fluctuations in the data to make the data smoother and more representative.
[0046] S2: Apply the local outlier factor algorithm to detect anomalies in the ticket purchase data, and use the initial k value to distinguish suspected abnormal data from suspected normal data.
[0047] Specifically, the local outlier factor algorithm is applied to the ticket purchasing data of each user to perform anomaly detection to obtain the anomaly score of each user's ticket purchasing data; the calculated anomaly scores of the ticket purchasing data of each user are summarized and a histogram of the anomaly scores is drawn, and based on the histogram of the anomaly scores, the ticket purchasing data of each user is divided into suspected abnormal data and suspected normal data, and the data with anomaly scores higher than the threshold are marked as suspected abnormal data, while the data with anomaly scores lower than the threshold are marked as suspected normal data; wherein the k nearest neighbor value in the local outlier factor algorithm is the initial k value.
[0048] In one embodiment, the initial k value is:
[0049]
[0050] In the formula, A′ represents the total number of ticket purchase data in the current time period, A represents the total number of ticket purchase data in the historical time period, and B represents the total number of abnormal data in the historical time period. It indicates the proportion of abnormal data in the historical time period, and the ticket purchase data and abnormal data in the historical time period can be directly obtained from the historical database.
[0051] S3: Calculate the evaluation index of the suspected normal data. If the evaluation index is lower than the threshold, adjust the k value according to the update rule until the evaluation index meets the requirements, and then obtain the optimal value.
[0052] In one embodiment, an evaluation index of suspected normal data is calculated, and the evaluation index is positively correlated with classification effectiveness and data similarity. The classification effectiveness represents the difference between the current suspected abnormal data and the abnormal data in the historical time period; the data similarity is:
[0053] S n,n+1 =α×d n,n+1 +(1-α)×y n,n+1 ;
[0054] In the formula, S n,n+1 Indicates the data similarity between the nth data and the n+1th data in the suspected normal data, d n,n+1 Indicates the Manhattan distance between the nth data and the n+1th data in the suspected normal data, y n,n+1 It represents the cosine similarity between the nth data and the n+1th data in the suspected normal data, and α represents the distance measurement weight.
[0055] The calculation formula of the distance metric weight α is as follows:
[0056]
[0057] In the formula, C represents the total number of suspected normal data, r represents the total number of characteristic parameters in the ticket purchase data, and d n,n+1 G represents the Manhattan distance between the nth data and the n+1th data in the suspected normal data. i,j represents the jth characteristic parameter of the i-th data in the suspected normal data, G i+1,j Represents the j-th characteristic parameter of the i+1-th data in the suspected normal data.
[0058] The classification validity is:
[0059]
[0060] Where H represents the classification validity, A′ represents the total number of ticket purchase data in the current time period; B′ represents the total number of suspected abnormal data in the current time period, A represents the total number of ticket purchase data in the historical time period, B represents the total number of abnormal data in the historical time period, and e is the base of the natural logarithm function.
[0061] The evaluation indicators are:
[0062]
[0063] In the formula, U represents the evaluation index, H represents the classification effectiveness, S n,n+1 represents the data similarity between the nth data and the n+1th data in the suspected normal data, and C represents the total number of suspected normal data.
[0064] Among them, the update rule is: when the proportion of suspected abnormal data is lower than the proportion of abnormal data in the historical time period, the product of the previous k value and the classification effectiveness is used as the k value after the current update; when the proportion of suspected abnormal data is higher than or equal to the proportion of abnormal data in the historical time period, the ratio of the previous k value to the classification effectiveness is used as the k value after the current update.
[0065] For example, when the second update is performed, when the proportion of suspected abnormal data is lower than the proportion of abnormal data in the historical time period, the updated k value is: k1=H×k; when the proportion of suspected abnormal data is higher than or equal to the proportion of abnormal data in the historical time period, the updated k value is: Where k1 represents the updated k value, H represents the classification effectiveness, and k is the initial k value.
[0066] It should be noted that the abnormal data ratio refers to the proportion of abnormal data within the time period to all ticket purchase data within the time period.
[0067] Exemplarily, the threshold may be 0.5, and may also be determined according to actual conditions.
[0068] S4: Perform final anomaly detection based on the optimal value, identify the final abnormal data, and take measures to prevent abnormal ticket purchasing behavior.
[0069] Among them, the k-nearest neighbor value in the local outlier algorithm is the optimal value. The local outlier algorithm at this time is used to perform anomaly detection on the ticket purchase data of each user, and the ticket purchase data is divided into normal data and abnormal data. After determining the final abnormal data, potential fraud or signs of account abuse are identified, and the abnormal ticket purchase behavior of the user corresponding to the final abnormal data is promptly prevented.
[0070] In this embodiment, when a user's abnormal ticket purchasing behavior is determined, a reminder can also be given, such as reminding the administrator in the form of an email or text message to verify whether there is indeed fraud or abuse, and then temporarily freeze the suspicious user's account to prevent further abnormal operations.
[0071] The present invention optimizes the anomaly detection process by dynamically adjusting the k value in the local outlier factor algorithm, combining the historical and current abnormal data proportions and data similarity, and improves the sensitivity and accuracy of the detection algorithm. By continuously updating and optimizing the k value, the evaluation index is ensured to be optimal, thereby achieving accurate anomaly detection and real-time risk control of user ticket purchase behavior, solving the problem of inaccurate risk assessment results of user ticket purchases, and effectively preventing potential abnormal ticket purchase behavior.
[0072] An embodiment of a self-service ticket purchasing human-computer interaction system based on artificial intelligence.
[0073] like Figure 2 As shown, a structural block diagram of an artificial intelligence-based self-service ticket purchasing human-computer interaction system of the present invention includes a processor and a memory.
[0074] The present invention also provides a self-service ticket purchase human-computer interaction system based on artificial intelligence. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the above-mentioned artificial intelligence-based self-service ticket purchase human-computer interaction method according to the present invention is implemented.
[0075] The artificial intelligence-based self-service ticket purchasing human-computer interaction system also includes other components familiar to those skilled in the art, such as communication interfaces. Their settings and functions are known in the art, so they will not be described here in detail.
[0076] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that may be used to store the required information and may be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.
[0077] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.
[0078] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.
Claims
1. A self-service ticket purchase human-computer interaction method based on artificial intelligence, characterized in that: include: Get the ticket purchase data of different users in the current time period; The local outlier factor algorithm is used to perform anomaly detection on the ticket purchase data of each user to obtain suspected abnormal data and suspected normal data of each ticket purchase data; wherein the k nearest neighbor value in the local outlier factor algorithm is the initial k value; Calculate the evaluation index of suspected normal data, the evaluation index is positively correlated with the classification validity and data similarity; the classification validity characterizes the difference between the current suspected abnormal data and the abnormal data in the historical time period; in response to the evaluation index being lower than the set threshold, update the initial value until the updated evaluation index is higher than the set threshold, stop updating, and obtain the updated optimal value; wherein the update rule is: when the proportion of suspected abnormal data is lower than the proportion of abnormal data in the historical time period, take the product of the last k value and the classification validity as the current updated k value; when the proportion of suspected abnormal data is higher than or equal to the proportion of abnormal data in the historical time period, take the ratio of the last k value to the classification validity as the current updated k value; Based on the optimal value, anomaly detection is performed on the ticket purchasing data of each user to obtain the final abnormal data of each ticket purchasing data, and the abnormal ticket purchasing behavior of the user corresponding to the final abnormal data is promptly prevented.
2. According to the artificial intelligence-based self-service ticket purchase human-computer interaction method of claim 1, it is characterized in that: The initial k value is: In the formula, A′ represents the total number of ticket purchase data in the current time period, A represents the total number of ticket purchase data in the historical time period, and B represents the total number of abnormal data in the historical time period. Indicates the proportion of abnormal data in the historical time period.
3. According to the artificial intelligence-based self-service ticket purchase human-computer interaction method of claim 1, it is characterized in that: The data similarity is: S n,n+1 =α×d n,n+1 +(1-a)×y n,n+1 ; In the formula, S n,n+1 Indicates the data similarity between the nth data and the n+1th data in the suspected normal data, d n,n+1 Indicates the Manhattan distance between the nth data and the n+1th data in the suspected normal data, y n,n+1 It represents the cosine similarity between the nth data and the n+1th data in the suspected normal data, and α represents the distance measurement weight.
4. According to the artificial intelligence-based self-service ticket purchase human-computer interaction method of claim 3, it is characterized in that: The calculation formula of the distance metric weight α is: In the formula, C represents the total number of suspected normal data, r represents the total number of characteristic parameters in the ticket purchase data, and d n,n+1 G represents the Manhattan distance between the nth data and the n+1th data in the suspected normal data. i,j represents the jth characteristic parameter of the i-th data in the suspected normal data, G i+1,j Represents the j-th characteristic parameter of the i+1-th data in the suspected normal data.
5. According to the artificial intelligence-based self-service ticket purchase human-computer interaction method of claim 1, it is characterized in that: The classification validity is: Where H represents the classification validity, A′ represents the total number of ticket purchase data in the current time period; B′ represents the total number of suspected abnormal data in the current time period, A represents the total number of ticket purchase data in the historical time period, B represents the total number of abnormal data in the historical time period, and e is the base of the natural logarithm function.
6. According to the artificial intelligence-based self-service ticket purchase human-computer interaction method of claim 1, it is characterized in that: The calculation formula of the evaluation index is: In the formula, U represents the evaluation index, H represents the classification effectiveness, S n,n+1 represents the data similarity between the nth data and the n+1th data in the suspected normal data, and C represents the total number of suspected normal data.
7. According to the artificial intelligence-based self-service ticket purchase human-computer interaction method of claim 1, it is characterized in that: The ticket purchase data includes multiple characteristic parameters, which are: ticket purchase time, ticket purchase frequency, ticket purchase total price, account login frequency, and average flight interval of air tickets.
8. The method of self-service ticket purchase based on artificial intelligence according to claim 1 is characterized in that: Also includes: The ticket purchase data is preprocessed, and the preprocessing process is: data normalization, missing value filling and data smoothing.
9. A self-service ticket purchase human-computer interaction system based on artificial intelligence, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an artificial intelligence-based self-service ticket purchase human-computer interaction method as described in any one of claims 1 to 8 is implemented.
Citation Information
Patent Citations
False alarm filtering method and device for wrong data tolerance
CN110286656A
Abnormal user behavior auditing method and device
CN111866023A
Water conservancy project anomaly detection method
CN116429220A
Electronic seal data management system based on data analysis
CN116776274A
Hard carbon process environmental protection monitoring data acquisition and processing method
CN116992391A
Cited By
Packaging temperature control method and system for LED braider
CN120447649A
