Flight query data processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a flight query data processing method and device, electronic equipment and a storage medium. The method comprises the steps that flight query information of a user in a preset historical segment and dynamic influence dimension information at the current moment are acquired, and the dynamic influence dimension information at least comprises one of time dimension information and event dimension information; determining target popularity values of the flight query requests based on the flight query information and the dynamic influence dimension information; the cache of the flight query system is adjusted based on the target popularity value, target cache data is obtained, and the target cache data is used for responding to a target flight query request initiated by a user and generating a target flight query result based on the target flight query request. According to the method and the device, the technical problem of relatively low efficiency of performing response feedback on the flight query request of the user by a flight query system in related technologies is solved.

Description

Technical Field

[0001] The present invention relates to the field of flight data processing, and in particular to a method, device, electronic device and storage medium for processing flight query data. Background Art

[0002] The user initiates a flight query request to the flight query system. After receiving the flight query request from the user, the flight query system usually needs to query the background query system or background flight database based on the information provided by the user, find the flight information that meets the conditions, and feedback it to the user.

[0003] When the flight query system receives a large number of flight query requests, the amount of data processing operations required for query feedback from the background query system or the background flight database is large, and it is difficult for the system to respond to each flight query request in a timely manner; and the number of flight query requests received by the flight query system is not evenly distributed. Simply expanding the concurrent processing performance of the flight query system will result in a high performance expansion cost for the system and idle resources in the system after the expansion. In summary, the efficiency of the flight query system in the related art in responding to the user's flight query request is low.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, electronic device and storage medium for processing flight query data, so as to at least solve the technical problem in the related art that the flight query system has low efficiency in responding to the flight query request of the user.

[0006] According to one aspect of an embodiment of the present application, a method for processing flight query data is provided, including: obtaining flight query information of users within a preset historical segment and dynamic impact dimension information at a current moment, wherein the flight query information includes multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests, and the dynamic impact dimension information includes at least one of the following: time dimension information and event dimension information, the time dimension information is used to characterize the time dimension that has an impact on the flight query popularity, and the event dimension information is used to characterize the event dimension that has an impact on the flight query popularity; based on the flight query information and the dynamic impact dimension information, determining target heat values ​​of the multiple flight query requests; based on the target heat value, adjusting the cache of the flight query system to obtain target cache data, wherein the adjustment operation includes at least one of the following: insert cache operation, replace cache operation and delete cache operation, and the target cache data is used to respond to the target flight query request initiated by the user and generate the target flight query result based on the target flight query request.

[0007] Optionally, based on the flight query information and the dynamic impact dimension information, the target heat values ​​of multiple flight query requests are determined, including: based on the flight query information, the query dimension information of any flight query request is determined, wherein the query dimension information includes at least one of the following: query frequency information, query destination information and user type information; based on the query dimension information and the dynamic impact dimension information, multi-dimensional information for thermal value calculation is determined; based on the thermal value calculation multi-dimensional information, the target heat value is determined.

[0008] Optionally, determining the target heat value based on the thermal value calculation multi-dimensional information includes: determining a weight parameter set corresponding to the thermal value calculation multi-dimensional information based on a pre-trained thermal value weight allocation model, wherein the pre-trained thermal value calculation model is used to represent a pre-trained machine learning model for performing thermal value weight allocation; determining the target heat value based on the thermal value calculation multi-dimensional information and the weight parameter set.

[0009] Optionally, based on the thermal value calculation multi-dimensional information and the weight parameter set, the target thermal value is determined, including: weighted summing the thermal value calculation multi-dimensional information and the weight parameter set to obtain a weighted summation result; based on the weighted summation result, determining the thermal values ​​corresponding to multiple flight query requests to obtain the target thermal value.

[0010] Optionally, adjusting the cache of the flight query system based on the target heat value to obtain target cache data includes: when the adjustment operation is a cache insertion operation or a cache replacement operation, screening multiple flight query requests based on the target heat value to obtain at least one flight query request to be stored; determining a flight query result to be stored corresponding to at least one flight query request to be stored based on a background query system of the flight query system; performing a cache insertion operation or a cache replacement operation on the cache of the flight query system based on the at least one flight query request to be stored and the corresponding flight query result to be stored to obtain target cache data; when the adjustment operation is a cache deletion operation, screening the cache of the flight query system based on the target heat value to obtain at least one flight query request to be deleted; determining a flight query result to be deleted corresponding to at least one flight query request to be deleted; performing a cache deletion operation on the cache of the flight query system based on the at least one flight query request to be deleted and the corresponding flight query result to be deleted to obtain target cache data.

[0011] Optionally, adjusting the cache of the flight query system based on the target heat value to obtain target cache data includes: determining the target application scenario at the current moment; when the target application scenario is the first application scenario, adjusting the cache of the flight query system based on the target heat value according to the first adjustment frequency and the first adjustment amplitude to obtain target cache data; when the target application scenario is the second application scenario, adjusting the cache of the flight query system based on the target heat value according to the second adjustment frequency and the second adjustment amplitude to obtain target cache data, wherein the real-time performance of the second application scenario is less than the real-time performance of the first application scenario, the second adjustment frequency is less than the first adjustment frequency, and the second adjustment amplitude is greater than the first adjustment amplitude.

[0012] According to another aspect of an embodiment of the present invention, a device for processing flight query data is also provided, including: an acquisition module, used to acquire flight query information of users in a preset historical segment and dynamic impact dimension information at the current moment, wherein the flight query information includes multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests, and the dynamic impact dimension information includes at least one of the following: time dimension information and event dimension information, the time dimension information is used to characterize the time dimension that has an impact on the flight query heat, and the event dimension information is used to characterize the event dimension that has an impact on the flight query heat; a determination module, used to determine target heat values ​​of the multiple flight query requests based on the flight query information and the dynamic impact dimension information; an adjustment module, used to adjust the cache of the flight query system based on the target heat value to obtain target cache data, wherein the adjustment operation includes at least one of the following: insert cache operation, replace cache operation and delete cache operation, and the target cache data is used to respond to the target flight query request initiated by the user and generate the target flight query result based on the target flight query request.

[0013] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0014] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0017] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0018] In an embodiment of the present invention, first, flight query information is obtained, including multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests. At the same time, dynamic impact dimension information is obtained, including time dimension information and event dimension information. The time dimension information is used to characterize the time dimension that has an impact on the flight query popularity, and the event dimension information is used to characterize the event dimension that has an impact on the flight query popularity. Based on the flight query information and the dynamic impact dimension information, the target heat values ​​of the multiple flight query requests are determined. According to the target heat value, the cache of the flight query system is adjusted to obtain target cache data. The adjustment operation includes insert cache operation, replace cache operation and delete cache operation. The target cache data is used to respond to the target flight query request initiated by the user, and generate the target flight query result based on the target flight query request. It is easy to notice that the present application presets the flight query information of the user in the historical segment and the dynamic impact dimension information at the current moment, determines the target heat values ​​of multiple flight query requests, and adjusts the cache based on the target heat values, including inserting, replacing or deleting the cache, etc., which can help the system better understand the user's query behavior and predict future query heat, so as to make more reasonable cache data adjustments and timely update the cache data. The flight query system can directly respond to the user's flight query request based on the dynamically adjusted target cache data without querying from the background query system or the background flight database. The system can better match the user's query needs and provide more accurate and faster query results to improve the user experience. By dynamically adjusting the cache data, the system can better respond to emergencies or query requests during peak hours and maintain the stability of the system. Timely adjustment of the cache data can avoid the system crashing or responding slowly due to excessive requests, thereby solving the technical problem of low efficiency of the flight query system in responding to the user's flight query request in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1is a flow chart of a method for processing flight query data according to an embodiment of the present invention;

[0021] Figure 2 is a schematic diagram of a model training business architecture in processing of an optional flight query data according to an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of a model training technology framework in processing flight query data according to an optional embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of a model runtime technical architecture in processing of an optional flight query data according to an embodiment of the present invention;

[0024] Figure 5 is a schematic diagram of an optional intelligent cache execution logic in processing flight query data according to an embodiment of the present invention;

[0025] Figure 6 is a schematic diagram of a model inference service in processing an optional flight query data according to an embodiment of the present invention;

[0026] Figure 7 4 is a schematic diagram of a flight query data processing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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 should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] According to an embodiment of the present invention, an embodiment of a method for processing flight query data is provided. It can be explained that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 is a flow chart of a method for processing flight query data according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0031] Step S102, obtaining the user's flight query information within a preset historical period and the dynamic impact dimension information at the current moment.

[0032] Among them, the flight query information includes multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests, and the dynamic impact dimension information includes at least one of the following: time dimension information and event dimension information. The time dimension information is used to characterize the time dimension that has an impact on the flight query popularity, and the event dimension information is used to characterize the event dimension that has an impact on the flight query popularity.

[0033] The above-mentioned preset historical segment may refer to a preset length of time before the current moment, for example, it may be one week or one year before the current moment. The preset historical segment may be determined according to actual needs and is not limited here.

[0034] The above-mentioned time dimension information may refer to the information corresponding to the time dimension that has an impact on the popularity of flight inquiries at the current moment. The impact here may refer to a positive impact or a negative impact. For example, the time dimension information may include but is not limited to the factors that may affect the popularity of flight inquiries at the current moment, such as holidays within the next month, whether it is a peak tourist season, whether it is a low tourist season, etc. The time dimension information may also be determined according to actual needs and is not limited here.

[0035] The above-mentioned event dimension information may refer to the information corresponding to the event dimension that has an impact on the popularity of flight inquiries at the current moment. For example, the event dimension information may include but is not limited to events that may affect the popularity of flight inquiries at the current moment, such as major conferences, exhibitions, sports events, concerts, etc. within the next month. The event dimension information can also be determined according to actual needs and is not limited here.

[0036] In an optional embodiment, by obtaining the flight query information of the user in the preset historical section and the dynamic impact dimension information at the current moment, the query habits and preferences of the user, as well as the impact of some dynamic factors at the current moment on the flight query popularity, can be obtained, which helps to better understand the dynamic adjustment and optimization of flight data, and facilitates the subsequent adjustment of cached data to improve user experience and the accuracy of flight query. Specifically, for example, the flight query information of the user in the preset historical section can be obtained. It can include multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests. By analyzing these historical data, the query behavior of the user can be understood, such as which flights the user often searches for, which routes are more popular, and the user's booking tendency, and the dynamic impact dimension information at the current moment can be obtained. The dynamic impact dimension information can include time dimension information and event dimension information. The time dimension information can represent the time dimension that has an impact on the flight query popularity, such as holidays, whether it is a tourist peak season, whether it is a tourist off-season, etc. The event dimension information can represent the event dimension that has an impact on the flight query popularity, such as major conferences, exhibitions, sports events, concerts, etc. These dynamic factors can affect the query popularity of flights, which is convenient for making corresponding adjustments according to different query needs. By analyzing the user's historical query information and the dynamic influencing dimension information at the current moment, we can more accurately understand the changes in the user's flight query needs, so that airlines can dynamically adjust queries based on user query needs and respond to user queries in a timely manner to improve user experience.

[0037] In this application, obtaining the flight query information of users in the preset historical segment and the dynamic impact dimension information at the current moment can help the system better understand the user's query behavior and predict the future query heat, so as to make more reasonable cache data adjustments and flight recommendations. Flight query information may include multiple flight query requests and corresponding query results. These query requests may include information such as the user's departure place, destination, departure time, cabin, etc., and the query results may include qualified flight information, such as flight number, cabin, estimated price, etc. By analyzing historical query data, the system can understand the user's preferences and habits, so as to better provide personalized flight recommendations for users. Dynamic impact dimension information may include time dimension information and event dimension information. Time dimension information can help the system understand the query heat of users in different time periods, such as weekends, holidays, etc. The query volume of users may increase. Event dimension information can help the system understand the impact of external events on query heat, such as important activities in a city, weather changes, etc., which can affect the user's travel needs. By analyzing these dynamic impact dimension information, the system can more accurately predict the user's query heat, so as to reasonably adjust the cache data.

[0038] Step S104: determining target heat values ​​of multiple flight query requests based on the flight query information and the dynamic impact dimension information.

[0039] In an optional embodiment, the heat values ​​corresponding to the multiple flight query requests, that is, the target heat values, can be determined based on the flight query information and the dynamic impact dimension information. Specifically, according to the flight query information and the dynamic impact dimension information, a method for calculating the flight heat value can be determined. This method can be rule-based or machine learning-based. Based on the flight query information and the dynamic impact dimension information, the target heat values ​​of multiple flight query requests can be determined by machine learning algorithms, such as regression models, neural networks, etc., combined with historical query data and dynamic impact dimension information, to predict the heat of future query requests, which can improve the response speed and accuracy of the airline query system. By predicting the user's query heat, the system can cache and load popular flight information in advance, reduce user waiting time, and improve the system's operating efficiency. By reasonably adjusting the cached data, the system can respond to the user's query needs more efficiently. The system can regularly update the heat value of the flight to reflect the latest situation, so as to ensure that the system can respond to the user's query request in a timely manner and improve the user experience. In the above process, determining the heat value of the flight query request can help the system better respond to the user's query request and improve the query efficiency. Users can find flight information that meets their needs more quickly and improve the user experience. By determining the target heat values ​​of multiple flight query requests, the system can better meet user needs and optimize user experience. Users can more easily find flight information that meets their needs and improve satisfaction.

[0040] Step S106, adjusting the cache of the flight query system based on the target heat value to obtain target cache data.

[0041] The adjustment operation includes at least one of the following: insert cache operation, replace cache operation and delete cache operation, and the target cache data is used to respond to the target flight query request initiated by the user and generate the target flight query result based on the target flight query request.

[0042] In an optional embodiment, by analyzing the heat value of the user query request, the system performance and user experience can be effectively improved. The present application can adjust the cache of the flight query system based on the target heat values ​​of multiple flight query requests, wherein the insert cache operation may refer to adding data to the cache to improve the response speed of the user querying the target flight; the replace cache operation may refer to replacing the data in the cache with new data when it is outdated or no longer popular; the delete cache operation may refer to clearing the flight information that is no longer needed to release the cache space. Through the above adjustment operations, the system can maintain the timely frame skipping and accuracy of the cache data, and improve the response speed and user experience of the system. When the user initiates a query request for the target flight, the system can directly obtain information from the target cache data, and the system does not have to initiate a query request to the background query system or database, thereby reducing the query burden of the system and improving the query efficiency. By analyzing and adjusting the heat value of the user query request, the system can also implement a personalized recommendation function, store the flight information of interest to the user in the cache according to the user's preferences and habits, improve user satisfaction, and make the system more intelligent, efficient and user-friendly.

[0043] In an embodiment of the present invention, first, flight query information is obtained, including multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests. At the same time, dynamic impact dimension information is obtained, including time dimension information and event dimension information. The time dimension information is used to characterize the time dimension that has an impact on the flight query popularity, and the event dimension information is used to characterize the event dimension that has an impact on the flight query popularity. Based on the flight query information and the dynamic impact dimension information, the target heat values ​​of the multiple flight query requests are determined. According to the target heat value, the cache of the flight query system is adjusted to obtain target cache data. The adjustment operation includes insert cache operation, replace cache operation and delete cache operation. The target cache data is used to respond to the target flight query request initiated by the user, and generate the target flight query result based on the target flight query request. It is easy to notice that the present application presets the flight query information of the user in the historical segment and the dynamic impact dimension information at the current moment, determines the target heat values ​​of multiple flight query requests, and adjusts the cache based on the target heat values, including inserting, replacing or deleting the cache, etc., which can help the system better understand the user's query behavior and predict future query heat, so as to make more reasonable cache data adjustments and timely update the cache data. The flight query system can directly respond to the user's flight query request based on the dynamically adjusted target cache data without querying from the background query system or the background flight database. The system can better match the user's query needs and provide more accurate and faster query results to improve the user experience. By dynamically adjusting the cache data, the system can better respond to emergencies or query requests during peak hours and maintain the stability of the system. Timely adjustment of the cache data can avoid the system crashing or responding slowly due to excessive requests, thereby solving the technical problem of low efficiency of the flight query system in responding to the user's flight query request in the related technology.

[0044] Optionally, based on the flight query information and the dynamic impact dimension information, the target heat values ​​of multiple flight query requests are determined, including: based on the flight query information, the query dimension information of any flight query request is determined, wherein the query dimension information includes at least one of the following: query frequency information, query destination information and user type information; based on the query dimension information and the dynamic impact dimension information, multi-dimensional information for thermal value calculation is determined; based on the thermal value calculation multi-dimensional information, the target heat value is determined.

[0045] In an optional embodiment, by analyzing the flight query information and the dynamic impact dimension information, the target heat value of multiple flight query requests can be determined, so as to better meet the user needs and improve the system performance and user experience. Specifically, firstly, based on the flight query information, the query dimension information of any flight query request can be determined, and the query dimension information can include query frequency information, query destination information and user type information. The query frequency information can reflect the number of queries of a certain flight by the user, so as to judge the heat of the flight. The query destination information can reflect the user's attention to a certain destination, and the cache data can be adjusted according to the heat of different destinations. User type information can help the system better understand user needs and provide personalized query results. Then, based on the query dimension information and the dynamic impact dimension information, the heat value calculation multi-dimensional information can be determined. By combining the query dimension information and the dynamic impact dimension information, the heat value of the flight can be more accurately calculated, so as to determine the target heat value. Finally, the target heat value can be determined based on the heat value calculation multi-dimensional information. By combining different query dimension information and dynamic impact dimension information, the heat value of the flight can be more accurately determined, so as to adjust the cache data of the system and improve the performance and user experience of the system. In the above process, by dynamically adjusting the cache data, user needs can be better met, the number of database queries can be reduced, the system response speed and performance can be improved, and more personalized query results can be provided based on user query habits and preferences, thereby improving user satisfaction and experience. Through the calculation and analysis of multi-dimensional information, user needs and behaviors can be better understood, providing airlines with more accurate data cache adjustment support.

[0046] Optionally, determining the target heat value based on the thermal value calculation multi-dimensional information includes: determining a weight parameter set corresponding to the thermal value calculation multi-dimensional information based on a pre-trained thermal value weight allocation model, wherein the pre-trained thermal value calculation model is used to represent a pre-trained machine learning model for performing thermal value weight allocation; determining the target heat value based on the thermal value calculation multi-dimensional information and the weight parameter set.

[0047] In an optional embodiment, the present application uses cache technology to store and manage query data to improve the query efficiency and accuracy of data. In the process of processing flight query data, the heat value of each flight query request can be determined by comprehensively considering information in multiple dimensions. Specifically, based on the pre-trained thermal value weight distribution model, the weight parameter set corresponding to the multi-dimensional information of thermal value calculation can be determined, and a pre-trained thermal value weight distribution model can be established in advance. The model can be trained by a machine learning algorithm to learn the influence of each dimensional information on the flight heat value. During the training process, historical data can be used to train the model to determine the weight parameter set of each dimensional information. These parameter sets can reflect the contribution of different dimensional information to the flight heat value. The pre-trained thermal value weight distribution model can be constructed based on algorithms such as neural networks and decision trees, and the distribution rules of weight parameters can be automatically learned according to the data characteristics of different dimensions. Based on the pre-trained thermal value weight distribution model, the system can obtain the weight parameters corresponding to each dimension in the multi-dimensional information of thermal value calculation, and obtain the weight parameter set. The weight parameter set can be used to calculate the target heat value to reflect the influence of different dimensional data on the heat value. Finally, according to the multi-dimensional information and weight parameter set calculated by the thermal value, the system can calculate the target thermal value through a certain calculation formula or algorithm, combining the data of each dimension and the corresponding weight parameter. In the above process, through the comprehensive consideration of multi-dimensional information and weight parameter set, the system can more accurately evaluate the popularity of different flight queries, facilitate dynamic adjustment of cache, and provide users with flight recommendation results that better meet their needs and preferences. By pre-training the thermal value weight distribution model, the system can automatically learn the correlation and weight distribution rules between data of different dimensions, thereby realizing intelligent thermal value calculation and improving the intelligence level of the system.

[0048] Optionally, based on the thermal value calculation multi-dimensional information and the weight parameter set, the target thermal value is determined, including: weighted summing the thermal value calculation multi-dimensional information and the weight parameter set to obtain a weighted summation result; based on the weighted summation result, determining the thermal values ​​corresponding to multiple flight query requests to obtain the target thermal value.

[0049] In an optional embodiment, the dynamic adjustment of the cache data of the airline query system can dynamically adjust the cache of flight information according to the heat value of the user query to improve the query efficiency of the system and the user experience. Specifically, the target heat value can be calculated based on the multi-dimensional information and the weight parameter set to determine which flight information should be cached. First, the multi-dimensional information and the weight parameter set can be calculated based on the thermal value, and the heat value of each flight query can be calculated based on the information of multiple dimensions. The influence of information of different dimensions on the heat value can be reasonably considered, and corresponding weight parameters can be set for each dimension to determine the importance of each dimension in calculating the heat value. Then the multi-dimensional information and the weight parameter set calculated by the thermal value can be weighted and summed to obtain the weighted summation result, that is, the information of each dimension is weighted according to its importance to the heat value, and the weighted values ​​of each dimension are added to obtain the final weighted summation result. This result can reflect the heat value of the flight query request under the current conditions. Finally, based on the weighted summation results, the heat values ​​corresponding to multiple flight query requests can be determined to obtain the target heat value, which can be used to dynamically adjust the system's cache data to improve the response speed and hit rate of user queries. By dynamically adjusting the cache data, the flight information that the user is interested in can be cached, which can reduce the query response time and improve the query efficiency of the system. By dynamically adjusting the cache data, the caching of infrequently queried flight information can be avoided, thereby saving the system's storage resources and improving the system's performance.

[0050] Optionally, adjusting the cache of the flight query system based on the target heat value to obtain target cache data includes: when the adjustment operation is a cache insertion operation or a cache replacement operation, screening multiple flight query requests based on the target heat value to obtain at least one flight query request to be stored; determining a flight query result to be stored corresponding to at least one flight query request to be stored based on a background query system of the flight query system; performing a cache insertion operation or a cache replacement operation on the cache of the flight query system based on the at least one flight query request to be stored and the corresponding flight query result to be stored to obtain target cache data; when the adjustment operation is a cache deletion operation, screening the cache of the flight query system based on the target heat value to obtain at least one flight query request to be deleted; determining a flight query result to be deleted corresponding to at least one flight query request to be deleted; performing a cache deletion operation on the cache of the flight query system based on the at least one flight query request to be deleted and the corresponding flight query result to be deleted to obtain target cache data.

[0051] In an optional embodiment, the dynamic adjustment of cache data of the flight query system can improve the performance of the system and the user experience. In this process, the adjustment operation of the cache based on the target heat value may include inserting a cache operation, replacing a cache operation and deleting a cache operation. Specifically, first, for the case of inserting a cache operation or replacing a cache operation, multiple flight query requests can be screened based on the target heat value to obtain at least one flight query request to be stored. Then, according to the flight query request to be stored, the corresponding flight query result to be stored can be determined based on the background system of the query system. Finally, according to the flight query request to be stored and the corresponding query result, an inserting cache operation or a replacing cache operation can be performed to obtain the target cache data. For the case of deleting a cache operation, the cache can be screened based on the target heat value to obtain at least one flight query request to be deleted in the cache. Then, the flight query result to be deleted corresponding to the flight query request to be deleted is determined in the cache. Finally, according to the flight query request to be deleted and the corresponding query result, a deleting cache operation can be performed to obtain the target cache data. In the above process, by dynamically adjusting the cache according to the target heat value, popular query results can be stored in the cache, reducing the response time of subsequent queries and improving the performance of the system. Since popular query results are stored in the cache, users can obtain the information they need more quickly, improving the user experience. By deleting infrequently used query results, cache space can be released, system resources can be saved, and the efficiency and stability of the system can be improved. The system performance can be improved, the user experience can be optimized, resources can be saved, and the flight query system can run more efficiently and stably.

[0052] Optionally, adjusting the cache of the flight query system based on the target heat value to obtain target cache data includes: determining the target application scenario at the current moment; when the target application scenario is the first application scenario, adjusting the cache of the flight query system based on the target heat value according to the first adjustment frequency and the first adjustment amplitude to obtain target cache data; when the target application scenario is the second application scenario, adjusting the cache of the flight query system based on the target heat value according to the second adjustment frequency and the second adjustment amplitude to obtain target cache data, wherein the real-time performance of the second application scenario is less than the real-time performance of the first application scenario, the second adjustment frequency is less than the first adjustment frequency, and the second adjustment amplitude is greater than the first adjustment amplitude.

[0053] In an optional embodiment, the cache of the flight query system can be adjusted based on the target heat value, and the performance and response speed of the system can be dynamically optimized according to different application scenarios and requirements. First, the target application scenario at the current moment can be determined. When the target application scenario is the first application scenario, the cache of the flight query system can be adjusted based on the target heat value according to the first adjustment frequency and the first adjustment amplitude to obtain the target cache data. The first adjustment frequency can be set according to the system load and user needs, and the first adjustment amplitude can be determined according to the change of the heat value. The storage amount of the cache data can be increased or decreased to improve the response speed and performance of the system. When the target application scenario is the second application scenario, the cache of the flight query system can be adjusted based on the target heat value according to the second adjustment frequency and the second adjustment amplitude to obtain the target cache data. The real-time performance of the second application scenario is less than that of the first application scenario, that is, the system can appropriately delay the update and adjustment operation of the data in the second application scenario to reduce the system load and resource consumption. The second adjustment frequency can be relatively low, and the second adjustment amplitude can be relatively large to reduce the frequent adjustment operation of the system and improve the stability and performance of the system. Through the above process, the cache data of the flight query system can be dynamically optimized according to different application scenarios and requirements, and the response speed and performance of the system can be improved. At the same time, by setting different adjustment frequencies and amplitudes, the real-time and stability of the system can be effectively balanced, the resource utilization and stability of the system can be optimized, and users can be provided with better flight query services.

[0054] The technical solution proposed in the present application is described below in combination with an optional embodiment. The present application proposes an adaptive dynamic decision flight query optimization system. Intelligent caching is a technology for improving data access performance, that is, frequently used data can be stored in a cache. In this way, when the system needs to access specific data during operation, it can be obtained from the cache at a faster speed, without having to spend time reading from a slower data source every time. The operation of the intelligent cache can determine which data should be cached and when to remove the data from the cache based on a series of rigorous and scientific strategies. The formulation of these strategies can be based on a variety of key factors, including the frequency of data access. For those data that are frequently accessed, they have a higher cache value to meet the system's requirements for response speed. Recent usage can also be a consideration. Data that has been used recently is relatively likely to be accessed again in the future, so it is more likely to be cached. In addition, the importance of the data can also be considered. For data that is related to the core functions of the system or has a significant impact on the user experience, even if the access frequency is not high, it can be cached first to ensure the stability and reliability of the system.

[0055] The intelligent caching technology proposed in this application has shown many significant advantages in practical applications. Its caching strategy introduces a data heat model, which can dynamically manage the access time with locality based on heat. For example, in the face of special events, whether it is a sudden increase in access volume due to emergencies or a decrease in temperature due to periodic factors, the intelligent cache can respond quickly to ensure the validity and availability of cached data. At the same time, it can also accurately adjust the data heat according to the dynamic access frequency, so as to fully and accurately reflect the access heat of ticket query data. In addition, the intelligent cache combines artificial intelligence models and expert models to further improve the cache hit rate and accuracy. By cooperating with the intelligent risk control system of the new aviation retail platform, the intelligent cache builds a high-quality data proprietary cache area. It can effectively reduce the response time of ticket queries and improve the overall performance of the new aviation retail system. In actual aviation business, by using intelligent caching technology, the system can reduce the number of visits to the data source and avoid delays and resource consumption caused by frequent access to the data source. This not only improves the overall performance of the system, but also improves the response speed, providing users with more efficient and convenient ticket inquiry services, and promoting the digital development and intelligent upgrading of aviation business.

[0056] Specifically, the introduction of intelligent caching can achieve the following goals: Improve the cache hit rate. Intelligent caching is committed to improving the cache hit rate by integrating artificial intelligence models and expert models. In an environment where data is frequently accessed, accurately predicting user needs and caching data that may be accessed in advance can reduce the number of times data is read from the data source. With its powerful data analysis and pattern recognition capabilities, combined with the professional experience of expert models, artificial intelligence models can more accurately determine which data should be cached, thereby significantly improving the cache hit rate and laying the foundation for the efficient operation of the system. It can build a crawler-specific cache. One of the important goals of intelligent caching is to build a crawler-specific cache area in conjunction with the risk control system. When faced with a large number of crawler requests, traditional systems often face great pressure. Intelligent caching works in conjunction with the risk control system to build a cache area specifically for crawlers, which can effectively deal with problems such as invalid empty queries and repeated queries caused by crawlers, while ensuring the query experience of normal users and maintaining the stability and security of the system. It can increase cache accuracy. In the flight price verification stage, intelligent caching uses artificial intelligence models and expert models to improve the flight price verification pass rate using cache. Accurate price verification is very important for airlines and passengers. By improving cache accuracy and ensuring that the flight price information in the cache is reliable, it can provide users with more accurate decision-making basis, and also help airlines optimize business processes and resource allocation.

[0057] The introduction of intelligent caching can improve system performance and reduce response time. Intelligent caching can improve overall system performance and reduce the response time of flight queries and packaged queries. By reducing access to data sources, effectively managing crawler requests, and improving cache accuracy, the system can respond to user queries more quickly and improve user experience. In the highly competitive aviation industry, efficient system performance can not only attract more users, but also improve the operating efficiency and market competitiveness of airlines. Dimensional model analysis of heat value calculation in intelligent caching systems. In intelligent caching systems, accurate calculation of heat values ​​is important for optimizing system performance and resource allocation. The calculation of heat values ​​involves multiple dimensional models, and these dimensions will be analyzed in detail below.

[0058] The dimension weight model in this application provides a general framework for heat value calculation. Different dimensions have different importance in heat value calculation. By assigning appropriate weights to each dimension, the actual heat of the data can be more accurately reflected. For example, for some specific application scenarios, the time dimension may have a higher weight, while in other scenarios, the passenger type dimension may be more critical. Frequency dimension model, the frequency dimension mainly counts the number of times the data is accessed. The higher the frequency of data access, the higher its heat value will be. This dimension directly reflects the popularity of the data and is one of the important bases for heat value calculation. By continuously monitoring the number of data accesses and adjusting the heat value according to a certain algorithm, it can be ensured that hot data can always be quickly cached and accessed. Time dimension model, the time dimension considers the timeliness of the data. Some data may have a high heat in a specific time period. For example, during holidays or tourist peak seasons, the heat of flight query data may increase significantly. At the same time, the heat of the data may gradually decrease over time. By analyzing the time distribution of data, the changing trend of heat value can be better grasped and dynamic adjustment can be achieved.

[0059] Location dimension model: The location dimension focuses on the association of data with specific geographic locations. There may be differences in flight demand and popularity in different regions. For example, flight query data for popular tourist cities may have high popularity. By considering location factors, more accurate cache services can be provided to users in different regions. Passenger type dimension model: The passenger type dimension calculates the popularity value based on the needs of different types of passengers. For example, business travelers and leisure travelers may have different preferences in flight selection, and the data popularity for different passenger types will also be different. Understanding the distribution of passenger types can optimize cache strategies and improve service quality. Cabin class dimension model: The cabin class dimension considers the popularity of flight data for different cabin classes. Premium cabins may be favored by specific user groups, while economy cabins may be more popular with general passengers. By analyzing the cabin class dimension, the needs of different users can be better met and the pertinence of cache can be improved. Itinerary type dimension model: The itinerary type dimension includes different itinerary types such as one-way, round-trip, and multi-trip. The flight query popularity of different itinerary types may be different. Calculating the popularity value based on the itinerary type can provide users with more personalized services. Event location dimension model: The event location dimension focuses on locations related to specific events. For example, flight query data for events such as large conferences and sports events may become more popular during the event. By analyzing the event location dimension, cache preparation can be done in advance to meet the needs of users during special periods. In summary, the heat value calculation of the intelligent cache system can more accurately reflect the actual heat of the data through comprehensive consideration of multiple dimensional models, providing strong support for the efficient operation and optimization of the system.

[0060] The access warming and periodic cooling functions of the intelligent cache of this application can be as follows: the access warming and periodic cooling functions can dynamically adjust the heat value according to the actual usage of the data, realize the optimal configuration of cache resources and improve the efficiency of data access. The heat value management mechanism of the intelligent cache, the heat value management of the intelligent cache is the basis for realizing access warming and periodic cooling. When the intelligent cache service initiates a call to the inference service application program interface, the heat value of the data item is calculated. This process integrates a dynamic heat adjustment mechanism. First, based on the initial heat evaluation returned by the inference service, combined with the recent query frequency statistics of the data item, a refined heat value adjustment strategy is implemented. This strategy follows the principle of dynamic feedback and can adjust the heat value in time according to the actual usage of the data item. The implementation of the access warming function, the access warming function means that when the query frequency of a data item increases significantly in the near future, the intelligent cache will automatically trigger the heat value floating operation to reflect its enhanced activity and importance. The implementation of this function follows the principle of dynamic feedback. By monitoring the changes in the query frequency of the data item, the heat value is adjusted in time to ensure that the hot data can be cached and accessed faster. For example, during the peak flight booking period, the query frequency of some popular routes will increase significantly. At this time, the intelligent cache system will automatically trigger the heat value floating operation, cache the data items of these popular routes to a faster storage medium, and improve data access efficiency. The realization of the periodic cooling function can mean that if the query frequency of a data item decreases over time, the intelligent cache will adjust its heat value accordingly to achieve a reasonable adjustment of resource allocation. The implementation of this function also follows the principle of dynamic feedback. By monitoring the changes in the query frequency of data items, the heat value is adjusted in time to avoid wasting cache resources. For example, during the off-season, the query frequency of some routes will decrease. At this time, the intelligent cache system will automatically lower the heat value of the data items of these routes, release cache resources, and make room for other popular data.

[0061] The importance of the heat value floating configuration table, the heat value floating configuration table is the support for the intelligent cache to realize the access heating and periodic cooling functions. This configuration table not only defines the specific rules for adjusting the heat value, including the trigger conditions and adjustment range of floating and lowering, but also ensures the high configurability and flexibility of the entire heat evaluation and adjustment process to adapt to the specific needs of different application scenarios. For example, in some scenarios with high real-time requirements, smaller trigger conditions and larger adjustment ranges can be set to ensure that popular data can be cached and accessed in a timely manner. In some scenarios with high requirements for resource utilization efficiency, larger trigger conditions and smaller adjustment ranges can be set to avoid resource consumption caused by frequent heat value adjustments.

[0062] The access warming and periodic cooling functions of smart cache have significant advantages, which can improve the cache hit rate, reduce the repeated acquisition of data, and thus improve the response speed of the system. At the same time, by optimizing the utilization of cache resources, the operating cost of the system is reduced. In the future, with the continuous growth of data volume and the increasing diversification of application requirements, this core function of smart cache will be widely used in more fields, such as e-commerce, logistics management, financial services, etc., making greater contributions to the efficient operation of various systems and the improvement of user experience. The access warming and periodic cooling functions of smart cache are one of its core functions. They can dynamically adjust the heat value according to the actual use of data, realize the optimal configuration of cache resources and improve data access efficiency. By calling the inference service application program interface and adjusting the heat value in combination with query frequency statistics, smart cache can capture and respond to data heat changes keenly and immediately, and promote the continuous optimization and efficient management of cache content. The introduction of the floating configuration table of heat value further enhances the configurability and flexibility of smart cache, enabling it to adapt to the specific needs of different application scenarios. In the future development of information technology, the access warming and periodic cooling functions of smart cache will have broad application prospects. Improve system performance. In aviation business, system performance is more important. The intelligent cache system greatly reduces the repeated acquisition of data by caching commonly used data. When passengers make flight inquiries and reservations, the system does not need to obtain data from the original data source every time, but can directly extract it from the cache quickly. This significantly improves the response speed of the system, allowing passengers to get the required information in a shorter time, providing strong support for efficient travel planning. In response to high-concurrency access, during peak flight booking periods or special periods, the system often faces greater access pressure. At this time, the intelligent cache system can store a large amount of popular data to alleviate the system's access pressure on the host. Even in high-concurrency situations, the stability of the system can be ensured to avoid crashes or slow responses, thereby ensuring the continuity of aviation business.

[0063] The intelligent cache proposed in this application can reduce the amount of data transmission, and the process of caching data actually reduces the frequent access to the host system. That is, in terms of data transmission, a large amount of bandwidth resources are saved. At the same time, the load on the server is also reduced to avoid the performance degradation of the server due to excessive access. By reducing the amount of data transmission, the intelligent cache system provides a more efficient operating environment for the information technology infrastructure of airlines. Improve user experience. For passengers, fast system response is an important manifestation of good service. The fast response brought by the intelligent cache system can make passengers more smooth when querying and booking flights, reduce waiting time, and enjoy better service. This efficient experience will improve passenger satisfaction and enhance their trust in airlines. Support real-time data updates, flight information is constantly changing, and passengers need to obtain flight dynamics. The intelligent cache system has the ability to update the data in the cache in a timely manner to ensure that passengers can always obtain flight information. Whether it is flight delays, cancellations or route adjustments, passengers can know in time and provide accurate basis for travel decisions.

[0064] The intelligent cache proposed in this application can adapt to route changes, and different routes have different needs and popularity. The intelligent cache system can automatically adjust the cache strategy according to these changes, increase the amount of cached data and update frequency for popular routes, and dynamically adjust for unpopular routes. This flexibility enables the system to better adapt to market changes and improve resource utilization efficiency. Optimize data management. The cache system plays a positive role in data management. Data can be sorted and classified to make data acquisition and use more efficient. Through reasonable cache strategies, data can be stored and called in an orderly manner, providing convenience for airlines' data analysis and decision-making. Reduce operating costs. From the perspective of airlines, reducing data transmission and server resource consumption means reducing operating costs. The intelligent cache system reduces bandwidth costs and server maintenance costs by optimizing data access and transmission. This enables airlines to effectively control costs and improve economic benefits while ensuring service quality. In short, the intelligent cache system has significant advantages in improving system performance, coping with high concurrent access, reducing data transmission volume, improving user experience, supporting real-time data updates, adapting to route changes, optimizing data management and reducing operating costs, and provides strong technical support for the business development of airlines.

[0065] Figure 2 FIG. 1 is a schematic diagram of a model training business architecture in processing flight query data according to an optional embodiment of the present invention, such as Figure 2As shown in the figure, the model training business architecture includes model training to data warehouse, that is, the machine learning platform calls the data warehouse to obtain query condition data; data warehouse to data collection log system; model training to model release, that is, after model training, the model is released; model training and model release constitute the machine learning platform. Among them, model training includes intelligent caching, which enables the machine learning platform to obtain dimension models and the machine learning platform to obtain heat calculation algorithms. The heat value calculation includes dimension weight model, frequency dimension model, time dimension model, location dimension model, passenger type dimension model, cabin class dimension model, itinerary type dimension model and event location dimension model. The heat calculation algorithm includes model deployment, model training and model analysis.

[0066] Figure 3 is a schematic diagram of a model training technology framework in processing flight query data according to an optional embodiment of the present invention, such as Figure 3 As shown, in the model training technology framework, machine learning can obtain basic data and cache heat features, and store the results in the product library (technology platform), where basic data can include query data collection (technology platform / airline tracking points) and query data storage (data warehouse), cache heat features can include heat feature dimensions (frequency dimension / time dimension / location dimension, etc.) and heat value algorithm, and machine learning includes model training algorithm (ML Flow) and the heat model generated by training.

[0067] The above-mentioned model training algorithm, the machine learning process (ML Flow) can be an open source platform for managing machine learning projects, providing functions such as tracking experiments, organizing codes, collaborating and deploying models.

[0068] Figure 4 is a schematic diagram of a model runtime technical architecture in processing an optional flight query data according to an embodiment of the present invention, such as Figure 4 As shown, the technical architecture of the model runtime includes interactive intelligent cache services, cache, streaming data platform, product library (technical platform), reasoning service, old aviation retail platform OTA_AirLowFareSearchRQ, Kafkatools, new aviation retail platform and host system. Among them, the new aviation retail platform includes UX, API gateway and new aviation retail platform. The intelligent cache service includes cache maintenance, temperature increase or decrease, expert strategy rule configuration, and combination of ticket data and temperature value. The reasoning service includes real-time operation of the model.

[0069] The above-mentioned Kafka tools can be a set of tools for managing and operating a streaming data platform (Kafka) message middleware, including a series of command line tools and graphical user interface tools for monitoring, maintaining, configuring, and testing a streaming data platform (Kafka) cluster.

[0070] The above-mentioned User Experience (UX) can refer to the overall experience that users get when interacting with products or services. User experience design aims to improve user satisfaction and loyalty to products or services, thereby increasing user usage frequency and recommendation rate. User experience design includes user interface design, user interaction design, user research and other aspects.

[0071] The above-mentioned Application Programming Interface (API) gateway can be a server that acts as an entry point for the API service, acting as a facade for the API service, receiving requests from clients and routing them to the corresponding backend services. Through the API gateway, requests can be authenticated, authorized, monitored, cached, converted, and routed.

[0072] Figure 5 FIG. 1 is a schematic diagram of an optional intelligent cache execution logic in processing flight query data according to an embodiment of the present invention, such as Figure 5 As shown, the intelligent cache execution logic includes cache data maintenance, real-time heat value calculation, cache, streaming data platform, inference service, cache heat value management and expert strategy rule setting, wherein cache data maintenance includes inserting cache, deleting cache and replacing cache, real-time heat value calculation includes Kafka logic processing, intelligent cache model service call and ticket data and heat data aggregation, cache heat value management includes access warming function and periodic cooling function, expert strategy rule setting includes heat value and TTL relationship setting and other strategy settings.

[0073] The above-mentioned Time To Live (TTL) relationship setting can be a mechanism for limiting the time or number of hops for a data packet to be transmitted in the network, aiming to prevent the data packet from circulating infinitely in the network. By setting the TTL value, the transmission range and life cycle of the data packet in the network can be controlled.

[0074] Figure 6 is a schematic diagram of a model inference service in processing an optional flight query data according to an embodiment of the present invention, such as Figure 6As shown, the model reasoning service includes the interactive model reasoning service scaffolding, model files, API calls, API result returns, monitoring / logs, model warehouses, business scenario application services (intelligent risk control, intelligent caching, etc.) and technical platforms. The model reasoning service scaffolding can include health and API Endpoint, and the technical platform can include monitoring and logs.

[0075] The above API Endpoint can refer to the terminal point of the application program interface, which can also be called the API end point. It can be a uniform resource locator defined in the application program interface, which is used to access specific functions or resources of the application program interface. APIEndpoint can be sent to a specific path on the server by a communication protocol (HTTP) request to call a specific function of the application program interface. The full name in Chinese is application program interface endpoint.

[0076] According to another aspect of an embodiment of the present application, a device for processing flight query data is also provided. The device can execute the method for processing flight query data of the above embodiment. The specific implementation method and preferred application scenario are the same as those of the above embodiment and will not be repeated here.

[0077] Figure 7 is a schematic diagram of a flight query data processing device according to an embodiment of the present application, such as Figure 7 As shown, the device includes the following: an acquisition module 702 , a determination module 704 and an adjustment module 706 .

[0078] Among them, the acquisition module is used to obtain the flight query information of the user in the preset historical segment and the dynamic impact dimension information at the current moment, wherein the flight query information includes multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests, and the dynamic impact dimension information includes at least one of the following: time dimension information and event dimension information, the time dimension information is used to characterize the time dimension that has an impact on the flight query popularity, and the event dimension information is used to characterize the event dimension that has an impact on the flight query popularity; the determination module is used to determine the target heat values ​​of the multiple flight query requests based on the flight query information and the dynamic impact dimension information; the adjustment module is used to adjust the cache of the flight query system based on the target heat value to obtain the target cache data, wherein the adjustment operation includes at least one of the following: insert cache operation, replace cache operation and delete cache operation, and the target cache data is used to respond to the target flight query request initiated by the user and generate the target flight query result based on the target flight query request.

[0079] Among them, the determination module is also used to determine the query dimension information of any flight query request based on the flight query information, wherein the query dimension information includes at least one of the following: query frequency information, query destination information and user type information; based on the query dimension information and dynamic impact dimension information, determine the thermal value calculation multi-dimensional information; based on the thermal value calculation multi-dimensional information, determine the target heat value.

[0080] Among them, the determination module is also used to determine the weight parameter set corresponding to the multi-dimensional information of thermal value calculation based on the pre-trained thermal value weight allocation model, wherein the pre-trained thermal value calculation model is used to represent the pre-trained machine learning model for thermal value weight allocation; based on the multi-dimensional information of thermal value calculation and the weight parameter set, the target heat value is determined.

[0081] Among them, the determination module is also used to perform weighted summation on the multi-dimensional information of thermal value calculation and the weight parameter set to obtain a weighted summation result; based on the weighted summation result, the thermal values ​​corresponding to multiple flight query requests are determined to obtain the target thermal value.

[0082] Among them, the adjustment module is also used to, when the adjustment operation is an insert cache operation or a replace cache operation, screen multiple flight query requests based on the target heat value to obtain at least one flight query request to be stored; determine the flight query result to be stored corresponding to the at least one flight query request to be stored based on the background query system of the flight query system; based on the at least one flight query request to be stored and the corresponding flight query result to be stored, perform an insert cache operation or a replace cache operation on the cache of the flight query system to obtain target cache data; when the adjustment operation is a delete cache operation, screen the cache of the flight query system based on the target heat value to obtain at least one flight query request to be deleted; determine the flight query result to be deleted corresponding to the at least one flight query request to be deleted; based on the at least one flight query request to be deleted and the corresponding flight query result to be deleted, perform a delete cache operation on the cache of the flight query system to obtain target cache data.

[0083] Among them, the adjustment module is also used to determine the target application scenario at the current moment; when the target application scenario is the first application scenario, according to the first adjustment frequency and the first adjustment amplitude, the cache of the flight query system is adjusted based on the target heat value to obtain target cache data; when the target application scenario is the second application scenario, according to the second adjustment frequency and the second adjustment amplitude, the cache of the flight query system is adjusted based on the target heat value to obtain target cache data, wherein the real-time performance of the second application scenario is less than the real-time performance of the first application scenario, the second adjustment frequency is less than the first adjustment frequency, and the second adjustment amplitude is greater than the first adjustment amplitude.

[0084] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0085] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0086] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0087] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0088] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0089] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0091] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0092] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0093] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0094] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for processing flight query data, characterized in that: include: Acquire flight query information of users in a preset historical segment and dynamic impact dimension information at the current moment, wherein the flight query information includes multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests, and the dynamic impact dimension information includes at least one of the following: time dimension information and event dimension information, wherein the time dimension information is used to characterize the time dimension that has an impact on the flight query popularity, and the event dimension information is used to characterize the event dimension that has an impact on the flight query popularity; Determining target heat values ​​of the multiple flight query requests based on the flight query information and the dynamic impact dimension information; An adjustment operation is performed on the cache of the flight query system based on the target heat value to obtain target cache data, wherein the adjustment operation includes at least one of the following: an insert cache operation, a replace cache operation, and a delete cache operation, and the target cache data is used to respond to a target flight query request initiated by a user and generate a target flight query result based on the target flight query request.

2. The method for processing flight query data according to claim 1, characterized in that: Determining target heat values ​​of the plurality of flight query requests based on the flight query information and the dynamic impact dimension information includes: Based on the flight query information, determining query dimension information of any flight query request, wherein the query dimension information includes at least one of the following: query frequency information, query destination information, and user type information; Determine the multi-dimensional information of thermal value calculation based on the query dimension information and the dynamic impact dimension information; The target heat value is determined based on the thermal value calculation multi-dimensional information.

3. The method for processing flight query data according to claim 2, characterized in that: Calculating multi-dimensional information based on the thermal value to determine the target thermal value includes: Determine a weight parameter set corresponding to the multi-dimensional information of thermal value calculation based on a pre-trained thermal value weight allocation model, wherein the pre-trained thermal value calculation model is used to represent a pre-trained machine learning model for performing thermal value weight allocation; The target heat value is determined based on the thermal value calculation multi-dimensional information and the weight parameter set.

4. The method for processing flight query data according to claim 3, characterized in that: Calculating the multi-dimensional information of the thermal value and the weight parameter set to determine the target thermal value includes: Performing weighted summation on the multi-dimensional information of thermal value calculation and the weight parameter set to obtain a weighted summation result; Based on the weighted sum result, the popularity values ​​corresponding to the multiple flight query requests are determined to obtain the target popularity value.

5. The method for processing flight query data according to claim 1, characterized in that: Based on the target heat value, the cache of the flight query system is adjusted to obtain target cache data, including: In the case where the adjustment operation is the cache insertion operation or the cache replacement operation, the multiple flight query requests are screened based on the target heat value to obtain at least one flight query request to be stored; based on the background query system of the flight query system, a flight query result to be stored corresponding to the at least one flight query request to be stored is determined; based on the at least one flight query request to be stored and the corresponding flight query result to be stored, the cache of the flight query system is subjected to the cache insertion operation or the cache replacement operation to obtain the target cache data; In the case where the adjustment operation is the cache deletion operation, the cache of the flight query system is screened based on the target heat value to obtain at least one flight query request to be deleted; the flight query result to be deleted corresponding to the at least one flight query request to be deleted is determined; based on the at least one flight query request to be deleted and the corresponding flight query result to be deleted, the cache deletion operation is performed on the cache of the flight query system to obtain the target cache data.

6. The method for processing flight query data according to claim 1, characterized in that: Based on the target heat value, the cache of the flight query system is adjusted to obtain target cache data, including: Determine the target application scenario at the current moment; When the target application scenario is the first application scenario, the adjustment operation is performed on the cache of the flight query system based on the target heat value according to the first adjustment frequency and the first adjustment amplitude to obtain the target cache data; When the target application scenario is the second application scenario, the adjustment operation is performed on the cache of the flight query system based on the target heat value according to a second adjustment frequency and a second adjustment amplitude to obtain the target cache data, wherein the real-time performance of the second application scenario is less than that of the first application scenario, the second adjustment frequency is less than the first adjustment frequency, and the second adjustment amplitude is greater than the first adjustment amplitude.

7. A flight query data processing device, characterized in that: include: An acquisition module is used to acquire flight query information of users in a preset historical segment and dynamic impact dimension information at the current moment, wherein the flight query information includes multiple flight query requests and multiple flight query results corresponding to the multiple flight query requests, and the dynamic impact dimension information includes at least one of the following: time dimension information and event dimension information, wherein the time dimension information is used to characterize the time dimension that has an impact on the flight query popularity, and the event dimension information is used to characterize the event dimension that has an impact on the flight query popularity; A determination module, configured to determine target heat values ​​of the plurality of flight query requests based on the flight query information and the dynamic impact dimension information; The adjustment module is used to adjust the cache of the flight query system based on the target heat value to obtain target cache data, wherein the adjustment operation includes at least one of the following: insert cache operation, replace cache operation and delete cache operation, and the target cache data is used to respond to the target flight query request initiated by the user and generate the target flight query result based on the target flight query request.

8. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program executes the flight query data processing method according to any one of claims 1 to 6 when running.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the flight query data processing method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for processing flight query data according to any one of claims 1 to 6.

Images