Aviation travel related service query method, device and equipment

Abstract

The invention provides an air travel related service query method, device and equipment, and relates to the technical field of data processing, and the method comprises the steps: obtaining a query request about a target air travel related service sent by a passenger; querying the first cache data according to the query request; the first cache data comprises query results of a plurality of air travel related service query requests; if the query request does not hit the first cache data, performing other data query processing on the query request to obtain a target query result of the query request; feeding back the target query result to the traveler; and using a first prediction model to predict whether the target query result needs to be cached and the caching duration of the target query result, indicating that the target query result needs to be cached according to the prediction result, caching the target query result into first cache data, and setting the caching duration of the target query result. The query efficiency and the query result accuracy of the air travel related service can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and equipment for querying air travel related services. Background Art

[0002] In order to facilitate passengers' travel, airlines work with external suppliers to provide passengers with travel-related services, such as baggage port-to-door service and airport pick-up service. Among them, baggage port-to-door service means that after passengers arrive at the destination airport by plane, they can leave the airport directly. Airport staff will collect the passengers' luggage based on the passenger information, and then deliver the luggage to the delivery location designated by the passenger through the baggage port-to-door service agency for luggage delivery.

[0003] Since airlines work with external suppliers to provide travel-related services to passengers, when passengers query travel-related services, they often involve data maintained in other systems of the airlines other than the travel-related service system and data maintained by external suppliers. In the current travel-related service query method, when the travel-related service system needs to use data from an external system, it obtains the required data by calling the interface of the corresponding system.

[0004] However, when the number of passengers to be queried is large, the current air travel related service query method has the problems of low air travel related service query efficiency and low query result accuracy. Summary of the invention

[0005] In order to solve the problems of low efficiency and low accuracy of query results of air travel related services in the prior art, the present invention provides an air travel related service query method, device and equipment.

[0006] The technical solution of the present invention is as follows:

[0007] The present invention provides a method for querying air travel related services, comprising:

[0008] Obtain inquiry requests sent by passengers regarding target travel-related services;

[0009] According to the query request, query first cache data; the first cache data includes query results of multiple air travel related service query requests;

[0010] If the query request does not hit the first cache data, performing other data query processing on the query request to obtain the target query result of the query request;

[0011] Feedback the target query result to the passenger;

[0012] Input the query request into a first prediction model to obtain a first prediction result output by the first prediction model, wherein the first prediction result is used to indicate whether to cache the target query result and, when the target query result needs to be cached, the cache duration corresponding to the target query result; from the time when the target query result is cached, the target query result will be deleted from the first cache data after the corresponding cache duration;

[0013] If the first prediction result indicates that the target query result needs to be cached, the target query result is cached in the first cache data, and a cache duration of the target query result is set.

[0014] The present invention also provides an air travel related service query device, comprising:

[0015] The acquisition module is used to obtain the query request sent by the passenger regarding the target air travel related service;

[0016] A first query module, configured to query first cache data according to the query request; the first cache data includes query results of multiple air travel related service query requests;

[0017] A second query module, configured to perform other data query processing on the query request if the query request does not hit the first cache data, so as to obtain a target query result of the query request;

[0018] A feedback module, used for feeding back the target query result to the passenger;

[0019] A first prediction module, used for inputting the query request into a first prediction model, obtaining a first prediction result output by the first prediction model, wherein the first prediction result is used to indicate whether to cache the target query result, and, when the target query result needs to be cached, the cache duration corresponding to the target query result; from the time when the target query result is cached, the target query result will be deleted from the first cache data after the corresponding cache duration;

[0020] The first cache module is used to cache the target query result into the first cache data and set a cache duration of the target query result if the first prediction result indicates that the target query result needs to be cached.

[0021] The present invention also provides an air travel related service query device, comprising:

[0022] at least one processor; and,

[0023] a memory communicatively connected to the at least one processor; wherein,

[0024] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the air travel related service query method as described above.

[0025] The present invention adopts the above technical solution and has the following beneficial effects:

[0026] A method for querying air travel related services, by pre-caching the query results of multiple air travel related service query requests, and subsequently, when a query request for a target air travel related service sent by a passenger is obtained, first query the first cache data (i.e., the pre-cached query result), if there is a query result of the corresponding query request that is the same as the current query request in the first cache data, then the query result will hit the current query request, and the query result can be directly returned without calling an external system interface to obtain relevant data, so as to generate the query result of the current query request according to the relevant data. Since the process of calling an external system interface to obtain relevant data is relatively time-consuming, and when the number of query requests is large, it is easy to have a call error, therefore, the present invention can improve the query efficiency and query result accuracy of air travel related services. Furthermore, when the query request does not hit the first cache data, after obtaining the target query result of the query request, the first prediction model is used to predict whether the target query result needs to be cached, and when the first prediction result indicates that the target query result needs to be cached, the target query result is cached in the first cache data, and the cache duration of the target query result is set. In this way, the accuracy of the cached data is improved and the amount of cached data is reduced, so that the present invention can shorten the time consumed in querying the cache while taking into account the cache hit rate, which further improves the query efficiency of the air travel related services of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0028] Figure 1 It is a flow chart of a method for querying air travel related services provided by an embodiment of the present invention;

[0029] Figure 2 It is a structural schematic diagram of an air travel related service query device provided by an embodiment of the present invention;

[0030] Figure 3 It is a structural schematic diagram of an air travel related service query device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0032] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0033] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0034] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0035] In order to make the technical solution of the present invention easier to understand, some professional terms that may be involved in the present invention are explained below.

[0036] Cache: is a technology used to temporarily store data. Its main purpose is to speed up data reading and thus improve the overall performance of the system.

[0037] Master data: data shared between systems.

[0038] Binary classification model: A binary classification problem refers to a classification task in which the model needs to classify the input data into two different categories or two mutually exclusive labels. Usually expressed as one of two categories, such as "positive" or "negative", "yes" or "no", etc.

[0039] In order to facilitate passengers' travel, airlines work with external suppliers to provide passengers with travel-related services, such as baggage port-to-door service and airport pick-up service. Among them, baggage port-to-door service means that after passengers arrive at the destination airport by plane, they can leave the airport directly. Airport staff will collect the passengers' luggage based on the passenger information, and then deliver the luggage to the delivery location designated by the passenger through the baggage port-to-door service agency for luggage delivery.

[0040] Since airlines work with external suppliers to provide travel-related services to passengers, when passengers inquire about travel-related services, they often involve data maintained in other systems of the airlines other than the travel-related service system and data maintained by external suppliers. In the current travel-related service query method, when the travel-related service system needs to use data from an external system, it obtains the required data by calling the API (Application Program Interface) of the corresponding system.

[0041] However, when the number of passengers is large, the current air travel related service query method needs to query the database of the external supplier with high concurrency. In this case, database connection errors are prone to occur. In addition, when querying the database of the external supplier with high concurrency, one request often needs to call multiple interfaces of the external supplier, and the interface return time is long. At the same time, it puts pressure on the supplier system and is prone to system errors. In addition, each query request often needs to call the airline's master data system to obtain the master data, and call LocationAPI (Global Location Information Interface) to obtain the location data in the airline's location service system. For example, the query request for the baggage port to door service contains the fields: origin and destination. It is necessary to call LocationAPI to obtain the relevant location data to verify the two fields of origin and destination in the query request. It can be seen that the current air travel related service query method has the problem of low efficiency of air travel related service query because each query request needs to call the data in the external system. Moreover, when the number of passengers is large, database connection errors and system errors are prone to occur, which makes the current air travel related service query method also have the problem of low accuracy of air travel related service query results.

[0042] Based on this, in order to improve the query efficiency and query result accuracy of air travel related services, the present invention provides an air travel related service query method, device and equipment. The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0043] Figure 1 1 is a flow chart of a method for querying air travel related services provided by an embodiment of the present invention. The method for querying air travel related services can be executed by an air travel related service system. Figure 1As shown, the air travel related service query method includes:

[0044] Step 101: Obtain a query request sent by a passenger regarding a target air travel related service.

[0045] Specifically, the query request includes but is not limited to the following attributes: sales start date, sales end date, travel start date and travel end date, etc. The attributes of the query request can be set according to specific air travel related services.

[0046] In a specific example, the target air travel related service is the baggage port to door service, and the query request includes: origin, destination, flight number and flight departure time (or estimated arrival time). For example, the query request indicates to query the baggage port to door service of CA1883 (flight number) from Beijing (origin) to Shanghai (destination) on December 1, 2023 (flight departure time).

[0047] Step 102: query first cache data according to the query request; the first cache data includes query results of multiple air travel related service query requests.

[0048] Specifically, the present invention pre-caches the query results of multiple air travel related service query requests, so that when the same query request is obtained later, the corresponding query result can be directly obtained from the first cache data.

[0049] For example, Zhang San inquired about a CA1234 (flight number) flight from Beijing (origin) to Shanghai (destination), with an estimated arrival time of 14:30 on December 1, 2023, for baggage port-to-door service. This is the first time that the air travel-related service system has obtained the query request. Therefore, after obtaining the query result of the query request, the air travel-related service system can cache the query result. Subsequently, when Li Si inquires about the same CA1234 flight from Beijing to Shanghai, with an estimated arrival time of 14:30 on December 1, 2023, for baggage port-to-door service, he uses Li Si's query request to query the first cached data. Li Si's query request will hit the query result of Zhang San's query request. Therefore, the air travel-related service system will take Zhang San's query result from the cache and return it directly to Li Si.

[0050] In addition, before querying the first cache data according to the query request, it is also possible to first determine whether the cache function of the air travel-related service system for the first cache data is in the on stage. If the cache function of the air travel-related service system for the first cache data is in the on stage, the first cache data is queried according to the query request. If the cache function of the air travel-related service system for the first cache data is in the off stage, other data query processing is performed on the query request to obtain the target query result of the query request.

[0051] Step 103: Determine whether the query request hits the first cache data. If the query request hits the first cache data, execute step 104; if the query request does not hit the first cache data, execute step 105.

[0052] Step 104: Determine that the target query result of the query request is the query result in the first cache data that hits the query request.

[0053] Step 105: Perform other data query processing on the query request to obtain the target query result of the query request.

[0054] Step 106: Feedback the target query result to the passenger.

[0055] Step 107: When the query request does not hit the first cached data, the query request is input into the first prediction model to obtain a first prediction result output by the first prediction model, and the first prediction result is used to indicate whether to cache the target query result and, when the target query result needs to be cached, the cache duration corresponding to the target query result; from the time the target query result is cached, the target query result will be deleted from the first cached data after the corresponding cache duration.

[0056] Specifically, the prediction model involved in the present invention includes a binary classification model for predicting whether to cache corresponding results and a regression model for predicting the corresponding cache duration. The input of the prediction model is a query condition, and the output of the prediction model is whether to cache the query result of the query condition, and, when the query result of the query condition needs to be cached, the corresponding cache duration.

[0057] Based on this, when training the first prediction model, first, a certain number of real travel-related service query requests in the production environment are collected, and each travel-related service query request is manually labeled. The specific labeling operations include whether the query results of the travel-related service query request need to be cached, and if the query results of the travel-related service query request need to be cached, label the cache duration of the query result.

[0058] It should be noted that data labelers can use statistical methods to analyze each travel-related service query request, and set a reasonable cache duration by analyzing the booking success rate. For example, after analyzing a large amount of log data, it can be determined which data is fixed and which data is frequently accessed and changes frequently. For fixed data, a longer cache duration is set, and for frequently accessed and frequently changing data, a shorter cache duration is set.

[0059] Next, the annotated flight-related service query requests are split into a training data set and a verification data set, and the preset model is iteratively trained using the training data set and the verification data set to obtain a first prediction model. The iterative training process includes:

[0060] (1) The annotated air travel-related service query request is input into the data preprocessing layer of the preset model to obtain a feature encoding vector of the air travel-related service query request.

[0061] Among them, the preset model can be a fully connected neural network with 64 input neurons, which uses the ReLU function as the activation function of the input layer and the hidden layer to increase the nonlinear expression ability of the model, and the output layer uses the Sigmoid activation function to predict the results of the binary classification problem, using binary cross entropy as the loss function, and the stochastic gradient descent function as the back propagation optimization function.

[0062] (2) Input the feature coding vector into the data coding layer of the preset model to obtain a feature vector coding set of the air travel related service query request. The data coding layer is used to perform correlation analysis between the feature coding vectors.

[0063] (3) The feature vector encoding set is input into the input layer of the preset model, and the first prediction result of the air travel related service query request is obtained according to the initialization weights of the neurons in each layer, wherein each layer of neurons in the neural network is used to perform correlation analysis between the feature encoding vector and its corresponding first prediction result.

[0064] (4) Using the first prediction result and the label carried by the air travel-related service query request (the result of the aforementioned manual labeling), calculate the prediction result loss value of the preset model.

[0065] Specifically, it is known that the first prediction result is used to indicate whether to cache the query result of the air travel related service query request, and, when the query result needs to be cached, the cache duration corresponding to the query result. In this embodiment, for the prediction result of whether to cache the query result of the air travel related service query request, the loss function used is the cross entropy loss function, which is as follows:

[0066] H （ p , q ） =− sum i = 1 N [ y i log( p i ) + ( 1 − y i )log( 1 − p i ) ] ...... (1)

[0067] Among them, p represents the true distribution, which usually represents the correct or target probability distribution in classification problems; q represents the fitted distribution, which is the probability distribution predicted by the model, that is, the predicted probability of the model for each category; y i represents the first true label (0 or 1); p i Represents the probability of the model predicting the positive class; N represents the total number of training samples.

[0068] By minimizing the cross entropy loss function, the probability distribution of the model's predicted values ​​can be gradually approached to the true probability distribution, thereby improving the accuracy of the model's prediction results.

[0069] Secondly, for the prediction result of the cache duration corresponding to the query result when the query result needs to be cached, the loss function used is the mean square error loss function, as follows:

[0070] ...... (2)

[0071] Where N is the total number of training samples; Y i Indicates the second real label (cache duration); Indicates that it corresponds to Y i The model prediction result (the cache duration predicted by the model).

[0072] (5) According to the prediction result loss value, the optimization parameters are selected for back propagation to adjust the parameter values ​​of each neuron.

[0073] (6) Repeat the above iterative process until the training stop condition is reached, and then export the first prediction model obtained through training and deploy it to provide external services.

[0074] It should be noted that the training method of the first prediction model is a prior art. Therefore, only a brief introduction to the training process of the first prediction model is given here. Those skilled in the art can easily train the first prediction model of the present application according to the above model training process.

[0075] Step 108: If the first prediction result indicates that the target query result needs to be cached, the target query result is cached in the first cache data, and a cache duration of the target query result is set.

[0076] The embodiment of the present invention adopts the above technical solution, a method for querying air travel related services, by pre-caching the query results of multiple air travel related service query requests, and subsequently, when obtaining a query request for a target air travel related service sent by a passenger, first query the first cache data (i.e., the pre-cached query result), if there is a query result of the corresponding query request that is the same as the current query request in the first cache data, then the query result will hit the current query request, and the query result can be directly returned without calling an external system interface to obtain relevant data, so as to generate the query result of the current query request based on the relevant data. Since the process of calling an external system interface to obtain relevant data is relatively time-consuming, and when the number of query requests is large, call errors are prone to occur, therefore, the present invention can improve the query efficiency and query result accuracy of air travel related services, and prevent network crawlers from causing performance impact on the system.

[0077] And, when the query request does not hit the first cache data, after obtaining the target query result of the query request, the first prediction model is used to predict whether the target query result needs to be cached, and when the first prediction result indicates that the target query result needs to be cached, the target query result is cached in the first cache data, and the cache duration of the target query result is set, so that the accuracy of the cached data is improved, the amount of cached data is reduced, so that the present invention can shorten the time consumed when querying the cache, while taking into account the cache hit rate, which further improves the query efficiency of the air travel related services of the present invention. Moreover, since the amount of cached data is reduced, the present invention also reduces the cache pressure of the system.

[0078] As can be seen from the foregoing, when the query request does not hit the first cache data, it is necessary to perform other data query processing on the query request to obtain the target query result of the query request. Here, the traditional method can be used to perform data query processing on the query request. In addition, in order to further improve the query efficiency and query result accuracy of air travel related services, some data required for the data query processing process can also be pre-cached so that when other data query processing is performed on the query request, the required data can be directly obtained from the cache.

[0079] Based on this, in the embodiment of the present invention, other data query processing is performed on the query request to obtain the target query result of the query request, which may specifically include:

[0080] (1) querying the second cache data according to the query request; the second cache data includes basic product information of multiple air travel related service query requests, and the basic product information includes product identification information, product usage requirement information, product sales requirement information and supplier information.

[0081] Specifically, product identification information may include: product ID (Identity) and product code; product usage requirements information may include: applicable flight type, applicable airport, travel start date and travel end date (the time period between the travel start date and the travel end date is the validity period); product sales requirements information includes: maximum purchase quantity, sales start date and sales end date; supplier information includes: supplier code, supplier name, supplier address, supplier city code and supplier country code. In addition, basic product information may also include: inventory type, product description, sub-product code and multi-language configuration information.

[0082] In a specific example, the basic product information query result of a query request for baggage port to door service is as follows:

[0083] Product code: ABC123456789; Inventory type: NONE-Unlimited; Maximum purchase quantity: 2; Product description: Baggage port to door service description; Product ID: 1234; Flight type: ALL-Unlimited; Sub-product code: ABCD-EFGH-IJKL; Applicable airport: SHA (the three-letter code of Shanghai Hongqiao International Airport); Sales start date: 2023-01-01; Sales end date: 2023-12-01; Travel start date: 2023-01-01; Travel end date: 2023-12-01; Supplier information {Supplier code: abcdefg01; Supplier name: Baggage port to door supplier; Supplier address: Shanghai; Supplier city code: 421300; Supplier country code: CN}

[0084] In actual application, the complete data query process for a query request is divided into three stages: the stage of obtaining basic product information, the stage of obtaining information at the supplier, and the stage of summarizing basic product information and information at the supplier. Among them, the constituent data of the basic product information are all maintained by the airline itself, and the information at the supplier is maintained by the supplier. The present invention pre-caches the basic product information of multiple air travel related service query requests. Subsequently, when querying the basic product information for the same query request as the air travel related service query request corresponding to any one of the basic product information in the second cache data, the basic product information that hits the query request can be directly taken from the second cache data as the target product basic information of the query request.

[0085] In addition, before querying the second cache data according to the query request, it is also possible to first determine whether the cache function for the second cache data of the air travel-related service system is in the on stage. If the cache function for the second cache data is in the on stage, the second cache data is queried according to the query request. If the cache function for the second cache data is in the off stage, the query strategy is executed when the query request does not hit the second cache data.

[0086] (2) If the query request hits the second cache data, it is determined that the target product basic information of the query request is the product basic information in the second cache data that hits the query request.

[0087] (3) Based on the target supplier information in the target product basic information, obtain the target supplier's partner enterprise and region information referred to in the target supplier information.

[0088] Specifically, the cooperative enterprise and region information of the target supplier referred to by the target supplier information can be obtained according to the target supplier code in the basic information of the target product.

[0089] (4) If the cooperation area indicated by the target supplier's cooperation enterprise and region information matches the target airport in the query request (i.e., the target airport belongs to the cooperation area indicated by the target supplier's cooperation enterprise and region information), the service information of the target supplier is obtained; the service information includes service price information; the target airport is the airport involved in the execution of the target air travel related service.

[0090] On the contrary, if the cooperation region indicated by the cooperation enterprise and region information of the target supplier does not match the target airport in the query request, it is determined that the current product is not applicable to the current query request, and the query process of the current query request about the current product is terminated.

[0091] (5) If the service information of the target supplier is obtained, the basic information of the target product, the cooperative enterprise and regional information of the target supplier, and the service information of the target supplier are summarized to obtain the target query result.

[0092] On the contrary, if the service information of the target supplier is not obtained (ie, the service information of the target supplier fails to be obtained), it is determined that the current product is not applicable to the current query request, and the query process of the current query request about the current product is terminated.

[0093] The air travel related service query method of the present invention may further include:

[0094] (1) If the query request does not hit the second cache data, the third cache data is queried according to the query request; the third cache data includes verification data, and the verification data comes from other systems of the airline outside the current system.

[0095] Specifically, the verification data may include master data and location data. Master data may include passenger type, frequent flyer level, passenger mobile phone number, carrier airline, cabin and sales channel, etc. Location data may include country code, city code, airport IATA (International Air Transport Association Airport Code), region code and station code, etc. Passenger types may include infants and adults, etc.

[0096] In actual application, the verification data will not change frequently. Therefore, the present invention adopts memory cache for the verification data, so that the required verification data can be directly obtained from the third cache data later. In this way, the frequent access of the air travel-related service system to the peripheral systems (that is, other systems of the airline except the air travel-related service system, such as the master data system and the location service system) can be reduced, the response speed of the air travel-related service system interface can be improved, and it is conducive to fast and accurate high-concurrency query.

[0097] (2) When the query request hits the third cache data, the target verification data of the query request is determined to be the verification data in the third cache data that hits the query request.

[0098] When the query request does not hit the third cache data, interfaces of other systems (such as the main data system and the location service system) are called to obtain target verification data, and the target verification data is cached in the third cache data.

[0099] (3) Based on the target verification data, according to the specified query conditions in the query request, the database of this system is queried, and the basic product information obtained by querying the database is determined as the basic information of the target product. It should be noted that this process is a prior art, so its specific implementation details are not repeated.

[0100] After determining the basic product information obtained by querying the database as the basic information of the target product, the air travel related service query method of the present invention may further include:

[0101] (1) Inputting a specified query condition into a second prediction model to obtain a second prediction result output by the second prediction model, wherein the second prediction result is used to indicate whether to cache the basic information of the target product and, when the basic information of the target product needs to be cached, the cache duration corresponding to the basic information of the target product.

[0102] (2) If the second prediction result indicates that the target product basic information needs to be cached, the target product basic information is cached in the second cache data, and the cache duration of the target product basic information is set.

[0103] In the embodiment of the present invention, according to the target supplier information in the target product basic information, obtaining the cooperative enterprise and region information of the target supplier indicated by the target supplier information may specifically include:

[0104] (1) According to the target supplier information, query the fourth cache data; the fourth cache data includes the cooperative enterprise and region information of multiple suppliers.

[0105] Specifically, the cooperative enterprise and region information will not change frequently. Therefore, the present invention adopts an active cache strategy for the cooperative enterprise and region information, so that the cooperative enterprise and region information of a supplier can be directly obtained from the fourth cache data later.

[0106] Continuing with the above example, Li Si queries the baggage port-to-door service of CA1234 flight from Beijing to Shanghai, with an estimated arrival time of 14:30 on December 1, 2023. The system feedbacks the partner companies and regional information of the target supplier as follows:

[0107] (a) Airport name: Shanghai Hongqiao Airport; Airport code: SHA; Province code: 310000; Province name: Shanghai; City code: 310100; City name: Shanghai; District code: 310116; District name: Jinshan District; Type: 2-Departure.

[0108] (b) Airport name: Guangzhou Baiyun International Airport; Airport code: CAN; Province code: 440000; Province name: Guangdong Province; City code: 440100; City name: Guangdong City; District code: 440103; District name: Liwan District; Type: 2-Departure.

[0109] (c) Airport name: Meixian Airport; Airport code: MXZ; Province code: 440000; Province name: Guangdong Province; City code: 441400; City name: Meizhou City; District code: 441403; District name: Meixian District; Type: 2-Departure.

[0110] In addition, before querying the fourth cache data according to the target supplier information, you can also first determine whether the cache function for the fourth cache data of the air travel related service system is in the on stage. If the cache function for the fourth cache data is in the on stage, query the fourth cache data according to the target supplier information. If the cache function for the fourth cache data is in the off stage, call the target supplier's cooperative enterprise and regional information interface to obtain the target supplier's cooperative enterprise and regional information.

[0111] (2) If the target supplier information hits the fourth cache data, the cooperative enterprise and region information in the fourth cache data that hits the target supplier information is determined as the cooperative enterprise and region information of the target supplier.

[0112] (3) If the target supplier information does not hit the fourth cache data, call the target supplier's cooperative enterprise and region information interface to obtain the target supplier's cooperative enterprise and region information from the target supplier's database.

[0113] Specifically, when the target supplier information does not hit the fourth cache data, a request for obtaining the cooperative enterprise and regional information is sent to the cooperative enterprise and regional information interface of the target supplier. After receiving the request for obtaining the cooperative enterprise and regional information, the target supplier system obtains the corresponding cooperative enterprise and regional information from its database according to the request for obtaining the cooperative enterprise and regional information, and returns it to the air travel related service system.

[0114] Here, the request for obtaining the cooperative enterprise and regional information may include the port of entry and exit type, timestamp, signature, and AppID (Application Identification) assigned by the target supplier. The port of entry and exit type is used to specify the specific product to be queried, and the other fields are necessary information required by the cooperative enterprise and regional information interface.

[0115] In the embodiment of the present invention, the service information may further include: service insurance information.

[0116] Obtain service information of target suppliers, which may include:

[0117] (1) According to the target supplier information, query the fifth cache data; the fifth cache data includes service price information of multiple suppliers.

[0118] Specifically, the service price information will not change frequently. Therefore, the present invention adopts an active cache strategy for the service price information, so that the service price information of a certain supplier can be directly obtained from the fifth cache data later.

[0119] In addition, before querying the fifth cache data according to the target supplier information, you can also first determine whether the cache function for the fifth cache data of the air travel-related service system is in the on stage. If the cache function for the fifth cache data is in the on stage, query the fifth cache data according to the target supplier information. If the cache function for the fifth cache data is in the off stage, call the service price information interface of the target supplier to obtain the service price information of the target supplier.

[0120] (2) If the target supplier information hits the fifth cache data, the service price information in the fifth cache data that hits the target supplier information is determined as the service price information of the target supplier.

[0121] On the contrary, if the target supplier information does not hit the fifth cache data, the service price information interface of the target supplier is called to obtain the service price information of the target supplier.

[0122] Specifically, when the target supplier information does not hit the fifth cache data, a service price information acquisition request is sent to the service price information interface of the target supplier. The target supplier system can obtain the corresponding service price information from its database based on the service price information acquisition request and return it to the air travel related service system.

[0123] Here, the service price information acquisition request may include the order type, timestamp, signature, and AppID assigned by the target supplier. When the target air travel related service is a baggage lane to door service, the service price information acquisition request may also include the selection result of whether to follow the flight and the type of consigned items.

[0124] In the present invention, if the service price information of the target supplier is not obtained by calling the service price information interface of the target supplier, it is determined that the current product is not applicable to the current query request, and the query process of the current query request about the current product is terminated.

[0125] (3) According to the target supplier information, query the sixth cache data; the sixth cache data includes service insurance information of multiple suppliers.

[0126] Specifically, the service insurance information will not change frequently. Therefore, the present invention adopts an active cache strategy for the service insurance information, so that the service insurance information of a certain supplier can be directly obtained from the sixth cache data later.

[0127] The service insurance information may include product information of multiple insurance products, and the product information of each insurance product includes the insurance number, insurance name, insurance type, whether the insurance is free, insurance coverage, insurance sales amount and product description.

[0128] Continuing with the above example, Li Si queries the baggage port-to-door service for flight CA1234 from Beijing to Shanghai, with an estimated arrival time of 14:30 on December 1, 2023. Therefore, the insurance type is baggage cargo insurance, and the corresponding service insurance information is as follows:

[0129] (a) Insurance number: BHWYSX-C; Insurance name: Baggage protection value-added service-C package; Type: 1- Baggage and cargo insurance; Whether insurance is provided for free: 0-No; Insurance coverage: 10,000 (unit: cents); Insurance sales amount: 70 (unit: cents); Product description: ***.

[0130] (b) Insurance number: RBHWYSX-B; Insurance name: Baggage protection value-added service - Package B; Type: 1- Baggage and cargo insurance; Whether insurance is provided for free: 0-No; Insurance coverage: 5000 (unit: cents); Insurance sales amount: 50 (unit: cents); Product description: ***.

[0131] (c) Insurance number: RBHWYSX-A; Insurance name: Baggage protection value-added service-Package A; Type: 1- Baggage and cargo insurance; Whether insurance is provided for free: 1-Yes; Insurance coverage: 2000 (unit: cents); Insurance sales amount: 5 (unit: cents); Product description: ***.

[0132] In addition, before querying the sixth cache data according to the target supplier information, you can also first determine whether the cache function for the sixth cache data of the air travel related service system is in the on stage. If the cache function for the sixth cache data is in the on stage, query the sixth cache data according to the target supplier information. If the cache function for the sixth cache data is in the off stage, call the service insurance information interface of the target supplier to obtain the service insurance information of the target supplier.

[0133] (4) If the target supplier information hits the sixth cache data, the service insurance information in the sixth cache data that hits the target supplier information is determined as the service insurance information of the target supplier.

[0134] On the contrary, if the target supplier information does not hit the sixth cache data, the service insurance information interface of the target supplier is called to obtain the service insurance information of the target supplier.

[0135] Specifically, when the target supplier information does not hit the sixth cache data, a service insurance information acquisition request can be sent to the service insurance information interface of the target supplier. The target supplier system obtains the corresponding service insurance information from its database based on the service insurance information acquisition request and returns it to the air travel related service system.

[0136] Here, the service insurance information acquisition request may include the insurance type (such as luggage and cargo insurance), timestamp, signature, and AppID assigned by the target supplier.

[0137] In the present invention, if the service insurance information of the target supplier is not obtained by calling the service insurance information interface of the target supplier, it is determined that the current product is not applicable to the current query request, and the query process of the current query request about the current product is terminated.

[0138] In the present invention, some service information of suppliers (which may include cooperative enterprise and region information, service price information, and service insurance information) is actively cached. In practical applications, when it is found that the service information of the target supplier is missing in the cache, the prediction model can be used to predict whether the information needs to be cached, and when the prediction result shows that the information needs to be cached, the information can be cached and its cache duration can be set.

[0139] Based on this, the air travel related service query method of the present invention may also include:

[0140] (1) When the target supplier information does not hit the fourth cache data, after calling the target supplier's cooperative enterprise and regional information interface to obtain the target supplier's cooperative enterprise and regional information, the corresponding cooperative enterprise and regional information query conditions are input into the third prediction model to obtain the third prediction result output by the third prediction model. The third prediction result is used to indicate whether to cache the target supplier's cooperative enterprise and regional information, and, when it is necessary to cache the cooperative enterprise and regional information, the cache duration corresponding to the cooperative enterprise and regional information.

[0141] (2) If the third prediction result indicates that the target supplier's partner enterprise and region information needs to be cached, the target supplier's partner enterprise and region information is cached in the fourth cache data, and a cache duration for the partner enterprise and region information is set.

[0142] (3) When the target supplier information does not hit the fifth cache data, after calling the service price information interface of the target supplier to obtain the service price information of the target supplier, the corresponding service price information query condition is input into the fourth prediction model to obtain the fourth prediction result output by the fourth prediction model. The fourth prediction result is used to indicate whether to cache the service price information of the target supplier and, when the service price information needs to be cached, the cache duration corresponding to the service price information.

[0143] (4) If the fourth prediction result indicates that the service price information of the target supplier needs to be cached, the service price information is cached into the fifth cache data, and a cache duration of the service price information is set.

[0144] (5) When the target supplier information does not hit the sixth cache data, after calling the service insurance information interface of the target supplier to obtain the service insurance information of the target supplier, the corresponding service insurance information query condition is input into the fifth prediction model to obtain the fifth prediction result output by the fifth prediction model. The fifth prediction result is used to indicate whether it is necessary to cache the service insurance information of the target supplier, and, when it is necessary to cache the service insurance information, the cache duration corresponding to the service insurance information.

[0145] (6) If the fifth prediction result indicates that the service insurance information of the target supplier needs to be cached, the service insurance information is cached into the sixth cache data, and a cache duration of the service insurance information is set.

[0146] It should be noted that the prediction principles of the first prediction model, the second prediction model, the third prediction model, the fourth prediction model and the fifth prediction model are the same or similar, that is, the training processes of the second prediction model, the third prediction model, the fourth prediction model and the fifth prediction model are the same or similar to the training process of the first prediction model. Therefore, the training process of the second prediction model, the third prediction model, the fourth prediction model and the fifth prediction model please refer to the aforementioned training process of the first prediction model, and the present invention will not go into details here.

[0147] Furthermore, the cache duration of each cached data of the present invention can be configured and supports later modification.

[0148] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0149] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0150] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0151] Although operations are depicted in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in a sequential order.Multitasking and parallel processing may be advantageous under certain circumstances.

[0152] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0153] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0154] Based on a general inventive concept, the present invention also provides an air travel related service query device. Figure 2 Schematic diagram of a structure of a flight travel related service query device provided by an embodiment of the present invention. Figure 2 As shown, the air travel related service query device includes:

[0155] The acquisition module 21 is used to acquire the query request sent by the passenger regarding the target air travel related service;

[0156] A first query module 22 is used to query first cache data according to a query request; the first cache data includes query results of multiple air travel related service query requests;

[0157] A second query module 23 is configured to perform other data query processing on the query request to obtain a target query result of the query request if the query request does not hit the first cache data;

[0158] Feedback module 24, used to feed back target query results to passengers;

[0159] The first prediction module 25 is used to input the query request into the first prediction model to obtain the first prediction result output by the first prediction model, the first prediction result is used to indicate whether to cache the target query result, and, when the target query result needs to be cached, the corresponding cache time length of the target query result; from the completion of caching the target query result, after the corresponding cache time length, the target query result will be deleted from the first cache data;

[0160] The first cache module 26 is configured to cache the target query result into the first cache data and set a cache duration for the target query result if the first prediction result indicates that the target query result needs to be cached.

[0161] Optionally, the second query module 23 may specifically include:

[0162] The query unit is used to query the second cache data according to the query request; the second cache data includes basic product information of multiple air travel related service query requests, and the basic product information includes product identification information, product usage requirement information, product sales requirement information and supplier information.

[0163] The determination unit is configured to determine, if the query request hits the second cache data, that the target product basic information of the query request is the product basic information in the second cache data that hits the query request.

[0164] The first acquisition unit is used to acquire the cooperative enterprise and region information of the target supplier indicated by the target supplier information according to the target supplier information in the basic information of the target product.

[0165] The second acquisition unit is used to acquire the service information of the target supplier if the cooperative area indicated by the cooperative enterprise and area information of the target supplier matches the target airport in the query request; the service information includes service price information; the target airport is the airport involved in executing the target air travel related service.

[0166] The summarizing unit is used to summarize the basic information of the target product, the cooperative enterprise and regional information of the target supplier, and the service information of the target supplier to obtain the target query result if the service information of the target supplier is obtained.

[0167] Optionally, the flight travel related service query device of the present invention may further include:

[0168] The third query module is used to query the third cache data according to the query request if the query request does not hit the second cache data; the third cache data includes verification data, and the verification data comes from other systems of the airline outside the current system.

[0169] The first determination module is used to determine, when the query request hits the third cache data, that the target verification data of the query request is the verification data in the third cache data that hits the query request.

[0170] The fourth query module is used to query the database of this system based on the target verification data and the specified query conditions in the query request.

[0171] The second determining module is used to determine the basic product information obtained by querying the database as the basic information of the target product.

[0172] Optionally, the flight travel related service query device of the present invention may further include:

[0173] The first calling module is used to call the interface of other systems to obtain target verification data when the query request does not hit the third cache data.

[0174] The second cache module is used to cache the target verification data into the third cache data.

[0175] Optionally, the flight travel related service query device of the present invention may further include:

[0176] The second prediction unit is used to input the specified query conditions into the second prediction model to obtain a second prediction result output by the second prediction model, and the second prediction result is used to indicate whether to cache the basic information of the target product and, when the basic information of the target product needs to be cached, the cache duration corresponding to the basic information of the target product.

[0177] The third cache module is used to cache the basic information of the target product into the second cache data if the second prediction result indicates that the basic information of the target product needs to be cached, and to set the cache duration of the basic information of the target product.

[0178] The first acquisition unit can be specifically used for:

[0179] (1) According to the target supplier information, query the fourth cache data; the fourth cache data includes the cooperative enterprise and region information of multiple suppliers.

[0180] (2) If the target supplier information hits the fourth cache data, the cooperative enterprise and region information in the fourth cache data that hits the target supplier information is determined as the cooperative enterprise and region information of the target supplier.

[0181] (3) If the target supplier information does not hit the fourth cache data, call the target supplier's cooperative enterprise and region information interface to obtain the target supplier's cooperative enterprise and region information.

[0182] Optionally, the service information may also include: service insurance information;

[0183] The second acquisition unit can be specifically used for:

[0184] (1) According to the target supplier information, query the fifth cache data; the fifth cache data includes service price information of multiple suppliers.

[0185] (2) If the target supplier information hits the fifth cache data, the service price information in the fifth cache data that hits the target supplier information is determined as the service price information of the target supplier.

[0186] (3) If the target supplier information does not hit the fifth cache data, call the service price information interface of the target supplier to obtain the service price information of the target supplier.

[0187] (4) According to the target supplier information, query the sixth cache data; the sixth cache data includes service insurance information of multiple suppliers.

[0188] (5) If the target supplier information hits the sixth cache data, the service insurance information in the sixth cache data that hits the target supplier information is determined as the service insurance information of the target supplier.

[0189] (6) If the target supplier information does not hit the sixth cache data, call the service insurance information interface of the target supplier to obtain the service insurance information of the target supplier.

[0190] Optionally, the flight travel related service query device of the present invention may further include:

[0191] The third prediction module is used to, when the target supplier information does not hit the fourth cache data, after calling the target supplier's cooperative enterprise and regional information interface to obtain the target supplier's cooperative enterprise and regional information, input the corresponding cooperative enterprise and regional information query conditions into the third prediction model to obtain the third prediction result output by the third prediction model. The third prediction result is used to indicate whether to cache the target supplier's cooperative enterprise and regional information, and, when the cooperative enterprise and regional information needs to be cached, the cache period corresponding to the cooperative enterprise and regional information.

[0192] A fourth cache module, configured to cache the target supplier's cooperative enterprise and regional information into the fourth cache data if the third prediction result indicates that the target supplier's cooperative enterprise and regional information needs to be cached, and to set a cache duration for the cooperative enterprise and regional information;

[0193] The fourth prediction module is used to, when the target supplier information does not hit the fifth cache data, after calling the service price information interface of the target supplier and obtaining the service price information of the target supplier, input the corresponding service price information query conditions into the fourth prediction model to obtain the fourth prediction result output by the fourth prediction model. The fourth prediction result is used to indicate whether to cache the service price information of the target supplier, and, when the service price information needs to be cached, the cache duration corresponding to the service price information.

[0194] The fifth cache module is used to cache the service price information of the target supplier into the fifth cache data if the fourth prediction result indicates that the service price information of the target supplier needs to be cached, and to set the cache duration of the service price information.

[0195] The fifth prediction module is used to, when the target supplier information does not hit the sixth cache data, after calling the service insurance information interface of the target supplier and obtaining the service insurance information of the target supplier, input the corresponding service insurance information query conditions into the fifth prediction model to obtain the fifth prediction result output by the fifth prediction model. The fifth prediction result is used to indicate whether it is necessary to cache the service insurance information of the target supplier, and, when it is necessary to cache the service insurance information, the cache duration corresponding to the service insurance information.

[0196] The sixth cache module is used to cache the service insurance information of the target supplier into the sixth cache data and set the cache duration of the service insurance information if the fifth prediction result indicates that the service insurance information of the target supplier needs to be cached.

[0197] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0198] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0199] Based on a general inventive concept, the present invention also provides an air travel related service query device. Figure 3 FIG. 1 is a schematic diagram of the structure of an air travel related service query device provided by an embodiment of the present invention. Figure 3 As shown, the air travel related service query device 300 includes:

[0200] at least one processor 310; and,

[0201] A memory 330 is communicatively connected to at least one processor 310; wherein,

[0202] The memory 330 stores instructions 320 that can be executed by at least one processor 310. The instructions 320 are executed by at least one processor 310 so that the at least one processor 310 can implement the air travel related service query method as described above.

[0203] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

[0204] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0205] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A method for querying air travel related services, characterized in that: include: Obtain inquiry requests sent by passengers regarding target travel-related services; According to the query request, query the first cache data; The first cache data includes query results of multiple air travel related service query requests; If the query request does not hit the first cache data, performing other data query processing on the query request to obtain the target query result of the query request; Feedback the target query result to the passenger; Input the query request into a first prediction model to obtain a first prediction result output by the first prediction model, wherein the first prediction result is used to indicate whether to cache the target query result and, when the target query result needs to be cached, the cache duration corresponding to the target query result; After the target query result is cached for a period of time corresponding to the cache time, the target query result is deleted from the first cache data; If the first prediction result indicates that the target query result needs to be cached, the target query result is cached in the first cache data, and a cache duration of the target query result is set.

2. The method for querying air travel related services according to claim 1, characterized in that: The performing other data query processing on the query request to obtain the target query result of the query request specifically includes: querying second cache data according to the query request; the second cache data includes basic product information of multiple air travel related service query requests, the basic product information including product identification information, product use requirement information, product sales requirement information and supplier information; If the query request hits the second cache data, determining that the target product basic information of the query request is the product basic information in the second cache data that hits the query request; According to the target supplier information in the target product basic information, obtaining the cooperative enterprise and region information of the target supplier indicated by the target supplier information; If the cooperative region indicated by the cooperative enterprise and region information of the target supplier matches the target airport in the query request, then obtaining the service information of the target supplier; the service information includes service price information; the target airport is the airport involved in executing the target air travel related service; If the service information of the target supplier is obtained, the basic information of the target product, the cooperative enterprise and region information of the target supplier, and the service information of the target supplier are summarized to obtain the target query result.

3. The method for querying air travel related services according to claim 2, characterized in that: Also includes: If the query request does not hit the second cache data, query the third cache data according to the query request; The third cache data includes verification data, and the verification data comes from other systems of the airline outside the present system; When the query request hits the third cache data, determining that the target verification data of the query request is the verification data in the third cache data that hits the query request; Based on the target verification data, according to the specified query conditions in the query request, the database of this system is queried, and the basic product information obtained by querying the database is determined as the basic information of the target product.

4. The method for querying air travel related services according to claim 3, characterized in that: Also includes: When the query request does not hit the third cache data, calling the interface of the other system to obtain the target verification data; The target verification data is cached in the third cache data.

5. The method for querying air travel related services according to claim 3 or 4, characterized in that: After determining the basic product information obtained by querying the database as the basic information of the target product, the method further includes: Input the specified query condition into a second prediction model to obtain a second prediction result output by the second prediction model, wherein the second prediction result is used to indicate whether to cache the target product basic information and, when the target product basic information needs to be cached, the cache duration corresponding to the target product basic information; If the second prediction result indicates that the target product basic information needs to be cached, the target product basic information is cached in the second cache data, and a cache duration of the target product basic information is set.

6. The method for querying air travel related services according to claim 2, characterized in that: According to the target supplier information in the target product basic information, the cooperative enterprise and region information of the target supplier referred to in the target supplier information is obtained, specifically including: According to the target supplier information, query the fourth cache data; the fourth cache data includes the cooperative enterprise and region information of multiple suppliers; If the target supplier information hits the fourth cache data, the cooperative enterprise and region information in the fourth cache data that hits the target supplier information is determined as the cooperative enterprise and region information of the target supplier; If the target supplier information does not hit the fourth cache data, the cooperative enterprise and region information interface of the target supplier is called to obtain the cooperative enterprise and region information of the target supplier.

7. The method for querying air travel related services according to claim 6, characterized in that: The service information also includes: service insurance information; Obtain the service information of the target supplier, including: According to the target supplier information, query the fifth cache data; the fifth cache data includes service price information of multiple suppliers; If the target supplier information hits the fifth cache data, the service price information in the fifth cache data that hits the target supplier information is determined as the service price information of the target supplier; If the target supplier information does not hit the fifth cache data, calling the service price information interface of the target supplier to obtain the service price information of the target supplier; According to the target supplier information, query the sixth cache data; the sixth cache data includes service insurance information of multiple suppliers; If the target supplier information hits the sixth cache data, the service insurance information in the sixth cache data that hits the target supplier information is determined as the service insurance information of the target supplier; If the target supplier information does not hit the sixth cache data, the service insurance information interface of the target supplier is called to obtain the service insurance information of the target supplier.

8. The method for querying air travel related services according to claim 7, characterized in that: Also includes: When the target supplier information does not hit the fourth cache data, after calling the target supplier's cooperative enterprise and region information interface to obtain the target supplier's cooperative enterprise and region information, the corresponding cooperative enterprise and region information query condition is input into the third prediction model to obtain the third prediction result output by the third prediction model, and the third prediction result is used to indicate whether to cache the target supplier's cooperative enterprise and region information, and, when the cooperative enterprise and region information needs to be cached, the cache duration corresponding to the cooperative enterprise and region information; If the third prediction result indicates that the target supplier's partner enterprise and region information needs to be cached, cache the target supplier's partner enterprise and region information into the fourth cache data, and set the cache duration of the partner enterprise and region information; When the target supplier information does not hit the fifth cache data, after calling the service price information interface of the target supplier to obtain the service price information of the target supplier, the corresponding service price information query condition is input into the fourth prediction model to obtain a fourth prediction result output by the fourth prediction model, and the fourth prediction result is used to indicate whether to cache the service price information of the target supplier, and, when the service price information needs to be cached, the cache duration corresponding to the service price information; If the fourth prediction result indicates that the service price information of the target supplier needs to be cached, cache the service price information into the fifth cache data, and set the cache time of the service price information; When the target supplier information does not hit the sixth cache data, after calling the service insurance information interface of the target supplier to obtain the service insurance information of the target supplier, the corresponding service insurance information query condition is input into the fifth prediction model to obtain the fifth prediction result output by the fifth prediction model, and the fifth prediction result is used to indicate whether the service insurance information of the target supplier needs to be cached, and, when the service insurance information needs to be cached, the cache duration corresponding to the service insurance information; If the fifth prediction result indicates that the service insurance information of the target supplier needs to be cached, the service insurance information is cached in the sixth cache data, and a cache duration of the service insurance information is set.

9. A device for querying air travel related services, characterized in that: include: The acquisition module is used to obtain the query request sent by the passenger regarding the target air travel related service; A first query module, configured to query first cache data according to the query request; The first cache data includes query results of multiple air travel related service query requests; A second query module, configured to perform other data query processing on the query request if the query request does not hit the first cache data, so as to obtain a target query result of the query request; A feedback module, used for feeding back the target query result to the passenger; A first prediction module, configured to input the query request into a first prediction model, and obtain a first prediction result output by the first prediction model, wherein the first prediction result is used to indicate whether to cache the target query result, and, when the target query result needs to be cached, the cache duration corresponding to the target query result; After the target query result is cached for a period of time corresponding to the cache time, the target query result is deleted from the first cache data; The first cache module is used to cache the target query result into the first cache data and set a cache duration of the target query result if the first prediction result indicates that the target query result needs to be cached.

10. A device for querying air travel related services, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the air travel related service query method as described in any one of claims 1 to 8.

Images