CN117473144B - Method for storing route data, computer equipment and readable storage medium - Google Patents
Method for storing route data, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN117473144B CN117473144B CN202311810188.1A CN202311810188A CN117473144B CN 117473144 B CN117473144 B CN 117473144B CN 202311810188 A CN202311810188 A CN 202311810188A CN 117473144 B CN117473144 B CN 117473144B
- Authority
- CN
- China
- Prior art keywords
- route
- stored
- current day
- search
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000000694 effects Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012417 linear regression Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000011478 gradient descent method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Abstract
The application relates to a storage method of route data, computer equipment and a readable storage medium, and relates to the technical field of computer software. The method comprises the following steps: and acquiring historical characteristic data of each route to be stored. And predicting the current day predicted search quantity of the route of each route to be stored according to the historical characteristic data of the route to be stored based on a pre-established prediction model. And determining the total current day predicted search amount according to the current day predicted search amount of the route of each route to be stored. And according to the preset number of storage service nodes, the average piece of the total prediction search quantity of the current day is stored to each storage service node. By adopting the method and the device, the load of each service node can be balanced.
Description
Technical Field
The present invention relates to the field of computer software technologies, and in particular, to a method for storing route data, a computer device, and a readable storage medium.
Background
Currently, with the popularization of travel and the development of aviation industry, flight searching and booking become an important link in the travel process of people. A concomitant problem is that when a user searches a large number of routes, the service node will be loaded high and even crash. Therefore, how to reasonably distribute route data to balance the load of each service node, and improve user experience and search efficiency becomes a problem that people need to solve.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method for storing route data, a computer device, and a readable storage medium.
In a first aspect, there is provided a method of storing route data, the method comprising:
acquiring historical characteristic data of each route to be stored;
based on a pre-established prediction model, predicting the current day prediction search amount of the route of each route to be stored according to the historical characteristic data of the route to be stored;
determining the current day total predicted search quantity according to the current day predicted search quantity of each route of the route to be stored;
and according to the preset number of storage service nodes, the average piece of the total prediction search quantity of the current day is stored to each storage service node.
As an alternative embodiment, the historical feature data includes an airline history search volume, an airline history departure date, a holiday attribute for the airline history departure date, an airline history departure location, an airline history destination, and an activity attribute for the airline history destination.
As an alternative embodiment, the pre-established prediction model includes a linear regression model, a time series model, or a neural network model.
As an optional implementation manner, the pre-established prediction model is a linear regression model, and the formula for predicting the current day prediction search amount of the route to be stored according to the historical feature data of the route to be stored for each route to be stored based on the pre-established prediction model is as follows:
；
wherein y is pred (i) Predicting search quantity, x, for route current day of ith route to be stored (i,j) And (3) j historical characteristic data of the ith route to be stored, wherein omega is the preset weight of the ith route to be stored, and b is a preset bias item.
As an optional implementation manner, the formula for determining the current day total predicted search amount according to the current day predicted search amount of each route to be stored is:
；
wherein S is T To predict the search amount of the day, y pred (i) Predicting search quantity for the current day of the route of the ith route to be stored, wherein n is the number of routes to be stored.
As an alternative embodiment, the method further comprises:
for each route to be stored, acquiring the current day actual search quantity of the route to be stored;
performing minimum mean square error evaluation on the current day predicted search quantity of the route to be stored and the current day actual search quantity of each route;
if the current predicted search amount of the route to be stored and the minimized mean square error of the current actual search amount of each route do not meet the preset minimized condition, updating the bias items in the prediction model and the weights corresponding to the route to be stored based on a preset gradient descent optimization algorithm so as to enable the current predicted search amount of the route to be stored and the minimized mean square error of the current actual search amount of each route to meet the preset minimized condition.
As an alternative implementation manner, the formula for performing the minimum mean square error evaluation on the route current day predicted search quantity of the route to be stored and the route current day actual search quantity is as follows:
；
wherein MSE is the minimum mean square error, y (i) is the current day actual search quantity of the route of the ith route to be stored, y pred (i) Predicting search quantity for the current day of the route of the ith route to be stored, wherein n is the number of routes to be stored.
As an alternative embodiment, the method further comprises:
if the minimized mean square error of the route current prediction search quantity of the route to be stored and the route current actual search quantity is smaller than or equal to a preset minimized mean square error threshold value, judging that the minimized mean square error of the route current prediction search quantity of the route to be stored and the route current actual search quantity of each route current day meets the preset minimized condition;
if the minimized mean square error of the route current prediction search quantity of the route to be stored and the route current actual search quantity is larger than the preset minimized mean square error threshold, judging that the minimized mean square error of the route current prediction search quantity of the route to be stored and the route current actual search quantity of each route does not meet the preset minimized condition.
In a second aspect, a computer device is provided, comprising a memory and a processor, the memory having stored thereon a computer program executable on the processor, the processor implementing the method steps according to any of the first aspects when the computer program is executed.
In a third aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method steps of any of the first aspects.
The application provides a storage method, computer equipment and readable storage medium of route data, and the technical scheme provided by the embodiment of the application at least brings the following beneficial effects: and acquiring historical characteristic data of each route to be stored. And predicting the current day predicted search quantity of the route of each route to be stored according to the historical characteristic data of the route to be stored based on a pre-established prediction model. And determining the total current day predicted search amount according to the current day predicted search amount of the route of each route to be stored. And according to the preset number of storage service nodes, the average piece of the total prediction search quantity of the current day is stored to each storage service node. According to the method and the device, the prediction model is built, the route current day prediction search quantity of the route is predicted, the storage service node resources are reasonably distributed, the load of each service node is balanced, the search efficiency and the user experience are improved, and the response time of a user in air ticket inquiry and purchase is reduced. Meanwhile, the accuracy and stability of search quantity prediction are further improved by optimizing the bias term and the weight of the prediction model.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for storing route data according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for updating a prediction model according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In the following, a detailed description will be given of a method for storing route data provided in the embodiment of the present application, and fig. 1 is a flowchart of a method for storing route data provided in the embodiment of the present application, as shown in fig. 1, and specific steps are as follows:
step 101, acquiring historical characteristic data of each route to be stored.
In practice, the computer may obtain historical characteristic data for each route to be stored in a database or other data storage center for further analysis in a subsequent step.
Preferably, due to the fact that the number of the airlines is large, a technician can preset screening conditions in a computer, reject airlines in the database, which are abnormal due to medical treatment, fire, emergency and the like, and take the screened airlines as airlines to be stored.
As an alternative embodiment, the historical feature data in step 101 includes an airline history search amount, an airline history departure date, a holiday attribute of the airline history departure date, an airline history departure place, an airline history destination, and an activity attribute of the airline history destination.
As an alternative embodiment, if the route history take-off date is a holiday, the holiday attribute of the route history take-off date is set to a preset first constant value, and if the route history take-off date is not a holiday, the holiday attribute of the route history take-off date is set to a preset second constant value. For example, if the route history take-off date of the route to be stored is a holiday, the computer sets the holiday attribute of the route history take-off date to 1, and if the route history take-off date of the route to be stored is a non-holiday, the computer sets the holiday attribute of the route history take-off date to 0.
As an alternative embodiment, the technician may set the activity attribute of the route history destination in the computer in advance, for example, the activity of the route history destination is activity a, then the computer may set the activity attribute of the route history destination to 2, for example, the activity of the route history destination is activity B, then the activity attribute of the route history destination is 3, for example, the activity of the route history destination is activity C, and then the activity attribute of the route history destination is 4.
Step 102, predicting the route current day predicted search amount of each route to be stored according to the historical characteristic data of the route to be stored based on a pre-established prediction model.
In the implementation, the computer predicts the route current day predicted search amount of each route to be stored according to the historical characteristic data of the route to be stored based on a pre-established prediction model.
As an alternative embodiment, the pre-established prediction model in step 102 comprises a linear regression model, a time series model or a neural network model.
As an optional implementation manner, the pre-established prediction model is a linear regression model, and based on the pre-established prediction model, for each route to be stored, a formula for predicting the route current day prediction search amount of the route to be stored according to the historical feature data of the route to be stored is as follows:
；
wherein y is pred (i) Predicting search quantity, x, for route current day of ith route to be stored (i,j) And (3) j historical characteristic data of the ith route to be stored, wherein omega is the preset weight of the ith route to be stored, and b is a preset bias item.
And step 103, determining the total current day predicted search amount according to the current day predicted search amount of the route of each route to be stored.
In an implementation, the computer may further obtain a route current prediction search amount for each route to be stored after predicting each route to be stored. Then, by summarizing the route current day predicted search amounts for each route to be stored, the current day total predicted search amounts can be determined.
As an alternative embodiment, in step 103, the formula for determining the total current day predicted search amount according to the current day predicted search amount of each route to be stored is:
；
wherein S is T To predict the search amount of the day, y pred (i) Predicting search quantity for the current day of the route of the ith route to be stored, wherein n is the number of routes to be stored.
And 104, storing the average piece of the total predicted search quantity of the current day to each storage service node according to the preset number of the storage service nodes.
In implementation, the computer may calculate the average daily predicted search amount corresponding to each storage service node according to the preset number of storage service nodes, and then store the average daily predicted search amount to each storage service node.
Alternatively, the computer may perform the optimal allocation according to the configuration and performance of the different storage server nodes.
As an alternative implementation manner, fig. 2 is a flowchart of a method for updating a prediction model provided in the embodiment of the present application, and as shown in fig. 2, specific steps are as follows:
step 201, for each route to be stored, obtaining the current day actual search quantity of the route to be stored.
In implementation, the method also relates to updating of the prediction model, and the computer can acquire the route current day actual search quantity of each route to be stored for each route to be stored, so that the computer can compare the route current day predicted search quantity with the route current day actual search quantity.
And 202, estimating the minimum mean square error of the route current day predicted search quantity of the route to be stored and the actual search quantity of each route current day.
In practice, the computer may perform a minimized mean square error evaluation of the route current day predicted search amount and each route current day actual search amount for the route current day predicted search amount and the route current day actual search amount for the route to be stored.
As an alternative embodiment, the formula for performing the minimum mean square error evaluation on the estimated current day search amount of the route and the actual current day search amount of each route in step 202 is as follows:
；
wherein MSE is the minimum mean square error, y (i) is the current day actual search quantity of the route of the ith route to be stored, y pred (i) Route current prediction search for ith route to be storedThe quantity, n, is the number of routes to be stored.
And 203, if the minimized mean square error of the route current prediction search quantity of the route to be stored and the actual search quantity of each route current day does not meet the preset minimized condition, updating the bias items in the prediction model and the weights corresponding to the route to be stored based on a preset gradient descent optimization algorithm so as to enable the minimized mean square error of the route current prediction search quantity of the route to be stored and the actual search quantity of each route current day to meet the preset minimized condition.
In practice, if the prediction accuracy of the prediction model does not reach the expectations, for example, the minimum mean square error of the current day predicted search amount of the route to be stored and the current day actual search amount of each route does not meet the preset minimum condition, it is necessary to update the prediction model by some methods. And adjusting the current prediction model, and updating the bias term and the weight according to a preset algorithm to optimize the prediction accuracy of the model. For example, a gradient descent method may be used to update parameters of a linear regression model, a time series model, or a neural network model to improve the accuracy of the model. This is an iterative process by which the accuracy of the predictive model can be gradually increased. For example: the computer predicts the search volume on the day of the route predicted from site a to site B. Based on the historical data, if site B is holding a large campaign, the route current day predicted search volume will increase, and if the departure date of the route is close to the legal holiday, the search volume will also increase. We can take these historical data as input to our linear regression model. Specifically, the historical search amount of the route, the number of days of departure date and holiday difference, whether activities exist or not and the like are taken as independent variables, the current day prediction search amount of the route is taken as dependent variables, and then the weight omega and the bias term b corresponding to the route are solved. Taking the linear regression model as an example, assuming we have established a linear regression model for the route from site A to site B, we now want to be able to adjust and optimize the predictive model by examining the actual data. For example, the predicted search amount on the current day of the route is 1000, but the actual search amount on the current day of the route is 1200, which indicates that the prediction model has errors. To optimize the model, we use the gradient descent method to find new weights ω and bias terms b, thereby minimizing the average squared error between the predicted and actual search volumes. The method comprises the following steps: first, the gradient of the error (e.g., minimizing the mean square error) with respect to the weight ω and the bias term b, i.e., the tangential slope of the function at the current point, is calculated, and the partial derivatives of the weight ω and bias term b in the error function with respect to the error are calculated. And secondly, the current weight omega and the bias term b are reduced by a certain step length according to the negative gradient direction, and a new weight omega and the bias term b are obtained. According to this step, we iterate until the gradient is almost zero, i.e. the weight ω and the bias term b that minimize the error are found, and the prediction model can output the optimized route current day prediction search amount based on the updated weight ω and bias term b. In addition, in the optimization process, a proper step length a needs to be found through multiple tests, the convergence is too slow due to the too small step length a, and the convergence cannot be achieved due to the fact that the repeated oscillation is caused near the optimal point due to the too large step length a.
As an alternative implementation, the computer may also predict the current day predicted search volume of the route using a neural network model as a prediction model, similar to the linear regression model. First, the computer collects history feature data as training data, including route history search amount, route history departure date, holiday attribute of departure date, route history departure place, route history destination, and activity attribute of destination. When building the neural network model, a technician may select an appropriate neural network architecture according to the particular situation. For example, the skilled artisan may choose to use a three-layer fully connected neural network, where the number of input layer nodes is equal to the number of historical feature data and the number of output layer nodes is equal to the number of targets we want to predict (e.g., may be 1, i.e., route current day predicts search volume), while we may set one or more hidden layers to increase the complexity of the prediction model. When the neural network model is trained, a forward propagation algorithm can be applied to obtain a predicted value, then an error between the predicted value and an actual value is calculated (for example, a minimized mean square error can be used as a loss function), and then a backward propagation algorithm is applied to carry out backward propagation on the error, and meanwhile, a gradient descent method is utilized to update the weight of nodes connected with each layer in the neural network. For example, assume that the model predicts a search for a route flying from location a to location B of 1000 and an actual search of 1200. After calculating the prediction error (e.g. 200), we input the error to the output layer of the neural network, and propagate the error layer by layer from the output layer to the input layer by a back propagation algorithm, and update the corresponding weights at each layer by a gradient descent method, so as to optimize the prediction capability of the neural network. The process may require multiple iterations to find a set of weights ω and bias terms b that minimize the loss function, and after a period of training, a set of weights ω and bias terms b that minimize the loss function may be determined, i.e., training of the neural network model is completed. When the current day of the route of the new route to be stored is predicted, the new characteristic is input into the neural network, and the predicted data needed by the user can be obtained by using the trained weight.
As an optional implementation manner, in step 203, the step of determining whether the minimum mean square error of the route current day predicted search amount of the route to be stored and the actual search amount of each route current day satisfies the preset minimum condition is as follows:
if the minimized mean square error of the route current prediction search quantity of the route to be stored and the route current actual search quantity of each route is smaller than or equal to a preset minimized mean square error threshold value, judging that the minimized mean square error of the route current prediction search quantity of the route to be stored and the route current actual search quantity of each route meets preset minimized conditions;
if the minimized mean square error of the route current prediction search quantity of the route to be stored and the actual search quantity of each route current day is larger than a preset minimized mean square error threshold, judging that the minimized mean square error of the route current day prediction search quantity of the route to be stored and the actual search quantity of each route current day does not meet a preset minimized condition.
The embodiment of the application provides a method for storing route data, which comprises the following steps: and acquiring historical characteristic data of each route to be stored. Based on a pre-established prediction model, predicting the current day prediction search amount of the route of each route to be stored according to the historical characteristic data of the route to be stored. And determining the total current day predicted search quantity according to the current day predicted search quantity of the route of each route to be stored. And according to the preset number of storage service nodes, storing the average fragments of the total prediction search quantity of the current day into each storage service node. According to the method and the device, the search amount of the airlines is predicted by establishing the prediction model, storage resources are reasonably distributed, the load of each service node is balanced, the search efficiency and the user experience are improved, and the response time of a user in the air ticket inquiry and purchasing process is reduced. Meanwhile, the accuracy and stability of search quantity prediction are further improved by optimizing the bias items and weights of the prediction model, and the problems that the data read-write speed of the hot route is low and the service node is high in load of the hot route key are solved.
It should be understood that, although the steps in the flowcharts of fig. 1 and 2 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps in fig. 1 and 2 may include a plurality of steps or stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the execution of the steps or stages is not necessarily sequential, but may be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps.
It should be understood that the same/similar parts of the embodiments of the method described above in this specification may be referred to each other, and each embodiment focuses on differences from other embodiments, and references to descriptions of other method embodiments are only needed.
In one embodiment, a computer device is provided, as shown in fig. 3, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method steps of storing the route data when executing the computer program.
In one embodiment, a computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the method of storing airline data as described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for presentation, analyzed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (7)
1. A method of storing route data, the method comprising:
acquiring historical characteristic data of each route to be stored;
based on a pre-established prediction model, predicting the current day prediction search amount of the route of each route to be stored according to the historical characteristic data of the route to be stored;
determining the current day total predicted search quantity according to the current day predicted search quantity of each route of the route to be stored;
according to the preset number of storage service nodes, the average piece of the total prediction search quantity of the current day is stored to each storage service node;
the history characteristic data comprises a route history search amount, a route history departure date, a festival attribute of the route history departure date, a route history departure place, a route history destination and an activity attribute of the route history destination; the method further comprises the steps of:
for each route to be stored, acquiring the current day actual search quantity of the route to be stored;
performing minimum mean square error evaluation on the current day predicted search quantity of the route to be stored and the current day actual search quantity of each route;
if the current predicted search amount of the route to be stored and the minimized mean square error of the current actual search amount of each route do not meet the preset minimized condition, updating the bias items in the prediction model and the weights corresponding to the route to be stored based on a preset gradient descent optimization algorithm so as to enable the current predicted search amount of the route to be stored and the minimized mean square error of the current actual search amount of each route to meet the preset minimized condition;
the method further comprises the steps of:
if the minimized mean square error of the route current prediction search quantity of the route to be stored and the route current actual search quantity is smaller than or equal to a preset minimized mean square error threshold value, judging that the minimized mean square error of the route current prediction search quantity of the route to be stored and the route current actual search quantity of each route current day meets the preset minimized condition;
if the minimized mean square error of the current day predicted search amount of the route to be stored and the current day actual search amount of each route is larger than the preset minimized mean square error threshold, judging that the minimized mean square error of the current day predicted search amount of the route to be stored and the current day actual search amount of each route does not meet the preset minimized condition;
the updating the bias items in the prediction model and the weights corresponding to the route to be stored based on the preset gradient descent optimization algorithm comprises the following steps: determining a gradient of a minimized mean square error relative to weights corresponding to the bias term and the route to be stored, and partial derivatives of the weights and the bias term relative to the minimized mean square error;
descending the weight and the bias term by a preset step length according to a negative gradient direction;
and when the gradient is smaller than or equal to a preset gradient threshold value, determining the current bias term and the current weight as the bias term in the updated prediction model and the weight corresponding to the route to be stored respectively.
2. The method of claim 1, wherein the pre-established predictive model comprises a linear regression model, a time series model, or a neural network model.
3. The method according to claim 2, wherein the pre-established prediction model is a linear regression model, and the formula for predicting the current day prediction search amount of the route to be stored according to the historical feature data of the route to be stored for each route to be stored based on the pre-established prediction model is as follows:
；
wherein y is pred (i) Predicting search quantity, x, for route current day of ith route to be stored (i,j) And (3) j historical characteristic data of the ith route to be stored, wherein omega is the preset weight of the ith route to be stored, and b is a preset bias item.
4. The method of claim 1, wherein the formula for determining the total current day predicted search amount from the current day predicted search amounts for each of the routes to be stored is:
；
wherein S is T To predict the search amount of the day, y pred (i) Predicting search quantity for the current day of the route of the ith route to be stored, wherein n is the number of routes to be stored.
5. The method of claim 1, wherein the formula for minimizing the mean square error estimate for the estimated current day search amount of the route and the actual current day search amount of each of the routes to be stored is:
；
wherein MSE is the minimum mean square error, y (i) is the current day actual search quantity of the route of the ith route to be stored, y pred (i) Predicting search quantity for the current day of the route of the ith route to be stored, wherein n is the number of routes to be stored.
6. A computer device comprising a memory and a processor, the memory having stored thereon a computer program executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 5 when the computer program is executed.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311810188.1A CN117473144B (en) | 2023-12-27 | 2023-12-27 | Method for storing route data, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311810188.1A CN117473144B (en) | 2023-12-27 | 2023-12-27 | Method for storing route data, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117473144A CN117473144A (en) | 2024-01-30 |
| CN117473144B true CN117473144B (en) | 2024-03-29 |
Family
ID=89635106
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311810188.1A Active CN117473144B (en) | 2023-12-27 | 2023-12-27 | Method for storing route data, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117473144B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005911A (en) * | 2015-06-26 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | Operating system for deep neural network and operating method |
| CN105095414A (en) * | 2015-07-10 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus used for predicting network search volume |
| CN105608200A (en) * | 2015-12-28 | 2016-05-25 | 湖南蚁坊软件有限公司 | Network public opinion tendency prediction analysis method |
| CN105868845A (en) * | 2016-03-24 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | Risk pre-warning method and apparatus |
| CN107908616A (en) * | 2017-10-18 | 2018-04-13 | 北京京东尚科信息技术有限公司 | The method and apparatus of anticipation trend word |
| CN108549700A (en) * | 2018-04-17 | 2018-09-18 | 携程旅游网络技术（上海）有限公司 | Pre-searching method and its system, storage medium, the electronic equipment of the page |
| CN109829115A (en) * | 2019-02-14 | 2019-05-31 | 上海晓材科技有限公司 | Search engine keywords optimization method |
| CN110322263A (en) * | 2018-03-30 | 2019-10-11 | 香港纺织及成衣研发中心有限公司 | The prediction technique and prediction meanss of garment marketing based on machine learning |
| CN111639789A (en) * | 2020-04-30 | 2020-09-08 | 南京理工大学 | Open sea area ship collision risk prediction method |
| CN113240187A (en) * | 2021-05-26 | 2021-08-10 | 合肥工业大学 | Prediction model generation method, system, device, storage medium and prediction method |
| CN113554473A (en) * | 2021-08-11 | 2021-10-26 | 上海明略人工智能(集团)有限公司 | Information search amount prediction method and device, electronic equipment and readable storage medium |
| CN113703688A (en) * | 2021-09-20 | 2021-11-26 | 河南锦誉网络科技有限公司 | Distributed storage node load adjustment method based on big data and file heat |
| CN114625477A (en) * | 2022-01-25 | 2022-06-14 | 浙江大华技术股份有限公司 | Service node capacity adjusting method, equipment and computer readable storage medium |
| CN114880071A (en) * | 2022-04-29 | 2022-08-09 | 广州华多网络科技有限公司 | Cluster configuration method and device, equipment, medium and product thereof |
| CN115392947A (en) * | 2022-07-22 | 2022-11-25 | 阿里巴巴（中国）有限公司 | Demand prediction method and device |
| CN116757731A (en) * | 2023-08-16 | 2023-09-15 | 中国民航信息网络股份有限公司 | Flight season factor prediction method and device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334839B (en) * | 2019-04-15 | 2021-05-14 | 北京航空航天大学 | Flight delay prediction method, device, equipment and storage medium |
-
2023
- 2023-12-27 CN CN202311810188.1A patent/CN117473144B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005911A (en) * | 2015-06-26 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | Operating system for deep neural network and operating method |
| CN105095414A (en) * | 2015-07-10 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus used for predicting network search volume |
| CN105608200A (en) * | 2015-12-28 | 2016-05-25 | 湖南蚁坊软件有限公司 | Network public opinion tendency prediction analysis method |
| CN105868845A (en) * | 2016-03-24 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | Risk pre-warning method and apparatus |
| CN107908616A (en) * | 2017-10-18 | 2018-04-13 | 北京京东尚科信息技术有限公司 | The method and apparatus of anticipation trend word |
| CN110322263A (en) * | 2018-03-30 | 2019-10-11 | 香港纺织及成衣研发中心有限公司 | The prediction technique and prediction meanss of garment marketing based on machine learning |
| CN108549700A (en) * | 2018-04-17 | 2018-09-18 | 携程旅游网络技术（上海）有限公司 | Pre-searching method and its system, storage medium, the electronic equipment of the page |
| CN109829115A (en) * | 2019-02-14 | 2019-05-31 | 上海晓材科技有限公司 | Search engine keywords optimization method |
| CN111639789A (en) * | 2020-04-30 | 2020-09-08 | 南京理工大学 | Open sea area ship collision risk prediction method |
| CN113240187A (en) * | 2021-05-26 | 2021-08-10 | 合肥工业大学 | Prediction model generation method, system, device, storage medium and prediction method |
| CN113554473A (en) * | 2021-08-11 | 2021-10-26 | 上海明略人工智能(集团)有限公司 | Information search amount prediction method and device, electronic equipment and readable storage medium |
| CN113703688A (en) * | 2021-09-20 | 2021-11-26 | 河南锦誉网络科技有限公司 | Distributed storage node load adjustment method based on big data and file heat |
| CN114625477A (en) * | 2022-01-25 | 2022-06-14 | 浙江大华技术股份有限公司 | Service node capacity adjusting method, equipment and computer readable storage medium |
| CN114880071A (en) * | 2022-04-29 | 2022-08-09 | 广州华多网络科技有限公司 | Cluster configuration method and device, equipment, medium and product thereof |
| CN115392947A (en) * | 2022-07-22 | 2022-11-25 | 阿里巴巴（中国）有限公司 | Demand prediction method and device |
| CN116757731A (en) * | 2023-08-16 | 2023-09-15 | 中国民航信息网络股份有限公司 | Flight season factor prediction method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117473144A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mandi et al. | Interior point solving for lp-based prediction+ optimisation | |
| US10311391B2 (en) | Optimizing inventory in accordance with a constrained network | |
| Xia et al. | A tutorial on event-based optimization—a new optimization framework | |
| Krishnamoorthy et al. | On a queueing-inventory with reservation, cancellation, common life time and retrial | |
| US20130346351A1 (en) | Assessing accuracy of trained predictive models | |
| KR102344383B1 (en) | Method for analyzing loyalty of the customer to store based on artificial intelligence and system thereof | |
| CA2834959A1 (en) | Predictive analytical modeling accuracy assessment | |
| Do et al. | Equilibrium customer behavior in the M/M/1 retrial queue with working vacations and a constant retrial rate | |
| Ribeiro et al. | A recommender system for process discovery | |
| Molina et al. | A Multi-start Algorithm with Intelligent Neighborhood Selection for solving multi-objective humanitarian vehicle routing problems | |
| Rahimi-Ghahroodi et al. | Integrated planning of spare parts and service engineers with partial backlogging | |
| González-Prida et al. | Dynamic Analytic Hierarchy Process: AHP method adapted to a changing environment | |
| Alfieri et al. | Mathematical programming models for joint simulation–optimization applied to closed queueing networks | |
| CN117473144B (en) | Method for storing route data, computer equipment and readable storage medium | |
| US20150142482A1 (en) | Search engine for identifying business travel proposals | |
| Nonås et al. | Optimal solutions in the multi-location inventory system with transshipments | |
| Maggioni et al. | The value of the right distribution in stochastic programming with application to a newsvendor problem | |
| Martin et al. | Using event logs to model interarrival times in business process simulation | |
| Phiboonbanakit et al. | Knowledge-based learning for solving vehicle routing problem | |
| van Lent | Using column generation for the time dependent vehicle routing problem with soft time windows and stochastic travel times | |
| Huang et al. | A cutting plane method for risk-constrained traveling salesman problem with random arc costs | |
| CN113935673A (en) | Warehouse network optimization method and device based on inventory, computer equipment and storage medium | |
| Liu et al. | Expected value-based method to determine the importance of engineering characteristics in QFD with uncertainty theory | |
| Verbeeck et al. | Solving the stochastic time-dependent orienteering problem | |
| Parsaei et al. | Buffer size determination for drum-buffer-rope controlled supply chain networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |