CN113554473A - Information search amount prediction method and device, electronic equipment and readable storage medium - Google Patents
Information search amount prediction method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN113554473A CN113554473A CN202110921141.7A CN202110921141A CN113554473A CN 113554473 A CN113554473 A CN 113554473A CN 202110921141 A CN202110921141 A CN 202110921141A CN 113554473 A CN113554473 A CN 113554473A
- Authority
- CN
- China
- Prior art keywords
- search
- target
- model
- prediction
- promotion
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000007667 floating Methods 0.000 claims abstract description 64
- 230000003068 static effect Effects 0.000 claims description 36
- 239000013598 vector Substances 0.000 claims description 26
- 238000004891 communication Methods 0.000 claims description 20
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 4
- 230000001737 promoting effect Effects 0.000 claims description 2
- 238000007418 data mining Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 2
- 238000001134 F-test Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0254—Targeted advertisements based on statistics
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method and a device for predicting information search volume, electronic equipment and a readable storage medium, and belongs to the technical field of data mining. The method comprises the following steps: inputting a promotion strategy of target promotion information into a target prediction model to obtain an initial search quantity of the target promotion information output by the target prediction model, wherein the target prediction model is obtained based on the initial prediction model; obtaining a plurality of floating search quantities of the target popularization information in a prediction time period by adopting an autoregressive and moving average model, wherein the floating search quantities are obtained based on historical search quantities of the target popularization information in a historical time period; and obtaining the predicted search amount of the target popularization information in a prediction time period according to the initial search amount and the plurality of floating search amounts. The present application improves the efficiency of obtaining the predicted search volume.
Description
Technical Field
The present application relates to the field of data mining technologies, and in particular, to a method and an apparatus for predicting an information search amount, an electronic device, and a readable storage medium.
Background
Effective advertisement delivery in the e-commerce platform has an important influence on an economic benefit generator of an advertiser, and the effective advertisement delivery is generally obtained based on the click rate or the conversion rate of the advertisement, but the effective advertisement delivery cannot accurately evaluate the effects of certain non-economic layers, such as sound volume, heat, influence and the like. Therefore, the concept of search volume is proposed, and the search volume can solve the defect of the evaluation level, namely the related search volume of the corresponding period of the advertising promotion activity can measure the comprehensive effect including the potential economic effect.
The search volume of the advertisement is generally associated with various factors such as advertisement brands, advertisement platforms, advertisement groups and advertisement time intervals, and at present, if the search volume of the advertisement needs to be predicted, a model needs to be set for each factor separately, so that the efficiency of predicting the search volume is low.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method, an apparatus, an electronic device, and a readable storage medium for predicting an information search amount, so as to solve a problem of low efficiency of predicting a search amount. The specific technical scheme is as follows:
in a first aspect, a method for predicting an information search amount is provided, the method including:
inputting a promotion strategy of target promotion information into a target prediction model to obtain an initial search quantity of the target promotion information output by the target prediction model, wherein the target prediction model is obtained based on the initial prediction model;
obtaining a plurality of floating search quantities of the target popularization information in a prediction time period by adopting an autoregressive and moving average model, wherein the floating search quantities are obtained based on historical search quantities of the target popularization information in a historical time period;
and obtaining the predicted search amount of the target popularization information in a prediction time period according to the initial search amount and the plurality of floating search amounts.
Optionally, the obtaining, according to the initial search volume and the plurality of floating search volumes, a predicted search volume of the target popularization information in a prediction time period includes:
increasing the initial search quantity on the basis of each floating search quantity to obtain a plurality of sub-prediction search quantities, wherein each floating search quantity corresponds to one search time in the prediction time period, and the prediction time period comprises a plurality of search times;
and arranging the plurality of sub-prediction search volumes according to the sequence of the corresponding search time to obtain a preset search volume in the prediction time period, wherein the preset search volume comprises a plurality of sub-prediction search volumes.
Optionally, the inputting the promotion strategy of the target promotion information into the target prediction model to obtain the initial search quantity of the target promotion information output by the target prediction model includes:
acquiring a promotion strategy of the target promotion information, wherein the promotion strategy comprises at least one of promotion audiences, promotion platforms and promotion modes of the target promotion information;
converting the promotion strategy into a corresponding promotion vector through a vector conversion scheme;
and inputting the popularization vector into the target prediction model to obtain an initial search quantity of the popularization vector output by the target prediction model, wherein the initial search quantity is a search quantity generated based on the popularization strategy.
Optionally, the obtaining, by using an autoregressive and moving average model, a plurality of floating search quantities of the target popularization information in a prediction period includes:
acquiring a history sub-search quantity of each history time in a history period, wherein the history period comprises a plurality of history times, and each history time corresponds to one history sub-search quantity;
and inputting the white noise sequence and the historical sub-search quantities arranged according to the sequence of the historical moments into the autoregressive and moving average model to obtain a plurality of floating search quantities output by the autoregressive and moving average model, wherein each floating search quantity corresponds to one historical sub-search quantity according to the sequence of the historical moments.
Optionally, before obtaining the history sub-search amount at each history time in the history period, the method further includes:
acquiring a historical time sequence formed by a plurality of historical sub-search quantities;
determining whether the historical time series is a static time series, wherein the static time series is used for indicating that the mean, the variance and the covariance of the historical time series do not change along with time;
and if the historical time sequence is determined to be a static time sequence, obtaining model parameters of an autoregressive and moving average model according to the static time sequence, wherein the model parameters are used for adjusting balance between model complexity and prediction accuracy, the model complexity is obtained through the parameter number of the model, and the prediction accuracy is obtained through a model linear fitting degree evaluation scheme.
Optionally, after determining whether the historical time series is a static time series, the method further includes:
if the historical time sequence is determined to be a non-static time sequence, acquiring a part of non-static sequences in the historical time sequence by adopting an autoregressive model;
determining a sequence difference value of the historical time sequence and the non-static sequence;
and obtaining model parameters of an autoregressive and moving average model according to the sequence difference, wherein the model parameters are used for adjusting balance between model complexity and prediction accuracy, the model complexity is obtained through the parameter number of the model, and the prediction accuracy is obtained through a model linear fitting degree evaluation scheme.
Optionally, before inputting the promotion strategy of the target promotion information into the target prediction model, the method further includes:
obtaining a sample popularization strategy and a sample search amount corresponding to the sample popularization strategy;
inputting the sample popularization strategy into the initial prediction model to obtain a search quantity result output by the initial prediction model;
and under the condition that the sample search volume is inconsistent with the search volume result, adjusting the model parameters of the initial prediction model until the sample search volume is consistent with the search volume result to obtain the target prediction model.
In a second aspect, an apparatus for predicting an information search amount is provided, the apparatus comprising:
the system comprises an input module, a target prediction module and a target search module, wherein the input module is used for inputting a promotion strategy of target promotion information into a target prediction model to obtain an initial search amount of the target promotion information output by the target prediction model, and the target prediction model is obtained based on the initial prediction model;
the first obtaining module is used for obtaining a plurality of floating search quantities of the target popularization information in a prediction time period by adopting an autoregressive and moving average model, wherein the floating search quantities are obtained based on historical search quantities of the target popularization information in a historical time period;
and the second obtaining module is used for obtaining the predicted search amount of the target popularization information in a prediction time period according to the initial search amount and the plurality of floating search amounts.
In a third aspect, an electronic device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and a processor for implementing any of the above-described information search amount prediction method steps when executing the program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, in which a computer program is stored, which, when being executed by a processor, implements any of the information search volume prediction method steps.
The embodiment of the application has the following beneficial effects:
the embodiment of the application is used for data mining in the technical field of data capacity. The embodiment of the application provides a method for predicting information search volume, wherein a server inputs a promotion strategy of target promotion information into a target prediction model to obtain initial search volume of the target promotion information output by the target prediction model, then a plurality of floating search volumes of the target promotion information in a prediction time period are obtained by adopting an autoregressive and moving average model, and the predicted search volume of the target promotion information in the prediction time period is obtained according to the initial search volume and the plurality of floating search volumes.
According to the method and the device, the predicted search volume can be obtained only through the target prediction model and the autoregressive and moving average models, models do not need to be established respectively according to different popularization strategies, and models do not need to be established respectively according to different time periods.
Of course, not all of the above advantages need be achieved in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a hardware environment diagram of a method for predicting an information search amount according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for predicting an information search amount according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a method for predicting an information search amount according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an apparatus for predicting an information search amount according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for the convenience of description of the present application, and have no specific meaning in themselves. Thus, "module" and "component" may be used in a mixture.
In order to solve the problems mentioned in the background, according to an aspect of embodiments of the present application, an embodiment of a method for predicting an information search amount is provided.
Alternatively, in the embodiment of the present application, the method for predicting the information search amount may be applied to a hardware environment formed by the terminal 101 and the server 103 as shown in fig. 1. As shown in fig. 1, a server 103 is connected to a terminal 101 through a network, which may be used to provide services for the terminal or a client installed on the terminal, and a database 105 may be provided on the server or separately from the server, and is used to provide data storage services for the server 103, and the network includes but is not limited to: wide area network, metropolitan area network, or local area network, and the terminal 101 includes but is not limited to a PC, a cell phone, a tablet computer, and the like.
The method for predicting the information search volume in the embodiment of the present application may be executed by the terminal 101, may be executed by the server 103, or may be executed by both the server 103 and the terminal 101.
The embodiment of the application provides a method for predicting information search volume, which can be applied to a server and is used for predicting the predicted search volume of target popularization information.
The following describes in detail an information search quantity prediction method provided in an embodiment of the present application with reference to a specific embodiment, as shown in fig. 2, the specific steps are as follows:
step 201: and inputting the popularization strategy of the target popularization information into the target prediction model to obtain the initial search quantity of the target popularization information output by the target prediction model.
Wherein the target prediction model is obtained based on the initial prediction model.
In the embodiment of the application, when promoting the target promotion information, a promotion policy needs to be set by a promoter, wherein the target promotion information may be an advertisement, and the promotion policy is a policy of advertisement promotion. Illustratively, the promotion strategy comprises at least one of promotion audience, promotion platform and promotion mode, wherein the promotion audience comprises the age, sex, hobbies and the like of the audience, the promotion platform comprises platform name, platform category and the like, and the promotion mode comprises promotion price and promotion type (factory promotion, platform promotion or factory joint platform promotion).
And the server inputs the promotion strategy of the target promotion information into the target prediction model to obtain the initial search quantity of the target promotion information output by the target prediction model, wherein the initial search quantity is obtained based on the promotion strategy.
Step 202: and obtaining a plurality of floating search quantities of the target popularization information in the prediction time period by adopting an autoregressive and moving average model.
Wherein the floating search quantity is obtained based on the historical search quantity of the target popularization information in the historical time period.
The Auto-Regressive and Moving Average model (ARMA) is the basic idea: the data sequence formed by the prediction object along with the time is regarded as a random sequence, and the sequence is approximately described by a certain mathematical model based on the autocorrelation analysis of the time sequence. Once identified, the model can predict future values from past and present values of the time series. The ARMA model considers the dependency of economic phenomena on a time sequence and the interference of random fluctuation in the economic prediction process, and has higher prediction accuracy on the short-term trend of economic operation.
In the embodiment of the application, the autoregressive and moving average model obtains a plurality of floating search quantities of the target popularization information in the prediction time period through the historical search quantity of the target popularization information in the historical time period, wherein the preset time period is located after the current time period, and the floating search quantity is a floating value of the predicted future search quantity relative to the historical search quantity.
Step 203: and obtaining the predicted search amount of the target popularization information in the prediction time period according to the initial search amount and the plurality of floating search amounts.
After the server obtains the initial search volume based on the popularization strategy and obtains a plurality of floating search volumes based on the time period, the initial search volume and the plurality of floating search volumes are comprehensively considered, and the predicted search volume of the target popularization information in the prediction time period is obtained.
In the method, the target prediction model obtains initial search volume according to the popularization strategy, the autoregressive model and the moving average model obtain predicted floating search volume, and then the predicted search volume is obtained according to the initial search volume and the plurality of floating search volumes, so that the predicted search volume can be obtained only through the target prediction model and the autoregressive model and the moving average model, models do not need to be respectively established for different popularization strategies, and models do not need to be respectively established for different time periods. The method provides a search quantity prediction method for crossing promotion audiences, crossing promotion platforms, crossing promotion modes and crossing time intervals, and the search quantity prediction efficiency is improved.
As an optional implementation manner, obtaining the predicted search amount of the target popularization information in the prediction time period according to the initial search amount and the plurality of floating search amounts includes: increasing initial search quantity on the basis of each floating search quantity to obtain a plurality of sub-prediction search quantities, wherein each floating search quantity corresponds to one search moment in a prediction time period, and the prediction time period comprises a plurality of search moments; and arranging the plurality of sub-prediction search volumes according to the sequence of the corresponding search time to obtain a preset search volume in the prediction time period, wherein the preset search volume comprises the plurality of sub-prediction search volumes.
The prediction time interval comprises a plurality of search moments arranged according to a time sequence, each search moment corresponds to one floating search amount, the server increases the initial search amount on the basis of each floating search amount to obtain a plurality of sub-prediction search amounts, and the plurality of sub-prediction search amounts are arranged according to the arrangement sequence of the search moments to form the prediction search amount in the prediction time interval. The prediction periods are settable by a technician, each with a corresponding floating search volume.
In the application, the floating search quantity represents a floating value of the search quantity of the prediction time period relative to the historical search quantity of the historical time period, the initial search quantity is obtained based on the current popularization strategy, the sum of the floating search quantity and the initial search quantity integrates the base value and the floating value of the search quantity, the popularization strategy is considered, the popularization time period is also considered, and the predicted search quantity is more accurate. In addition, the sub-prediction search quantity can be set as a weighted summation result of the floating search quantity and the initial search quantity.
As an optional implementation manner, inputting the promotion strategy of the target promotion information into the target prediction model, and obtaining the initial search quantity of the target promotion information output by the target prediction model includes: acquiring a promotion strategy of the target promotion information, wherein the promotion strategy comprises at least one of promotion audiences, promotion platforms and promotion modes of the target promotion information; converting the promotion strategy into a corresponding promotion vector through a vector conversion scheme; and inputting the popularization vector into the target prediction model to obtain an initial search quantity of the popularization vector output by the target prediction model, wherein the initial search quantity is a search quantity generated based on a popularization strategy.
Technical personnel store the promotion strategy of the target promotion information in a memory or a cloud end of the server, the server can acquire the promotion strategy in real time, and when the promotion strategy is updated, the cloud end can automatically send the updated promotion strategy to the server. The promotion strategy comprises at least one of promotion audiences, promotion platforms and promotion modes of the target promotion information.
The server converts the popularization strategy into a corresponding popularization vector through a vector conversion scheme, then inputs the popularization vector into the target prediction model, and obtains an initial search quantity of the popularization vector output by the target prediction model, wherein the initial search quantity is a search quantity generated based on the popularization strategy. Vector conversion schemes include, but are not limited to, word2vec, glove, or BERT models, among others.
The target prediction model may be implemented by selecting MLP (multi layer Perceptron), which is an artificial neural network with a forward structure and maps a set of input vectors to a set of outputs. MLP consists of multiple layers of nodes, each layer being fully connected to the next layer, except for the input nodes, each node being a neuron (or processing unit) with a nonlinear activation function. In the training process, the MLP can be trained by using a supervised learning method of a classical back propagation algorithm to obtain parameters of each neuron.
As an alternative implementation, obtaining a plurality of floating search quantities of the target popularization information in the prediction period by using an autoregressive and moving average model includes: acquiring a history sub-search quantity of each history time in a history period, wherein the history period comprises a plurality of history times, and each history time corresponds to one history sub-search quantity; and inputting the white noise sequence and the historical sub-search quantities arranged according to the sequence of the historical moments into an autoregressive and moving average model to obtain a plurality of floating search quantities output by the autoregressive and moving average model, wherein each floating search quantity corresponds to one historical sub-search quantity according to the sequence of the historical moments.
In the embodiment of the present application, the history period includes the current period and a period before the current period, or the history period is a period before the current period. The historical time period comprises a plurality of historical moments arranged according to time sequence, and each historical moment corresponds to one historical sub-search quantity. The server obtains an output time sequence according to the historical time sequence and the white noise sequence through an autoregressive and moving average model, and the output time sequence comprises a plurality of floating search quantities. Each floating search volume corresponds to a historical sub-search volume at a corresponding time.
As an optional implementation manner, before obtaining the history sub-search amount at each history time in the history period, the method further includes: acquiring a historical time sequence formed by a plurality of historical sub-search quantities; determining whether the historical time series is a static time series, wherein the static time series is used for indicating that the mean, the variance and the covariance of the historical time series do not change along with time; and if the historical time sequence is determined to be a static time sequence, obtaining model parameters of an autoregressive and moving average model according to the static time sequence, wherein the model parameters are used for adjusting balance between model complexity and prediction accuracy, the model complexity is obtained through the number of the parameters of the model, and the prediction accuracy is obtained through a model linear fitting degree evaluation scheme.
In the embodiment of the application, a server obtains a historical time sequence formed by a plurality of historical sub-search quantities, then detects a historical time sequence status, namely determines whether the historical time sequence is a static time sequence, the static time sequence is determined by a mean, a variance and a covariance of the historical time sequence, if the mean, the variance and the covariance of the historical time sequence are not related to time, the historical time sequence is the static time sequence, and the server obtains model parameters of an autoregressive and moving average model according to the static time sequence.
Only static time series (the time series is stationary) can the time series model be built. If the server detects that the historical time sequence is a non-static time sequence, firstly, the historical time sequence is enabled to become stable, and then a random model is adopted to predict the time sequence. The specific process is as follows: the server obtains a part of non-static sequences in the historical time sequence by adopting an autoregressive model, then determines a sequence difference value between the historical time sequence and the non-static sequences, and finally obtains model parameters of an autoregressive and moving average model according to the sequence difference value.
The process of the server obtaining the model parameters of the autoregressive and moving average models is as follows: the server puts the static time series or the sequence difference value into the autoregressive and moving average models, the process of the fit is essentially to adjust the balance between the complexity and the prediction accuracy of the autoregressive and moving average models, and the server checks whether the prediction accuracy of the models is improved along with the improvement of the complexity of the models. And if the model prediction accuracy is improved, continuing to adjust the model parameters, and if the model prediction accuracy is not improved, acquiring the current model parameters.
Wherein, the accuracy of the detection model can be realized by adopting F-test (homogeneity test of variance), the complexity of the model is obtained by the parameter number of the model, and the prediction accuracy is obtained by a model linear fitting degree evaluation scheme (R-square).
As an optional implementation manner, before inputting the promotion strategy of the target promotion information into the target prediction model, the method further includes: the method comprises the steps that a server obtains a sample popularization strategy and a sample search volume corresponding to the sample popularization strategy, then the sample popularization strategy is input into an initial prediction model, a search volume result output by the initial prediction model is obtained, if the server determines that the sample search volume is inconsistent with the search volume result, model parameters of the initial prediction model are adjusted until the sample search volume is consistent with the search volume result, and a target prediction model is obtained.
Optionally, an embodiment of the present application further provides a processing flow chart of a method for predicting an information search amount, as shown in fig. 3, and the specific steps are as follows.
Step 1: and acquiring a popularization strategy of the target popularization information.
Step 2: and converting the promotion strategy into a corresponding promotion vector through a vector conversion scheme.
And step 3: and inputting the popularization vector into the target prediction model to obtain the initial search quantity of the popularization vector output by the target prediction model.
And 4, step 4: and obtaining a plurality of floating search quantities of the target popularization information in the prediction time period by adopting an autoregressive and moving average model.
And 5: and obtaining the predicted search amount of the target popularization information in the prediction time period according to the initial search amount and the plurality of floating search amounts.
Wherein, step 3 and step 4 can be performed simultaneously.
Based on the same technical concept, an embodiment of the present application further provides an apparatus for predicting an information search amount, as shown in fig. 4, the apparatus includes:
an input module 401, configured to input a promotion policy of the target promotion information into a target prediction model, so as to obtain an initial search amount of the target promotion information output by the target prediction model, where the target prediction model is obtained based on the initial prediction model;
a first obtaining module 402, configured to obtain multiple floating search quantities of the target popularization information in a prediction time period by using an autoregressive and moving average model, where the floating search quantities are obtained based on historical search quantities of the target popularization information in a historical time period;
a second obtaining module 403, configured to obtain, according to the initial search amount and the multiple floating search amounts, a predicted search amount of the target popularization information in the prediction time period.
Optionally, the second obtaining module 403 is configured to:
increasing initial search quantity on the basis of each floating search quantity to obtain a plurality of sub-prediction search quantities, wherein each floating search quantity corresponds to one search moment in a prediction time period, and the prediction time period comprises a plurality of search moments;
and arranging the plurality of sub-prediction search volumes according to the sequence of the corresponding search time to obtain a preset search volume in the prediction time period, wherein the preset search volume comprises the plurality of sub-prediction search volumes.
Optionally, the input module 401 is configured to:
acquiring a promotion strategy of the target promotion information, wherein the promotion strategy comprises at least one of promotion audiences, promotion platforms and promotion modes of the target promotion information;
converting the promotion strategy into a corresponding promotion vector through a vector conversion scheme;
and inputting the popularization vector into the target prediction model to obtain an initial search quantity of the popularization vector output by the target prediction model, wherein the initial search quantity is a search quantity generated based on a popularization strategy.
Optionally, the first obtaining module 402 is configured to:
acquiring a history sub-search quantity of each history time in a history period, wherein the history period comprises a plurality of history times, and each history time corresponds to one history sub-search quantity;
and inputting the white noise sequence and the historical sub-search quantities arranged according to the sequence of the historical moments into an autoregressive and moving average model to obtain a plurality of floating search quantities output by the autoregressive and moving average model, wherein each floating search quantity corresponds to one historical sub-search quantity according to the sequence of the historical moments.
Optionally, the apparatus is further configured to:
acquiring a historical time sequence formed by a plurality of historical sub-search quantities;
determining whether the historical time series is a static time series, wherein the static time series is used for indicating that the mean, the variance and the covariance of the historical time series do not change along with time;
and if the historical time sequence is determined to be a static time sequence, obtaining model parameters of an autoregressive and moving average model according to the static time sequence, wherein the model parameters are used for adjusting balance between model complexity and prediction accuracy, the model complexity is obtained through the number of the parameters of the model, and the prediction accuracy is obtained through a model linear fitting degree evaluation scheme.
Optionally, the apparatus is further configured to:
if the historical time sequence is determined to be a non-static time sequence, acquiring a part of the non-static sequence in the historical time sequence by adopting an autoregressive model;
determining a sequence difference value between the historical time sequence and the non-static sequence;
and obtaining model parameters of the autoregressive and moving average models according to the sequence difference, wherein the model parameters are used for adjusting balance between model complexity and prediction accuracy, the model complexity is obtained through the parameter number of the models, and the prediction accuracy is obtained through a model linear fitting degree evaluation scheme.
Optionally, the apparatus is further configured to:
acquiring a sample popularization strategy and a sample search amount corresponding to the sample popularization strategy;
inputting the sample popularization strategy into the initial prediction model to obtain a search quantity result output by the initial prediction model;
and under the condition that the sample search volume is inconsistent with the search volume result, adjusting the model parameters of the initial prediction model until the sample search volume is consistent with the search volume result to obtain the target prediction model.
According to another aspect of the embodiments of the present application, there is provided an electronic device, as shown in fig. 5, including a memory 503, a processor 501, a communication interface 502, and a communication bus 504, where the memory 503 stores a computer program that can be executed on the processor 501, the memory 503 and the processor 501 communicate through the communication interface 502 and the communication bus 504, and the processor 501 executes the computer program to implement the steps of the method.
The memory and the processor in the electronic equipment are communicated with the communication interface through a communication bus. The communication bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
There is also provided, in accordance with yet another aspect of an embodiment of the present application, a computer-readable medium having non-volatile program code executable by a processor.
Optionally, in an embodiment of the present application, a computer readable medium is configured to store program code for the processor to execute the above method.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment is not described herein again.
When the embodiments of the present application are specifically implemented, reference may be made to the above embodiments, and corresponding technical effects are achieved.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially implemented or make a contribution to the prior art, or may be implemented in the form of a software product stored in a storage medium and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk. It is noted that, in this document, relational terms such as "first" and "second," and the like, may be 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. Also, 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 an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for predicting an information search amount, the method comprising:
inputting a promotion strategy of target promotion information into a target prediction model to obtain an initial search quantity of the target promotion information output by the target prediction model, wherein the target prediction model is obtained based on the initial prediction model;
obtaining a plurality of floating search quantities of the target popularization information in a prediction time period by adopting an autoregressive and moving average model, wherein the floating search quantities are obtained based on historical search quantities of the target popularization information in a historical time period;
and obtaining the predicted search amount of the target popularization information in a prediction time period according to the initial search amount and the plurality of floating search amounts.
2. The method of claim 1, wherein the obtaining the predicted search volume of the target promotional information over a prediction period according to the initial search volume and the plurality of floating search volumes comprises:
increasing the initial search quantity on the basis of each floating search quantity to obtain a plurality of sub-prediction search quantities, wherein each floating search quantity corresponds to one search time in the prediction time period, and the prediction time period comprises a plurality of search times;
and arranging the plurality of sub-prediction search volumes according to the sequence of the corresponding search time to obtain a preset search volume in the prediction time period, wherein the preset search volume comprises a plurality of sub-prediction search volumes.
3. The method of claim 1, wherein the inputting the promotion strategy of the target promotion information into a target prediction model, and obtaining the initial search amount of the target promotion information output by the target prediction model comprises:
acquiring a promotion strategy of the target promotion information, wherein the promotion strategy comprises at least one of promotion audiences, promotion platforms and promotion modes of the target promotion information;
converting the promotion strategy into a corresponding promotion vector through a vector conversion scheme;
and inputting the popularization vector into the target prediction model to obtain an initial search quantity of the popularization vector output by the target prediction model, wherein the initial search quantity is a search quantity generated based on the popularization strategy.
4. The method of claim 1, wherein the obtaining a plurality of floating search quantities of the target promotion information within a prediction period by using an autoregressive and moving average model comprises:
acquiring a history sub-search quantity of each history time in a history period, wherein the history period comprises a plurality of history times, and each history time corresponds to one history sub-search quantity;
and inputting the white noise sequence and the historical sub-search quantities arranged according to the sequence of the historical moments into the autoregressive and moving average model to obtain a plurality of floating search quantities output by the autoregressive and moving average model, wherein each floating search quantity corresponds to one historical sub-search quantity according to the sequence of the historical moments.
5. The method of claim 4, wherein prior to obtaining the historical sub-search amount for each historical time in the historical period, the method further comprises:
acquiring a historical time sequence formed by a plurality of historical sub-search quantities;
determining whether the historical time series is a static time series, wherein the static time series is used for indicating that the mean, the variance and the covariance of the historical time series do not change along with time;
and if the historical time sequence is determined to be a static time sequence, obtaining model parameters of an autoregressive and moving average model according to the static time sequence, wherein the model parameters are used for adjusting balance between model complexity and prediction accuracy, the model complexity is obtained through the parameter number of the model, and the prediction accuracy is obtained through a model linear fitting degree evaluation scheme.
6. The method of claim 5, wherein after determining whether the historical time series is a static time series, the method further comprises:
if the historical time sequence is determined to be a non-static time sequence, acquiring a part of non-static sequences in the historical time sequence by adopting an autoregressive model;
determining a sequence difference value of the historical time sequence and the non-static sequence;
and obtaining model parameters of an autoregressive and moving average model according to the sequence difference, wherein the model parameters are used for adjusting balance between model complexity and prediction accuracy, the model complexity is obtained through the parameter number of the model, and the prediction accuracy is obtained through a model linear fitting degree evaluation scheme.
7. The method of claim 1, wherein before entering the promotion strategy for the target promotion information into the target prediction model, the method further comprises:
obtaining a sample popularization strategy and a sample search amount corresponding to the sample popularization strategy;
inputting the sample popularization strategy into the initial prediction model to obtain a search quantity result output by the initial prediction model;
and under the condition that the sample search volume is inconsistent with the search volume result, adjusting the model parameters of the initial prediction model until the sample search volume is consistent with the search volume result to obtain the target prediction model.
8. An apparatus for predicting an information search amount, the apparatus comprising:
the system comprises an input module, a target prediction module and a target search module, wherein the input module is used for inputting a promotion strategy of target promotion information into a target prediction model to obtain an initial search amount of the target promotion information output by the target prediction model, and the target prediction model is obtained based on the initial prediction model;
the first obtaining module is used for obtaining a plurality of floating search quantities of the target popularization information in a prediction time period by adopting an autoregressive and moving average model, wherein the floating search quantities are obtained based on historical search quantities of the target popularization information in a historical time period;
and the second obtaining module is used for obtaining the predicted search amount of the target popularization information in a prediction time period according to the initial search amount and the plurality of floating search amounts.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 7 when executing a program stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110921141.7A CN113554473A (en) | 2021-08-11 | 2021-08-11 | Information search amount prediction method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110921141.7A CN113554473A (en) | 2021-08-11 | 2021-08-11 | Information search amount prediction method and device, electronic equipment and readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113554473A true CN113554473A (en) | 2021-10-26 |
Family
ID=78105525
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110921141.7A Pending CN113554473A (en) | 2021-08-11 | 2021-08-11 | Information search amount prediction method and device, electronic equipment and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113554473A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117473144A (en) * | 2023-12-27 | 2024-01-30 | 深圳市活力天汇科技股份有限公司 | Method for storing route data, computer equipment and readable storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070239703A1 (en) * | 2006-03-31 | 2007-10-11 | Microsoft Corporation | Keyword search volume seasonality forecasting engine |
CN103368811A (en) * | 2012-04-06 | 2013-10-23 | 华为终端有限公司 | Bandwidth distribution method and equipment |
CN104182810A (en) * | 2014-09-09 | 2014-12-03 | 莱芜钢铁集团电子有限公司 | Dynamic gas balance control 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 |
CN106779859A (en) * | 2016-12-27 | 2017-05-31 | 南京安讯科技有限责任公司 | A kind of real-time Method for Sales Forecast method of mobile terminal product |
CN112070272A (en) * | 2020-08-11 | 2020-12-11 | 南瑞集团有限公司 | Method and device for predicting icing thickness of power transmission line |
CN112270569A (en) * | 2020-11-02 | 2021-01-26 | 创新奇智(成都)科技有限公司 | Advertisement putting method and device, electronic equipment and storage medium |
-
2021
- 2021-08-11 CN CN202110921141.7A patent/CN113554473A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070239703A1 (en) * | 2006-03-31 | 2007-10-11 | Microsoft Corporation | Keyword search volume seasonality forecasting engine |
CN103368811A (en) * | 2012-04-06 | 2013-10-23 | 华为终端有限公司 | Bandwidth distribution method and equipment |
CN104182810A (en) * | 2014-09-09 | 2014-12-03 | 莱芜钢铁集团电子有限公司 | Dynamic gas balance control 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 |
CN106779859A (en) * | 2016-12-27 | 2017-05-31 | 南京安讯科技有限责任公司 | A kind of real-time Method for Sales Forecast method of mobile terminal product |
CN112070272A (en) * | 2020-08-11 | 2020-12-11 | 南瑞集团有限公司 | Method and device for predicting icing thickness of power transmission line |
CN112270569A (en) * | 2020-11-02 | 2021-01-26 | 创新奇智(成都)科技有限公司 | Advertisement putting method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
洪新军: "《大数据挖掘及分析研究》", 31 December 2018, 北京工业大学出版社, pages: 106 - 108 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117473144A (en) * | 2023-12-27 | 2024-01-30 | 深圳市活力天汇科技股份有限公司 | Method for storing route data, computer equipment and readable storage medium |
CN117473144B (en) * | 2023-12-27 | 2024-03-29 | 深圳市活力天汇科技股份有限公司 | Method for storing route data, computer equipment and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200118145A1 (en) | Characterizing and Modifying User Experience of Computing Environments Based on Behavior Logs | |
CN110008973B (en) | Model training method, method and device for determining target user based on model | |
CN109711929A (en) | Business recommended method and device based on prediction model | |
US20200074504A1 (en) | Change Point Detection in a Multi-Armed Bandit Recommendation System | |
CN111061979A (en) | User label pushing method and device, electronic equipment and medium | |
CN113763019A (en) | User information management method and device | |
Toyama et al. | Reinforcement learning with parsimonious computation and a forgetting process | |
CN111667024B (en) | Content pushing method, device, computer equipment and storage medium | |
Satapathy et al. | Class point approach for software effort estimation using soft computing techniques | |
CN113780479A (en) | Periodic prediction model training method and device, and periodic prediction method and equipment | |
CN113554473A (en) | Information search amount prediction method and device, electronic equipment and readable storage medium | |
Tkachenko et al. | Customer simulation for direct marketing experiments | |
CN111680213A (en) | Information recommendation method, data processing method and device | |
CN112906896A (en) | Information processing method and device and computing equipment | |
CN111177564B (en) | Product recommendation method and device | |
CN116578400A (en) | Multitasking data processing method and device | |
CN113449176A (en) | Recommendation method and device based on knowledge graph | |
US20150134443A1 (en) | Testing a marketing strategy offline using an approximate simulator | |
US11200989B1 (en) | Aperiodic data driven cognitive control system | |
CN111784091B (en) | Method and device for processing information | |
CN113393269A (en) | Method and device for determining conversion rate of contact medium, electronic equipment and storage medium | |
CN111339432A (en) | Recommendation method and device of electronic object and electronic equipment | |
CN109472454B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
CN112348587B (en) | Information pushing method and device and electronic equipment | |
US12038823B2 (en) | Hierarchical attention time-series (HAT) model for behavior prediction |
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 |