CN113590962B - Flow data prediction system, method, computer equipment and medium - Google Patents
Flow data prediction system, method, computer equipment and medium Download PDFInfo
- Publication number
- CN113590962B CN113590962B CN202110887163.6A CN202110887163A CN113590962B CN 113590962 B CN113590962 B CN 113590962B CN 202110887163 A CN202110887163 A CN 202110887163A CN 113590962 B CN113590962 B CN 113590962B
- Authority
- CN
- China
- Prior art keywords
- determining
- information
- holiday
- flow
- floating
- 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 52
- 238000012937 correction Methods 0.000 claims abstract description 36
- 230000015654 memory Effects 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 5
- 239000000470 constituent Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005094 computer simulation Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000000926 separation 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
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data monitoring, and particularly discloses a flow data prediction system, a method, computer equipment and a medium, wherein the system comprises: the system comprises a time period determining module, a basic flow generating module, a floating proportion determining module and a correcting module, wherein the basic flow generating module is used for sequentially inputting different time periods into a trained flow model to obtain basic flow; the floating proportion determining module is used for generating a basic flow with a floating value; the correction module is used for correcting the basic flow with the floating value according to weather. According to the invention, different time periods are sequentially input into the trained flow model to obtain the basic flow, the floating proportion is determined by the floating proportion determining module, the basic flow with the floating value is determined based on the basic flow and the floating proportion, and in addition, the basic flow with the floating value is corrected according to weather information, so that the prediction accuracy is high, and the popularization is convenient.
Description
Technical Field
The invention relates to the technical field of data monitoring, in particular to a flow data prediction system, a flow data prediction method, computer equipment and a medium.
Background
Along with the continuous development of computer application technology, the flow data prediction technology is increasingly applied to various different scenes to obtain people flow data in different application scenes, such as scenic spots, stations, large conference sites, sports event sites and other large activity sites in advance, so that in different application scenes, work arrangement of field staff is performed in advance according to the people flow, field management and control schemes are formulated, emergency occurrence is prevented, and in various application scenes, people flow data are often influenced by various factors such as holidays, weather and the like, so that it is quite significant to provide a flow prediction system and method with high prediction accuracy.
Disclosure of Invention
The present invention is directed to a traffic data prediction system, a method, a computer device and a medium, so as to solve the problems set forth in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a traffic data prediction system, the system comprising:
the time period determining module is used for acquiring the holiday information and generating different time periods according to the holiday information，/>Indicates the start date,/->Indicating the end date;
a basic flow generation module for sequentially inputting different time periods into the trained flow modelIn (3) obtaining the basic flow->；
The floating proportion determining module is used for obtaining the access quantity and the operation quantity in the unit time of the promoted file, wherein the operation quantity at least comprises the collection quantity, the sharing quantity and the search quantity, determining the floating proportion according to the access quantity and the operation quantity, and determining the basic flow with the floating value based on the basic flow and the floating proportionWherein the number of people is intendedEffective value->，/>Representing historical intent number->Representing the popularization return rate, the%>Representing the amount of access->Representing the number of valid values corresponding to each access amount, < >> ，/>Representing the operation amounts of different types of operations and the number of effective values corresponding to each operation amount respectively;
the correction module is used for acquiring weather state information in a preset period, generating correction parameters based on the weather state information, correcting the basic flow with the floating value according to the correction parameters, and obtaining the predicted flow,Wherein->Representing a calculation model used in determining correction parameters;
the period determining module specifically includes:
the position determining unit is used for acquiring the holiday information, determining the center moment according to the length of the holiday in the holiday information, and calculating the position proportion of the center moment in one year;
the radius determining unit is used for determining the light-rich season information and determining the influence radius of each holiday based on the light-rich season information;
the first execution unit is used for generating a holiday table based on the position proportion and the influence radius of the holiday and determining different time periods according to the holiday table;
the period determination module further includes:
the search unit is used for determining keywords, inputting the keywords into a search class App and obtaining search contents;
the file classifying unit is used for classifying the search content to obtain a text file, an image file and a video file;
a conversion unit configured to convert the video file into an audio file and an image file and convert the audio file into a text file when the search content is a video file;
and the second execution unit is used for respectively carrying out content identification on the acquired text file and the acquired image file and updating the light and vigorous season information according to the identification result.
The output of the period determining module in the above content is different periods, the period of the invention is different from the conventional period determination, and we can recall that the conventional period determination is a simple light-rich season, the time of one year is divided into two sections, and the span of one time section is very large due to the too small number of the divided sections, which is also related to the purpose of the section thereof, such as for scenic spots, the conventional section purpose is only to determine fare, and for the technical scheme of the invention, the purpose of the section is to predict flow better. The process of segmentation is to segment nodes according to vacation, the time period between different vacations is different, for example, summer holidays of students are between noon and mid-autumn, and the flow rate is higher than that of the time period between other vacations, so that it is significant to segment the time of one year according to the vacation nodes and then to perform subsequent operations according to the segmented time period.
The purpose of the floating proportion generation module is to generate a floating proportion, and then determine a basic flow with a floating value according to the floating proportion to form a data form of a+/-b.
The correction module corrects the basic flow with the floating value according to weather, and the correction basis is that weather prediction information is related to prediction time, in other words, weather on the open day is predicted to be more accurate than weather on the following day, so that the weather prediction information is changed continuously, correction parameters are changed continuously, and the correction process is a dynamic process, but the change amplitude is not large.
Firstly, converting vacation information into nodes, generating each time period, then adding light and vigorous season information such as scenic spots mainly of snowscapes in each time period, and reducing passenger flow in summer, so that passenger flow in the labor section vacation is also reduced, the specific influence mode is to influence the radius, and if the radius is zero, the vacation influence factor is reduced to zero in practice; however, for example, in scenic spots mainly including snowscenes, the primordial holidays are important, and the holiday time is 3 days, but in practice, many tourists can "lengthen" the holiday by asking for a holiday, etc., and reflect the holiday into the modules, so that the radius is increased. It is worth mentioning that the radius of influence is typically in days.
As a further limitation of the technical solution of the present invention, the floating proportion determining module specifically includes:
the effective value determining unit is used for acquiring the access quantity and the operation quantity in the popularization file and determining the effective value of the popularization file according to the access quantity and the operation quantity;
the report rate generating unit is used for reading the calculated popularization report rate and correcting the report rate based on the effective value;
the comparison unit is used for determining the number of intention people according to the corrected return rate and comparing the number of intention people with the corresponding historical intention people;
and the floating proportion determining unit is used for determining the floating proportion according to the comparison result.
As a further limitation of the technical solution of the present invention, the effective value determining unit specifically includes:
the weight value determining subunit is used for acquiring the operation amounts in the popularization file and determining weight values of different operations in the operation amounts;
the interest value calculating subunit is used for calculating the interest value of the corresponding operation according to the weight value;
and the accumulation subunit is used for accumulating interest values of different operations and determining the effective value of the popularization file based on the accumulated interest values, the access quantity and the operation quantity of the popularization file.
As a further limitation of the technical solution of the present invention, the system further includes:
the receiving module is used for receiving the user access request and setting the number of requests as one;
the identity confirmation module is used for acquiring login information containing a user ID and determining user registration information corresponding to the login information;
the first judging module is used for judging whether the login information containing the user ID is the same as the user registration information corresponding to the login information, and if the login information containing the user ID is the same as the user registration information corresponding to the login information, the verification is passed;
the second judging module is used for judging the request times and the threshold value if the login information containing the user ID is different from the user registration information corresponding to the login information, repeatedly receiving the user access requests and increasing the request times if the request times are smaller than the threshold value; and if the number of requests is greater than the threshold value, stopping receiving the user access request.
The above is an auxiliary function, which is an additional function of the technical solution of the present invention, that is, for a simple permission determination of a person using the present system, not all persons have access rights, and the person having access rights may be a manager or a partner, because the determination of the flow model in the technical solution of the present invention may use sample data of other partners.
The technical scheme of the invention also provides a flow data prediction method, which specifically comprises the following steps:
acquiring vacation information, and generating different time periods according to the vacation information;
sequentially inputting different time periods into the trained flow model to obtain basic flow;
obtaining access quantity and operation quantity in unit time of a popularization file, determining a floating proportion according to the access quantity and the operation quantity, and determining a basic flow with a floating value based on the basic flow and the floating proportion; the operation quantity at least comprises collection quantity, sharing quantity and search quantity;
and acquiring weather state information in a preset period, generating correction parameters based on the weather state information, and correcting the basic flow with the floating value according to the correction parameters to obtain the predicted flow.
As a further limitation of the technical solution of the present invention, the obtaining the holiday information, and generating different time periods according to the holiday information specifically includes:
acquiring holiday information, determining a central moment according to the length of the holiday in the holiday information, and calculating the position proportion of the central moment in one year;
determining light-rich season information, and determining the influence radius of each holiday based on the light-rich season information;
a holiday table is generated based on the location ratio and the influence radius of the holiday, and different time periods are determined according to the holiday table.
The technical scheme of the invention also provides computer equipment, which comprises one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the program code realizes the functions of the flow data prediction method when being loaded and executed by the one or more processors.
The technical scheme of the invention also provides computer equipment, at least one program code is stored in the computer storage medium, and the program code realizes the functions of the flow data prediction method when being loaded and executed by a processor.
Compared with the prior art, the invention has the beneficial effects that:
1. the basic flow generation module is used for sequentially inputting different time periods into the trained flow model to obtain basic flow; the floating proportion determining module is used for obtaining the access quantity and the operation quantity in the unit time of the promoted file, determining the floating proportion according to the access quantity and the operation quantity, and determining the basic flow with a floating value based on the basic flow and the floating proportion; the correction module is used for acquiring weather state information in a preset period, generating correction parameters based on the weather state information, correcting the basic flow with the floating value according to the correction parameters, and obtaining the predicted flow.
2. According to the invention, different time periods are sequentially input into a trained flow model to obtain a basic flow, a floating proportion is determined through a floating proportion determining module, and the basic flow with a floating value is determined based on the basic flow and the floating proportion.
3. The invention also corrects the basic flow with the floating value according to weather information, has high prediction accuracy and is convenient for popularization.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 shows a first component block diagram of a traffic data prediction system.
Fig. 2 shows a first constituent structural diagram of a period determination module in a traffic data prediction system.
Fig. 3 shows a second constituent structural diagram of the period determination module in the traffic data prediction system.
Fig. 4 shows a constitution diagram of a floating ratio determination module in the flow data prediction system.
Fig. 5 shows a constitution diagram of the effective value determination unit in the floating ratio determination module.
Fig. 6 shows a second component block diagram of the traffic data prediction system.
Fig. 7 shows a flow diagram of a flow data prediction method.
Fig. 8 shows a sub-flow block diagram of a traffic data prediction method.
Fig. 9 shows a holiday period chart of 2021 from 4 months to 6 months.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, etc. may be used in embodiments of the invention to describe different modules, these modules should not be limited by these terms. These terms are only used to distinguish one module of the same type from another. For example, a first determination module may also be referred to as a second determination module without necessarily requiring or implying any such actual such relationship or order between such entities or operations without departing from the scope of embodiments of the present invention. Similarly, the second determination module may also be referred to as the first determination module. 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.
Example 1
Fig. 1 shows a first component structure diagram of a traffic data prediction system, and in an embodiment of the present invention, a traffic data prediction system, a method, a computer device, and a medium, where the system 10 specifically includes:
a time period determining module 11 for acquiring vacation information and generating different time periods according to the vacation information，/>The start date and the end date are indicated.
A basic flow generation module 12 for sequentially inputting different time periods into the trained flow modelIn (3) obtaining the basic flow->；
A floating proportion determining module 13 for obtaining access amount and operation amount of the promoted file in unit time, wherein the operation amount at least comprises collection amount, sharing amount and search amount, determining a floating proportion according to the access amount and the operation amount, and determining a basic flow with a floating value based on the basic flow and the floating proportionWherein the number of intention people is->Effective value->，/>Representing historical intent number->Represents the popularization return rate and the application rate,representing the amount of access->Representing the number of valid values corresponding to each access amount, < >> ，/>Representing the operation amounts of different types of operations and the number of effective values corresponding to each operation amount respectively;
a correction module 14 for acquiring weather state information within a preset period, generating correction parameters based on the weather state information, and correcting the basic flow with the floating value according to the correction parameters to obtain a predicted flow,Wherein->Representing a computational model that determines the correction parameters.
The output of the period determining module in the above content is different periods, the period of the invention is different from the conventional period determination, and we can recall that the conventional period determination is a simple light-rich season, the time of one year is divided into two sections, and the span of one time section is very large due to the too small number of the divided sections, which is also related to the purpose of the section thereof, such as for scenic spots, the conventional section purpose is only to determine fare, and for the technical scheme of the invention, the purpose of the section is to predict flow better. The process of segmentation is to segment nodes according to vacation, the time period between different vacations is different, for example, summer holidays of students are between noon and mid-autumn, and the flow rate is higher than that of time periods between other vacations, so that it is significant to segment a time of one year according to the vacation nodes and then to perform subsequent operations according to the segmented time period.
The basic flow generation module needs to carry out a simple description on a flow model, and the most commonly used flow model generation method is generated by a sample fitting method, so that the method is very suitable for actual engineering, is also very effective, and has higher and higher accuracy along with the increase of the number of samples. It should be noted that, the samples are not only historical data of own scenes, and model generation according to samples of similar scale scenes is also a feasible scheme.
The purpose of the floating proportion generation module is to generate a floating proportion, and then determine a basic flow with a floating value according to the floating proportion to form a data form of a+/-b.
The correction module is used for correcting the basic flow with the floating value according to weather, firstly, the weather state in a certain period needs to be acquired, the weather state can directly influence the rising or falling of the passenger flow, therefore, the influence of the weather state on the passenger flow is also required to be estimated according to the weather state in a certain period, the passenger flow influenced by the weather state, namely, the correction parameter is used for further correcting the basic flow with the floating value, the correction parameter is determined by using a calculation model, for example, different machine learning models are trained for different weather states, the model can predict the passenger flow influenced by the weather state by inputting the basic flow with the floating value into the machine learning model trained in advance, and the weather prediction information is related to the prediction time, in other words, the weather of the weather is predicted to be more accurate than the weather after the weather is predicted, so that the weather prediction information is changed continuously, the correction parameter is changed continuously, and the correction process is a dynamic process.
Fig. 2 shows a first component structural diagram of a period determining module in the traffic data prediction system, and the period determining module 11 specifically includes:
a position determining unit 111, configured to obtain vacation information, determine a center time according to a vacation length in the vacation information, and calculate a position proportion of the center time within a year;
a radius determining unit 112 for determining light-rich season information, and determining each holiday influence radius based on the light-rich season information;
the first execution unit 113 is configured to generate a holiday table based on the location proportion and the influence radius of the holiday, and determine different time periods according to the holiday table.
Firstly, converting vacation information into nodes, generating each time period, then adding light and vigorous season information such as scenic spots mainly of snowscapes in each time period, and reducing passenger flow in summer, so that passenger flow in the labor section is also reduced, the specific influence mode is to influence the radius, and if the radius is zero, the vacation influence factor is reduced to zero in practice; however, for example, in scenic spots mainly including snowscenes, the primordial holidays are important, and the holiday time is 3 days, but in practice, many tourists can "lengthen" the holiday by asking for a holiday, etc., and reflect the holiday into the modules, so that the radius is increased. It is worth mentioning that the radius of influence is typically in days.
For example, as shown in fig. 9, taking an example of a time interval of 2021, 4 months, 1 to 2021, 6 months, 30 days, which includes a Qingming festival, a labor festival, and an end noon festival, first, a center time is determined according to a holiday length, next, a holiday influence radius is determined in days based on light-rich season information, and finally, a holiday schedule is generated based on the center time and the influence radius of the holiday, so that 2021, 4 months, 1 to 2021, 6 months, 30 days are divided into a plurality of time periods according to different holidays and output.
Fig. 3 shows a second constituent structural diagram of a period determination module in the flow data prediction system, the period determination module 11 further including:
a search unit 114, configured to determine a keyword, input the keyword into a search class App, and obtain search content;
a file classifying unit 115, configured to classify the search content to obtain a text file, an image file, and a video file;
a conversion unit 116 for converting the video file into an audio file and an image file, and converting the audio file into a text file when the search content is a video file;
the second execution unit 117 is configured to perform content recognition on the acquired text file and image file, respectively, and update the light and strong season information according to the recognition result.
The light-rich season information is used for determining the influence radius of a holiday, wherein the light-rich season information can be changed, for example, if a popularization article finds that a scenic spot mainly including a snow scene is also in a summer holiday, the time of the light season of the scenic spot will be prolonged, and correspondingly, the influence radius of the summer holiday of the scenic spot will be prolonged, and it is noted that the influence radius of the holiday is not necessarily two continuous times, but also can be a multi-stage separation time.
Fig. 4 shows a component structure diagram of a floating proportion determining module in the flow data prediction system, and the floating proportion determining module 13 specifically includes:
an effective value determining unit 131, configured to obtain an access amount and an operation amount in a promotion file, and determine an effective value of the promotion file according to the access amount and the operation amount;
the report rate generating unit 132 is configured to read the calculated promotion report rate and correct the report rate based on the effective value;
the comparison unit 133 is configured to determine the number of intention people according to the corrected return rate, and compare the number of intention people with the corresponding historical intention people;
a floating ratio determining unit 134, configured to determine a floating ratio according to the comparison result.
The above describes the floating ratio workflow in detail, and from the rise of media technology, it is easier to popularize online, and this also describes from the side that the self media file has an effect on the flow, for convenience of explanation, the invention is described by specific examples: for example, a promotion document is an article, and the system can read the access amount and the operation amount of the article to further determine the effective value of the article, wherein the effective value is a value reflecting the promotion effect.
Fig. 5 shows a constitution diagram of an effective value determining unit in the floating ratio determining module, the effective value determining unit 131 specifically including:
a weight value determining subunit 1311, configured to obtain an operation amount in the promotion file, and determine weight values of different operations in the operation amount;
an interest value calculating subunit 1312, configured to calculate an interest value of the corresponding operation according to the weight value;
and an accumulation subunit 1313, configured to accumulate interest values of different operations, and determine an effective value of the promotion file based on the accumulated interest values and the access amount and the operation amount of the promotion file.
The effective value determining process is important, and as can be seen from the above, the purpose of the effective value is to obtain the popularization effect of the popularization file, taking the above article as an example, if the user agrees with the article, the user is interested, and if the user shares the article, the interest value of the user is higher, so that the interest value of the user can be determined based on the operation amount; it should be noted that, an access amount can be regarded as an interest value, and the user can be interested only by accessing the promotion file, because in the big data age, the personal interests are easy to obtain, and many existing promotion software are promoted according to the interests of the user, in other words, the corresponding software is regarded as belonging to the interests of the user as long as the user accesses the promotion file, so that an access amount can be regarded as an interest value.
The content flow is perfect, and it is to be noted that the sharing amount in the operation amount is more important than the access amount, and for the convenience of calculation, we set a unit, that is, an interest value, for example, one sharing amount is equivalent to 10 interest values, and one interest value is equivalent to 1 effective value, so that the operation amount can be distinguished, and the proportion determining process is more accurate.
Specifically, effective valueCan be expressed by the formula->Performing calculation of>Representing the amount of access->Representing the number of valid values corresponding to each access amount, < >>Representing collection amount, ->Representing the number of effective values corresponding to each collection>Representing the shared quantity->Representing the number of effective values corresponding to each sharing amount, +.>Representing search volume->Representing the number of valid values corresponding to each search quantity, and so on,，/>representing the operation amounts of other types of operations and the number of effective values corresponding to each operation amount respectively.
After determining the effective value, reading the popularization return rateThe promotion return rate is->It is an existing data, and different platforms send what articles have their predictions in different ways, which in today's big data age, accuracy is very high, but although accuracy is very high, there are exceptions, so it is necessary to correct the rate of return by a valid value.
Specifically, the correction method is to calculate the effective value of a certain timeMean effective value from history->Comparing to obtain an offset rate, and correcting the return rate according to the offset rate, wherein the corrected return rate can be expressed as +.>The method comprises the steps of carrying out a first treatment on the surface of the The corrected return rate is directly multiplied by the sum of the access quantity and the operation quantity, so that the intentional people number can be determined>Wherein->Representing the amount of access->Representing collection amount, ->Representing the shared quantity->Representing the search volume, and so on, +.>An operation amount representing other types of operations; the number of people who intend to do so>Historical intent number corresponding to Uniform time period +.>Performing comparison, and determining floating proportion according to the comparison result>。
The final process of the above process is to generate a proportionSome redundancy may be left, because since the number of people is calculated, the number of people is not directly used as a predicted value; on the one hand, the self-media only affects one factor of the flow, but cannot be considered as a whole, the real prediction process of the invention is completed by the basic flow generation module, on the other hand, the data of the self-media greatly fluctuates, and the acquired intention number is actually contained in the basic flow. The purpose of the above is therefore to produce a ratio, for example, how much fire is in the scenic spot today compared to the last year, based on the comparisonAs a result, the floating ratio is determined, and then the base flow is corrected, and a base flow with floating flow is obtained>Wherein->Representing a trained flow model, +.>Representative period, & lt & gt>Indicates the start date,/->Indicating the end date.
Determining a base flow with float valuesLater, the influence of the weather state on the passenger flow volume in the time period is also considered, so that the passenger flow volume influenced by the weather state in the time period is required to be determined according to the weather state in the time period, namely, a correction parameter is required, and the correction parameter is used for further correcting the basic flow volume with the floating value to obtain the predicted flow volume>,Wherein->Representing a computational model used in determining the correction parameters.
Fig. 6 shows a second component block diagram of a traffic data prediction system, the system 10 further comprising:
a receiving module 15, configured to receive a user access request and set the number of requests to one;
the identity confirmation module 16 is configured to obtain login information including a user ID, and determine user registration information corresponding to the login information;
a first judging module 17, configured to judge whether login information including a user ID is the same as user registration information corresponding to the login information, and if the login information including the user ID is the same as the user registration information corresponding to the login information, pass verification;
the second judging module 18 is configured to judge the number of requests and the threshold value if the login information including the user ID is different from the user registration information corresponding to the login information, and repeatedly receive the user access request and increase the number of requests if the number of requests is less than the threshold value; and if the number of requests is greater than the threshold value, stopping receiving the user access request.
The above is an auxiliary function, which is an additional function of the technical solution of the present invention, that is, for a simple permission determination of a person using the present system, not all persons have access rights, and the person having access rights may be a manager or a partner, because the determination of the flow model in the technical solution of the present invention may use sample data of other partners.
Example 2
Fig. 7 shows a flow chart of a flow data prediction method, and in an embodiment of the present invention, there is further provided a flow data prediction method, where the method specifically includes:
step S200: acquiring vacation information, and generating different time periods according to the vacation information;
the step S200 is completed by the period determination module 11;
step S400: sequentially inputting different time periods into the trained flow model to obtain basic flow;
step S400 is completed by the base flow generation module 12;
step S600: obtaining access quantity and operation quantity in unit time of a popularization file, determining a floating proportion according to the access quantity and the operation quantity, and determining a basic flow with a floating value based on the basic flow and the floating proportion; the operation quantity at least comprises collection quantity, sharing quantity and search quantity;
the step S600 is completed by the floating proportion determining module 13;
step S800: acquiring weather state information in a preset period, generating correction parameters based on the weather state information, and correcting the basic flow with a floating value according to the correction parameters to obtain predicted flow;
the step S800 is completed by the correction module 14.
Fig. 8 shows a sub-flowchart of a traffic data prediction method, where the acquiring the holiday information and generating different time periods according to the holiday information specifically includes:
step S201: acquiring holiday information, determining a central moment according to the length of the holiday in the holiday information, and calculating the position proportion of the central moment in one year;
the step S201 is completed by the position determining unit 111;
step S203: determining light-rich season information, and determining the influence radius of each holiday based on the light-rich season information;
the step S203 is completed by the radius determination unit 112;
step S205: generating a holiday table based on the position proportion and the influence radius of the holiday, and determining different time periods according to the holiday table;
the step S205 is completed by the first execution unit 113.
It should be noted that the system and the method for predicting traffic data described in the foregoing are applicable to scenic spots, stations, large conference sites, sports events, and any other large activity sites where accurate prediction of traffic is required.
The functions that can be achieved by the flow data prediction method are all completed by computer equipment, the computer equipment comprises one or more processors and one or more memories, at least one program code is stored in the one or more memories, and the program code is loaded and executed by the one or more processors to achieve the functions of the flow data prediction method.
The processor takes out instructions from the memory one by one, analyzes the instructions, then completes corresponding operation according to the instruction requirement, generates a series of control commands, enables all parts of the computer to automatically, continuously and cooperatively act to form an organic whole, realizes the input of programs, the input of data, the operation and the output of results, and the arithmetic operation or the logic operation generated in the process is completed by the arithmetic unit; the Memory comprises a Read-Only Memory (ROM) for storing a computer program, and a protection device is arranged outside the Memory.
For example, a computer program may be split into one or more modules, one or more modules stored in memory and executed by a processor to perform the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the terminal device.
It will be appreciated by those skilled in the art that the foregoing description of the service device is merely an example and is not meant to be limiting, and may include more or fewer components than the foregoing description, or may combine certain components, or different components, such as may include input-output devices, network access devices, buses, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal device described above, and which connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used for storing computer programs and/or modules, and the processor may implement various functions of the terminal device by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function (such as an information acquisition template display function, a product information release function, etc.), and the like; the storage data area may store data created according to the use of the berth status display system (e.g., product information acquisition templates corresponding to different product types, product information required to be released by different product providers, etc.), and so on. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The modules/units integrated in the terminal device may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on this understanding, the present invention may implement all or part of the modules/units in the system of the above-described embodiments, or may be implemented by instructing the relevant hardware by a computer program, which may be stored in a computer-readable storage medium, and which, when executed by a processor, may implement the functions of the respective system embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
It should be noted that, in this document, 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.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (8)
1. A traffic data prediction system, the system comprising:
the time period determining module is used for acquiring the holiday information and generating different time periods according to the holiday information，/>Indicates the start date,/->Indicating the end date;
a basic flow generation module for sequentially inputting different time periods into the trained flow modelIn (1) obtaining a foundation；
The floating proportion determining module is used for obtaining the access quantity and the operation quantity in the unit time of the promoted file, wherein the operation quantity at least comprises the collection quantity, the sharing quantity and the search quantity, determining the floating proportion according to the access quantity and the operation quantity, and determining the basic flow with the floating value based on the basic flow and the floating proportionWherein the number of people is intendedEffective value->，/>Representing historical intent number->Representing the popularization return rate, the%>Representing the amount of access->Representing the number of valid values corresponding to each access amount, < >>，/>Representing the operation amounts of different types of operations and the number of effective values corresponding to each operation amount respectively;
a correction module for acquiring presetWeather state information in a period of time, generating correction parameters based on the weather state information, and correcting the basic flow with a floating value according to the correction parameters to obtain a predicted flow，Wherein->Representing a calculation model used in determining correction parameters;
the period determining module specifically comprises the following units:
the position determining unit is used for acquiring the holiday information, determining the center moment according to the length of the holiday in the holiday information, and calculating the position proportion of the center moment in one year;
the radius determining unit is used for determining the light-rich season information and determining the influence radius of each holiday based on the light-rich season information;
the first execution unit is used for generating a holiday table based on the position proportion and the influence radius of the holiday and determining different time periods according to the holiday table;
the period determination module further includes the following units:
the search unit is used for determining keywords, inputting the keywords into a search class App and obtaining search contents;
the file classifying unit is used for classifying the search content to obtain a text file, an image file and a video file;
a conversion unit configured to convert the video file into an audio file and an image file and convert the audio file into a text file when the search content is a video file;
and the second execution unit is used for respectively carrying out content identification on the acquired text file and the acquired image file and updating the light and vigorous season information according to the identification result.
2. The flow data prediction system of claim 1, wherein the float ratio determination module specifically comprises:
the effective value determining unit is used for acquiring the access quantity and the operation quantity in the popularization file and determining the effective value of the popularization file according to the access quantity and the operation quantity;
the report rate generating unit is used for reading the calculated popularization report rate and correcting the report rate based on the effective value;
the comparison unit is used for determining the number of intention people according to the corrected return rate and comparing the number of intention people with the corresponding historical intention people;
and the floating proportion determining unit is used for determining the floating proportion according to the comparison result.
3. The flow rate data prediction system according to claim 2, wherein the effective value determination unit specifically includes:
the weight value determining subunit is used for acquiring the operation amounts in the popularization file and determining weight values of different operations in the operation amounts;
the interest value calculating subunit is used for calculating the interest value of the corresponding operation according to the weight value;
and the accumulation subunit is used for accumulating interest values of different operations and determining the effective value of the popularization file based on the accumulated interest values, the access quantity and the operation quantity of the popularization file.
4. The flow data prediction system of claim 1, wherein the system further comprises:
the receiving module is used for receiving the user access request and setting the number of requests as one;
the identity confirmation module is used for acquiring login information containing a user ID and determining user registration information corresponding to the login information;
the first judging module is used for judging whether the login information containing the user ID is the same as the user registration information corresponding to the login information, and if the login information containing the user ID is the same as the user registration information corresponding to the login information, the verification is passed;
the second judging module is used for judging the request times and the threshold value if the login information containing the user ID is different from the user registration information corresponding to the login information, repeatedly receiving the user access requests and increasing the request times if the request times are smaller than the threshold value; and if the number of requests is greater than the threshold value, stopping receiving the user access request.
5. A flow data prediction method implemented based on the flow data prediction system according to any one of claims 1 to 4, characterized in that the method specifically comprises:
acquiring vacation information, and generating different time periods according to the vacation information;
sequentially inputting different time periods into the trained flow model to obtain basic flow;
obtaining access quantity and operation quantity in unit time of a popularization file, determining a floating proportion according to the access quantity and the operation quantity, and determining a basic flow with a floating value based on the basic flow and the floating proportion; the operation quantity at least comprises collection quantity, sharing quantity and search quantity;
and acquiring weather state information in a preset period, generating correction parameters based on the weather state information, and correcting the basic flow with the floating value according to the correction parameters to obtain the predicted flow.
6. The traffic data prediction method according to claim 5, wherein the acquiring holiday information and generating different time periods according to the holiday information specifically comprises:
acquiring holiday information, determining a central moment according to the length of the holiday in the holiday information, and calculating the position proportion of the central moment in one year;
determining light-rich season information, and determining the influence radius of each holiday based on the light-rich season information;
a holiday table is generated based on the location ratio and the influence radius of the holiday, and different time periods are determined according to the holiday table.
7. A computer device comprising one or more processors and one or more memories, the one or more memories having stored therein at least one program code that, when loaded and executed by the one or more processors, performs the functions of the traffic data prediction method of any of claims 5 to 6.
8. A computer storage medium having stored therein at least one program code which, when loaded and executed by a processor, performs the functions of the flow data prediction method of any one of claims 5 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110887163.6A CN113590962B (en) | 2021-08-03 | 2021-08-03 | Flow data prediction system, method, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110887163.6A CN113590962B (en) | 2021-08-03 | 2021-08-03 | Flow data prediction system, method, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113590962A CN113590962A (en) | 2021-11-02 |
| CN113590962B true CN113590962B (en) | 2023-07-25 |
Family
ID=78254566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110887163.6A Active CN113590962B (en) | 2021-08-03 | 2021-08-03 | Flow data prediction system, method, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113590962B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113592196A (en) * | 2021-08-23 | 2021-11-02 | 田继伟 | Flow data prediction system, method, computer equipment and medium |
| CN114493726A (en) * | 2022-04-06 | 2022-05-13 | 萨科(深圳)科技有限公司 | Order monitoring method and monitoring platform |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408143A (en) * | 2014-12-01 | 2015-03-11 | 北京国双科技有限公司 | Webpage data monitoring method and device |
| CN110443314A (en) * | 2019-08-08 | 2019-11-12 | 中国工商银行股份有限公司 | Scenic spot passenger flow forecast method and device based on machine learning |
| CN110689184A (en) * | 2019-09-21 | 2020-01-14 | 广东毓秀科技有限公司 | Method for predicting rail traffic stream of people through deep learning |
| CN110910659A (en) * | 2019-11-29 | 2020-03-24 | 腾讯云计算（北京）有限责任公司 | Traffic flow prediction method, device, equipment and storage medium |
| CN112733002A (en) * | 2020-12-02 | 2021-04-30 | 珠海南方数字娱乐公共服务中心 | Brand promotion key data extraction and analysis method based on new media platform |
| CN113592196A (en) * | 2021-08-23 | 2021-11-02 | 田继伟 | Flow data prediction system, method, computer equipment and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10719521B2 (en) * | 2017-09-18 | 2020-07-21 | Google Llc | Evaluating models that rely on aggregate historical data |
-
2021
- 2021-08-03 CN CN202110887163.6A patent/CN113590962B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408143A (en) * | 2014-12-01 | 2015-03-11 | 北京国双科技有限公司 | Webpage data monitoring method and device |
| CN110443314A (en) * | 2019-08-08 | 2019-11-12 | 中国工商银行股份有限公司 | Scenic spot passenger flow forecast method and device based on machine learning |
| CN110689184A (en) * | 2019-09-21 | 2020-01-14 | 广东毓秀科技有限公司 | Method for predicting rail traffic stream of people through deep learning |
| CN110910659A (en) * | 2019-11-29 | 2020-03-24 | 腾讯云计算（北京）有限责任公司 | Traffic flow prediction method, device, equipment and storage medium |
| CN112733002A (en) * | 2020-12-02 | 2021-04-30 | 珠海南方数字娱乐公共服务中心 | Brand promotion key data extraction and analysis method based on new media platform |
| CN113592196A (en) * | 2021-08-23 | 2021-11-02 | 田继伟 | Flow data prediction system, method, computer equipment and medium |
Non-Patent Citations (3)
| Title |
|---|
| Hybrid holiday traffic predictions in cellular networks;Meng Xu et al.;《NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium》;1-6 * |
| 南京旅游客源市场及旅游流的时空特征研究————基于手机信令的分析;王茜雅;《中国优秀硕士学位论文全文数据库 经济与管理科学辑》;J153-87 * |
| 基于深度学习的特色小镇热点区域预测模型研究;费城;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;C038-1021 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113590962A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113590962B (en) | Flow data prediction system, method, computer equipment and medium | |
| Kumar et al. | Short-term traffic flow prediction using seasonal ARIMA model with limited input data | |
| CN111881158B (en) | Processing method, device, computer system and readable storage medium for managing report data | |
| US10942931B2 (en) | Automated database record activation using predictive modeling of database access | |
| CN113592196A (en) | Flow data prediction system, method, computer equipment and medium | |
| Rafei et al. | Big data for finite population inference: Applying quasi-random approaches to naturalistic driving data using Bayesian additive regression trees | |
| Englberger et al. | Two-stage stochastic master production scheduling under demand uncertainty in a rolling planning environment | |
| CN112036795A (en) | Method, device, equipment and storage medium for determining medicine purchasing plan | |
| CN111815420B (en) | Matching method, device and equipment based on trusted asset data | |
| Gao et al. | Cost overruns and formal risk assessment program in US rail transit projects | |
| CN113838303B (en) | Parking lot recommendation method and device, electronic equipment and storage medium | |
| CN113610230A (en) | Training method, prediction method, device, computer system and storage medium | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN113284343B (en) | Traffic monitoring system and method based on intelligent traffic Internet of things | |
| Antunes et al. | A review of heteroscedasticity treatment with Gaussian processes and quantile regression meta-models | |
| KR102549230B1 (en) | Method, apparatus and program for providing attorney work analysis service using ai-based big data analysis | |
| CN114491134B (en) | Trademark registration success rate analysis method and system | |
| GB2584862A (en) | System and method for populating a database with occupancy data of parking facilities | |
| Kamolov et al. | Digital innovation technologies in public governance: Budget geolocation system | |
| Bomboi et al. | On the stochastic vehicle routing problem with time windows, correlated travel times, and time dependency | |
| Ghandeharioun et al. | Exploring deep learning approaches for short-term passenger demand prediction | |
| CN114548463A (en) | Line information prediction method, line information prediction device, computer equipment and storage medium | |
| CN113240192A (en) | Model training and predicting method and device, computer equipment and storage medium | |
| López-Tamayo et al. | Minimum wages, youth employment and spatial spillovers: New evidence for Spain | |
| Orlowski et al. | Decision processes based on IoT data for sustainable smart cities |
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 |