CN110443657A - Customer traffic data processing method, device, electronic equipment and readable medium - Google Patents
Customer traffic data processing method, device, electronic equipment and readable medium Download PDFInfo
- Publication number
- CN110443657A CN110443657A CN201910764124.XA CN201910764124A CN110443657A CN 110443657 A CN110443657 A CN 110443657A CN 201910764124 A CN201910764124 A CN 201910764124A CN 110443657 A CN110443657 A CN 110443657A
- Authority
- CN
- China
- Prior art keywords
- distribution
- distribution function
- distribution parameter
- customer
- historic
- 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.)
- Granted
Links
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
- G06Q30/01—Customer relationship services
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This disclosure relates to a kind of customer traffic data processing method, device, electronic equipment and computer-readable medium.This method comprises: obtaining the first business scenario feature and multiple historic customer flow sequences；The corresponding multiple distribution parameters of the multiple historic customer flow sequence are determined according to the target distribution function of business scenario, and utilize the multiple distribution parameter of the historic customer flow sequence and historic customer flow sequence training distribution parameter prediction model；By the first business scenario feature input distribution parameter prediction model to predict current distribution parameter；And customer traffic is predicted according to current distribution parameter and target distribution function.This disclosure relates to customer traffic data processing method, device, electronic equipment and computer-readable medium, the distribution parameter prediction model obtained based on the training of customer traffic historical data predicts current distribution parameter, can be according to current distribution parameter Accurate Prediction customer traffic.
Description
Technical field
This disclosure relates to field of computer technology, in particular to a kind of customer traffic data processing method, device,
Electronic equipment and computer-readable medium.
Background technique
Current many enterprises are provided which clients' intensity industry such as customer service, especially financial services industry.To meet
Expectation of the fragmentation and client of the customer service of continuous improvement to experience, enterprise need constantly to be promoted the clothes of itself customer service department
Business ability.For the service ability for improving customer service department, customer service capacity can be increased；Or predict customer traffic in advance, i.e. customer service
Pressure, to dispatch customer service resource accordingly.It is current in the related technology, increase customer service capacity usually there are two types of mode, one is draw
Into artificial intelligence customer service, but artificial intelligence is still in the primary intelligent stage at this stage, and it is fine to solve simple advisory task,
It is often helpless for complicated customer service task；Another kind is the scale for expanding artificial customer service team, but human cost
Rise so that the artificial increased scale of customer service team relative to paroxysmal, the intermittent customer service demand exponentially increased and
Say an utterly inadequate amount that seems.When predicting customer traffic, current the relevant technologies are usually according to history manually through flowing unknown client
Amount is predicted that prediction deviation is big, is unable to satisfy the needs of actual production.
Therefore, it is necessary to a kind of new customer traffic data processing method, device, electronic equipment and computer-readable mediums.
Above- mentioned information are only used for reinforcing the understanding to the background of the disclosure, therefore it disclosed in the background technology part
It may include the information not constituted to the relevant technologies known to persons of ordinary skill in the art.
Summary of the invention
In view of this, the disclosure provides a kind of customer traffic data processing method, device, electronic equipment and computer-readable
Medium, the distribution parameter prediction model obtained based on the training of customer traffic historical data predict current distribution parameter, being capable of basis
Current distribution parameter Accurate Prediction customer traffic.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the one side of the disclosure, a kind of customer traffic data processing method is proposed, this method comprises: obtaining the first industry
Scene characteristic of being engaged in and multiple historic customer flow sequences；The multiple history visitor is determined according to the target distribution function of business scenario
The corresponding multiple distribution parameters of family flow sequence, and utilize the historic customer flow sequence and the historic customer flow sequence
The multiple distribution parameter training distribution parameter prediction model；The first business scenario feature is inputted into the distribution parameter
Prediction model is to predict current distribution parameter；And client is predicted according to the current distribution parameter and the target distribution function
Flow.
In a kind of exemplary embodiment of the disclosure, determined in the target distribution function according to business scenario the multiple
Before the corresponding multiple distribution parameters of historic customer flow sequence, the method also includes: according to multiple alternative distribution functions pair
The multiple historic customer flow sequence is fitted；Distribution similarity is calculated based on fitting result, in multiple alternative distributions
The target distribution function is determined in function.
In a kind of exemplary embodiment of the disclosure, distribution similarity is calculated based on fitting result, multiple alternative
Determine that the target distribution function includes: to determine multiple history warps according to the multiple historic customer flow sequence in distribution function
Test distribution；Calculate multiple distances of the multiple historical experience distribution and the multiple alternative distribution function；It is the multiple away from
Minimum range is obtained from middle screening, and determines that the alternative distribution function of the minimum range is target distribution function.
In a kind of exemplary embodiment of the disclosure, distribution similarity is calculated based on fitting result, multiple alternative
Determine that the target distribution function includes: according to Kolmogorov-Smirnove test method described in distribution function
The target distribution function is determined in multiple alternative distribution functions；Or according to the Anderson-Da Lin method of inspection the multiple standby
It selects and determines the target distribution function in distribution function；Or it is true in the multiple alternative distribution function according to Chi-square Test method
The fixed target distribution function.
In a kind of exemplary embodiment of the disclosure, the historic customer flow sequence and the historic customer stream are utilized
The multiple distribution parameter training distribution parameter prediction model for measuring sequence includes: to extract in the historic customer flow sequence
Obtain the second business scenario feature；It is described to go through using the second business scenario feature of the historic customer flow sequence as input
The distribution parameter of history customer traffic sequence is integrated into training sample set as output；Utilize training sample set training
The distribution parameter prediction model.
It is pre- according to the current distribution parameter and the target distribution function in a kind of exemplary embodiment of the disclosure
Surveying customer traffic includes: to determine that there is the client of maximum probability to flow according to the current distribution parameter and the target distribution function
Measure section.
In a kind of exemplary embodiment of the disclosure, obtaining multiple historic customer flow sequences includes: with business scenario
Time window size on the basis of, extracted in historic customer data on flows library and obtain multiple historic customer flow sequences.
According to the one side of the disclosure, propose that a kind of customer traffic data processing equipment, the device include: data acquisition mould
Block, for obtaining the first business scenario feature and multiple historic customer flow sequences；Model training module, for according to business field
The target distribution function of scape determines the corresponding multiple distribution parameters of the multiple historic customer flow sequence, and utilizes the history
The multiple distribution parameter of customer traffic sequence and the historic customer flow sequence trains distribution parameter prediction model；Distribution
Parameter prediction module, for the first business scenario feature to be inputted the distribution parameter prediction model to predict currently to be distributed
Parameter；And customer traffic prediction module, for predicting client according to the current distribution parameter and the target distribution function
Flow.
According to the one side of the disclosure, a kind of electronic equipment is proposed, which includes: one or more processors；
Storage device, for storing one or more programs；When one or more programs are executed by one or more processors, so that one
A or multiple processors realize method as described above.
According to the one side of the disclosure, it proposes a kind of computer-readable medium, is stored thereon with computer program, the program
Method as described above is realized when being executed by processor.
Customer traffic data processing method, device, electronic equipment and the computer provided according to some embodiments of the disclosure
Readable medium carries out distribution function fitting to historic customer flow sequence according to the distribution function of business scenario, to obtain history
The corresponding distribution parameter of customer traffic sequence, can depth excavate customer traffic historical data, and by historic customer flow sequence
Convert statistics available distribution parameter group；Meanwhile mould is predicted according to historic customer flow sequence and distribution parameter training distribution parameter
Type, being capable of Accurate Prediction distribution parameter；The distribution parameter and target distribution function that final basis predicts being capable of Accurate Prediction visitors
The variation of family flow；The variation of customer traffic is no longer specific numerical value, but specific sections and associated probability, energy
It is enough to provide decision-making foundation more flexiblely for customer service Resource allocation and smoothing.This disclosure relates to customer traffic data processing method, dress
It sets, electronic equipment and computer-readable medium, the distribution parameter prediction model obtained based on the training of customer traffic historical data is pre-
Current distribution parameter is surveyed, it can be according to current distribution parameter Accurate Prediction customer traffic.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
It becomes more fully apparent.Drawings discussed below is only some embodiments of the present disclosure, for the ordinary skill of this field
For personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of customer traffic data processing method shown according to an exemplary embodiment.
Fig. 2 is a kind of flow chart of the customer traffic data processing method shown according to another exemplary embodiment.
Fig. 3 is a kind of block diagram of customer traffic data processing equipment shown according to an exemplary embodiment.
Fig. 4 is a kind of block diagram of the customer traffic data processing equipment shown according to another exemplary embodiment.
Fig. 5 is a kind of block diagram of the customer traffic data processing equipment shown according to another exemplary embodiment.
Fig. 6 is a kind of block diagram of the customer traffic data processing equipment shown according to another exemplary embodiment.
Fig. 7 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Fig. 8 is that a kind of computer readable storage medium schematic diagram is shown according to an exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can with technical solution of the disclosure without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
It should be understood that although herein various assemblies may be described using term first, second, third, etc., these groups
Part should not be limited by these terms.These terms are to distinguish a component and another component.Therefore, first group be discussed herein below
Part can be described as the second component without departing from the teaching of disclosure concept.As used herein, term " and/or " include associated
All combinations for listing any of project and one or more.
It will be understood by those skilled in the art that attached drawing is the schematic diagram of example embodiment, module or process in attached drawing
Necessary to not necessarily implementing the disclosure, therefore it cannot be used for the protection scope of the limitation disclosure.
In customer traffic data processing scene in the related technology, the prediction of customer traffic and subsequent customer service dispatching
Tend to rely on the working experience of relevant staff.Such as under normal circumstances, period customer service pressure meeting different in one day
There is metastable variation tendency；When company pushes specific activity, customer service demand pressure has violent fluctuation.But it relies on
It not can guarantee the correctness of customer traffic prediction in the scheduling mode of experience, be easy to produce artificial careless omission.
Currently, can not cope with the technical solution of drawbacks described above.
In view of the defects of the relevant technologies, present applicant proposes a kind of customer traffic data processing method and devices, lead to
The excavation to customer traffic historical data is crossed, the relationship of customer service pressure change and exogenous variable is extracted, establishes distribution parameter prediction
Model, can in customer service later Accurate Prediction customer traffic variation.
Fig. 1 is a kind of flow chart of customer traffic data processing method shown according to an exemplary embodiment.The disclosure
The customer traffic data processing method that embodiment provides can be executed by arbitrarily having the electronic equipment of calculation processing ability, such as
User terminal and/or server are illustrated so that server executes the method as an example in the following embodiments, but
It's not limited to that for the disclosure.The embodiment of the present disclosure provide customer traffic data processing method 10 may include step S102 extremely
S108。
As shown in Figure 1, in step s 102, obtaining the first business scenario feature and multiple historic customer flow sequences.Its
In, the first business scenario feature is characteristic quantity relevant to customer traffic, such as, but not limited to it is current whether festivals or holidays, current tool
Body time, the gender of current business main foreigner tourists, age range, educational level equality.Historic customer flow sequence description has been sent out
In raw certain time, the numerical value change situation of customer traffic.Historic customer flow sequence can mention in customer traffic database
It takes.
In one embodiment, multiple historic customer flow sequences are obtained can include: big with the time window of business scenario
On the basis of small, extracted in historic customer data on flows library and obtain multiple historic customer flow sequences.Wherein, time window size
For preset value.Rule of thumb method specific time window size can be determined, to guarantee while pay close attention to global information and instantaneous letter
Breath.
In step S104, the multiple historic customer flow sequence pair is determined according to the target distribution function of business scenario
The multiple distribution parameters answered, and the multiple point of the utilization historic customer flow sequence and the historic customer flow sequence
Cloth parameter training distribution parameter prediction model.Wherein, each business scenario has a target distribution function.Customer traffic can be seen
Make stochastic variable, probability distribution is described by distribution function.Target distribution function is general with the customer traffic of current business scene
The immediate distribution function of rate distribution situation.Target distribution function can be fitted really previously according to historic customer flow sequence
It is fixed.It is right since the corresponding business scenario characteristic value of multiple historic customer flow sequences is different even if target distribution function is identical
The distribution parameter answered also will be different.
In one embodiment, the multiple historic customer flow sequence is determined in the target distribution function according to business scenario
Before arranging corresponding multiple distribution parameters, the multiple historic customer flow sequence can be carried out according to multiple alternative distribution functions
Fitting；Distribution similarity is calculated based on fitting result, to determine the target distribution function in multiple alternative distribution functions.Its
In, when calculating distribution similarity, the fitting result that historical experience is distributed respectively with each alternative distribution function can be compared
It is right, select closest alternative distribution function as target distribution function.Historical experience distribution refers to based on each historic customer
The customer traffic actual observed value that flow sequence statistic obtains.
In one embodiment, distribution similarity is calculated based on fitting result, to determine in multiple alternative distribution functions
The target distribution function can include: determine that multiple historical experiences are distributed according to the multiple historic customer flow sequence；It calculates
Multiple distances of the multiple historical experience distribution and the multiple alternative distribution function；It screens and obtains in the multiple distance
Minimum range, and determine that the alternative distribution function of the minimum range is target distribution function.Alternative distribution function can such as table 1
It is shown.
Table 1
In one embodiment, distribution similarity is calculated based on fitting result, to determine in multiple alternative distribution functions
The target distribution function determines the target distribution letter based on the goodness of fit of fitting result in multiple alternative distribution functions
Number includes: to determine the mesh in the multiple alternative distribution function according to Kolmogorov-Smirnove test method
Mark distribution function；Or the target distribution is determined in the multiple alternative distribution function according to the Anderson-Da Lin method of inspection
Function；Or the target distribution function is determined in the multiple alternative distribution function according to Chi-square Test method.Wherein, Ke Er
Brother's love-Smirnov test method, the Anderson-Da Lin method of inspection are not to examine two experiences based on Cumulative Distribution Function
Whether distribution is different or an experience is distributed the method for inspection whether different from another ideal distribution.Chi-square Test method can unite
Count the departure degree between the actual observed value and theoretical implications value of sample, the deviation between actual observed value and theoretical implications value
Degree just determines the size of chi-square value, if chi-square value is bigger, the two extent of deviation is bigger；Conversely, the two deviation is smaller；If two
It is a value it is essentially equal when, chi-square value is just 0, shows that theoretical value complies fully with.
In one embodiment, the described more of the historic customer flow sequence and the historic customer flow sequence are utilized
A distribution parameter training distribution parameter prediction model can include: second business that obtains is extracted in the historic customer flow sequence
Scene characteristic；Using the second business scenario feature of the historic customer flow sequence as input, the historic customer flow sequence
The distribution parameter of column is integrated into training sample set as output；Utilize the training sample set training distribution parameter
Prediction model.Wherein, the second business scenario feature is history feature.Each historic customer flow sequence have its corresponding second
Business scenario characteristic value and distribution parameter.Distribution parameter prediction model is based on historical data, and the model is with the second business scenario spy
Sign is input, and distribution parameter is output.Distribution parameter prediction model is corresponding with business scenario, under different business scenario features
Distribution function is different, and distribution parameter prediction model is not also identical.The disclosure to the concrete form of distribution parameter prediction model simultaneously
It is not particularly limited, neural network model can be such as, but not limited to, the number of distribution parameter is determined by target distribution function.
By taking Johnson SB distribution in table 1 as an example, there are four parameters for the branch.If the target distribution function of current business scene is
When Johnson SB is distributed, then its distribution parameter prediction model has 4 outputs, respectively corresponds four ginsengs of Johnson SB distribution
Number.
In step s 106, the first business scenario feature is inputted into the distribution parameter prediction model to predict currently
Distribution parameter.Wherein, the first business scenario feature describes current signature.According to the trained distribution parameter prediction of step S104
Model can be predicted to obtain current distribution parameter according to the first business scenario feature.Current distribution parameter describes current client
The concrete shape of the distribution function of flow.
In step S108, customer traffic is predicted according to the current distribution parameter and the target distribution function.Wherein,
Target distribution function and current distribution parameter can describe the probability distribution of existing customer flow jointly.Probability distribution can be passed through
Situation predicts customer traffic.
In one embodiment, it can determine have most probably according to the current distribution parameter and the target distribution function
The customer traffic section of rate.In another example can be the allotment of customer service human resources according to the customer traffic section with maximum probability
Improve decision-making foundation.
According to the customer traffic data processing method that disclosure embodiment provides, according to the distribution function pair of business scenario
Historic customer flow sequence carries out distribution function fitting, to obtain the corresponding distribution parameter of historic customer flow sequence, Neng Goushen
Degree excavates customer traffic historical data, and by the Sequence Transformed statistics available distribution parameter group of historic customer flow；Meanwhile according to going through
History customer traffic sequence and distribution parameter training distribution parameter prediction model, being capable of Accurate Prediction distribution parameter；Final basis is pre-
The distribution parameter and target distribution function that measure are capable of the variation of Accurate Prediction customer traffic；The variation of customer traffic is no longer special
Fixed numerical value, but specific sections and associated probability, can provide certainly for customer service Resource allocation and smoothing more flexiblely
Plan foundation.This disclosure relates to customer traffic data processing method, device, electronic equipment and computer-readable medium, based on visitor
The distribution parameter prediction model that flow histories data training in family obtains predicts current distribution parameter, can be according to current distribution parameter
Accurate Prediction customer traffic.
It will be clearly understood that the present disclosure describes how to form and use particular example, but the principle of the disclosure is not limited to
These exemplary any details.On the contrary, the introduction based on disclosure disclosure, these principles can be applied to many other
Embodiment.
Fig. 2 is a kind of flow chart of the customer traffic data processing method shown according to another exemplary embodiment.
As shown in Fig. 2, customer traffic data processing method may include step S202 to step S210.
Before model, needing to collect mass data, these data contain the time that client accesses customer service system, and
Feature relevant to client's amount of access, if whether the same day is regionalism that whether festivals or holidays, business have activity, business to carry out
Feature (gender of such as target customer, age, the text of the targeted customer group of (population, GDP that such as business carries out ground), business
Change horizontal) etc..
In step s 201, fitting of distribution is carried out to multiple historic customer flow sequences.Wherein, it can be shown according in table 1
A variety of alternative distributions go to be fitted the historic customer flow sequence that multiple time windows are one hour.
In step S203, distribution similarity is calculated based on fitting result, to determine institute in multiple alternative distribution functions
State target distribution function.Wherein, the method for digital simulation similarity may be, for example: Kolmogorov-Smirnove test
(Kolmogorov-Smirnov Test), Anderson-Da Lin examine (Anderson-Darling Test), Chi-square Test
(Chi-Squared Test) etc..Kolmogorov-Smirnove test is based on Cumulative Distribution Function and examines two experiences
Whether distribution is different or whether an experience distribution is different from another ideal distribution, and the distance between two cumulative distributions can root
It is calculated according to formula (1), (2):
Wherein, I[- inf, x]For indicator function (indicator function), may be expressed as:
supxIt is the supremum (supremum) of distance, based on literal arts theorem (Glivenko-in lattice
Cantellitheorem), if XiIt obeys theoretical distribution F (x), then the D when n tends to be infinitenTend to 0.
- Da Lin inspection in Anderson is similar with Kolmogorov-Smirnove test, can be calculated according to formula (3)
The distance between two cumulative distributions:
Wherein, F (x) is standard just too cumulative distribution function, FnIt (x) is distribution function to be detected.
For example, the target distribution function that this step determines is that bounded Johnson is distributed (Johnson SB), the distribution function
There are four parameters for tool, and corresponding probability-distribution function and cumulative distribution function are respectively as formula (4), (5) are shown:
Wherein, λ, γ, δ, z are four parameters of bounded Johnson distribution function.
In step S205, the distribution parameter group of each historic customer flow sequence is determined according to target distribution function, and
The business scenario feature of historic customer flow sequence and distribution parameter group are configured to training sample set.Wherein, the present embodiment selects
The business scenario feature taken can be as follows:
(1) whether the same day is festivals or holidays
(2) the customer traffic data corresponding time
(3) whether business has special events
(4) as business carries out the population on ground
(5) as business carries out the GDP on ground
(6) gender of the targeted customer group of business
(7) age range of the targeted customer group of business
(8) educational level of the targeted customer group of business
(9) business channel
(10) type of service
In step S207, using training sample set training distribution parameter prediction model, to complete the building of model.Its
In, the citing of aforementioned Johnson's distribution is connect, can be by business scenario feature set --- the training that distribution parameter collection (γ, δ, λ) is constituted
Sample set input distribution parameter prediction module has carried out tutor's training, completes the building of model.
In step S209, the business scenario feature on the same day is inputted into distribution parameter prediction model, with every in the prediction same day
Customer traffic distribution parameter in a time window, and flowed according to the forecast of distribution client that distribution parameter and target distribution function determine
Amount.
It is quasi- to carry out distribution according to business scenario feature first for customer traffic data processing method according to an embodiment of the present invention
It closes, to obtain distribution function and the corresponding distribution parameter of customer traffic variation, customer traffic can be characterized by distribution parameter
Variation；Then the prediction of distribution parameter is carried out according to current business scenario feature, and is determined by distribution parameter and distribution function
The fixed variation being distributed to predict customer traffic, predicts that the variation of the customer traffic obtained is no longer specific numerical value, but
Specific section and associated probability, provide decision-making foundation for more flexible deployment of human resources.
It will be appreciated by those skilled in the art that realizing that all or part of the steps of above-described embodiment is implemented as being executed by CPU
Computer program.When the computer program is executed by CPU, above-mentioned function defined by the above method that the disclosure provides is executed
Energy.The program can store in a kind of computer readable storage medium, which can be read-only memory, magnetic
Disk or CD etc..
Further, it should be noted that above-mentioned attached drawing is only the place according to included by the method for disclosure exemplary embodiment
Reason schematically illustrates, rather than limits purpose.It can be readily appreciated that above-mentioned processing shown in the drawings is not indicated or is limited at these
The time sequencing of reason.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.It is real for disclosure device
Undisclosed details in example is applied, embodiments of the present disclosure is please referred to.
Fig. 3 is a kind of block diagram of customer traffic data processing equipment shown according to an exemplary embodiment.The disclosure is real
The customer traffic data processing equipment 30 for applying example offer includes: data acquisition module 302, model training module 304, distribution parameter
Prediction module 306 and customer traffic prediction module 308.
Data acquisition module 302 is for obtaining the first business scenario feature and multiple historic customer flow sequences.
Model training module 304 is used to determine the multiple historic customer flow according to the target distribution function of business scenario
The corresponding multiple distribution parameters of sequence, and utilize the described of the historic customer flow sequence and the historic customer flow sequence
Multiple distribution parameter training distribution parameter prediction models.
Distribution parameter prediction module 306 is used to the first business scenario feature inputting the distribution parameter prediction model
To predict current distribution parameter.
Customer traffic prediction module 308 is used to predict client according to the current distribution parameter and the target distribution function
Flow.
In one embodiment, data acquisition module 302 is used on the basis of the time window size of business scenario, is being gone through
It is extracted in history customer traffic database and obtains multiple historic customer flow sequences.
In one embodiment, model training module 304 is used to determine institute in the target distribution function according to business scenario
Before stating the corresponding multiple distribution parameters of multiple historic customer flow sequences, gone through according to multiple alternative distribution functions to the multiple
History customer traffic sequence is fitted；Distribution similarity is calculated based on fitting result, to determine in multiple alternative distribution functions
The target distribution function.
In one embodiment, customer traffic prediction module 308 is used for according to the current distribution parameter and the target
Distribution function determines the customer traffic section with maximum probability.
Fig. 4 is a kind of block diagram of the customer traffic data processing equipment shown according to another exemplary embodiment.
As shown in figure 4, in embodiments of the present invention, customer traffic data processing equipment include: data acquisition module 402,
Model training module 404, distribution parameter prediction module 406, customer traffic prediction module 408, experience distribution determining module 410,
Distance calculation module 412 and target distribution function determining module 414.Wherein, data acquisition module 402, model training module
404, the data acquisition module 302 in distribution parameter prediction module 406, customer traffic prediction module 408 and previous embodiment, mould
Type training module 304, distribution parameter prediction module 306 and customer traffic prediction module 308 are identical, and previous embodiment has been made
It explains in detail, details are not described herein again.Experience is distributed determining module 410 and is used to be determined according to the multiple historic customer flow sequence
Multiple historical experience distributions；Distance calculation module 412 is for calculating the multiple historical experience distribution and the multiple alternative point
Multiple distances of cloth function；Target distribution function determining module 414 is used for the screening in the multiple distance and obtains minimum range,
And determine that the alternative distribution function of the minimum range is target distribution function.
Fig. 5 is a kind of block diagram of the customer traffic data processing equipment shown according to another exemplary embodiment.
As shown in figure 5, in embodiments of the present invention, customer traffic data processing equipment include: data acquisition module 502,
Model training module 504, distribution parameter prediction module 506, customer traffic prediction module 508, Andrei Kolmogorov-Si meter Er Nuo
Husband's inspection module 510, Anderson-Da Lin inspection module 512 and Chi-square Test module 514.Wherein, data acquisition module 502,
Model training module 504, distribution parameter prediction module 506, customer traffic prediction module 508 and the data in previous embodiment obtain
Modulus block 302, model training module 304, distribution parameter prediction module 306 and customer traffic prediction module 308 are identical, aforementioned
Embodiment, which has been made, to be explained in detail, and details are not described herein again.Kolmogorov-Smirnove test module 510 is used for basis
Kolmogorov-Smirnove test method determines the target distribution function in the multiple alternative distribution function；
Anderson-Da Lin inspection module 512 is used to be determined in the multiple alternative distribution function according to the Anderson-Da Lin method of inspection
The target distribution function；Chi-square Test module 514 is used for according to Chi-square Test method in the multiple alternative distribution function
Determine the target distribution function.
Fig. 6 is a kind of block diagram of the customer traffic data processing equipment shown according to another exemplary embodiment.
As shown in fig. 6, in embodiments of the present invention, customer traffic data processing equipment include: data acquisition module 602,
Historical rethinking parameter determination module 604, the second business scenario characteristic extracting module 606, training sample generation module 608, model
Training module 610, distribution parameter prediction module 612, customer traffic prediction module 614.Wherein, data acquisition module 602, distribution
Parameter prediction module 612, customer traffic prediction module 614 and data acquisition module 302, the distribution parameter in previous embodiment are pre-
It surveys module 306 and customer traffic prediction module 308 is identical, previous embodiment, which has been made, to be explained in detail, and details are not described herein again.It goes through
History distribution parameter determining module 604 is used to determine the multiple historic customer flow sequence according to the target distribution function of business scenario
Arrange corresponding multiple distribution parameters；Second business scenario characteristic extracting module 606 is used in the historic customer flow sequence
It extracts and obtains the second business scenario feature；Training sample generation module 608 is used for the second of the historic customer flow sequence
Business scenario feature is integrated into trained sample as output as input, the distribution parameter of the historic customer flow sequence
This collection；Model training module 610 is used to utilize the training sample set training distribution parameter prediction model.
According to the customer traffic data processing equipment that disclosure embodiment provides, according to the distribution function pair of business scenario
Historic customer flow sequence carries out distribution function fitting, to obtain the corresponding distribution parameter of historic customer flow sequence, Neng Goushen
Degree excavates customer traffic historical data, and by the Sequence Transformed statistics available distribution parameter group of historic customer flow；Meanwhile according to going through
History customer traffic sequence and distribution parameter training distribution parameter prediction model, being capable of Accurate Prediction distribution parameter；Final basis is pre-
The distribution parameter and target distribution function that measure are capable of the variation of Accurate Prediction customer traffic；The variation of customer traffic is no longer special
Fixed numerical value, but specific sections and associated probability, can provide certainly for customer service Resource allocation and smoothing more flexiblely
Plan foundation.This disclosure relates to customer traffic data processing method, device, electronic equipment and computer-readable medium, based on visitor
The distribution parameter prediction model that flow histories data training in family obtains predicts current distribution parameter, can be according to current distribution parameter
Accurate Prediction customer traffic.
Fig. 7 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
The electronic equipment 700 of this embodiment according to the application is described referring to Fig. 7.The electronics that Fig. 7 is shown
Equipment 700 is only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in fig. 7, computer system 700 includes central processing unit (CPU) 701, it can be read-only according to being stored in
Program in memory (ROM) 702 or be loaded into the program in random access storage device (RAM) 703 from storage part 708 and
Execute various movements appropriate and processing.For example, central processing unit 701 can execute as shown in Figure 1, Figure 2 one or more of
Shown step.
In RAM703, various programs and data needed for system operatio are also stored with, such as resource status table, service are in fact
Example etc..CPU 701, ROM 702 and RAM703 are connected with each other by bus 704.Input/output (I/O) interface 705 also connects
To bus 704.
I/O interface 705 is connected to lower component: the importation 706 including touch screen, keyboard etc.；Including such as liquid crystal
The output par, c 707 of display (LCD) etc. and loudspeaker etc.；Storage part 708 including flash memory etc.；And including such as without
The communications portion 709 of gauze card, High_speed NIC etc..Communications portion 709 executes communication process via the network of such as internet.It drives
Dynamic device 710 is also connected to I/O interface 705 as needed.Detachable media 711, semiconductor memory, disk etc., according to
It needs to be mounted on driver 710, in order to be mounted into storage part as needed from the computer program read thereon
708。
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, the present invention is implemented
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions are used so that a calculating equipment (can be a
People's computer, server, mobile terminal or smart machine etc.) it executes according to the method for the embodiment of the present invention, such as Fig. 1, figure
Step shown in one or more of 2.
Fig. 8 schematically shows a kind of computer readable storage medium schematic diagram in disclosure exemplary embodiment.
Refering to what is shown in Fig. 8, describing the program product for realizing the above method according to embodiment of the present disclosure
800, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, the program product of the disclosure is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with any combination of one or more programming languages come write for execute the disclosure operation program
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by one
When the equipment executes, so that the computer-readable medium implements function such as: obtaining the first business scenario feature and multiple history
Customer traffic sequence；Determine that the multiple historic customer flow sequence is corresponding multiple according to the target distribution function of business scenario
Distribution parameter, and instructed using the multiple distribution parameter of the historic customer flow sequence and the historic customer flow sequence
Practice distribution parameter prediction model；The first business scenario feature is inputted into the distribution parameter prediction model to predict currently to divide
Cloth parameter；And customer traffic is predicted according to the current distribution parameter and the target distribution function.
It will be appreciated by those skilled in the art that above-mentioned each module can be distributed in device according to the description of embodiment, it can also
Uniquely it is different from one or more devices of the present embodiment with carrying out corresponding change.The module of above-described embodiment can be merged into
One module, can also be further split into multiple submodule.
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implemented according to the disclosure
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, mobile terminal or network equipment etc.) it executes according to the method for the embodiment of the present disclosure.
It is particularly shown and described the exemplary embodiment of the disclosure above.It should be appreciated that the present disclosure is not limited to
Detailed construction, set-up mode or implementation method described herein；On the contrary, disclosure intention covers included in appended claims
Various modifications and equivalence setting in spirit and scope.
In addition, structure shown by this specification Figure of description, ratio, size etc., only to cooperate specification institute
Disclosure, for skilled in the art realises that be not limited to the enforceable qualifications of the disclosure with reading, therefore
Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the disclosure
Under the technical effect and achieved purpose that can be generated, it should all still fall in technology contents disclosed in the disclosure and obtain and can cover
In the range of.Meanwhile cited such as "upper" in this specification, " first ", " second " and " one " term, be also only and be convenient for
Narration is illustrated, rather than to limit the enforceable range of the disclosure, relativeness is altered or modified, without substantive change
Under technology contents, when being also considered as the enforceable scope of the disclosure.
Claims (10)
1. a kind of customer traffic data processing method characterized by comprising
Obtain the first business scenario feature and multiple historic customer flow sequences；
The corresponding multiple distribution parameters of the multiple historic customer flow sequence are determined according to the target distribution function of business scenario,
And utilize the multiple distribution parameter of the historic customer flow sequence and historic customer flow sequence training distribution ginseng
Number prediction model；
The first business scenario feature is inputted into the distribution parameter prediction model to predict current distribution parameter；And
Customer traffic is predicted according to the current distribution parameter and the target distribution function.
2. the method as described in claim 1, which is characterized in that determined in the target distribution function according to business scenario described more
Before the corresponding multiple distribution parameters of a historic customer flow sequence, the method also includes:
The multiple historic customer flow sequence is fitted according to multiple alternative distribution functions；
Distribution similarity is calculated based on fitting result, to determine the target distribution function in multiple alternative distribution functions.
3. method according to claim 2, which is characterized in that distribution similarity is calculated based on fitting result, multiple standby
It selects and determines that the target distribution function includes: in distribution function
Multiple historical experience distributions are determined according to the multiple historic customer flow sequence；
Calculate multiple distances of the multiple historical experience distribution and the multiple alternative distribution function；
Screening obtains minimum range in the multiple distance, and determines the alternative distribution function of the minimum range for target point
Cloth function.
4. method according to claim 2, which is characterized in that distribution similarity is calculated based on fitting result, multiple standby
It selects and determines that the target distribution function includes: in distribution function
The target point is determined in the multiple alternative distribution function according to Kolmogorov-Smirnove test method
Cloth function；Or
The target distribution function is determined in the multiple alternative distribution function according to the Anderson-Da Lin method of inspection；Or
The target distribution function is determined in the multiple alternative distribution function according to Chi-square Test method.
5. the method as described in claim 1, which is characterized in that utilize the historic customer flow sequence and the historic customer
Flow sequence the multiple distribution parameter training distribution parameter prediction model include:
It is extracted in the historic customer flow sequence and obtains the second business scenario feature；
Using the second business scenario feature of the historic customer flow sequence as input, the institute of the historic customer flow sequence
Distribution parameter is stated as output, is integrated into training sample set；
Utilize the training sample set training distribution parameter prediction model.
6. the method as described in claim 1, which is characterized in that according to the current distribution parameter and the target distribution function
Predict that customer traffic includes:
The customer traffic section with maximum probability is determined according to the current distribution parameter and the target distribution function.
7. the method as described in claim 1, which is characterized in that obtaining multiple historic customer flow sequences includes:
On the basis of the time window size of business scenario, is extracted in historic customer data on flows library and obtain multiple historic customers
Flow sequence.
8. a kind of customer traffic data processing equipment characterized by comprising
Data acquisition module, for obtaining the first business scenario feature and multiple historic customer flow sequences；
Model training module determines the multiple historic customer flow sequence pair for the target distribution function according to business scenario
The multiple distribution parameters answered, and the multiple point of the utilization historic customer flow sequence and the historic customer flow sequence
Cloth parameter training distribution parameter prediction model；
Distribution parameter prediction module, for the first business scenario feature to be inputted the distribution parameter prediction model to predict
Current distribution parameter；And
Customer traffic prediction module, for predicting customer traffic according to the current distribution parameter and the target distribution function.
9. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-7.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1-7 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910764124.XA CN110443657B (en) | 2019-08-19 | 2019-08-19 | Client flow data processing method and device, electronic equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910764124.XA CN110443657B (en) | 2019-08-19 | 2019-08-19 | Client flow data processing method and device, electronic equipment and readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110443657A true CN110443657A (en) | 2019-11-12 |
| CN110443657B CN110443657B (en) | 2022-03-18 |
Family
ID=68436393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910764124.XA Active CN110443657B (en) | 2019-08-19 | 2019-08-19 | Client flow data processing method and device, electronic equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110443657B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369121A (en) * | 2020-02-27 | 2020-07-03 | 深圳市赤狐软件技术有限公司 | Client data processing method and device, computer equipment and storage medium |
| CN111860856A (en) * | 2020-01-15 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Probability distribution function training method, service incentive processing method, device and equipment |
| CN112001563A (en) * | 2020-09-04 | 2020-11-27 | 深圳天源迪科信息技术股份有限公司 | Method and device for managing phone bill amount, electronic equipment and storage medium |
| CN112862597A (en) * | 2021-02-19 | 2021-05-28 | 招商银行股份有限公司 | Network point time-sharing classification type number allocation method, device, equipment and storage medium |
| CN112862197A (en) * | 2021-02-19 | 2021-05-28 | 招商银行股份有限公司 | Intelligent network point number allocation method, device, equipment and storage medium |
| CN113159934A (en) * | 2021-05-26 | 2021-07-23 | 中国工商银行股份有限公司 | Method and system for predicting passenger flow of network, electronic equipment and storage medium |
| CN113435122A (en) * | 2021-06-30 | 2021-09-24 | 平安科技（深圳）有限公司 | Real-time flow data processing method and device, computer equipment and storage medium |
| CN113595930A (en) * | 2020-04-30 | 2021-11-02 | 华为技术有限公司 | Flow identification method and flow identification equipment |
| CN113888060A (en) * | 2021-11-24 | 2022-01-04 | 中国工商银行股份有限公司 | Method, apparatus, electronic device and medium for determining website operation strategy |
| CN114449569A (en) * | 2020-11-02 | 2022-05-06 | 中国移动通信集团广东有限公司 | User traffic usage processing method, network device and service processing system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573849A (en) * | 2014-12-12 | 2015-04-29 | 安徽富煌和利时科技股份有限公司 | Bus dispatch optimization method for predicting passenger flow based on ARIMA model |
| CN106803137A (en) * | 2017-01-25 | 2017-06-06 | 东南大学 | Urban track traffic AFC system enters the station volume of the flow of passengers method for detecting abnormality in real time |
| CN108197739A (en) * | 2017-12-29 | 2018-06-22 | 中车工业研究院有限公司 | A kind of urban track traffic ridership Forecasting Methodology |
| CN108197760A (en) * | 2018-01-31 | 2018-06-22 | 民航成都电子技术有限责任公司 | A kind of airport traffic above-ground passenger traffic volume Forecasting Methodology |
| CN109002988A (en) * | 2018-07-18 | 2018-12-14 | 平安科技（深圳）有限公司 | Risk passenger method for predicting, device, computer equipment and storage medium |
| CN109034469A (en) * | 2018-07-20 | 2018-12-18 | 成都中科大旗软件有限公司 | A kind of tourist flow prediction technique based on machine learning |
| CN110046764A (en) * | 2019-04-12 | 2019-07-23 | 成都四方伟业软件股份有限公司 | The method and device of passenger flow forecast amount |
-
2019
- 2019-08-19 CN CN201910764124.XA patent/CN110443657B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573849A (en) * | 2014-12-12 | 2015-04-29 | 安徽富煌和利时科技股份有限公司 | Bus dispatch optimization method for predicting passenger flow based on ARIMA model |
| CN106803137A (en) * | 2017-01-25 | 2017-06-06 | 东南大学 | Urban track traffic AFC system enters the station volume of the flow of passengers method for detecting abnormality in real time |
| CN108197739A (en) * | 2017-12-29 | 2018-06-22 | 中车工业研究院有限公司 | A kind of urban track traffic ridership Forecasting Methodology |
| CN108197760A (en) * | 2018-01-31 | 2018-06-22 | 民航成都电子技术有限责任公司 | A kind of airport traffic above-ground passenger traffic volume Forecasting Methodology |
| CN109002988A (en) * | 2018-07-18 | 2018-12-14 | 平安科技（深圳）有限公司 | Risk passenger method for predicting, device, computer equipment and storage medium |
| CN109034469A (en) * | 2018-07-20 | 2018-12-18 | 成都中科大旗软件有限公司 | A kind of tourist flow prediction technique based on machine learning |
| CN110046764A (en) * | 2019-04-12 | 2019-07-23 | 成都四方伟业软件股份有限公司 | The method and device of passenger flow forecast amount |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860856A (en) * | 2020-01-15 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Probability distribution function training method, service incentive processing method, device and equipment |
| CN111860856B (en) * | 2020-01-15 | 2024-05-28 | 北京嘀嘀无限科技发展有限公司 | Probability distribution function training method, service excitation processing method, device and equipment |
| CN111369121A (en) * | 2020-02-27 | 2020-07-03 | 深圳市赤狐软件技术有限公司 | Client data processing method and device, computer equipment and storage medium |
| CN113595930A (en) * | 2020-04-30 | 2021-11-02 | 华为技术有限公司 | Flow identification method and flow identification equipment |
| CN112001563A (en) * | 2020-09-04 | 2020-11-27 | 深圳天源迪科信息技术股份有限公司 | Method and device for managing phone bill amount, electronic equipment and storage medium |
| CN112001563B (en) * | 2020-09-04 | 2023-10-31 | 深圳天源迪科信息技术股份有限公司 | Method and device for managing ticket quantity, electronic equipment and storage medium |
| CN114449569A (en) * | 2020-11-02 | 2022-05-06 | 中国移动通信集团广东有限公司 | User traffic usage processing method, network device and service processing system |
| CN114449569B (en) * | 2020-11-02 | 2024-01-16 | 中国移动通信集团广东有限公司 | User traffic usage processing method, network equipment and service processing system |
| CN112862597A (en) * | 2021-02-19 | 2021-05-28 | 招商银行股份有限公司 | Network point time-sharing classification type number allocation method, device, equipment and storage medium |
| CN112862597B (en) * | 2021-02-19 | 2024-05-10 | 招商银行股份有限公司 | Method, device, equipment and storage medium for classifying number in time-sharing mode of network points |
| CN112862197A (en) * | 2021-02-19 | 2021-05-28 | 招商银行股份有限公司 | Intelligent network point number allocation method, device, equipment and storage medium |
| CN113159934A (en) * | 2021-05-26 | 2021-07-23 | 中国工商银行股份有限公司 | Method and system for predicting passenger flow of network, electronic equipment and storage medium |
| CN113435122A (en) * | 2021-06-30 | 2021-09-24 | 平安科技（深圳）有限公司 | Real-time flow data processing method and device, computer equipment and storage medium |
| CN113435122B (en) * | 2021-06-30 | 2023-11-07 | 平安科技（深圳）有限公司 | Real-time flow data processing method, device, computer equipment and storage medium |
| CN113888060A (en) * | 2021-11-24 | 2022-01-04 | 中国工商银行股份有限公司 | Method, apparatus, electronic device and medium for determining website operation strategy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110443657B (en) | 2022-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443657A (en) | Customer traffic data processing method, device, electronic equipment and readable medium | |
| US11386496B2 (en) | Generative network based probabilistic portfolio management | |
| Nozhati et al. | Near-optimal planning using approximate dynamic programming to enhance post-hazard community resilience management | |
| CN110399983A (en) | Shape similarity analysis | |
| CN111612249A (en) | Method, device, equipment and storage medium for predicting human flow | |
| EP4202888A1 (en) | Parking area recommendation method and apparatus, electronic device, and medium | |
| US11037064B2 (en) | Recognizing recurrent crowd mobility patterns | |
| CN105701617A (en) | Overall process information management and control visualization method based on electric power material supply chain and system thereof | |
| Du et al. | Cost performance as a stochastic process: EAC projection by Markov Chain simulation | |
| CN112182118B (en) | Target object prediction method based on multiple data sources and related equipment thereof | |
| US20220058590A1 (en) | Equipment maintenance in geo-distributed equipment | |
| Zou et al. | Long-term origin-destination demand prediction with graph deep learning | |
| Xue et al. | A stochastic spatiotemporal weather-impact simulator: Representative scenario selection | |
| CN110309961A (en) | Fire alarm method and apparatus | |
| CN113159934A (en) | Method and system for predicting passenger flow of network, electronic equipment and storage medium | |
| Noursalehi et al. | Predictive decision support platform and its application in crowding prediction and passenger information generation | |
| Wei et al. | Bi-level programming model for multi-modal regional bus timetable and vehicle dispatch with stochastic travel time | |
| CN111123778B (en) | Method and device for monitoring vehicle use condition and electronic equipment | |
| Vu et al. | Bus running time prediction using a statistical pattern recognition technique | |
| Wang et al. | Study of time-dependent queuing models of the national airspace system | |
| CN116187154A (en) | Modeling climate data using machine learning | |
| US11182393B2 (en) | Spatial data analyzer support | |
| US20220188727A1 (en) | Predictive capacity optimizer | |
| CN110413632A (en) | Method, apparatus, computer-readable medium and the electronic equipment of controlled state | |
| CN110874737B (en) | Payment mode recommendation method and device, electronic equipment and storage medium |
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 | ||
| CP03 | Change of name, title or address |
Address after: Floor 36, Zheshang Building, No. 718 Jianshe Avenue, Jiang'an District, Wuhan, Hubei 430019 Patentee after: TK.CN INSURANCE Co.,Ltd. Patentee after: TAIKANG INSURANCE GROUP Co.,Ltd. Address before: 156 fuxingmennei street, Xicheng District, Beijing 100031 Patentee before: TAIKANG INSURANCE GROUP Co.,Ltd. Patentee before: TK.CN INSURANCE Co.,Ltd. |
|
| CP03 | Change of name, title or address |