CN112712396A - Service internet control method based on service community succession prediction model - Google Patents
Service internet control method based on service community succession prediction model Download PDFInfo
- Publication number
- CN112712396A CN112712396A CN202110046833.1A CN202110046833A CN112712396A CN 112712396 A CN112712396 A CN 112712396A CN 202110046833 A CN202110046833 A CN 202110046833A CN 112712396 A CN112712396 A CN 112712396A
- Authority
- CN
- China
- Prior art keywords
- service
- population
- community
- individuals
- internet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000000694 effects Effects 0.000 claims abstract description 17
- 230000008033 biological extinction Effects 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000011161 development Methods 0.000 claims abstract description 14
- 230000008859 change Effects 0.000 claims description 23
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 230000004083 survival effect Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 abstract description 14
- 238000004519 manufacturing process Methods 0.000 description 25
- 238000009833 condensation Methods 0.000 description 4
- 230000005494 condensation Effects 0.000 description 4
- 238000013178 mathematical model Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000009960 carding Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of service internet control optimization in service calculation, and particularly relates to a service internet control method based on a service community succession prediction model. The method constructs parameter indexes such as the new service individual growth rate of the service population, the service individual extinction rate of the service population, the service value importance of the service population, the service population cohesion degree and the service population cohesion effect, predicts the internal service community succession trend of the service internet, has high accuracy and objectivity, can clearly know the internal succession development trend of the service community in the service internet in a short period in the future, further timely makes adjustment management strategies aiming at different succession situations of the service community, and finally provides good support for ensuring the sustainable, healthy and prosperous development of the service internet.
Description
Technical Field
The invention belongs to the technical field of service internet control optimization in service calculation, and particularly relates to a service internet control method based on a service community succession prediction model.
Background
In recent years, as big data and cloud computing technologies have been increasingly popularized, the concept of serving the internet has been developed. The method is used as a ubiquitous networking and intelligent service foundation and can provide support for other industries. The service internet is a complex service network consisting of a large number of heterogeneous service individuals. The services herein include not only web services, but also scientific and technical services, medical care services, and life consumption services. And the system also belongs to a service ecosystem essentially according to the service collaboration and service competition relationship existing in the system. The service population in the service internet refers to a set of service individuals with similar internal service functions, and the service community is a relatively fixed set formed by a plurality of service populations under the influence of external service requirements. How to know the development trend of a service community in a service ecosystem of a service internet under various actions, quantifying and predicting the succession state of the service community by using a relevant mathematical model, adopting different control optimization strategies aiming at different service communities, realizing the maximization of the capacity that the service community can integrally meet the external service demand, further realizing the maximization of the service value creation capacity of the service internet, and is the problem of the service internet at present.
The service internet control optimization method based on the service community succession prediction model is characterized in that the succession situation inside a service community is represented by the change of the service resource occupancy rate of each service community inside the service community along with time, the service information data of each service community inside the service community in the past period is subjected to quantitative processing, a set of mathematical model for carrying out succession prediction analysis on the service community in the service internet is established, the model is subjected to parameter estimation, short-term trend prediction can be performed on the succession trend of the service community in the service internet, and therefore the control optimization method for the service internet can be further provided in a targeted manner. The control and optimization method for the service internet directly formulated by people is lack of scientificity due to the fact that subjective factors are too strong, and the academic world generally adopts a service internet control and optimization method based on a linear model and a nonlinear model. Common service internet control optimization methods can be classified into a service internet control optimization method based on a ridge regression model, a service internet control optimization method based on a lasso regression model, and other model methods.
Disclosure of Invention
The invention aims to provide a service community succession prediction model-based service internet control optimization method, which utilizes the dynamic change characteristic of the service resource occupancy of each service community in a service community to infer a mathematical model of the succession trend of the service community and estimates the parameters of the model according to historical service information data, so that the model can predict and analyze the future short-term succession trend of any service community in the service internet. And optimally controlling the service internet.
The invention provides a service internet control method based on a service community succession prediction model, which comprises the following steps:
(1) collecting the number of service information of each service population in a service community C in a service Internet in a time period t from a typical application case of the service Internet in the real world, setting n service populations in the service community C, constructing a service community succession prediction data set DC, wherein the data set DC comprises the number of newly generated service individuals, the number of lost service individuals, the size of the number of service individuals of the service population, the size of the service value scale of the service population, the occupation condition of service resources, the times of service business transactions among internal service individuals, the times of service business transactions when the change rate of the number of the service individuals of the service population is maximum and the times of internal overall service business transactions of the service Internet in the service community C in the time period t;
(2) preprocessing the service community succession prediction data set DC in the step (1), namely detecting abnormal values of data items of data elements in the data set DC, supplementing missing values to incomplete data elements and enabling the data element formats in the data set DC to be uniform;
(3) normalizing the processed data set in the step (2) by using a linear normalization method to obtain a normalized data set DC;
(4) respectively calculating the development conditions of the service populations within the time period t according to the data set DC obtained in the step (3), including the service new growth rate Em of the service population i in the service community CiI.e. the proportion of the new service individuals in the service population i in the time period t to all the service individuals in the service population i, and the service extinction rate Ex of the service population ciThat is, the service individuals lost in the service group i in the time period t account for all the service individuals in the service group iSpecific weight of number, initial service resource occupancy q of service population iiThe service resources occupied by the service population i at the end of the time period t account for the proportion of all the service resources of the service internet, wherein i is 1,2,3, …, n;
(5) respectively calculating the value importance Con of n service populations in the service community C according to the data in the data set DC obtained in the step (3)i：
Wherein v isiRepresenting the historical accumulated service value scale of the service population i, i.e. the accumulated service value scale of the service population i within a time period t, giThe change rate of the service value scale of the service population i is represented, namely the ratio of the service income of the service population i in the time period t to the time length, and tau is a dimension conversion coefficient, so that the value importance Con of all n service populations is obtainediCon importance of value of n service groupsiSorting in descending order and marking the sorting number as k, i is 1,2,3, …, n, k is 1,2,3, …, n;
(6) calculating the service population compactness Ad of the service population i according to the data in the data set DC obtained in the step (3)iAnd service population crowding effect AeiWherein the service population is densely populated with a degree AdiThe service interaction frequency in the service population is the ratio of the service transaction times among the service individuals in the service population to the service transaction times among all the service individuals in the service internet in the time period t; service population crowding effect AeiExpressed as the influence of the service population compactness of the current service population on the scale increase of the number of service individuals of the service population,
Aei＝1-(Adi-Adbesti)2
wherein, AdiService population denseness degree, 0, representing service population i<Adi<1，AdiThe larger the service population, the more densely the service population i hasHigh, AdbestiRepresenting the best service population density degree of the service population i, namely the service population density degree when the scale increase rate of the number of service individuals of the service population is maximum, and represented by the ratio of the service business times when the scale change rate of the number of the service individuals of the service population is maximum to the service business times among all the service individuals in the whole service internet; aeiThe service population crowding effect of the representative service population i can be calculated by the formula, 0<Aei<1；
(7) According to the step (4), the step (5) and the step (6), a service resource occupation change rate model of the service population i in the succession process of the service population C in the service internet is constructed as follows:
wherein q iskRepresenting the service resource occupancy rate of the service population with the current service population value importance ranking of k; emkRepresenting the service individual new growth rate of the service population with the value importance ranking of the current service population being k, and being obtained by the calculation mode listed in the step (4); exkRepresenting the service individual extinction rate of the service population with the value importance ranking of the current service population being k, and being obtained by the calculation mode listed in the step (4); the first item of the formula represents the successful occupation of the service resources by the current service category group; the second item represents that the service resource occupancy rate is reduced caused by the extinction of service individuals in the current service population; the third item represents that the strong competition service population causes the weak competition service population to reduce the occupancy rate of the service resources in the service population, and k is 1,2,3, …, n, j is 1,2,3, …, k;
(8) according to the step (7), for the service community C containing n service communities, constructing a service community C succession prediction model in the service Internet as follows:
(9) estimating model parameters according to the acquired data set DC by the service community succession prediction model obtained in the step (8), and calculating dynamic changes of service resource occupancy of each service community in the service community in a short term in the future, namely finishing prediction of succession trend of the service community;
(10) and (4) according to the succession trend of the service community obtained by calculation in the step (9), if the change condition of the service resource occupancy rate q of any one service community is continuously reduced and is close to 0, indicating that the service community dies off, and adjusting the development condition of each service community in the service community to ensure the survival condition of the service community, maintain or further improve the service community meeting capacity for service demands, thereby realizing maximization of service value creation capacity of the service internet.
The service internet control optimization method based on the service community succession prediction model has the advantages that:
1. the method carries out induction and carding on a common model-based service internet control optimization method, carries out targeted quantification on the characteristics of the service internet innovatively based on the ecological characteristics and the system characteristics of the service internet, constructs parameter indexes such as the new growth rate of service individuals of a service population, the extinction rate of the service individuals of the service population, the service value importance of the service population, the service population cohesiveness degree and the service population cohesiveness effect of the service population, replaces the traditional expert manual judgment mode, and further constructs a service population succession prediction model under the service internet.
2. The method overcomes the problem of limited prediction precision of the service internet service community succession trend in the prior art, removes subjective factor impression in the service community succession trend prediction as much as possible, is reasonable in design, rapid and accurate, predicts the service community succession trend in the service internet through the method, has high accuracy and objectivity, can clearly know the internal succession development trend of the service community in the service internet in a short period in the future, further timely makes adjustment management strategies aiming at different succession situations of the service community, and finally provides good support for ensuring sustainable, healthy and prosperous development of the service internet.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a graph showing a real succession data curve of a service community based on a real world service Internet case data set.
FIG. 2 is a model prediction curve diagram of a certain service community succession situation based on a real world service Internet case data set by the method of the present invention.
FIG. 3 is a graph of a service community succession result after control optimization is performed according to a succession prediction result of a service community by the method of the present invention.
Detailed Description
The invention provides a service internet control method based on a service community succession prediction model, which comprises the following steps:
(1) collecting the number of service information of each service population in a service community C in a service Internet in a time period t from a typical application case of the service Internet in the real world, setting n service populations in the service community C, constructing a service community succession prediction data set DC, wherein the data set DC comprises the number of newly generated service individuals, the number of lost service individuals, the size of the number of service individuals of the service population, the size of the service value scale of the service population, the occupation condition of service resources, the times of service business transactions among internal service individuals, the times of service business transactions when the change rate of the number of the service individuals of the service population is maximum and the times of internal overall service business transactions of the service Internet in the service community C in the time period t;
(2) preprocessing the service community succession prediction data set DC in the step (1), namely detecting abnormal values of data items of data elements in the data set DC, supplementing missing values to incomplete data elements and enabling the data element formats in the data set DC to be uniform;
(3) normalizing the processed data set in the step (2) by using a linear normalization method to obtain a normalized data set DC;
(4) respectively calculating the development conditions of the service populations within the time period t according to the data set DC obtained in the step (3), including the service new growth rate Em of the service population i in the service community CiI.e. the proportion of the new service individuals in the service population i in the time period t to all the service individuals in the service population i, and the service extinction rate Ex of the service population ciThe proportion of the lost service individuals of the service population i in the time period t to the number of all the service individuals in the service population i, and the initial service resource occupancy q of the service population iiThe service resources occupied by the service population i at the end of the time period t account for the proportion of all the service resources of the service internet, wherein i is 1,2,3, …, n;
(5) respectively calculating the value importance Con of n service populations in the service community C according to the data in the data set DC obtained in the step (3)i：
Wherein v isiRepresenting the historical accumulated service value scale of the service population i, i.e. the accumulated service value scale of the service population i within a time period t, giThe change rate of the service value scale of the service population i is represented, namely the ratio of the service income of the service population i in the time period t to the time length, and tau is a dimension conversion coefficient, so that the value importance Con of all n service populations is obtainediCon importance of value of n service groupsiSorting in descending order and marking the sorting number as k, i is 1,2,3, …, n, k is 1,2,3, …, n;
(6) calculating the service population compactness Ad of the service population i according to the data in the data set DC obtained in the step (3)iAnd service population crowding effect AeiWherein the service population is densely populated with a degree AdiFor serving seedThe service business interaction frequency in the group is the ratio of the service business times among the service individuals in the service group to the service business times among all the service individuals in the service internet in the time period t; service population crowding effect AeiExpressed as the influence of the service population compactness of the current service population on the scale increase of the number of service individuals of the service population,
Aei＝1-(Adi-Adbesti)2
wherein, AdiService population denseness degree, 0, representing service population i<Adi<1，AdiThe larger the service population, the higher the service population density of the service population i, AdbestiRepresenting the best service population density degree of the service population i, namely the service population density degree when the scale increase rate of the number of service individuals of the service population is maximum, and represented by the ratio of the service business times when the scale change rate of the number of the service individuals of the service population is maximum to the service business times among all the service individuals in the whole service internet; aeiThe service population crowding effect of the representative service population i can be calculated by the formula, 0<Aei<1; the larger the service population condensation effect of the service population i is, the more favorable the service population condensation degree of the service population i is for further expanding the number scale of the service individuals of the service population i, and i is 1,2,3, …, n;
(7) according to the step (4), the step (5) and the step (6), a service resource occupation change rate model of the service population i in the succession process of the service population C in the service internet is constructed as follows:
wherein q iskRepresenting the service resource occupancy rate of the service population with the current service population value importance ranking of k; emkRepresenting the new generation rate of the service individuals of the service population with the importance ranking of the current service population value k, which can be calculated by the calculation method listed in the step (4)Obtaining the compound of formula (II); exkRepresenting the service individual extinction rate of the service population with the value importance ranking of the current service population being k, and being obtained by the calculation mode listed in the step (4); the first item of the formula represents the successful occupation of the service resources by the current service category group; the second item represents that the service resource occupancy rate is reduced caused by the extinction of service individuals in the current service population; the third item represents that the strong competition service population causes the weak competition service population to reduce the occupancy rate of the service resources in the service population, and k is 1,2,3, …, n, j is 1,2,3, …, k;
(8) according to the step (7), for the service community C containing n service communities, constructing a service community C succession prediction model in the service Internet as follows:
(9) estimating model parameters according to the acquired data set DC by the service community succession prediction model obtained in the step (8), and calculating dynamic changes of service resource occupancy of each service community in the service community in a short term in the future, namely finishing prediction of succession trend of the service community;
(10) and (4) according to the succession trend of the service community obtained by calculation in the step (9), if the change condition of the service resource occupancy rate q of any one service community is continuously reduced and is close to 0, indicating that the service community dies off, and adjusting the development condition of each service community in the service community to ensure the survival condition of the service community, maintain or further improve the service community meeting capacity for service demands, thereby realizing maximization of service value creation capacity of the service internet.
The invention is described in further detail below with reference to one embodiment of the invention:
(1) in a typical application case of a real world service internet, service information data of each service population in a service population C in the service internet within a time period t is collected. Assuming that n service populations exist in a service community C, constructing a service community succession prediction data set DC, wherein the data set DC mainly comprises the number of new service individuals, the number of lost service individuals, the number scale of the number of service individuals of the service community C within the period t, the size of the service value scale of the service community, the service resource occupation condition, the number of times of service business transactions among internal service individuals, the number of times of service business transactions when the change rate of the number scale of the service individuals of the service community is maximum, and the number of times of total service business transactions in the service internet.
In this embodiment, an automobile manufacturing service community of a certain automobile industry cluster is used as an application object of the method. The time period t is set to be 300 weeks before 450 weeks from the past, wherein the service information data of the automobile manufacturing service community mainly comprises the number of the automobile manufacturing service individuals of each automobile manufacturing service population in the automobile manufacturing service community in the time period, the number of the automobile manufacturing service individuals lost, the size of the quantity scale of the automobile manufacturing service individuals of the automobile manufacturing service population, the size of the service value scale of the automobile manufacturing service population, the occupation condition of automobile manufacturing service resources, the number of times of the automobile manufacturing service business transaction when the change rate of the quantity scale of the automobile manufacturing service individuals of the automobile manufacturing service population is maximum, and the number of times of the automobile manufacturing service business transaction in the automobile industry cluster. Meanwhile, a graph is drawn according to the service resource occupation situation within 150 weeks after each service population in the automobile manufacturing community, as shown in fig. 1.
(2) Preprocessing the service community succession prediction data set DC in the step (1), namely detecting abnormal values of data items of data elements in the data set DC, supplementing missing values to incomplete data elements and enabling the data element formats in the data set DC to be uniform;
in the face of missing values, the proportion of missing contents in the field and the importance degree of the field are analyzed first. If the field is missing seriously or the field is less important, the field which is not needed can be deleted directly. If the missing content needs to be supplemented, the following ways can be adopted: analyzing (mean, median, mode, etc.) the data of the same field to fill in missing values; manually filling missing values;
regarding format content unification, it is difficult to keep the format and the content consistent due to differences in sources and generation manners of service information data. At this time, the format of the service information data needs to be checked and unified. While outliers, which generally refer to data that deviates significantly from the average of the observed values, need to be detected and processed. The outlier may be a logical error value, or a valid outlier. The abnormal value detection means deleting or correcting a common logic error value in the service information data, preventing a low-level service information data analysis error from being generated, and performing key analysis on a valid abnormal value. Outlier detection the main contents are: removing the repeated value and preventing the service information data from being repeatedly input; and correcting, screening or removing unreasonable values and correcting contradictory contents.
(3) Normalizing the processed data set in the step (2) by using a linear normalization method to obtain a normalized data set DC;
the normalization processing is a common method, and the formula is X _ Nor (X-Min)/(Max-Min), Max is the maximum value of the data in the data set to be normalized, and Min is the minimum value of the data in the data set to be normalized. X _ Nor is a value after the data X normalization process.
(4) And (4) respectively calculating the development condition of each service population in the time period t according to the data set DC obtained in the step (3). Service renewal rate Em including service population i in service population CiThe new service individuals in the service population i account for the proportion of all the service individuals in the service population i in the time period t, and the service extinction rate Ex of the service population iiThe proportion of the lost service individuals of the service population i in the time period t to the number of all the service individuals in the service population i, and the initial service resource occupancy q of the service population iiThe service resources occupied by the service population i at the end of the time period t account for the proportion of all the service resources of the service internet, wherein i is 1,2,3, …, n;
(5) respectively calculating the value importance Con of n service populations in the service community C according to the data in the data set DC obtained in the step (3)i：
Wherein v isiRepresenting the historical accumulated service value scale of the service population i, i.e. the accumulated service value scale of the service population i within a time period t, giAnd (4) representing the scale change rate of the service value of the service population i, namely the ratio of the service income of the service population i in the time period t to the time length, and tau is a dimension conversion coefficient. Con value importance for obtaining all n service populationsiCon importance of value of n service groupsiSorting in descending order and marking the sorting number as k, wherein i is 1,2,3, …, n, k is 1,2,3, …, n;
(6) calculating the service population compactness Ad of the service population i according to the data in the data set DC obtained in the step (3)iAnd service population crowding effect Aei. The service population density degree is the service business interaction frequency in the service population, namely the ratio of the service business times among the service individuals in the service population to the service business times among all the service individuals in the service internet in the time period t; the service population crowding effect is expressed as the influence of the service population crowding degree of the current service population on the increase of the number scale of service individuals of the service population,
Aei＝1-(Adi-Adbesti)2
wherein, AdiService population denseness degree, 0, representing service population i<Adi<1，AdiThe larger the service population, the higher the service population density of the service population i, AdbestiThe optimal service population compactness degree of the representative service population i, namely the service population compactness degree when the scale increase rate of the number of service individuals of the service population is maximum, can be represented by the ratio of the service business times when the scale change rate of the number of the service individuals of the service population is maximum to the service business times among all the service individuals in the whole service internet; aeiA service population crowding effect on behalf of the service population iThe above formula can be calculated to be 0<Aei<1. The larger the service population condensation effect of the service population i is, the more favorable the service population condensation degree of the service population i is for further expanding the number scale of the service individuals of the service population i, and i is 1,2,3, …, n;
(7) according to the step (4), the step (5) and the step (6), a service resource occupation change rate model of the service population i in the succession process of the service population C in the service internet is constructed as follows:
wherein q iskRepresenting the service resource occupancy rate of the service population with the current service population value importance ranking of k; emkRepresenting the service individual new growth rate of the service population with the value importance ranking of the current service population being k, and being obtained by the calculation mode listed in the step (4); exkAnd (4) the service individual extinction rate of the service population with the importance ranking k of the current service population value can be obtained by the calculation mode listed in the step (4). The first item of the formula represents the successful occupation of the service resources by the current service category group; the second item represents that the service resource occupancy rate is reduced caused by the extinction of service individuals in the current service population; the third item represents that the strong competition service population causes the weak competition service population to reduce the occupancy rate of the service resources in the service population, and k is 1,2,3, …, n, j is 1,2,3, …, k;
(8) by the step (7), aiming at the service community C containing n service communities, a service community C succession prediction model in the service Internet is constructed as follows:
for the selected service community for automobile manufacturing, the service community succession prediction model is as follows:
based on the above model, the relevant parameters are calculated according to the steps (4), (5) and (6), as shown in the following table.
| Service group | N1 | N2 | N3 | N4 |
| Service value importance ranking | 3 | 1 | 2 | 4 |
| Service population crowding effect | 0.94 | 0.92 | 0.89 | 0.97 |
| New service rate | 0.0096 | 0.0157 | 0.0244 | 0.0381 |
| Service extinction rate | 0.0074 | 0.0094 | 0.0082 | 0.0078 |
| Initial service resource occupancy of service population | 0.094 | 0.072 | 0.087 | 0.102 |
The model prediction curve is also plotted, as shown in fig. 2. As shown in fig. 1 and fig. 2, the description of the prediction model can describe the service resource occupancy rate variation trend of each service population in the short-term service population in the future, that is, the successive development situation of the service population.
(9) Estimating model parameters according to the acquired data set DC by using the service community succession prediction model obtained in the step (8) to calculate dynamic changes of service resource occupancy of each service community in the service community in a short term in the future, namely completing prediction of succession trend of the service community;
(10) and (4) according to the succession trend of the service groups obtained by the calculation in the step (9), if the change condition of the service resource occupancy rate q of a certain service group is continuously reduced and is close to 0, the service group is most likely to be killed. Therefore, the development conditions of each service population in the service community need to be adjusted, so that the survival condition of the service population is ensured, the capability of the service community for meeting the service requirements is maintained or further improved, and the maximization of the service value creation capability of the service internet is further realized.
Aiming at the prediction result, the automobile manufacturing service population N4 is found to have the possibility of service population extinction, therefore, the service internet manager is required to adjust and manage the individual new growth rate, the individual death rate, the interaction frequency or the function guidance of the automobile manufacturing service of each automobile manufacturing service population in the automobile manufacturing service community, for example, increasing the individual service new rate of the automobile manufacturing service population N4, adjusting the frequency of the automobile manufacturing service business, or the new growth rate or the death rate of the service individuals of other automobile manufacturing service populations are controlled to avoid the death of the service populations caused by malignant service competition and the like, therefore, the capability of meeting the service requirements of the automobile manufacturing service community is ensured and improved, and the size of the service value scale of the automobile industry community is controlled and optimized. The optimized succession trend curve chart of the automobile manufacturing service community is shown in fig. 3.
Claims (1)
1. A service internet control method based on a service community succession prediction model is characterized by comprising the following steps:
(1) collecting the number of service information of each service population in a service community C in a service Internet in a time period t from a typical application case of the service Internet in the real world, setting n service populations in the service community C, constructing a service community succession prediction data set DC, wherein the data set DC comprises the number of newly generated service individuals, the number of lost service individuals, the size of the number of service individuals of the service population, the size of the service value scale of the service population, the occupation condition of service resources, the times of service business transactions among internal service individuals, the times of service business transactions when the change rate of the number of the service individuals of the service population is maximum and the times of internal overall service business transactions of the service Internet in the service community C in the time period t;
(2) preprocessing the service community succession prediction data set DC in the step (1), namely detecting abnormal values of data items of data elements in the data set DC, supplementing missing values to incomplete data elements and enabling the data element formats in the data set DC to be uniform;
(3) normalizing the processed data set in the step (2) by using a linear normalization method to obtain a normalized data set DC;
(4) obtained according to step (3)Respectively calculating the development status of each service population in the time period t, including the service new growth rate Em of the service population i in the service community CiI.e. the proportion of the new service individuals in the service population i in the time period t to all the service individuals in the service population i, and the service extinction rate Ex of the service population ciThe proportion of the lost service individuals of the service population i in the time period t to the number of all the service individuals in the service population i, and the initial service resource occupancy q of the service population iiThe service resources occupied by the service population i at the end of the time period t account for the proportion of all the service resources of the service internet, wherein i is 1,2,3, …, n;
(5) respectively calculating the value importance Con of n service populations in the service community C according to the data in the data set DC obtained in the step (3)i：
Wherein v isiRepresenting the historical accumulated service value scale of the service population i, i.e. the accumulated service value scale of the service population i within a time period t, giThe change rate of the service value scale of the service population i is represented, namely the ratio of the service income of the service population i in the time period t to the time length, and tau is a dimension conversion coefficient, so that the value importance Con of all n service populations is obtainediCon importance of value of n service groupsiSorting in descending order and marking the sorting number as k, i is 1,2,3, …, n, k is 1,2,3, …, n;
(6) calculating the service population compactness Ad of the service population i according to the data in the data set DC obtained in the step (3)iAnd service population crowding effect AeiWherein the service population is densely populated with a degree AdiThe service interaction frequency in the service population is the ratio of the service transaction times among the service individuals in the service population to the service transaction times among all the service individuals in the service internet in the time period t; service population crowding effect AeiIs indicated as the currentThe influence of the service population compactness of the service population on the scale increase of the number of service individuals of the service population,
Aei＝1-(Adi-Adbesti)2
wherein, AdiService population denseness degree, 0, representing service population i<Adi<1，AdiThe larger the service population, the higher the service population density of the service population i, AdbestiRepresenting the best service population density degree of the service population i, namely the service population density degree when the scale increase rate of the number of service individuals of the service population is maximum, and represented by the ratio of the service business times when the scale change rate of the number of the service individuals of the service population is maximum to the service business times among all the service individuals in the whole service internet; aeiThe service population crowding effect of the representative service population i can be calculated by the formula, 0<Aei<1；
(7) According to the step (4), the step (5) and the step (6), a service resource occupation change rate model of the service population i in the succession process of the service population C in the service internet is constructed as follows:
wherein q iskRepresenting the service resource occupancy rate of the service population with the current service population value importance ranking of k; emkRepresenting the service individual new growth rate of the service population with the value importance ranking of the current service population being k, and being obtained by the calculation mode listed in the step (4); exkRepresenting the service individual extinction rate of the service population with the value importance ranking of the current service population being k, and being obtained by the calculation mode listed in the step (4); the first item of the formula represents the successful occupation of the service resources by the current service category group; the second item represents that the service resource occupancy rate is reduced caused by the extinction of service individuals in the current service population; the third item represents that the strong competition service group causes the weak competition service group to reduce the service resource occupancy rate of the service community, and k is 1,2,3,…,n，j＝1,2,3,…,k；
(8) According to the step (7), for the service community C containing n service communities, constructing a service community C succession prediction model in the service Internet as follows:
(9) estimating model parameters according to the acquired data set DC by the service community succession prediction model obtained in the step (8), and calculating dynamic changes of service resource occupancy of each service community in the service community in a short term in the future, namely finishing prediction of succession trend of the service community;
(10) and (4) according to the succession trend of the service community obtained by calculation in the step (9), if the change condition of the service resource occupancy rate q of any one service community is continuously reduced and is close to 0, indicating that the service community dies off, and adjusting the development condition of each service community in the service community to ensure the survival condition of the service community, maintain or further improve the service community meeting capacity for service demands, thereby realizing maximization of service value creation capacity of the service internet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110046833.1A CN112712396A (en) | 2021-01-14 | 2021-01-14 | Service internet control method based on service community succession prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110046833.1A CN112712396A (en) | 2021-01-14 | 2021-01-14 | Service internet control method based on service community succession prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112712396A true CN112712396A (en) | 2021-04-27 |
Family
ID=75549016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110046833.1A Pending CN112712396A (en) | 2021-01-14 | 2021-01-14 | Service internet control method based on service community succession prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112712396A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113342331A (en) * | 2021-05-21 | 2021-09-03 | 武汉大学 | Evolution analysis method of ecology-oriented software service system |
-
2021
- 2021-01-14 CN CN202110046833.1A patent/CN112712396A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113342331A (en) * | 2021-05-21 | 2021-09-03 | 武汉大学 | Evolution analysis method of ecology-oriented software service system |
| CN113342331B (en) * | 2021-05-21 | 2023-10-03 | 武汉大学 | Ecological-oriented software service system evolution analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111105104A (en) | Short-term power load prediction method based on similar day and RBF neural network | |
| CN111553463B (en) | Method for estimating throughput of wireless access point based on deep learning and network parameters | |
| CA2590438A1 (en) | System and method for predictive product requirements analysis | |
| CN114666224A (en) | Dynamic allocation method, device, equipment and storage medium for business resource capacity | |
| CN112712396A (en) | Service internet control method based on service community succession prediction model | |
| CN109167806B (en) | Uncertain QoS (quality of service) perception Web service selection method based on foreground theory | |
| CN107977855B (en) | Method and device for managing user information | |
| CN116909751B (en) | Resource allocation method in cloud computing system | |
| CN114584601A (en) | User loss identification and intervention method, system, terminal and medium | |
| CN115544250B (en) | Data processing method and system | |
| CN115689201A (en) | Multi-criterion intelligent decision optimization method and system for enterprise resource supply and demand allocation | |
| TWI792101B (en) | Data Quantification Method Based on Confirmed Value and Predicted Value | |
| CN112712397A (en) | Service internet optimization management method based on service population evolution prediction model | |
| CN113052629A (en) | Network user image drawing method based on CECU system intelligent algorithm model | |
| CN112631882A (en) | Capacity estimation method combined with online service index characteristics | |
| Van Berkel | Adaptive Survey Design for the Dutch Labour Force Survey | |
| CN117541200B (en) | Project management method and system based on LTC flow | |
| CN117828371B (en) | Intelligent analysis method for business information of comprehensive operation and maintenance platform | |
| CN117114761B (en) | Supply chain information management system based on integral data analysis | |
| CN111080456B (en) | ERP project auxiliary decision support system and method based on environmental effect feedback | |
| CN117828389B (en) | Distributed system monitoring method based on intelligent operation and maintenance | |
| Weijie et al. | Estimation of single equipment standard in equipment maintenance expenditure based on cluster analysis | |
| CN118158092A (en) | Computing power network scheduling method and device and electronic equipment | |
| CN116720322A (en) | Intelligent recommendation model design method for demand response potential users, industries and lines | |
| CN117078290A (en) | Method for dynamically adjusting price of air ticket |
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 |