CN106022827A - Power grid service method and system based on user behavior information - Google Patents

Abstract

The invention discloses a power grid service method based on user behavior information, and the method comprises the steps: obtaining the information of a registered user of a state grid electronic mall platform, all registration information of a third side company and the transaction information; listing information resource hierarchical structures in an electronic mall according to the types of information, the number of pieces of information and the obtaining complexity; building a value evaluation index system of the electronic mall information from the view of the information characteristics and user characteristics; carrying out the analysis of the information in the value evaluation index system of the electronic mall information through employing a fuzzy synthetic evaluation method, and screening out the valuable information. Therefore, the method provided by the invention solves problems that mass data cannot be used reasonably, even becomes a burden, and finally is abandoned.

Description

A kind of grid service method and system based on user behavior information

Technical field

The present invention relates to big data technique field, particularly relate to a kind of grid service method based on user behavior information and System.

Background technology

Along with computer networking technology and the continuous maturation of database technology, current conventional business is the most progressively towards electricity Sub-commercial affairs stride forward.The trend of this electronization in trade is not only the mode of doing business provided convenience of client and selects widely, together Time also provide for businessman and more in depth understand client requirement information and the probability of Shopping Behaviors feature.

Along with the foundation in state's net store, traditional operation is netted by state and service mode will be changed, " the Internet+intelligence Electricity consumption " developing direction of following electrical network will be become.But, the difficult problem that e-commerce website often is faced with is not how to build Erect, but how to attract, excavate and keep here the customer resources of oneself.Internet era be one for ecommerce Opportunity, it is possible to expand the business of oneself easily, but simultaneously for user for, acquisition information also becomes abnormal quick, energy Enough suppliers finding oneself within the shortest time, and get a good buy by shopping around, select most suitable one.This time Waiting, what e-commerce website was to be accomplished is how to allow users select oneself, and the demand of client the most just becomes primary pre- The information first found.

Electronic emporium website all may produce millions of trading volumes and the friendship of hundreds of millions of pages every day Mutually.But substantial amounts of data only record the behavior of user, and do not reflect valuable information, many potential rule Then the most it is not found with the knowledge buried.Although e-commerce website is able to record that abundant Transaction Information, accesses letter Cease the data relevant with client, but a large amount of advantageous information contained in these data resources the most but fail to obtain sufficiently Excavate and utilize.Mass data for electronic emporium website, it is to understand that they are far beyond the ability of people.Want to make number According to really becoming the resource of a company, only make full use of operational decision making and strategic development service that data are company self, The most substantial amounts of data are likely to become burden, even become rubbish.But, the computing capability beaten along with our calculating and storage Ability is while developing rapidly, and its intellectuality is but still in the primary stage.Similarly, an e-business network stands in scale day While flaring is big, although produce huge data set with accumulating over a long period, but cannot be given in sales tactics and more have valency The tutorial message of value, often allows client get lost in the ocean of commodity and information, it is very difficult to find the commodity that oneself is required smoothly, thus Lose patience, ultimately result in the loss of corporate client group.

Summary of the invention

In view of this, it is an object of the invention to propose a kind of grid service method based on user behavior information and be System, solving above-mentioned mass data can not rationally apply, and even becomes burden, burden, final outcast problem.

Based on above-mentioned purpose present invention grid service based on user behavior information method, including step:

Obtain the information of registered users of state's net electronic emporium platform, whole log-on messages of third company and transaction letter Breath；The information resources hierarchical structure in electronic emporium is enumerated according to the complexity of the kind of information, quantity and acquisition；

From information characteristic and the angle of user personality, build the value evaluation index system of electronic emporium information；

Carried out by the information value in the fuzzy synthetic appraisement method the value evaluation index system to electronic emporium information Analyze, filter out the valuable information of tool.

In some embodiments of the invention, described information resources hierarchical structure includes:

The information of ontology level: include user profile data, order master data, order detailed data, merchandise news Deng；

The information of perception level: user is to the evaluation information of commodity and the satisfaction information of shopping；

The information of intensive level: this hierarchical information is issued by various third company, is that third company or people are according to respectively The information planting ontology level and perception level is integrated；Including advertising message, excitation information.

In some embodiments of the invention, described from information characteristic with user personality angle, construct electronic emporium Information value assessment indicator system；Wherein, first class index is user personality and information characteristic, corresponding again under each first class index Corresponding two-level index.

In some embodiments of the invention, the described value assessment by fuzzy synthetic appraisement method to electronic emporium information Information value in index system is analyzed, and filters out the valuable information of tool and includes:

Analyze the significance level of each attribute, reasonably determine the weight of each attribute；

Use Field Using Fuzzy Comprehensive Assessment that information value index is carried out overall merit.

In some embodiments of the invention, information value index is comprehensively commented by described employing Field Using Fuzzy Comprehensive Assessment Valency, including:

First, determine set of factors and Comment gathers: the set of one-level evaluation index is designated as the first level factor collection U={U₁,U₂, U₁, U₂It is respectively user personality and information characteristic；The set of two-level appraisement index is respectively the second level factor collection U={u₁,u₂, u₁Be by 6 sub-indexs of user personality are constituted, u₂It is made up of 12 sub-indexs of " information characteristic "；Comment gathers is designated as V={v₁,v₂, v₃,v₄,v₅, for different factors and the value of information, 5 grades of comments in Comment gathers represent different implications respectively；

Second, determine fuzzy overall evaluation matrix: to set of factors u₁To u₂In each factor do an evaluation, respectively Obtain FUZZY MAPPING f of u to V₁To f₅, FUZZY MAPPING can induce fuzzy relation:

R∈F(u_i× V), i=1,2,3,4,5

Note set of factors U₁The evaluation vector of i-th factor be (r_i1,r_i2,r_i3,r_i4,r_i5) (i=1,2 ... 5), so Corresponding fuzzy evaluating matrix is:

$R=\left[\begin{array}{cccc}{r}_{11}& r_{12}& \mathrm{...}& r_{15}\\ r_{21}& r_{22}& \mathrm{...}& r_{25}\\ .& .& & .\\ .& .& & .\\ .& .& & .\\ r_{51}& r_{52}& \mathrm{...}& r_{55}\end{array}\right]$

Wherein

Rij is that i-th factor is to the degree of membership of jth grade comment in Comment gathers；

3rd, calculate fuzzy synthesis rating result: the first level factor user personality of information value, information characteristic evaluation to Amount is respectively

V₁=W₁·R₁=(v_a1,v_a2,...,v_a5),

V₂=W₂·R₂=(v_b1,v_b2,...,v_b5),

Wherein, W₁、W₂Represent user personality, information characteristic every sub-index weights vector respectively；R₁、R₂Represent set of factors u₁、u₂Fuzzy evaluating matrix；v_a1、v_b1Be respectively the first level factor user personality ", information characteristic is to the comment of i-th grade Degree of membership；

The evaluation vector obtaining information value the most further is

$C=W\·\left[\begin{array}{c}V1\\ V2\end{array}\right]=(v_{c1},v_{c2},\mathrm{...},v_{c5}),$

Wherein v_c1(i=1,2 ... 5) it is respectively the information value degree of membership to the comment of i-th grade；It is subordinate to according to maximum Genus degree principle, to the information comment being evaluated be

From the above it can be seen that the grid service method and system based on user behavior information that the present invention provides, The mass data produced electronic emporium by rational method carries out category filter, extracts valuable information, the most again Valuable information is analyzed, thus is best understood from electricity consumption behavior and the consumption habit of user, set up " Xiao of user As describing ", learn the hobby of user, thus formulate more targeted Innovative Service Modes for user, improve service quality, real Existing user and the two-way interaction of electrical network.

Accompanying drawing explanation

Fig. 1 is grid service method flow schematic diagram based on user behavior information in the embodiment of the present invention；

Fig. 2 is the application architecture schematic diagram of embodiment of the present invention China net store platform；

Fig. 3 is the E-R figure of embodiment of the present invention China net mall system；

Fig. 4 is the data type figure in embodiment of the present invention China net store.

Detailed description of the invention

For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference Accompanying drawing, the present invention is described in more detail.

It should be noted that the statement of all uses " first " and " second " is for distinguishing two in the embodiment of the present invention The entity of individual same names non-equal or the parameter of non-equal, it is seen that " first " " second ", only for the convenience of statement, should not Being interpreted as the restriction to the embodiment of the present invention, this is illustrated by subsequent embodiment the most one by one.

Refering to shown in Fig. 1, for grid service method flow schematic diagram based on user behavior information in the embodiment of the present invention, Described grid service method based on user behavior information includes:

Step 101, obtains registration user, whole log-on messages of third company and the friendship of state's net electronic emporium platform Easily information.

In an embodiment, the application architecture of described state's net store platform is as in figure 2 it is shown, mainly include database side, clothes Business device end, application end, mobile terminal and store back-stage management.Wherein, the mass data of described state net store platform is mainly deposited In database side.And server end is provided with cloud platform, interface service and payment platform etc..Especially, in described state The application end of net store platform includes order management, checks price and stock, information analysis and evaluation, activity management, consulting pipe Reason, mobile register, data analysis, e-management, member's integration managing etc. functional module.It addition, in store back-stage management In include commodity consultation distribution, precision marketing, consumer interaction, consumption data analysis, and devise issue sales promotion, electronics Preferential, Below-the-line, and unified member management, integration managing etc..The most then include mobile register, The inquiry of member's integration, one-button-to-buy, and membership service, barcode scanning place an order, mobile payment, and geo-location service, neighbouring door Shop pushes, and the management of sales promotion information, electronic offers, also have share online, member interactive etc..It addition, the described the 3rd Fang company can be electric automobile sales company, distributed power source sales company and energy supplier etc..

It is preferred that as it is shown on figure 3, also store operation flow and the analysis of data and refinement are netted by state, drawn state's net The E-R figure of mall system.Wherein, the data base of state's net store platform relates to user, manager, commodity, shopping cart, order Five entities.By analyzing their content and data flow, specifically devise data below item and data structure:

(1) user subject, the attribute comprised has: user name, login password, email address, number, Real Name, sex, Better address, postcode, telephone number, integration.

(2) manager's entity, the attribute comprised has: login name, login password.

(3) commodity entity, the attribute comprised has: trade name, commodity, commodity price, commodity brief introduction, author, quantity in stock.

(4) shopping cart entity, the attribute comprised has: trade name, unit price, quantity, integration, preferential, subtotal.

(5) order entity, the attribute comprised has: O/No., buyer, trade name, unit price, quantity, delivery mode, in detail Thin address, total.

Further, according to state net store design data item and data structure, state net store produce data type (as Shown in Fig. 4), mainly include user profile data, order master data, order detailed data, merchandise news master meter etc..Its In, user profile data can set up incidence relation by member account and order master data, and order master data can be led to Cross order account and order detailed data and set up incidence relation, described order detailed data then can by commodity account with Merchandise news master meter sets up incidence relation.

Step 102, enumerates the information resources in electronic emporium according to the complexity of the kind of information, quantity and acquisition Hierarchical structure.

As embodiment, after collecting the data in store, according to the complexity of data acquisition, the quantity of data and The information resources of electronic emporium are divided into following 3 levels by the method for data acquisition:

1) information of ontology level.This hierarchical information is issued by " thing ", is the truth of objective world.This layer Secondary information is structurized initial data, independent of man's will, is substantially not have significant cognitive element.Example As: include user profile data, order master data, order detailed data, merchandise news etc..

2) information of perception level.This hierarchical information is issued by people, is that things perception is sent out by people according to oneself The information of cloth, it is worth cognitive competence and the level depending on publisher.This hierarchical information is typically unstructured information, than Such as user's information such as satisfaction to the evaluation of commodity and shopping.

3) information of intensive level.This hierarchical information is many to be issued by various third company, has small part to be issued by people, is Third company or people according to the information of various ontology levels and perception level integrated after, by processed according still further to necessarily The systemic information that normal structure is got up.This hierarchical information existing structure information, also has unstructured information.Believe including advertisement Breath, excitation information etc..

Step 103, from information characteristic and the angle of user personality, the value assessment building electronic emporium information refers to Mark system.

In one specifically embodiment, as shown in table 1, comprehensively commenting of state's net electronic emporium information value is mainly listed Valency index system, the present invention refers to from information characteristic and user personality angle, the information value evaluation constructing electronic emporium Mark system.Wherein, first class index is " user personality " and " information characteristic ", because information user determines him to the demand of information Judgement to information value, the value of network business information needs the utilization through user just can be achieved, each one-level Corresponding corresponding two-level index again under index.

The System of Comprehensive Evaluation of table 1 state net electronic emporium information value

Step 104, by the information in the fuzzy synthetic appraisement method the value evaluation index system to electronic emporium information Value is analyzed, and filters out more valuable information.

In an embodiment, after having determined information value System of Comprehensive Evaluation, combining of information value to be set up Close evaluation model.The foundation of the comprehensive evaluation model of information value is broadly divided into two steps:

(1) analyze the significance level of each attribute, reasonably determine the weight of each attribute.

By a large amount of inspection informations and pertinent literature, obtain information value evaluation based on user personality and information characteristic The weight of each index of index system.The respective weights of index, indices is sets forth based on user personality and information characteristic Corresponding weight is shown in Table 2.

Table 2 information value comprehensive evaluation index weight

(2) select suitable method, complete the overall merit to information value.

Then selecting Field Using Fuzzy Comprehensive Assessment that information value index is carried out overall merit, specifically flow process is as follows:

Step one: set of factors and the determination of Comment gathers:

The set of one-level evaluation index is designated as the first level factor collection U={U₁,U₂, U₁,U₂It is respectively user personality and information is special Property.The set of two-level appraisement index is respectively the second level factor collection U={u₁,u₂, u₁It is by 6 of " user personality " sub-index structures Become, u₂It is made up of 12 sub-indexs of " information characteristic ".

Comment gathers is designated as V={v₁,v₂,v₃,v₄,v₅, for different factors and the value of information, 5 in Comment gathers Level comment represents different implications respectively.The concrete meaning of Comment gathers correspondence difference factor is shown in Table 3.

The corresponding Comment gathers of each factor of table 3 information value

Step 2: the determination of fuzzy overall evaluation matrix:

In this embodiment, to set of factors u₁To u₂In each factor do an evaluation, respectively obtain the fuzzy of u to V Map f₁To f₅, FUZZY MAPPING can induce fuzzy relation:

R∈F(u_i× V), i=1,2,3,4,5

In reality, it is common that the every factor being worth information according to Comment gathers by expert group is evaluated, by commenting Valency result constructs evaluation vector and the fuzzy matrix of each factor.That is, note set of factors U₁The evaluation vector of i-th factor be (r_i1,r_i2,r_i3,r_i4,r_i5) (i=1,2 ... 5), so corresponding fuzzy evaluating matrix is:

$R=\left[\begin{array}{cccc}{r}_{11}& r_{12}& \mathrm{...}& r_{15}\\ r_{21}& r_{22}& \mathrm{...}& r_{25}\\ .& .& & .\\ .& .& & .\\ .& .& & .\\ r_{51}& r_{52}& \mathrm{...}& r_{55}\end{array}\right]$

Wherein

Rij is that i-th factor is to the degree of membership of jth grade comment in Comment gathers.

Step 3: the calculating of fuzzy synthesis rating result

The first level factor " user personality " of information value, the evaluation vector of " information characteristic " are respectively

V₁=W₁·R₁=(v_a1,v_a2,...,v_a5),

V₂=W₂·R₂=(v_b1,v_b2,...,v_b5),

Wherein, W₁、W₂Represent " user personality ", " information characteristic " every sub-index weights vector respectively；R₁、R₂Represent because of Element collection u₁、u₂Fuzzy evaluating matrix.v_a1、v_b1It is respectively the first level factor " user personality ", " information characteristic " to i-th grade The degree of membership of comment.

The evaluation vector obtaining information value the most further is

$C=W\·\left[\begin{array}{c}V1\\ V2\end{array}\right]=(v_{c1},v_{c2},\mathrm{...},v_{c5}),$

Wherein v_c1(i=1,2 ... 5) it is respectively the information value degree of membership to the comment of i-th grade.It is subordinate to according to maximum Genus degree principle, to the information comment being evaluated be

As an alternative embodiment of the invention, described grid service method based on user behavior information can also basis The valuable information extracted to formulate corresponding Innovative Service Modes for user and third company.Thus, for user More targeted service is provided, strengthens the two-way interaction of user and electrical network.

Wherein, can comform to extract in multi information by said method is worth higher " user credit information ", for User credit information can propose user credit service, sets up user credit evaluation platform, evaluates the credit of user, its The client of middle different credit grade can specifically be subdivided into following a few class:

Credit A level (high credit client): open up green channel, carries out customer manager's unrestricted choice system, periodically visits, preferentially Handling the power supply service of client, the problem of priority treatment client, when power supply shortage, electric power resource tilts to it, client Internal accident maintenance, routine test and maintenance expense preference.Enjoy the information that electrical network is up-to-date, seek on the net at state's net 95598 Industry Room transacting business, payment etc. enjoys certain preferential, buys product and also enjoy certain discount in this external state net store, or Person uses the modes such as accumulated point exchanging.

User's B level (general credit client): risk is relatively low, answers A clear guidance can develop into A class, loosens management and control and then drop For C class, Service Principle is to check erroneous ideas at the outset, many multihomings, and concrete incentive measure can refer to A level client, and some prevention and control measure can With reference to C level client.

User's C level (low credit client): certain measure in addition management and control should be taked, shorten the payment cycle of client, the electricity charge Transfer by stages, reduce the probability of the new-debt electricity charge；Sign the old deficient electricity charge agreement of amortization, it is to avoid owed the electricity charge and formed bad credit； Require to provide electricity charge guarantee or the guarantee of electricity consumption facility.

User D level (seriously breaking one's promise) client: increase credit review frequency, its behavior of credit of looking over one's shoulder；Cancelling comments A to provide Lattice；It is exposed by open channel, causes pressure from public opinion to it；Automatically implemented by load control unit to ration the power supply or stop Electricity.

In addition can also be multiplied by the electric power integration of user according to different credit grades in conjunction with electric power integration system (0.5-2) coefficient, class A user is multiplied by 2；Class B user is multiplied by 1；Class C user is multiplied by 0.8；Class D user is multiplied by 0.5, thus comes Excitation user improves credit grade.

Additionally, corresponding service can also be designed for analyzing other valuable information, thus, provide the user and more have pin Service to property, strengthens the two-way interaction of user and electrical network.According to above-mentioned information value evaluation methodology, obtain state's net store and respectively believe The breath degree of membership to comments at different levels in Comment gathers, filters out according to maximum membership grade principle and is worth higher information.Wherein, user With can demand information, price change state's net store is serviced by the information that affect of user behavior, user evaluation information, user Credit information there is the highest value, to state net store operation have important directive function, by analyze above-mentioned information, Thought in conjunction with " the Internet+intelligent power " proposes Innovative Service Modes.It is preferred that described Innovative Service Modes includes dripping Drip energy services, the energy purchases by group service, energy comment services and user credit service.

Wherein, described drip energy services, by analyze user with can demand information draw user by energy demand Difference, along with the continuous progress of technology, the difference of energy requirements is gradually changed by user, and what user needed is no longer single energy Source supplying mode but efficiently variation energy supply mode, can be different energy based on above-mentioned analysis state net electronic emporium Source supplier provides a unified platform, with reference to the service mode of the O2O of " drip and call a taxi ", for different types of energy consumption user Personalized point-to-point energy services is provided.Energy consumption user can by oneself with can demand information be published to electronic emporium platform On, the demand information of user is uniformly processed by electronic emporium, and is determined the particular location of user by location, thus is User screens suitable energy supplier, and neighbouring energy supplier is optional after seeing the information that user issues to be carried out Join or ignore.After coupling confirms, both sides can consult further and conclude the business, thus improve the efficiency of energy services.

Wherein, the described energy purchases by group service and must find the information that affects of user behavior by analyzing price change, with One product, when price is the highest, the number of users of purchase compare price low time buy number of users lacked 3-5 times, though user So may have and attempt new forms of energy, the wish of new service, but the restriction of purchasing power makes them abandon attempting new forms of energy, and still protect Stay consumption habit originally, propose the energy based on above-mentioned analysis and purchase by group service, be similar to existing network group buying.User is to purchase by group Mode assemble purchasing power, to promote user status in Market Games；And purchase by group and can make product or service price fall Low, improve the enthusiasm that user buys；Provide the platform of bulk sale for energy provider, it is simple to it carries out unifying pipe simultaneously Control.It is applicable to dispersion but the considerable town and country individual consumer group of total amount, is conducive to saving bilateral cost.From the perspective of enterprise, Group buying websites is a distributor selling product, is also an Information Communication platform gathering numerous consumer.Enterprise leads to Cross the cooperation with group buying websites, can promote popularity and power of influence, and obtain the concern of the user of enormous amount, work as consumption Person's First Consumption obtains and preferably experiences and buy high-quality product, and this will obtain new client for enterprise and lay the foundation.Group Purchase product or the service of website, price possesses degree of depth discount, kind has multiformity, geographically there is localization Etc. feature.

Wherein, the evaluation information of state's net store service is found by the comment service of the described energy by analyzing user, and user produces The basis of raw purchasing behavior is " needs ", and on an as-needed basis, the purchasing behavior of user can be experienced and know, understands, likes, partially Get well, be sure of, buy these stages.The final consumption decision-making that user makes is affected by evaluation information the most more and more. According to evaluation information, it is processed arranging to individual consumption information, becomes the work done when user selects and important ginseng Examine standard.In addition user also affects other consumers by uploading evaluation information to the propagation of oneself consumption experience, is formed Chain effect.For new user, true, complete evaluation information can stimulate the desire to purchase of new user, reduces due to " not Know " and abandon the probability bought.Propose energy comment service based on above-mentioned analysis, develop special energy field comment soft Part, it is allowed to all types of user and energy services class company carry out two-way comment.This pattern is similar to existing " popular comment ".Favorably Coming into the open in Transaction Information, can carry out with other business models coupling and be conducive to improve its efficiency and credit.Consumer can So that product and the service bought on electronic emporium to be evaluated accordingly, electronics so can be understood the most objectively The deficiency that store service exists, thus update and improve products & services quality.Raising consumer can also be allowed to state's net " credibility " of electronic emporium, thus realize " relieved consumption " at electronic emporium, it is also possible to pushed away rapidly by " public praise " effect A wide service, thus improve the efficiency that state's net store intelligent power service is universal.

Wherein, user credit service by analyze the credits such as the payment of user, demand response information it is found that for The user that credit grade is high, pushes demand response service or can obtain the active response of user with energy guidance, improving electricity consumption effect Rate, but for the low user of credit grade, Push Service would generally be placed to be paid no attention to, if considering the use that credit is low in a large number Family, it is likely that can not be completed plan target, it is impossible to collect the electricity charge in time, causes further loss, and therefore state's net store should User is carried out credit classification, and the user for different credit grades formulates service and information pushing targetedly, improves and uses The responsiveness at family, based on above-mentioned analysis, proposes user credit service.User credit evaluation platform is set up in state's net store, to user Credit evaluate, wherein the client of different credit grades can specifically be subdivided into following a few class:

Credit A level (high credit client): open up green channel, carries out customer manager's unrestricted choice system, periodically visits, preferentially Handling the power supply service of client, the problem of priority treatment client, when power supply shortage, electric power resource tilts to it, client Internal accident maintenance, routine test and maintenance expense preference.Enjoy the information that electrical network is up-to-date, seek on the net at state's net 95598 Industry Room transacting business, payment etc. enjoys certain preferential, buys product and also enjoy certain discount in this external state net store, or Person uses the modes such as accumulated point exchanging.

User's B level (general credit client): risk is relatively low, answers A clear guidance can develop into A class, loosens management and control and then drop For C class, Service Principle is to check erroneous ideas at the outset, many multihomings, and concrete incentive measure can refer to A level client, and some prevention and control measure can With reference to C level client.

User's C level (low credit client): certain measure in addition management and control should be taked, shorten the payment cycle of client, the electricity charge Transfer by stages, reduce the probability of the new-debt electricity charge；Sign the old deficient electricity charge agreement of amortization, it is to avoid owed the electricity charge and formed bad credit； Require to provide electricity charge guarantee or the guarantee of electricity consumption facility.

User D level (seriously breaking one's promise) client: increase credit review frequency, its behavior of credit of looking over one's shoulder；Cancelling comments A to provide Lattice；It is exposed by open channel, causes pressure from public opinion to it；Automatically implemented by load control unit to ration the power supply or stop Electricity.

In addition can also be multiplied by the electric power integration of user according to different credit grades in conjunction with electric power integration system (0.5-2) coefficient, class A user is multiplied by 2；Class B user is multiplied by 1；Class C user is multiplied by 0.8；Class D user is multiplied by 0.5, thus comes Excitation user improves credit grade.

In sum, the grid service method based on user behavior information that the present invention provides, creatively by electricity Sub-store magnanimity information is tentatively layered according to information type, quantity, acquisition complexity, then from information characteristic with And the angle of user personality sets out, build the value evaluation index system of electronic emporium information；Further, fuzzy assessment method is used The information of electronic emporium is carried out value assessment, filters out more valuable information, finally by the information of analysis, in conjunction with " interconnection Net+intelligent power " thought, it is proposed that state's net store Innovative Service Modes, solve information resources waste, state's net is mutual with user The problem that dynamic few, service mode is of low quality, user responds enthusiasm difference；Thus, the present invention has extensive, great popularization meaning Justice；Finally, whole described grid service method based on user behavior information is compact, it is easy to control.

Those of ordinary skill in the field are it is understood that the discussion of any of the above embodiment is exemplary only, not It is intended to imply that the scope of the present disclosure (including claim) is limited to these examples；Under the thinking of the present invention, above example Or can also be combined between the technical characteristic in different embodiments, step can realize with random order, and exists such as Other change of the many of the different aspect of the upper described present invention, in order to concisely they do not provide in details.

It addition, for simplifying explanation and discussing, and in order to obscure the invention, can in the accompanying drawing provided To illustrate or can not illustrate and integrated circuit (IC) chip and the known power supply/grounding connection of other parts.Furthermore, it is possible to Device is shown in block diagram form, in order to avoid obscuring the invention, and this have also contemplated that following facts, i.e. about this The details of the embodiment of a little block diagram arrangements be the platform that depends highly on and will implement the present invention (that is, these details should In the range of being completely in the understanding of those skilled in the art).Elaborating that detail (such as, circuit) is to describe the present invention's In the case of exemplary embodiment, it will be apparent to those skilled in the art that can there is no these details In the case of or these details change in the case of implement the present invention.Therefore, these descriptions are considered as explanation Property rather than restrictive.

Although invention has been described to have been incorporated with the specific embodiment of the present invention, but according to retouching above Stating, a lot of replacements, amendment and the modification of these embodiments will be apparent from for those of ordinary skills.Example As, other memory architecture (such as, dynamic ram (DRAM)) can use discussed embodiment.

Embodiments of the invention be intended to fall into all such replacement within the broad range of claims, Amendment and modification.Therefore, all within the spirit and principles in the present invention, any omission of being made, amendment, equivalent, improvement Deng, should be included within the scope of the present invention.

Claims (5)

1. a grid service method based on user behavior information, it is characterised in that include step:

Obtain information of registered users, whole log-on messages of third company and the Transaction Information of state's net electronic emporium platform； The information resources hierarchical structure in electronic emporium is enumerated according to the complexity of the kind of information, quantity and acquisition；

From information characteristic and the angle of user personality, build the value evaluation index system of electronic emporium information；

It is analyzed by the information value in the fuzzy synthetic appraisement method the value evaluation index system to electronic emporium information, Filter out the valuable information of tool.

Method the most according to claim 1, it is characterised in that described information resources hierarchical structure includes:

The information of ontology level: include user profile data, order master data, order detailed data, merchandise news etc.；

The information of perception level: user is to the evaluation information of commodity and the satisfaction information of shopping；

The information of intensive level: this hierarchical information is issued by various third company, is that third company or people are according to various The information of body opinion level and perception level is integrated；Including advertising message, excitation information.

Method the most according to claim 2, it is characterised in that described from information characteristic with user personality angle, structure Build the information value assessment indicator system of electronic emporium；Wherein, first class index is user personality and information characteristic, each one-level Corresponding corresponding two-level index again under index.

Method the most according to claim 3, it is characterised in that described by fuzzy synthetic appraisement method to electronic emporium believe Information value in the value evaluation index system of breath is analyzed, and filters out the valuable information of tool and includes:

Analyze the significance level of each attribute, reasonably determine the weight of each attribute；

Use Field Using Fuzzy Comprehensive Assessment that information value index is carried out overall merit.

Method the most according to claim 4, it is characterised in that described employing Field Using Fuzzy Comprehensive Assessment is to information value index Carry out overall merit, including:

First, determine set of factors and Comment gathers: the set of one-level evaluation index is designated as the first level factor collection U={U₁,U₂, U₁,U₂Point Wei user personality and information characteristic；The set of two-level appraisement index is respectively the second level factor collection U={u₁,u₂, u₁It is by user 6 sub-indexs of characteristic are constituted, u₂It is made up of 12 sub-indexs of " information characteristic "；Comment gathers is designated as V={v₁,v₂,v₃,v₄, v₅, for different factors and the value of information, 5 grades of comments in Comment gathers represent different implications respectively；

Second, determine fuzzy overall evaluation matrix: to set of factors u₁To u₂In each factor do an evaluation, respectively obtain u FUZZY MAPPING f to V₁To f₅, FUZZY MAPPING can induce fuzzy relation:

R∈F(u_i× V), i=1,2,3,4,5

Note set of factors U₁The evaluation vector of i-th factor be (r_i1,r_i2,r_i3,r_i4,r_i5) (i=1,2 ... 5), so accordingly Fuzzy evaluating matrix be:

$R=\left[\begin{array}{cccc}{r}_{11}& r_{12}& ...& r_{15}\\ r_{21}& r_{22}& ...& r_{25}\\ \begin{array}{c}.\\ .\\ .\end{array}& \begin{array}{c}.\\ .\\ .\end{array}& \begin{array}{c}\\ \\ \end{array}& \begin{array}{c}.\\ .\\ .\end{array}\\ r_{51}& r_{52}& ...& r_{55}\end{array}\right]$

Wherein

Rij is that i-th factor is to the degree of membership of jth grade comment in Comment gathers；

3rd, calculate fuzzy synthesis rating result: the first level factor user personality of information value, the evaluation vector of information characteristic divide It is not

V₁=W₁·R₁=(v_a1,v_a2,...,v_a5),

V₂=W₂·R₂=(v_b1,v_b2,...,v_b5),

Wherein, W₁、W₂Represent user personality, information characteristic every sub-index weights vector respectively；R₁、R₂Represent set of factors u₁、u₂ Fuzzy evaluating matrix；v_a1、v_b1Be respectively the first level factor user personality ", information characteristic is subordinate to the comment of i-th grade Degree；

The evaluation vector obtaining information value the most further is

$C=W\·\left[\begin{array}{c}V1\\ V2\end{array}\right]=(v_{c1},v_{c2},...,v_{c5}),$

Wherein v_c1(i=1,2 ... 5) it is respectively the information value degree of membership to the comment of i-th grade；According to maximum membership degree Principle, to the information comment being evaluated be