CN102215300A - Telecommunication service recommendation method and system - Google Patents
Telecommunication service recommendation method and system Download PDFInfo
- Publication number
- CN102215300A CN102215300A CN2011101350032A CN201110135003A CN102215300A CN 102215300 A CN102215300 A CN 102215300A CN 2011101350032 A CN2011101350032 A CN 2011101350032A CN 201110135003 A CN201110135003 A CN 201110135003A CN 102215300 A CN102215300 A CN 102215300A
- Authority
- CN
- China
- Prior art keywords
- telecommunication service
- interest
- user
- user interest
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a telecommunication service recommendation method and system, wherein the method comprises: acquiring telecommunication service information, identity information of users, order business information and net access journal information; acquiring subject indexing of webpage documents accessed by users according to the net access journal information; setting up a user interest model according to the subject indexing of webpage documents accessed by the users and the net access journal information; acquiring the incidence relation of the user interest and the telecommunication service according to the user interest model, the telecommunication service information and the order service information; and acquiring a recommendation service list and recommending the telecommunication service according to the incidence relation of the user interest and the telecommunication service and the user interest model. According to the invention, the precision marketing of the telecommunication service is realized, and simultaneously the user experience is improved.
Description
Technical field
The present invention relates to the communication technology, particularly a kind of telecommunication service recommend method and system.
Background technology
Present stage China's telecommunication service faces the market pressure of homogeneity competition, makes that the new user of development is more and more difficult; Telecom operators just progressively attract user's extensive style operation from competitive methods such as dependence price war in the past, change to Focus service, fine management, and the numerous and confused data digging system of building oneself is assisted and carried out precision marketing.
Generally be based at present the analysis and the excavation of the data such as basic document, geographical position, communication behavior of telecommunication user, therefrom find the service operation rule, and then carry out telecommunication service and recommend.The drawback of this method is, do not consider user's hobby, user's hobby can't be directly obtains from data such as user's basic document, geographical position, communication behaviors, the user may occur loses interest in to the telecommunication service of recommending, both made that user experience was relatively poor, reduced the success rate that telecommunication service is recommended again.
Summary of the invention
The purpose of this invention is to provide a kind of telecommunication service recommend method and system, recommend, realize the precision marketing of telecommunication service to carry out telecommunication service based on user interest.
The invention provides a kind of telecommunication service recommend method, comprising:
Obtain telecommunication service information, user's identity information, order business information and internet log information;
Obtain the subject indexing of user capture web document according to described internet log information; Subject indexing and internet log information according to described user capture web document are set up user interest model;
According to described user interest model, telecommunication service information and order business information, obtain the incidence relation of user interest and telecommunication service; And, obtain recommending service lists according to the incidence relation and the described user interest model of described user interest and telecommunication service, the user is carried out telecommunication service recommend.
The invention provides a kind of telecommunication service commending system, comprising: user data acquisition module, user interest study module and telecommunication service recommending module;
Described user data acquisition module is used to obtain telecommunication service information, user's identity information, order business information and internet log information;
Described user interest study module is used for obtaining according to described internet log information the subject indexing of user capture web document; Subject indexing and internet log information according to described user capture web document are set up user interest model;
Described telecommunication service recommending module is used for according to described user interest model, telecommunication service information and order business information, obtains the incidence relation of user interest and telecommunication service; And, obtain recommending service lists according to the incidence relation and the described user interest model of described user interest and telecommunication service, the user is carried out telecommunication service recommend.
Telecommunication service recommend method of the present invention and system, by collection and analysis to the internet behavior of telecommunication user under the full-service operation environment, fully digging user interest and and telecommunication service between incidence relation, carrying out telecommunication service based on user interest recommends, realize the precision marketing of telecommunication service, promote user experience simultaneously.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, to do one to the accompanying drawing of required use in embodiment or the description of the Prior Art below introduces simply, apparently, accompanying drawing in describing below is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the structural representation of telecommunication service commending system embodiment of the present invention;
Fig. 2 is the schematic flow sheet of telecommunication service recommend method embodiment of the present invention;
Fig. 3 is the schematic flow sheet of the generation text classifier among the telecommunication service recommend method embodiment of the present invention;
Fig. 4 is the schematic flow sheet of the acquisition user capture web document subject indexing among the telecommunication service recommend method embodiment of the present invention;
Fig. 5 is the acquisition user interest among the telecommunication service recommend method embodiment of the present invention and the schematic flow sheet of telecommunication service incidence relation;
The schematic flow sheet that Fig. 6 recommends for the telecommunication service among the telecommunication service recommend method embodiment of the present invention.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, the every other embodiment that those of ordinary skills are obtained under the prerequisite of not making creative work belongs to the scope of protection of the invention.
Embodiment one
Fig. 1 is the structural representation of telecommunication service commending system embodiment of the present invention, and as shown in Figure 1, this system can comprise user data acquisition module 11, user interest study module 12 and telecommunication service recommending module 13;
Wherein, described user data acquisition module 11 is used to obtain telecommunication service information, user's identity information, order business information and internet log information; This internet log information can be stored to user's internet log storehouse 14.
Described user interest study module 12 is used for obtaining user capture web document subject indexing according to described internet log information; Set up user interest model according to described user capture web document subject indexing and internet log information; This user interest model can be stored to user interest model storehouse 15;
Described telecommunication service recommending module 13 is used for according to described user interest model, telecommunication service information and order business information, obtains the incidence relation of user interest and telecommunication service; And, obtain recommending service lists according to the incidence relation and the described user interest model of described user interest and telecommunication service, the user is carried out telecommunication service recommend; The incidence relation of this user interest and telecommunication service can be stored to interest-business association storehouse 16.
For example, user interest study module 12 can comprise judging unit, first processing unit and second processing unit; Wherein, judging unit is used for obtaining the URL address that the user visits according to described internet log information, and according to described URL address lookup URL-theme mapping library, judges whether the user capture web document of this URL address correspondence has carried out subject indexing; First processing unit is used in the judged result of described judging unit directly obtaining described subject indexing when being; Second processing unit is used in the judged result of described judging unit for not the time, uses the webpage collector to obtain the user capture web document of described URL correspondence, and described user capture web document is carried out preliminary treatment, and text obtains standardizing; Described standardization text is carried out Chinese word segmentation and the identification of English phrase, remove the non-categorical information speech, obtain being with participle sign text; Described band participle sign text is carried out word frequency statistics and feature weight calculating, generate text vector; And described text vector carried out text classification, obtain described user capture web document subject indexing; Store described user capture web document subject indexing into described URL-theme mapping library.
For example, user interest study module 12 can also comprise the first interest unit and the second interest unit; Wherein, the first interest unit, be used for setting up user interest model according to described user capture web document subject indexing and internet log information, comprise a plurality of user interest items in the described user interest model, comprise category of interest, the interest-degree corresponding in the described user interest item with described category of interest; The quantity of described user interest equals the quantity of described user capture web document subject indexing, described interest-degree is directly proportional with the daily record quantity corresponding with described category of interest in the described internet log information, is inversely proportional to the nearest time of occurrence with the corresponding daily record quantity of described category of interest in the described internet log information; The second interest unit is used for described interest-degree is carried out normalization process, obtains regular interest-degree.
For example, described telecommunication service recommending module comprises: aggregation units, processing unit, associative cell, credible unit and recommendation unit;
Aggregation units is used for setting up two-dimentional cum rights set of records ends according to described user interest model, telecommunication service information and order business information;
Processing unit is used for calculating the support of all kinds of interest of described set; Calculate an interest and a professional two dimension support that collects in the described set;
Associative cell is used for obtaining the confidence level of the correlation rule of user interest and telecommunication service according to the support of described all kinds of interest and the support of a two dimension collection;
Credible unit is used for the confidence level according to the correlation rule of described user interest model and described user interest and telecommunication service, obtains the confidence level that telecommunication service is recommended;
Recommendation unit is used for the confidence level according to described telecommunication service recommendation, with institute's professional arrangement to be recommended, generates described recommendation service lists.
Further, also comprise: recommend evaluation module 17, be used for the effect that telecommunication service is recommended is assessed, obtain assessment result; Recommend optimal module 18, be used for, optimize described telecommunication service and recommend according to described assessment result.
The telecommunication service recommend method of present embodiment, set up user interest model by internet log information according to the user, and the incidence relation of user interest and telecommunication service etc., can generate the recommendation service lists in view of the above, the user is carried out telecommunication service recommend, solved the low problem of success rate that telecommunication service is recommended, realized that carrying out telecommunication service based on user interest recommends, and the precision marketing of telecommunication service, promote the user experience that telecommunication service is recommended.
Embodiment two
Fig. 2 is the schematic flow sheet of telecommunication service recommend method embodiment of the present invention, and the telecommunication service recommend method of present embodiment can be carried out by the telecommunication service commending system described in the embodiment one, and as shown in Figure 2, the method for present embodiment can may further comprise the steps:
For example, can be by information such as BSS/OSS system acquisition subscriber identity information, order business information, telecommunication service information, by BAS Broadband Access Server (Broadband Remote Access Server, be called for short: BRAS) with (the Remote Authentication Dial In User Service of remote customer dialing authentication system, be called for short: RADIUS) gather the raw information of user capture the Internet, obtain the internet log information of user capture URL; This internet behavior comprises fixed network broadband, mobile WAP/Web online etc.Described internet log information can store user's internet log storehouse into.
Wherein, user's identity information is used for the user identity that the user data acquisition module gathers from BRAS and RADIUS after the raw information of user's internet usage to be differentiated, and consumer taste (by the internet log reflection) and the excavation of user subscribes service information incidence relation; Can comprise order business quantity in the order business information, order telecommunication service title etc.; Can comprise telecommunication service sum, telecommunication service title etc. in the telecommunication service information; Internet log information can comprise user capture URL address information, certain class daily record quantity and visit time of such daily record etc.
For example, can be by the URL address that obtains user capture in the internet log information, obtain the URL address that the user visits according to described internet log information, and according to described URL address lookup URL-theme mapping library, whether the user capture web document theme of judging this URL address correspondence index.When being, directly obtain described subject indexing in the judged result of described judging unit.For not the time, use the webpage collector in the judged result of described judging unit, gather and obtain the pairing web document in described URL address, i.e. user capture web document; Described user capture web document is handled, obtained user capture web document subject indexing; And store described user capture web document subject indexing into described URL-theme mapping library.
Wherein, described user capture web document is handled, obtained user capture web document subject indexing, specifically can comprise two parts content; A part is to carry out the text classification training by the document to classification based training document library that subject categories mark is arranged, generates text classifier, this partial content specifically can referring among the embodiment three to the explanation of text classification training; Another part is to use the above-mentioned text classifier that obtains to carry out text classification in to the processing procedure of user capture web document, thereby obtain the subject indexing of user capture web document, this partial content specifically can be referring to the explanation that obtains user capture web document subject indexing among the embodiment four.
For example, can determine user's interest quantity, in this user interest model, can comprise a plurality of item of interest, wherein, can comprise factors such as category of interest title and interest-degree in the described item of interest according to user capture web document subject indexing.This user interest model specifically can referring among the embodiment five for the detailed description of user interest model.The user interest model that generates can be stored to the user interest model storehouse.
For example, can be according to the user interest model of being set up in the step 203, and telecommunication service information of being obtained in the step 201 and order business information etc., by calculating and handle the incidence relation that obtains between user interest and the telecommunication service.The generation of this incidence relation specifically can be referring to the explanation of embodiment six.The interest that generates-business association relation can be stored in interest-business association storehouse.
For example, in step 204, obtain after the incidence relation of user interest and telecommunication service, can obtain recommending service lists, the user is carried out telecommunication service recommend according to user interest model and described incidence relation.Specifically can be referring to the explanation that generates for the telecommunication service recommendation list among the embodiment seven.
The telecommunication service recommend method of present embodiment, set up user interest model by internet log information according to the user, and the incidence relation of user interest and telecommunication service etc., can generate the recommendation service lists in view of the above, the user is carried out telecommunication service recommend, solved the low problem of success rate that telecommunication service is recommended, realized that carrying out telecommunication service based on user interest recommends, and the precision marketing of telecommunication service, promote the user experience that telecommunication service is recommended.
Embodiment three
Fig. 3 is the schematic flow sheet of the generation text classifier among the telecommunication service recommend method embodiment of the present invention, and as shown in Figure 3, present embodiment can may further comprise the steps:
For example, the user interest study module carries out preliminary treatment to the document of classification based training document library that subject categories mark is arranged.Wherein, described classification based training document library can be set up voluntarily by the user of telecommunication service commending system, and form can be the document or the tables of data of big file and " the example document subject indexing table of comparisons " by name in " example document storehouse " by name.Be some example documents in the described example document storehouse, the described example document subject indexing table of comparisons illustrates the subject indexing of each example document, as " physical culture ", " music ", " finance and economics " or the like.According to the needs that telecommunication service is recommended, the refinement again of the granularity of document subject matter can be subdivided into " football ", " vollyball " or the like again as " physical culture ".The form of described example document is not limit, can be txt plain text, web text, word text, ppt text, pdf text or the like, also need to do document recognition work during document preliminary treatment beyond txt and the web type, so the suggesting system for wearing user preferably selects the example document of txt and web type when setting up document library voluntarily.The language of described example document is not limit, and can be Chinese text, English text, Chinese and English mixing text.
When preliminary treatment, can remove the noise in the described sample text, as advertisement bar, navigation bar, bookmark etc.; And use morphological rule that English text is carried out morphological analysis, and the speech after the distortion is recovered prototype, comprise the tense conversion, the conversion of the verb third person, stem extraction of plural number removal, the verb of noun etc., obtain normalized text.
For example, the user interest study module can be according to dictionary for word segmentation, the standardization text that obtains in the step 301 is carried out Chinese word segmentation and the identification of English phrase, and according to the stop words dictionary, remove the non-categorical information speech in this standardization text, the speech that does not promptly contain classified information, for example the function words such as adverbial word, article, conjunction, pronoun, modal verb or tone auxiliary word of preposition, band subordinate clause obtain being with participle sign text.
Wherein, participle just is to use the division symbol, and carrying out with speech or phrase to text is the division of unit.Divide symbol and can be the identifier of shape as " w ".For example, " cloud computing (Cloud Computing) is the development of distributed treatment (Distributed Computing), parallel processing (Parallel Computing) and grid computing (Grid Computing), or perhaps the commerce of these computer science notions realizes." employing " w " symbol participle and remove the non-categorical information speech after can obtain: " cloud computing wCloud Computing the w distributed treatment wDistributed Computing the w parallel processing w Parallel Computing the w grid computing w Grid Computing the w development the w computer the w science the w notion w commercial w realize w ".
Step 303, user interest study module carry out word frequency statistics and feature extraction to band participle sign text, generate text vector;
For example, the user interest study module carries out word frequency statistics and feature extraction to the text of the band participle sign that step 302 obtains, and obtains characteristic vector space, generates the vector space model of text thus, promptly generates text vector.
The telecommunication service recommend method of present embodiment, set up user interest model by internet log information according to the user, and the incidence relation of user interest and telecommunication service etc., can generate the recommendation service lists in view of the above, the user is carried out telecommunication service recommend, solved the low problem of success rate that telecommunication service is recommended, realized that carrying out telecommunication service based on user interest recommends, and the precision marketing of telecommunication service, promote the user experience that telecommunication service is recommended.
Embodiment four
Fig. 4 is the schematic flow sheet of the acquisition user capture web document subject indexing among the telecommunication service recommend method embodiment of the present invention, and as shown in Figure 4, present embodiment can may further comprise the steps:
For example, the user interest study module can obtain user access logs by user's internet log storehouse, comprising the URL address information.
Whether step 402, user interest study module judge the index of the pairing web document theme in this URL address;
Whether for example, the user interest study module can be inquired about URL-theme mapping library, judge the index of the pairing web document theme in this URL address; If the index of user accessing web page document subject matter, then execution in step 403; Otherwise if the not index of user accessing web page document subject matter, then execution in step 404;
For example, the user interest study module carries out preliminary treatment to the user capture web document that obtains in the step 404, and the document can be the web text, can remove the noise in the web text when preliminary treatment, as advertisement bar, navigation bar, bookmark etc.; And use morphological rule that English text is carried out morphological analysis, and the speech after the distortion is recovered prototype, comprise the tense conversion, the conversion of the verb third person, stem extraction of plural number removal, the verb of noun etc., obtain normalized text.
For example, the user interest study module can be according to dictionary for word segmentation, the standardization text that obtains in the step 405 is carried out Chinese word segmentation and the identification of English phrase, and according to the stop words dictionary, remove the non-categorical information speech in this standardization text, the speech that does not promptly contain classified information, for example the function words such as adverbial word, article, conjunction, pronoun, modal verb or tone auxiliary word of preposition, band subordinate clause obtain being with participle sign text.
Step 407, user interest study module carry out word frequency statistics and feature extraction to band participle sign text, generate text vector;
For example, the user interest study module is according to the characteristic vector space that obtains among the embodiment three, and the text that the band participle that step 406 is obtained identifies carries out word frequency statistics and feature weight calculates, and generates the vector space model of text, promptly generates text vector.
Wherein, described subject indexing can be used for generating user interest model.The effect of described URL-theme mapping library is the efficient that improves the telecommunication service commending system, for example, a plurality of users have browsed same webpage (the URL address is identical), the web document only need be when the user visits first this URL address pointed to of telecommunication service commending system is handled once so, just can be directly when follow-up other users visit once more obtains the subject indexing of web document correspondence by inquiring about this mapping library.
The telecommunication service recommend method of present embodiment, set up user interest model by internet log information according to the user, and the incidence relation of user interest and telecommunication service etc., can generate the recommendation service lists in view of the above, the user is carried out telecommunication service recommend, solved the low problem of success rate that telecommunication service is recommended, realized that carrying out telecommunication service based on user interest recommends, and the precision marketing of telecommunication service, promote the user experience that telecommunication service is recommended.
Embodiment five
Present embodiment is elaborated to the user interest model described in the embodiment two: user interest model
Be defined as follows shown in the formula (1):
Wherein, m (0<m≤| C|) be this user's interest quantity (being the quantity of user capture web document subject indexing), | C| is a subject indexing classification sum, (c
i, w
i, n
i, t
i) be this user's i+1 (the class item of interest of 0≤i<m), c
iBe category of interest title (being subject indexing), w
iBe c
iThe weight of class interest (interest-degree), n
iBe this user c in the access log that surfs the Net
iThe quantity of class daily record, t
iBe this user c in the access log that surfs the Net
iThe nearest time of occurrence of class daily record.
This user's the i+1 (weight of class interest (interest-degree) w of 0≤i<m)
iDefine as the formula (2):
Wherein, n
iBe this user c in the access log that surfs the Net
iThe quantity of class daily record, t
iBe this user c in the access log that surfs the Net
iThe nearest time of occurrence of class daily record, T are current system times, and α>0 is one and adjusts coefficient.The meaning of formula (2) is, since user's hobby can be in time passing and dynamic change, some users passing that interested content can be in time originally and forgeing gradually, new interest can produce gradually, so user's the i+1 (weight of class interest (interest-degree) w of 0≤i<m)
iWith user's interest c
iClass web document number is directly proportional, with nearest reading c
iThe time difference of class web document is inversely proportional to.This interest-degree is equivalent to introduce the user interest Dynamic Updating Mechanism, has realized the stable of user interest and accurately renewal, makes the user interest hobby information that obtains more accurately with in time, further promotes user experience, has solved the user interest drift problem.
Wherein, Adjustment System α value is used to prevent that the denominator of f () function from being 0, can also adjust interest-degree w simultaneously
iThe rate of decay, the α value is more little, interest-degree w
iThe rate of decay fast more, therefore can determine the value of α according to real needs.
For preventing the interest-degree data active user (being that daily record quantity is than the large user) of excessively being partial to surf the Net, therefore need regular interest-degree data.(the weight of class interest (interest-degree) of 0≤i<m) of this user's i+1 after the normalization
Define as the formula (3):
Wherein, w
iCalculate by formula (2).
The user interest study module can regularly upgrade user interest model, and the mode of renewal is according to above-mentioned internet log information, as theme, quantity and the time etc. of daily record, interest-degree is upgraded.
The telecommunication service recommend method of present embodiment, set up user interest model by internet log information according to the user, and the incidence relation of user interest and telecommunication service etc., can generate the recommendation service lists in view of the above, the user is carried out telecommunication service recommend, solved the low problem of success rate that telecommunication service is recommended, realized that carrying out telecommunication service based on user interest recommends, and the precision marketing of telecommunication service, promote the user experience that telecommunication service is recommended.
Embodiment six
Fig. 5 is the acquisition user interest among the telecommunication service recommend method embodiment of the present invention and the schematic flow sheet of telecommunication service incidence relation, and as shown in Figure 5, present embodiment can may further comprise the steps:
For example, the telecommunication service commending system is set up two-dimentional cum rights set of records ends T according to user's order business information, telecommunication service information and user interest model storehouse, wherein, and T={t
1, t
2..., t
n, wherein n is active user's number in the system; Each record t among the T
uThe two-dimentional cum rights item set of a corresponding user u
Wherein, m
u(0<m
u≤ | C|) be the interest quantity of user u, | C| is system's subject indexing classification sum, c
UiBe i+1 (0≤i<m of user u
u) class interest title, n
u(0<n
u≤ | S|) be this user subscribes service quantity, | S| is the telecommunication service sum, s
UjBe j+1 (0≤j<n of user u
u) the type telecommunications Business Name, record t
uCorresponding weight vectors
Wherein, w
UiBe c after the user u normalization
UiThe weight of class interest (0≤i<m
u), p
UjBe user u order business s
UjWeight (0≤j<n
u), according to system requirements, make p here
Uj=1.
For example, the telecommunication service commending system calculates all kinds of interest C among the two-dimentional cum rights set of records ends T according to formula (4) and formula (5)
k(0≤k<| support Support (C C|)
k);
For example, the telecommunication service recommending module is calculated { interest, business } two dimension collection { C among the two-dimentional cum rights set of records ends T according to formula (6) and formula (7)
k, S
l(0≤k<| C|, 0≤l<| support Support (C S|)
k, S
l):
For example, the telecommunication service commending system calculates interest-business association rule among the two-dimentional cum rights set of records ends T according to formula (8)
Confidence level
And with itself and rule
Store interest-business association storehouse together into;
The telecommunication service recommend method of present embodiment, set up user interest model by internet log information according to the user, and the incidence relation of user interest and telecommunication service etc., can generate the recommendation service lists in view of the above, the user is carried out telecommunication service recommend, solved the low problem of success rate that telecommunication service is recommended, realized that carrying out telecommunication service based on user interest recommends, and the precision marketing of telecommunication service, promote the user experience that telecommunication service is recommended.
Embodiment seven
The schematic flow sheet that Fig. 6 recommends for the telecommunication service among the telecommunication service recommend method embodiment of the present invention, as shown in Figure 6, present embodiment can may further comprise the steps:
The telecommunication service recommend method of present embodiment, set up user interest model by internet log information according to the user, and the incidence relation of user interest and telecommunication service etc., can generate the recommendation service lists in view of the above, the user is carried out telecommunication service recommend, solved the low problem of success rate that telecommunication service is recommended, realized that carrying out telecommunication service based on user interest recommends, and the precision marketing of telecommunication service, promote the user experience that telecommunication service is recommended.
Embodiment eight
On the basis of the foregoing description, further, the effect that telecommunication service is recommended is assessed, and, optimized described telecommunication service and recommend according to described assessment result.
By taking recommendation effect assessment feedback and update mechanism, the closed loop work of realization flow has improved the adaptive ability of system.
For example, this assessment feedback can be with a period of time (week, month or season etc.) be the cycle, observation is recommended its not order business S to the user
1After, whether the user has ordered should business, the interval of business recommended time and order business time started or the like, thereby estimates the validity of these recommendations and ageing, and can be in conjunction with the marketing strategy of telecommunication service department, corresponding adjustment
For example, recommend evaluation module to calculate interest-business association rule according to formula (10) and formula (11)
Fitness
Wherein, N
uBe all recommended professional S
1And has interest C
kTotal number of users.TO
iThe professional S that has been recommended
1And has interest C
kUser i begin order business S
1Time, TR
iBe to recommend professional S to user i
1Time.Obviously have
Recommend optimal module to adjust interest-business association rule according to formula (12)
Confidence level
One of ordinary skill in the art will appreciate that: all or part of step that realizes said method embodiment can be finished by the relevant hardware of program command, aforesaid program can be stored in the computer read/write memory medium, this program is carried out the step that comprises said method embodiment when carrying out; And aforesaid storage medium comprises: various media that can be program code stored such as ROM, RAM, magnetic disc or CD.
It should be noted that at last: above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment the present invention is had been described in detail, those of ordinary skill in the art is to be understood that: it still can be made amendment to the technical scheme that aforementioned each embodiment put down in writing, and perhaps part technical characterictic wherein is equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution break away from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (12)
1. a telecommunication service recommend method is characterized in that, comprising:
Obtain telecommunication service information, user's identity information, order business information and internet log information;
Obtain the subject indexing of user capture web document according to described internet log information; Subject indexing and internet log information according to described user capture web document are set up user interest model;
According to described user interest model, telecommunication service information and order business information, obtain the incidence relation of user interest and telecommunication service; And, obtain recommending service lists according to the incidence relation and the described user interest model of described user interest and telecommunication service, the user is carried out telecommunication service recommend.
2. telecommunication service recommend method according to claim 1 is characterized in that, obtains user capture web document subject indexing according to described internet log information, comprising:
Obtain the URL address that the user visits according to described internet log information, and, judge whether the user capture web document of this URL address correspondence has carried out subject indexing according to described URL address lookup URL-theme mapping library; If then directly obtain the subject indexing of described user capture web document;
Otherwise use webpage collector obtains the user capture web document of described URL correspondence, and described user capture web document is carried out preliminary treatment, obtains the text that standardizes; Described standardization text is carried out Chinese word segmentation and the identification of English phrase, remove the non-categorical information speech, obtain being with participle sign text; Described band participle sign text is carried out word frequency statistics and feature weight calculating, generate text vector; And described text vector carried out text classification, obtain described user capture web document subject indexing; Store described user capture web document subject indexing into described URL-theme mapping library.
3. telecommunication service recommend method according to claim 1 is characterized in that, sets up user interest model according to described user capture web document subject indexing and internet log information, comprising:
Comprise a plurality of user interest items in the described user interest model, comprise category of interest, the interest-degree corresponding in the described user interest item with described category of interest; The quantity of described user interest equals the quantity of described user capture web document subject indexing;
Described interest-degree is directly proportional with the daily record quantity corresponding with described category of interest in the described internet log information, is inversely proportional to the nearest time of occurrence with the corresponding daily record quantity of described category of interest in the described internet log information.
4. telecommunication service recommend method according to claim 3 is characterized in that, also comprises:
Described interest-degree is carried out normalization process, obtain regular interest-degree.
5. telecommunication service recommend method according to claim 1 is characterized in that, according to described user interest model, telecommunication service information and order business information, obtains the incidence relation of user interest and telecommunication service, comprising:
According to described user interest model, telecommunication service information and order business information, set up two-dimentional cum rights set of records ends;
Calculate the support of all kinds of interest in the described set; Calculate an interest and a professional two dimension support that collects in the described set;
According to the support of described all kinds of interest and the support of a two dimension collection, obtain the confidence level of the correlation rule of user interest and telecommunication service.
6. telecommunication service recommend method according to claim 5 is characterized in that, incidence relation and described user interest model according to described user interest and telecommunication service obtain recommending service lists, comprising:
According to the confidence level of the correlation rule of described user interest model and described user interest and telecommunication service, obtain the confidence level that telecommunication service is recommended;
Confidence level according to described telecommunication service is recommended with institute's professional arrangement to be recommended, generates described recommendation service lists.
7. according to the arbitrary described telecommunication service recommend method of claim 1-6, it is characterized in that, also comprise:
The effect that telecommunication service is recommended is assessed, and, optimized described telecommunication service and recommend according to described assessment result.
8. a telecommunication service commending system is characterized in that, comprising: user data acquisition module, user interest study module and telecommunication service recommending module;
Described user data acquisition module is used to obtain telecommunication service information, user's identity information, order business information and internet log information;
Described user interest study module is used for obtaining according to described internet log information the subject indexing of user capture web document; Subject indexing and internet log information according to described user capture web document are set up user interest model;
Described telecommunication service recommending module is used for according to described user interest model, telecommunication service information and order business information, obtains the incidence relation of user interest and telecommunication service; And, obtain recommending service lists according to the incidence relation and the described user interest model of described user interest and telecommunication service, the user is carried out telecommunication service recommend.
9. telecommunication service commending system according to claim 8 is characterized in that, described user interest study module comprises:
Judging unit is used for obtaining the URL address that the user visits according to described internet log information, and according to described URL address lookup URL-theme mapping library, judges whether the user capture web document of this URL address correspondence has carried out subject indexing;
First processing unit is used in the judged result of described judging unit directly obtaining described subject indexing when being;
Second processing unit is used in the judged result of described judging unit for not the time, uses the webpage collector to obtain the user capture web document of described URL correspondence, and described user capture web document is carried out preliminary treatment, and text obtains standardizing; Described standardization text is carried out Chinese word segmentation and the identification of English phrase, remove the non-categorical information speech, obtain being with participle sign text; Described band participle sign text is carried out word frequency statistics and feature weight calculating, generate text vector; And described text vector carried out text classification, obtain described user capture web document subject indexing; Store described user capture web document subject indexing into described URL-theme mapping library.
10. telecommunication service commending system according to claim 8 is characterized in that, described user interest study module also comprises:
The first interest unit, be used for setting up user interest model according to described user capture web document subject indexing and internet log information, comprise a plurality of user interest items in the described user interest model, comprise category of interest, the interest-degree corresponding in the described user interest item with described category of interest; The quantity of described user interest equals the quantity of described user capture web document subject indexing; Described interest-degree is directly proportional with the daily record quantity corresponding with described category of interest in the described internet log information, is inversely proportional to the nearest time of occurrence with the corresponding daily record quantity of described category of interest in the described internet log information;
The second interest unit is used for described interest-degree is carried out normalization process, obtains regular interest-degree.
11. telecommunication service commending system according to claim 8 is characterized in that, described telecommunication service recommending module comprises:
Aggregation units is used for setting up two-dimentional cum rights set of records ends according to described user interest model, telecommunication service information and order business information;
Processing unit is used for calculating the support of all kinds of interest of described set; Calculate an interest and a professional two dimension support that collects in the described set;
Associative cell is used for obtaining the confidence level of the correlation rule of user interest and telecommunication service according to the support of described all kinds of interest and the support of a two dimension collection;
Credible unit is used for the confidence level according to the correlation rule of described user interest model and described user interest and telecommunication service, obtains the confidence level that telecommunication service is recommended;
Recommendation unit is used for the confidence level according to described telecommunication service recommendation, with institute's professional arrangement to be recommended, generates described recommendation service lists.
12. arbitrary according to Claim 8-11 described telecommunication service commending system is characterized in that, also comprises:
Recommend evaluation module, be used for that the user is carried out the effect that telecommunication service recommends and assess, obtain assessment result;
Recommend optimal module, be used for, optimize described telecommunication service and recommend according to described assessment result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110135003 CN102215300B (en) | 2011-05-24 | 2011-05-24 | Telecommunication service recommendation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110135003 CN102215300B (en) | 2011-05-24 | 2011-05-24 | Telecommunication service recommendation method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102215300A true CN102215300A (en) | 2011-10-12 |
CN102215300B CN102215300B (en) | 2013-11-06 |
Family
ID=44746421
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110135003 Active CN102215300B (en) | 2011-05-24 | 2011-05-24 | Telecommunication service recommendation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102215300B (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102402766A (en) * | 2011-12-27 | 2012-04-04 | 纽海信息技术(上海)有限公司 | User interest modeling method based on web page browsing |
CN102547554A (en) * | 2011-12-28 | 2012-07-04 | 华中科技大学 | Mobile service recommendation method based on mobile user behavior |
CN103179152A (en) * | 2011-12-22 | 2013-06-26 | 中国电信股份有限公司 | Business information issue method, system and business platform |
CN103488788A (en) * | 2011-12-27 | 2014-01-01 | 奇智软件(北京)有限公司 | Method and device for recommending applications automatically |
CN103514266A (en) * | 2013-09-04 | 2014-01-15 | 快传(上海)广告有限公司 | Method and system for issuing network information to mobile terminal |
CN103617547A (en) * | 2013-12-04 | 2014-03-05 | 中国联合网络通信集团有限公司 | Service recommendation method and system |
CN103905507A (en) * | 2012-12-28 | 2014-07-02 | ***通信集团公司 | Service information recommendation system and service information recommendation method |
CN105447159A (en) * | 2015-12-02 | 2016-03-30 | 北京信息科技大学 | Query expansion method based on user query association degree |
CN105975479A (en) * | 2016-04-20 | 2016-09-28 | 重庆重邮汇测通信技术有限公司 | Tag library-based telecom user interest degree analysis method and system |
CN105989040A (en) * | 2015-02-03 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Intelligent question-answer method, device and system |
CN106294755A (en) * | 2016-08-11 | 2017-01-04 | 上海携程商务有限公司 | Web Page Recommender System and webpage recommending method for URL classification |
CN106375369A (en) * | 2016-08-18 | 2017-02-01 | 南京邮电大学 | Mobile Web service recommendation method and collaborative recommendation system based on user behavior analysis |
CN106997397A (en) * | 2017-04-17 | 2017-08-01 | 山东辰华科技信息有限公司 | Scientific and technological information personalized customization supplying system based on big data |
CN107391692A (en) * | 2017-07-26 | 2017-11-24 | 腾讯科技(北京)有限公司 | The appraisal procedure and device of a kind of recommendation effect |
CN108764988A (en) * | 2018-05-21 | 2018-11-06 | 中国联合网络通信有限公司重庆市分公司 | A kind of marketing strategy put-on method and system |
CN109829108A (en) * | 2019-01-28 | 2019-05-31 | 北京三快在线科技有限公司 | Information recommendation method, device, electronic equipment and readable storage medium storing program for executing |
CN111309588A (en) * | 2019-11-19 | 2020-06-19 | 广州市科传计算机科技股份有限公司 | Marketing strategy evaluation method based on customer behavior drive |
CN111861513A (en) * | 2020-07-29 | 2020-10-30 | 浪潮天元通信信息***有限公司 | Simplified management method and model based on communication operator CRM system |
TWI726398B (en) * | 2019-08-27 | 2021-05-01 | 中華電信股份有限公司 | Self-adapted telecommunication service recommend system and method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20080087467A (en) * | 2007-03-27 | 2008-10-01 | 주식회사 하이닉스반도체 | Method for manufacturing of semiconductor device |
CN101923545A (en) * | 2009-06-15 | 2010-12-22 | 北京百分通联传媒技术有限公司 | Method for recommending personalized information |
-
2011
- 2011-05-24 CN CN 201110135003 patent/CN102215300B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20080087467A (en) * | 2007-03-27 | 2008-10-01 | 주식회사 하이닉스반도체 | Method for manufacturing of semiconductor device |
CN101923545A (en) * | 2009-06-15 | 2010-12-22 | 北京百分通联传媒技术有限公司 | Method for recommending personalized information |
Non-Patent Citations (1)
Title |
---|
马春山: "移动增值业务的个性化推荐研究", 《北京邮电大学博士研究生学位论文》, 13 January 2009 (2009-01-13), pages 58 - 67 * |
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103179152A (en) * | 2011-12-22 | 2013-06-26 | 中国电信股份有限公司 | Business information issue method, system and business platform |
CN103179152B (en) * | 2011-12-22 | 2016-04-20 | 中国电信股份有限公司 | Business information delivery method, system and business platform |
CN102402766A (en) * | 2011-12-27 | 2012-04-04 | 纽海信息技术(上海)有限公司 | User interest modeling method based on web page browsing |
CN103488788A (en) * | 2011-12-27 | 2014-01-01 | 奇智软件(北京)有限公司 | Method and device for recommending applications automatically |
CN103488788B (en) * | 2011-12-27 | 2019-03-08 | 北京奇虎科技有限公司 | It is a kind of to apply the method and device recommended automatically |
CN102402766B (en) * | 2011-12-27 | 2017-07-28 | 北京京东尚科信息技术有限公司 | A kind of user interest modeling method based on web page browsing |
CN102547554A (en) * | 2011-12-28 | 2012-07-04 | 华中科技大学 | Mobile service recommendation method based on mobile user behavior |
CN102547554B (en) * | 2011-12-28 | 2015-03-04 | 华中科技大学 | Mobile service recommendation method based on mobile user behavior |
CN103905507A (en) * | 2012-12-28 | 2014-07-02 | ***通信集团公司 | Service information recommendation system and service information recommendation method |
CN103514266A (en) * | 2013-09-04 | 2014-01-15 | 快传(上海)广告有限公司 | Method and system for issuing network information to mobile terminal |
CN103617547B (en) * | 2013-12-04 | 2017-07-07 | 中国联合网络通信集团有限公司 | A kind of business recommended method and system |
CN103617547A (en) * | 2013-12-04 | 2014-03-05 | 中国联合网络通信集团有限公司 | Service recommendation method and system |
CN105989040A (en) * | 2015-02-03 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Intelligent question-answer method, device and system |
CN105989040B (en) * | 2015-02-03 | 2021-02-09 | 创新先进技术有限公司 | Intelligent question and answer method, device and system |
CN105447159A (en) * | 2015-12-02 | 2016-03-30 | 北京信息科技大学 | Query expansion method based on user query association degree |
CN105975479A (en) * | 2016-04-20 | 2016-09-28 | 重庆重邮汇测通信技术有限公司 | Tag library-based telecom user interest degree analysis method and system |
CN105975479B (en) * | 2016-04-20 | 2019-08-27 | 重庆重邮汇测通信技术有限公司 | A kind of telecommunication user interest-degree analysis method and system based on tag library |
CN106294755A (en) * | 2016-08-11 | 2017-01-04 | 上海携程商务有限公司 | Web Page Recommender System and webpage recommending method for URL classification |
CN106294755B (en) * | 2016-08-11 | 2019-09-24 | 上海携程商务有限公司 | Web Page Recommender System and webpage recommending method for URL classification |
CN106375369A (en) * | 2016-08-18 | 2017-02-01 | 南京邮电大学 | Mobile Web service recommendation method and collaborative recommendation system based on user behavior analysis |
CN106375369B (en) * | 2016-08-18 | 2019-05-28 | 南京邮电大学 | The business recommended method of mobile Web and Collaborative Recommendation system based on user behavior analysis |
CN106997397A (en) * | 2017-04-17 | 2017-08-01 | 山东辰华科技信息有限公司 | Scientific and technological information personalized customization supplying system based on big data |
CN107391692A (en) * | 2017-07-26 | 2017-11-24 | 腾讯科技(北京)有限公司 | The appraisal procedure and device of a kind of recommendation effect |
CN107391692B (en) * | 2017-07-26 | 2023-04-07 | 腾讯科技(北京)有限公司 | Recommendation effect evaluation method and device |
CN108764988A (en) * | 2018-05-21 | 2018-11-06 | 中国联合网络通信有限公司重庆市分公司 | A kind of marketing strategy put-on method and system |
CN109829108A (en) * | 2019-01-28 | 2019-05-31 | 北京三快在线科技有限公司 | Information recommendation method, device, electronic equipment and readable storage medium storing program for executing |
TWI726398B (en) * | 2019-08-27 | 2021-05-01 | 中華電信股份有限公司 | Self-adapted telecommunication service recommend system and method |
CN111309588A (en) * | 2019-11-19 | 2020-06-19 | 广州市科传计算机科技股份有限公司 | Marketing strategy evaluation method based on customer behavior drive |
CN111309588B (en) * | 2019-11-19 | 2023-11-17 | 广州市科传计算机科技股份有限公司 | Marketing strategy evaluation method based on customer behavior driving |
CN111861513A (en) * | 2020-07-29 | 2020-10-30 | 浪潮天元通信信息***有限公司 | Simplified management method and model based on communication operator CRM system |
Also Published As
Publication number | Publication date |
---|---|
CN102215300B (en) | 2013-11-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102215300B (en) | Telecommunication service recommendation method and system | |
CN108536852B (en) | Question-answer interaction method and device, computer equipment and computer readable storage medium | |
CN107807987B (en) | Character string classification method and system and character string classification equipment | |
CN106940705A (en) | A kind of method and apparatus for being used to build user's portrait | |
CN104239373B (en) | Add tagged method and device for document | |
CN106022800A (en) | User feature data processing method and device | |
CN103324666A (en) | Topic tracing method and device based on micro-blog data | |
US9015158B2 (en) | Contents creating device and contents creating method | |
CN103440242A (en) | User search behavior-based personalized recommendation method and system | |
CN105809464A (en) | Method and device for information delivery | |
CN103235824A (en) | Method and system for determining web page texts users interested in according to browsed web pages | |
CN102982042A (en) | Personalization content recommendation method and platform and system | |
Vakulenko et al. | Enriching iTunes App Store Categories via Topic Modeling. | |
CN106776860A (en) | One kind search abstraction generating method and device | |
CN102646132B (en) | Method and device for recognizing attributes of broadband users | |
CN112528007B (en) | Confirmation method and confirmation device for target enterprise of business inviting project | |
CN102890698A (en) | Method for automatically describing microblogging topic tag | |
CN103810162A (en) | Method and system for recommending network information | |
CN102609424B (en) | Method and equipment for extracting assessment information | |
US20170228378A1 (en) | Extracting topics from customer review search queries | |
CN106980667B (en) | A kind of method and apparatus to article mark label | |
CN105930507A (en) | Method and apparatus for obtaining Web browsing interest of user | |
CN111447575A (en) | Short message pushing method, device, equipment and storage medium | |
Ye et al. | Mining sentiment tendencies and summaries from consumer reviews | |
Park et al. | Phrase embedding and clustering for sub-feature extraction from online data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |