CN105022729A - User preference determination method and device - Google Patents
User preference determination method and device Download PDFInfo
- Publication number
- CN105022729A CN105022729A CN201410150723.XA CN201410150723A CN105022729A CN 105022729 A CN105022729 A CN 105022729A CN 201410150723 A CN201410150723 A CN 201410150723A CN 105022729 A CN105022729 A CN 105022729A
- Authority
- CN
- China
- Prior art keywords
- preference
- user
- service
- type
- flow
- 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
Abstract
The invention discloses a user preference determination method comprising the following steps: determining frequency of each business type in a user visit classification system in a preset time period, using a H index algorithm to determine a frequency preference degree of each business in the user visit classification system; or, determining visit flow of each business in the user visit classification system in the preset time period, and using the H index algorithm to determine the flow preference degree of each business in the user visit classification system; determining a business type firstly visited by the user in each day in the classification system, calculating a first total day number of business type firstly visited by the user in each day in the preset time period, and using the H index algorithm to determine a browse preference degree of each business in the user visit classification system; determining a second total day number of all business types contentiously visited by the user in the classification system in the preset time period, and using the H index algorithm to determine business types preference degree of all businesses in the user visit classification system. The invention also discloses a user preference determination device.
Description
Technical field
The present invention relates to business support technology, particularly relate to a kind of user preference defining method and device.
Background technology
Along with developing rapidly of mobile Internet, and smart mobile phone is universal rapidly, the main body of existing customer just changes from communication clients to Internet subscribers, customer demand has changed personalized internet demand into by single communication requirement, is the change of the change and customer demand of complying with market, needs in tradition on divided data basis, depth analysis is carried out to type of service and flow etc., deeply see clearly user's request, the final construction effectively promoting intelligent pipeline, promotes flow scale and income.
Summary of the invention
For solving the technical matters of existing existence, embodiments provide a kind of user preference defining method and device, Neng Shi operator recommends the business of user preference more accurately to user.
The technical scheme of the embodiment of the present invention is achieved in that the embodiment of the present invention provides a kind of user preference defining method, and described method comprises:
Determine that user accesses the number of times of each type of service in preset time period in taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by described number of times, determine that user accesses the number of times preference of each business in taxonomic hierarchies; Or, determine that user accesses the flowing of access of each business in described preset time period in taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by flowing of access, determine that user accesses the flow preference of each business in taxonomic hierarchies;
Determine the type of service in the taxonomic hierarchies of user's first time every day access, and in described preset time period, add up first total number of days that described user accesses described type of service first time every day, adopt H exponentiation algorithm to be sorted by first total number of days, that determines that user accesses each business in taxonomic hierarchies browses preference;
Determine second of each type of service in described Preset Time in user's connected reference taxonomic hierarchies total number of days, adopt H exponentiation algorithm to be sorted by second total number of days, determine that user accesses the type of service preference of each business in taxonomic hierarchies.
Further, described method also comprises:
Be respectively described number of times preference, browse preference and type of service preference arranges weight, determine described number of times preference, browse the weighted mean value of preference and type of service preference according to weight, using determined weighted mean value as number of times preference coefficient.
Further, described method also comprises:
Be respectively described flow preference, browse preference and type of service preference arranges weight, determine described flow preference, browse the weighted mean value of preference and type of service preference according to weight, using determined weighted mean value as flow preference coefficient.
Further, described method also comprises:
Determine the flow used in each preset time period during described user is in preset time period described in N number of continuous print respectively;
Determine that flow stepping identifies, and determine the flow stepping mark residing for the flow that described user uses in each preset time period respectively;
Flow stepping mark residing for the flow that described user uses in each preset time period determines the class letter of described user.
Further, described method also comprises:
According to described number of times preference, flow preference, browse preference, the class letter of type of service preference and user is the business that described user recommends described user preference.
The embodiment of the present invention also provides a kind of user preference determining device, comprising:
First determining unit, for determining that user accesses the number of times of each type of service in preset time period in taxonomic hierarchies, adopting H exponentiation algorithm to be sorted by described number of times, determining that user accesses the number of times preference of each business in taxonomic hierarchies; Or, determine that user accesses the flowing of access of each business in described preset time period in taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by flowing of access, determine that user accesses the flow preference of each business in taxonomic hierarchies;
Second determining unit, for determining the type of service in the taxonomic hierarchies of user's first time every day access, and in described preset time period, add up first total number of days that described user accesses described type of service first time every day, adopt H exponentiation algorithm to be sorted by first total number of days, that determines that user accesses each business in taxonomic hierarchies browses preference;
3rd determining unit, for determining second total number of days of each type of service in described Preset Time in user's connected reference taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by second total number of days, determine that user accesses the type of service preference of each business in taxonomic hierarchies.
Further, described device also comprises:
Setting unit, for being respectively described number of times preference, browses preference and type of service preference arranges weight;
Computing unit, for determining described number of times preference, browsing the weighted mean value of preference and type of service preference according to the described number of times preference arranged, the weight of browsing preference and type of service preference, using determined weighted mean value as number of times preference coefficient.
Further, described setting unit, also for arranging weight for described flow preference, and again for described in browse preference and type of service preference arranges weight; Accordingly,
Described computing unit, also for determining described flow preference according to the described flow preference arranged, the weight of browsing preference and type of service preference, browse the weighted mean value of preference and type of service preference, using the weighted mean value determined as flow preference coefficient.
Further, described device also comprises:
4th determining unit, for determining the flow used in each preset time period during described user is in preset time period described in N number of continuous print respectively;
5th determining unit, for determining that flow stepping identifies, and determines the flow stepping mark residing for the flow that described user uses in each preset time period respectively;
6th determining unit, determines the class letter of described user for the flow stepping mark residing for the flow that uses in each preset time period according to described user.
Further, described device also comprises: recommendation unit, for according to described number of times preference, flow preference, browse preference, the class letter of type of service preference and user is the business that described user recommends described user preference.
The user preference defining method that the embodiment of the present invention provides and device, by taxonomic hierarchies and the H exponentiation algorithm of refinement, determine the type of service of user preference, for laying a good foundation to user's business of recommending accurately, improves the accuracy of promotion;
In addition, embodiment of the present invention method can in conjunction with user tag storehouse, the timely type of service identifying user and the described user use using competing product, and the marketing activity etc. of the type of service used according to described user and described user and operator, trigger user preference is recommended by business from operator to described user.
Accompanying drawing explanation
Fig. 1 is the realization flow schematic diagram of embodiment of the present invention user preference defining method;
Fig. 2 is the structural representation one of embodiment of the present invention user preference determining device;
Fig. 3 is the structural representation two of embodiment of the present invention user preference determining device;
Fig. 4 is the structural representation three of embodiment of the present invention user preference determining device.
Embodiment
In order to more at large understand feature of the present invention and technology contents, below in conjunction with accompanying drawing, realization of the present invention is described in detail, the use of appended accompanying drawing explanation only for reference, is not used for limiting the present invention.
Fig. 1 is the realization flow schematic diagram of embodiment of the present invention user preference defining method, and as shown in Figure 1, described method comprises:
Step 101: determine that user accesses the number of times of each type of service in preset time period in taxonomic hierarchies, adopts H exponentiation algorithm to be sorted by described number of times, determines that user accesses the number of times preference of each business in taxonomic hierarchies; Or, determine that user accesses the flowing of access of each business in described preset time period in taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by flowing of access, determine that user accesses the flow preference of each business in taxonomic hierarchies;
Here, described H exponentiation algorithm is that the user that determines according to the height of the access times of type of service is to the method for the preference of described type of service; Accordingly, described number of times sorts by described employing H exponentiation algorithm, determines that user accesses the number of times preference of each business in taxonomic hierarchies, specifically comprises:
Corresponding to each type of service in taxonomic hierarchies, the number of times of the type of service of user being accessed in taxonomic hierarchies respectively sorts from big to small, and from big to small label is carried out to described number of times, the number of times of the type of service that the user that h label is corresponding before and if only if accesses in taxonomic hierarchies is at least h, simultaneously, when the number of times of the type of service that the user that h+1 label is corresponding accesses in taxonomic hierarchies is less than h+1, the number of times preference of the type of service that described user accesses in taxonomic hierarchies is h;
According to said method, different business in corresponding taxonomic hierarchies, all can determine that user accesses the number of times preference of each business; Wherein, described H index is higher, and user preference degree is higher.
In like manner, described flow preference, described in browse the defining method of preference and type of service preference similar to the defining method of described number of times preference, therefore repeat no more.
Step 102: determine the type of service in the taxonomic hierarchies of user's first time every day access, and in described preset time period, add up first total number of days that described user accesses described type of service first time every day, adopt H exponentiation algorithm to be sorted by first total number of days, that determines that user accesses each business in taxonomic hierarchies browses preference;
Step 103: determine second of each type of service in described Preset Time in user's connected reference taxonomic hierarchies total number of days, adopts H exponentiation algorithm to be sorted by second total number of days, determines that user accesses the type of service preference of each business in taxonomic hierarchies.
Here, step 102 can be exchanged to the execution sequence of step 103.
Further, described method also comprises:
Be respectively described number of times preference, browse preference and type of service preference arranges weight, determine described number of times preference, browse the weighted mean value of preference and type of service preference according to weight, using determined weighted mean value as number of times preference coefficient.
Further, described method also comprises:
Be respectively described flow preference, browse preference and type of service preference arranges weight, determine described flow preference, browse the weighted mean value of preference and type of service preference according to weight, using determined weighted mean value as flow preference coefficient.
Here, if the number of times preference of certain class business of user, flow preference, browse arbitrary value in preference and type of service preference for empty, then null value is replaced with a fixed value, subsequently calculation times preference coefficient and flow preference coefficient;
Such as, if the preference of browsing determining the B type of service of user A is empty, then the preference of browsing of the B business corresponding to described user A is replaced with 1000, determines the number of times preference coefficient of described user A subsequently:
I.e. described number of times preference coefficient
Wherein, described C is the number of times preference of the B type of service of user A, and described D is the type of service preference of the B type of service of user A; Described X1, Y1 and Z1 are the weight corresponding to described number of times preference, browse preference and type of service preference, and described X1, Y1 and Z1 are empirical value.
Here, if number of times preference coefficient corresponding to the B type of service of described user A is larger, illustrate that described user A gets over B type of service described in preference; If flow preference coefficient corresponding to the B type of service of described user A is larger, illustrate that the flow that described user A spends in described B type of service is more, i.e. more B type of service described in preference.
Further, described method also comprises:
Determine the flow used in each preset time period during described user is in preset time period described in N number of continuous print respectively;
Determine that flow stepping identifies, and determine the flow stepping mark residing for the flow that described user uses in each preset time period respectively;
Flow stepping mark residing for the flow that described user uses in each preset time period determines the class letter of described user.
Here, described N specifically can be arranged according to actual conditions, is generally the positive integer being more than or equal to 2, described preset time period can be arranged arbitrarily according to the actual requirements, as being set to one month, determine the number of times preference of the user in month, flow preference, browse preference, type of service preference, number of times preference coefficient and flow preference coefficient, simultaneously, according to the flow stepping mark of the use of the user in N continuous month, determine the class letter of user, as high consumption group or low consumption group, and then, be the type of service that user recommends user preference according to the preference of user and the class letter of user, so, Neng Shi operator recommends the business of user preference more accurately to user.
Further, described method also comprises:
According to described number of times preference, flow preference, browse preference, the class letter of type of service preference and user is the business that described user recommends described user preference.
Here, described is full dose data in taxonomic hierarchies for data involved in preference defining method, namely the number of times of user's access service type, flowing of access, first time access service type total number of days and total number of days of connected reference type of service be full dose data in taxonomic hierarchies.
Here, in described taxonomic hierarchies, the division of classification by setting up classification tree, in conjunction with own type of service sorting technique, and with reference to Internet service genre classification methods etc., can be sorted out business from different perspectives; Meanwhile, for specific transactions, can be each detailed subclass the content Further Division related in business as required, such as reading is further divided into city, science fiction, through subclasses such as pipe and history; In addition, in taxonomic hierarchies, the division of classification also needs to take into account different agreement, namely considers HTTP and non-http protocol simultaneously, is convenient to flexibly the business that each agreement uses be segmented as far as possible, for recommending the business of user preference to lay the foundation to all types of user accurately.
Here, the embodiment of the present invention can number of pass times preference, flow preference, browse preference, type of service preference, number of times preference coefficient, flow preference coefficient and user class letter determine the preference of user to certain class business, and determine the business that user's frequency of utilization is higher, so, operator can be made to user according to user preference to recommend the business of user preference more accurately.
In addition, adopt that the embodiment of the present invention can be determined in a time period, situation that user moves to the product of rival, the situation of user being moved to the product of rival is as the factor weighing operator's planning own service, be conducive to operator and analyze the user situation using competing product, with the marketing strategy of the user situation planning operator according to use competing product; Meanwhile, because the excavation of the competing product of each business needs regular update, therefore, by manually pay close attention to last word dynamically and the user preference dynamically determined of the embodiment of the present invention combine, can enrich analysis identification user preference business model storehouse.
The embodiment of the present invention additionally provides a kind of user preference determining device, and as shown in Figure 2, shown device comprises:
First determining unit 21, for determining that user accesses the number of times of each type of service in preset time period in taxonomic hierarchies, adopting H exponentiation algorithm to be sorted by described number of times, determining that user accesses the number of times preference of each business in taxonomic hierarchies; Or, determine that user accesses the flowing of access of each business in described preset time period in taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by flowing of access, determine that user accesses the flow preference of each business in taxonomic hierarchies;
Second determining unit 22, for determining the type of service in the taxonomic hierarchies of user's first time every day access, and in described preset time period, add up first total number of days that described user accesses described type of service first time every day, adopt H exponentiation algorithm to be sorted by first total number of days, that determines that user accesses each business in taxonomic hierarchies browses preference;
3rd determining unit 23, for determining second total number of days of each type of service in described Preset Time in user's connected reference taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by second total number of days, determine that user accesses the type of service preference of each business in taxonomic hierarchies.
Based on the device shown in Fig. 2, as shown in Figure 3, described device also comprises:
Setting unit 24, for being respectively described number of times preference, browses preference and type of service preference arranges weight;
Computing unit 25, for determining described number of times preference, browsing the weighted mean value of preference and type of service preference according to the described number of times preference arranged, the weight of browsing preference and type of service preference, using determined weighted mean value as number of times preference coefficient.
Further, described setting unit 24 also for arranging weight for described flow preference, and again for described in browse preference and type of service preference arranges weight; Accordingly,
Described computing unit 25, also for determining described flow preference according to the described flow preference arranged, the weight of browsing preference and type of service preference, browse the weighted mean value of preference and type of service preference, using the weighted mean value determined as flow preference coefficient.
Based on the device shown in Fig. 3, as shown in Figure 4, described device also comprises: the 4th determining unit 26, for determining the flow used in each preset time period during described user is in preset time period described in N number of continuous print respectively;
5th determining unit 27, for determining that flow stepping identifies, and determines the flow stepping mark residing for the flow that described user uses in each preset time period respectively;
6th determining unit 28, determines the class letter of described user for the flow stepping mark residing for the flow that uses in each preset time period according to described user.
Recommendation unit 29, for according to described number of times preference, flow preference, browse preference, the class letter of type of service preference and user is the business that described user recommends described user preference.
Described first determining unit, the second determining unit, the 3rd determining unit, setting unit, computing unit, the 4th determining unit, the 5th determining unit, the 6th determining unit and recommendation unit all can run on computing machine, can be realized by the central processing unit be positioned on computing machine (CPU) or microprocessor (MPU) or digital signal processor (DSP) or programmable gate array (FPGA).
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
The above, be only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.
Claims (10)
1. a user preference defining method, is characterized in that, described method comprises:
Determine that user accesses the number of times of each type of service in preset time period in taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by described number of times, determine that user accesses the number of times preference of each business in taxonomic hierarchies; Or, determine that user accesses the flowing of access of each business in described preset time period in taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by flowing of access, determine that user accesses the flow preference of each business in taxonomic hierarchies;
Determine the type of service in the taxonomic hierarchies of user's first time every day access, and in described preset time period, add up first total number of days that described user accesses described type of service first time every day, adopt H exponentiation algorithm to be sorted by first total number of days, that determines that user accesses each business in taxonomic hierarchies browses preference;
Determine second of each type of service in described Preset Time in user's connected reference taxonomic hierarchies total number of days, adopt H exponentiation algorithm to be sorted by second total number of days, determine that user accesses the type of service preference of each business in taxonomic hierarchies.
2. method according to claim 1, is characterized in that, described method also comprises:
Be respectively described number of times preference, browse preference and type of service preference arranges weight, determine described number of times preference, browse the weighted mean value of preference and type of service preference according to weight, using determined weighted mean value as number of times preference coefficient.
3. method according to claim 1, is characterized in that, described method also comprises:
Be respectively described flow preference, browse preference and type of service preference arranges weight, determine described flow preference, browse the weighted mean value of preference and type of service preference according to weight, using determined weighted mean value as flow preference coefficient.
4. the method according to any one of claims 1 to 3, is characterized in that, described method also comprises:
Determine the flow used in each preset time period during described user is in preset time period described in N number of continuous print respectively;
Determine that flow stepping identifies, and determine the flow stepping mark residing for the flow that described user uses in each preset time period respectively;
Flow stepping mark residing for the flow that described user uses in each preset time period determines the class letter of described user.
5. method according to claim 4, is characterized in that, described method also comprises:
According to described number of times preference, flow preference, browse preference, the class letter of type of service preference and user is the business that described user recommends described user preference.
6. a user preference determining device, is characterized in that, described device comprises:
First determining unit, for determining that user accesses the number of times of each type of service in preset time period in taxonomic hierarchies, adopting H exponentiation algorithm to be sorted by described number of times, determining that user accesses the number of times preference of each business in taxonomic hierarchies; Or, determine that user accesses the flowing of access of each business in described preset time period in taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by flowing of access, determine that user accesses the flow preference of each business in taxonomic hierarchies;
Second determining unit, for determining the type of service in the taxonomic hierarchies of user's first time every day access, and in described preset time period, add up first total number of days that described user accesses described type of service first time every day, adopt H exponentiation algorithm to be sorted by first total number of days, that determines that user accesses each business in taxonomic hierarchies browses preference;
3rd determining unit, for determining second total number of days of each type of service in described Preset Time in user's connected reference taxonomic hierarchies, adopt H exponentiation algorithm to be sorted by second total number of days, determine that user accesses the type of service preference of each business in taxonomic hierarchies.
7. device according to claim 6, is characterized in that, described device also comprises:
Setting unit, for being respectively described number of times preference, browses preference and type of service preference arranges weight;
Computing unit, for determining described number of times preference, browsing the weighted mean value of preference and type of service preference according to the described number of times preference arranged, the weight of browsing preference and type of service preference, using determined weighted mean value as number of times preference coefficient.
8. device according to claim 6, is characterized in that, described setting unit, also for arranging weight for described flow preference, and again for described in browse preference and type of service preference arranges weight; Accordingly,
Described computing unit, also for determining described flow preference according to the described flow preference arranged, the weight of browsing preference and type of service preference, browse the weighted mean value of preference and type of service preference, using the weighted mean value determined as flow preference coefficient.
9. the device according to any one of claim 6 to 8, is characterized in that, described device also comprises:
4th determining unit, for determining the flow used in each preset time period during described user is in preset time period described in N number of continuous print respectively;
5th determining unit, for determining that flow stepping identifies, and determines the flow stepping mark residing for the flow that described user uses in each preset time period respectively;
6th determining unit, determines the class letter of described user for the flow stepping mark residing for the flow that uses in each preset time period according to described user.
10. device according to claim 9, it is characterized in that, described device also comprises: recommendation unit, for according to described number of times preference, flow preference, browse preference, the class letter of type of service preference and user is the business that described user recommends described user preference.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410150723.XA CN105022729B (en) | 2014-04-15 | 2014-04-15 | A kind of user preference determines method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410150723.XA CN105022729B (en) | 2014-04-15 | 2014-04-15 | A kind of user preference determines method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105022729A true CN105022729A (en) | 2015-11-04 |
| CN105022729B CN105022729B (en) | 2018-03-23 |
Family
ID=54412713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410150723.XA Active CN105022729B (en) | 2014-04-15 | 2014-04-15 | A kind of user preference determines method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105022729B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106066864A (en) * | 2016-05-27 | 2016-11-02 | 重庆邮电大学 | A kind of various dimensions mobile subscriber's preference dynamic identifying method |
| CN106897960A (en) * | 2015-12-18 | 2017-06-27 | 中国移动通信集团公司 | A kind of classification information acquisition methods and device |
| CN107169825A (en) * | 2017-05-08 | 2017-09-15 | 浙江敢尚网络科技有限公司 | A kind of user preference analysis method and system |
| CN107451140A (en) * | 2016-05-30 | 2017-12-08 | 阿里巴巴集团控股有限公司 | A kind of determination method and device of user preference degree |
| CN107995289A (en) * | 2017-12-01 | 2018-05-04 | 中国联合网络通信集团有限公司 | The behaviortrace method and platform of a kind of network user |
| CN108629608A (en) * | 2017-03-22 | 2018-10-09 | 腾讯科技（深圳）有限公司 | User data processing method and processing device |
| CN110796505A (en) * | 2018-08-03 | 2020-02-14 | 阿里巴巴集团控股有限公司 | Service object recommendation method and device |
| CN111093251A (en) * | 2019-12-11 | 2020-05-01 | 深圳市高德信通信股份有限公司 | Internet access selection system based on user requirements |
| CN112333040A (en) * | 2020-10-12 | 2021-02-05 | 联通智网科技有限公司 | Flow separation method and device, storage medium and computer equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101500136A (en) * | 2008-02-01 | 2009-08-05 | 深圳市同洲电子股份有限公司 | Method and system for implementing personalized digital television service providing |
| CN102421025A (en) * | 2011-11-22 | 2012-04-18 | 康佳集团股份有限公司 | Television program guide method and system based on program content attributes |
| CN102957969A (en) * | 2012-05-18 | 2013-03-06 | 华东师范大学 | Device and method for recommending program to IPTV (Internet protocol television) terminal user |
| CN103051960A (en) * | 2011-10-13 | 2013-04-17 | 纬创资通股份有限公司 | Television program recommendation system and method thereof |
| US20140033256A1 (en) * | 2004-04-26 | 2014-01-30 | Sirius Xm Radio Inc. | Method and apparatus for providing enhanced electronic program guide with personalized selection of broadcast content using affinities data and user preferences |
-
2014
- 2014-04-15 CN CN201410150723.XA patent/CN105022729B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140033256A1 (en) * | 2004-04-26 | 2014-01-30 | Sirius Xm Radio Inc. | Method and apparatus for providing enhanced electronic program guide with personalized selection of broadcast content using affinities data and user preferences |
| CN101500136A (en) * | 2008-02-01 | 2009-08-05 | 深圳市同洲电子股份有限公司 | Method and system for implementing personalized digital television service providing |
| CN103051960A (en) * | 2011-10-13 | 2013-04-17 | 纬创资通股份有限公司 | Television program recommendation system and method thereof |
| CN102421025A (en) * | 2011-11-22 | 2012-04-18 | 康佳集团股份有限公司 | Television program guide method and system based on program content attributes |
| CN102957969A (en) * | 2012-05-18 | 2013-03-06 | 华东师范大学 | Device and method for recommending program to IPTV (Internet protocol television) terminal user |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106897960A (en) * | 2015-12-18 | 2017-06-27 | 中国移动通信集团公司 | A kind of classification information acquisition methods and device |
| CN106066864B (en) * | 2016-05-27 | 2019-04-30 | 重庆邮电大学 | A kind of various dimensions mobile subscriber preference dynamic identifying method |
| CN106066864A (en) * | 2016-05-27 | 2016-11-02 | 重庆邮电大学 | A kind of various dimensions mobile subscriber's preference dynamic identifying method |
| CN107451140B (en) * | 2016-05-30 | 2020-08-25 | 阿里巴巴集团控股有限公司 | Method and device for determining user preference degree |
| CN107451140A (en) * | 2016-05-30 | 2017-12-08 | 阿里巴巴集团控股有限公司 | A kind of determination method and device of user preference degree |
| CN108629608A (en) * | 2017-03-22 | 2018-10-09 | 腾讯科技（深圳）有限公司 | User data processing method and processing device |
| CN108629608B (en) * | 2017-03-22 | 2023-02-24 | 腾讯科技（深圳）有限公司 | User data processing method and device |
| CN107169825A (en) * | 2017-05-08 | 2017-09-15 | 浙江敢尚网络科技有限公司 | A kind of user preference analysis method and system |
| CN107995289A (en) * | 2017-12-01 | 2018-05-04 | 中国联合网络通信集团有限公司 | The behaviortrace method and platform of a kind of network user |
| CN107995289B (en) * | 2017-12-01 | 2019-08-06 | 中国联合网络通信集团有限公司 | A kind of the behaviortrace method and platform of the network user |
| CN110796505A (en) * | 2018-08-03 | 2020-02-14 | 阿里巴巴集团控股有限公司 | Service object recommendation method and device |
| CN110796505B (en) * | 2018-08-03 | 2023-07-04 | 淘宝（中国）软件有限公司 | Business object recommendation method and device |
| CN111093251B (en) * | 2019-12-11 | 2021-03-16 | 深圳市高德信通信股份有限公司 | Internet access selection system based on user requirements |
| CN111093251A (en) * | 2019-12-11 | 2020-05-01 | 深圳市高德信通信股份有限公司 | Internet access selection system based on user requirements |
| CN112333040A (en) * | 2020-10-12 | 2021-02-05 | 联通智网科技有限公司 | Flow separation method and device, storage medium and computer equipment |
| CN112333040B (en) * | 2020-10-12 | 2023-05-02 | 联通智网科技股份有限公司 | Flow separation method and device, storage medium and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105022729B (en) | 2018-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105022729A (en) | User preference determination method and device | |
| US10841743B2 (en) | Branching mobile-device to system-namespace identifier mappings | |
| CN106850750B (en) | Method and device for pushing information in real time | |
| CN102208086A (en) | Field-oriented personalized intelligent recommendation system and implementation method | |
| CN102999506B (en) | A kind of method and apparatus obtaining user's independent access number | |
| Ye et al. | Development of a highly flexible mobile GIS-based system for collecting arable land quality data | |
| CN102932206B (en) | The method and system of monitoring website access information | |
| CN110418200A (en) | A kind of video recommendation method, device and terminal device | |
| CN106250513A (en) | A kind of event personalization sorting technique based on event modeling and system | |
| CN104102696A (en) | Content recommendation method and device | |
| CN104537000A (en) | Method and device for pushing information | |
| CN103136683A (en) | Method and device for calculating product reference price and method and system for searching products | |
| CN109255564A (en) | Pick-up point address recommendation method and device | |
| CN102339296A (en) | Method and device for sorting query results | |
| CN106919625A (en) | A kind of internet customer attribute recognition methods and device | |
| CN110300084A (en) | A kind of IP address-based portrait method and apparatus | |
| CN104978406A (en) | User behavior analysis method of Internet platform | |
| CN105975486A (en) | Information recommendation method and apparatus | |
| CN103853809A (en) | Efficient space allocation for business objects | |
| CN108984735A (en) | Label Word library updating method, apparatus and electronic equipment | |
| CN104123321A (en) | Method and device for determining recommended pictures | |
| TWI618017B (en) | Landmark recommendation method combining life behavior analysis and community and its computer program product | |
| CN112183885A (en) | Position determination method and device | |
| CN108985805A (en) | A kind of method and apparatus that selectivity executes push task | |
| CN107423315A (en) | The excavation processing method and system of a kind of outdoor media resource 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |