WO2019062013A1 - 电子装置、用户分群的方法、系统及计算机可读存储介质 - Google Patents

电子装置、用户分群的方法、系统及计算机可读存储介质 Download PDF

Info

Publication number
WO2019062013A1
WO2019062013A1 PCT/CN2018/077633 CN2018077633W WO2019062013A1 WO 2019062013 A1 WO2019062013 A1 WO 2019062013A1 CN 2018077633 W CN2018077633 W CN 2018077633W WO 2019062013 A1 WO2019062013 A1 WO 2019062013A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
access
browsing
grouping
users
Prior art date
Application number
PCT/CN2018/077633
Other languages
English (en)
French (fr)
Inventor
武湖
王建明
肖京
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019062013A1 publication Critical patent/WO2019062013A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations

Definitions

  • the present application relates to the field of communications technologies, and in particular, to an electronic device, a method and system for grouping users, and a computer readable storage medium.
  • User portrait grouping can group independent users in the network to group users, and can truly understand users, which has a great impact on the network marketing environment.
  • the products are mainly grouped by users who have purchased or expressed obvious preferences as a label, and the user portrait grouping scheme has one-sidedness and certain limitations.
  • the user history browsing path can also reflect the user's willingness to consume. For users with highly overlapping browsing paths, their product preferences and consumer will have similar similarities. How to use the user path as a label for user grouping to fully exploit the internal grouping The potential for consumption has become a problem to be solved.
  • the purpose of the present application is to provide an electronic device, a method and system for user grouping, and a computer readable storage medium, which are intended to perform user grouping by an access path reflecting the potential consumer desire of the user, so as to fully exploit the consumption potential within the group.
  • the present application provides an electronic device including a memory and a processor coupled to the memory, wherein the memory stores a system for grouping users operable on the processor, When the system of user grouping is executed by the processor, the following steps are implemented:
  • S101 Obtain a browsing record generated when the user browses on the terminal device, and extract key information in the browsing record, where the key information includes a user identifier, an access column, product information, and a browsing time;
  • S102 The user represented by the user identifier is used as an analysis object, and the key information is divided into corresponding multiple access records, and each access record is converted into a corresponding access path.
  • the present application further provides a method for grouping users, and the method for grouping users includes:
  • S1 Obtain a browsing record generated when the user browses on the terminal device, and extract key information in the browsing record, where the key information includes a user identifier, an access column, product information, and a browsing time;
  • the user represented by the user identifier is used as an analysis object, and the key information is divided into corresponding multiple access records, and each access record is converted into a corresponding access path;
  • S3 Perform user grouping based on the access path and a preset grouping rule.
  • the present application further provides a system for user grouping, where the user grouping system includes:
  • An extraction module configured to obtain a browsing record generated when the user browses on the terminal device, and extract key information in the browsing record, where the key information includes a user identifier, an access column, product information, and a browsing time;
  • a conversion module configured to use the user represented by the user identifier as an analysis object, divide the key information into corresponding multiple access records, and convert each access record into a corresponding access path;
  • the grouping module is configured to perform user grouping based on the access path and the preset grouping rule.
  • the present application further provides a computer readable storage medium having a system for grouping users, wherein the user grouping system is implemented by a processor to implement steps:
  • S101 Obtain a browsing record generated when the user browses on the terminal device, and extract key information in the browsing record, where the key information includes a user identifier, an access column, product information, and a browsing time;
  • S102 The user represented by the user identifier is used as an analysis object, and the key information is divided into corresponding multiple access records, and each access record is converted into a corresponding access path.
  • the application extracts key information in the browsing record, and the key information includes user identification, access columns, product information, and browsing time, and the key information is divided into access records and converted into access paths, and the user accesses the access path.
  • this application performs user grouping through an access path that reflects the user's potential willingness to consume, which can break the limitations of existing programs and further tap the consumption potential within the group.
  • FIG. 1 is a schematic diagram of an optional application environment of each embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a first embodiment of a method for grouping users according to the present application
  • FIG. 3 is a schematic flowchart of a second embodiment of a method for grouping users according to the present application.
  • FIG. 4 is a schematic flowchart diagram of a third embodiment of a method for grouping users according to the present application.
  • FIG. 1 is a schematic diagram of an optional application environment according to various embodiments of the present application.
  • the application environment diagram includes an electronic device 1 and a terminal device 2 .
  • the electronic device 1 can perform data interaction with the terminal device 2 through a suitable technology such as a network or a near field communication technology.
  • the terminal device 2 includes, but is not limited to, any electronic product that can interact with a user through a keyboard, a mouse, a remote controller, a touch panel, or a voice control device, for example, a personal computer, a tablet computer, or a smart phone. , Personal Digital Assistant (PDA), game consoles, Internet Protocol Television (IPTV), smart wearable devices, navigation devices, etc., or mobile devices such as digital TVs, desktop computers, Fixed terminal for notebooks, servers, etc.
  • PDA Personal Digital Assistant
  • IPTV Internet Protocol Television
  • smart wearable devices navigation devices, etc.
  • mobile devices such as digital TVs, desktop computers, Fixed terminal for notebooks, servers, etc.
  • the electronic device 1 is an apparatus capable of automatically performing numerical calculation and/or information processing in accordance with an instruction set or stored in advance.
  • the electronic device 1 may be a computer, a single network server, a server group composed of multiple network servers, or a cloud-based cloud composed of a large number of hosts or network servers, where cloud computing is a type of distributed computing.
  • a super virtual computer consisting of a group of loosely coupled computers.
  • the electronic device 1 may include, but is not limited to, a memory 11, a processor 12 and a network interface 13 communicably connected to each other through a system bus, and the memory 11 stores a system for grouping users that can be run on the processor 12.
  • FIG. 1 only shows the electronic device 1 having the components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 includes a memory and at least one type of readable storage medium.
  • the memory provides a cache for the operation of the electronic device 1;
  • the readable storage medium may be, for example, a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM).
  • a non-volatile storage medium such as a read only memory (ROM), an electrically erasable programmable read only memory (EEPROM), a programmable read only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, or the like.
  • the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1; in other embodiments, the non-volatile storage medium may also be external to the electronic device 1.
  • the storage device for example, a plug-in hard disk provided on the electronic device 1, a smart memory card (SMC), a Secure Digital (SD) card, a flash card, or the like.
  • the readable storage medium of the memory 11 is generally used to store an operating system installed in the electronic device 1 and various types of application software, such as program codes for storing a system of user groups in an embodiment of the present application. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.
  • the processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 12 is typically used to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with the terminal device 2.
  • the processor 12 is configured to run program code or process data stored in the memory 11, such as a system running a user group.
  • the network interface 13 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the electronic device 1 and other electronic devices.
  • the network interface 13 is mainly used to connect the electronic device 1 with one or more terminal devices 2, and establish a data transmission channel and a communication connection between the electronic device 1 and one or more terminal devices 2 to obtain one. Or a browsing record of the user on the plurality of terminal devices 2.
  • the user grouping system is stored in the memory 11 and includes at least one computer readable instruction stored in the memory 11, the at least one computer readable instruction being executable by the processor 12 to implement user grouping of embodiments of the present application.
  • the method; as described later, the at least one computer readable instruction can be classified into different logic modules depending on the functions implemented by the various parts thereof.
  • Step S101 Acquire a browsing record generated when the user browses on the terminal device, and extract key information in the browsing record, where the key information includes a user identifier, an access column, product information, and a browsing time;
  • a browsing record is generated, and each browsing record includes information such as a user identifier, a browsing time, and a browsing content.
  • the terminal device can upload the browsing record to the electronic device in real time after the browsing record is generated, or upload the browsing record to the electronic device periodically, thereby completing the collecting operation of the browsing record generated on each terminal device.
  • key information is extracted in a large number of accumulated historical browsing records, and the key information includes a user identifier, an access column, product information, and browsing time.
  • the access column and product information can be obtained from the browsing content.
  • the user identifier is, for example, a device number or a mobile phone number.
  • the access column is, for example, insurance, wealth management, loan, etc.
  • the product information includes products corresponding to each access column, for example, the product information is a car insurance product under the insurance column. Or accident insurance products, etc.
  • Step S102 The user represented by the user identifier is used as an analysis object, and the key information is divided into corresponding multiple access records, and each access record is converted into a corresponding access path;
  • each user identifier represents a user, for example, a device number or a mobile phone number represents a user, and each user is analyzed as an analysis object.
  • Each user has multiple pieces of key information corresponding to the browsing history. All key information corresponding to each user is segmented to obtain multiple complete one-time access records.
  • the access column and product information of each analysis object are browsed within a preset browsing time.
  • An access record for example, for a terminal device where a device number is located, first confirm the start browsing time, and then segment the access column and product information that is browsed for half an hour or one hour from the start browsing time as a visit. Recording; in other embodiments, it is possible to determine all the links from the beginning of the browsing to the end of the browsing process when each analysis object browses the product, and visit the access section and product information in all links from the beginning of the browsing to the end of the browsing as a visit.
  • Recording for example, for a user corresponding to a certain mobile phone number, when browsing a certain insurance product, the user determines that the browsing start session starts to browse the corresponding insurance product in an access column, and the intermediate link may compare the insurance product with other Comparing similar insurance products, if the user ends up Buy the insurance products, it is determined that the purchase of insurance products to browse the end of the session.
  • the access column and product information are connected and associated in the order of browsing, and the corresponding access path is obtained.
  • the corresponding access path is obtained.
  • Insurance products click on the short-term comprehensive accident insurance to browse, return, click on the travel accident insurance to browse, return, click on the short-term comprehensive accident insurance to browse, select the high-end models in the short-term comprehensive accident insurance, click on the immediate insurance, then the corresponding access path
  • Step S103 Perform user grouping based on the access path and the preset grouping rule.
  • the user may not purchase the browsed product while browsing the product, but if multiple users browse the product multiple times and have not purchased the product, it can be seen that the product is recognized by these users, or there are multiple users.
  • the product was purchased during the browsing of the product, which also indicates that the product is recognized by these users.
  • the browsing behavior of the user is obtained through the user's access path analysis, thereby obtaining the user's purchasing psychology or purchasing intention, and then performing user grouping.
  • the preset grouping rule includes: counting the access frequency of each access path, and the access frequency may be in units of days or weeks, for example, 100 times per day or 1000 times per week, and obtaining access frequency.
  • the access path is greater than or equal to the preset frequency, and the preset frequency is, for example, 300 times per day or 2000 times per week, and all the users in each access path obtained are divided into the same group; or the coincidence rate of the access path is analyzed, where
  • the coincidence rate of two access paths means that there are several partial paths in the two access paths that are the same. In this case, the coincidence rate of the two can be calculated.
  • the preset coincidence rate can be 50%, etc., for example, the first The access path is: "Insurance in China Ping An's official website (column) - Accident insurance - short-term comprehensive accident insurance - high-end models in short-term comprehensive accident insurance", the second access path is: "Insurance in China Ping An official website (column) - Accident insurance - Travel accident insurance - Short-term comprehensive accident insurance - Basic section in short-term comprehensive accident insurance - Insured", these two access routes include three identical parts: Ping An Insurance (column), accident insurance, short-term comprehensive accident insurance in the network, for the first access path, the second access path and its coincidence rate reaches 75%, then the first access path and the second access path
  • the access path is regarded as an access path with a coincidence rate greater than or equal to the preset coincidence rate, and the access path with the coincidence rate greater than or equal to the preset coincidence rate is regarded as a similar access path set, and the access frequency of each similar access path set is counted,
  • the embodiment extracts key information in the browsing record, and the key information includes user identifier, access column, product information, and browsing time, and the key information is divided into an access record and converted into an access path, and the user is clicked.
  • the path is grouped.
  • the user is grouped by the access path reflecting the potential consumption intention of the user, which can break the limitation of the existing solution and further explore the consumption potential in the group.
  • the product information to be recommended is determined, and the determined product information is recommended to the user to be recommended.
  • a large number of user attribute information corresponding to the customer is stored in the database, and the user attribute information includes a name, education, income, position, address, contact information, and device number, etc., and the user identifier of the user in a certain group Matching with the user attribute information in the database, if the matching is that the user identifiers of the two are the same, the user attribute information that is the same as the user identifier is obtained, and in the group, the grouping is obtained based on the obtained user attribute information.
  • the user to be recommended for example, based on age, education, income, and/or position, select the users to be recommended in each group, determine the product information to be recommended, and recommend the determined product information to the user to be recommended, for example, a product has a common or mid-range file. For high-end points, you can recommend the high-end models of the product to the higher-recommended users.
  • the user After the user is grouped, the user is associated with a large number of clients in the database to obtain the user to be recommended, and then recommend the product information to be recommended to the user to be recommended. In this way, the user can be accurately and widely recommended. Product information to further tap the internal consumption potential of the group.
  • the preference information of the users in each group may also be extracted, and the product information is recommended to all users in the corresponding group based on the user's preference information.
  • the preference information of the user in each group can be analyzed from the access path of the user in the group. For example, in addition to analyzing the access frequency of the user's access path, it is also possible to analyze between two identical or similar access paths in the same user.
  • the access time if the time interval between access times between two identical or similar access paths is shorter, it means that the user currently approves or likes the corresponding product in the access path, and analyzes all the users in the group.
  • the user's preference information in the group is obtained by the user's approved or favorite product in the group, and the product information is recommended to all users in the corresponding group based on the preference information.
  • the preference information of the user in the group is extracted, and the product information corresponding to the preference information is recommended to the users in the group, and the internal consumption potential of the group can be further explored.
  • FIG. 2 is a schematic flowchart of a first embodiment of a method for grouping users according to the present application.
  • the method for grouping users includes:
  • Step S1 Obtain a browsing record generated when the user browses on the terminal device, and extract key information in the browsing record, where the key information includes a user identifier, an access column, product information, and a browsing time;
  • a browsing record is generated, and each browsing record includes information such as a user identifier, a browsing time, and a browsing content.
  • the terminal device can upload the browsing record to the electronic device in real time after the browsing record is generated, or upload the browsing record to the electronic device periodically, thereby completing the collecting operation of the browsing record generated on each terminal device.
  • key information is extracted in a large number of accumulated historical browsing records, and the key information includes a user identifier, an access column, product information, and browsing time.
  • the access column and product information can be obtained from the browsing content.
  • the user identifier is, for example, a device number or a mobile phone number.
  • the access column is, for example, insurance, wealth management, loan, etc.
  • the product information includes products corresponding to each access column, for example, the product information is a car insurance product under the insurance column. Or accident insurance products, etc.
  • Step S2 The user represented by the user identifier is used as an analysis object, and the key information is divided into corresponding multiple access records, and each access record is converted into a corresponding access path;
  • each user identifier represents a user, for example, a device number or a mobile phone number represents a user, and each user is analyzed as an analysis object.
  • Each user has multiple pieces of key information corresponding to the browsing history. All key information corresponding to each user is segmented to obtain multiple complete one-time access records.
  • the access column and product information of each analysis object are browsed within a preset browsing time.
  • An access record for example, for a terminal device where a device number is located, first confirm the start browsing time, and then segment the access column and product information that is browsed for half an hour or one hour from the start browsing time as a visit. Recording; in other embodiments, it is possible to determine all the links from the beginning of the browsing to the end of the browsing process when each analysis object browses the product, and visit the access section and product information in all links from the beginning of the browsing to the end of the browsing as a visit.
  • Recording for example, for a user corresponding to a certain mobile phone number, when browsing a certain insurance product, the user determines that the browsing start session starts to browse the corresponding insurance product in an access column, and the intermediate link may compare the insurance product with other Comparing similar insurance products, if the user ends up If the insurance product is purchased, it is determined that the insurance product is purchased as the end of the browsing.
  • the access column and product information are connected and associated in the order of browsing, and the corresponding access path is obtained.
  • the corresponding access path is obtained.
  • Insurance products click on the short-term comprehensive accident insurance to browse, return, click on the travel accident insurance to browse, return, click on the short-term comprehensive accident insurance to browse, select the high-end models in the short-term comprehensive accident insurance, click on the immediate insurance, then the corresponding access path
  • Step S3 Perform user grouping based on the access path and the preset grouping rule.
  • the user may not purchase the browsed product while browsing the product, but if multiple users browse the product multiple times and have not purchased the product, it can be seen that the product is recognized by these users, or there are multiple users.
  • the product was purchased during the browsing of the product, which also indicates that the product is recognized by these users.
  • the browsing behavior of the user is obtained through the user's access path analysis, thereby obtaining the user's purchasing psychology or purchasing intention, and then performing user grouping.
  • the preset grouping rule includes: counting the access frequency of each access path, and the access frequency may be in units of days or weeks, for example, 100 times per day or 1000 times per week, and obtaining access frequency.
  • the access path is greater than or equal to the preset frequency, and the preset frequency is, for example, 300 times per day or 2000 times per week, and all the users in each access path obtained are divided into the same group; or the coincidence rate of the access path is analyzed, where
  • the coincidence rate of two access paths means that there are several partial paths in the two access paths that are the same. In this case, the coincidence rate of the two can be calculated.
  • the preset coincidence rate can be 50%, etc., for example, the first The access path is: "Insurance in China Ping An's official website (column) - Accident insurance - short-term comprehensive accident insurance - high-end models in short-term comprehensive accident insurance", the second access path is: "Insurance in China Ping An official website (column) - Accident insurance - Travel accident insurance - Short-term comprehensive accident insurance - Basic section in short-term comprehensive accident insurance - Insured", these two access routes include three identical parts: Ping An Insurance (column), accident insurance, short-term comprehensive accident insurance in the network, for the first access path, the second access path and its coincidence rate reaches 75%, then the first access path and the second access path
  • the access path is regarded as an access path with a coincidence rate greater than or equal to the preset coincidence rate, and the access path with the coincidence rate greater than or equal to the preset coincidence rate is regarded as a similar access path set, and the access frequency of each similar access path set is counted,
  • the present embodiment extracts key information in the browsing record, and the key information includes the user identifier, the access column, the product information, and the browsing time, and the key information is divided into the access record and converted into an access path, and the user is pressed.
  • the access path is grouped.
  • the user is grouped by the access path reflecting the potential consumption intention of the user, which can break the limitation of the existing solution and further explore the consumption potential in the group.
  • the method further includes:
  • step S4 the user identifier of each user in each group is matched with the user attribute information pre-stored in the database, and the user attribute information in the database that is the same as the user identifier is obtained, and each group is filtered based on the obtained user attribute information.
  • step S5 the product information to be recommended is determined, and the determined product information is recommended to the user to be recommended.
  • a large number of user attribute information corresponding to the customer is stored in the database, and the user attribute information includes a name, education, income, position, address, contact information, and device number, etc., and the user identifier of the user in a certain group Matching with the user attribute information in the database, if the matching is that the user identifiers of the two are the same, the user attribute information that is the same as the user identifier is obtained, and in the group, the grouping is obtained based on the obtained user attribute information.
  • the user to be recommended for example, based on age, education, income, and/or position, select the users to be recommended in each group, determine the product information to be recommended, and recommend the determined product information to the user to be recommended, for example, a product has a common or mid-range file. For high-end points, you can recommend the high-end models of the product to the higher-recommended users.
  • the user After the user is grouped, the user is associated with a large number of clients in the database to obtain the user to be recommended, and then recommend the product information to be recommended to the user to be recommended. In this way, the user can be accurately and widely recommended. Product information to further tap the internal consumption potential of the group.
  • the user grouping method further includes:
  • Step S6 extracting preference information of users in each group, and recommending product information to all users in the corresponding group based on the preference information of the user.
  • the preference information of the user in each group can be analyzed from the access path of the user in the group. For example, in addition to analyzing the access frequency of the user's access path, it is also possible to analyze between two identical or similar access paths in the same user.
  • the access time if the time interval between access times between two identical or similar access paths is shorter, it means that the user currently approves or likes the corresponding product in the access path, and analyzes all the users in the group.
  • the user's preference information in the group is obtained by the user's approved or favorite product in the group, and the product information is recommended to all users in the corresponding group based on the preference information.
  • the preference information of the user in the group is extracted, and the product information corresponding to the preference information is recommended to the users in the group, and the internal consumption potential of the group can be further explored.
  • the present application also provides a computer readable storage medium having stored thereon a system of user groupings, the steps of the user grouping method described above when the user grouped system is executed by the processor.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better.
  • Implementation Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Databases & Information Systems (AREA)
  • Finance (AREA)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种电子装置、用户分群的方法、系统及计算机可读存储介质，所述用户分群的方法包括：获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间（S1）；以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径（S2）；基于所述访问路径及预设的分群规则进行用户分群（S3）。所述方法通过反映用户潜在的消费意愿的访问路径进行用户分群，以充分挖掘群内的消费潜力。

Description

电子装置、用户分群的方法、系统及计算机可读存储介质
优先权申明
本申请基于巴黎公约申明享有2017年09月30日递交的申请号为CN 201710914567.3、名称为“电子装置、用户分群的方法及计算机可读存储介质”中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种电子装置、用户分群的方法、系统及计算机可读存储介质。
背景技术
用户画像分群能够将网络中独立的用户关联起来进行分组，能够真实了解用户，其对于网络营销环境具有很大的影响。现有的用户画像分群方案中，主要是以用户购买过或者表达过明显偏好的产品作为标签进行分群，这种用户画像分群方案具有片面性及一定的局限性。实际上，用户历史浏览路径也可以反映用户的消费意愿，对于浏览路径高度重合的用户，其产品喜好和消费意愿具有一定的相似性，如何以用户路径作为标签进行用户分群，以充分挖掘分群内部消费潜力，成为有待解决的问题。
发明内容
本申请的目的在于提供一种电子装置、用户分群的方法、系统及计算机可读存储介质，旨在通过反映用户潜在的消费意愿的访问路径进行用户分群，以充分挖掘群内的消费潜力。
为实现上述目的，本申请提供一种电子装置，所述电子装置包括存储器及与所述存储器连接的处理器，所述存储器中存储有可在所述处理器上运行 的用户分群的系统，所述用户分群的系统被所述处理器执行时实现如下步骤：
S101，获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
S102，以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
S103，基于所述访问路径及预设的分群规则进行用户分群。
为实现上述目的，本申请还提供一种用户分群的方法，所述用户分群的方法包括：
S1，获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
S2，以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
S3，基于所述访问路径及预设的分群规则进行用户分群。
为实现上述目的，本申请还提供一种用户分群的系统，所述用户分群的系统包括：
提取模块，用于获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
转化模块，用于以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
分群模块，用于基于所述访问路径及预设的分群规则进行用户分群。
为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有用户分群的系统，所述用户分群的系统被处理器执行时实现步骤：
S101，获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
S102，以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
S103，基于所述访问路径及预设的分群规则进行用户分群。
本申请的有益效果是：本申请提取浏览记录中的关键信息，关键信息包括用户标识、访问栏目、产品信息及浏览时间，将关键信息分割为访问记录并转化为访问路径，对用户按访问路径进行分群，本申请通过反映用户潜在的消费意愿的访问路径进行用户分群，能够打破现有方案的局限性，进一步挖掘群内的消费潜力。
附图说明
图1为本申请各个实施例一可选的应用环境示意图；
图2为本申请用户分群的方法第一实施例的流程示意图；
图3为本申请用户分群的方法第二实施例的流程示意图；
图4为本申请用户分群的方法第三实施例的流程示意图。
具体实施方式
以下结合附图对本申请的原理和特征进行描述，所举实例只用于解释本申请，并非用于限定本申请的范围。
如图1所示，图1为本申请各个实施例一可选的应用环境示意图，该应用环境示意图包括电子装置1及终端设备2。电子装置1可以通过网络、近 场通信技术等适合的技术与终端设备2进行数据交互。
所述终端设备2包括，但不限于，任何一种可与用户通过键盘、鼠标、遥控器、触摸板或者声控设备等方式进行人机交互的电子产品，例如，个人计算机、平板电脑、智能手机、个人数字助理(Personal Digital Assistant，PDA)、游戏机、交互式网络电视(Internet Protocol Television,IPTV)、智能式穿戴式设备、导航装置等等的可移动设备，或者诸如数字TV、台式计算机、笔记本、服务器等等的固定终端。用户在终端设备2上浏览时产生浏览记录，浏览记录发送给电子装置1。
所述电子装置1是一种能够按照事先设定或者存储的指令，自动进行数值计算和/或信息处理的设备。所述电子装置1可以是计算机、也可以是单个网络服务器、多个网络服务器组成的服务器组或者基于云计算的由大量主机或者网络服务器构成的云，其中云计算是分布式计算的一种，由一群松散耦合的计算机集组成的一个超级虚拟计算机。
本实施例中，电子装置1可包括，但不仅限于，可通过系统总线相互通信连接的存储器11、处理器12及网络接口13，存储器11存储有可在处理器12上运行的用户分群的系统。需要指出的是，图1仅示出了具有组件11-13的电子装置1，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
其中，存储器11包括内存及至少一种类型的可读存储介质。内存为电子装置1的运行提供缓存；可读存储介质可为如闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等的非易失性存储介质。在一些实施例中，可读存储介质可以是电子装置1的内部存储单元，例如该电子装置1的硬盘；在另一些实施例中，该非易失性存储介质也可以是电子装置1的外部存储设备，例如电子装置1上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD) 卡，闪存卡(Flash Card)等。本实施例中，存储器11的可读存储介质通常用于存储安装于电子装置1的操作系统和各类应用软件，例如存储本申请一实施例中的用户分群的系统的程序代码等。此外，存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
所述处理器12在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器12通常用于控制所述电子装置1的总体操作，例如执行与所述终端设备2进行数据交互或者通信相关的控制和处理等。本实施例中，所述处理器12用于运行所述存储器11中存储的程序代码或者处理数据，例如运行用户分群的系统等。
所述网络接口13可包括无线网络接口或有线网络接口，该网络接口13通常用于在所述电子装置1与其他电子设备之间建立通信连接。本实施例中，网络接口13主要用于将电子装置1与一个或多个终端设备2相连，在电子装置1与一个或多个终端设备2之间建立数据传输通道和通信连接，以获取一个或多个终端设备2上的用户的浏览记录。
所述用户分群的系统存储在存储器11中，包括至少一个存储在存储器11中的计算机可读指令，该至少一个计算机可读指令可被处理器12执行，以实现本申请各实施例的用户分群的方法；如后续所述，该至少一个计算机可读指令依据其各部分所实现的功能不同，可被划为不同的逻辑模块。
其中，用户分群的系统被所述处理器12执行时实现如下步骤：
步骤S101，获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
本实施例中，用户在终端设备的app上浏览产品信息时产生浏览记录，每条浏览记录包括用户标识、浏览时间及浏览内容等信息。终端设备可以在产生浏览记录后实时将其上传至电子装置中，也可以定时将浏览记录上传至电子装置中，由此，完成对各个终端设备上产生的浏览记录的收集操作。
本实施例在累积的大量的历史浏览记录中提取关键信息，关键信息包括用户标识、访问栏目、产品信息及浏览时间，访问栏目及产品信息可从浏览内容中获取。其中，用户标识例如为设备号或者手机号等，对于平安APP,访问栏目例如为保险、理财、借贷等，产品信息包括各个访问栏目下对应的产品，例如产品信息为保险栏目下的汽车保险产品或者意外保险产品等。
步骤S102，以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
本实施例中，以每一用户标识代表一个用户，例如某一设备号或手机号代表一用户，将每一用户作为一个分析对象进行分析。每个用户有多条浏览记录对应的关键信息。将每一个用户对应的所有关键信息进行分割，以分割得到多个完整的一次访问记录。
其中，将关键信息分割为对应的多个一次访问记录的方法有多种，优选地，在一实施例中，可以是将每一分析对象在预设浏览时间内浏览的访问栏目及产品信息作为一次访问记录，例如对于某一设备号所在的终端设备，首先确认开始浏览时刻，然后将从开始浏览时刻为起始时刻半个小时或者一个小时内浏览的访问栏目及产品信息分割出来作为一次访问记录；在其他实施例中，可以确定每一分析对象浏览产品时的浏览开始环节至浏览结束环节的所有环节，将浏览开始环节至浏览结束环节的所有环节中的访问栏目及产品信息作为一次访问记录，例如，对于某一手机号对应的用户，用户在浏览某款保险产品时，确定浏览开始环节为开始对某一访问栏目中对应的保险产品进行浏览，中间环节可能将该保险产品与其他同类的保险产品进行比较，如果用户最终购买了该保险产品，则确定购买了该保险产品为浏览结束环节。
在将一次访问记录转化为访问路径时，具体的，将访问栏目及产品信息按照浏览的先后顺序进行连接及关联，得到对应的访问路径，例如用户进入中国平安官网后，点击保险栏目，选择意外险产品，点击短期综合意外险进行浏览，返回，点击旅行意外险进行浏览，返回，再次点击短期综合意外险进行浏览，选择短期综合意外险中的高端款、点击立即投保，则对应的访问 路径为：中国平安官网中的保险(栏目)-意外险-短期综合意外险-旅行意外险-短期综合意外险-短期综合意外险中的高端款-投保。
步骤S103，基于所述访问路径及预设的分群规则进行用户分群。
用户在浏览产品的过程中可能并未购买所浏览的产品，但如果多个用户多次浏览该产品且未购买该产品时，可以看出该款产品得到这些用户的认同，或者有多个用户在浏览产品的过程中均购买了该产品，也说明该款产品得到这些用户的认同。本实施例中，通过用户的访问路径分析得到用户的浏览行为，进而得到用户的购买心理或购买意愿，进而对其进行用户分群。
在一优选的实施例中，预设的分群规则包括：统计每一访问路径的访问频率，该访问频率可以是以天或者星期等为单位，例如每天100次或者每星期1000次，获取访问频率大于等于预设频率的访问路径，预设频率例如为每天300次或者每星期2000次，将所获取的每一访问路径中的所有用户分为同一群体；或者分析访问路径的重合率，其中，两条访问路径的重合率指的是：两条访问路径中有若干个部分路径是相同的，这时可以计算两者的重合率，预设的重合率可以是50％等，例如第一条访问路径为：“中国平安官网中的保险(栏目)-意外险-短期综合意外险-短期综合意外险中的高端款”，第二条访问路径为：“中国平安官网中的保险(栏目)-意外险-旅游意外险-短期综合意外险-短期综合意外险中的基本款-投保”，这两条访问路径中包括3个相同的部分：中国平安官网中的保险(栏目)、意外险、短期综合意外险，对于第一条访问路径而言，第二条访问路径与它的重合率达到75％，则可以将第一条访问路径与第二条访问路径视为重合率大于等于预设重合率的访问路径，将重合率大于等于预设重合率的访问路径作为一个相似访问路径集合，统计各个相似访问路径集合的访问频率，获取访问频率大于等于预设频率(例如每天500次或者每星期3000次)的相似访问路径集合，将所获取的同一相似访问路径集合中的所有用户分为同一群体。
与现有技术相比，本实施例提取浏览记录中的关键信息，关键信息包括用户标识、访问栏目、产品信息及浏览时间，将关键信息分割为访问记录并 转化为访问路径，对用户按访问路径进行分群，本实施例通过反映用户潜在的消费意愿的访问路径进行用户分群，能够打破现有方案的局限性，进一步挖掘群内的消费潜力。
在一优选的实施例中，在上述图1的实施例的基础上，所述用户分群的系统被所述处理器执行时，还实现如下步骤：
将各分群中的每一用户的用户标识与数据库中预存的用户属性信息进行匹配，获取数据库中与所述用户标识相同的用户属性信息，基于所获取的用户属性信息筛选各分群中的待推荐用户；
确定待推荐的产品信息，向待推荐用户推荐所确定的产品信息。
本实施例中，数据库中存储有大量的客户对应的用户属性信息，该用户属性信息包括姓名、学历、收入、职位、住址、联系方式及设备号等，将某一分群中的用户的用户标识与数据库中的用户属性信息进行匹配，若匹配得出两者的用户标识相同，则获取与该用户标识相同的用户属性信息，在该分群中，基于所获取的用户属性信息筛选得到该分群的待推荐用户，例如基于年龄、学历、收入和/或职位筛选各分群中的待推荐用户，确定待推荐的产品信息，向待推荐用户推荐所确定的产品信息，例如某款产品有普通、中档、高档之分，则可以向收入较高的待推荐用户推荐该产品的高档款。
本实施例将用户分群后，与数据库中的大量客户进行关联，以得到待推荐用户，然后向待推荐用户推荐待推荐的产品信息，通过这种方式，可以准确地、大范围地向用户推荐产品信息，进一步挖掘分群内部消费潜力。
在其他实施例中，还可以提取各分群中的用户的偏好信息，基于用户的偏好信息向对应的分群中的所有用户推荐产品信息。
其中，各分群中用户的偏好信息可以从该分群中用户的访问路径分析得出，例如除了分析用户的访问路径的访问频率外，还可以分析同一用户中两条相同或者相似的访问路径之间的访问时间，若两条相同或者相似的访问路径之间的访问时间的时间间隔越短，则说明该用户当前比较认可或喜好该访问路径中对应的产品，在分析出该分群中所有的用户认可或喜好的产品后， 通过该分群中的用户认可或喜好的产品得出该分群中的用户的偏好信息，基于该偏好信息向对应的分群中的所有用户推荐产品信息。
本实施例提取分群中的用户的偏好信息，向该分群中的用户推荐偏好信息对应的产品信息，能够进一步挖掘分群内部消费潜力。
如图2所示，图2为本申请用户分群的方法第一实施例的流程示意图，该用户分群的方法包括：
步骤S1，获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
本实施例中，用户在终端设备的app上浏览产品信息时产生浏览记录，每条浏览记录包括用户标识、浏览时间及浏览内容等信息。终端设备可以在产生浏览记录后实时将其上传至电子装置中，也可以定时将浏览记录上传至电子装置中，由此，完成对各个终端设备上产生的浏览记录的收集操作。
本实施例在累积的大量的历史浏览记录中提取关键信息，关键信息包括用户标识、访问栏目、产品信息及浏览时间，访问栏目及产品信息可从浏览内容中获取。其中，用户标识例如为设备号或者手机号等，对于平安APP,访问栏目例如为保险、理财、借贷等，产品信息包括各个访问栏目下对应的产品，例如产品信息为保险栏目下的汽车保险产品或者意外保险产品等。
步骤S2，以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
本实施例中，以每一用户标识代表一个用户，例如某一设备号或手机号代表一用户，将每一用户作为一个分析对象进行分析。每个用户有多条浏览记录对应的关键信息。将每一个用户对应的所有关键信息进行分割，以分割得到多个完整的一次访问记录。
其中，将关键信息分割为对应的多个一次访问记录的方法有多种，优选地，在一实施例中，可以是将每一分析对象在预设浏览时间内浏览的访问栏目及产品信息作为一次访问记录，例如对于某一设备号所在的终端设备，首 先确认开始浏览时刻，然后将从开始浏览时刻为起始时刻半个小时或者一个小时内浏览的访问栏目及产品信息分割出来作为一次访问记录；在其他实施例中，可以确定每一分析对象浏览产品时的浏览开始环节至浏览结束环节的所有环节，将浏览开始环节至浏览结束环节的所有环节中的访问栏目及产品信息作为一次访问记录，例如，对于某一手机号对应的用户，用户在浏览某款保险产品时，确定浏览开始环节为开始对某一访问栏目中对应的保险产品进行浏览，中间环节可能将该保险产品与其他同类的保险产品进行比较，如果用户最终购买了该保险产品，则确定购买了该保险产品为浏览结束环节。
在将一次访问记录转化为访问路径时，具体的，将访问栏目及产品信息按照浏览的先后顺序进行连接及关联，得到对应的访问路径，例如用户进入中国平安官网后，点击保险栏目，选择意外险产品，点击短期综合意外险进行浏览，返回，点击旅行意外险进行浏览，返回，再次点击短期综合意外险进行浏览，选择短期综合意外险中的高端款、点击立即投保，则对应的访问路径为：中国平安官网中的保险(栏目)-意外险-短期综合意外险-旅行意外险-短期综合意外险-短期综合意外险中的高端款-投保。
步骤S3，基于所述访问路径及预设的分群规则进行用户分群。
用户在浏览产品的过程中可能并未购买所浏览的产品，但如果多个用户多次浏览该产品且未购买该产品时，可以看出该款产品得到这些用户的认同，或者有多个用户在浏览产品的过程中均购买了该产品，也说明该款产品得到这些用户的认同。本实施例中，通过用户的访问路径分析得到用户的浏览行为，进而得到用户的购买心理或购买意愿，进而对其进行用户分群。
在一优选的实施例中，预设的分群规则包括：统计每一访问路径的访问频率，该访问频率可以是以天或者星期等为单位，例如每天100次或者每星期1000次，获取访问频率大于等于预设频率的访问路径，预设频率例如为每天300次或者每星期2000次，将所获取的每一访问路径中的所有用户分为同一群体；或者分析访问路径的重合率，其中，两条访问路径的重合率指的是：两条访问路径中有若干个部分路径是相同的，这时可以计算两者的重 合率，预设的重合率可以是50％等，例如第一条访问路径为：“中国平安官网中的保险(栏目)-意外险-短期综合意外险-短期综合意外险中的高端款”，第二条访问路径为：“中国平安官网中的保险(栏目)-意外险-旅游意外险-短期综合意外险-短期综合意外险中的基本款-投保”，这两条访问路径中包括3个相同的部分：中国平安官网中的保险(栏目)、意外险、短期综合意外险，对于第一条访问路径而言，第二条访问路径与它的重合率达到75％，则可以将第一条访问路径与第二条访问路径视为重合率大于等于预设重合率的访问路径，将重合率大于等于预设重合率的访问路径作为一个相似访问路径集合，统计各个相似访问路径集合的访问频率，获取访问频率大于等于预设频率(例如每天500次或者每星期3000次)的相似访问路径集合，将所获取的同一相似访问路径集合中的所有用户分为同一群体。
与现有技术相比，本实施例通过提取浏览记录中的关键信息，关键信息包括用户标识、访问栏目、产品信息及浏览时间，将关键信息分割为访问记录并转化为访问路径，对用户按访问路径进行分群，本实施例通过反映用户潜在的消费意愿的访问路径进行用户分群，能够打破现有方案的局限性，进一步挖掘群内的消费潜力。
在一优选的实施例中，如图3所示，在图2的实施例的基础上，所述步骤S3之后还包括：
步骤S4，将各分群中的每一用户的用户标识与数据库中预存的用户属性信息进行匹配，获取数据库中与所述用户标识相同的用户属性信息，基于所获取的用户属性信息筛选各分群中的待推荐用户；
步骤S5，确定待推荐的产品信息，向待推荐用户推荐所确定的产品信息。
本实施例中，数据库中存储有大量的客户对应的用户属性信息，该用户属性信息包括姓名、学历、收入、职位、住址、联系方式及设备号等，将某一分群中的用户的用户标识与数据库中的用户属性信息进行匹配，若匹配得出两者的用户标识相同，则获取与该用户标识相同的用户属性信息，在该分 群中，基于所获取的用户属性信息筛选得到该分群的待推荐用户，例如基于年龄、学历、收入和/或职位筛选各分群中的待推荐用户，确定待推荐的产品信息，向待推荐用户推荐所确定的产品信息，例如某款产品有普通、中档、高档之分，则可以向收入较高的待推荐用户推荐该产品的高档款。
本实施例将用户分群后，与数据库中的大量客户进行关联，以得到待推荐用户，然后向待推荐用户推荐待推荐的产品信息，通过这种方式，可以准确地、大范围地向用户推荐产品信息，进一步挖掘分群内部消费潜力。
在一优选的实施例中，如图4所示，在图2的实施例的基础上，所述用户分群的方法还包括：
步骤S6，提取各分群中的用户的偏好信息，基于用户的偏好信息向对应的分群中的所有用户推荐产品信息。
其中，各分群中用户的偏好信息可以从该分群中用户的访问路径分析得出，例如除了分析用户的访问路径的访问频率外，还可以分析同一用户中两条相同或者相似的访问路径之间的访问时间，若两条相同或者相似的访问路径之间的访问时间的时间间隔越短，则说明该用户当前比较认可或喜好该访问路径中对应的产品，在分析出该分群中所有的用户认可或喜好的产品后，通过该分群中的用户认可或喜好的产品得出该分群中的用户的偏好信息，基于该偏好信息向对应的分群中的所有用户推荐产品信息。
本实施例提取分群中的用户的偏好信息，向该分群中的用户推荐偏好信息对应的产品信息，能够进一步挖掘分群内部消费潜力。
本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有用户分群的系统，所述用户分群的系统被处理器执行时实现上述的用户分群的方法的步骤。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的 技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种电子装置，其特征在于，所述电子装置包括存储器及与所述存储器连接的处理器，所述存储器中存储有可在所述处理器上运行的用户分群的系统，所述用户分群的系统被所述处理器执行时实现如下步骤：
    S101，获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
    S102，以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
    S103，基于所述访问路径及预设的分群规则进行用户分群。
  2. 根据权利要求1所述的电子装置，其特征在于，所述步骤S102包括：
    以所述用户标识代表的用户为分析对象，将每一分析对象在预设浏览时间内浏览的访问栏目及产品信息作为一次访问记录，并将各个访问记录转化为对应的访问路径；或者
    以所述用户标识代表的用户为分析对象，确定每一分析对象浏览产品时的浏览开始环节至浏览结束环节的所有环节，将浏览开始环节至浏览结束环节的所有环节中的访问栏目及产品信息作为一次访问记录，并将各个访问记录转化为对应的访问路径。
  3. 根据权利要求2所述的电子装置，其特征在于，所述预设的分群规则包括：
    统计每一访问路径的访问频率，获取所述访问频率大于等于预设频率的访问路径，将所获取的每一访问路径中的所有用户分为同一群体；或者
    分析所述访问路径的重合率，将所述重合率大于等于预设重合率的访问路径作为一个相似访问路径集合，统计各个相似访问路径集合的访问频率，获取所述访问频率大于等于预设频率的相似访问路径集合，将所获取的同一 相似访问路径集合中的所有用户分为同一群体。
  4. 根据权利要求1至3任一项所述的电子装置，其特征在于，所述用户分群的系统被所述处理器执行时，还实现如下步骤：
    S104，将各分群中的每一用户的用户标识与数据库中预存的用户属性信息进行匹配，获取数据库中与所述用户标识相同的用户属性信息，基于所获取的用户属性信息筛选各分群中的待推荐用户；
    S105，确定待推荐的产品信息，向待推荐用户推荐所确定的产品信息。
  5. 根据权利要求1至3任一项所述的电子装置，其特征在于，所述用户分群的系统被所述处理器执行时，还实现如下步骤：
    提取各分群中的用户的偏好信息，基于用户的偏好信息向对应的分群中的所有用户推荐产品信息。
  6. 一种用户分群的方法，其特征在于，所述用户分群的方法包括：
    S1，获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
    S2，以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
    S3，基于所述访问路径及预设的分群规则进行用户分群。
  7. 根据权利要求6所述的用户分群的方法，其特征在于，所述步骤S2包括：
    以所述用户标识代表的用户为分析对象，将每一分析对象在预设浏览时间内浏览的访问栏目及产品信息作为一次访问记录，并将各个访问记录转化为对应的访问路径；或者
    以所述用户标识代表的用户为分析对象，确定每一分析对象浏览产品时的浏览开始环节至浏览结束环节的所有环节，将浏览开始环节至浏览结束环 节的所有环节中的访问栏目及产品信息作为一次访问记录，并将各个访问记录转化为对应的访问路径。
  8. 根据权利要求7所述的用户分群的方法，其特征在于，所述预设的分群规则为：
    统计每一访问路径的访问频率，获取所述访问频率大于等于预设频率的访问路径，将所获取的每一访问路径中的所有用户分为同一群体；或者
    分析所述访问路径的重合率，将所述重合率大于等于预设重合率的访问路径作为一个相似访问路径集合，统计各个相似访问路径集合的访问频率，获取所述访问频率大于等于预设频率的相似访问路径集合，将所获取的同一相似访问路径集合中的所有用户分为同一群体。
  9. 根据权利要求6至8任一项所述的用户分群的方法，其特征在于，所述步骤S3之后还包括：
    S4，将各分群中的每一用户的用户标识与数据库中预存的用户属性信息进行匹配，获取数据库中与所述用户标识相同的用户属性信息，基于所获取的用户属性信息筛选各分群中的待推荐用户；
    S5，确定待推荐的产品信息，向待推荐用户推荐所确定的产品信息。
  10. 根据权利要求6至8任一项所述的用户分群的方法，其特征在于，所述用户分群的方法还包括：
    S6，提取各分群中的用户的偏好信息，基于用户的偏好信息向对应的分群中的所有用户推荐产品信息。
  11. 一种用户分群的系统，其特征在于，所述用户分群的系统包括：
    提取模块，用于获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
    转化模块，用于以所述用户标识代表的用户为分析对象，将所述关键信 息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
    分群模块，用于基于所述访问路径及预设的分群规则进行用户分群。
  12. 根据权利要求11所述的用户分群的系统，其特征在于，所述转化模块，具体用于以所述用户标识代表的用户为分析对象，将每一分析对象在预设浏览时间内浏览的访问栏目及产品信息作为一次访问记录，并将各个访问记录转化为对应的访问路径；或者
    以所述用户标识代表的用户为分析对象，确定每一分析对象浏览产品时的浏览开始环节至浏览结束环节的所有环节，将浏览开始环节至浏览结束环节的所有环节中的访问栏目及产品信息作为一次访问记录，并将各个访问记录转化为对应的访问路径。
  13. 根据权利要求12所述的用户分群的系统，其特征在于，所述预设的分群规则为：
    统计每一访问路径的访问频率，获取所述访问频率大于等于预设频率的访问路径，将所获取的每一访问路径中的所有用户分为同一群体；或者
    分析所述访问路径的重合率，将所述重合率大于等于预设重合率的访问路径作为一个相似访问路径集合，统计各个相似访问路径集合的访问频率，获取所述访问频率大于等于预设频率的相似访问路径集合，将所获取的同一相似访问路径集合中的所有用户分为同一群体。
  14. 根据权利要求11至13任一项所述的用户分群的系统，其特征在于，还包括：
    筛选模块，用于将各分群中的每一用户的用户标识与数据库中预存的用户属性信息进行匹配，获取数据库中与所述用户标识相同的用户属性信息，基于所获取的用户属性信息筛选各分群中的待推荐用户；
    第一推荐模块，用于确定待推荐的产品信息，向待推荐用户推荐所确定 的产品信息。
  15. 根据权利要求11至13任一项所述的用户分群的系统，其特征在于，还包括：
    第二推荐模块，用于提取各分群中的用户的偏好信息，基于用户的偏好信息向对应的分群中的所有用户推荐产品信息。
  16. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有用户分群的系统，所述用户分群的系统被处理器执行时实现步骤：
    S101，获取用户在终端设备上浏览时产生的浏览记录，并提取所述浏览记录中的关键信息，所述关键信息包括用户标识、访问栏目、产品信息及浏览时间；
    S102，以所述用户标识代表的用户为分析对象，将所述关键信息分割为对应的多个一次访问记录，并将各个访问记录转化为对应的访问路径；
    S103，基于所述访问路径及预设的分群规则进行用户分群。
  17. 根据权利要求16所述的计算机可读存储介质，其特征在于，所述步骤S102包括：
    以所述用户标识代表的用户为分析对象，将每一分析对象在预设浏览时间内浏览的访问栏目及产品信息作为一次访问记录，并将各个访问记录转化为对应的访问路径；或者
    以所述用户标识代表的用户为分析对象，确定每一分析对象浏览产品时的浏览开始环节至浏览结束环节的所有环节，将浏览开始环节至浏览结束环节的所有环节中的访问栏目及产品信息作为一次访问记录，并将各个访问记录转化为对应的访问路径。
  18. 根据权利要求17所述的计算机可读存储介质，其特征在于，所述预设的分群规则包括：
    统计每一访问路径的访问频率，获取所述访问频率大于等于预设频率的 访问路径，将所获取的每一访问路径中的所有用户分为同一群体；或者
    分析所述访问路径的重合率，将所述重合率大于等于预设重合率的访问路径作为一个相似访问路径集合，统计各个相似访问路径集合的访问频率，获取所述访问频率大于等于预设频率的相似访问路径集合，将所获取的同一相似访问路径集合中的所有用户分为同一群体。
  19. 根据权利要求16至18任一项所述的计算机可读存储介质，其特征在于，所述用户分群的系统被所述处理器执行时，还实现如下步骤：
    S104，将各分群中的每一用户的用户标识与数据库中预存的用户属性信息进行匹配，获取数据库中与所述用户标识相同的用户属性信息，基于所获取的用户属性信息筛选各分群中的待推荐用户；
    S105，确定待推荐的产品信息，向待推荐用户推荐所确定的产品信息。
  20. 根据权利要求16至18任一项所述的计算机可读存储介质，其特征在于，所述用户分群的系统被所述处理器执行时，还实现如下步骤：
    提取各分群中的用户的偏好信息，基于用户的偏好信息向对应的分群中的所有用户推荐产品信息。
PCT/CN2018/077633 2017-09-30 2018-02-28 电子装置、用户分群的方法、系统及计算机可读存储介质 WO2019062013A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710914567.3 2017-09-30
CN201710914567.3A CN108427700B (zh) 2017-09-30 2017-09-30 电子装置、用户分群的方法及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019062013A1 true WO2019062013A1 (zh) 2019-04-04

Family

ID=63155637

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/077633 WO2019062013A1 (zh) 2017-09-30 2018-02-28 电子装置、用户分群的方法、系统及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108427700B (zh)
WO (1) WO2019062013A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110162697A (zh) * 2019-04-12 2019-08-23 深圳壹账通智能科技有限公司 基于大数据的用户浏览行为分析方法、装置、介质及终端
CN110659269B (zh) * 2019-08-15 2024-04-02 中国平安财产保险股份有限公司 用户访问数据处理方法、装置、计算机设备及存储介质
WO2022001747A1 (zh) * 2020-06-30 2022-01-06 拉扎斯网络科技（上海）有限公司 拼单方法及装置
CN113095892B (zh) * 2021-04-30 2024-05-31 北京大米科技有限公司 一种数据处理方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103593413A (zh) * 2013-10-27 2014-02-19 西安电子科技大学 基于Agent的元搜索引擎个性化方法
CN103823883A (zh) * 2014-03-06 2014-05-28 焦点科技股份有限公司 一种网站用户访问路径的分析方法及系统
CN104298782A (zh) * 2014-11-07 2015-01-21 辽宁四维科技发展有限公司 互联网用户主动访问行为轨迹的分析方法
CN105357054A (zh) * 2015-11-26 2016-02-24 上海晶赞科技发展有限公司 网站流量分析方法、装置和电子设备

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101114287B (zh) * 2006-07-27 2011-06-15 国际商业机器公司 为数据生成浏览路径的方法和装置及浏览数据的方法
US20140006096A1 (en) * 2012-06-29 2014-01-02 Mastercard International Incorporated System and method for determining congestion using point of sale authorization data
US20140040774A1 (en) * 2012-08-01 2014-02-06 Google Inc. Sharing photos in a social network system
CN104932920B (zh) * 2015-06-16 2018-02-23 广东欧珀移动通信有限公司 一种应用程序的浏览路径引导方法及装置
CN105976161A (zh) * 2016-04-29 2016-09-28 随身云（北京）信息技术有限公司 一种基于时间轴上的智能推荐日历及基于用户的呈现方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103593413A (zh) * 2013-10-27 2014-02-19 西安电子科技大学 基于Agent的元搜索引擎个性化方法
CN103823883A (zh) * 2014-03-06 2014-05-28 焦点科技股份有限公司 一种网站用户访问路径的分析方法及系统
CN104298782A (zh) * 2014-11-07 2015-01-21 辽宁四维科技发展有限公司 互联网用户主动访问行为轨迹的分析方法
CN105357054A (zh) * 2015-11-26 2016-02-24 上海晶赞科技发展有限公司 网站流量分析方法、装置和电子设备

Also Published As

Publication number Publication date
CN108427700A (zh) 2018-08-21
CN108427700B (zh) 2021-08-24

Similar Documents

Publication Publication Date Title
WO2019061994A1 (zh) 电子装置、保险产品推荐方法、系统及计算机可读存储介质
US10496653B1 (en) Data workflow analysis service
US9310879B2 (en) Methods and systems for displaying web pages based on a user-specific browser history analysis
JP5717858B2 (ja) テキストセットの照合
US9990436B2 (en) Personal trends module
CN109190024A (zh) 信息推荐方法、装置、计算机设备及存储介质
US10546348B1 (en) Cleaning noise words from transaction descriptions
WO2019062013A1 (zh) 电子装置、用户分群的方法、系统及计算机可读存储介质
US8868570B1 (en) Selection and display of online content items
US12086616B1 (en) Parameterized user interface for capturing user feedback
US20140074851A1 (en) Dynamic data acquisition method and system
CN111695938B (zh) 产品推送方法及系统
CN112825089B (zh) 文章推荐方法、装置、设备及存储介质
JP2011227721A (ja) 関心抽出装置、関心抽出方法、及び関心抽出プログラム
CN105808642B (zh) 推荐方法及装置
CN111699487A (zh) 用于快速且安全的内容提供的系统
CN111476595A (zh) 产品推送方法、装置、计算机设备和存储介质
CN108694174B (zh) 内容投放数据的分析方法及装置
US11295326B2 (en) Insights on a data platform
US20140101064A1 (en) Systems and Methods for Automated Reprogramming of Displayed Content
US10614145B2 (en) Presenting content on a webpage in a desired format
CN113515703A (zh) 信息推荐方法、装置、电子设备及可读存储介质
US20180129664A1 (en) System and method to recommend a bundle of items based on item/user tagging and co-install graph
WO2019024238A1 (zh) 范围值数据统计方法、系统、电子装置及计算机可读存储介质
CN111127057B (zh) 一种多维用户画像恢复方法

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 08/10/2020)

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18862219

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 18862219

Country of ref document: EP

Kind code of ref document: A1