WO2018006726A1 - 识别用户潜在求助的知识点的方法及装置 - Google Patents

识别用户潜在求助的知识点的方法及装置 Download PDF

Info

Publication number
WO2018006726A1
WO2018006726A1 PCT/CN2017/090312 CN2017090312W WO2018006726A1 WO 2018006726 A1 WO2018006726 A1 WO 2018006726A1 CN 2017090312 W CN2017090312 W CN 2017090312W WO 2018006726 A1 WO2018006726 A1 WO 2018006726A1
Authority
WO
WIPO (PCT)
Prior art keywords
knowledge point
operation behavior
behavior path
help
user
Prior art date
Application number
PCT/CN2017/090312
Other languages
English (en)
French (fr)
Inventor
张寒瑞
张长江
宣竞
Original Assignee
阿里巴巴集团控股有限公司
张寒瑞
张长江
宣竞
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 阿里巴巴集团控股有限公司, 张寒瑞, 张长江, 宣竞 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2018006726A1 publication Critical patent/WO2018006726A1/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

Definitions

  • the present application relates to the field of Internet technologies, and in particular, to a method and apparatus for identifying a knowledge point of a user's potential help.
  • various applications provide corresponding customer service systems.
  • the user can interact with the customer service system to obtain the answer information corresponding to the knowledge point required to be assisted.
  • the way of interacting with the customer service system includes, for example, accessing the customer service system by telephone or accessing the customer service system through the client of the application.
  • the customer service system can obtain the answer information corresponding to the knowledge point and feed back to the user by means of manual answering or querying the database.
  • the customer service system obtains the answer information corresponding to the knowledge point according to the knowledge points provided by the user and feeds back to the user.
  • the number of users of the application increases, the number of users simultaneously accessing the customer service system may exceed a preset threshold (full). In this case, since the user cannot access the customer service system, the customer service system cannot be accessed. Get the answer information corresponding to the knowledge points you need.
  • the purpose of the embodiments of the present application is to provide a method and apparatus for identifying a knowledge point of a user's potential help to solve the problems in the prior art.
  • a method of identifying a user's potential help points including:
  • the queried knowledge point is determined as the knowledge point of the potential help of the account to be identified.
  • a device for identifying a knowledge point of a user's potential help comprising:
  • the query unit queries the knowledge point corresponding to the obtained operation behavior path according to the correspondence between the predetermined operation behavior path and the knowledge point; the corresponding relationship between the operation behavior path and the knowledge point is corresponding to the same operation behavior path
  • the number of different knowledge points is determined by the number of statistics
  • Determining the unit if queried, determining the queried knowledge point as the knowledge point of the potential help of the account to be identified.
  • An embodiment of the present application obtains an operation behavior path of an account to be identified, and queries a knowledge point corresponding to the acquired operation behavior path according to a predetermined correspondence between the operation behavior path and the knowledge point, so as to be queried and acquired. After the knowledge point corresponding to the operation behavior path, the queried knowledge point is determined as the knowledge point of the potential help of the account to be identified. It can be seen that, in the foregoing process, the knowledge points that may be required to be identified by the account may be identified by the foregoing process, so that after identifying the knowledge points that the account to be identified may require assistance, the account to be identified (ie, the potential help user) may be Provide services corresponding to knowledge points to improve the operational efficiency of the customer service system.
  • FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present application.
  • FIG. 2 is a flowchart of a method for identifying a knowledge point of a potential help of a user according to an embodiment of the present application
  • Figure 3 illustrates an example of generating an operational behavior path
  • 4A shows an example of a statistical number of accounts having the same operational behavior path and seeking assistance for the same knowledge point
  • FIG. 4B shows an example of a statistical probability value of an account for a knowledge point corresponding to each operation behavior path
  • FIG. 4C shows an example of a correspondence between the determined operational behavior path and the knowledge point
  • FIG. 5 is a schematic structural diagram of an apparatus for identifying a knowledge point of a potential help of a user according to an embodiment of the present application.
  • helping transaction a transaction in which a user consults (or asks for help) about a knowledge point of an application APP by means of a client or a telephone is referred to as a "helping transaction.”
  • helper refers to a user terminal (such as a mobile phone).
  • the helper refers to the customer service system of the application APP, and the knowledge point of the help is the content that the user asks for, and the common knowledge point may be pre-defined by the customer service system.
  • an application APP includes several sub-function blocks (such as: “transfer”, “credit card repayment”, “red envelope”, etc.), for each sub-function block (such as “credit card repayment”), Sub-work Users of the block may ask for help or user history help, and delineate one or more knowledge points (such as: “credit card repayment progress”, “credit card repayment off”, “credit card repayment limit” Wait). That is to say, the above knowledge points can represent a type of knowledge.
  • the answer information corresponding to the content can be obtained by inputting the content requested.
  • the user can input "credit card repayment progress" to match the answer information corresponding to the knowledge point.
  • the user can select the knowledge points he needs on the page provided by the customer service system. For example, the user can first select the "credit card”, and then select the knowledge points required from the plurality of knowledge points corresponding to the "credit card”.
  • the present application aims to provide a technique for identifying knowledge points that a user may seek for help, and the present technical solution will be described in detail below.
  • FIG. 1 is a schematic diagram of a system architecture provided by an embodiment of the present application.
  • the system includes a user terminal 10, a server 20, a network 30 for implementing communication between the user terminal 10 and the server 20, and a first database 40 and a number connected to the server 20.
  • the first database 40 and the second database 50 may be integrated with the server 20 or independent of the server 20.
  • the server may be a service platform of an application APP (social application or payment application, etc.).
  • the network 30 described above may include a local area network ("LAN”), a wide area network (“WAN”), an intranet, the Internet, a mobile telephone network, a virtual private network (VPN), a cellular or other mobile communication network, Bluetooth, NFC, or any combination thereof.
  • LAN local area network
  • WAN wide area network
  • VPN virtual private network
  • Each of the network devices on which the above-described terminal 10 is based may include a server, a desktop computer, a laptop computer, a tablet computer, a smart phone, a handheld computer, a personal digital assistant (“PDA”), or any other wired or wireless processing. Drive unit.
  • a server a desktop computer, a laptop computer, a tablet computer, a smart phone, a handheld computer, a personal digital assistant (“PDA”), or any other wired or wireless processing.
  • PDA personal digital assistant
  • the client application software may be installed on each terminal 10, and the user may log in to the account of the application APP at the terminal 10.
  • the server 20 can record each step of the operation behavior of each user in the process of using the application APP, thereby forming log data corresponding to each account.
  • the first database 40 is used to store log data corresponding to each account.
  • the log data may include a user's operation behavior for a specific function or page and a time stamp of each operation behavior.
  • the user's operational behavior path analysis is a kind of data analysis method in the Internet field. It mainly obtains the user's operation behavior path according to the log data of each user in the application App (or website), and according to the user's operation behavior path. Analyze the operation rules and characteristics of each module in the application App (or website), and explore the user's access or click mode to achieve some specific business purposes.
  • the application can determine whether the user is a potential user who needs assistance according to the user's operation behavior path.
  • the customer service system is subsequently accessed to seek assistance or difficulty.
  • the content (knowledge point) that the user needs to help can be related to the operation behavior path of the user within a certain period of time (a period of time corresponding to the help-seeking transaction).
  • the user's operational behavior path during the above specific time period can reflect the difficulty or problem (knowledge point) that the user may encounter.
  • the user path may generally be composed of individual user operation behaviors having a certain order. For example, the user has made "open page", "put an item into the shopping cart” and "in a certain period of time”.
  • the operation of the payment, the user's operation behavior path is: "open the page” ⁇ "put an item into the shopping cart” ⁇ "payment”.
  • a corresponding behavior ID can be set for each operation behavior, and the user's operation behavior path can be, for example, a ⁇ b ⁇ c.
  • the second database 50 is based on data as a knowledge point for identifying potential user assistance.
  • the server 20 can have the functions of an operating system and a customer service system.
  • the operational system server and the customer service system server can be set separately.
  • FIG. 2 is a flowchart of a method for identifying a knowledge point of a user's potential help according to an embodiment of the present disclosure.
  • the method may include a server, and the method includes the following steps:
  • Figure 3 shows an example of generating an operational behavior path
  • an application APP is assumed
  • the first page 301, the second page 303, and the third page 305 are included, wherein it is assumed that the first page 301 includes a function block (such as a button or a link) A, and the second page 303 includes a function block (such as a button, Or link) B, the function block C is included in the third page 305 above.
  • the application APP can jump from the first page 301 to the second page 303.
  • the application APP can be accessed by the second page.
  • the user's operation behavior includes three, namely: clicking the click behavior of the function block A, clicking the click behavior of the function block B, and clicking the click behavior of the function block C, thereby, in accordance with the order in which the operation behavior occurs , it can be determined that the operation behavior path of the user (account) is: "x ⁇ y ⁇ z".
  • x is used to identify a click behavior corresponding to function block A
  • y is used to identify a click behavior corresponding to function block B
  • z is used to identify a click behavior corresponding to function block C.
  • the server may acquire an operation behavior path of the user collected by the terminal in real time.
  • the server in a process in which the user uses the application APP, the server generates a behavior log corresponding to the operation behavior of the user, and the server may acquire the operation behavior path of the user according to the generated behavior log.
  • S102 Query a knowledge point corresponding to the acquired operation behavior path according to a predetermined correspondence between the operation behavior path and the knowledge point.
  • the correspondence between the operation behavior path and the knowledge point is determined according to the statistical quantity of different knowledge points corresponding to the same operation behavior path.
  • the correspondence between the operation behavior path and the knowledge point needs to be determined in advance and stored.
  • data statistics and analysis can be performed based on the pre-stated operation behavior paths (history) of several users and the knowledge points of the plurality of user history assistance, and the corresponding relationship between the operation behavior path and the knowledge points is obtained.
  • the process of determining the correspondence between the operation behavior path and the knowledge point may specifically include the following steps:
  • Step 1 Record the operation path of each user and the knowledge point of help in the preset time period.
  • the knowledge points that the user asks for in the help transaction are recorded. Then, acquiring a behavior log generated within a preset time period corresponding to the help transaction to pass the analysis line For the log, obtain the path of the action behavior of the helper user. Finally, the correspondence between the knowledge points of the help-seeking transaction and the acquired operation behavior path is recorded. Correspondingly, according to the corresponding relationship between the recorded knowledge point of the help-seeking transaction and the obtained operation behavior path, the number of users who perform the help transaction for the same knowledge point and generate the same operation behavior path may be counted.
  • the user's help account can be determined for each user-initiated help transaction (if the call is made by means of a phone call, the phone number can be used to determine the association with the current phone number. Account).
  • the customer service system may obtain the log data generated by the current help account for a certain period of time from the first database 40, and extract the help account according to the obtained log data during the specific time period.
  • the path of the operational behavior within For example, if in a certain help transaction, the knowledge point of the account a for help is Q1, the account a can be obtained to use the application in the 0:00-24:00 (specific time period) on the day when the help transaction occurs.
  • the operation behavior path may refer to a complete path of a session behavior between the client and the server.
  • the session may generally refer to a process from the user entering the application to exiting the application, in which process the application APP may give a unique session ID corresponding to the present callback.
  • each operation behavior path generated in the foregoing preset time period is an operation behavior path that needs to be recorded.
  • the knowledge point of the account a for help is Q1
  • the operation behavior path of the account a is 0:00-24:00 (specific time period) on the day when the account a occurs.
  • ⁇ y ⁇ z”, “x ⁇ z” it is necessary to separately record the above operation behavior path: “x ⁇ y ⁇ z” and the above operation behavior path: “x ⁇ z”, and the above operation behavior path to be recorded
  • the knowledge point Q1 that the account a asks for.
  • the correspondence between the knowledge points that the user asks for and the user's operational behavior path within a certain time period can be recorded accordingly.
  • Step 2 For each operation behavior path, count the number of help users of each knowledge point in the operation behavior path (as shown in FIG. 4A), and use the knowledge point corresponding to the maximum number of help users as The knowledge point corresponding to the operation behavior path.
  • the number of help users corresponding to different knowledge points under the operation behavior path “A ⁇ C” can be separately obtained, for example, the operation behavior path.
  • the number of help users corresponding to the knowledge point Q3 under "A ⁇ C” is 2946
  • the number of help users corresponding to the knowledge point Q5 under the operation behavior path "A ⁇ C” is 1507, and so on.
  • the number and content of the knowledge points corresponding to the operation behavior path may be different, for example, the knowledge points corresponding to the operation behavior path “A ⁇ C” are There are five knowledge points corresponding to the operation behavior path "B ⁇ E".
  • the number of help users of each knowledge point in each operation behavior path obtained by the above statistics is continuously accumulated, so that the accuracy of the data is continuously improved.
  • part of the data can be selectively retained based on the number of statistically requested users. For example, sort the number of users per user from large to small, and selectively retain the data of the top N (such as: 1000) bits; or, the number of statistical help users is greater than the preset value (such as: 500) Data is retained, the rest of the data is eliminated; and so on. Storage resources can be saved by selectively retaining data.
  • the probability values corresponding to different knowledge points in each operation behavior path can be further calculated.
  • the number of help users corresponding to the knowledge point Q3 under the operation behavior path that is pre-stated can be queried as: 2946; the operation behavior path
  • the number of help users corresponding to the knowledge point Q5 is: 1507; the number of help users corresponding to the knowledge point Q8 in the operation behavior path is: 1405; the number of help users corresponding to the knowledge point Q11 under the operation behavior path is: 618; the number of help users corresponding to the knowledge point Q9 in the operation behavior path is: 570.
  • the knowledge point corresponding to the maximum number of help users is used as the The knowledge point corresponding to the operation behavior path.
  • the statistically obtained knowledge points corresponding to the operation behavior path include: Q3, Q5, Q8, Q11, Q9, specifically, the number of help users corresponding to the above knowledge points: Q3, Q5, Q8, Q11, and Q9 are: "2946", “1507”, “1405", "618", "570".
  • the number of users who ask for help for a certain knowledge point is larger, it indicates that the user who has the above-mentioned operation behavior path has a higher probability of seeking help for the knowledge point.
  • the knowledge point corresponding to the maximum number of help users "2946": Q3 can be determined as the knowledge point corresponding to the operation behavior path "A ⁇ C”.
  • a knowledge point corresponding to each operation behavior path can be determined (the knowledge point is generally a knowledge point that the user having the operation behavior path is most likely to need help), thereby obtaining the operation behavior path and knowledge.
  • the correspondence of points is as shown in FIG. 4C and stored.
  • the potential help knowledge points corresponding to each operation behavior path may include multiple, for example, for the operation behavior path A ⁇ C”, If the number of users seeking help for the knowledge points Q3 and Q5 is found to be very close, it can be determined that the knowledge points corresponding to the above-mentioned operational behavior path: "A ⁇ C" are Q3 and Q5.
  • the foregoing step 2 may specifically include: for each operation behavior path, counting the help of each knowledge point in the operation behavior path The number of users, if the number of the largest number of help users obtained by the statistics is greater than a preset threshold, the knowledge point corresponding to the maximum number of help users is used as the knowledge point corresponding to the operation behavior path.
  • the preset threshold value and determining whether the maximum number of help users obtained by the statistics is greater than a preset threshold the correspondence between the operation path and the knowledge point with low accuracy can be filtered out. For example, for an operation behavior path, the statistics are obtained under the operation behavior path.
  • the statistical numbers of different knowledge points are: "1", "5", "8".
  • the number of the above-mentioned maximum number of help users obtained by statistics: "8" is small, which has certain contingency. If the number of the largest number of help users: "8" corresponds to the knowledge action path, it will be accurate. Not very sexual.
  • a preset threshold for example, 10000
  • the foregoing step 2 may include: determining, for each operation behavior path, whether the number of the one or more of the help users corresponding to the operation behavior path is greater than or equal to a preset number threshold, If yes, the knowledge point corresponding to the number of the number of help users greater than or equal to the preset number threshold is corresponding to the operation behavior path.
  • a preset number threshold As in the example shown in FIG. 4A above, assuming that the preset number threshold is 1500, the number greater than the preset number threshold is 1507 and 2946, and the operation behavior path: "A ⁇ C" may be associated with the knowledge points Q3 and Q5.
  • the process of determining the knowledge point and the operation behavior path is not limited to the above embodiment.
  • the correspondence between the above knowledge points and the operation behavior path may also be determined manually.
  • the content of the knowledge point Q1 is: “Cannot find the credit card repayment inquiry button”, however, the statistically obtained operation path corresponding to the knowledge point Q1 includes: clicking on the credit card repayment inquiry button.
  • Operational behavior obviously, the correspondence between the operational behavior path and the above knowledge point Q1 is unreasonable, and the corresponding relationship needs to be eliminated.
  • the account to be identified is a potential help account that may be required to be requested, and the knowledge point may be determined as a knowledge point of potential help of the account to be identified.
  • the embodiment of the present application obtains the operation behavior path of the account to be identified, and queries the knowledge corresponding to the obtained operation behavior path according to the corresponding relationship between the operation path and the knowledge point. Point, so that after querying the knowledge point corresponding to the acquired operation behavior path, the queried knowledge point is determined as the knowledge point of the potential help of the account to be identified.
  • the knowledge points that may be required to be identified by the account may be identified by the foregoing process, so that after identifying the knowledge points that the account to be identified may require assistance, the account to be identified (ie, the potential help user) may be Provide services corresponding to knowledge points to improve the operational efficiency of the customer service system.
  • the application scenario of the application includes at least one of the following:
  • the answer information corresponding to the knowledge point is pushed to the terminal corresponding to the account to be identified by identifying the potential help account and the potential help knowledge point.
  • the corresponding guiding information is pushed to the terminal to guide the user to use the application APP through a corresponding way.
  • the customer behavior warning can be made in advance for the operation behavior path. For example, the corresponding announcement information is pushed on the application client to remind and guide. user.
  • data reference can be provided for product design.
  • the user clicks the function block A in the first page 301, the user can jump to the second page 303.
  • the process of using the product if such product design is found to cause more users to ask for help (or other problems), you can modify the subsequent products to support the above situation, for example: in the modified product, the user After the function block A in the first page 301 is clicked, it is possible to jump directly to the third page 305.
  • the correspondence between the knowledge points and the operation behavior path obtained by the above statistics may be stored in the second database 50 for query.
  • the knowledge point corresponding to the operation behavior path may be queried according to the data table shown in FIG. 4C, and the knowledge of identifying the potential account to be identified may be performed. Know the point.
  • the knowledge points corresponding to the operation behavior path may also be queried according to the data table shown in FIG. 4A or FIG. 4B, and when multiple knowledge points corresponding to the operation behavior path are queried, The knowledge points identifying the potential help of the account to be identified are determined by corresponding judgment logic.
  • the determining logic may, for example, determine a knowledge point corresponding to the maximum number of users in the number of users as a knowledge point that identifies potential help for the account to be identified. Or determining whether the number of users is greater than or equal to a preset number threshold, and if yes, determining a knowledge point corresponding to the number of users greater than or equal to a preset number threshold as a knowledge point for identifying potential help for the account to be identified, and many more.
  • execution bodies of the steps of the methods provided by the foregoing embodiments may all be the same device, or the method may also be performed by different devices.
  • the execution body of step S101 and step S102 may be device 1
  • the execution body of step S103 may be device 2
  • the execution body of step S101 may be device 1
  • the execution body of step S102 and step S103 may be device 2 ;and many more.
  • FIG. 5 is a schematic structural diagram of an apparatus for identifying a knowledge point of a potential help of a user according to an embodiment of the present application.
  • the functions that can be implemented by each unit in the device for identifying the knowledge point of the user's potential help are similar to the functions that can be implemented in the steps of the method for identifying the user's potential help points.
  • the device for identifying the knowledge point of the user's potential help may be formed in the server by a combination of software or software and hardware.
  • the device 100 for identifying the user's potential help point may include: the obtaining unit 101 , the query unit 102 and the determining unit 103; wherein:
  • the obtaining unit 101 acquires an operation behavior path of the account to be identified.
  • the query unit 102 queries the knowledge points corresponding to the acquired operation behavior path according to the correspondence between the predetermined operation behavior path and the knowledge point.
  • the correspondence between the operation behavior path and the knowledge point is determined according to the statistical quantity of different knowledge points corresponding to the same operation behavior path.
  • the determining unit 103 determines the queried knowledge point as a knowledge point for the potential help of the account to be identified.
  • the embodiment of the present application obtains an operation behavior path of the account to be identified, and according to the correspondence between the predetermined operation behavior path and the knowledge point, the query corresponds to the acquired operation behavior path.
  • the knowledge point so that after querying the knowledge point corresponding to the acquired operation behavior path, the queried knowledge point is determined as the knowledge point of the potential help of the account to be identified.
  • the knowledge points that may be required to be identified by the account may be identified by the foregoing process, so that after identifying the knowledge points that the account to be identified may require assistance, the account to be identified (ie, the potential help user) may be Provide services corresponding to knowledge points to improve the operational efficiency of the customer service system.
  • the device further includes:
  • a recording unit that records each user's operation behavior path and the help knowledge point in the preset time period
  • the relationship determining unit counts the number of help users of each knowledge point in the operation behavior path for each operation behavior path, and uses the knowledge point corresponding to the maximum number of help users as the knowledge point corresponding to the operation behavior path.
  • the relationship determining unit counts the number of help users of each knowledge point in the operation behavior path for each operation behavior path, and if the number of the largest number of help users obtained by the statistics is greater than a preset threshold, The knowledge point corresponding to the maximum number of help users is the knowledge point corresponding to the operation behavior path.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the present invention is directed to a method, apparatus (system), and computer program according to an embodiment of the present invention.
  • the flow chart and/or block diagram of the product is described. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG.
  • These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the application can be described in the general context of computer-executable instructions executed by a computer, such as Such as program modules.
  • program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types.
  • the present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network.
  • program modules can be located in both local and remote computer storage media including storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种识别用户潜在求助的知识点的方法及装置，其中，所述方法包括：获取待识别账户的操作行为路径（S101）；根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点（S102）；若查询到，将查询到的知识点确定为所述待识别账户潜在求助的知识点（S103）。通过上述过程可以对待识别账户可能需要求助的知识点进行识别，从而在识别到上述待识别账户可能需要求助的知识点之后，可以针对上述待识别账户（即潜在求助用户）提供与知识点对应的服务，提升客服系统的运行效率。

Description

识别用户潜在求助的知识点的方法及装置 技术领域
本申请涉及互联网技术领域，特别涉及一种识别用户潜在求助的知识点的方法及装置。
背景技术
目前，各种应用(Application，APP)均提供相应的客服系统。用户在使用应用APP的过程中，如果遇到需要求助的知识点时，可以通过与客服系统进行交互来获得与上述需要求助的知识点相对应的答案信息。与客服系统的交互方式例如包括：通过电话接入客服系统或通过应用的客户端接入客服系统。通常客服系统针对用户所求助的知识点，可以通过人工解答的方式或查询数据库的方式，获得与所述知识点对应的答案信息并反馈至用户。
在现有技术中，客服系统根据用户提供的求助的知识点，来获得与所述知识点对应的答案信息并反馈至用户。然而，随着应用的用户数的增长，可能出现同时接入客服系统的用户数超过预设阈值(客满)的情况，在此情况中，由于用户无法接入客服系统，则无法通过客服系统获取与所需求助的知识点对应的答案信息。
可见，目前需要提出一种可以识别用户潜在求助的知识点的技术，以便于向识别到的可能需要求助的潜在求助用户提供相应的服务。
发明内容
本申请实施例的目的是提供一种识别用户潜在求助的知识点的方法及装置，以解决现有技术中存在的问题。
为解决上述技术问题，本申请实施例提供的识别用户潜在求助的知识点的方法及装置是这样实现的：
一种识别用户潜在求助的知识点的方法，包括：
获取待识别账户的操作行为路径；
根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点；所述操作行为路径与知识点的对应关系是根据同一个操作行为路径对应不同知识点的统计数量来确定的；
若查询到，将查询到的知识点确定为所述待识别账户潜在求助的知识点。
一种识别用户潜在求助的知识点的装置，包括：
获取单元，获取待识别账户的操作行为路径；
查询单元，根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点；所述操作行为路径与知识点的对应关系是根据同一个操作行为路径对应不同知识点的统计数量来确定的；
确定单元，若查询到，将查询到的知识点确定为所述待识别账户潜在求助的知识点。
本申请实施例采用的上述至少一个技术方案能够达到以下有益效果：
本申请实施例通过获取待识别账户的操作行为路径，并根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点，从而在查询到与获取的所述操作行为路径对应的知识点之后，将查询到的知识点确定为所述待识别账户潜在求助的知识点。可见，本申请实施例通过上述过程可以对待识别账户可能需要求助的知识点进行识别，从而在识别到上述待识别账户可能需要求助的知识点之后，可以针对上述待识别账户(即潜在求助用户)提供与知识点对应的服务，提升客服系统的运行效率。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请中记载的一些实施例，对于本领域普通技术人员来讲， 在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的系统架构的示意图；
图2为本申请一实施例提供的识别用户潜在求助的知识点的方法的流程图；
图3示出了生成操作行为路径的一种示例；
图4A示出了统计的具有同一操作行为路径的并且针对同一知识点进行求助的账户的数量的一种示例；
图4B示出了统计的与每一操作行为路径对应的账户针对知识点进行求助的概率值的一种示例；
图4C示出了确定的操作行为路径和知识点的对应关系的一种示例；
图5为本申请一实施例提供的识别用户潜在求助的知识点的装置的结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本申请中的技术方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
一般地，将用户通过客户端或电话等方式，针对应用APP的知识点进行咨询(或求助)的事务称为“求助事务”。通常，在网络中发生的每一求助事务中，可包含“求助者”、“被求助者”及“求助的知识点”三个要素，其中，所述求助者是指用户终端(如手机)，所述被求助者是指应用APP的客服系统，所述求助的知识点是用户所求助的内容，通常知识点可以是客服系统预先划定的。举例而言，某应用APP包含若干个子功能块(如：“转账”、“信用卡还款”“红包”等)，针对每一子功能块(如：“信用卡还款”)，可以根据使用该子功 能块的用户可能会求助的内容或用户历史求助的内容，划定相应的一个或多个知识点(如：“信用卡还款进度”、“信用卡还款关闭”、“信用卡还款的限额”等)。也就是说，上述知识点可以代表一种类型的知识。
对于接入客服系统的用户而言，可以通过输入所需求助的内容的方式来获得与之对应的答案信息。例如：用户可以输入“信用卡还款进度”来匹配到与该知识点对应的答案信息。或者，用户可以在客服系统提供的页面上，选择所需求助的知识点。例如：用户可以先选中“信用卡”，再从与“信用卡”对应的多个知识点中选取所需求助的知识点。
本申请旨在提供一种可以识别用户潜在求助的知识点的技术，下文将详细介绍本技术方案。
图1为本申请实施例提供的系统架构的示意图。本申请一实施例中，该系统包括用户终端10、服务器20，用以实现所述用户终端10和所述服务器20的通信的网络30，以及与所述服务器20连接的第一数据库40和第二数据库50。所述第一数据库40和所述第二数据库50可以集成于所述服务器20或独立于服务器20。所述服务器可以是应用APP(社交应用或支付应用等)的服务平台。上述网络30可以包括局域网(“LAN”)、广域网(“WAN”)、内部网、互联网、移动电话网络、虚拟专用网(VPN)、蜂窝式或其它移动通信网络、蓝牙、NFC或其任何组合。每个上述终端10所基于的网络装置都可以包括服务器、台式计算机、膝上型计算机、平板计算机、智能手机、手持式计算机、个人数字助理(“PDA”)，或者其它任何的有线或无线处理器驱动装置。
本申请实施例中，上述各个终端10上可以安装有客户端应用软件，用户可以在上述终端10登录该应用APP的账户。一般地，服务器20可以将每个用户在使用应用APP的过程中的每一步操作行为都记录下来，从而形成与每个账户对应的日志数据。上述第一数据库40便是用以存储各个账户对应的日志数据。其中，所述日志数据可以包括用户针对特定功能或页面的操作行为及发生每一操作行为的时间戳。
用户的操作行为路径分析是互联网领域中的一类数据分析方法，它主要根据每一用户在应用App(或网站)中的日志数据来获取用户的操作行为路径，并依据用户的操作行为路径来分析用户在应用App(或网站)中各个模块的操作规律与特点，挖掘用户的访问或点击模式，进而实现一些特定的业务用途。本申请可以根据用户的操作行为路径来确定用户是否为潜在需要求助的用户。
一般地，用户在使用应用APP的过程中遇到的困难或问题时，随后便会通过接入客服系统来对遇到的困难或问题进行求助。可见，用户所需求助的内容(知识点)在一定程度上，可以与该用户一段特定时间段内(与求助事务对应的一段时间段)的操作行为路径相关。换句话说，用户在上述特定时间段内的操作行为路径，可以反映该用户可能遇到的困难或问题(知识点)是什么。需要说明的是，用户路径一般可由具有一定的先后次序的各个用户操作行为组成，例如，用户在某段时间段内，先后作出了“打开页面”、“将某商品放入购物车”及“付款”的操作，则该用户的操作行为路径为：“打开页面”→“将某商品放入购物车”→“付款”。当然，可以为每个操作行为设定相应的行为ID，则用户的操作行为路径可以例如为：a→b→c。
本申请实施例提供的方法中，需要针对每一种操作行为路径，预先统计具有该操作行为路径的并且针对每一知识点进行求助事务的账户的数量值，并将统计得到的结果存放于上述第二数据库50中，以作为用以识别用户潜在求助的知识点的数据依据。
值得说明的是，在图1所示的示例性的系统中，服务器20可以具备运营系统和客服系统的功能。然而，在其他实施例中，可以将运营系统服务器和客服系统服务器分开设置。
图2为本申请一实施例提供的识别用户潜在求助的知识点的方法的流程，本申请实施例中，该方法的执行主体可以是服务器，该方法包括如下步骤：
S101：获取待识别账户的操作行为路径。
图3示出了生成操作行为路径的一种示例，在该示例中，假设某应用APP 包括第一页面301、第二页面303和第三页面305，其中，假设上述第一页面301中包括功能块(如按键、或链接)A，上述第二页面303中包含功能块(如按键、或链接)B，上述第三页面305中包括功能块C。用户在点击上述功能块A时，该应用APP可以由第一页面301跳转至第二页面303，此后用户若在第二页面303中，点击功能块B后，该应用APP可以由第二页面303跳转至第三页面305，在第三页面305中，用户可以点击上述功能块C。在上述过程中，可以看出用户的操作行为包括三个，即：点击功能块A的点击行为、点击功能块B的点击行为和点击功能块C的点击行为，从而，按照操作行为发生的顺序，可以确定该用户(账户)的操作行为路径为：“x→y→z”。其中，x用以标识与功能块A对应的点击行为，y用以标识与功能块B对应的点击行为，z用以标识与功能块C对应的点击行为。
在上述步骤S101中，所述服务器可以获取由终端实时采集到的用户的操作行为路径。或者，在用户使用应用APP的过程中，所述服务器生成与用户的操作行为对应的行为日志，所述服务器可以根据生成的行为日志，获取用户的操作行为路径。
S102：根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点。其中，所述操作行为路径与知识点的对应关系是根据同一个操作行为路径对应不同知识点的统计数量来确定的。
在该步骤S102之前，需要预先确定操作行为路径与知识点的对应关系并存储。一般地，可以基于预先统计的若干用户的操作行为路径(历史)以及该若干用户历史求助的知识点，进行数据统计和分析，得到上述操作行为路径与知识点的对应关系。本申请一实施例，确定操作行为路径与知识点的对应关系的过程可以具体包括如下步骤：
步骤一：记录预设时间段内每一个用户的操作行为路径和求助的知识点。
对于发生的每一求助事务，记录在该求助事务中用户所求助的知识点。随后，获取在与该求助事务对应的预设时间段内产生的行为日志，以通过分析行 为日志，获得该求助用户的操作行为路径。最终，记录所述求助事务求助的知识点与获取的所述操作行为路径的对应关系。相应地，可以根据记录的所述求助事务求助的知识点与获取的所述操作行为路径的对应关系，统计针对同一知识点进行求助事务并且产生同一操作行为路径的用户数。对于客服系统(服务器20)来说，可以针对每一个由用户发起的求助事务，确定该用户的求助账户(若是通过电话的方式进行求助，则可通过电话号码来确定与当前电话号码进行关联的账户)。在确定求助账户之后，客服系统可以从上述第一数据库40中获取到当前求助账户的在一特定时间段内产生的日志数据，并依据获取到的日志数据，提取该求助账户在上述特定时间段内的操作行为路径。举例而言，若在某一求助事务中，账户a求助的知识点是Q1，则可以获取该账户a在求助事务发生的当天的0:00-24:00(特定时间段)内使用该应用APP所产生的日志数据，并依据所述日志数据，分别获得该账户a在当天的0:00-24:00内的一个或多个操作行为路径。其中，关于操作行为路径，可以指客户端与服务端的一次会话行为的完整路径。所述会话一般可以指从用户进入这个应用到退出这个应用的过程，在这一过程中，应用APP可以给予与本次回话对应的唯一的会话ID。
本申请实施例中，一般需要将上述预设时间段内产生的每一操作行为路径确定为需要记录的操作行为路径。继续举例来说，账户a求助的知识点是Q1，在该账户a发生该求助事务的当天0:00-24:00(特定时间段)内，假如该账户a的操作行为路径包括：“x→y→z”、“x→z”，则需要分别对上述操作行为路径：“x→y→z”和上述操作行为路径：“x→z”记录一次，并且将记录的上述操作行为路径与该账户a求助的知识点Q1进行对应。总之，对于每一个求助事务，均可以相应地记录用户所求助的知识点和用户在特定时间段内的操作行为路径的对应关系。
步骤二：对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量(如图4A所示)，将与最大求助用户数量对应的知识点作为与该 操作行为路径对应的知识点。
如图4A所示，举例而言，对于操作行为路径“A→C”，可以分别统计得到该操作行为路径“A→C”下的不同知识点对应的求助用户数量，例如：该操作行为路径“A→C”下的知识点Q3对应的求助用户数量为2946，该操作行为路径“A→C”下的知识点Q5对应的求助用户数量为1507，等等。其中，需要说明的是，对于不同的操作行为路径，统计得到的与该操作行为路径对应的知识点的数量和内容均可以不同，例如：与操作行为路径“A→C”对应的知识点有5个，与操作行为路径“B→E”对应的知识点为1个。
随着求助事务的不断发生，上述统计得到的每个操作行为路径下各个知识点的求助用户数量会(即上述图4A所示的数据表)不断累加，从而使得数据的准确性不断提升。此外，在上述图4A所示的数据表中，可以根据统计到的求助用户数量，选择性地保留部分数据。例如：将统计每一用户数从大到小进行排序，并选择性地保留排名前N(如：1000)位的数据；抑或，将统计的求助用户数量大于预设值(如：500)的数据进行保留，其余数据剔除；等等。通过对数据进行选择性的保留，可以节省存储资源。
值得一提的是，基于上述图4A所示的数据表中的统计数据，可以进一步计算得到与每一操作行为路径下不同知识点对应的概率值。如图4B所示，在该示例中，对于操作行为路径：“A→C”，可以查询得到预先统计的该操作行为路径下的知识点Q3对应的求助用户数量为：2946；该操作行为路径下的知识点Q5对应的求助用户数量为：1507；该操作行为路径下的知识点Q8对应的的求助用户数量为：1405；该操作行为路径下的知识点Q11对应的的求助用户数量为：618；该操作行为路径下的知识点Q9对应的的求助用户数量为：570。基于上述统计得到的求助用户数量，可以计算得到与操作行为路径“A→C”下的知识点Q3对应的概率值＝2946/(2946+1507+1405+618+570)＝41.8％；与操作行为路径“A→C”下的知识点Q5对应的概率值＝1507/(2946+1507+1405+618+570)＝21.4％；与操作行为路径“A→C”下的知识点Q8 对应的概率值＝1405/(2946+1507+1405+618+570)＝19.9％；等等。
本申请实施例中，对于每一操作行为路径，基于统计得到的该操作行为路径下各个知识点的求助用户数量(如图4A所示)，将与最大求助用户数量对应的知识点作为与该操作行为路径对应的知识点。
继续参照上述图4A所示的例子，对于操作行为路径：“A→C”而言，统计得到的与该操作行为路径对应的求助次数较多的知识点包括：Q3、Q5、Q8、Q11、Q9，具体地，与上述知识点：Q3、Q5、Q8、Q11、Q9对应的求助用户数量分别是：“2946”，“1507”，“1405”，“618”，“570”。一般地，若对某个知识点进行求助的用户数量越大，则表明具有上述操作行为路径的用户针对该知识点进行求助的几率越大。鉴于此，可以确定与上述操作行为路径：“A→C”对应的用户数：“2946”，“1507”，“1405”，“618”，“570”中的最大求助用户数量为：2946，最终，可以将与最大求助用户数量“2946”对应的知识点：Q3确定为与操作行为路径“A→C”对应的知识点。按照这样的原理，可以为每一操作行为路径确定一个与之对应的知识点(该知识点一般是具有该操作行为路径的用户最有可能需要求助的知识点)，从而得到操作行为路径和知识点的对应关系如图4C所示并存储。当然，需要说明的是，在最终生成的如图4C所示的数据表中，与每一操作行为路径对应的潜在求助的知识点可以包括多个，如，针对操作行为路径A→C”，若发现针对知识点Q3和Q5进行求助的用户数量非常接近，则可以确定与上述操作行为路径：“A→C”对应的知识点是Q3和Q5。
为了进一步提升确定的操作行为路径与知识点的对应关系的准确性，本申请具体实施例中，上述步骤二可以具体包括：对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量，如果统计得到的最大求助用户数量大于预设阈值，将与所述最大求助用户数量对应的知识点作为与该操作行为路径对应的知识点。通过设定上述预设阈值，并通过判断统计得到的最大求助用户数量是否大于预设阈值，可以过滤掉准确性不高的操作行为路径和知识点的对应关系。例如，对于某个操作行为路径，统计得到的该操作行为路径下 的不同知识点的统计数量分别是：“1”，“5”，“8”。其中，由于统计得到的上述最大求助用户数量：“8”较小，这存在一定的偶然性，若将最大求助用户数量：“8”对应的知识点与该操作行为路径进行对应，则会造成准确性不高。本发明实施例中，通过设定一个预设阈值(如：10000)，可以确保将较为准确的对应关系予以保留。
另外，上述步骤二还可以通过其他具体过程来实现。例如，在某些具体实施例中，上述步骤二可以具体包括：对于每一操作行为路径，判断与该操作行为路径对应的一个或多个所述求助用户数量是否大于或等于预设数量阈值，若是，则将大于或等于预设数量阈值的所述求助用户数量所对应的知识点与该操作行为路径进行对应。如上述图4A所示的例子，假设预设数量阈值是1500，则大于该预设数量阈值的数量是1507和2946，可以将操作行为路径：“A→C”与知识点Q3和Q5对应。
需要说明的是，确定知识点和操作行为路径的过程并不限于上述实施例。在本申请其他可行的实施例中，还可以通过人工方式来确定上述知识点和操作行为路径的对应关系。以图4B所示的数据表为例，在统计得到该数据表之后，还需要通过人工来判断与操作行为路径对应的知识点是否属于不匹配的情况，并对这种不匹配的数据进行剔除。举例而言，知识点Q1的内容是：“找不到信用卡还款查询按钮”，然而，统计得到的与该知识点Q1对应的某操作行为路径中包括：对信用卡还款查询按钮进行点击的操作行为，显然，该操作行为路径与上述知识点Q1的对应关系是不合理的，需要将这一对应关系进行剔除。
S103：若查询到，将查询到的知识点确定为所述待识别账户潜在求助的知识点。
本申请实施例中，基于预先生成的知识点和操作行为路径的对应关系(如图4C)，如果查询到与操作行为路径对应的知识点(该操作行为路径存在于预先统计的数据表中)则表明上述待识别账户是可能需要求助的潜在求助账户，可以将该知识点确定为所述待识别账户潜在求助的知识点。
在上述实施例介绍的方法中，本申请实施例通过获取待识别账户的操作行为路径，并根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点，从而在查询到与获取的所述操作行为路径对应的知识点之后，将查询到的知识点确定为所述待识别账户潜在求助的知识点。可见，本申请实施例通过上述过程可以对待识别账户可能需要求助的知识点进行识别，从而在识别到上述待识别账户可能需要求助的知识点之后，可以针对上述待识别账户(即潜在求助用户)提供与知识点对应的服务，提升客服系统的运行效率。
本申请的应用场景至少包括如下之一：
i.在客服系统无法接入时，通过识别潜在的求助账户和潜在求助的知识点，将与知识点对应的答案信息推送至所述待识别账户对应的终端上。或者，向所述终端推送相应的引导信息，以引导用户通过相应的途径来使用应用APP。
ii.如监测到某时段出现某个操作行为路径的用户数增多时，可以针对该操作行为路径，提前做好客服预警，如：及早在应用客户端上推送相应的公告信息，以提醒和引导用户。
iii.根据知识点和操作行为路径的对应关系，可以给产品设计环节提供数据参考。以上图3为例，如原先的产品设计中，用户在第一页面301中的功能块A被点击后，可以跳转至第二页面303。在产品使用过程中，若发现这样的产品设计会导致较多的用户出现求助的情况(或其他问题)，则可以通过对后续产品进行修改来客服上述情况，例如：修改后的产品中，用户在第一页面301中的功能块A被点击后，可以直接跳转至第三页面305。
上述统计得到知识点与操作行为路径的对应关系可以被存储于第二数据库50中以供查询。需要说明的是，本申请实施例可以依据上述图4C所示的数据表来查询与操作行为路径对应的知识点，进行识别待识别账户潜在求助的知 识点。在其他可行的实施例中，也可以依据上述图4A或图4B所示的数据表来查询与操作行为路径对应的知识点，在查询到与操作行为路径对应的多个知识点时，则可以通过相应的判断逻辑来确定识别待识别账户潜在求助的知识点。所述判断逻辑可以例如：将所述用户数中的最大用户数对应的知识点确定为识别待识别账户潜在求助的知识点。或者，判断所述用户数是否大于或等于预设数量阈值，若大于，则将大于或等于预设数量阈值的所述用户数所对应的知识点确定为识别待识别账户潜在求助的知识点，等等。
需要说明的是，以上各实施例所提供方法的各步骤的执行主体均可以是同一设备，或者，该方法也由不同设备作为执行主体。比如，步骤S101和步骤S102的执行主体可以为设备1，步骤S103的执行主体可以为设备2；又比如，步骤S101的执行主体可以为设备1，步骤S102和步骤S103的执行主体可以为设备2；等等。
图5为本申请一实施例提供的识别用户潜在求助的知识点的装置的结构示意图。需要说明的是，上述识别用户潜在求助的知识点的装置中的各个单元所能够实现的功能与以上介绍的识别用户潜在求助的知识点的方法中的各个步骤所能够实现的功能类似，故该识别用户潜在求助的知识点的装置的具体细节可以参照上述识别用户潜在求助的知识点的方法实施例的内容，本文不再予以赘述。本申请实施例中，所述识别用户潜在求助的知识点的装置可以以软件或软硬件结合的方式形成于所述服务器中，该识别用户潜在求助的知识点的装置100可以包括：获取单元101、查询单元102及确定单元103；其中：
获取单元101，获取待识别账户的操作行为路径。
查询单元102，根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点。其中，所述操作行为路径与知识点的对应关系是根据同一个操作行为路径对应不同知识点的统计数量来确定的。
确定单元103，若查询到，将查询到的知识点确定为所述待识别账户潜在求助的知识点。
在本申请实施例提供的上述装置中，本申请实施例通过获取待识别账户的操作行为路径，并根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点，从而在查询到与获取的所述操作行为路径对应的知识点之后，将查询到的知识点确定为所述待识别账户潜在求助的知识点。可见，本申请实施例通过上述过程可以对待识别账户可能需要求助的知识点进行识别，从而在识别到上述待识别账户可能需要求助的知识点之后，可以针对上述待识别账户(即潜在求助用户)提供与知识点对应的服务，提升客服系统的运行效率。
本申请一实施例中，所述装置还包括：
记录单元，记录预设时间段内每一个用户的操作行为路径和求助的知识点；
关系确定单元，对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量，将与最大求助用户数量对应的知识点作为与该操作行为路径对应的知识点。
本申请一实施例中，所述关系确定单元对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量，如果统计得到的最大求助用户数量大于预设阈值，将与所述最大求助用户数量对应的知识点作为与该操作行为路径对应的知识点。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本申请时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产 品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请可以在由计算机执行的计算机可执行指令的一般上下文中描述，例 如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本申请，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所述仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (6)

  1. 一种识别用户潜在求助的知识点的方法，其特征在于，包括：
    获取待识别账户的操作行为路径；
    根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点；所述操作行为路径与知识点的对应关系是根据同一个操作行为路径对应不同知识点的统计数量来确定的；
    若查询到，将查询到的知识点确定为所述待识别账户潜在求助的知识点。
  2. 根据权利要求1所述的方法，其特征在于，所述操作行为路径与知识点的对应关系是根据同一个操作行为路径对应不同求助知识点的统计数量来确定的，包括：
    记录预设时间段内每一个用户的操作行为路径和求助的知识点；
    对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量，将与最大求助用户数量对应的知识点作为与该操作行为路径对应的知识点。
  3. 根据权利要求2所述的方法，其特征在于，所述对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量，将最多数量的求助用户对应的知识点作为与该操作行为路径对应的知识点，包括：
    对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量，如果统计得到的最大求助用户数量大于预设阈值，将与所述最大求助用户数量对应的知识点作为与该操作行为路径对应的知识点。
  4. 一种识别用户潜在求助的知识点的装置，其特征在于，包括：
    获取单元，获取待识别账户的操作行为路径；
    查询单元，根据预先确定的操作行为路径与知识点的对应关系，查询与获取的所述操作行为路径对应的知识点；所述操作行为路径与知识点的对应关系是根据同一个操作行为路径对应不同知识点的统计数量来确定的；
    确定单元，若查询到，将查询到的知识点确定为所述待识别账户潜在求助的知识点。
  5. 根据权利要求4所述的装置，其特征在于，所述装置还包括：
    记录单元，记录预设时间段内每一个用户的操作行为路径和求助的知识点；
    关系确定单元，对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量，将与最大求助用户数量对应的知识点作为与该操作行为路径对应的知识点。
  6. 根据权利要求5所述的装置，其特征在于，所述关系确定单元对于每一个操作行为路径，统计该操作行为路径下各个知识点的求助用户数量，如果统计得到的最大求助用户数量大于预设阈值，将与所述最大求助用户数量对应的知识点作为与该操作行为路径对应的知识点。
PCT/CN2017/090312 2016-07-08 2017-06-27 识别用户潜在求助的知识点的方法及装置 WO2018006726A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610538724.0 2016-07-08
CN201610538724.0A CN107608979B (zh) 2016-07-08 2016-07-08 识别用户潜在求助的知识点的方法及装置

Publications (1)

Publication Number Publication Date
WO2018006726A1 true WO2018006726A1 (zh) 2018-01-11

Family

ID=60921581

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/090312 WO2018006726A1 (zh) 2016-07-08 2017-06-27 识别用户潜在求助的知识点的方法及装置

Country Status (3)

Country Link
CN (1) CN107608979B (zh)
TW (1) TWI686750B (zh)
WO (1) WO2018006726A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109636378B (zh) * 2018-10-31 2023-06-02 创新先进技术有限公司 账户识别方法和装置、电子设备
CN111581356B (zh) * 2020-05-15 2023-08-01 北京易数科技有限公司 用户行为路径分析方法和装置
CN115018482B (zh) * 2022-08-10 2023-01-13 杭州星犀科技有限公司 抢红包防作弊方法及装置、存储介质和终端

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102651052A (zh) * 2012-03-29 2012-08-29 陶杰 一种智能套餐化点菜方法
CN103412936A (zh) * 2013-08-21 2013-11-27 五八同城信息技术有限公司 一种基于数据挖掘和云计算服务的菜品推荐系统
CN104951447A (zh) * 2014-03-25 2015-09-30 上海市玻森数据科技有限公司 全网舆情监控系统

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI256006B (en) * 2004-12-27 2006-06-01 Ind Tech Res Inst Shopping assistant method and system
US8131731B2 (en) * 2007-12-27 2012-03-06 Microsoft Corporation Relevancy sorting of user's browser history
CN102681999A (zh) * 2011-03-08 2012-09-19 阿里巴巴集团控股有限公司 一种用户行为信息收集及信息发送方法及装置
CN103365844B (zh) * 2012-03-26 2016-05-11 阿里巴巴集团控股有限公司 一种提供搜索路径的方法及装置
CN104426881B (zh) * 2013-09-03 2019-06-11 深圳市腾讯计算机系统有限公司 一种检测恶意行为的方法及装置
CN103729446B (zh) * 2013-12-30 2018-02-02 广州猎豹网络科技有限公司 一种用户操作数据的处理方法、处理装置及服务器
CN105468630A (zh) * 2014-09-04 2016-04-06 口碑控股有限公司 提供用户信息的方法及装置
CN104881774A (zh) * 2015-05-18 2015-09-02 百度在线网络技术（北京）有限公司 一种自动建立日程的方法和装置
CN105242999B (zh) * 2015-09-22 2019-09-20 深圳怡化电脑股份有限公司 一种测试金融自助设备的方法及装置
CN105357054B (zh) * 2015-11-26 2019-01-29 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
CN105677813A (zh) * 2015-12-30 2016-06-15 五八有限公司 一种信息展示方法及装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102651052A (zh) * 2012-03-29 2012-08-29 陶杰 一种智能套餐化点菜方法
CN103412936A (zh) * 2013-08-21 2013-11-27 五八同城信息技术有限公司 一种基于数据挖掘和云计算服务的菜品推荐系统
CN104951447A (zh) * 2014-03-25 2015-09-30 上海市玻森数据科技有限公司 全网舆情监控系统

Also Published As

Publication number Publication date
CN107608979B (zh) 2020-09-22
CN107608979A (zh) 2018-01-19
TW201802730A (zh) 2018-01-16
TWI686750B (zh) 2020-03-01

Similar Documents

Publication Publication Date Title
US20200327551A1 (en) Resource transferring monitoring method and device
US8719178B2 (en) Prioritizing social activity postings
US10678894B2 (en) Disambiguation and authentication of device users
US11263401B2 (en) Method and system for securely storing private data in a semantic analysis system
WO2017067394A1 (zh) 客户服务方式的分配方法及系统
US10069891B2 (en) Channel accessible single function micro service data collection process for light analytics
Heymann et al. Turkalytics: analytics for human computation
US20110125826A1 (en) Stalking social media users to maximize the likelihood of immediate engagement
CN112671823A (zh) 基于机器学习的交互到联络中心代理的最优路由
WO2020164269A1 (zh) 基于用户群组的消息推送方法、装置及计算机设备
US20160110810A1 (en) Research Systems and Methods for Integrating Query Data and Individual User Profile
TW201502836A (zh) 用於透過通信網路提供資料處理方式清單的方法及裝置
US20150032746A1 (en) System and method for discovering and exploring concepts and root causes of events
TW201305944A (zh) 商品資訊投放方法和設備
WO2018045915A1 (zh) 调整业务语音播放顺序的方法及设备
US20200175522A1 (en) Predicting online customer service requests based on clickstream key patterns
WO2018006726A1 (zh) 识别用户潜在求助的知识点的方法及装置
US11431726B2 (en) Systems and methods for communication between a plurality of electronic devices based on subscriber access score
WO2019024497A1 (zh) 客户回访事件的生成方法、装置、终端设备及介质
US11121859B1 (en) Efficient incremental consensus for block commit in blockchain network
US9747175B2 (en) System for aggregation and transformation of real-time data
WO2015013554A1 (en) System and method for discovering and exploring concepts
US10664457B2 (en) System for real-time data structuring and storage
WO2013143417A1 (zh) 一种微博中的搜索方法、系统及计算机存储介质
CN112488860B (zh) 一种团单处理方法和系统

Legal Events

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

Ref document number: 17823538

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17823538

Country of ref document: EP

Kind code of ref document: A1