Information recommendation method of intelligent customer service, server and computer readable medium

A technology for intelligent customer service and information recommendation, applied in computing, digital data information retrieval, instruments, etc., can solve problems such as low prediction accuracy and deviation

Active Publication Date: 2019-07-16
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
18 Cites 7 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0006] However, in the existing technology, the user’s access behavior track to the website or application page before entering the intelligent customer service may be only the appearance, which has deviated from the question to be consulted. For example, the user’s visit to the website or application page before entering the intelligent customer service may be the user I want to try to solve the proble...
View more

Method used

The information recommendation method of the intelligent customer service of the present embodiment, when detecting that the user enters the intelligent customer service, by obtaining the characteristic parameter of the user entering the intelligent customer service; obtaining the user's business status; according to the user entering the characteristic parameter of the intelligent customer service and the user's business State, obtain the corresponding N target questions from the knowledge base; recommend N target questions to the user. Compared with the prediction proble...
View more

Abstract

The invention provides an information recommendation method of an intelligent customer service, a server and a computer readable medium. The method comprises: when it is detected that a user enters anintelligent customer service, acquring characteristic parameters of the user entering the intelligent customer service; acquiring a service state of a user; obtaining corresponding N target questionsfrom a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; and recommending the N target questions to the user. Compared with the problem of predicting according to the access behavior track of the user in the prior art, in the technical scheme of the invention, the N target problems are obtained according to the service state of the user and the characteristic parameters of the intelligent customer service, and the problem that the user wants to consult can be predicted more accurately, so that theaccuracy of predicting the problem is effectively improved. Moreover, the accuracy of the prediction problem is effectively improved, so that the operation cost of the user can be effectively reduced, and the use experience of the user can be effectively improved.

Application Domain

Digital data information retrievalForecasting +1

Technology Topic

Knowledge baseComputer science

Image

  • Information recommendation method of intelligent customer service, server and computer readable medium
  • Information recommendation method of intelligent customer service, server and computer readable medium
  • Information recommendation method of intelligent customer service, server and computer readable medium

Examples

  • Experimental program(1)

Example Embodiment

[0092] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
[0093] figure 1 It is a flowchart of Embodiment 1 of an information recommendation method for intelligent customer service of the present invention. Such as figure 1 As shown, the method for recommending information for intelligent customer service in this embodiment may specifically include the following steps:
[0094] 100. When it is detected that the user enters the smart customer service, obtain the characteristic parameters of the user to enter the smart customer service;
[0095] The executor of the method for recommending information for smart customer service in this embodiment is the server of the smart customer service. The server of the smart customer service can communicate with the website or App client or other platforms of the network company it serves, and provide services for online customer service from various portals of the network company.
[0096] In this embodiment, users entering smart customer service have certain characteristics. For example, the user can provide the online customer service portal on the webpage of the website to enter the smart customer service, or enter the smart customer service through the online customer service portal in the APP of the website, or even You can enter the smart customer service through the online customer service portal of other service platforms provided by this website. For example, if a wealth management website publishes multiple wealth management products and insurance products, the introduction page of each product will link to the entrance of smart customer service. Similarly, in the App, there will also be a link to the smart customer service portal on the introduction page of each product. Therefore, optionally, in this embodiment, the characteristic parameters for entering the smart customer service may include the entry location of the smart customer service. Normally, the user will usually enter the page of the product that has the related problem for which question the user wants to consult Intelligent customer service, therefore, the entry location of the intelligent customer service can more accurately predict the direction of the question that the user wants to consult. No matter which way the user enters the smart customer service, when the server of the smart customer service detects that the user enters the smart customer service, it can obtain the characteristic parameters of the user entering the smart customer service, such as the entrance location.
[0097] 101. Obtain the user's business status;
[0098] The service status of the user in this embodiment may be various stages in the service used by the user. For example, the business status of purchasing a service may include an unpurchased status, an inactive status after purchase, an activated status, and so on. For another example, the business status of a loan application may include the unapplied status, the pending approval status after the application, the approval pending loan status, the repayment status, the loan cancellation status, and so on. In a similar way, for each service, the status of the service can be determined according to the characteristics of the service.
[0099] For example, step 101 may specifically include: obtaining a user's identity; according to the user's identity, obtaining the user's business status from the user information database.
[0100] In this embodiment, the user consulting the smart customer service may be a logged-in user, and the user's identity may be the user's account. In the server of the intelligent customer service, a user information database can be stored. The user information database stores information of all users served by the website, for example, it can include the user's account number, contact information, and the business identification handled by the user, as well as each business's information. Business status. For example, for a loan application website, a user can apply for a loan through an App or website. The user information database stored in the server of the smart customer service of the website can record the information of each applied user, such as the user's account number, name, and Information such as contact information can also store the user's business status, such as application phase, approval phase, repayment phase, and so on. For different services, corresponding to the service status of different users, the examples are not repeated here. In addition, if a user applies for multiple services at the same time on a certain website, correspondingly, the service status of each service applied by the user can be obtained from the user information database of the smart customer service according to the user's identification.
[0101] When it needs to be clarified, for a user's identification, if the user's information is not yet stored in the user information database, it means that the user has not performed any related services. At this time, the service status can be identified as 0, that is, no Any business progress.
[0102] Optionally, in this embodiment, for a user who enters the smart customer service as a tourist, that is, a user who is not logged in or a user who has not registered an account, the service status identifier of the corresponding user may be 0, that is, there is no business progress.
[0103] 102. According to the characteristic parameters of the user entering the intelligent customer service and the user's business status, obtain the corresponding N target questions from the knowledge base;
[0104] 103. Recommend N target questions to users.
[0105] In this embodiment, when the corresponding N target questions are obtained from the knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the user's business status, the characteristic parameters of the user entering the intelligent customer service and the user's business status are obtaining N goals Two conditions of the problem. That is, the obtained N target questions need to meet these two conditions at the same time. When obtaining N questions, these two conditions can be first selected to meet the characteristic parameters of entering the intelligent customer service, or first to meet the user's business status. If the characteristic parameter of entering the intelligent customer service is the entry location of the intelligent customer service, these two conditions will prioritize the selection of candidate questions that meet the requirements of the entry location of the intelligent customer service, and then filter the obtained candidate questions that meet the user's business status The condition of the problem, and finally N target problems.
[0106] Optionally, step 102 in this embodiment "Acquire the corresponding N target questions from the knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the user's business status" may specifically include: according to the characteristic parameters of the user entering the intelligent customer service According to the user’s business status, obtain multiple candidate questions from the knowledge base; obtain the top N candidate questions with the highest consultation frequency from the multiple candidate questions as the corresponding N target questions. That is to say, if multiple candidate questions are directly used as the target question, the number of candidate questions may be large, resulting in insufficient key issues. In this embodiment, the historical consultation frequency can be obtained from multiple candidate questions. The top N high as the target problem.
[0107] It should be noted that if the number of candidate questions is less than N or equal to N, all candidate questions will be regarded as target questions. If the characteristic parameter of the user entering the intelligent customer service is the entry position of the user entering the intelligent customer service, when the corresponding multiple candidate questions are obtained from the knowledge base according to the characteristic parameter of the user entering the intelligent customer service and the user's business status, preferably, first According to the entry position of the intelligent customer service, obtain the corresponding several questions from the knowledge base, and then obtain the corresponding multiple candidate questions from the several questions according to the user's business status. Finally, obtain the top N candidate questions with the highest consultation frequency from multiple candidate questions.
[0108] The knowledge base of this embodiment may be created in advance based on all products included in the website served by the smart customer service and various types of questions under each product. For example, for an education installment product, there can be "Limit Application", "Limit Activation", "Lending Consultation", "Repayment Questions", and "Refund Consultation" and other types of questions below it. Among them, under "Repayment Issues" there can also be questions such as "How to repay", "Repayment amount", "Overdue repayment" and "Early repayment". Among them, under "How to repay" there are questions such as "APP repayment", "secret-free repayment" and "automatic repayment". In this way, the educational installment can be used as the first-level parent node, and "Limit Application", "Limit Activation", "Lending Consultation", "Repayment Questions", and "Refund Consultation" are divided into child nodes as the parent node "Education Staging" ; Further, "how to repay", "repayment amount", "overdue repayment" and "early repayment" can also be used as sub-nodes of "repayment issue"; "APP repayment" and "secret repayment" "And "automatic repayment" can also be used as sub-nodes of "how to repay". According to the parent-child relationship of the nodes of the above problems, a corresponding tree structured knowledge base can be created. According to the structure of the above knowledge base, a similar tree-like knowledge base can be created on each website.
[0109] Among them, "How to repay", "Repayment amount", "Overdue repayment", "Early repayment", "APP repayment", "Secret-free repayment" and "Automatic repayment" in the knowledge base can be In the lowest-level node of the tree structure of the knowledge base, each lowest-level node can store one or more knowledge points, each knowledge point includes a question and a corresponding answer under the corresponding node, each The attribute information corresponding to the knowledge point may include the consultation frequency of the knowledge point. And in the knowledge base, each node can be linked to multiple entry points into the intelligent customer service. In the same way, based on the problems in the nodes in the knowledge base, there is a corresponding relationship with the user's business status. Therefore, an information table can be established in advance to store the correspondence between the user's business status and the nodes in the knowledge base to facilitate subsequent follow-up Obtain target questions according to the user's business status. For problems with centralized consulting features, you can also count the peak consulting period in advance, and record the corresponding relationship between the peak consulting period of the problem and the corresponding node in the knowledge base in the information table, so as to facilitate the follow-up according to whether the consulting time hits the query Peak period, to get the target question.
[0110] In this embodiment, users in different business states will consult different questions. Take the online company that provides services as an example. For users who have not purchased the service, the business state is 0, and the questions the user consults will be more inclined to how to purchase and purchase. After enjoying the service, the cost of purchase and payment problems, etc. For users who have purchased the service but are in an inactive business state, the questions to be consulted will be more biased towards how to activate, activation precautions, and how to deal with various errors in activation. For users who have purchased the service and have activated the business status, the consultation questions will be more biased towards the problems in use, the problem of renewing the use of the follow-up, and the problem of refunding if the use is suspended in advance. That is to say, for each business state, there will be a matching node in the knowledge base, and multiple problems in multiple knowledge points in the node's subordinate nodes.
[0111] In the same way, for each entry point into the intelligent customer service, there will be a matching node in the knowledge base, as well as multiple questions in multiple knowledge points in the node's subordinate nodes. In this way, according to the user's entry location of the smart customer service and the user's business status, N target questions corresponding to the user's entry location of the smart customer service and the user's business status are obtained from the knowledge base. Then, the N target questions obtained can be recommended to the user through the interface through which the intelligent customer service communicates with the user. In this embodiment, according to the user’s entry point into the intelligent customer service and the user’s business status, the number of N target questions obtained from the knowledge base can be set according to actual needs, for example, 3 or 5 can be selected Or 10, or other integers.
[0112] Specifically, when the characteristic parameter of the user entering the intelligent customer service is the entry position of the user entering the intelligent customer service, in the above-mentioned embodiment, the step "the characteristic parameter of the user entering the intelligent customer service and the user's business status" is obtained from the knowledge base. Alternative questions" can specifically include the following steps:
[0113] (a1) According to the entry position of the user entering the intelligent customer service, multiple corresponding first nodes are obtained from the knowledge base;
[0114] (b1) Acquire at least one corresponding second node from a plurality of first nodes according to the user's business status and the correspondence between the user's business status in the pre-established information table and the nodes in the knowledge base;
[0115] (c1) Obtain multiple candidate questions from each second node in the knowledge base.
[0116] The above steps (a1)-(c1) realize the sequential screening of multiple conditions when obtaining multiple candidate questions. For example, first select the nodes that meet the requirements of the entry location for the user to enter the intelligent customer service, and obtain the corresponding multiple first nodes from the knowledge base; then according to the user's business status and the user's business status and knowledge in the pre-established information table The correspondence between the nodes in the library is used to screen at least one second node corresponding to the user's service state from the multiple first nodes. Among them, each first node and each second node may be a middle-level node in the knowledge base or may be the lowest-level node. If the second node is the lowest node in the knowledge base, the second node may include multiple knowledge points, and multiple questions can be obtained from the multiple knowledge points as candidate questions. If the second node is an intermediate node of the knowledge base, multiple corresponding questions can be obtained as candidate questions from the lowermost child node corresponding to the second node in the knowledge base.
[0117] Still further optionally, the characteristic parameters of the user entering the smart customer service in this embodiment also include consultation time; the granularity of the consultation time in this embodiment can be set according to the requirements of the product business. For example, for a loan repayment product with a monthly repayment cycle, the corresponding consultation time can be recorded at the granularity of days, and correspondingly the peak period of the consultation time is recorded at the granularity of days. If the 18th of each month is the repayment date, you can set the 13-18th of each month as the repayment consultation peak period. For consultations during this period, it is preferable to push N targets related to the repayment of the user’s business status problem.
[0118] Specifically, when the characteristic parameters of the user entering the smart customer service are the entry location and consultation time of the user entering the smart customer service, the step in the above embodiment "the characteristic parameters of the user entering the smart customer service and the user’s business status, obtain the corresponding information from the knowledge base The multiple alternative questions" can include the following steps:
[0119] (a2) According to the entry position of the user entering the intelligent customer service, multiple corresponding first nodes are obtained from the knowledge base;
[0120] (b2) According to the user's business status and the correspondence between the user's business status in the pre-established information table and the nodes in the knowledge base, obtain at least one corresponding second node from the plurality of first nodes;
[0121] (c2) According to the corresponding relationship between the consulting peak period in the information table and the nodes in the knowledge base, obtain the consulting peak period corresponding to each second node;
[0122] (d2)) According to the consultation time, obtain at least one third node in the consultation peak period hit by the consultation time from at least one second node;
[0123] (e2) Obtain multiple preset questions corresponding to the corresponding consultation peak period from each third node in the knowledge base as multiple candidate questions.
[0124] The difference between the steps (a2)-(e2) of this embodiment and the above-mentioned steps (a1)-(c1) is that when multiple candidate questions are obtained in this embodiment, the user enters the smart customer service entry position and the user’s On the basis of business status, time for consultation on screening conditions has been added. The priority order of the screening conditions is as follows: first select multiple first nodes that meet the user's entrance location conditions for entering the intelligent customer service, and then select multiple second nodes that meet the user's business status conditions from the multiple first nodes that are selected. Then, at least one third node that meets the consultation time condition is selected from the obtained multiple second nodes. According to the consultation time, when screening at least one third node from multiple second nodes, you can first obtain the consultation peak period of each second node, and then judge whether the current consultation time hits the consultation peak period of some second nodes If it hits, the corresponding second node is selected as the third node. Otherwise, if it misses, discard the second node. It can be understood that the knowledge points stored in the third node or the lowest-level child node downstream of the third node are all questions and answers corresponding to the consultation peak period. For example, the 18th of each month is the repayment date, and the 13-18th of each month is the peak repayment consultation period. For consultations during this consultation peak period, it can be assumed that all consultations about repayment related issues can be Store the knowledge points of repayment-related issues in the node corresponding to the consultation peak period or the lowermost node downstream. In this way, when the third node is subsequently screened, if the consultation time hits the consultation peak period, the node can be screened out. Multiple questions related to repayment can be obtained as alternative questions.
[0125] For example, for a loan repayment product with a monthly cycle, multiple alternative questions related to repayment can be obtained in the above manner, and finally the top N alternative questions with the highest consultation frequency are obtained from the multiple alternative questions as the corresponding N target questions. Similarly, if the number of multiple alternative questions related to repayment is less than N or equal to N, all multiple alternative questions related to repayment can be regarded as corresponding target questions.
[0126] In this embodiment, for inquiries outside the peak period of repayment, the corresponding N target questions are obtained from the knowledge base according to the user’s entry point into the smart customer service and the user’s business status. The detailed implementation process is the same as above. Repeat it again.
[0127] In the above embodiment, the consultation time is recorded at the granularity of days. In practical applications, for other products, it can be based on the periodic characteristics of the product itself. For example, every day is a cycle, and the granularity of the consultation time can be hours. For insurance products that are renewed every year, each year is a cycle, and the granularity of the consultation time can be months, etc., and I will not repeat them here.
[0128] Further optionally, in this embodiment, after step 103 "recommend N target questions to the user", it may further include: if the first target question among the N target questions is selected by the user, obtaining the corresponding first target question Answer: feedback the answer corresponding to the first target question to the user. Specifically, the answer corresponding to the first target question is obtained from the knowledge base and fed back to the user.
[0129] Further optionally, before step 102 of this embodiment "acquire the corresponding N target questions from the knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the user's business status", the following steps may also be included:
[0130] (a3) Create a tree-like knowledge base based on the category of products served by the smart customer service and the hierarchical relationship of the problem categories in each product;
[0131] (b3) According to the historical consultation information of intelligent customer service, mine all the questions of each node in the knowledge base, the corresponding answers to each question, and the consultation frequency of each question;
[0132] (c3) Store each question, corresponding answer, and corresponding consultation frequency on the corresponding node in the knowledge base;
[0133] Each question and the corresponding answer can be stored as a knowledge point in the corresponding node, and the consultation frequency can be stored as the attribute information of the knowledge point in the attribute of the knowledge point.
[0134] (d3) According to the historical consulting information of intelligent customer service, mining the business status of the user corresponding to each problem of each node in the consulting knowledge base, the entry location of the intelligent customer service, and the consulting peak period of problems with centralized consulting characteristics;
[0135] (e3) Hook the corresponding entry point into the intelligent customer service on each node in the knowledge base;
[0136] (f3) According to the user's business status corresponding to each problem of each node in the mining knowledge base, obtain the correspondence between the user's business status and the node in the knowledge base, and store it in the information table;
[0137] (g3) According to the peak consulting period of the problems with the centralized consulting characteristics excavated, the corresponding relationship between the consulting peak period of the problems with the centralized consulting characteristics and the nodes in the knowledge base is obtained and stored in the information table.
[0138] The above steps (a3)-(g3) are the process of creating a knowledge base and establishing an information table based on the knowledge base, so that it can be obtained from the knowledge base according to the screening conditions, combined with the knowledge base and the information table established according to the knowledge base. Corresponding target question. For the process of creating the tree structure of the knowledge base, reference may be made to the explanation of the above related embodiments. When generating and storing knowledge points stored in the lowest node in the knowledge base, it is necessary to collect historical consultation information of the intelligent customer service. For example, the historical consultation information of this embodiment not only includes the questions and answers pushed by the intelligent customer service for the user. At the same time, it also includes the user's answer to the user's question manually by the intelligent customer service staff who did not solve their own problems in the questions and answers pushed by the intelligent customer service, but the questions entered by themselves. That is, in this embodiment, the server of the intelligent customer service can also collect the question input by the user and the answer of the manual customer service to answer the question, thereby enriching the question information of the intelligent customer service. Then the intelligent customer service history consulting information, mining all the questions of various categories in the intelligent customer service and the corresponding answer to each question. The category in this embodiment may be a category of smart customer service. For example, a certain website includes 5 products, each product may correspond to a category, and each category has corresponding questions that may be consulted. Further, for each product, there are various sub-categories, such as pre-sales (corresponding to the business status of the service not purchased), activation, payment, repayment, and other sub-categories. Each sub-category also has a corresponding possibility Questions to be consulted; further, for each sub-category of pre-sales, activation, payment, and repayment, further sub-categories may be included. By analogy, the category of the product served by the smart customer service and all the hierarchical categories in each product can be obtained. According to the categories of each level, a tree-like knowledge base structure can be generated. Then, each knowledge point corresponding to each category, that is, the question, the corresponding answer, and attribute information such as the consultation frequency, can be stored in a corresponding node at the bottom of the knowledge base. For example, the knowledge points of the educational staging product in the above embodiment are stored in the lowest-level node corresponding to the educational staging. Among them, the knowledge points corresponding to the category of "repayment issues" under the education installment are stored in the nodes corresponding to the categories of "how to repay", "repayment amount", "overdue repayment" and "early repayment"; further, For example, the knowledge points corresponding to the "How to repay" category are stored in the knowledge points corresponding to the categories of "APP Repayment", "Password Repayment" and "Automatic Repayment". According to the above method, each knowledge point corresponding to each category can be stored in the corresponding lowest-level node according to the corresponding relationship of the category at each level in the knowledge base.
[0139] In addition, according to the historical consulting information of the intelligent customer service, it is also possible to mine the business status of the user corresponding to each problem of each node in the consulting knowledge base, the entry location of the intelligent customer service, and the consulting peak period of the problem with the centralized consulting feature. Then, according to the information mined, the corresponding entry location for entering the smart customer service is linked to each node, that is, the corresponding relationship between each node and the corresponding entry location for entering the smart customer service is established. In this embodiment, one node can correspond to one , Two or more entrances into the intelligent customer service. Then, according to the mined information, the corresponding relationship between the user's business status and the nodes in the knowledge base is established. In this embodiment, the corresponding relationship can be stored in an information table. In the information table, the user's business can be directly stored. The corresponding relationship between the status identifier and the node identifier in the knowledge base is used to identify the corresponding relationship between the user's business status and the node in the knowledge base. At the same time, in the information table, the consulting peak period of some nodes can also be stored. Since the problems in some knowledge points have the characteristics of centralized consulting, in this embodiment, the consulting peak period and the problems with centralized consulting characteristics can be established. The corresponding relationship of the corresponding node in the knowledge base is stored in the information. In other words, some nodes in the information table still have corresponding consultation peak periods. The problems in the knowledge points in the nodes corresponding to the consulting peak period have the characteristics of centralized consulting. In the above manner, the knowledge base and the information table are established. Subsequently, according to the knowledge base and the information table, the corresponding target question can be obtained from the knowledge base in the manner of the foregoing embodiment.
[0140] The information recommendation method of the smart customer service of this embodiment detects that the user enters the smart customer service by acquiring the characteristic parameters of the user entering the smart customer service; acquiring the user’s business status; according to the characteristic parameters of the user entering the smart customer service and the user’s business status, Obtain the corresponding N target questions in the knowledge base; recommend N target questions to the user. Compared with the problem of predicting the trajectory of the user's access behavior in the prior art, the technical solution of this embodiment obtains N target problems according to the user's business status and the characteristic parameters of entering the intelligent customer service, which can more accurately predict the user's desire Consultation issues, thereby effectively improving the accuracy of predicting issues. Moreover, because the accuracy of the prediction problem is effectively increased, the user's operating cost can be effectively reduced, and the user's experience can be effectively improved.
[0141] figure 2 It is a structural diagram of the first embodiment of the intelligent customer service server of the present invention. Such as figure 2 As shown, the intelligent customer service server of this embodiment may specifically include: a characteristic parameter acquisition module 10, a business status acquisition module 11, a question acquisition module 12, and a recommendation module 13.
[0142] The characteristic parameter acquisition module 10 is used to acquire characteristic parameters of the user entering the intelligent customer service when detecting that the user enters the intelligent customer service;
[0143] The business state acquisition module 11 is used to acquire the business state of the user;
[0144] The question obtaining module 12 is configured to obtain corresponding N target questions from the knowledge base according to the characteristic parameters of entering the intelligent customer service obtained by the characteristic parameter obtaining module 10 and the user's business state obtained by the service state obtaining module 11; N is a positive integer;
[0145] The recommendation module 13 is used to recommend the N target questions acquired by the question acquisition module 12 to the user.
[0146] In the smart customer service server of this embodiment, the implementation principle and technical effect of the intelligent customer service information recommendation by using the above-mentioned modules are the same as those of the above-mentioned related method embodiments. For details, please refer to the record of the above-mentioned related method embodiments, which will not be omitted Repeat.
[0147] image 3 It is a structural diagram of the second embodiment of the intelligent customer service server of the present invention. Such as image 3 As shown, the intelligent customer service server of this embodiment is figure 2 On the basis of the technical solution of the illustrated embodiment, the technical solution of the present invention is further described in more detail.
[0148] Such as image 3 As shown, the intelligent customer service server of this embodiment further includes:
[0149] The answer obtaining module 14 is used to obtain the answer corresponding to the first target question if the first target question among the N questions is selected by the user:
[0150] The recommendation module 13 is also used to feed back the answer corresponding to the first target question acquired by the answer acquiring module 14 to the user.
[0151] Further optionally, in the server of the intelligent customer service of this embodiment, the service status obtaining module 10 is specifically configured to:
[0152] Obtain the user's identity;
[0153] According to the user's identification, the user's business status is obtained from the user information database.
[0154] Further optionally, in the server of the intelligent customer service of this embodiment, the question acquisition module 12 is specifically configured to:
[0155] According to the characteristic parameters of the user entering the intelligent customer service acquired by the characteristic parameter acquiring module 10 and the business status of the user acquired by the business status acquiring module 11, multiple corresponding candidate questions are acquired from the knowledge base;
[0156] Obtain the top N candidate questions with the highest consultation frequency from multiple candidate questions as the corresponding N target questions.
[0157] Further optionally, in the server of the smart customer service of this embodiment, the characteristic parameter obtaining module 10 is specifically configured to obtain the entry location of the user into the smart customer service;
[0158] Correspondingly, the question acquisition module 12 is specifically used for:
[0159] According to the entry position of the user entering the intelligent customer service acquired by the characteristic parameter acquisition module 10, corresponding multiple first nodes are acquired from the knowledge base;
[0160] According to the user’s business status acquired by the business status acquiring module 11 and the correspondence between the user’s business status in the pre-established information table and the nodes in the knowledge base, acquire at least one corresponding second node from the multiple first nodes. node;
[0161] Obtain multiple corresponding candidate questions from each second node in the knowledge base.
[0162] Further optionally, in the intelligent customer service server of this embodiment, the characteristic parameter obtaining module 11 is specifically configured to obtain the entrance location and consultation time of the user entering the intelligent customer service;
[0163] Correspondingly, the question acquisition module 12 is specifically used for:
[0164] According to the entry position of the user entering the intelligent customer service acquired by the characteristic parameter acquisition module 10, corresponding multiple first nodes are acquired from the knowledge base;
[0165] According to the user’s business status acquired by the business status acquiring module 11 and the correspondence between the user’s business status in the pre-established information table and the nodes in the knowledge base, acquire at least one corresponding second node from the multiple first nodes. node;
[0166] According to the corresponding relationship between the consulting peak period in the information table and the nodes in the knowledge base, obtain the consulting peak period corresponding to each second node;
[0167] According to the consultation time, obtain at least one third node in the consultation peak period hit by the consultation time from the at least one second node;
[0168] Obtain multiple corresponding candidate questions from each third node in the knowledge base.
[0169] Further optionally, such as image 3 As shown, the intelligent customer service server of this embodiment further includes:
[0170] The creation module 15 is used to create a tree structure knowledge base according to the category of the product served by the intelligent customer service and the hierarchical relationship of the problem category in each product;
[0171] The mining module 16 is used to mine all the questions of each node in the knowledge base created by the creation module 15, the answers corresponding to each question, and the consultation frequency of each question according to the historical consultation information of the intelligent customer service;
[0172] The storage module 17 is used to store each question, the corresponding answer, and the corresponding consultation frequency on the corresponding node in the knowledge base;
[0173] The mining module 16 is also used to mine the business status of the user corresponding to each problem of each node in the knowledge base created by the consultation creation module 15 and the entry position of the user to enter the smart customer service according to the historical consultation information of the intelligent customer service, as well as those with centralized consultation characteristics Peak consultation period for issues;
[0174] The storage module 17 is also used to hook the corresponding entry positions for entering the intelligent customer service on each node in the knowledge base;
[0175] The storage module 17 is also used to obtain the corresponding relationship between the user's business state and the node in the knowledge base according to the user's business state corresponding to each problem of each node in the mining knowledge base, and store it in the information table;
[0176] The storage module 17 is also used to obtain the corresponding relationship between the peak consulting period of the problem with the centralized consulting characteristic and the node in the knowledge base according to the peak consulting period of the question with the centralized consulting characteristic mined, and store it in the information table.
[0177] Correspondingly, the question acquisition module 12 is configured to obtain the corresponding N information from the knowledge base created by the creation module 15 according to the characteristic parameters of entering the intelligent customer service acquired by the characteristic parameter acquisition module 10 and the business status of the user acquired by the business status acquisition module 11 Target question.
[0178] In the smart customer service server of this embodiment, the implementation principles and technical effects of the intelligent customer service information recommendation by using the above-mentioned modules are the same as those of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be omitted here. Go into details.
[0179] Figure 4 It is a structural diagram of an embodiment of a server device of the present invention. Such as Figure 4 As shown, the server device in this embodiment includes: one or more processors 30 and a memory 40. The memory 40 is used to store one or more programs. When one or more programs stored in the memory 40 are One processor 30 executes, so that one or more processors 30 implement the above Figure 1-Figure 3 The information recommendation method of the smart customer service of the illustrated embodiment. Figure 4 In the illustrated embodiment, multiple processors 30 are included as an example.
[0180] E.g, Figure 5 This is an example diagram of a server device provided by the present invention. Figure 5 A block diagram of an exemplary server device 12a suitable for implementing embodiments of the present invention is shown. Figure 5 The server device 12a shown is only an example, and should not bring any limitation to the function and scope of use of the embodiment of the present invention.
[0181] Such as Figure 5 As shown, the server device 12a is represented in the form of a general-purpose computing device. The components of the server device 12a may include, but are not limited to: one or more processors 16a, a system memory 28a, and a bus 18a connecting different system components (including the system memory 28a and the processor 16a).
[0182] The bus 18a represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any bus structure among multiple bus structures. For example, these architectures include but are not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and peripheral component interconnection ( PCI) bus.
[0183] The server device 12a typically includes a variety of computer system readable media. These media may be any available media that can be accessed by the server device 12a, including volatile and non-volatile media, removable and non-removable media.
[0184] The system memory 28a may include a computer system readable medium in the form of volatile memory, such as random access memory (RAM) 30a and/or cache memory 32a. The server device 12a may further include other removable/non-removable, volatile/non-volatile computer system storage media. For example only, the storage system 34a can be used to read and write non-removable, non-volatile magnetic media ( Figure 5 Not shown, usually referred to as "hard drive"). in spite of Figure 5 It is not shown in, it can provide a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and a removable non-volatile disk (such as CD-ROM, DVD-ROM or other optical Media) CD-ROM drive for reading and writing. In these cases, each drive can be connected to the bus 18a through one or more data media interfaces. The system memory 28a may include at least one program product, the program product having a set (for example, at least one) of program modules, and these program modules are configured to execute the foregoing Figure 1-Figure 3 Function of each embodiment.
[0185] A program/utility 40a having a set of (at least one) program module 42a can be stored in, for example, the system memory 28a. Such program module 42a includes, but is not limited to, an operating system, one or more application programs, and others. Program modules and program data, each of these examples or some combination may include the realization of a network environment. The program module 42a usually executes the above described in the present invention Figure 1-Figure 5 Functions and/or methods in various embodiments.
[0186] The server device 12a may also communicate with one or more external devices 14a (such as a keyboard, pointing device, display 24a, etc.), and may also communicate with one or more devices that enable users to interact with the server device 12a, and/or communicate with Any device (such as a network card, modem, etc.) that enables the server device 12a to communicate with one or more other computing devices. This communication can be performed through an input/output (I/O) interface 22a. In addition, the server device 12a may also communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 20a. As shown in the figure, the network adapter 20a communicates with other modules of the server device 12a through the bus 18a. It should be understood that although not shown in the figure, other hardware and/or software modules can be used in conjunction with the server device 12a, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.
[0187] The processor 16a executes various functional applications and data processing by running programs stored in the system memory 28a, for example, to implement the information recommendation method for intelligent customer service shown in the foregoing embodiment.
[0188] The present invention also provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the intelligent customer service information recommendation method shown in the above-mentioned embodiment is realized.
[0189] The computer-readable medium of this embodiment may include the above Figure 5 The RAM 30a, and/or the cache memory 32a, and/or the storage system 34a in the system memory 28a in the illustrated embodiment.
[0190] With the development of science and technology, the dissemination of computer programs is no longer limited to tangible media. It can also be downloaded directly from the Internet or obtained by other means. Therefore, the computer-readable media in this embodiment may include not only tangible media, but also intangible media.
[0191] The computer-readable medium of this embodiment may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.
[0192] The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
[0193] The program code contained on the computer-readable medium can be transmitted by any suitable medium, including, but not limited to, wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0194] The computer program code for performing the operations of the present invention can be written in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
[0195] In the several embodiments provided by the present invention, it should be understood that the disclosed system, device, and method may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation.
[0196] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
[0197] In addition, the functional units in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.
[0198] The above-mentioned integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor execute the method described in the various embodiments of the present invention. Part of the steps. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .
[0199] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the present invention Within the scope of protection.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products