CN111917804B

CN111917804B - Service channel recommendation method, system and equipment

Info

Publication number: CN111917804B
Application number: CN201810776727.7A
Authority: CN
Inventors: 刘乾
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-07-13
Filing date: 2018-07-13
Publication date: 2022-11-15
Anticipated expiration: 2038-07-13
Also published as: CN111917804A

Abstract

The embodiment of the application provides a service channel recommendation method, system and device. The method comprises the following steps: acquiring multi-source data information related to a user; selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information; and recommending the first service channel to the user. The technical scheme provided by the embodiment of the application can realize the personalized recommendation of the service channel, not only can reduce the user time and improve the user experience, but also can optimize the distribution of service resources.

Description

Service channel recommendation method, system and equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to a service channel recommendation method, system, and device.

Background

Currently, various types of platforms, for example: the e-commerce platform and the financial platform provide various services for users, and meanwhile, need to provide customer service for the users so as to improve user experience.

When a user logs in a platform and needs to seek customer service when encountering problems, one service channel needs to be selected from service channels such as intelligent robot customer service, artificial customer service and Interactive Voice Response (IVR) hot line provided by the platform to seek the customer service. The selection mode of the service channel easily causes the switching of the user among a plurality of service channels, wastes the time and the energy of the user and easily causes the problem of uneven distribution of platform service resources.

Disclosure of Invention

In view of the above problems, the present application is proposed to provide a service channel recommendation method, system and apparatus that solve the above problems or at least partially solve the above problems.

Accordingly, in one embodiment of the present application, a service channel recommendation method is provided. The method comprises the following steps:

acquiring multi-source data information related to a user;

selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information;

recommending the first service channel to the user.

In yet another embodiment of the present application, a service channel recommendation method is provided. The method is suitable for the client and comprises the following steps:

responding to a service request event triggered by a user, and acquiring a first service channel recommended for the user from a service end;

displaying the first service channel as a recommended channel;

wherein the first service channel is selected from a plurality of service channels based on multi-source profile information associated with the user.

In yet another embodiment of the present application, a service channel recommendation method is provided. The method is suitable for a server and comprises the following steps:

after receiving a service request sent by a client used by a user, acquiring multi-source data information related to the user;

and feeding back the first service channel to the client so that the client displays the first service channel as a recommended channel.

In yet another embodiment of the present application, a service channel recommendation system is provided. The system, comprising:

the client is used for responding to a service request event triggered by a user and sending a recommendation request to the server; receiving a first service channel recommended by the server for the user; displaying the first service channel as a recommended channel;

the server is used for acquiring multi-source data information related to a user after receiving a service request sent by a client used by the user; selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information; and feeding back the first service channel to the client.

In yet another embodiment of the present application, an electronic device is provided. The electronic device includes: a first memory and a first processor, wherein,

the first memory is used for storing programs;

the first processor, coupled with the first memory, to execute the program stored in the first memory to:

acquiring multi-source data information related to a user;

recommending the first service channel to the user.

In yet another embodiment of the present application, a client device is provided. The client device includes: a second memory and a second processor, wherein,

the second memory is used for storing programs;

the second processor, coupled to the second memory, is configured to execute the program stored in the second memory to:

displaying the first service channel as a recommended channel;

In yet another embodiment of the present application, a server device is provided. The server side equipment comprises: a third memory and a third processor, wherein,

the third memory is used for storing programs;

the third processor, coupled to the third memory, is configured to execute the program stored in the third memory to:

and feeding back the first service channel to the client so that the first service channel is displayed as a recommended channel by the client.

According to the technical scheme provided by the embodiment of the application, when a user wants to solve the problem through customer service, a proper service channel is recommended to the user through analysis of multi-source data information related to the user, so that the problem of the user is solved quickly. The technical scheme provided by the embodiment of the application can realize the personalized recommendation of the service channel, not only can reduce the user time and improve the user experience, but also can optimize the distribution of service resources.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic flowchart of a service channel recommendation method according to an embodiment of the present application;

FIG. 2 is a block diagram illustrating a service channel recommendation system according to another embodiment of the present application;

FIG. 3 is a flowchart illustrating a service channel recommendation method according to another embodiment of the present application;

FIG. 4 is a flowchart illustrating a service channel recommendation method according to another embodiment of the present application;

FIG. 5 is a flowchart illustrating an example of a service channel recommendation method according to another embodiment of the present application;

fig. 6 is a block diagram illustrating a service channel recommendation apparatus according to an embodiment of the present application;

fig. 7 is a block diagram illustrating a service channel recommendation apparatus according to another embodiment of the present application;

fig. 8 is a block diagram illustrating a service channel recommendation apparatus according to another embodiment of the present application;

fig. 9 is a block diagram of an electronic device according to an embodiment of the present application;

fig. 10 is a block diagram of a client device according to an embodiment of the present application;

fig. 11 is a block diagram of a server device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

In some of the flows described in the specification, claims, and above-described figures of the present application, a number of operations are included that occur in a particular order, and these operations may be performed out of order or in parallel as they occur herein. The sequence numbers of the operations, e.g., 101, 102, etc., are used merely to distinguish between the various operations, and do not represent any order of execution per se. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit the types of "first" and "second".

In the existing large platforms, when a user needs to seek customer service when encountering problems, the user can select a service channel for solving the problems from service channels such as intelligent robot customer service, artificial customer service, IVR hot lines and the like. The user's self-selection has great randomness, some due to personal use habits, some due to service experiences provided by past service channels, and the like. A user selects a service channel by himself, so that part of the service channels are easily in an exploded state and part of the service channels are in an idle state. Sometimes, the service channel selected by the user is not suitable for the user, for example: the problems encountered by the user can be solved by the intelligent robot customer service, but the user does not select the manual customer service needing waiting or needs to interact with multiple rounds of IVR hot lines, so that a great deal of waste of time and energy of the user is inevitably caused, and the user experience is seriously influenced. Before a user communicates with a platform customer service, a service channel suitable for the user can be calculated according to data relevant to the user, so that the time of the user can be reduced, and the distribution of platform service resources can be optimized. The technical scheme provided by the application is realized based on the thought, and the user is analyzed according to the relevant data of the user, so that a proper service channel is recommended for the user.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Fig. 1 shows a flowchart of a service channel recommendation method according to an embodiment of the present application. The execution main body of the method provided by the embodiment of the application can be a server side or a user side client side. The server may be a universal server, a cloud, or a virtual server, and the like, which is not specifically limited in this embodiment of the application. The user-side client may be hardware integrated on the terminal and having an embedded program, may also be application software installed in the terminal, and may also be tool software embedded in an operating system of the terminal, which is not limited in this embodiment of the present application. The terminal can be any terminal equipment including a mobile phone, a tablet personal computer, intelligent wearable equipment and the like. Specifically, as shown in fig. 1, the method provided in this embodiment includes:

101. and acquiring multi-source data information related to the user.

102. And selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information.

103. And recommending the first service channel to the user.

In the above 101, the multi-source data information includes, but is not limited to, at least two of user behavior data, user positioning information, hot spot events, and user source interface information for seeking services.

Wherein the user behavior data includes but is not limited to at least one of the following: historical common service channels, user order information, and historical service contents provided by service channels requested by users. The historical common service channel can be a service channel which is used by the user with a historical use frequency larger than or equal to a first frequency threshold value or a service channel which is used by the user with a use frequency larger than or equal to a second frequency threshold value in a specific historical period. The specific historical period may be the last year, the last month, or the last week, which is not specifically limited in the embodiments of the present application. The user order information may include: time of placing an order, order details, order number, and the like. The order details may vary from application scenario to application scenario. For example: on the ticket ordering platform, the order details may include: flight information, boarding time, ticket fees, etc.; on an e-commerce or take-away platform, the order details may include: commodity name, commodity price, merchant information, etc. In the customer service application scenario, the service content historically requested by the user to be provided by the service channel may be a question that the user has historically asked.

The user Location information may be obtained through an existing GPS or LBS (Location Based Service) technology.

A hotspot event refers to an event that causes a large number of queries, or complaints within a short time, such as: a problem occurs in a certain product on a platform, a large number of user complaints are caused in a certain time period, and the event is called a hot event; the weather such as snowstorm or fog causes flight delay or even cancellation, resulting in a large number of users querying or asking for relevant information, such events are also called hot events.

The service content of most clients capable of providing services for users is more and more extensive. For example, a user may book a hotel, purchase an air ticket, train ticket, etc. using a client APP (Application). Suppose that user a purchases a ticket through APP. However, when the airplane cannot take off due to heavy fog, the user wants to refund the ticket. The user can enter the air ticket order interface through the APP to apply for returning the air ticket. Before applying for a refund, when a user wants to consult a question related to the refund, the user can seek to consult the question related to the refund by touching a control, such as an 'online customer service' control, on the air ticket order interface. At this time, the user seeks service source interface information, namely, an air ticket order interface. In the embodiment of the present application, "the user seeks service source interface information" is used as one of the multi-source data information to be used as a basis for recommending a service channel for the user, and the reason is that: the service scene of the current possible consultation problem of the user can be analyzed by searching the service source interface information by the user; problems and the like which are possibly met by the user can be estimated based on the service scene, and the recommendation accuracy is improved. For example, in the case of a ticket refund, the intelligent robot service channel can quickly and accurately respond, so that the intelligent robot service channel (intelligent robot service) can be recommended to the user as a recommendation object. In addition, when the problems possibly encountered by the user are presumed based on the service scene, corresponding solutions can be prepared in advance, the problems of the user can be solved in time, and the user experience is improved.

In 102, the service channel includes, but is not limited to, a hotline service channel, a manual service channel, and an intelligent robot service channel. The hotline service channel refers to a service channel for contacting customer service by making a phone call, for example: IVR (Interactive Voice Response) hotline, which is the Interactive access of enterprise to information data such as computer database and so on by using self-help Voice prompt in customer service to guide user to select service content and input data needed by service and receiving the information input by user on telephone dial-up keyboard. A manual service channel refers to a service channel that makes online contact with manual customer service. The service channel of the intelligent robot refers to a service channel which is in online contact with the intelligent robot. The intelligent robot is a virtual robot, and solves common problems of users through a large-scale knowledge processing technology, a natural language understanding technology and a knowledge management technology by an automatic question-answering system.

The multi-source data information related to the user is synthesized to carry out multi-dimensional analysis on the user in multiple aspects, and the comprehensive understanding of the use habits, the actual requirements and other aspects of the user is facilitated. And selecting a first service channel suitable for the user from a plurality of service channels by comprehensively considering factors such as the use habits, the actual requirements and the like of the user.

For example: determining the business scene of the user according to the service source interface information and/or the user order information sought by the user; acquiring service content historically provided by a user request service channel in a service scene same as or similar to the service scene; if the service contents exceeding the threshold number in the service contents provided by the historical user request service channels can be solved by the intelligent robot service channel, taking the intelligent robot service channel as a first service channel; and if the service contents exceeding the threshold number in the service contents provided by the historical user request service channels cannot be solved by the intelligent robot service channel, using a manual service channel or a hot line service channel as a first service channel.

In 103, the recommending the first service channel to the user may adopt an inquiry recommending method or a forced recommending method. The inquiry recommendation method refers to: firstly, inquiring whether a user uses a first service channel recommended by a platform, and implanting the first service channel into a client of the user after the user confirms so that the user can solve the problem through the first service channel. Mandatory recommendations refer to: the first service channel is implanted directly into the user's client for resolution of the problem by the user through the first service channel without querying the user. In the interrogative recommendation method, the recommendation process is user-aware; in the mandatory recommendation method, the recommendation process user is unaware. Those skilled in the art can select a suitable recommendation method according to actual situations, and the embodiment of the present application is not limited in this respect.

According to the technical scheme, when a user wants to solve the problem through customer service, a proper service channel is recommended to the user through analysis of multi-source data information related to the user, and therefore the problem of the user is solved quickly. The technical scheme provided by the embodiment of the application can realize the personalized recommendation of the service channel, not only can reduce the user time and improve the user experience, but also can optimize the distribution of service resources.

In an implementation, the specific implementation of 102 can be implemented by the following steps:

1021. and determining user requirements according to the multi-source data information.

1022. Selecting the first service channel from the plurality of service channels according to the user demand.

At 1021, the user requirement includes but is not limited to at least one of channel selection tendency information and service content that the user may request. The channel picking tendency information can be simply understood as: the service channel selected by the user with the maximum probability is predicted information which is used for guiding the decision center to make service channel recommendation. The service contents that a user may request can be simply understood as: the information is also a forecast information for guiding the decision center to make service channel recommendation.

Specifically, in step 1021, "determine the channel selection tendency information according to the multi-source data information" may specifically be implemented by the following steps:

s11, extracting behavior data related to channel selection from the user behavior data.

And S12, determining the channel selection tendency information according to the behavior data related to channel selection.

Wherein the multi-source profile information comprises user behavior data.

In the above S11, the behavior data related to channel selection includes: all service channels used by the user in history and the use frequency corresponding to each service channel; or all service channels used by the user in a specific period of history and the corresponding use frequency of each service channel. The specific time period of the history may be the last year, the last month or the last week, which is not particularly limited in this embodiment.

In the above S12, the service channel with the highest selection frequency of the user in history may be used as the channel selection tendency information. Or, the service channel selected by the user last time is used as the channel selection tendency information.

For example, when a problem occurs in a certain product on the platform, a large amount of user complaints are caused in a certain period of time, by adopting the scheme, qualified users who often use intelligent services can be led into the intelligent customer service robot, and related emergency treatment and related problems of the product can be pushed to the users; and (4) connecting the hot-line obsessive-compulsive user to the hot line. Different service channels are distributed to different users according to the channel selection tendency information of the users, so that the user experience can be improved, and the distribution of service resources can be effectively optimized.

In the aforementioned 1021, "determining the service content that the user may request according to the multi-source data information" may be implemented by specifically adopting the following steps:

and S13, analyzing the service scene of the user according to the multi-source data information.

And S14, determining service contents possibly requested by the user based on the service scene.

In an implementation scheme, the above S13 is specifically: the service source interface and/or the user order information can be searched according to the user in the multi-source data information, and the service scene of the user can be analyzed. For example: on the E-commerce platform, a user seeks a commodity detail page with a service source interface being a female T-shirt, and can analyze that the user is in a business scene of browsing the female T-shirt. Accordingly, in S14, based on the user browsing the service scene of a female T-shirt, it can be determined that the service content that the user may request includes the query size, the query T-shirt material, and the like.

In another implementation, the above S13 is specifically: the business scene of the user can be analyzed according to the user order information and the service content provided by the service channel which is historically requested by the user. For example: the user has an order, and the user previously checks the relevant service progress of the order, so that the user can be determined to be in a business scene for inquiring the order progress. That is, in the above S14, in the business scenario that the user is in the query order progress, the service content that the user may request is the query order progress.

In another implementation, the above S13 is specifically: the service scene of the user can be analyzed according to the user order information, the user positioning information and the hot event. The hot event can be a hot event related to the order or a hot event related to the location of the user. For example: on the airline ticket ordering platform, a large number of hot events for inquiring the delay information of flights related to orders appear, and according to the hot events, the situation that a user is in a service scene of flight delay can be analyzed. Accordingly, in the above S14, according to the service scenario that the user is in flight delay, it can be determined that the service content that the user may request has related problems such as ticket refund, ticket change, and cost.

In the above 1022, the purpose of selecting the service channel according to the user requirement is to select a service channel meeting the user requirement from the plurality of service channels as the first service channel. Assume that the plurality of service channels includes: but are not limited to, hotline service channels, manual service channels, intelligent robot service channels, etc. For example, user requirements include: the channel selection tendency information is a manual service channel, and the service contents possibly requested by the user are questions inquiring about related sizes, inquiring about T-shirt materials and the like. The problems related to clothes size selection and the like cannot be solved well by the intelligent robot service channel and the hot line service channel, so that the artificial service channel can be selected from a plurality of service channels as the first service channel. As another example, user requirements include: the channel selection tendency information is a manual service channel, and the service contents possibly requested by the user are related questions about ticket refunding, ticket change, cost and the like. Because relevant processes such as ticket refunding, ticket change, expense and the like are fixed, the service channel of the intelligent robot can process the ticket refunding, ticket change, expense and the like. Therefore, the intelligent robot service channel can be recommended to the user as the first service channel, so that the user can be provided with quicker response service. For another example, it is found through the user behavior data that the user is a user who likes a manual service channel, and the manual service channel is selected each time the user enters the intelligent robot service channel, or the manual service channel is selected each time the hotline service channel or the intelligent robot service channel is recommended, so that the manual service channel can be recommended to the user as the first service channel.

Further, the method provided by the embodiment of the present application may further include:

104. and acquiring a corresponding service scheme according to the service content possibly requested by the user.

105. And pushing the service scheme to the first service channel for providing the service for the user so as to provide the service to the user through the first service channel when the user selects the first service channel and requests the content which is the same as or similar to the service content possibly requested by the user.

By adopting the steps 104 and 105, the service scheme meeting the requirement is provided for the user in advance. Therefore, once a user requests the content which is the same as or similar to the service content possibly requested by the user through the first service channel, the service scheme can be immediately provided for the user through the first service channel, the user problem is solved in time, and the user time is saved. For example: if the service contents possibly requested by the user include the problems of ticket refunding, ticket change and the like, the operation flows corresponding to the ticket refunding and the ticket change are taken as corresponding service schemes to be pushed to the first service channel, and when the user selects the first service channel and consults the 'ticket refunding flow' through the first service channel, the service scheme corresponding to the ticket refunding is recommended to the user. The embodiment of the application adds the steps 104 and 105, which is helpful for accelerating the problem of the user, and is helpful for improving the service efficiency of the platform, and the user experience is good.

In practical applications, a channel selection policy model may be established according to the analysis processing logic related to step 102 in the above embodiments, and the channel selection policy model may be trained through a preset amount of training data. The preset amount may be set by a technician according to actual needs and experience, or may be obtained by sampling actual data. And enabling the training data to be enough to ensure the user matching of the first service channel output by the trained channel selection strategy model. Specifically, the step 102 may be implemented by:

s1, a channel selection strategy model is obtained.

S2, taking the multi-source data information as an input parameter of the channel selection strategy model, and executing the channel selection strategy model to obtain the first service channel.

For example, the channel selection policy model may be implemented by using a learning model (e.g., a neural network learning model). And training the learning model based on the preset amount of training data to obtain a channel selection strategy model. The learning model can refer to relevant contents in the prior art, and details thereof are not repeated herein.

Further, the method provided by the embodiment of the present application further includes:

106. channel resource usage status information associated with a service channel is obtained.

107. And determining whether the first service channel meets a preset recommendation condition or not according to the channel resource use state information.

Correspondingly, the step 103 "recommending the first service channel to the user" specifically includes: and recommending the first service channel to the user when the preset recommendation condition is met.

Wherein the channel resource usage status information includes: the operating status information and/or the load status information of each service channel. The operating state information may include: normal state, abnormal state, etc. The load status information may include: low load conditions, high load conditions, etc. The abnormal state may be a state in which a system failure has occurred, system maintenance, or the like.

The preset recommendation condition can be set by self. The preset recommended condition is assumed to be a normal state or a low-load state. If the first service channel is in a normal state or a low-load state, the first service channel meets a preset recommendation condition. If the first service channel is in an abnormal state or a high-load state, the first service channel does not meet the preset recommendation condition.

Considering that the service channel in the low load state is not necessarily capable of normally operating, the service channel in the normal operation is not necessarily in the low load state. Therefore, the preset recommendation condition can be set to be in a normal state and a low-load state so as to ensure that the first service channel recommended to the user is in the normal state and the low-load state.

Further, the method provided in the embodiment of the present application may further include: when the preset recommendation condition is not met, selecting a second service channel from the plurality of service channels; and recommending the second service channel to the user. Therefore, the first service channel which runs abnormally and/or in high load can be effectively prevented from being recommended to the user, and the user experience is improved; meanwhile, the reasonable distribution of the resources of the service channels is realized, and the service channels are shared and processed when a hot spot event occurs, so that the phenomenon that some service channels run in an overload mode and some service channels are idle is avoided.

108. and storing the event of the first service channel selected by the user as profile information related to the user into big data. The logging format may be: user ID number-first service channel name-timestamp. The timestamp may be a timestamp when the user triggers the service request or a timestamp when the user triggers the selection of the first service channel.

109. and acquiring the service content provided by the first service channel requested by the user and the service result of the first service channel.

110. And storing the service content and the service result into big data as data information related to the user.

The service content may be a question input by the user or a keyword extracted according to the question input by the user. For example: the user inputs the question of 'i wants to know how to refund the ticket', the 'i wants to know how to refund the ticket' is refined by a key word to obtain 'refund' and the detailed process of the refund of the 'refund' and the first service channel for the user question feedback is stored into big data as data information associated with the user.

The data information of the user in the big data can be updated in real time through the above 108, 109 and 110, so as to be convenient for reference when recommending a service channel for the user subsequently.

The service channel recommendation method provided by the embodiment of the application can be further realized based on the following system architecture. As shown in fig. 2, a schematic structural diagram of a service channel recommendation system provided in an embodiment of the present application is shown. As shown in fig. 2, the system provided in this embodiment includes: a client 201 and a server 202. Wherein the content of the first and second substances,

the client 201 is used for responding to a service request event triggered by a user and sending a recommendation request to a server; receiving a first service channel recommended by the service terminal for the user; and displaying the first service channel as a recommended channel.

The server 202 is used for acquiring multi-source data information related to a user after receiving a service request sent by a client used by the user; selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information; and feeding back the first service channel to the client.

It should be noted here that the system provided by the foregoing embodiment may be applied to various service platforms, for example: e-commerce platform, air ticket/train ticket/bus ticket ordering platform, take-away platform, financial services platform, etc.

The specific workflow and signaling interaction between the components, such as the client and the server, in the service channel recommendation system provided in the embodiment of the present application will be further described in the following embodiments.

Fig. 3 shows a flowchart of a service channel recommendation method according to an embodiment of the present application. The method provided by the embodiment is suitable for the client. The client may be hardware integrated on the terminal and having an embedded program, or may also be application software installed in the terminal, or may also be tool software embedded in an operating system of the terminal, and the like, which is not limited in this embodiment of the present application. The terminal can be any terminal equipment including a mobile phone, a tablet personal computer, intelligent wearable equipment and the like. As shown in fig. 3, includes:

301. and responding to a service request event triggered by a user, and acquiring a first service channel recommended for the user from a service end.

302. And displaying the first service channel as a recommended channel.

In 301, the user may trigger the service request event through a control, voice or action. Triggering the service request event through the control may specifically include: the method comprises the steps that a first control (such as a contact service button) used for triggering a service request is provided for a user in a client interface, and a service request event is generated when the triggering operation of the first control by the user is monitored. Triggering of the service request event by voice may specifically include: receiving voice information of a user; recognizing the voice information; if the user is identified to contact the customer service, a service request event is triggered. For example: the user long presses the voice input button on the client interface and speaks: "I want to contact customer service," a service request event can be triggered. Triggering the service request event by an action may specifically include: specific actions that trigger service request events are configured in advance, for example: shaking the mixture. Thus, a user, when in use, may trigger a service request event by shaking.

In response to a service request event triggered by a user, a service request may be sent to a server. After receiving a service request, the server selects a first service channel suitable for the user from a plurality of service channels according to the multi-source data information related to the user, and recommends the first service channel to the client. The first service channel includes, but is not limited to: a hotline service channel, a human service channel, or an intelligent robotic service channel, among others. The service request may carry user information of the user, where the user information includes, but is not limited to, a user ID number, a login name, and the like.

In this embodiment, for specific implementation of selecting the first service channel suitable for the user from the multiple service channels according to the multi-source information related to the user, reference may be made to corresponding contents in the foregoing embodiments, which is not described herein again.

The above 302 can be implemented by one of the following methods:

the first method comprises the step of displaying recommendation information of a first service channel as a recommendation channel on a user interface. For example, information like "recommend you use the first service channel, which is more suitable for you" is displayed on the user interface.

And in the second mode, a control corresponding to the first service channel is highlighted on the user interface so as to prompt the user that the first service channel is a recommended channel. For example, controls corresponding to multiple service channels are displayed on a user interface for a user to select, the control corresponding to the first service channel is highlighted, a mark prompting that the control is a recommended channel is displayed in an attachment of the control corresponding to the first service channel, and the like.

And thirdly, displaying an operation interface corresponding to the first service channel. When the first service channel is an intelligent robot or a manual service channel, the operation interface is a response interface; when the first service channel is a hotline service channel, the operation interface is a dialing interface, wherein the dialing interface automatically generates a hotline telephone number, and a user can make a call by clicking a dialing button. It should be noted that, when the first service channel is the hotline service channel, the operation interface may be a call interface, so that the user does not need to click a "dial" button, thereby reducing the operation cost of the user.

The method I and the method II have the advantages that a user has perception on the recommendation process, knows the channel recommended by the system, and has the initiative of selecting the recommended channel; in the third method, the user does not sense the recommendation process, and the user passively selects a recommendation channel. In addition, if the method one and the method two are adopted, the method provided by the embodiment of the present application may further include: and responding to a trigger event of selecting the first service channel by a user, and displaying an operation interface corresponding to the first service channel. Specifically, when the first service channel is a hotline service channel, a call request is initiated to a service party corresponding to the first service channel in response to a trigger event that a user selects the first service channel, and a call interface is displayed; and when the first service channel is a manual service channel or an intelligent robot service channel, responding to a trigger event of selecting the first service channel by a user, and displaying a corresponding response interface.

Here, it should be noted that: for specific implementation of each step in the embodiment of the present application, reference may be made to relevant contents in each embodiment in parts that are not described in detail in this embodiment, and details are not described here again.

Fig. 4 is a flowchart illustrating a service channel recommendation method according to an embodiment of the present application. The method provided by the embodiment is suitable for the server. The server may be a common server, a cloud, a virtual server, and the like, which is not specifically limited in this embodiment of the application. As shown in fig. 4, the method provided by this embodiment includes:

401. after receiving a service request sent by a client used by a user, acquiring multi-source data information related to the user.

402. And selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information.

403. And feeding back the first service channel to the client so that the first service channel is displayed as a recommended channel by the client.

In 401, the client may send a service request to the server in response to a service request event triggered by the user. And after receiving the service request, the server acquires multi-source data information related to the user according to the user information carried in the service request. For example: multi-source profile information related to a user may be queried in the big data. User information may include, but is not limited to: user ID number, login name. Wherein, the multi-source data information includes but is not limited to: at least two of user behavior data, user positioning information, hot events and user seeking service source interface information. The user behavior data includes, but is not limited to, at least one of: historical common service channels, user order information and historical service contents provided by the service channels requested by the users. For specific implementation of the service request event triggered by the user, reference may be made to corresponding contents in the foregoing embodiments, which are not described herein again.

The specific implementation of "the client displays the first service channel as the recommended channel" in 402 and 403 may refer to corresponding content in the foregoing embodiments, and details are not described herein again.

Further, the method provided in the embodiment of the present application may further include:

404. channel resource usage status information associated with a service channel is obtained.

405. And determining whether the first service channel meets a preset recommendation condition or not according to the channel resource use state information.

And, the specific implementation of "feeding back the first service channel to the client" in the foregoing 403 is: and when the preset recommendation condition is met, feeding the first service channel back to the client.

Wherein the channel resource usage status information includes: the operating status information and/or the load status information of each service channel. For specific implementation of the above 404 and 405, reference may be made to corresponding contents in the above embodiments, and details are not described herein.

When the first service channel does not meet the preset recommendation condition, a second service channel different from the first service channel can be selected from the plurality of service channels. Specifically, the method provided in the embodiment of the present application may further include: when the preset recommendation condition is not met, selecting a second service channel from the plurality of service channels; and feeding back the second service channel to the client so that the client can display the second service channel as a recommended channel. Specifically, a second service channel in a normal state and/or a low load state is selected from the plurality of service channels.

Therefore, the first service channel which runs abnormally or in high load can be effectively prevented from being recommended to the user, and the user experience is improved; meanwhile, reasonable resource distribution of a plurality of service channels is realized, and the plurality of service channels are shared and processed when a hot spot event occurs, so that the phenomenon that some service channels are overloaded to run and some service channels are idle is avoided.

406. and storing the event of the first service channel selected by the user as profile information related to the user into big data. The logging format may be: user ID number-first service channel name-timestamp. The timestamp may be a timestamp when the user triggers the service request or a timestamp when the user triggers the selection of the first service channel.

407. and acquiring the service content provided by the first service channel requested by the user and the service result of the first service channel.

408. And storing the service content and the service result into big data as data information related to the user.

The data information of the user in the big data can be updated in real time through the 406, 407 and 408, so as to be convenient for reference when recommending a service channel for the user subsequently.

Here, it should be noted that: for specific implementation of each step in the embodiments of the present application, parts that are not elaborated in this embodiment may refer to relevant contents in the above embodiments, and details are not described here.

The technology provided by the embodiment of the present application will be further described with reference to the theoretical flow provided by fig. 5:

the user seeks services: and the user side client sends a service request to the server side in response to the operation that the user clicks a contact service button in the application interface. The service request carries user location information (e.g., user LBS information) and source information (i.e., user seeks service source interface information), etc.

Preparing data: and acquiring data information such as user behavior data and hot events related to the user from the big data.

The strategy center: and recommending a service channel for the user according to the LBS information, the source information, the user behavior data, the hot event and the like of the user.

The problems are solved: the user can select the recommended service channel to solve the problem, and can also select the non-recommended service channel to solve the problem. Here, it should be noted that: how each service channel solves the problem for the user can refer to corresponding contents in the prior art, which is not described herein again. The behavior data of the user selecting the recommended service channel can be fed back to the strategy center.

And (3) counting related data: selecting behavior data of a service channel by a user, such as selecting a recommended service channel, or selecting another service channel besides the recommended service channel; and storing the problem to be solved by the user request and the solution provided by the service channel as multi-source data information related to the user into the big data.

To sum up, according to the technical scheme provided by the embodiment of the application, when the user wants to solve the problem, a service channel for quickly solving the problem is recommended to the user through data analysis, so that the user time is shortened, the efficiency is improved, the user experience is improved to a great extent, and the service resource allocation is optimized. The technical scheme provided by the embodiment of the application is that a service strategy is advanced to the place before the user communicates with the platform customer service, a channel for solving the user problem most quickly is calculated, and the user service experience is improved while the platform service resources are optimized.

Fig. 6 is a schematic structural diagram illustrating a service channel recommendation apparatus according to an embodiment of the present application. As shown in fig. 6, the apparatus includes:

the first obtaining module 601, the user obtains multi-source data information related to the user;

the first selection module 602 selects a first service channel suitable for the user from a plurality of service channels according to the multi-source data information;

a first recommending module 603, configured to recommend the first service channel to the user.

Further, the multi-source data information includes at least two of the following: user behavior data, user positioning information, hot events, user seeking service source interface information.

Further, the user behavior data includes at least one of: historical common service channels, user order information, and historical service contents provided by service channels requested by users.

Further, the first selecting module 602 includes: the device comprises a first determining unit and a first selecting unit; wherein, the first and the second end of the pipe are connected with each other,

the first determining unit is used for determining user requirements according to the multi-source data information;

a first selecting unit, configured to select the first service channel from the plurality of service channels according to the user requirement.

Further, the user requirements include at least one of: channel picking tendency information, service contents that the user may request.

Further, the multi-source profile information includes user behavior data, and the first determining unit is specifically configured to:

extracting behavior data related to channel selection from the user behavior data;

and determining the channel selection tendency information according to the behavior data related to channel selection.

Further, the first determining unit is specifically configured to:

analyzing the service scene of the user according to the multi-source data information;

and determining the service content which is possibly requested by the user based on the service scene.

Further, the apparatus further includes:

a second obtaining module, configured to obtain a corresponding service scheme according to service content that the user may request;

the first pushing module is used for pushing the service scheme to the first service channel for providing services for the user so as to provide the service scheme to the user through the first service channel when the user selects the first service channel and requests the content which is the same as or similar to the service content possibly requested by the user.

Further, the first selecting module 602 is specifically configured to:

acquiring a channel selection strategy model;

and taking the multi-source data information as an input parameter of the channel selection strategy model, and executing the channel selection strategy model to obtain the first service channel.

Further, the apparatus further includes:

the third acquisition module is used for acquiring channel resource use state information related to the service channel;

the second determining unit is used for determining whether the first service channel meets a preset recommendation condition according to the channel resource use state information; and

the first recommending module 603 is specifically configured to: and recommending the first service channel to the user when the preset recommendation condition is met.

Further, the channel resource usage status information includes: the service channels comprise working state information and/or load state information of each service channel.

Further, the first selecting module 602 is further configured to: and when the preset recommendation condition is not met, selecting a second service channel from the plurality of service channels.

The first recommending module 603 is further configured to: and recommending the second service channel to the user.

Further, the apparatus further includes:

and the first storage module is used for storing the event of the first service channel selected by the user as data information related to the user into big data.

Further, the apparatus further includes:

a fourth obtaining module, configured to obtain a service content provided by the first service channel requested by the user and a service result of the first service channel;

the first storage module is also used for storing the service content and the service result into big data as data information related to the user.

Further, the plurality of service channels includes at least two of: a hotline service channel, a manual service channel, an intelligent robot service channel.

Here, it should be noted that: the service channel recommendation device provided in the above embodiments may implement the technical solutions described in the above method embodiments, and the specific implementation principle of each module or unit may refer to the corresponding content in the above method embodiments, which is not described herein again.

Fig. 7 is a schematic structural diagram illustrating a service channel recommendation apparatus according to an embodiment of the present application. As shown in fig. 7, the apparatus includes:

a fifth obtaining module 701, configured to obtain, from a server, a first service channel recommended for a user in response to a service request event triggered by the user;

a first display module 702, configured to display the first service channel as a recommended channel;

Further, the first service channel is: a hotline service channel, a manual service channel, or an intelligent robot service channel.

Further, the first display module is further configured to:

when the first service channel is a hotline service channel, responding to a trigger event of a user selecting the first service channel, initiating a call request to a service party corresponding to the first service channel, and displaying a call interface;

and when the first service channel is a manual service channel or an intelligent robot service channel, responding to a trigger event of selecting the first service channel by a user, and displaying a corresponding response interface.

Fig. 8 is a schematic structural diagram illustrating a service channel recommendation apparatus according to an embodiment of the present application. As shown in fig. 8, the apparatus includes:

a sixth obtaining module 801, configured to obtain multi-source data information related to a user after receiving a service request sent by a client used by the user;

a second selecting module 802, configured to select a first service channel suitable for the user from multiple service channels according to the multi-source profile information;

a first feedback module 803, configured to feed back the first service channel to the client, so that the client displays the first service channel as a recommended channel.

Further, the multi-source data information includes at least two of the following: user behavior data, user positioning information, hot events, and user seeking service source interface information.

Further, the apparatus further includes:

a seventh obtaining module, configured to obtain channel resource usage status information related to the service channel;

the third determining module is used for determining whether the first service channel meets a preset recommendation condition according to the channel resource use state information; and

the first feedback module 803 is specifically configured to: and when the preset recommendation condition is met, feeding the first service channel back to the client.

Further, the second selecting module 802 is further configured to select a second service channel from the plurality of service channels when the preset recommendation condition is not met;

the first feedback module 803 is further configured to feed back the second service channel to the client, so that the client displays the second service channel as a recommended channel.

Further, the apparatus further includes:

and the second storage module is used for storing the event of the first service channel selected by the user as data information related to the user into big data.

Further, the apparatus further includes:

an eighth obtaining module, configured to obtain a service content provided by the first service channel requested by the user and a service result of the first service channel;

and the two storage modules are used for storing the service content and the service result into big data as data information related to the user.

Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the application. The electronic device includes: a first memory 1101, and a first processor 1102. The first memory 1101 may be configured to store other various data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device. The first memory 1101 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The first processor 1102, coupled to the first memory 1101, is configured to execute the program stored in the first memory 1101 to:

acquiring multi-source data information related to a user;

recommending the first service channel to the user.

When executing the program in the first memory 1101, the first processor 1102 may also implement other functions in addition to the above functions, which may be specifically referred to in the description of the foregoing embodiments.

Further, as shown in fig. 9, the electronic device further includes: a first communication component 1103, a first display 1104, a first power component 1105, a first audio component 1106, and the like. Only some of the components are schematically shown in fig. 9, and the electronic device is not meant to include only the components shown in fig. 9.

Accordingly, embodiments of the present application further provide a computer-readable storage medium storing a computer program, where the computer program, when executed by a computer, can implement the steps or functions of the service channel recommendation method provided in the foregoing embodiments.

Fig. 10 shows a schematic structural diagram of a client device according to an embodiment of the present application. As shown, the client device includes a second memory 1201 and a second processor 1202. The second memory 1201 may be configured to store other various data to support operations on the client device. Examples of such data include instructions for any application or method operating on the client device. The second memory 1201 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The second processor 1202, coupled to the second memory 1201, is configured to execute the program stored in the second memory 1201, so as to:

displaying the first service channel as a recommended channel;

When executing the program in the second memory 1201, the second processor 1202 may also implement other functions in addition to the above functions, which may be specifically referred to the description of the foregoing embodiments.

Further, as shown in fig. 10, the client device further includes: a second communication component 1203, a second display 1204, a second power component 205, a second audio component 1206, and the like. Only some of the components are shown schematically in fig. 10, and the client device is not meant to include only the components shown in fig. 10.

Accordingly, the present application further provides a computer-readable storage medium storing a computer program, where the computer program can implement the steps or functions of the service channel recommendation method provided in the foregoing embodiments when executed by a computer.

Fig. 11 shows a schematic structural diagram of a server device according to an embodiment of the present application. As shown, the server device includes a third memory 1301 and a third processor 1302. The third memory 1301 may be configured to store other various data to support operations on the server device. Examples of such data include instructions for any application or method operating on the server device. The third memory 1301 may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The third processor 1302, coupled to the third memory 1301, is configured to execute the program stored in the third memory 1301 to:

When executing the program in the third memory 1301, the third processor 1302 may also implement other functions in addition to the above functions, which may be specifically referred to in the description of the foregoing embodiments.

Further, as shown in fig. 11, the server device further includes: a third communication component 1303, a third display 1304, a third power component 1305, a third audio component 1306, and other components. Only some of the components are schematically shown in fig. 11, and it is not meant that the server device includes only the components shown in fig. 11.

Accordingly, embodiments of the present application further provide a computer-readable storage medium storing a computer program, where the computer program, when executed by a computer, can implement the steps or functions of the service channel method provided in the foregoing embodiments.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A service channel recommendation method is characterized by comprising the following steps:

acquiring multi-source data information related to a user;

selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information, wherein the selecting comprises the following steps: determining user requirements according to the multi-source data information; the user requirements comprise channel selection tendency information and service contents possibly requested by the user; the channel selection tendency information comprises the service channel with the highest selection frequency of the user in history: selecting the first service channel from the plurality of service channels according to the user requirement;

recommending the first service channel to the user.

2. The method of claim 1, wherein the multi-source information comprises at least two of: user behavior data, user positioning information, hot events, user seeking service source interface information.

3. The method of claim 2, wherein the user behavior data comprises at least one of: historical common service channels, user order information, and historical service contents provided by service channels requested by users.

4. The method of claim 1, wherein the multi-source profile information includes user behavior data, an

Determining the channel selection tendency information according to the multi-source data information, wherein the channel selection tendency information comprises the following steps:

5. The method of claim 1, wherein determining the service content that the user may request based on the multi-source profile information comprises:

6. The method of claim 1, further comprising:

acquiring a corresponding service scheme according to service contents possibly requested by the user;

and pushing the service scheme to the first service channel for providing services for the user, so that when the user selects the first service channel and requests the content which is the same as or similar to the service content possibly requested by the user, the service scheme is provided for the user through the first service channel.

7. The method of any of claims 1 to 3, wherein selecting a first service channel from a plurality of service channels suitable for the user based on the multi-source profile information comprises:

acquiring a channel selection strategy model;

8. The method of any of claims 1 to 3, further comprising:

acquiring channel resource use state information related to a service channel;

determining whether the first service channel meets a preset recommendation condition or not according to the channel resource use state information; and

recommending the first service channel to the user, including: and recommending the first service channel to the user when the preset recommendation condition is met.

9. The method of claim 8, wherein the channel resource usage status information comprises: the service channels comprise working state information and/or load state information of each service channel.

10. The method of claim 9, further comprising:

when the preset recommendation condition is not met, selecting a second service channel from the plurality of service channels;

and recommending the second service channel to the user.

11. The method of any of claims 1 to 3, further comprising:

and storing the event of the first service channel selected by the user as profile information related to the user into big data.

12. The method of any of claims 1 to 3, further comprising:

acquiring service content provided by the first service channel requested by the user and a service result of the first service channel;

and storing the service content and the service result into big data as data information related to the user.

13. The method of any of claims 1 to 3, wherein the plurality of service channels comprises at least two of: a hotline service channel, a manual service channel, an intelligent robot service channel.

14. A service channel recommendation method is suitable for a client side and is characterized by comprising the following steps:

displaying the first service channel as a recommended channel;

wherein the first service channel is selected from a plurality of service channels based on multi-source profile information associated with the user; the first service channel is selected from the plurality of service channels according to user requirements; the user requirements comprise channel selection tendency information and service contents possibly requested by the user; the channel selection tendency information comprises service channels with the highest selection frequency of the user historically: the user requirements are determined according to the multi-source data information.

15. The method of claim 14, wherein the first service channel is: a hotline service channel, a manual service channel, or an intelligent robot service channel.

16. The method of claim 15, further comprising:

17. A service channel recommendation method is suitable for a server side and is characterized by comprising the following steps:

selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information, wherein the selecting comprises the following steps: determining user requirements according to the multi-source data information; the user requirements comprise channel selection tendency information and service contents possibly requested by the user; the channel selection tendency information comprises service channels with the highest selection frequency of the user historically: selecting the first service channel from the plurality of service channels according to the user requirement;

18. A service channel recommendation system, comprising:

the client is used for responding to a service request event triggered by a user and sending a recommendation request to the server; receiving a first service channel recommended by the service terminal for the user; the first service channel is used as a recommended channel to be displayed;

the server is used for acquiring multi-source data information related to a user after receiving a service request sent by a client used by the user; selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information, wherein the selecting comprises the following steps: determining user requirements according to the multi-source data information; the user requirements comprise channel selection tendency information and service contents possibly requested by the user; the channel selection tendency information comprises service channels with the highest selection frequency of the user historically: selecting the first service channel from the plurality of service channels according to the user requirement; and feeding back the first service channel to the client.

19. An electronic device, comprising: a first memory and a first processor, wherein,

the first memory is used for storing programs;

the first processor, coupled to the first memory, to execute the program stored in the first memory to:

acquiring multi-source data information related to a user;

selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information, wherein the method comprises the following steps: determining user requirements according to the multi-source data information; the user requirements comprise channel selection tendency information and service contents possibly requested by the user; the channel selection tendency information comprises service channels with the highest selection frequency of the user historically: selecting the first service channel from the plurality of service channels according to the user requirement;

recommending the first service channel to the user.

20. A client device, comprising: a second memory and a second processor, wherein,

the second memory is used for storing programs;

displaying the first service channel as a recommended channel;

21. A server device, characterized by a third memory and a third processor, wherein,

the third memory is used for storing programs;

the third processor, coupled to the third memory, for executing the program stored in the third memory to:

selecting a first service channel suitable for the user from a plurality of service channels according to the multi-source data information, wherein the method comprises the following steps: determining user requirements according to the multi-source data information; the user requirements comprise channel selection tendency information and service contents possibly requested by the user; the channel selection tendency information comprises the service channel with the highest selection frequency of the user in history: selecting the first service channel from the plurality of service channels according to the user requirement;