CN113256173A - Routing method, routing device, electronic equipment and storage medium - Google Patents
Routing method, routing device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113256173A CN113256173A CN202110730762.7A CN202110730762A CN113256173A CN 113256173 A CN113256173 A CN 113256173A CN 202110730762 A CN202110730762 A CN 202110730762A CN 113256173 A CN113256173 A CN 113256173A
- Authority
- CN
- China
- Prior art keywords
- user
- customer service
- service
- manual
- consultation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a routing method, a routing device, electronic equipment and a storage medium, and relates to the technical field of computers. The embodiment of the invention comprises the following steps: and receiving the consultation message input by the user in the customer service dialog box, and judging whether the user has the requirement of manual customer service according to the consultation message. And if the user is determined to have the requirement of transferring to the manual customer service, determining the matching degree of each manual customer service and the user according to other consultation messages input by the user in the customer service dialog box, the position information of the user and the portrait data of the user and each manual customer service, and distributing the manual customer service to the user according to the matching degree of each manual customer service and the user. The problem that manual customer service distributed for the user is not matched with the user requirement is solved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a routing method and apparatus, an electronic device, and a storage medium.
Background
The development of the artificial intelligence technology enables the field of customer service to change from top to bottom, in order to reduce manpower expenditure and improve service volume, a large number of enterprises introduce artificial intelligence customer service robots, and the artificial intelligence customer service robots are trained by adopting a large number of samples, so that the artificial intelligence customer service robots can automatically answer questions of users. However, the current artificial intelligence service robot cannot completely solve all the problems of the user, and the user still can choose to change to the artificial service under the condition that the artificial intelligence service robot cannot answer the user problems correctly or the artificial intelligence service robot understands that the user intention has deviation.
In the related art, an idle customer service can be randomly selected from all online customer services, or customer services can be distributed to users according to a certain sequence. However, in most service scenarios, different manual customer services have different professional fields and question and answer authorities, and the manual customer service allocated to the user by the current allocation method may not solve the problem of the user, so that the manual customer service allocated to the user is not matched with the user requirement.
Disclosure of Invention
Embodiments of the present invention provide a routing method, an apparatus, an electronic device, and a storage medium, so as to solve the problem that customer service allocated to a user does not match with a user requirement. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a routing method, including:
receiving a consultation message input by a user in a customer service dialog box;
judging whether the user has the requirement of transferring to the manual customer service according to the consultation message;
if the user is determined to have the requirement of transferring to the manual customer service, determining the matching degree of each manual customer service and the user according to other consultation messages input by the user in the customer service dialog box, the position information of the user and the image data of the user and each manual customer service;
and distributing the manual customer service to the user according to the matching degree of each manual customer service and the user.
In a possible implementation manner, the determining, according to other consultation messages input by the user in the customer service dialog box, the location information of the user, and the portrait data of the user and each customer service, a degree of matching between each customer service and the user includes:
determining the target service type consulted by the user according to other consultation messages input by the user in the customer service dialog box;
screening the artificial customer service matched with the position information of the user and the target service category;
and matching the portrait data of the user with the portrait data of the screened artificial customer service, and determining the matching degree of each screened artificial customer service and the user.
In a possible implementation manner, determining a target service category consulted by the user according to other consultation messages input by the user in the customer service dialog box includes:
identifying the service type of each consultation message one by one according to the sequence of the consultation message time input by the user in the customer service dialog box from late to early;
if the service category of one consultation message is identified, terminating the identification, and determining the identified service category of the consultation message as a target service category consulted by the user;
and if the service type of any consultation message cannot be determined after all the consultation messages input by the user in the customer service dialog box are identified, determining that the target service type consulted by the user cannot be identified.
In one possible implementation manner, the filtering of the artificial customer service matched with the location information of the user and the target service category includes:
determining location information of the user;
screening the manual customer service in the same preset range with the user according to the position information of the user;
and screening out the artificial customer service with the service authority for processing the target service class from the artificial customer services in the same preset range with the user.
In one possible implementation manner, matching the portrait data of the user with the portrait data of the screened artificial customer service, and determining a matching degree of each screened artificial customer service with the user includes:
inputting the portrait data of the user and the portrait data of each screened artificial customer service into a matching prediction model to obtain the matching degree between the portrait data of each screened artificial customer service and the portrait data of the user, wherein the matching prediction model is obtained by training a neural network model based on a preset training set.
In a possible implementation manner, the determining whether the user has a manual customer service requirement according to the consultation message includes:
identifying a service class to which the advisory message belongs; if the business category to which the consultation message belongs is a category for representing manual customer service transfer, determining that the user has the demand of manual customer service transfer; alternatively, the first and second electrodes may be,
and identifying whether the consultation message comprises a preset keyword or not, and if the consultation message comprises the preset keyword, determining that the user has the requirement of transferring to manual customer service.
In one possible implementation manner, the user figure data comprises any one or more of user age, visit times, historical consultation satisfaction and historical complaint times, and the artificial customer service figure data comprises any one or more of response speed, historical satisfaction, age and violation times.
In a second aspect, an embodiment of the present invention provides a routing apparatus, including:
the receiving module is used for receiving the consultation message input by the user in the customer service dialog box;
the judging module is used for judging whether the user has the requirement of transferring to the manual customer service according to the consultation message;
the determining module is used for determining the matching degree of each artificial customer service and the user according to other consultation messages input by the user in the customer service dialog box, the position information of the user and the portrait data of the user and each artificial customer service if the user is determined to have the requirement of transferring the artificial customer service;
and the distribution module is used for distributing the manual customer service to the user according to the matching degree of each manual customer service and the user.
In a possible implementation manner, the determining module is specifically configured to:
determining the target service type consulted by the user according to other consultation messages input by the user in the customer service dialog box;
screening the artificial customer service matched with the position information of the user and the target service category;
and matching the portrait data of the user with the portrait data of the screened artificial customer service, and determining the matching degree of each screened artificial customer service and the user.
In a possible implementation manner, the determining module is specifically configured to:
identifying the service type of each consultation message one by one according to the sequence of the consultation message time input by the user in the customer service dialog box from late to early;
if the service category of one consultation message is identified, terminating the identification, and determining the identified service category of the consultation message as a target service category consulted by the user;
and if the service type of any consultation message cannot be determined after all the consultation messages input by the user in the customer service dialog box are identified, determining that the target service type consulted by the user cannot be identified.
In a possible implementation manner, the determining module is specifically configured to:
determining location information of the user;
screening the manual customer service in the same preset range with the user according to the position information of the user;
and screening out the artificial customer service with the service authority for processing the target service class from the artificial customer services in the same preset range with the user.
In a possible implementation manner, the determining module is specifically configured to:
inputting the portrait data of the user and the portrait data of each screened artificial customer service into a matching prediction model to obtain the matching degree between the portrait data of each screened artificial customer service and the portrait data of the user, wherein the matching prediction model is obtained by training a neural network model based on a preset training set.
In a possible implementation manner, the determining module is specifically configured to:
identifying a service class to which the advisory message belongs; if the business category to which the consultation message belongs is a category for representing manual customer service transfer, determining that the user has the demand of manual customer service transfer; alternatively, the first and second electrodes may be,
and identifying whether the consultation message comprises a preset keyword or not, and if the consultation message comprises the preset keyword, determining that the user has the requirement of transferring to manual customer service.
In one possible implementation manner, the user figure data comprises any one or more of user age, visit times, historical consultation satisfaction and historical complaint times, and the artificial customer service figure data comprises any one or more of response speed, historical satisfaction, age and violation times.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;
a memory for storing a computer program;
and a processor for implementing any of the above-described routing method steps when executing the program stored in the memory.
In a fourth aspect, this application further provides a computer-readable storage medium, in which a computer program is stored, and when executed by a processor, the computer program implements the routing method described in the first aspect.
In a fifth aspect, embodiments of the present application further provide a computer program product containing instructions, which when run on a computer, cause the computer to perform the routing method described in the first aspect.
The embodiment of the invention has the following beneficial effects:
by adopting the technical scheme, whether the user has the requirement of manual customer service is judged by receiving the message input by the user through the customer service dialog box. When the user is judged to have the requirement of changing into manual work, the manual customer service can be distributed to the user at the first time when the message is received. After confirming that the user needs to seek for the help of the manual customer service, the matching degree of each manual customer service and the user is determined through multiple angles through other consultation messages input by the user in the customer service dialog box, the position information of the user and the portrait data of the user and each manual customer service, and the obtained matching degree is more accurate. The higher the matching degree of a user and a certain manual customer service is, the higher the estimated satisfaction degree of the user to the customer service is, compared with the method for simply and randomly selecting a manual customer service to serve the user in the prior art, the method and the system for providing the customer service with the high matching degree of the user select the customer service with the high matching degree of the user to provide the service for the user, and the matching degree of the customer service and the user distributed to the user is guaranteed.
Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained by referring to these drawings.
Fig. 1 is a flowchart of a routing method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for determining matching degree between artificial customer service and user according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for determining a target service category consulted by a user according to an embodiment of the present invention;
fig. 4 is an exemplary flowchart of a routing method according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a routing device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived from the embodiments given herein by one of ordinary skill in the art, are within the scope of the invention.
In order to allocate artificial customer service matching with user requirements for a user, an embodiment of the present invention provides a routing method, including:
receiving a consultation message input by a user in a customer service dialog box;
judging whether the user has the requirement of transferring to the manual customer service according to the consultation message;
if the user is determined to have the requirement of transferring to the manual customer service, determining the matching degree of each manual customer service and the user according to other consultation messages input in a customer service dialog box by the user, the position information of the user and the portrait data of the user and each manual customer service;
and distributing the manual customer service to the users according to the matching degree of each manual customer service and the users.
By the method, the matching degree of the user and each artificial customer service can be determined according to other consultation messages input by the user, the position information of the user and a plurality of angles of the portrait data of the user and each artificial customer service, the artificial customer service is distributed to the user according to the matching degree of each artificial customer service and the user, and the customer service distribution to the user is matched with the user requirement.
The following describes in detail a routing method provided in an embodiment of the present application.
An embodiment of the present application provides a routing method, which is applied to an electronic device, and as shown in fig. 1, the method includes:
s101, receiving the consultation message input by the user in the customer service dialog box.
Alternatively, the counseling message inputted by the user in the customer service dialog box may be a text form or a voice form counseling message. When the counseling message input by the user in the customer service dialog box is a voice-form counseling message, the electronic device needs to convert the voice-form counseling message into a text form.
And S102, judging whether the user has the requirement of manual customer service according to the consultation message.
In the embodiment of the application, every time a piece of consultation message of a user is received, whether the user has the requirement of changing to the artificial customer service is judged according to the currently received consultation message, and if the user has the requirement of changing to the artificial customer service is determined according to the consultation message, S103 is executed; and if the user does not need to change the manual customer service according to the consultation message, continuously receiving the consultation message input by the user in the customer service dialog box, and executing S102 until the user has the information of changing the manual customer service according to the consultation message, and executing S103.
S103, if the user is determined to have the requirement of transferring to the manual customer service, determining the matching degree of each manual customer service and the user according to other consultation messages input in the customer service dialog box by the user, the position information of the user and the portrait data of the user and each manual customer service.
Wherein, the other consultation messages are the consultation messages input in the customer service dialog box in the consultation process before the user receives the consultation message with the manual change requirement.
For example, the user opens a customer dialog box, enters question A first, then receives the response from the intelligent robot, enters question B, and receives the response from the intelligent robot again. At this time, the user inputs the manual service switching, and the user can be determined to have the manual service switching requirement according to the consultation message of manual service switching. At this time, the other advisory message includes the question a and/or the question B.
The portrait data of the user and each artificial customer service is user characteristic data generated after the user consults the artificial customer service, and the portrait data of each artificial customer service is each artificial customer service characteristic data generated after each artificial customer service provides service for the user. The portrait data of the user and each man-made customer service can be obtained by counting the service records of the preset time or the preset times.
And S104, distributing the manual customer service to the user according to the matching degree of each manual customer service and the user.
And after the matching degree of each artificial customer service and the user is obtained, the artificial customer service can be distributed to the user, and the consultation information input by the user in the customer service dialog box is solved.
The routing method provided by the embodiment of the invention judges whether the user has the requirement of manual customer service by receiving the message input by the user through the customer service dialog box. When the user is judged to have the requirement of changing into manual work, the manual customer service can be distributed to the user at the first time when the message is received. After confirming that the user needs to seek for the help of the artificial customer service, the matching degree of each artificial customer service and the user is determined through multiple angles through other consultation messages input by the user in the customer service dialog box, the position information of the user and the portrait data of the user and each artificial customer service. The higher the matching degree of a user and a certain manual customer service is, the higher the estimated satisfaction degree of the user to the customer service is, compared with the method for simply and randomly selecting one manual customer service to serve the user in the prior art, the method and the system for providing the customer service with the high matching degree of the user select the customer service with the high matching degree of the user to serve the user, and the matching degree of the manual customer service distributed to the user and the user is guaranteed.
In addition, in the prior art, when manual customer service allocation is performed for a user, in order to ensure the allocation speed, a mode of randomly allocating manual customer service to the user or a mode of sequentially selecting an idle manual customer service is generally adopted to provide service for the user. However, the above-mentioned method of randomly or sequentially allocating an idle manual customer service to a user often results in that the manual customer service allocated to the user cannot solve the problem of the user, and other manual customer services need to be allocated to the user again. According to the invention, the matching degree of each artificial customer service and the user is determined by adopting multiple angles, and then the artificial customer service is distributed to the user according to the matching degree of each artificial customer service and the user, so that the matching degree of the artificial customer service distributed to the user and the user is improved, and the problem of secondary distribution of the artificial customer service caused by inaccurate distribution in the follow-up process is avoided.
In an embodiment of the present invention, the above S104, the method for allocating the artificial customer service to the user according to the matching degree between each artificial customer service and the user includes the following three ways:
and selecting the manual customer service with the highest matching degree with the user from the idle manual customer services to serve the user.
For example, there are 5 idle manual customer services in total, the matching degree of the manual customer service 001 and the user is 80%, the matching degree of the manual customer service 002 and the user is 60%, the matching degree of the manual customer service 003 and the user is 65%, the matching degree of the manual customer service 004 and the user is 70%, and the matching degree of the manual customer service 005 and the user is 90%. In the 5 idle artificial customer services, the degree of matching between the artificial customer service 005 and the user is the highest, so the artificial customer service 005 is selected to provide service for the user.
And secondly, displaying the manual customer service with the preset number of threshold matching degrees from high to low for the user, receiving the operation that the user selects the manual customer service from the manual customer service with the preset number of threshold matching degrees from high to low, and distributing the manual customer service selected by the user for the user.
For example, the preset number threshold may be 10, that is, the user is presented with top 10 artificial customer services sorted from high to low according to the matching degree. The user can select one customer service which the user wants to obtain the service from the 10 manual customer services according to personal preference to provide the service for the user.
And thirdly, notifying the manual customer service with the preset number of threshold values from high to low in matching degree to serve the user, and receiving the notification determined by the manual customer service with the preset number of threshold values from high to low in matching degree to serve the user. The user is assigned a human customer service that first issues a notification that is determined to serve the user.
For example, the preset number threshold may be 10, that is, the manual customer service is sorted from high to low according to the matching degree, the manual customer service ranked 10 top after sorting is found, and the 10 manual customer services select whether to serve the user. The 10 manual customer service can decide whether to provide service for the user. The electronic device assigns to the user a manual customer service that was first determined to provide service to the user.
For example: and the electronic equipment selects the first 10 artificial customer services after ordering the artificial customer services according to the matching degree from high to low, and displays an interface for determining whether to provide service for the user for the 10 artificial customer services. And receiving the results of the 10 manual customer service selections, selecting the first manual customer service determined to provide service for the user, and distributing the manual customer service to the user.
Optionally, before any of the first, second, and third manners is performed to allocate the artificial customer service to the user, the selection range of the artificial customer service may be determined according to the preset range matched by the artificial customer service, and then the step of determining to allocate the artificial customer service to the user is performed. When the manual customer service matching preset range cannot find the manual customer service distributed for the user, the manual customer service matching preset range can be expanded by one level. For example, all the manual customer services can be divided into individual websites, all the websites at the market level, all the websites at the provincial level and all the websites at the country according to the websites where the manual customer services are located. If the matching preset range of the artificial customer service is the maximum range, namely all the network sites in the whole country, opening all the artificial customer services meeting the authority to perform order grabbing.
Therefore, the manual customer service is distributed to the user in the first mode, the number of steps is small, the speed of distributing the manual customer service to the user is the fastest, and the user can obtain the service provided by the manual customer service with the highest matching degree in the first time.
The second mode and the third mode give the user and the manual customer service selection right, and the user can select the manual customer service according to the preference of the user by the second mode, so that the selected manual customer service can be matched with the preference of the user. And in the third mode, the manual customer service can be determined to serve the user under the condition that the manual customer service determines that the manual customer service can provide high-quality service for the user. The electronic equipment distributes the manual customer service to the user by adopting the first mode, the second mode or the third mode, and the service quality of the manual customer service is further ensured.
In an embodiment of the present invention, as shown in fig. 2, in the step S103, determining the matching degree between each customer service and the user according to the other consultation messages input by the user in the customer service dialog box, the location information of the user, and the image data of the user and each customer service may be implemented as follows:
and S1031, determining the target service type consulted by the user according to other consultation messages input by the user in the customer service dialog box.
Different users consult different business categories, and in industries with higher professional degrees such as finance, education and the like, different artificial customer services have different professional fields and question-answering authorities. When the type of the business consulted by the user does not conform to the professional field of allocating manual customer service to the user or the authority of the manual customer service is insufficient, the situation that the manual customer service cannot answer the user question occurs. In order to enable the assignment of appropriate manual customer service to the user, a target business category consulted by the user may be determined.
Taking the financial industry as an example, the business categories consulted by the user may include all business categories included in the financial industry that the user may consult manually, such as securities category, fund category, account activation category, software operation consultation category, activity consultation category, and the like. For the consulting information of securities and funds, the manual customer service with professional knowledge of securities and funds has the answering authority; for the software operation type consultation message, a human customer service is required to be familiar with the software operation.
In the embodiment of the present application, the target business category consulted by the user may be determined through an intention recognition model. The counseling message inputted by the user can be inputted into the intention recognition model, and the target business category is determined according to the output of the intention recognition model. After the consultation message is input into the intention recognition model, the probability that the consultation message belongs to each target service class can be obtained. And selecting the target service category with the highest probability as the target service category consulted by the user, namely selecting one service category which is most likely to be consulted by the user from all the service categories as the target service category consulted by the user.
The intention recognition model may be implemented by a natural language processing technique, for example, the intention recognition model may be a model obtained by training a neural network model based on a preset training set. Alternatively, the neural network model in the embodiment of the present application may be a Long Short-Term Memory network (LSTM) model, which has five layers, where the first layer is an input layer, and the input layer includes a plurality of input units, and each input unit represents a combination of a plurality of features of the advisory message. The second layer is a Dropout layer, and the Dropout layer reduces the number of intermediate features by randomly setting the input unit to 0 according to the ratio, thereby reducing feature redundancy, improving orthogonality between features, and achieving the effect of preventing over-fitting. After the Dropout layer, there is an LSTM two-layer structure with neurons 128 and 64, respectively, both layers of LSTM structure using the mean square error function as the loss function, and the regularization term coefficient is 0.0001. The fifth layer is a fully connected layer classified using logistic regression softmax. Of course, the neural network model in the embodiment of the present application may also be other neural network models, which is not limited in the present application.
S1032, screening the artificial customer service matched with the position information and the target service category of the user.
In one embodiment, the step S1032 of filtering the manual customer service matching the location information of the user and the target service category includes:
determining location information of a user; screening the manual customer service in the same preset range as the user according to the position information of the user; and screening out the artificial customer service with the service authority for processing the target service class from the artificial customer services in the same preset range with the user.
The position information of the user can be determined according to the registration place of the account number logged in by the user, taking the financial industry as an example: the location information of the user may be a home network point of the user. If the user logs in the account, whether the user has the home website can be detected, and if the user has the home website, the position information of the user is determined to be the website to which the user belongs. If the user does not log in, the home network point of the user cannot be determined, the city where the IP address of the user is located is determined, and the home network point of the user is determined to be all network points in the city. For example, when a user inputs a consultation message in the customer service dialog box, the user does not log in, and the electronic device cannot acquire the home network point of the user. Through detection, the IP address of the user is determined to be 43.226.236.233, so that the position information of the user is determined to be the great prosperous area of Beijing City in China. If the city where the IP address of the user is located cannot be determined, the home network point of the user is determined to be all network points in the whole country.
In the embodiment of the present application, the network nodes may be divided into four levels, which are an individual network node, a market-level all network node, a provincial-level all network node, and a national all network node. Accordingly, the preset range may be the same individual network point, all network points in the same city, all network points in the same province, or all network points in the national range.
If the individual network points to which the users belong can be determined, the artificial customer service with the service authority for processing the target service class can be screened from the individual network points to which the users belong. If the home network points of the users are all network points in the city, screening out artificial customer service with service authority for processing the target service category from all network points in the city; similarly, if the home network of the user is determined to be all network nodes nationwide, the manual customer service with the service authority for processing the target service category is screened from all network nodes nationwide.
If the artificial customer service with the service authority for processing the target service class cannot be found in the current preset range, the preset range can be expanded. As an example, if the preset range is all the websites in beijing, and the user wishes to consult the securities, the manual customer service with the securities working qualification is screened from the manual customer services in all the websites in beijing. If no idle artificial customer service with the securities working qualification exists in the artificial customer service of all the sites in Beijing, the preset range is expanded to the sites in the whole country. And screening the artificial customer service with the security working qualification from the artificial customer service of national branches.
By determining the position information of the user, the individual network points to which the user belongs can be obtained, and the artificial customer service with the service authority for processing the target service class is screened from the individual network points to which the user belongs to provide service for the user. Generally, the artificial customer service at the individual network to which the user belongs is more aware of the user than the artificial customer service not at the individual network to which the user belongs, the communication with the user is smoother, personalized service can be provided for the user, and the satisfaction degree of the user is improved.
S1033, matching the portrait data of the user with the portrait data of the screened artificial customer service, and determining the matching degree of each screened artificial customer service and the user.
Wherein the portrait data of the user may include: any one or more of user age, number of visits, historical consultation satisfaction, and historical number of complaints.
The access times are the total times of seeking the service provided by the manual customer service for the user, and the access times are increased once when the manual customer service provides the service for the user.
The historical consultation satisfaction is an average value of the satisfaction degree scores of the manual customer service after the user receives the service provided by the manual customer service. For example, the user receives services provided by artificial customer service for 5 times in total, after the first artificial customer service is finished for the user service, the user scores 80% for the satisfaction degree of the artificial customer service, after the second artificial customer service is finished for the user service, the user scores 60% for the satisfaction degree of the artificial customer service, after the third artificial customer service is finished for the user service, the user scores 90% for the satisfaction degree of the artificial customer service, after the fourth artificial customer service is finished for the user service, the user scores 100% for the satisfaction degree of the artificial customer service, and after the fifth artificial customer service is finished for the user service, the user scores 80% for the satisfaction degree of the artificial customer service. The calculation result shows that the historical consultation satisfaction degree of the user is 82%.
The historical complaint times are the times that the user is unsatisfied with the manual customer service and complaints after receiving the manual customer service providing service. For example, a user receives 20 times of services provided by manual customer service, and is dissatisfied and complained once. The historical number of complaints by the user is 1.
The portrait data for the artificial customer service may include: any one or more of response speed, historical satisfaction, age, and number of violations.
The response speed can be determined by calculating the average value of the speed of providing help for the user after receiving the request of the user for manual customer service help for a preset number of times in the near term. For example, the preset number is 1000, and it is calculated that after a human customer service receives a user request for help for nearly 1000 times, the user is provided with help in 3 seconds on average, and the response speed of the human customer service is 3 seconds.
The historical satisfaction degree of the artificial customer service can be determined by calculating the average value of the scores of the artificial customer service when the artificial customer service provides help for the user for the preset number of times in the near term. For example, the preset number is 500, and the average value of the received user scores is 89% after one artificial customer service provides service for the user, so that the historical satisfaction degree of the artificial customer service is 89%.
The violation times of one manual customer service are the times of violation behaviors of the manual customer service in providing services for users. Violations include, but are not limited to, giving an error indication when a user is being serviced, not honoring a user when a user is being serviced, or overriding the provision of a service for a user.
The matching degree of each artificial customer service and the user determined by the electronic equipment represents the degree of satisfaction of the user to each artificial customer service estimated by the electronic equipment. The higher the matching degree of the user and a certain manual customer service is, the higher the estimated satisfaction degree of the user to the customer service is.
In one embodiment, the image data of the user and the image data of each selected customer service may be input into a matching prediction model, and the degree of matching between the image data of each selected customer service and the image data of the user may be obtained.
The matching prediction model is a model obtained by training a neural network model based on a preset training set. The matching prediction model may be a LightGBM model, which is a fast, distributed, and high-performance gradient lifting framework based on a decision tree algorithm, and the matching prediction model may also be other neural network models, which is not specifically limited in the present application.
By adopting the neural network model trained based on the preset training set, the matching degree between the portrait data of each artificial customer service and the portrait data of the user is predicted, the predicted matching degree value is more accurate, and the matching degree between the portrait data of each artificial customer service and the portrait data of the user can be closer to the real scene.
By adopting the embodiment of the application, the home node of the user can be determined by determining the position information of the user. The manual customer service in the user home network site is more aware of the user and is more smoothly communicated with the user. When distributing artificial customer service of the home network for the user, compared with the mode of randomly distributing the screened artificial customer service for the user or distributing the screened artificial customer service for the user in sequence in the prior art, the method distributes the artificial customer service for the user according to the matching degree of the portrait data of each artificial customer service and the portrait data of the user. The user representation represents characteristic data of the user, and the artificial customer service representation data represents characteristic data of the artificial customer service. The user portrait data is matched with the portrait data of each artificial customer service, the artificial customer service is distributed to the user, and the matching degree of the artificial customer service distributed to the user and the user is higher.
In an embodiment of the present invention, as shown in fig. 3, the step S1011 of determining the target service category consulted by the user according to the other consultation messages input by the user in the customer service dialog box may be implemented as follows:
s301, according to the sequence of the consultation message time input by the user in the customer service dialog box from late to early, identifying the service type of each consultation message one by one.
S302, if the service category of a consultation message is identified, terminating the identification, and determining the identified service category of the consultation message as the target service category consulted by the user.
After the user inputs the consultation message in the customer service dialog box, the artificial intelligent robot can answer the consultation message. If the user feels that the artificial intelligence robot cannot answer the user consultation message, the user usually selects to transfer to artificial customer service. Therefore, after the fact that the user has the manual change requirement is identified, the service category to which each piece of consultation message belongs is identified one by one according to the sequence of the time of the consultation messages input by the user in the customer service dialog box from late to early, and the speed of identifying the service category to which the user consultation message belongs can be improved.
S303, if the service type of any consultation message cannot be determined after identifying all the consultation messages input by the user in the customer service dialog box, determining that the target service type consulted by the user cannot be identified.
Identifying each piece of consultation information in the sequence from late to early, and if the target service type consulted by the user cannot be identified, namely no artificial customer service matched with the information consulted by the user exists, dividing the target service type consulted by the user into unrecognizable types. Under the condition that the service category of the consultation message of the user cannot be accurately determined, in order to ensure that the consultation message of the user can be processed by the artificial customer service, the artificial customer service with the highest authority can be distributed to the user, and the condition that the artificial customer service cannot be distributed to the user is avoided.
The method for identifying the business category to which each piece of consultation message belongs one by one according to the sequence of the time of the consultation messages input by the user in the customer service dialog box from late to early determines the target business category consulted by the user, and the user can choose to seek the help of manual customer service when the artificial intelligent customer service robot cannot provide the satisfactory answer to the user because the user inputs the consultation messages. By adopting the method and the device, the business category to which the consultation message belongs is identified in a reverse order mode, the business category to which the consultation message belongs of the user can be determined more quickly, and the time for distributing manual customer service to the user is reduced. After all the consultation messages input by the user in the customer service dialog box are identified, if the service type of any consultation message can not be determined, the target service type consulted by the user is determined to be unidentifiable.
In an embodiment of the present invention, the step S102 of determining whether the user has a need of customer service transfer according to the consultation message may be implemented in the following two ways:
and identifying the business class to which the consultation message belongs, and determining that the user has the requirement of transferring to the manual customer service if the business class to which the consultation message belongs is the class for expressing the transfer to the manual customer service.
In S1031, the target service category consulted by the user may further include a category for manual customer service.
The manner of determining whether the service category to which the consultation message belongs is the category for indicating the service of the manual service is the same as that of S1031, and details are not repeated here.
In order to avoid that the normal consultation message of the user is identified as having the requirement of transferring to the manual customer service by mistake, a confidence coefficient can be set, and when the class probability of transferring to the manual customer service output by the target service class judgment model is greater than the preset confidence coefficient, the user is determined to have the requirement of transferring to the manual customer service.
For example, the preset confidence level is 90%. When the target business class judgment model determines that a piece of consultation message belongs to the manual customer service transfer class, and the probability that the piece of consultation message belongs to the manual customer service transfer class is 70%, the fact that the user has the manual customer service transfer requirement cannot be determined because 70% is less than 90%.
And secondly, identifying whether the consultation message comprises preset keywords or not, and if the consultation message comprises the preset keywords, determining that the user has the requirement of transferring to manual customer service.
Wherein, the preset keywords may include: the terms such as manual customer service, manual transfer, manual service and the like can reflect the requirement of the user for manual customer service transfer.
As an example, the preset keywords are: "manual customer service", "manual transfer", and "manual service". When the user enters and sends "i need manual service" in the customer service dialog. And after that, the fact that the consultation message sent by the user contains a preset keyword 'manual service' is detected, so that the fact that the user has the requirement of transferring manual customer service is determined.
Therefore, the first mode adopts a target service class judgment model based on the neural network to confirm whether the user has the requirement of manual customer service, and the identification is more accurate. And a confidence coefficient is added, and the user is determined to have the requirement of transferring to the manual customer service only when the category of the manual customer service is greater than the preset confidence coefficient, so that the possibility of false recognition is reduced, the workload of the manual customer service is also reduced, the efficiency of the manual customer service is improved, and the waiting time of the user who really needs the assistance of the manual customer service is also reduced.
And in the second mode, the keyword matching method is adopted to determine that the user has the requirement of transferring to the artificial customer service, and compared with the first mode, the second mode is adopted to determine whether the user has the requirement of transferring to the artificial customer service, the calculation of the user consultation message through a neural network is not needed, and the determination speed is higher.
The following describes a routing method provided in the embodiment of the present application with reference to a specific scenario, as shown in fig. 4:
s401, the consultation messages input and sent by the user in the customer service dialog box are sorted according to time sequence, and the sorting is Q = { Q1, Q2 … Qn }, wherein Qn is the latest input consultation message.
S402, judging whether n is larger than or equal to 1. If n is greater than or equal to 1, executing S403; if n is less than 1, S404 is executed.
If n <1, that is, all the consultation messages of the user have been recognized, it is determined that the service class of the consultation of the user is 'unrecognizable', and S407 is performed.
S403, identifying Qn, and judging whether the confidence of the business class of Qn 'manual' is greater than alpha. If yes, let n = n-1, and execute S402; if not, go to S405.
S404, determining that the service type consulted by the user is 'unrecognizable', and executing S407.
S405, judging whether the business type Xy exists or not, and enabling the confidence coefficient of the Qn to be returned to the business type Xy to be larger than alpha. If yes, S406 is executed, otherwise, n = n-1 is set, and S402 is executed.
The confidence coefficient for identifying the classification of the user consultation message into the service category Xy is the probability of the classification of the user consultation message into the service category Xy. For example, α =90%, the confidence that the user advisory message is classified into the business category Xy is 70%, at this time, the confidence that the user advisory message is classified into the business category Xy is less than α, let n = n-1, and S402 is performed.
S406, classifying the user into an Xy business category.
And S407, judging whether the user has the home website, if so, executing S408, and if not, executing S409.
S408, setting the range of matching the manual customer service for the user as the website, and executing S412.
S409, judging whether the user position can be determined according to the user IP address. If yes, go to S410; if not, S411 is executed.
S410, setting the range of matching the manual customer service for the user as all the websites of the city range of the user position, and executing S412.
S411, setting the range for matching the manual customer service for the user as the maximum range.
For example, the maximum range may be all dots nationwide.
S412, judging whether the service type consulted by the user is 'unrecognizable'. If yes, go to S413; if not, go to S414.
S413, from the range setting for matching the manual customer service for the user, the manual customer service with all the rights is screened, and S415 is executed.
And S414, screening the artificial customer service with the Xy business class authority from the range setting of matching the artificial customer service for the user.
And S415, carrying out satisfaction prediction on the screened artificial customer service.
And S416, screening the former N artificial customer services according to the satisfaction degree predicted value.
S417, informing the former N manual customer services to perform order grabbing, if the manual customer services are performed, distributing the manual customer services which are successfully subjected to order grabbing for the user, and determining that the matching is successful.
And S418, judging whether the matching is successful within the preset time length. If yes, matching is completed; if not, go to S419.
S419, judging whether the range of the user matched with the manual customer service is the maximum range. If yes, go to S420; if not, S421 is executed.
And S420, allowing all manual customer service orders to be preempted, and completing matching when the customer service orders are preempted.
S421, the range is expanded by one step, and the process returns to S412.
Based on the same inventive concept, an embodiment of the present application further provides a routing apparatus, applied to an electronic device, as shown in fig. 5, the apparatus includes:
a receiving module 501, configured to receive a consultation message input by a user in a customer service dialog;
a judging module 502, configured to judge whether the user has a manual customer service transfer requirement according to the consultation message;
a determining module 503, configured to determine, if it is determined that the user has a need for manual customer service, a matching degree between each manual customer service and the user according to other consultation messages input by the user in the customer service dialog box, the location information of the user, and the portrait data of the user and each manual customer service;
and the distribution module 504 is used for distributing the manual customer service to the user according to the matching degree of each manual customer service and the user.
Optionally, the determining module 503 is specifically configured to:
determining the target service type consulted by the user according to other consultation messages input by the user in the customer service dialog box;
screening artificial customer service matched with the position information and the target service category of the user;
and matching the portrait data of the user with the portrait data of the screened artificial customer service, and determining the matching degree of each screened artificial customer service and the user.
Optionally, the determining module 503 is specifically configured to:
identifying the business category of each consultation message one by one according to the sequence of the time of the consultation messages input by the user in the customer service dialog box from late to early;
if the service category of one consultation message is identified, terminating the identification, and determining the identified service category of the consultation message as a target service category consulted by the user;
and if the service type of any consultation message cannot be determined after all the consultation messages input by the user in the customer service dialog box are identified, determining that the target service type consulted by the user cannot be identified.
Optionally, the determining module 503 is specifically configured to:
determining location information of a user;
screening the manual customer service in the same preset range as the user according to the position information of the user;
and screening out the artificial customer service with the service authority for processing the target service class from the artificial customer services in the same preset range with the user.
Optionally, the determining module 503 is specifically configured to:
inputting the portrait data of the user and the portrait data of each screened artificial customer service into a matching prediction model to obtain the matching degree between the portrait data of each screened artificial customer service and the portrait data of the user, wherein the matching prediction model is a model obtained by training a neural network model based on a preset training set.
Optionally, the determining module 502 is specifically configured to:
identifying a service class to which the advisory message belongs; if the business category to which the consultation message belongs is a category for representing manual customer service transfer, determining that the user has the demand of manual customer service transfer; alternatively, the first and second electrodes may be,
and identifying whether the consultation message comprises a preset keyword, and if the consultation message comprises the preset keyword, determining that the user has the requirement of transferring to manual customer service.
Optionally, the user profile data includes any one or more of user age, visit times, historical consultation satisfaction and historical complaint times, and the artificial customer service profile data includes any one or more of response speed, historical satisfaction, age and violation times.
An embodiment of the present invention further provides an electronic device, as shown in fig. 6, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604, where the processor 601, the communication interface 602, and the memory 603 complete mutual communication through the communication bus 604,
a memory 603 for storing a computer program;
the processor 601 is configured to implement the method steps in the above method embodiments when executing the program stored in the memory 603.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In a further embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any of the above routing methods.
In a further embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the routing methods of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus, the electronic device and the storage medium, since they are substantially similar to the method embodiments, the description is relatively simple, and the relevant points can be referred to the partial description of the method embodiments.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A routing method, comprising:
receiving a consultation message input by a user in a customer service dialog box;
judging whether the user has the requirement of transferring to the manual customer service according to the consultation message;
if the user is determined to have the requirement of transferring to the manual customer service, determining the matching degree of each manual customer service and the user according to other consultation messages input by the user in the customer service dialog box, the position information of the user and the image data of the user and each manual customer service;
and distributing the manual customer service to the user according to the matching degree of each manual customer service and the user.
2. The method of claim 1, wherein determining how well each customer service matches the user based on other advisory messages entered by the user in the customer service dialog box, location information of the user, and profile data of the user and each customer service comprises:
determining the target service type consulted by the user according to other consultation messages input by the user in the customer service dialog box;
screening the artificial customer service matched with the position information of the user and the target service category;
and matching the portrait data of the user with the portrait data of the screened artificial customer service, and determining the matching degree of each screened artificial customer service and the user.
3. The method of claim 2, wherein determining the target business category consulted by the user according to other consultation messages input by the user in the customer service dialog box comprises:
identifying the service type of each consultation message one by one according to the sequence of the consultation message time input by the user in the customer service dialog box from late to early;
if the service category of one consultation message is identified, terminating the identification, and determining the identified service category of the consultation message as a target service category consulted by the user;
and if the service type of any consultation message cannot be determined after all the consultation messages input by the user in the customer service dialog box are identified, determining that the target service type consulted by the user cannot be identified.
4. The method of claim 2, wherein the filtering of the artificial customer service matching the user's location information and the target business category comprises:
determining location information of the user;
screening the manual customer service in the same preset range with the user according to the position information of the user;
and screening out the artificial customer service with the service authority for processing the target service class from the artificial customer services in the same preset range with the user.
5. The method of claim 2, wherein matching the user profile data with the screened profile data of the artificial customer service and determining a degree of match of each of the screened artificial customer services with the user comprises:
inputting the portrait data of the user and the portrait data of each screened artificial customer service into a matching prediction model to obtain the matching degree between the portrait data of each screened artificial customer service and the portrait data of the user, wherein the matching prediction model is obtained by training a neural network model based on a preset training set.
6. The method of claim 1, wherein said determining whether said user has a need for manual customer service based on said advisory message comprises:
identifying a service class to which the advisory message belongs; if the business category to which the consultation message belongs is a category for representing manual customer service transfer, determining that the user has the demand of manual customer service transfer; alternatively, the first and second electrodes may be,
and identifying whether the consultation message comprises a preset keyword or not, and if the consultation message comprises the preset keyword, determining that the user has the requirement of transferring to manual customer service.
7. The method of claim 5, wherein the user profile data includes any one or more of user age, number of visits, historical consultation satisfaction, and historical number of complaints, and the artificial customer service profile data includes any one or more of response speed, historical satisfaction, age, and number of violations.
8. A routing device, comprising:
the receiving module is used for receiving the consultation message input by the user in the customer service dialog box;
the judging module is used for judging whether the user has the requirement of transferring to the manual customer service according to the consultation message;
the determining module is used for determining the matching degree of each artificial customer service and the user according to other consultation messages input by the user in the customer service dialog box, the position information of the user and the portrait data of the user and each artificial customer service if the user is determined to have the requirement of transferring the artificial customer service;
and the distribution module is used for distributing the manual customer service to the user according to the matching degree of each manual customer service and the user.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 7 when executing a program stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110730762.7A CN113256173A (en) | 2021-06-30 | 2021-06-30 | Routing method, routing device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110730762.7A CN113256173A (en) | 2021-06-30 | 2021-06-30 | Routing method, routing device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113256173A true CN113256173A (en) | 2021-08-13 |
Family
ID=77190160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110730762.7A Pending CN113256173A (en) | 2021-06-30 | 2021-06-30 | Routing method, routing device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113256173A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115099629A (en) * | 2022-06-28 | 2022-09-23 | 中国银行股份有限公司 | Customer service demand evaluation distribution method and system, electronic device and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060136474A1 (en) * | 2004-12-21 | 2006-06-22 | Inventec Corporation | Customer service automatic answering system and method |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | 中国移动通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN110213450A (en) * | 2019-05-14 | 2019-09-06 | 长沙手之声信息科技有限公司 | Based on polycentric sign language online customer service allocation management method, apparatus and system |
| CN110377712A (en) * | 2019-07-12 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of intelligence conversation switching method, device, equipment and storage medium |
| CN110837587A (en) * | 2019-09-30 | 2020-02-25 | 北京健康之家科技有限公司 | Data matching method and system based on machine learning |
| CN110995944A (en) * | 2019-12-19 | 2020-04-10 | 易谷网络科技股份有限公司 | Customer service seat recommendation method and device, customer service equipment and storage medium |
| CN111585874A (en) * | 2020-07-17 | 2020-08-25 | 支付宝(杭州)信息技术有限公司 | Method and system for automatically controlling service group |
| CN112215448A (en) * | 2019-07-11 | 2021-01-12 | 北京京东尚科信息技术有限公司 | Method and device for distributing customer service |
-
2021
- 2021-06-30 CN CN202110730762.7A patent/CN113256173A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060136474A1 (en) * | 2004-12-21 | 2006-06-22 | Inventec Corporation | Customer service automatic answering system and method |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | 中国移动通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN110213450A (en) * | 2019-05-14 | 2019-09-06 | 长沙手之声信息科技有限公司 | Based on polycentric sign language online customer service allocation management method, apparatus and system |
| CN112215448A (en) * | 2019-07-11 | 2021-01-12 | 北京京东尚科信息技术有限公司 | Method and device for distributing customer service |
| CN110377712A (en) * | 2019-07-12 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of intelligence conversation switching method, device, equipment and storage medium |
| CN110837587A (en) * | 2019-09-30 | 2020-02-25 | 北京健康之家科技有限公司 | Data matching method and system based on machine learning |
| CN110995944A (en) * | 2019-12-19 | 2020-04-10 | 易谷网络科技股份有限公司 | Customer service seat recommendation method and device, customer service equipment and storage medium |
| CN111585874A (en) * | 2020-07-17 | 2020-08-25 | 支付宝(杭州)信息技术有限公司 | Method and system for automatically controlling service group |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115099629A (en) * | 2022-06-28 | 2022-09-23 | 中国银行股份有限公司 | Customer service demand evaluation distribution method and system, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11176154B1 (en) | Collaborative dataset management system for machine learning data | |
| AU2021258049A1 (en) | Cooperatively operating a network of supervised learning processors to concurrently distribute supervised learning processor training and provide predictive responses to input data | |
| CN109816483B (en) | Information recommendation method and device and readable storage medium | |
| US20100077301A1 (en) | Systems and methods for electronic document review | |
| US10410626B1 (en) | Progressive classifier | |
| Vinod et al. | Simulation-based metamodels for scheduling a dynamic job shop with sequence-dependent setup times | |
| KR102285142B1 (en) | Apparatus and method for recommending learning data for chatbots | |
| CN112667825B (en) | Intelligent recommendation method, device, equipment and storage medium based on knowledge graph | |
| CN113052676A (en) | Intelligent wind control decision method, device, equipment and readable storage medium | |
| US11729317B1 (en) | Systems and methods for electronic request routing and distribution | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| JP7409061B2 (en) | Document management device and document management program | |
| KR20200094311A (en) | Method for providing chatbot service, apparatus and system thereof | |
| US20220277409A1 (en) | Methods and systems for civil administration in smart city based on internet of things (iot) | |
| CN110689211A (en) | Method and device for evaluating website service capability | |
| CN114548118A (en) | Service conversation detection method and system | |
| CN113256173A (en) | Routing method, routing device, electronic equipment and storage medium | |
| CN114330550A (en) | Model fusion strategy selection method and device and electronic equipment | |
| US8073717B2 (en) | Systems for digital management of underwriting insurance contracts | |
| CN115577983B (en) | Enterprise task matching method based on block chain, server and storage medium | |
| CN111353728A (en) | Risk analysis method and system | |
| CN114238615B (en) | Enterprise service result data processing method and system | |
| CN115660101A (en) | Data service providing method and device based on service node information | |
| CN116187675A (en) | Task allocation method, device, equipment and storage medium | |
| US11822562B2 (en) | Unstructured text processing for geographical location determination system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210813 |