CN110533324B - Method and device for automatically distributing insurance customer service - Google Patents

Method and device for automatically distributing insurance customer service Download PDF

Info

Publication number
CN110533324B
CN110533324B CN201910809115.8A CN201910809115A CN110533324B CN 110533324 B CN110533324 B CN 110533324B CN 201910809115 A CN201910809115 A CN 201910809115A CN 110533324 B CN110533324 B CN 110533324B
Authority
CN
China
Prior art keywords
client
customer service
insurance
information
insurance customer
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.)
Active
Application number
CN201910809115.8A
Other languages
Chinese (zh)
Other versions
CN110533324A (en
Inventor
陈健
柳岸
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Huize Times Technology Co ltd
Original Assignee
Shenzhen Huize Times Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Huize Times Technology Co ltd filed Critical Shenzhen Huize Times Technology Co ltd
Priority to CN201910809115.8A priority Critical patent/CN110533324B/en
Publication of CN110533324A publication Critical patent/CN110533324A/en
Application granted granted Critical
Publication of CN110533324B publication Critical patent/CN110533324B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q10/06311—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
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • Finance (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Technology Law (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The invention provides an automatic distribution method and a device of insurance customer service, wherein the method comprises the following steps: acquiring consultation information of a client; obtaining product information corresponding to the consultation information of the client according to a preset automatic distribution model; determining insurance customer service matched with product information corresponding to the consultation information of the client according to the corresponding relation between a preset product and the insurance customer service; and constructing a communication link between the insurance customer service and the client to realize the communication between the client and the insurance customer service. The method achieves the aim of accurately and automatically distributing insurance customer service for knowing the type of the insurance products according to the type of the insurance products which are required to be known by the client, so that the insurance customer service is more comprehensive when answering the questions of the client for consulting the type of the insurance products.

Description

Method and device for automatically distributing insurance customer service
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for automatically distributing insurance customer service.
Background
With the rise of people's social risk awareness and the development of computer technology, more and more people know and learn about the way of insurance products through face-to-face communication with sales personnel, becoming a more efficient way of internet communication.
But in this more efficient mode of communication, a salesperson is often faced with a large customer base. Generally, a salesperson contacts about 50 customers a day, and in these customer groups, each customer wants to know different products, and in such an environment, an insurer is required to grasp all the products and their detailed rules. If the insurance customer service does not completely know the insurance products consulted by the user, some questions provided by the client cannot be answered, so that how to automatically allocate the insurance customer service for the user and effectively improve the accuracy of allocating the insurance customer service becomes a core technical problem to be solved at present.
Disclosure of Invention
In view of this, the embodiment of the present invention provides an automatic insurance customer service distribution method, which is used for accurately and automatically distributing an insurance customer service knowing an insurance product according to the type of the insurance product that a client needs to know, so that the insurance customer service is more comprehensive when answering the problem of the client consulting the insurance product.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
a method of automatic allocation of insurance customer service, comprising:
acquiring consultation information of a client;
obtaining product information corresponding to the consultation information of the client according to a preset automatic distribution model;
determining insurance customer service matched with product information corresponding to the consultation information of the client according to the corresponding relation between a preset product and the insurance customer service;
and constructing a communication link between the insurance customer service and the client to realize the communication between the client and the insurance customer service.
Optionally, the obtaining of the product information corresponding to the customer consultation information according to the preset automatic allocation model includes:
according to the consultation information of the client, matching is carried out in a slot value model in the preset automatic allocation model, and product information corresponding to the consultation information of the client is obtained; the model is obtained by preliminarily screening the slot value model according to the corresponding relation between the chat records of the client and the insurance customer service and the product information, the corresponding relation between the network information and the product information and the grammatical rules.
Optionally, before obtaining the product information corresponding to the customer consultation information according to the preset automatic allocation model, the method further includes:
judging whether the consultation information is information of a consultation insurance product or not by using a corpus in a preset intention model; the corpus is a corpus database obtained by preliminarily screening the corpus according to the chat records, the network information and the grammar rules of the client and the insurance customer service in the past;
and if the consultation information is judged to be the information of consulting insurance products, executing the automatic allocation model according to the preset automatic allocation model to obtain the product information corresponding to the consultation information of the client.
Optionally, the determining, according to a preset correspondence between the product and the insurance customer service, the insurance customer service matched with the product information corresponding to the consultation information of the client includes:
determining an insurance customer service list matched with the product information corresponding to the consultation information of the client in the corresponding relation between the preset product and the insurance customer service;
and finding out an businessstate insurance customer service according to the insurance customer service list obtained by matching and the preset sequence of the insurance customer service list.
Optionally, after obtaining the consulting information of the client, the method further includes:
acquiring personal information of a client; wherein the personal information of the customer includes: an insurance purchase record for the customer;
judging whether the client has own exclusive insurance customer service or not according to the insurance purchase record;
if the client is judged to have own exclusive insurance customer service, directly distributing the client to the insurance customer service;
and if the client is judged not to have the exclusive insurance customer service, executing an automatic distribution model according to the preset automatic distribution model to obtain the product information corresponding to the consultation information of the client.
An apparatus for automatic distribution of insurance customer service, comprising:
the first acquisition unit is used for acquiring consultation information of a client;
the second acquisition unit is used for acquiring product information corresponding to the consultation information of the client according to a preset automatic distribution model;
the determining unit is used for determining insurance customer service matched with the product information corresponding to the consultation information of the client according to the corresponding relation between the preset product and the insurance customer service;
and the construction unit is used for constructing a communication link between the insurance customer service and the client so as to realize the communication between the client and the insurance customer service.
Optionally, the second obtaining unit includes:
the second acquisition subunit is used for matching in the slot value model in the preset automatic allocation model according to the consultation information of the client to obtain the product information corresponding to the consultation information of the client; the model is obtained by preliminarily screening the slot value model according to the corresponding relation between the chat records of the client and the insurance customer service and the product information, the corresponding relation between the network information and the product information and the grammatical rules.
Optionally, the apparatus for automatically allocating insurance customer service further includes:
the first judgment unit is used for judging whether the consultation information is the information of the consultation insurance product or not by utilizing the corpus in the preset intention model; the corpus is a corpus database obtained by preliminarily screening the corpus according to the chat records, the network information and the grammar rules of the client and the insurance customer service in the past;
and if the first judging unit judges that the consultation information is the information of consulting insurance products, the second acquiring unit is utilized to acquire the product information corresponding to the customer consultation information according to a preset automatic distribution model.
Optionally, the determining unit includes:
a determining subunit, configured to determine, in the preset correspondence between the product and the insurance customer service, an insurance customer service list matched with the product information corresponding to the consultation information of the client;
and the third acquisition unit is used for finding out an insurance customer service in a non-busy state according to the insurance customer service list obtained by matching and the preset sequence of the insurance customer service list.
Optionally, the apparatus for automatically allocating insurance customer service further includes:
a fourth acquisition unit configured to acquire personal information of the customer; wherein the personal information of the customer includes: an insurance purchase record for the customer;
the second judgment unit is used for judging whether the client has own exclusive insurance customer service according to the insurance purchase record;
the distribution unit is used for directly distributing the client to the insurance customer service if the client has the exclusive insurance customer service judged by the second judgment unit;
and if the client is judged to have no exclusive insurance customer service, the second acquisition unit is utilized to obtain the product information corresponding to the consultation information of the client according to a preset automatic allocation model.
According to the scheme, in the method and the device for automatically distributing the insurance customer service, the consultation information of the client is acquired; obtaining product information corresponding to the consultation information of the client according to a preset automatic distribution model; determining insurance customer service matched with product information corresponding to the consultation information of the client according to the corresponding relation between a preset product and the insurance customer service; and constructing a communication link between the insurance customer service and the client to realize the communication between the client and the insurance customer service. The method achieves the aim of accurately and automatically distributing insurance customer service for knowing the type of the insurance products according to the type of the insurance products which are required to be known by the client, so that the insurance customer service is more comprehensive when answering the questions of the client for consulting the type of the insurance products.
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 embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a specific flowchart of a method for automatically allocating insurance customer services according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for automatically assigning insurance customer services according to another embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for automatically assigning insurance customer services according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of an apparatus for automatic distribution of insurance customer service according to another embodiment of the present invention;
FIG. 5 is a schematic diagram of an apparatus for automatic distribution of insurance customer service according to another embodiment of the present invention;
fig. 6 is a schematic diagram of an apparatus for automatically allocating insurance customer service according to another 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 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 invention.
An embodiment of the present invention provides a method for automatically allocating insurance customer services, as shown in fig. 1, including:
and S101, acquiring consultation information of the client.
Wherein, the consultation information of the client can be 'please help me XXX'; i want to see "XXX"; "I want to buy XXX insurance", etc.
Specifically, the consultation information of the client can be acquired in a service platform of the insurance industry, and can also be acquired in internet tools such as WeChat and the like.
And S102, obtaining product information corresponding to the consultation information of the client according to a preset automatic distribution model.
The automatic distribution model can be obtained through neural network training, dynamic matching can be performed according to statement information and the like prestored in the model to obtain product information desired by a client, namely, one-time prediction judgment is performed according to consultation information of the client to obtain product information which is possibly desired by the client.
Optionally, in another embodiment of the present invention, one implementation manner of step S102 includes:
and according to the consultation information of the client, matching in a slot value model in a preset automatic allocation model to obtain the product information corresponding to the consultation information of the client.
The slot value model is obtained by performing preliminary screening according to the corresponding relation between the chat records of the client and the insurance customer service and the product information, the corresponding relation between the network information and the product information and grammatical rules.
Specifically, the slot value model may be labeled by B-I, and in order to distinguish product hierarchies, LAYER _ ONE, LAYER _ TWO, and the like are used for distinguishing, and a first letter is used in a label for distinguishing, so that the first hierarchy is defined as B _ L _ O _ NAME, I _ L _ O _ NAME, the second hierarchy is defined as B _ L _ T _ NAME, I _ L _ T _ NAME, and so on; such as: the "risk of X major disease in my want to buy adult insurance" marker is:
i am O
Want to O
Buy O
Become into B_L_O_NAME
Human being I_L_O_NAME
Health-care product I_L_O_NAME
Danger (Risk) I_L_O_NAME
Is/are as follows O
X B_L_T_NAME
Heavy load I_L_T_NAME
Big (a) I_L_T_NAME
Disease of the heart I_L_T_NAME
Disease and illness I_L_T_NAME
Danger (Risk) I_L_T_NAME
The "I want to buy X regular life insurance" is marked as:
Figure BDA0002184551590000061
Figure BDA0002184551590000071
and (5) sending the recorded linguistic data into the Bert for training to generate a trough value model.
Optionally, in another embodiment of the present invention, before step S102, the method further includes:
and judging whether the consultation information is the information of the consultation insurance product or not by utilizing the corpus in the preset intention model.
The corpus database is obtained by preliminarily screening the corpus set according to the chat records, the network information and the grammar rules of the client and the insurance customer service.
Specifically, rules can be constructed according to a backhaul-Naur Form mode to generate some corpora of insurance industry, such as:
defining a PREFIX as PREFIX, i.e. helping me, please help me, i.e. i want to see;
defining the PRODUCT as PRODUCT, i.e. number 2 | Darwin number 1 of the guardian;
defining the rule as DETAIL, i.e. the insurable time | exemption right;
defining the grammar rule as [ PREFIX ] < PRODUCT > [ DETAIL ]
In the rule, "|" indicates either, "[ ] indicates optional," < > "indicates optional,
and after the corpora are obtained through the steps, concentrated screening and cleaning are carried out, redundant emoticons and messy codes are removed, and a corpus set is formed.
It should be noted that the intention model is to label the intention according to a part of the corpus in the corpus set, which is not specifically limited herein, depending on the application environment; the concrete amount of the used corpora is determined according to actual requirements, and is not limited herein, and the concrete amount is within the protection scope of the application. When the intention is labeled, a binary label can be adopted, a statement intended for the consultation insurance product is labeled as 1, a statement intended for the consultation insurance product is labeled as 2, and the labeled linguistic data is sent into a Convolutional Neural Network (CNN) for training to generate an intention model.
It should be noted that the slot value model in the above embodiment may also be obtained by marking the slot value according to the intention model, and similarly, the marked corpus may also be sent to a Convolutional Neural Network (CNN) for training to generate the intention model. And the intention model and the slot value model can uniformly adopt json format when returning contents, such as:
{
is _ query: 1; whether it is a consulting product, 0 is no, 1 is yes
LAYER _ ONE xxxx; // name corresponding to the first level of the product
LAYER _ TWO: xxxx// product second level corresponding name
...// name corresponding to final product level
}
In the specific implementation process of this embodiment, if it is determined that the advisory information is information of an advisory insurance product, the product information corresponding to the customer advisory information is obtained according to a preset automatic allocation model.
S103, determining the insurance customer service matched with the product information corresponding to the consultation information of the client according to the preset corresponding relation between the product and the insurance customer service.
It should be noted that, when the corresponding relationship between the product and the insurance customer service is constructed, the insurance product can be classified in advance and labeled. After the insurance products are classified in various modes such as the characteristics of the insurance products, the functions of the insurance products or audience groups of the insurance products, the insurance products correspond to insurance customer service to form a preset corresponding relation between the products and the insurance customer service, and the insurance products can also be understood as a relation library of the insurance products and the insurance customer service.
In the specific implementation process of the embodiment, insurance products can be classified greatly according to the modes of adult insurance, child insurance, middle-aged and old-aged insurance, characteristic insurance, enterprise insurance, travel insurance, traffic insurance, property insurance and the like; subdividing the large categories again, and finally, setting the final layer as a specific insurance product. Taking adult insurance as an example, first, adult insurance is divided into: major diseases, health care, life guarantee, accident guarantee and financial annuity insurance, and secondly, subdividing the classification obtained in the last step, such as the major disease risk: XXX major disease insurance, XXX major disease insurance; the life insurance is divided into: XX is used for life insurance and XXX life insurance, for convenient retrieval, a table is established according to the hierarchy, and specific insurance customer service is filled in the table. For example, the correspondence between the XXX major disease insurance and the insurance customer service may be:
NAME CONTACTS
XXX big disease insurance Zhang San, Li Siang and Wang Wu
XXX major disease insurance ...
... ...
Optionally, in another embodiment of the present invention, as shown in fig. 2, an implementation manner of step S103 includes:
s201, determining an insurance customer service list matched with the product information corresponding to the consultation information of the client in the preset corresponding relation between the product and the insurance customer service.
It should be noted that in the step S103, it can be determined that the insurance customer service matched with the product information corresponding to the consultation information of the client is not a single insurance customer service in the preset corresponding relationship between the product and the insurance customer service, if a plurality of insurance customer services are good at the product sale consulted by the client, then the plurality of insurance customer services need to be sorted, and the sorting mode can be sorting modes such as qualification, rating, number of good comments of the user, and the like.
S202, finding out the insurance customer service in the non-busy state according to the insurance customer service list obtained by matching and the preset sequence of the insurance customer service list.
Specifically, the insurance customer service list can also display the current state of the insurance customer service, which can be on-line, off-line, away, busy, etc., and according to the sorting of the insurance customer service list, an on-line insurance customer service is found from top to bottom for the communication between the subsequent insurance customer service and the client.
And S104, constructing a communication link between the insurance customer service and the client to realize the communication between the client and the insurance customer service.
Specifically, in the internet communication process, the user can be prompted to click the head portrait of the insurance customer service and the like by recommending the insurance customer service matched with the product information corresponding to the consultation information of the client to the user, so that a communication link between the insurance customer service and the client is established.
In the specific implementation process of the invention, a basic customer service can communicate with the customer service, the basic customer service is only responsible for simple conversation, all insurance type product information can not be understood, chat information is uploaded to a server in real time in the conversation process, and after the server acquires consultation information between the basic customer service and a client, the consultation information is matched in an automatic distribution model according to data in the consultation information to obtain product information required by the client, and the insurance customer service matched with the product information corresponding to the consultation information of the client is obtained through the corresponding relation between the product information and the insurance customer service. At this time, the basic customer service may recommend the customer to insurance customer service matched with the product information corresponding to the consultation information of the customer. Therefore, the client can obtain more professional responses when consulting the insurance products in the follow-up process.
Optionally, in another embodiment of the present invention, after step S101, as shown in fig. 3, the method further includes:
s301, acquiring personal information of the client.
Wherein the personal information of the client includes: the customer's insurance purchase record.
S302, judging whether the client has own exclusive insurance customer service according to the insurance purchase record.
Specifically, in the process that a user purchases an insurance product before, the insurance customer service can be subjected to star level evaluation once, and the like, if the star level evaluation of the insurance customer service by the client is higher, a record can be made once, and the client can directly establish a communication link with the insurance customer service through the record in the previous system when purchasing the insurance product next time; similarly, when the client performs star-level evaluation on the insurance customer service, the client can set the insurance customer service as the own exclusive insurance customer service, and the contact way of the insurance customer service is reserved, so that the client can conveniently contact the insurance customer service when needing to purchase an insurance product next time.
In the specific implementation process of this embodiment, if it is determined that the client has its own exclusive insurance customer service, step S303 is executed; if it is determined that the client does not have the exclusive insurance service, step S304 is executed.
And S303, distributing the client to insurance customer service.
And S304, obtaining product information corresponding to the consultation information of the client according to a preset automatic distribution model.
It should be noted that the preset automatic allocation model is consistent with the preset automatic allocation model in step S102.
According to the scheme, in the method for automatically distributing the insurance customer service, the consultation information of the client is obtained; obtaining product information corresponding to the consultation information of the client according to a preset automatic distribution model; determining insurance customer service matched with product information corresponding to the consultation information of the client according to the corresponding relation between a preset product and the insurance customer service; and constructing a communication link between the insurance customer service and the client to realize the communication between the client and the insurance customer service. The method achieves the aim of accurately and automatically distributing insurance customer service for knowing the type of the insurance products according to the type of the insurance products which are required to be known by the client, so that the insurance customer service is more comprehensive when answering the questions of the client for consulting the type of the insurance products.
Another embodiment of the present invention provides an apparatus for automatically allocating insurance customer service, as shown in fig. 4, including:
a first obtaining unit 401, configured to obtain consultation information of a client.
A second obtaining unit 402, configured to obtain product information corresponding to the consultation information of the client according to a preset automatic allocation model.
Optionally, in another embodiment of the present invention, an implementation manner of the second obtaining unit 402 includes:
and the second acquisition subunit is used for matching the slot value models in the preset automatic allocation model according to the consultation information of the client to obtain the product information corresponding to the consultation information of the client.
The slot value model is obtained by performing preliminary screening according to the corresponding relation between the chat records of the client and the insurance customer service and the product information, the corresponding relation between the network information and the product information and grammatical rules.
Optionally, in another embodiment of the present invention, the apparatus for automatically allocating insurance customer service further includes:
and the first judgment unit is used for judging whether the consultation information is the information of the consultation insurance product or not by utilizing the corpus in the preset intention model.
The corpus database is obtained by preliminarily screening the corpus set according to the chat records, the network information and the grammar rules of the client and the insurance customer service.
Specifically, if the first determining unit determines that the consulting information is the information of consulting insurance products, the second obtaining unit 402 is used to obtain the product information corresponding to the consulting information of the client according to the preset automatic allocation model.
The determining unit 403 is configured to determine, according to a preset correspondence between a product and insurance customer service, insurance customer service matched with product information corresponding to the consultation information of the client.
Optionally, in another embodiment of the present invention, an implementation manner of the determining unit 403, as shown in fig. 5, includes:
the determining subunit 501 is configured to determine, in the preset correspondence between the product and the insurance customer service, an insurance customer service list matched with the product information corresponding to the consultation information of the client.
A third obtaining unit 502, configured to find an insurance customer service in a non-busy state according to the insurance customer service list obtained by matching and according to a preset sequence of the insurance customer service list.
For the specific working process of the unit disclosed in the above embodiment of the present invention, reference may be made to the content of the corresponding method embodiment, as shown in fig. 2, which is not described herein again.
A building unit 404, configured to build a communication link between the insurance customer service and the client, so as to implement communication between the client and the insurance customer service.
For the specific working process of the unit disclosed in the above embodiment of the present invention, reference may be made to the content of the corresponding method embodiment, as shown in fig. 1, which is not described herein again.
Optionally, in another embodiment of the present invention, the apparatus for automatically allocating insurance customer service, as shown in fig. 6, further includes:
a fourth obtaining unit 601, configured to obtain personal information of the customer.
Wherein the personal information of the client includes: the customer's insurance purchase record.
The second determining unit 602 is configured to determine whether the customer has his own exclusive insurance customer service according to the insurance purchase record.
The allocating unit 603 is configured to, if the second determining unit 602 determines that the client has the own exclusive insurance customer service, directly allocate the client to the insurance customer service.
If the determining unit 602 determines that the client does not have the exclusive insurance customer service, the second obtaining unit 402 is utilized to obtain the product information corresponding to the consultation information of the client according to the preset automatic allocation model.
For the specific working process of the unit disclosed in the above embodiment of the present invention, reference may be made to the content of the corresponding method embodiment, as shown in fig. 3, which is not described herein again.
According to the scheme, in the method and the device for automatically distributing the insurance customer service, the consultation information of the client is acquired through the first acquisition unit 401; the second obtaining unit 402 obtains product information corresponding to the consultation information of the client according to a preset automatic distribution model; the determining unit 403 determines the insurance customer service matched with the product information corresponding to the consultation information of the client according to the preset corresponding relationship between the product and the insurance customer service; and then a communication link between the insurance customer service and the client is constructed through a construction unit 404 to realize the communication between the client and the insurance customer service. The method achieves the aim of accurately and automatically distributing insurance customer service for knowing the type of the insurance products according to the type of the insurance products which are required to be known by the client, so that the insurance customer service is more comprehensive when answering the questions of the client for consulting the type of the insurance products.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. A method for automatic distribution of insurance customer service, comprising:
acquiring consultation information of a client;
obtaining product information corresponding to the consultation information of the client according to a preset automatic distribution model; the product information includes a name of a specific insurance product; the obtaining of the product information corresponding to the consultation information of the client according to the preset automatic allocation model comprises the following steps: according to the consultation information of the client, matching is carried out in a slot value model in the preset automatic allocation model, and product information corresponding to the consultation information of the client is obtained; the model is obtained by preliminarily screening the slot value model according to the corresponding relation between the chat records of the client and the insurance customer service and the product information, the corresponding relation between the network information and the product information and a grammatical rule;
determining insurance customer service matched with product information corresponding to the consultation information of the client according to the corresponding relation between a preset product and the insurance customer service;
and constructing a communication link between the insurance customer service and the client to realize the communication between the client and the insurance customer service.
2. The method of claim 1, wherein before obtaining the product information corresponding to the customer consultation information according to the preset automatic distribution model, the method further comprises:
judging whether the consultation information is information of a consultation insurance product or not by using a corpus in a preset intention model; the corpus is a corpus database obtained by preliminarily screening the corpus according to the chat records, the network information and the grammar rules of the client and the insurance customer service in the past;
and if the consultation information is judged to be the information of consulting insurance products, executing the automatic allocation model according to the preset automatic allocation model to obtain the product information corresponding to the consultation information of the client.
3. The method according to claim 1, wherein the determining the insurance customer service matched with the product information corresponding to the consultation information of the client according to the preset correspondence between the product and the insurance customer service comprises:
determining an insurance customer service list matched with the product information corresponding to the consultation information of the client in the corresponding relation between the preset product and the insurance customer service;
and finding out an businessstate insurance customer service according to the insurance customer service list obtained by matching and the preset sequence of the insurance customer service list.
4. The method of claim 1, wherein after obtaining the consulting information of the client, the method further comprises:
acquiring personal information of a client; wherein the personal information of the customer includes: an insurance purchase record for the customer;
judging whether the client has own exclusive insurance customer service or not according to the insurance purchase record;
if the client is judged to have own exclusive insurance customer service, directly distributing the client to the insurance customer service;
and if the client is judged not to have the exclusive insurance customer service, executing an automatic distribution model according to the preset automatic distribution model to obtain the product information corresponding to the consultation information of the client.
5. An apparatus for automatic distribution of insurance customer service, comprising:
the first acquisition unit is used for acquiring consultation information of a client;
the second acquisition unit is used for acquiring product information corresponding to the consultation information of the client according to a preset automatic distribution model; the product information includes a name of a specific insurance product;
the second acquisition unit includes: the second acquisition subunit is used for matching in the slot value model in the preset automatic allocation model according to the consultation information of the client to obtain the product information corresponding to the consultation information of the client; the model is obtained by preliminarily screening the slot value model according to the corresponding relation between the chat records of the client and the insurance customer service and the product information, the corresponding relation between the network information and the product information and a grammatical rule;
the determining unit is used for determining insurance customer service matched with the product information corresponding to the consultation information of the client according to the corresponding relation between the preset product and the insurance customer service;
and the construction unit is used for constructing a communication link between the insurance customer service and the client so as to realize the communication between the client and the insurance customer service.
6. The apparatus of claim 5, further comprising:
the first judgment unit is used for judging whether the consultation information is the information of the consultation insurance product or not by utilizing the corpus in the preset intention model; the corpus is a corpus database obtained by preliminarily screening the corpus according to the chat records, the network information and the grammar rules of the client and the insurance customer service in the past;
and if the first judging unit judges that the consultation information is the information of consulting insurance products, the second acquiring unit is utilized to acquire the product information corresponding to the customer consultation information according to a preset automatic distribution model.
7. The apparatus of claim 5, wherein the determining unit comprises:
a determining subunit, configured to determine, in the preset correspondence between the product and the insurance customer service, an insurance customer service list matched with the product information corresponding to the consultation information of the client;
and the third acquisition unit is used for finding out an insurance customer service in a non-busy state according to the insurance customer service list obtained by matching and the preset sequence of the insurance customer service list.
8. The apparatus of claim 5, further comprising:
a fourth acquisition unit configured to acquire personal information of the customer; wherein the personal information of the customer includes: an insurance purchase record for the customer;
the second judgment unit is used for judging whether the client has own exclusive insurance customer service according to the insurance purchase record;
the distribution unit is used for directly distributing the client to the insurance customer service if the client has the exclusive insurance customer service judged by the second judgment unit;
and if the client is judged to have no exclusive insurance customer service, the second acquisition unit is utilized to obtain the product information corresponding to the consultation information of the client according to a preset automatic allocation model.
CN201910809115.8A 2019-08-29 2019-08-29 Method and device for automatically distributing insurance customer service Active CN110533324B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910809115.8A CN110533324B (en) 2019-08-29 2019-08-29 Method and device for automatically distributing insurance customer service

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910809115.8A CN110533324B (en) 2019-08-29 2019-08-29 Method and device for automatically distributing insurance customer service

Publications (2)

Publication Number Publication Date
CN110533324A CN110533324A (en) 2019-12-03
CN110533324B true CN110533324B (en) 2022-04-22

Family

ID=68665236

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910809115.8A Active CN110533324B (en) 2019-08-29 2019-08-29 Method and device for automatically distributing insurance customer service

Country Status (1)

Country Link
CN (1) CN110533324B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111104498B (en) * 2019-12-12 2023-04-25 华南理工大学 Semantic understanding method in task type dialogue system
CN112073458B (en) * 2020-07-29 2023-04-07 重庆市人口和计划生育科学技术研究院 Sperm bank remote guidance service system
CN112396300A (en) * 2020-11-04 2021-02-23 武汉悦学帮网络技术有限公司 Customer service resource allocation method and device, storage medium and electronic equipment
CN112381661B (en) * 2020-11-27 2024-01-30 深圳市慧择时代科技有限公司 Insurance product similarity determination method and apparatus
CN113326265B (en) * 2021-06-17 2023-11-10 深圳市慧择时代科技有限公司 Construction method and device of family information, storage medium and electronic equipment
CN118396637B (en) * 2024-06-27 2024-09-13 江西科技学院 Online consultation method and system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103684874A (en) * 2013-12-31 2014-03-26 成都金铠甲科技有限公司 Method and device for automatically distributing online customer service executives to conduct customer service
CN108418981A (en) * 2018-03-16 2018-08-17 苏州思必驰信息科技有限公司 The method and device of dialogue service is provided for client
CN109002434A (en) * 2018-05-31 2018-12-14 青岛理工大学 Customer service question and answer matching method, server and storage medium
CN109918680A (en) * 2019-03-28 2019-06-21 腾讯科技（上海）有限公司 Entity recognition method, device and computer equipment
CN109933654A (en) * 2019-01-30 2019-06-25 神思电子技术股份有限公司 A kind of dialogue management method based on State Tree
CN110175223A (en) * 2019-05-29 2019-08-27 北京搜狗科技发展有限公司 A kind of method and device that problem of implementation generates

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103684874A (en) * 2013-12-31 2014-03-26 成都金铠甲科技有限公司 Method and device for automatically distributing online customer service executives to conduct customer service
CN108418981A (en) * 2018-03-16 2018-08-17 苏州思必驰信息科技有限公司 The method and device of dialogue service is provided for client
CN109002434A (en) * 2018-05-31 2018-12-14 青岛理工大学 Customer service question and answer matching method, server and storage medium
CN109933654A (en) * 2019-01-30 2019-06-25 神思电子技术股份有限公司 A kind of dialogue management method based on State Tree
CN109918680A (en) * 2019-03-28 2019-06-21 腾讯科技（上海）有限公司 Entity recognition method, device and computer equipment
CN110175223A (en) * 2019-05-29 2019-08-27 北京搜狗科技发展有限公司 A kind of method and device that problem of implementation generates

Also Published As

Publication number Publication date
CN110533324A (en) 2019-12-03

Similar Documents

Publication Publication Date Title
CN110533324B (en) Method and device for automatically distributing insurance customer service
CN104731895A (en) Auto-answer method and device
CN111461827B (en) Push method and device for product evaluation information
US10496751B2 (en) Avoiding sentiment model overfitting in a machine language model
CN104933204A (en) Intelligent network response method and device
CN114266443A (en) Data evaluation method and device, electronic equipment and storage medium
CN109840319B (en) Method, system, computer device and storage medium for determining object entity
CN111104590A (en) Information recommendation method, device, medium and electronic equipment
Albudoor et al. Factors influencing US speech and language therapists’ use of technology for clinical practice
US20140337101A1 (en) System and method for businesses to collect personality information from their customers
WO2014185651A2 (en) Method for providing integrated management service for creative products in cultural arts reflecting needs of requester
WO2020087828A1 (en) Pre-sales risk assessment method and system, computer apparatus and readable storage medium
CN114528389A (en) Intelligent customer service response method and device, intelligent customer service response system and computer readable storage medium
KR101977236B1 (en) Method for providing partial payment cancellation service for conflict resolution occured in outsource service transaction
CN110532374A (en) The processing method and processing device of insurance information
CN116842166A (en) Customer service response result generation method and device, storage medium and computer equipment
US9208248B2 (en) Social network posting analysis using degree of separation correlation
CN114092264A (en) Intelligent passenger obtaining method, system and electronic equipment
CN113780610A (en) Customer service portrait construction method and device
Mishra et al. The influence of online reviews on consumer decision-making in the hotel industry
CN113743435A (en) Business data classification model training method and device, and business data classification method and device
CN110232115A (en) Question processing method, unit and computer readable storage medium
CN114547385B (en) Label construction method, label construction device, electronic equipment and storage medium
A Manap et al. Instrument validation to determine the relationship between social media acceptance and cuti-cuti 1 Malaysia facebook user engagement
Wulandari et al. Measuring the impact of healthcare service quality of hospitals on customer satisfaction

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
GR01 Patent grant
GR01 Patent grant