阅读说明：本技术 一种基于匹配度的客服分配方法 (Customer service distribution method based on matching degree ) 是由 郑鑫 杨尚伟 逄凯 吴正旭 徐楠楠 陈丽娜 于 2021-07-15 设计创作，主要内容包括：一种基于匹配度的客服分配方法,所述方法包括如下步骤：提取用户所属公司的业务向量；确定当前处于活跃状态的客户经理；计算客户经理与用户的匹配度集合；若当前无空闲的客户经理为用户提供服务,由用户自主选择继续等待或稍后由客户经理主动发起对话结束此次,当用户选择等待或稍后由客户经理主动发起对话时,确定待为其提供服务的客户经理；若用户选择结束此次对话,则跳出此次客户经理匹配的过程；确定为用户提供服务的客户经理；更新客户经理的业务向量；更新客户经理的服务人数；更新客户经理的状态。本方法匹配的结果更加准确,能够更加有效的为用户提供精准的服务,从而提升用户满意度和体验。(A customer service distribution method based on matching degree comprises the following steps: extracting a business vector of a company to which a user belongs; determining a customer manager currently in an active state; calculating a matching degree set of a customer manager and a user; if no idle client manager provides service for the user, the user autonomously selects to continue waiting or the client manager actively initiates a conversation to finish the time, and when the user selects to wait or the client manager actively initiates the conversation later, the client manager to be provided with service is determined; if the user selects to finish the conversation, jumping out of the matching process of the client manager; determining a customer manager providing service for the user; updating the business vector of the customer manager; updating the number of service people of the customer manager; and updating the state of the client manager. The method has more accurate matching result, and can provide accurate service for the user more effectively, thereby improving the satisfaction degree and experience of the user.)

1. A customer service distribution method based on matching degree is characterized by comprising the following steps:

the method comprises the following steps: extracting the business vector of the company to which the user belongs, wherein the business vector of the company of the user is recorded as:

wherein, c_iRepresenting a business vector of an ith registered enterprise;representing registered Business c_iThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class;

step two: determining the client managers in the active state currently, recording the client managers in the active state as a set A, and entering a fourth step if the set is empty; if the set is not empty, entering a third step;

step three: calculating a matching degree set f of the customer manager and the user in the set A, and entering a fifth step;

A＝[a₁，a₂，…，a_k，…，a_m]，k＝1，2，…，m，m＝|A|

wherein m is the number of elements in the set A; a is_iRepresenting the business vectors of the customer managers in the ith set A;

wherein the content of the first and second substances,representing customer manager a_kThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class;

the matching degree of the user and the customer manager is calculated as follows:

wherein f is_kRepresenting customer manager a_kAnd user c_iDegree of matching therebetween, in the range of f_k∈[-1，1]，f_kThe closer to 1, the customer manager a is represented_kAnd user c_iThe higher the degree of matching between them; f. of_kThe closer to-1, the customer manager a is represented_kAnd user c_iThe lower the matching degree between them;

the matching degree set between the customer manager and the user in the set a is as follows:

f＝[f₁，f₂，…，f_k，…，f_m]，k＝1，2，…，m，m＝|A|

step four: if the set A is empty, the fact that no idle client manager provides service for the user currently is indicated, the user autonomously selects to continue waiting or the client manager actively initiates a conversation to finish the conversation, and when the user selects to wait or the client manager actively initiates the conversation later, the client manager to be provided with service is determined; if the user selects to finish the conversation, jumping out of the matching process of the client manager;

step five: determining a customer manager aindex for providing service for the user, and entering a sixth step;

index＝max f，index＝1，2，…，m，m＝|A|

wherein index represents the subscript corresponding to the maximum value of the matching degree set f, and then the customer manager providing service for the user is determined to be a_index；

Step six: updating the business vector of the customer manager;

step seven: updating a service people count for a customer manager_iDetermining the service number count of the customer manager when the customer manager provides the service for the user_i＝count_i+ 1; when the user leaves the customer manager to finish the service, the service number count of the customer manager_i＝count_i-1；

Step eight: updating the status of the client manager if count_i＜limit_count_iIn time, the state of the client manager is still active and is not updated; if count_i＝limit_count_iWhen the client manager is in a busy state, the state of the client manager is updated to a busy state;limit_count_iand the upper limit of the number of the service people of the ith customer manager is shown, and the upper limit of the number of the service people of each customer manager is set in advance and dynamically adjusted according to the working experience and the capacity of the customer manager.

2. The method for distributing customer service based on matching degree as claimed in claim 1, wherein in the first step: extracting the business vector of the company to which the user belongs, wherein the specific determination method comprises the following steps:

(1) extraction of corporate business vectors

The company business vector is composed of the final grade class of the platform product, and the position of each element of the company business vector is 0 or 1; if the element position is 0, the last class represented by the element is not involved in the company business vector; if the element is 1, representing the final class related to the element representation in the company business vector; the company business vector relates to the initialization and the updating of the company business vector, the company business vector is stored as the latest company business vector, and the company business vector can be directly extracted and called when being extracted;

(2) initialization of corporate business vectors

When a company registers, a user is required to select a final product class label related to a company purchasing service, and the corresponding position of the related final product class in a service vector is set to be 1, and the rest positions are set to be 0; taking the service vector as an initialized company service vector, and expressing the service vector as:

wherein, c_i0The initialized business vector of the ith registered enterprise is represented;representing registered Business c_iThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; q represents the total number of platform users, in which case c_i＝c_i0；

(3) Update of corporate business vectors

(3.1) update of corporate traffic vectors when a transaction occurs

When a company carries out operation transaction on a subsequent platform, if a product of a certain class is traded and the corresponding element of the class in the corresponding company business vector is 0, updating the element to 1;

registered enterprise c_iIn the platform pairThe corresponding final-class material is traded and before this trade the registered user c_iCorresponding toThat is, the business vector of the company does not relate to the final class represented by the element before the transaction;

after the final class is traded, the element is addedUpdating to 1, namely, the business vector of the company is updated to the final class related to the element representation;

(3.2) update of corporate traffic vectors when consulted and not traded

If a product of a certain class is consulted and not traded, the elements are updated:

when the final class is consulted and not traded, the corresponding value of the element of the class in the corresponding company business vector satisfiesWill be the elementIs updated toWherein the limit _ c is a preset element value upper limit, the value of the limit _ c ensures that the limit _ c is less than or equal to 1, and the tentative limit _ c is 0.5; the sigma is temporarily 0.1, and the modification and the adjustment are carried out according to the specific application condition; if not satisfied withNamely, it isThen, it is maintainedI.e. the company's business vector is updated to the final class that may be related to the elemental representation; i.e. the company traffic vector has undergone an update operation, i.e. update c_iAnd elements corresponding to the middle and last grade classes.

3. The method for distributing customer service based on matching degree according to claim 1, wherein in the second step: determining the client manager in an active state at present, wherein a specific state confirmation method of the client manager comprises the following steps:

(1) the off-line state is used for adjusting the state of a customer manager according to the working condition; if the client manager is in the abnormal working state, including the conditions of asking for leave, taking a rest and putting on leave, the client manager is in the off-line state; if the customer manager is in the working state, determining the state of the customer manager through the following steps;

(2) adjusting the state of a customer manager according to the number of service people; if the number of the service people of the customer manager reaches the upper limit, the state of the customer manager is adjusted to be a busy state; and if the number of the service people of the client manager does not reach the upper limit of the number of the service people or is reduced to be lower than the upper limit of the number of the service people, the state of the client manager is adjusted to be an active state.

4. The method for distributing customer service based on matching degree according to claim 1, wherein in the second step: the customer manager in the active state is referred to as a set A, and the determination method of the service vector of each customer manager in the set A is as follows:

(1) extraction of customer manager business vectors

The business vector of the customer manager is composed of the final class of the platform product, and the value range of each element position of the business vector of the customer manager is [0, 1 ]; if the element position is 0, the last class represented by the element is represented in the business vector of the customer manager; if the company element is greater than or equal to limit _ a, representing the final class in the business vector of the customer manager related to the representation of the element; if the company element is valued at (0, limit _ a), it indicates that the last class indicated by the element is related to the last class indicated by the element in the service vector of the customer manager, but the last class indicated by the element is not included, where limit _ a is a preset upper limit of the element, and the value of limit _ a guarantees that limit _ a is less than or equal to 1, where the tentative limit _ a is 0.5;

wherein, a_lRepresenting the business vector of the ith customer manager;representing customer manager a_lThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; p represents the total number of platform customer managers;

the business vector of the customer manager relates to the initialization and the updating of the business vector of the customer manager, the business vector of the customer manager is stored as the latest business vector of the customer manager, and when the business vector of a company is extracted, the business vector of the company can be directly extracted and called;

(2) initialization of customer manager business vectors

When a customer manager establishes a customer manager service right for the first time, the customer manager is required to select a final class label capable of performing service, after the examination is completed, the corresponding position of the final class capable of being served in a service vector is set to be limit _ a, and the rest positions are set to be 0; and taking the service vector as an initialized service vector of the customer manager, and expressing as follows:

wherein, a_l0An initial service vector representing the ith customer manager;representing customer manager a_lThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; p represents the total number of platform customer managers; at this time a_l＝a_l0。

5. The matching-based customer service distribution method according to claim 4, wherein in the sixth step: and updating the service vector of the client manager, wherein the specific updating method comprises the following steps:

when a customer manager provides corresponding services for users for products of a certain class in the service process of a subsequent platform, and ordering of the users is facilitated or the consultation problem of the users is solved to obtain the approval of the users, the business vector of the customer manager is updated; wherein, the updating comprises two parts, one part is the updating of the service final class, and the other part is the updating of the corresponding final class which belongs to the previous class with the service class;

(1) updating of service end-level class corresponding element in customer manager business vector

Wherein the content of the first and second substances,representing the corresponding elements of the current service final class of the client manager in the service vector of the client manager;

(1.1) when the customer manager causes the final class to be placed and the corresponding element in the customer manager's business vectorAt the same time, updateComprises the following steps:

(1.2) when the customer manager causes the final class to be placed and the corresponding element in the customer manager's business vectorAt the same time, updateComprises the following steps:

wherein δ represents an update amount, δ is temporarily set to δ equal to 0.05, and is adjusted according to the later specific use condition;

(1.3) when the customer manager causes the final class to be placed and the corresponding element in the customer manager's business vectorAt the same time, updateComprises the following steps:

(2) updating elements corresponding to the last-level product class which belongs to the same upper-level classification as the service class in the service vector of the customer manager;

wherein the content of the first and second substances,representing other final class belonging to the previous class as the current service final class of the client manager;

(2.1) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the business vector of the customer manager corresponds to other final-stage classes which belong to the last-stage class and are the same as the final-stage classAt the same time, updateComprises the following steps:

(2.2) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the business vector of the customer manager corresponds to other final-stage classes which belong to the last-stage class and are the same as the final-stage classAt the same time, updateComprises the following steps:

(2.3) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the business vector of the customer manager corresponds to other final-stage classes which belong to the last-stage class and are the same as the final-stage classAt the same time, updateComprises the following steps:

(2.4) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the business vector of the customer manager corresponds to other final-stage classes which belong to the last-stage class and are the same as the final-stage classAt the same time, updateComprises the following steps:

6. the method for distributing customer service based on matching degree according to claim 1, wherein in the fourth step: when a user chooses to wait or later actively initiate a conversation by a customer manager, the method of determining the customer manager to be served is as follows:

when the set A is empty, no customer manager in an active state provides service for the user; if the user selects to continue waiting for the response of the client manager or the client manager initiatively initiates a conversation later, calculating the matching degree of all the client managers and the user for the user, and extracting the number of waiting users of the user;

(1) calculating the matching degree of all customer managers and users

The set A re-extracts the customer manager service vectors of all the customer managers of the current platform;

A＝[a₁，a₂，…，a_k，…，a_m]，k＝1，2，…，p

wherein p represents the total number of customer managers on the platform; a is_iRepresenting the business vectors of the customer managers in the ith set A;

wherein the content of the first and second substances,representing customer manager a_kThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class;

the matching degree of the user and the customer manager is calculated as follows:

wherein f is_kRepresenting customer manager a_kAnd user c_iDegree of matching therebetween, in the range of f_k∈[-1，1]，f_kThe closer to 1, the customer manager a is represented_kAnd user c_iThe higher the degree of matching between them; f. of_kThe closer to-1, the customer manager a is represented_kAnd user c_iThe lower the matching degree between them;

the matching degree set between the customer manager and the user in the set a is as follows:

f＝[f₁，f₂，…，f_k，…，f_p]，k＝1，2，…，p

(2) calculating the number of waiting users of all the client managers, and recording as:

w＝[w₁，w₂，…，w_k，…，w_p]

(3) calculating the appropriateness between all client managers and users:

the set of appropriateness between all customer managers and users is:

s＝[s₁，s₂，…，s_k，…，s_p]，k＝1，2，…，p

(4) determining a customer manager to serve a user

Determining the client manager with the matching degree greater than or equal to 0:

index_f＝{k|f_k≥0}

determining the suitability of the customer manager with the matching degree greater than or equal to 0:

s_f＝{s_k|k∈index_f}

determining a customer manager to serve a user:

(5) updating a to-be-serviced list of a client manager, and adding the user into the to-be-serviced list of the client manager, namely, the number of waiting users, count _ wait, is equal to count _ wait + 1; if the user in the waiting service list leaves, the count _ wait is equal to count _ wait-1.

Technical Field

The invention relates to the technical field of electronic commerce, in particular to a customer service distribution method based on matching degree.

Background

The existing customer service distribution to the user is mainly characterized by fast response, most of customer services need to serve the customer at the C end by means of the customer service, the customer service can be provided with services without professional knowledge under general conditions, and meanwhile, in order to solve problems quickly, a certain method is generally adopted to provide familiar or communicated customer services for the user.

For a B2B website platform, especially a customer service (hereinafter referred to as a customer manager) in the field of electronic components, it is necessary to have a certain professional knowledge to solve a problem for a user, so as to provide a better service effect for the user and improve the efficiency of solving the problem. Meanwhile, the fair distribution problem of the customer manager is considered, the matching degree of the user and the customer manager is used as a primary matching condition, and more professional and smoother service communication is provided for the user.

Disclosure of Invention

The purpose of the invention is: aiming at the problems described in the background art, the invention provides the customer service distribution method based on the matching degree, the matching result is more accurate, and professional client managers aiming at the mouth can more effectively provide more accurate service for users, so that the satisfaction degree and experience of the users are improved.

In order to solve the problems, the technical scheme adopted by the invention is as follows:

a customer service distribution method based on matching degree is characterized by comprising the following steps:

the method comprises the following steps: extracting the business vector of the company to which the user belongs, wherein the business vector of the company of the user is recorded as:

wherein, c_iRepresenting a business vector of an ith registered enterprise;representing registered Business c_iThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class;

step two: determining the client managers in the active state currently, recording the client managers in the active state as a set A, and entering a fourth step if the set is empty; if the set is not empty, entering a third step;

step three: calculating a matching degree set f of the customer manager and the user in the set A, and entering a fifth step;

A＝[a₁，a₂，…，a_k，…，a_m]，k＝1，2，…，m，m＝|A|

wherein m is the number of elements in the set A; a is_iRepresenting the business vectors of the customer managers in the ith set A;

wherein the content of the first and second substances,representing customer manager a_kThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class;

the matching degree of the user and the customer manager is calculated as follows:

wherein f is_kRepresenting customer manager a_kAnd user c_iDegree of matching therebetween, in the range of f_k∈[-1，1]The closer f is to 1, the customer manager a is shown_kAnd user c_iThe higher the degree of matching between them; f. of_kThe closer to-1, the customer manager a is represented_kAnd user c_iThe lower the matching degree between them;

the matching degree set between the customer manager and the user in the set a is as follows:

f＝[f₁，f₂，…，f_k，…，f_m]，k＝1，2，…，m，m＝|A|

step four: if the set A is empty, the fact that no idle client manager provides service for the user currently is indicated, the user autonomously selects to continue waiting or the client manager actively initiates a conversation to finish the conversation, and when the user selects to wait or the client manager actively initiates the conversation later, the client manager to be provided with service is determined; if the user selects to finish the conversation, jumping out of the matching process of the client manager;

step five: determining a customer manager a to provide a service to a user_indexEntering a sixth step;

index＝maxf，index＝1，2，…，m，m＝|A|

wherein index represents the subscript corresponding to the maximum value of the matching degree set f, and then the customer manager providing service for the user is determined to be a_index；

Step six: updating the business vector of the customer manager;

step seven: updating a service people count for a customer manager_iDetermining the service number count of the customer manager when the customer manager provides the service for the user_i＝count_i+ 1; when the user leaves the customer manager to finish the service, the service number count of the customer manager_i＝count_i-1；

Step eight: updating the status of the client manager if count_i＜limit_count_iIn time, the state of the client manager is still active and is not updated; if count_i＝limit_count_iWhen the client manager is in a busy state, the state of the client manager is updated to a busy state; limit _ count_iAnd the upper limit of the number of the service people of the ith customer manager is shown, and the upper limit of the number of the service people of each customer manager is set in advance and dynamically adjusted according to the working experience and the capacity of the customer manager.

Further, in the first step: extracting the business vector of the company to which the user belongs, wherein the specific determination method comprises the following steps:

(1) extraction of corporate business vectors

The company business vector is composed of the final grade class of the platform product, and the position of each element of the company business vector is 0 or 1; if the element position is 0, the last class represented by the element is not involved in the company business vector; if the element is 1, representing the final class related to the element representation in the company business vector; the company business vector relates to the initialization and the updating of the company business vector, the company business vector is stored as the latest company business vector, and the company business vector can be directly extracted and called when being extracted;

(2) initialization of corporate business vectors

When a company registers, a user is required to select a final product class label related to a company purchasing service, and the corresponding position of the related final product class in a service vector is set to be 1, and the rest positions are set to be 0; taking the service vector as an initialized company service vector, and expressing the service vector as:

wherein, c_i0The initialized business vector of the ith registered enterprise is represented;representing registered Business c_iThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; q represents the total number of platform users, in which case c_i＝c_i0；

(3) Update of corporate business vectors

(3.1) update of corporate traffic vectors when a transaction occurs

When a company carries out operation transaction on a subsequent platform, if a product of a certain class is traded and the corresponding element of the class in the corresponding company business vector is 0, updating the element to 1;

registered enterprise c_iIn the platform pairThe corresponding final-class material is traded and before this trade the registered user c_iCorresponding toThat is, the business vector of the company does not relate to the final class represented by the element before the transaction;

after the final class is traded, the element is addedUpdating to 1, namely, the business vector of the company is updated to the final class related to the element representation;

(3.2) update of corporate traffic vectors when consulted and not traded

If a product of a certain class is consulted and not traded, the elements are updated:

when the final class is consulted and not traded, the corresponding value of the element of the class in the corresponding company business vector satisfiesWill be the elementIs updated toWherein the limit _ c is a preset element value upper limit, the value of the limit _ c ensures that the limit _ c is less than or equal to 1, and the tentative limit _ c is 0.5; the sigma is temporarily 0.1, and the modification and the adjustment are carried out according to the specific application condition; if not satisfied withNamely, it isThen, it is maintainedI.e. the company's business vector is updated to the final class that may be related to the elemental representation; i.e. the company traffic vector has undergone an update operation, i.e. update c_iAnd elements corresponding to the middle and last grade classes.

Further, in the second step: determining the client manager in an active state at present, wherein a specific state confirmation method of the client manager comprises the following steps:

(1) the off-line state is used for adjusting the state of a customer manager according to the working condition; if the client manager is in the abnormal working state, including the conditions of asking for leave, taking a rest and putting on leave, the client manager is in the off-line state; if the customer manager is in the working state, determining the state of the customer manager through the following steps;

(2) adjusting the state of a customer manager according to the number of service people; if the number of the service people of the customer manager reaches the upper limit, the state of the customer manager is adjusted to be a busy state; and if the number of the service people of the client manager does not reach the upper limit of the number of the service people or is reduced to be lower than the upper limit of the number of the service people, the state of the client manager is adjusted to be an active state.

Further, in the second step: the customer manager in the active state is referred to as a set A, and the determination method of the service vector of each customer manager in the set A is as follows:

(1) extraction of customer manager business vectors

The business vector of the customer manager is composed of the final class of the platform product, and the value range of each element position of the business vector of the customer manager is [0, 1 ]; if the element position is 0, the last class represented by the element is represented in the business vector of the customer manager; if the company element is greater than or equal to limit _ a, representing the final class in the business vector of the customer manager related to the representation of the element; if the company element is valued at (0, limit _ a), it indicates that the last class indicated by the element is related to the last class indicated by the element in the service vector of the customer manager, but the last class indicated by the element is not included, where limit _ a is a preset upper limit of the element, and the value of limit _ guarantees that limit _ a is less than or equal to 1, where the tentative limit _ a is 0.5;

wherein, a_lRepresenting the business vector of the ith customer manager;representing customer manager a_lThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; p represents the total number of platform customer managers;

the business vector of the customer manager relates to the initialization and the updating of the business vector of the customer manager, the business vector of the customer manager is stored as the latest business vector of the customer manager, and when the business vector of a company is extracted, the business vector of the company can be directly extracted and called;

(2) initialization of customer manager business vectors

When a customer manager establishes a customer manager service right for the first time, the customer manager is required to select a final class label capable of performing service, after the examination is completed, the corresponding position of the final class capable of being served in a service vector is set to be limit _ a, and the rest positions are set to be 0; and taking the service vector as an initialized service vector of the customer manager, and expressing as follows:

wherein, a_l0An initial service vector representing the ith customer manager;representing customer manager a_lThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; p tableShowing the total number of platform customer managers; at this time a_l＝a_l0。

Further, in the sixth step: and updating the service vector of the client manager, wherein the specific updating method comprises the following steps:

when a customer manager provides corresponding services for users for products of a certain class in the service process of a subsequent platform, and ordering of the users is facilitated or the consultation problem of the users is solved to obtain the approval of the users, the business vector of the customer manager is updated; wherein, the updating comprises two parts, one part is the updating of the service final class, and the other part is the updating of the corresponding final class which belongs to the previous class with the service class;

(1) updating of service end-level class corresponding element in customer manager business vector

Wherein the content of the first and second substances,representing the corresponding elements of the current service final class of the client manager in the service vector of the client manager;

(1.1) when the customer manager causes the final class to be placed and the corresponding element in the customer manager's business vectorAt the same time, updateComprises the following steps:

(1.2) when the customer manager causes the final class to be placed and the corresponding element in the customer manager's business vectorAt the same time, updateComprises the following steps:

wherein δ represents an update amount, δ is temporarily set to δ equal to 0.05, and is adjusted according to the later specific use condition;

(1.3) when the customer manager causes the final class to be placed and the corresponding element in the customer manager's business vectorAt the same time, updateComprises the following steps:

(2) updating elements corresponding to the last-level product class which belongs to the same upper-level classification as the service class in the service vector of the customer manager;

wherein the content of the first and second substances,representing other final class belonging to the previous class as the current service final class of the client manager;

(2.1) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the business vector of the customer manager corresponds to other final-stage classes which belong to the last-stage class and are the same as the final-stage classAt the same time, updateComprises the following steps:

(2.2) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the business vector of the customer manager corresponds to other final-stage classes which belong to the last-stage class and are the same as the final-stage classAt the same time, updateComprises the following steps:

(2.3) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the business vector of the customer manager corresponds to other final-stage classes which belong to the last-stage class and are the same as the final-stage classAt the same time, updateComprises the following steps:

(2.4) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the business vector of the customer manager corresponds to other final-stage classes which belong to the last-stage class and are the same as the final-stage classAt the same time, updateComprises the following steps:

further, in the fourth step: when a user chooses to wait or later actively initiate a conversation by a customer manager, the method of determining the customer manager to be served is as follows:

when the set A is empty, no customer manager in an active state provides service for the user; if the user selects to continue waiting for the response of the client manager or the client manager initiatively initiates a conversation later, calculating the matching degree of all the client managers and the user for the user, and extracting the number of waiting users of the user;

(1) calculating the matching degree of all customer managers and users

The set A re-extracts the customer manager service vectors of all the customer managers of the current platform;

A＝[a₁，a₂，…，a_k，…，a_m]，k＝1，2，…，p

wherein p represents the total number of customer managers on the platform; a is_iRepresenting the business vectors of the customer managers in the ith set A;

wherein the content of the first and second substances,representing customer manager a_kThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class;

the matching degree of the user and the customer manager is calculated as follows:

wherein f is_kRepresenting customer manager a_kAnd user c_iDegree of matching therebetween, in the range of f_k∈[-1，1]，f_kThe closer to 1, the customer manager a is represented_kAnd user c_iThe higher the degree of matching between them; f. of_kThe closer to-1, representsCustomer manager a_kAnd user c_iThe lower the matching degree between them;

the matching degree set between the customer manager and the user in the set a is as follows:

f＝[f₁，f₂，…，f_k，…，f_p]，k＝1，2，…，p

(2) calculating the number of waiting users of all the client managers, and recording as:

w＝[w₁，w₂，…，w_k，…，w_p]

(3) calculating the appropriateness between all client managers and users:

the set of appropriateness between all customer managers and users is:

s＝[s₁，s₂，…，s_k，…，s_p]，k＝1，2，…，p

(4) determining a customer manager to serve a user

Determining the client manager with the matching degree greater than or equal to 0:

index_f＝{k|f_k≥0}

determining the suitability of the customer manager with the matching degree greater than or equal to 0:

s_f＝{s_k|k∈index_f}

determining a customer manager to serve a user:

(5) updating a to-be-serviced list of a client manager, and adding the user into the to-be-serviced list of the client manager, namely, the number of waiting users, count _ wait, is equal to count _ wait + 1; if the user in the waiting service list leaves, the count _ wait is equal to count _ wait-1.

The technical scheme provided by the embodiment of the invention has the beneficial effects that at least: the matching degree-based customer service distribution method has the advantages that:

1. the matching result is more accurate, more professional service is provided for the user, and more accurate service can be more effectively provided for the user by a professional client manager who is in a correct position.

2. The matching result is smoother, automatic distribution is achieved, coordination is not needed, and professional services can be provided for the user more quickly.

3. The business vector data of the user can be dynamically adjusted in practical application, and the actual demand degree of the user can be recorded, so that client managers with different degrees can be matched, the client managers can be more effectively and reasonably distributed, and the professional skills of the client managers can be better exerted.

4. In practical application, the business vector data of the user is dynamically adjusted, the double combination of the actual service capability and the professional knowledge of the client manager can be recorded, the growth condition of the client manager on a platform can be reflected, and meanwhile, the data support of the professional skill is provided for the client manager in the aspect of providing service for the user.

5. The matching result is fairer, a fair competition environment is provided for the client manager, the service capacity of the client manager is improved, and the improvement of the capacity of the client manager is facilitated.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the features particularly pointed out in the written description and claims hereof.

DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION

Exemplary embodiments of the present disclosure will be described in more detail below. It should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The embodiment of the invention provides a customer service distribution method based on matching degree, which comprises the following six steps:

the method comprises the following steps: the business vector of the company to which the user belongs is extracted, and a specific determination method is shown in the first part. The corporate business vector for the user is written as:

wherein, c_iRepresenting the ith registered enterprise;representing registered Business c_iThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final classes.

Step two: and determining the client manager in the active state, wherein the state confirmation method of the specific client manager is shown in the second part. The customer manager in the active state is referred to as set a, and the determination of each traffic vector in set a is found in the third section. If the set is empty, entering the fourth step; and if the set is not empty, entering the step three.

Step three: and (5) calculating a matching degree set f of the customer manager and the user in the set A, and entering the step five.

A＝[a₁，a₂，…，a_k，…，a_m]，k＝1，2，…，m，m＝|A|

Wherein m is the number of elements in the set A; a is_iRepresenting the traffic vectors of the customer managers in the ith set a.

Wherein the content of the first and second substances,representing customer manager a_kCorresponding to the jth element of the service vectorA value; n represents the number of service vector elements, corresponding to the number of final classes.

The matching degree of the user and the customer manager is calculated as follows:

wherein f is_kRepresenting customer manager a_kAnd user c_iDegree of matching therebetween, in the range of f_k∈[-1，1]，f_kThe closer to 1, the customer manager a is represented_kAnd user c_iThe higher the degree of matching between them; f. of_kThe closer to-1, the customer manager a is represented_kAnd user c_iThe lower the degree of match between.

The matching degree set between the customer manager and the user in the set a is as follows:

f＝[f₁，f₂，…，f_k，…，f_m]，k＝1，2，…，m，m＝|A|

step four: if the set A is empty, the client manager which is not idle currently provides service for the user, the user autonomously selects to continue waiting or the client manager actively initiates a conversation to finish the conversation, and when the user selects to wait or the client manager actively initiates the conversation later, the fourth part determines the client manager to provide service for the client manager; and if the user selects to end the conversation, jumping out of the matching process of the client manager.

Step five: determining a customer manager a to provide a service to a user_indexAnd entering the step six.

index＝maxf，index＝1，2，…，m，m＝|A|

Wherein index represents the subscript corresponding to the maximum value of the matching degree set f, and then the customer manager providing service for the user is determined to be a_index。

Step six: and updating the service vector of the client manager, wherein the specific updating method is shown in the third part.

Step seven: updating a service people count for a customer manager_iDetermining that the customer manager provides for the userWhen in service, the service people count of the customer manager_i＝count_i+ 1; when the user leaves the customer manager to finish the service, the service number count of the customer manager_i＝count_i-1。

Step eight: updating the status of the client manager if count_i＜limit_count_iIn time, the state of the client manager is still active and is not updated; if count_i＝limit_count_iWhen the client manager's status is updated to busy (limit _ count)_iThe service upper limit number of the ith client manager is represented and needs to be set in advance, the specific value of the service upper limit number is properly adjusted by the client through a leader in the using process, and the limit _ count is initially tentatively set_i＝10)。

First part, related operation of company business vector

1. Extraction of corporate business vectors

The company service vector is composed of the final-stage products of the platform product (the final-stage products include MLCC capacitors, chip resistors and the like, the hierarchical relationship of the MLCC capacitors is MLCC-ceramic capacitor-electronic components, the hierarchical relationship of the chip resistors is chip resistor-electronic components, the relationship of the rest products and the specific final-stage products are shown as an attachment 1), and each element position of the company service vector is 0 or 1. If the element position is 0, the last class represented by the element is not involved in the company business vector; if the element is 1, the final class in the company business vector related to the representation of the element is represented. The company traffic vector is represented as:

wherein, c_iRepresenting a business vector of an ith registered enterprise;representing registered Business c_iThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final classes.

The company business vector mainly relates to the initialization and the updating of the company business vector, the company business vector is stored as the latest company business vector, and when the company business vector is extracted, the extraction and the calling can be directly carried out.

2. Initialization of corporate business vectors

When the company registers, the user is required to select the final product class label involved in the purchase service of the company, and the corresponding position of the involved final product class in the service vector is set as 1, and the rest positions are set as 0. Taking the service vector as an initialized company service vector, and expressing the service vector as:

wherein, c_i0The initialized business vector of the ith registered enterprise is represented;representing registered Business c_iThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; q represents the total number of platform users. At this time c_i＝c_i0。

3. Update of corporate business vectors

(1) Updating corporate business vectors when a transaction occurs

When a company carries out operation transaction on a subsequent platform, if a product of a certain class is traded and the element of the class corresponding to the corresponding company business vector is 0, the element is updated to 1.

Registered enterprise c_iIn the platform pairCorresponding final classThe material is traded and before this transaction, the registered user c_iCorresponding toI.e. the company's traffic vector does not relate to the final class represented by the element before this transaction.

After the final class is traded, the element is addedThe update is 1, i.e. the business vector of the company is updated to the final class related to the representation of the element.

(2) Update of corporate traffic vectors when consulted and not transacted

If a product of a certain class is consulted and not traded, the elements are updated:

when the final class is consulted and not traded, the corresponding value of the element of the class in the corresponding company business vector satisfiesWill be the elementIs updated to(wherein limit _ c is a preset element value upper limit, the value of limit _ c ensures that limit _ c is less than or equal to 1, and the tentative limit _ c is 0.5; sigma is 0.1, and can be modified and adjusted according to specific application conditions); if not satisfied withNamely, it isThen, it will ensureHand holderI.e. the business vector of the company is updated to the final class that may be related to the representation of the element.

I.e. the company traffic vector has undergone an update operation, i.e. update c_iAnd elements corresponding to the middle and last grade classes.

A second part: client manager status

(1) And the off-line state is used for adjusting the state of the customer manager according to the working condition. If the client manager is in the abnormal working state (including the situations of asking for leave, taking a rest, putting on leave and the like), the state of the client manager is in an off-line state; if the client manager is in the working state, the state of the client manager is determined through the following steps.

(2) And adjusting the state of the customer manager according to the number of the service people. If the number of the service people of the customer managers reaches the upper limit (the upper limit of the number of the service people, the upper limit of the number of the service people of each customer manager is set in advance and dynamically adjusted according to the work experience and the capacity), the state of the customer managers is adjusted to be in a busy state; and if the number of the service people of the client manager does not reach the upper limit of the number of the service people or is reduced to be lower than the upper limit of the number of the service people, the state of the client manager is adjusted to be an active state.

And a third part: correlation of customer manager business vectors

1. Extraction of customer manager business vectors

The customer manager service vector is composed of the final grades of the platform products (the final grades have the relation which belongs to the previous grade, such as the MLCC capacitor, the ceramic chip capacitor and the Y capacitor belong to the ceramic capacitor), and the value range of each element position of the customer manager service vector is [0, 1 ]. If the element position is 0, the last class represented by the element is represented in the business vector of the customer manager; if the company element is greater than or equal to limit _ a, representing the final class in the business vector of the customer manager related to the representation of the element; if the company element is valued at (0, limit _ a), it indicates that the last class indicated by the element is involved in the service vector of the customer manager and belongs to the same last class as the previous class, but does not include the last class indicated by the element, where limit _ a is a preset upper limit of the element, and the value of limit _ a guarantees that limit _ a is less than or equal to 1, where the tentative limit _ a is 0.5.

Wherein, a_lRepresenting the business vector of the ith customer manager;representing customer manager a_lThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; p represents the total number of platform customer managers.

The business vector of the customer manager is stored as the latest business vector of the customer manager, and can be directly extracted and called when the business vector of a company is extracted.

2. Initialization of customer manager business vectors

When a customer manager establishes a customer manager service right for the first time, the customer manager is required to select a final class label capable of performing service, after the examination is completed, the corresponding position of the final class capable of being served in a service vector is set to be limit _ a, and the rest positions are set to be 0. And taking the service vector as an initialized service vector of the customer manager, and expressing as follows:

wherein, a_l0An initial service vector representing the ith customer manager;representing customer manager a_lThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final class; p represents the total number of platform customer managers.At this time a_l＝al0。

3. Updating of customer manager traffic vectors

And in the service process of the subsequent platform, if the client manager provides corresponding service for the user for a certain class of products and prompts the user to place an order or solves the problem of consultation of the user and obtains user approval, updating the service vector of the client manager. The updating comprises two parts, wherein one part is the updating of the service final class, and the other part is the updating of the corresponding final class which belongs to the previous class with the service class.

1. Updating of service end-level class corresponding element in customer manager business vector

Wherein the content of the first and second substances,representing the corresponding elements of the customer manager's current service final class in the customer manager's traffic vector.

(1) When the customer manager causes the final class to be placed, and the corresponding element in the business vector of the customer managerAt the same time, updateComprises the following steps:

(2) when the customer manager causes the final class to be placed, and the corresponding element in the business vector of the customer managerAt the same time, updateComprises the following steps:

where δ represents the update amount, δ is temporarily set to δ equal to 0.05, and δ can be adjusted according to the later specific use condition.

(3) When the customer manager causes the final class to be placed, and the corresponding element in the business vector of the customer managerAt the same time, updateComprises the following steps:

2. updating the corresponding elements of the last class which belongs to the last class and is the same as the service class in the business vector of the customer manager.

Wherein the content of the first and second substances,representing other last class which belongs to the last class with the current service last class of the customer manager, if the last class of the current service of the customer manager is MLCC (multilayer ceramic capacitor)And the MLCC capacitor, the ceramic chip capacitor and the Y capacitor belong to the ceramic capacitor classified at the upper stage.

(1) When the customer manager solves the consultation problem of the user and obtains the approval of the user, and the elements corresponding to other final-stage products which belong to the last-stage classification in the service vector of the customer manager are the same as the final-stage products At the same time, updateComprises the following steps:

(2) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the elements corresponding to other final-stage products which belong to the last-stage classification in the service vector of the customer manager are the same as the final-stage products At the same time, updateComprises the following steps:

(3) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the corresponding element limit _ avjci of other final-stage product classes which belong to the last-stage classification in the service vector of the customer manager and the final-stage product class is not more than 1-delta 2, updating vjci as follows: vjci + δ 2;

(4) when the customer manager solves the consultation problem of the user and obtains the approval of the user, and the elements corresponding to other final-stage products which belong to the last-stage classification in the service vector of the customer manager are the same as the final-stage productsAt the same time, updateComprises the following steps:

the fourth part: service mode of customer manager without active state

When set a is empty, i.e., no customer managers currently in an active state are serving the user. And if the user selects to continue waiting for the response of the client manager or the client manager actively initiates a conversation later, calculating the matching degree of all the client managers and the user for the user, and extracting the number of waiting users of the user.

(1) Calculating the matching degree of all customer managers and users

Set a re-extracts the customer manager traffic vectors for all customer managers of the current platform.

A＝[a₁，a₂，…，a_k，…，a_m]，k＝1，2，…，p

Wherein p represents the total number of customer managers on the platform; a is_iRepresenting the traffic vectors of the customer managers in the ith set a.

Wherein the content of the first and second substances,representing customer manager a_kThe value corresponding to the jth element of the service vector of (a); n represents the number of service vector elements, corresponding to the number of final classes.

The matching degree of the user and the customer manager is calculated as follows:

wherein f is_kRepresenting customer manager a_kAnd user c_iDegree of matching therebetween, in the range of f_k∈[-1，1]，f_kThe closer to 1, the customer manager a is represented_kAnd user c_iThe higher the degree of matching between；f_kThe closer to-1, the customer manager a is represented_kAnd user c_iThe lower the degree of match between.

The matching degree set between the customer manager and the user in the set a is as follows:

f＝[f₁，f₂，…，f_k，…，f_p]，k＝1，2，…，p

(2) calculating the number of waiting users of all the client managers, and recording as:

w＝[w₁，w₂，…，w_k，…，w_p]

(3) calculating the appropriateness between all the customer managers and the users.

The set of appropriateness between all customer managers and users is:

s＝[s₁，s₂，…，s_k，…，s_p]，k＝1，2，…，p

(4) a customer manager is determined that is to provide services for the user.

Determining the client manager with the matching degree greater than or equal to 0:

index_f＝{k|f_k≥0}

determining the suitability of the customer manager with the matching degree greater than or equal to 0:

s_f＝{s_k|k∈index_f}

determining a customer manager to serve a user:

(5) updating a to-be-serviced list of a client manager, and adding the user into the to-be-serviced list of the client manager, namely, the number of waiting users, count _ wait, is equal to count _ wait + 1; if the user in the waiting service list leaves, the count _ wait is equal to count _ wait-1.

It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.

In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Of course, the processor and the storage medium may reside as discrete components in a user terminal.

For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in memory units and executed by processors. The memory unit may be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.

What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".