CN110544021A - service distribution method and device - Google Patents
service distribution method and device Download PDFInfo
- Publication number
- CN110544021A CN110544021A CN201910754473.3A CN201910754473A CN110544021A CN 110544021 A CN110544021 A CN 110544021A CN 201910754473 A CN201910754473 A CN 201910754473A CN 110544021 A CN110544021 A CN 110544021A
- Authority
- CN
- China
- Prior art keywords
- customer service
- service
- social platform
- target
- target user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000012545 processing Methods 0.000 claims abstract description 68
- 230000008569 process Effects 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000036449 good health Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
the embodiment of the invention provides a business distribution method and a business distribution device, and relates to the field of finance. The embodiment of the invention can determine the service to be distributed through the text information issued by the user on the social platform, and determine the customer service staff of the service to be distributed according to the importance degree of the user on the social platform. The method solves the importance problem of service allocation and improves the accuracy of service allocation. The method comprises the following steps: and determining the service to be distributed corresponding to the target text information published by the target user through the social platform. And determining target customer service personnel for processing the service to be distributed according to the user information of the target user on the social platform. The invention is applied to service distribution.
Description
Technical Field
The present invention relates to the field of finance, and in particular, to a method and an apparatus for service allocation.
Background
The present bank online customer service system distributes the customer service personnel to the business in the order of the time of receiving the business.
In the prior art, the problem of service priority is not considered, and important services are not processed preferentially. Meanwhile, the load capacity of customer service personnel for processing the service is not considered, and the service cannot be processed quickly.
Disclosure of Invention
The embodiment of the invention provides a service distribution method and device, which can determine a service to be distributed through text information issued by a user on a social platform, and determine customer service personnel of the service to be distributed according to the importance degree of the user on the social platform. The method solves the importance problem of service allocation and improves the accuracy of service allocation.
In a first aspect, the present invention provides a service allocation method, including: determining a service to be distributed corresponding to target text information issued by a target user through a social platform; determining a target customer service person for processing the service to be distributed according to the user information of the target user on the social platform; the user information comprises information used for determining the importance degree of the target user in the social platform.
In a second aspect, an embodiment of the present invention provides a service allocating apparatus, including: the processing unit is used for determining a service to be distributed corresponding to target text information issued by a target user through a social platform; the processing unit is further configured to determine, after the processing unit determines a to-be-allocated service corresponding to target text information issued by a target user through a social platform, a target customer service person who processes the to-be-allocated service according to user information of the target user on the social platform; the user information comprises information used for determining the importance degree of the target user in the social platform.
In a third aspect, an embodiment of the present invention provides another service allocating apparatus, including: a processor, a memory, a bus, and a communication interface; the memory is used for storing computer-executable instructions, the processor is connected with the memory through a bus, and when the service distribution device runs, the processor executes the computer-executable instructions stored in the memory, so that the service distribution device executes the service distribution method provided by the first aspect.
in a fourth aspect, an embodiment of the present invention provides a computer storage medium, which includes instructions, and when the computer storage medium is run on a service distribution apparatus, the service distribution apparatus executes a service distribution method provided in the first aspect.
In a fifth aspect, an embodiment of the present invention provides a computer program product including instructions, which, when run on a computer, causes the computer to execute the service allocation method according to the first aspect and any one of the implementation manners of the first aspect.
The service distribution method and the service distribution device provided by the embodiment of the invention can determine the service to be distributed through the text information issued by the user on the social platform, and simultaneously determine the customer service staff of the service to be distributed according to the importance degree of the user on the social platform. The method solves the importance problem of service allocation and improves the accuracy of service allocation.
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.
fig. 1 is a schematic flow chart of a service allocation method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a training process of a bayesian classifier according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating the variation of accuracy with the feature dimension according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating the variation of recall rate with feature dimension according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating the variation of F1 value with the feature dimension according to an embodiment of the present invention;
Fig. 6 is a schematic diagram illustrating a variation of a feature dimension with a change of a word frequency threshold according to an embodiment of the present invention;
Fig. 7 is a second schematic flowchart of a service allocation method according to an embodiment of the present invention;
Fig. 8 is a schematic structural diagram of a service allocating apparatus according to an embodiment of the present invention;
fig. 9 is a second schematic structural diagram of a service distribution apparatus according to an embodiment of the present invention;
fig. 10 is a third schematic structural diagram of a service allocating apparatus according to an embodiment of the present invention.
Detailed Description
The service allocation method and apparatus provided in the present application will be described in detail below with reference to the accompanying drawings.
The terms "first" and "second", etc. in the description and drawings of the present application are used for distinguishing between different objects and not for describing a particular order of the objects.
Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
it should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
the term "and/or" as used herein includes the use of either or both of the two methods.
In the description of the present application, the meaning of "a plurality" means two or more unless otherwise specified.
The invention principle of the invention is as follows: at present, banks mainly distribute corresponding customer service personnel according to the time sequence of receiving services, and the importance degree of the services is not considered. The difference of the importance degree of the service can be embodied on the clients with different importance degrees corresponding to different services. Therefore, corresponding customer service personnel can be allocated to the service according to the importance degrees of different users.
Based on the above inventive principle, an embodiment of the present invention provides a service allocation method. As shown in fig. 1, the method includes S101-S112:
S101, text information published on a social platform by a plurality of users is obtained.
Specifically, the social platform comprises public communication platforms such as a microblog platform and a WeChat platform. The text information released on the social platform includes that if the social platform is a microblog, the text information may include private messages sent by a plurality of users to related official microblogs of the bank, comments and forwards related microblogs of the bank, or at least one other user is @ in the related microblogs of the bank by the plurality of users, and the like. If the social platform is a WeChat, the text information may include messages left by a plurality of users in different public numbers of the bank, or WeChat documents issued by the plurality of users forwarding and approving the different public numbers of the bank, and the like, wherein the different public numbers of the bank include group public numbers, micro-bank public numbers and credit card public numbers.
S102, training a preset Bayesian classifier by using text information published on a social platform by a plurality of users.
The preset Bayesian classifier is a binary classifier used for dividing the text information into complaint information and non-complaint information.
Specifically, a preset Bayesian classifier is adopted to classify the text information issued by a plurality of users on the social platform through emotion analysis, and the text information is divided into complaint classes and non-complaint classes.
Illustratively, sentiment analysis is performed on comments of a plurality of users in a microblog, and the comments in the microblog are classified into a complaint class and a non-complaint class (i.e., a binary class), as shown in fig. 2.
comments of a plurality of users in the microblog are divided into a training set and a testing set (the number ratio of the training set to the testing set can be 9 to 1), the training set is used for training the preset Bayes classifier, and the testing set is used for testing the classification effect of the preset Bayes classifier. The feature words of the preset Bayes classifier are selected (namely, the feature selection shown in the figure) by carrying out word segmentation and word frequency statistics on the comment texts of the training set, and after the feature selection, a feature set, prior probability and class conditional probability of the preset Bayes classifier are obtained. The word segmentation of the test set is the same as the word segmentation of the training set, but the word frequency statistics is determined by a feature set obtained by the training set, after the word frequency statistics of the test set, the features are vectorized to form feature vectors, the final decision category of the test set is obtained according to the prior probability and the class conditional probability, and the classification effect of the preset Bayes classifier is verified.
The number of training texts in the training set is shown in table 1, and there are 3341 complaint classes and 3205 non-complaint classes. The training sets with the text information of complaints (3341) and non-complaints (3205) are subjected to binary classification, and the accuracy, the recall ratio and the F1 value related to the test set are obtained under different feature scales, as shown in FIGS. 3, 4 and 5. As can be seen from fig. 3, 4, and 5, when the feature dimension is 900, the accuracy, recall, and F1 of the test set are the highest, i.e., the preset bayesian classifier has the best classification effect. The correct rate, recall rate and F1 values for the complaint and non-complaint classes at a feature dimension of 900, and the average of the correct rate, recall rate and F1 values for all texts of the training set (complaint class + non-complaint class) are shown in table 2.
| Text categories | complaints | non-complaints |
| Number of texts | 3314 pieces | 3205 there are |
TABLE 1
| Test set | Accuracy rate | Recall rate | f1 value |
| Complaints | 82.40％ | 79.05％ | 80.69％ |
| non-complaints | 79.86％ | 83.11％ | 81.46％ |
| mean value of | 81.13％ | 81.03％ | 81.07％ |
TABLE 2
And training a preset Bayesian classifier by using text information to find out a classification form with the best classification effect. Furthermore, the preset Bayesian classifier can also be used as a binary classifier for dividing the text information into the negative information and the positive information.
Specifically, before classifying the text information, the most likely category cmap to which the text information belongs is found out by using the maximum posterior probability through prior knowledge and statistics of the existing data. The formula is as follows:
The number of texts in the training set is shown in table 3, and it can be seen that the distribution of text information is uneven, the scale difference between the complaint class and the proposed class is more than 10 times, and the complaint class and the non-complaint class are relatively balanced.
| Text categories | Complaints | Advice classes | Classes of consultation | Class of superficies |
| Number of texts | 3341A composition | 255 piece | 2607 pieces of | 305 pieces |
TABLE 3
Furthermore, in an implementation manner of the embodiment of the present invention, classifying the preset bayesian classifier by using text information published by a plurality of users on the social platform specifically includes:
And performing secondary classification on the preset Bayesian classifier by using the text information published on the social platform by the plurality of users. The first-level classification is used for classifying the text information into a binary classification of complaint information and non-complaint information; the second-level classification user divides the non-complaint information into multiple classifications of suggested information, consultation information and suggestive information.
Illustratively, the non-complaint text information (including 255 suggestive classes, 2607 counsel classes and 305 suggestive classes) from 3205 of the training set is classified in the second stage by using a cost-sensitive naive Bayes classification algorithm.
The costs are classified into two types, i.e., costs that misclassify most into minority and costs that misclassify minority into majority. The cost function can be expressed as:
Wherein, F (ci, cj) is the cost of the class ci being misclassified as the class cj, ni is the number of samples of the class ci, nj is the number of samples of the class cj, and α and β are cost factors. Typically, the cost of misclassifying minority classes into majority classes is higher than the cost of misclassifying majority classes into minority classes, so the cost factor β is often less than α for unbalanced data. Through multiple cross validation, the embodiment of the invention takes the cost factor with relatively stable test effect, namely alpha is 0.30, and beta is 0.05. The resulting cost matrix is:
The cost matrix is introduced to construct the risk function. The least risky class is used as the class cmap to which the test set is most likely to belong:
As shown in fig. 6, when the word frequency threshold is 9, most of the feature words with the discrimination can be retained, the feature dimension is about 1700, and the correct rate, the recall rate and the F1 value of the test set are the highest, which corresponds to the best classification effect of the preset bayesian assigner. Meanwhile, the accuracy, recall, F1 value and average value of the recommendation class, the consultation class and the suggestive class in the test set are shown in table 4.
| Test set | Accuracy rate | Recall rate | F1 value |
| Advice classes | 78.73％ | 68.24％ | 73.11％ |
| Classes of consultation | 94.92％ | 95.40％ | 95.16％ |
| Class of superficies | 71.17％ | 76.07％ | 73.53％ |
| mean value of | 81.61％ | 79.90％ | 80.60％ |
TABLE 4
S103, determining the service to be distributed corresponding to the text information published by the target user through the social platform.
Illustratively, a user A posts a comment on a microblog, and the embodiment of the invention can determine the service to be distributed according to the comment or determine the service to be distributed according to other text information of the user A on the microblog.
And S104, if the target text information is determined to be the complaint information by using the preset classifier, preferentially processing the service to be distributed.
Specifically, in the embodiment of the present invention, the complaint information is used as the text information with a high degree of importance, and the priority processing is performed on the task to be allocated corresponding to the complaint information. At this time, how to preferentially process the to-be-allocated services becomes a technical problem to be solved urgently.
Furthermore, in an implementation manner of the present invention, the preferentially processing the to-be-allocated service specifically includes:
S104a1, acquiring the number of the services being processed by each of the n customer service staff.
S104a2, determining a second customer service staff for processing the service to be distributed from the n customer service staff.
The second customer service staff comprises the customer service staff with the minimum service quantity in the n customer service staff.
In another implementation manner of the present invention, the preferentially processing the to-be-allocated service specifically further includes:
S104b1, obtaining the average duration of the service processed by each customer service staff in the n customer service staff.
s104b2, determining a third customer service person from the n customer service persons.
The third customer service staff comprises the customer service staff with the shortest average time length for processing the service in the n customer service staff.
it should be noted that, in the embodiment of the present invention, in order to ensure the accuracy of service allocation, the preset bayesian classifier is trained by using text information, so as to preferentially process the service to be allocated. In an implementation manner, the preset bayesian classifier may not be trained, and when the preset bayesian classifier is not trained, the method provided in the embodiment of the present invention may not perform S101 to S102 and S104, but directly start to perform S103 and S105 to S112:
And S105, determining the importance degree of the target user in the social platform according to the preset information.
The preset information comprises authentication information of the target user on the social platform, concerned times and the asset amount of a financial account corresponding to the target user.
And S106, generating user information of the target user on the social platform according to the importance degree of the target user on the social platform.
Specifically, the importance degree of the target user in the social platform is determined according to the authentication information of the target user on the social platform, the concerned times and the asset amount of the financial account corresponding to the target user, and then the user information of the target user on the social platform is generated according to the importance degree of the target user in the social platform.
illustratively, as shown in tables 5 and 6, the embodiment of the present invention divides the user according to the authentication information of the user, the concerned times and the asset amount of the financial account corresponding to the user.
| User classification | How to determine the importance of a user |
| Strategic users | Opinion leader, company focus on media, company channels of important customers |
| authenticating a user | Authenticating microblog users (including businesses and individuals) |
| People of good health | Non-authentication microblog user with vermicelli amount more than or equal to 10 ten thousand |
| Reach the person user | Non-authentication microblog user with fan amount being more than or equal to 1 ten thousand and less than 10 ten thousand |
| General users | Non-authentication microblog user with vermicelli amount less than 1 ten thousand |
TABLE 5
| user classification | How to determine the importance of a user |
| Private bank customer | Assets of over 100 ten thousand yuan |
| high net value customer | assets of 50-100 ten thousand yuan |
| middle and high end customer | Assets of 20-50 ten thousand yuan |
| General customers | Assets of 1-20 ten thousand yuan |
| Potential customer | Unknown amount of assets (unbound bank account) |
TABLE 6
In table 5, the users are classified into authenticated users (including strategic users and authenticated users) and non-authenticated users (including popularity users, reach users and normal users) according to the authentication information of the microblog users, and then the non-authenticated users are classified into popularity users, reach users and normal users according to the number of times (i.e., fan volume) that the users are concerned about. The importance degree of the user is from high to low: strategic users, authenticated users, people-qi users, reach users, and ordinary users.
in table 6, the wechat user will typically bind to an individual wechat asset account, and divide the user according to the amount of the wechat user's assets. The importance degree of the user is from high to low: private bank customers, high-net-value customers, medium-high-end customers, ordinary customers, and potential customers.
It should be noted that, in the embodiment of the present invention, the importance degree of the target user needs to be determined according to the preset information. In one implementation, the importance of the user may be determined directly without reference to preset information. When the importance degree of the user is not determined according to the preset information, the method provided by the embodiment of the invention may not execute S105-S106, but directly start to execute S103, S107-S112:
And S107, determining target customer service personnel for processing the service to be distributed according to the user information of the target user on the social platform.
User information, including information used to determine the importance of the target user in the social platform.
Specifically, target customer service personnel are allocated to the target text information sent by the target user according to the importance degree of the target user.
For example, if the user a is a normal user in the microblog, a customer service staff for processing services related to the normal user is allocated to the text message issued by the user a in the microblog. The common user is information of the importance degree of the user on a microblog (social platform).
The embodiment determines the target customer service personnel according to the information of the importance degree of the target user in the social platform.
In an implementation manner of this embodiment, the target customer service person may also be determined without depending on the information about the importance degree of the target user in the social platform, and the steps S103, S108 to S112 are directly performed:
And S108, judging whether a customer service staff performing business service with the target user at the last time exists.
And if so, determining the customer service personnel which performs business service with the target user last time as the target customer service personnel.
Specifically, in order to improve the pertinence of service allocation, especially for services with a high importance degree, the embodiment processes the service requirements of the same customer by allocating the last customer service staff of the customer. The method and the device can improve the efficiency of service processing and improve the user experience.
Illustratively, a user A publishes a piece of text information on a microblog, and if the fact that a customer service person A who processes related services for the last time related to the user A exists is judged, the customer service person A is the customer service person who processes the related services for the user A.
In another implementation manner of the embodiment, the target customer service person may also be determined without depending on the information about the importance degree of the target user in the social platform, and the steps S103, S109 to S112 are directly performed:
And S109, acquiring the work content of a plurality of customer service staff.
The working contents of the plurality of customer service staff comprise different services corresponding to different text messages sent by users with different importance degrees on the social platform, which can be processed by each customer service staff in the plurality of customer service staff.
for example, the work content of the plurality of customer service staff may be: the customer service A processes a service corresponding to a private letter sent by an authenticated user to a bank official microblog on the microblog, the customer service B processes a service corresponding to a related microblog commented by a common user on the microblog, and the customer service C processes a service corresponding to another user in the related microblog of the bank by a user.
S110, selecting a first customer service person meeting a first preset condition from a plurality of customer service persons.
the first preset condition comprises customer service staff capable of processing the service to be distributed of the target user.
And S111, if the number of the first customer service personnel is more than one, respectively acquiring the number of services processed by each customer service personnel in the first customer service personnel.
Specifically, each customer service person has the capability of handling a plurality of different services, and there may be a situation that a plurality of customer service persons can handle different services. And if the number of the customer service staff capable of processing the service to be distributed of the target user is one, directly distributing the service to be distributed to the customer service staff. If the persons to be allocated that can be handled are not unique, it is necessary to determine the number of services being handled by each service person that can handle the services to be allocated.
and S112, determining target customer service personnel from the first customer service personnel.
The target customer service staff comprises the customer service staff with the minimum service quantity in the first customer service staff.
Specifically, the customer service staff with the minimum service number in the customer service staff capable of processing the services to be distributed is found. The task to be distributed can be distributed more effectively, a load balancing effect is achieved for the whole business service system, the utilization rate of resource distribution is improved, and user experience is improved.
In one embodiment of the invention, the method further comprises:
And storing a plurality of services corresponding to text information published on the social platform by a plurality of users in a task pool.
The plurality of services stored in the task pool include a plurality of service processing states.
The processing state of the service comprises unallocated state, allocated state, interactive processing state, transfer order processing state, reply ending processing state and non-reply processing state. The interactive processing, the transfer order processing, the end of reply processing and the end of no reply processing can be understood as the final state of the service.
and comprehensively queuing the unallocated services in the task pool according to the importance degree of the user on the social platform, the published text information and the published text time.
When the work is changed or the temporary work arrangement is adjusted, the customer service staff can choose to return the assigned service staff, and the customer service manager can force to return the assigned service of the customer service staff. When the customer service person or the customer service manager returns the assigned service, the task state is changed to the unassigned service.
Each customer service person can view and process the business in the individual's work task list.
exemplarily, as shown in fig. 7, a schematic flow chart of a service allocation method provided in an embodiment of the present invention is shown. The method comprises the following steps:
and S1, reading the configuration file (namely acquiring the text information sent by the user).
And S2, inquiring the customer service configuration information (information of customer service staff corresponding to the service to be distributed corresponding to the processing text information), the historical processing record and the unprocessed task list from the database.
S3, inquiring whether the client has the original handler (i.e. the service person who processed the service last time) from the history.
If so, the service is directly assigned to the original handler, and the process goes to step S8.
And S4, if no original handler exists, finding out the customer service staff meeting the configuration. The customer service staff meeting the configuration can also be directly determined according to the customer service configuration information acquired in the step S1.
And S5, distributing the service to the customer service staff with the least current task amount by a load balancing method.
And S6, judging whether the task amount of the customer service staff with the least task amount exceeds the rated task amount.
If the number of services currently allocated to the customer service person with the least amount of tasks exceeds the rated number, go to step S7, if the number of services currently allocated to the customer service person with the least amount of tasks does not exceed the rated number, allocate the services to the service handler with the least amount of tasks, and go to step S8.
s7, after waiting for a period, returning to the step S5, and reassigning to the customer service staff with the least amount of tasks.
And S8, updating the task distribution result. Meanwhile, a cyclic process is performed. Wherein, the cycle processing, including changing the task state from unallocated to allocated, updating the service allocation time to allocation success time, and adding 1 (not shown in the figure) to the corresponding service number of the customer service personnel.
The present application provides a service allocating apparatus, configured to execute the foregoing service allocating method, as shown in fig. 8, which is a schematic diagram of a possible structure of a service allocating apparatus 20 according to an embodiment of the present invention. Wherein, the device includes:
The processing unit 201 is configured to determine a service to be allocated corresponding to target text information published by a target user through a social platform.
The processing unit 201 is further configured to determine, according to the user information of the target user on the social platform, a target customer service person who processes the service to be distributed. User information, including information used to determine the importance of the target user in the social platform.
Optionally, the processing unit 201 is further configured to determine whether a customer service staff performing service with the target user last time exists. And if so, determining the customer service personnel which performs business service with the target user last time as the target customer service personnel.
Optionally, the apparatus further comprises an obtaining unit 202.
the acquiring unit 202 is configured to acquire work content of a plurality of customer service staff. The working contents of the plurality of customer service staff comprise different services corresponding to different text messages sent by users with different importance degrees on the social platform, which can be processed by each customer service staff in the plurality of customer service staff.
The processing unit 201 is further configured to select a first customer service person meeting a first preset condition from the plurality of customer service persons. The first preset condition comprises customer service staff capable of processing the service to be distributed of the target user.
The obtaining unit 202 is further configured to, if the number of the first customer service staff is greater than one, respectively obtain the number of services being processed by each of the first customer service staff.
The processing unit 201 is further configured to determine a target customer service from the first customer service staff. The target customer service staff comprises the customer service staff with the minimum business quantity in the first customer service staff.
Optionally, the obtaining unit 202 is further configured to obtain text information published on the social platform by a plurality of users.
The processing unit 201 is further configured to train a preset bayesian classifier by using text information published on the social platform by the multiple users. The preset Bayesian classifier is a binary classifier used for classifying the text information into complaint information and non-complaint information.
The processing unit 201 is further configured to preferentially process the service to be allocated if the target text information is determined to be the complaint type information by using a preset bayesian classifier.
Optionally, the processing unit 201 is further configured to determine, according to preset information, an importance degree of the target user in the social platform. The preset information comprises authentication information of the target user in the social platform, concerned times and the asset amount of a financial account corresponding to the target user.
the processing unit 201 is further configured to generate user information of the target user on the social platform according to the importance degree of the target user on the social platform.
In the embodiment of the present application, the service allocating apparatus may be divided into the functional modules or the functional units according to the above method examples, for example, each functional module or functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module may be implemented in a form of hardware, or may be implemented in a form of a software functional module or a functional unit. The division of the modules or units in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.
In the case of an integrated unit, fig. 9 shows a schematic diagram of a possible structure of the service distribution device according to the above embodiment. The service distribution apparatus 30 includes: a processing module 301, a communication module 302 and a storage module 303. The processing module 301 is used for controlling and managing the actions of the service distribution apparatus 30, for example, the processing module 301 is used for supporting the service distribution apparatus 30 to execute the processes S101-S112 in fig. 1. The communication module 302 is used to support communication between the service distribution apparatus 30 and other entities. The memory module 303 is used to store program codes and data of the service distribution apparatus.
the processing module 301 may be a processor or a controller, such as a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an application-specific integrated circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. A processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, a DSP and a microprocessor, or the like. The communication module 302 may be a transceiver, a transceiving circuit or a communication interface, etc. The storage module 303 may be a memory.
When the processing module 301 is a processor as shown in fig. 10, the communication module 302 is a transceiver as shown in fig. 10, and the storage module 303 is a memory as shown in fig. 10, the service distribution apparatus according to the embodiment of the present invention may be the following service distribution apparatus 40.
Referring to fig. 10, the service distribution apparatus 40 includes: a processor 401, a transceiver 402, a memory 403, and a bus 404.
The processor 401, the transceiver 402 and the memory 403 are connected to each other through a bus 404; the bus 404 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
Processor 401 may be a general-purpose Central Processing Unit (CPU), a microprocessor, an Application-Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to control the execution of programs in accordance with the present invention.
the Memory 403 may be a Read-Only Memory (ROM) or other type of static storage device that can store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that can store information and instructions, an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these. The memory may be self-contained and coupled to the processor via a bus. The memory may also be integral to the processor.
Wherein the memory 403 is used for storing application program codes for executing the scheme of the present invention, and the execution is controlled by the processor 401. The transceiver 402 is configured to receive content input from an external device, and the processor 401 is configured to execute application program codes stored in the memory 403, so as to implement a service distribution method provided in an embodiment of the present invention.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. 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 invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the invention are all or partially effected when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optics, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or can comprise one or more data storage devices, such as a server, a data center, etc., that can be integrated with the medium. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (12)
1. A method for service allocation, the method comprising:
Determining a service to be distributed corresponding to target text information issued by a target user through a social platform;
Determining a target customer service person for processing the service to be distributed according to the user information of the target user on the social platform; the user information comprises information used for determining the importance degree of the target user in the social platform.
2. The traffic distribution method according to claim 1, characterized in that the method further comprises:
Judging whether a customer service staff who performs business service with the target user last time exists; and if so, determining the customer service personnel which performs business service with the target user last time as the target customer service personnel.
3. The traffic distribution method according to claim 1, characterized in that the method further comprises:
Acquiring the work content of a plurality of customer service personnel; the working contents of the plurality of customer service staff comprise different services corresponding to different text messages sent by users with different importance degrees on the social platform, which can be processed by each customer service staff in the plurality of customer service staff;
Selecting a first customer service person meeting a first preset condition from the plurality of customer service persons; the first preset condition comprises customer service personnel capable of processing the service to be distributed of the target user;
If the number of the first customer service personnel is more than one, respectively acquiring the number of services being processed by each of the first customer service personnel;
Determining target customer service personnel from the first customer service personnel; the target customer service staff comprises the customer service staff with the minimum service quantity in the first customer service staff.
4. The service distribution method according to any one of claims 1 to 3, wherein before the determining, according to the user information of the target user on the social platform, a target customer service person who handles the service to be distributed, the method further comprises:
Acquiring text information published on the social platform by a plurality of users;
Training a preset Bayesian classifier by using the text information published on the social platform by the users; the preset Bayesian classifier is a binary classifier used for classifying the text information into complaint information and non-complaint information;
after determining the task to be allocated corresponding to the target text information published by the target user through the social platform, the method further comprises:
And if the target text information is determined to be complaint information by using the preset Bayesian classifier, preferentially processing the service to be distributed.
5. The service distribution method according to any one of claims 1 to 3, wherein before the determining, according to the user information of the target user on the social platform, a target customer service person who handles the service to be distributed, the method further comprises:
determining the importance degree of the target user in the social platform according to preset information; the preset information comprises authentication information of the target user in the social platform, concerned times and an asset amount of a financial account corresponding to the target user;
And generating user information of the target user on the social platform according to the importance degree of the target user on the social platform.
6. A traffic distribution apparatus, characterized in that the apparatus comprises:
The processing unit is used for determining a service to be distributed corresponding to target text information issued by a target user through a social platform;
the processing unit is further configured to determine, after the processing unit determines a to-be-allocated service corresponding to target text information issued by a target user through a social platform, a target customer service person who processes the to-be-allocated service according to user information of the target user on the social platform; the user information comprises information used for determining the importance degree of the target user in the social platform.
7. Traffic distribution apparatus according to claim 6,
The processing unit is also used for judging whether a customer service staff who performs business service with the target user last time exists; and if so, determining the customer service personnel which performs business service with the target user last time as the target customer service personnel.
8. The traffic distribution apparatus of claim 6, wherein the apparatus further comprises:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the working contents of a plurality of customer service staff; the working contents of the plurality of customer service staff comprise different services corresponding to different text messages sent by users with different importance degrees on the social platform, which can be processed by each customer service staff in the plurality of customer service staff;
The processing unit is used for selecting a first customer service person meeting a first preset condition from the plurality of customer service persons after the acquisition unit acquires the work content of the plurality of customer service persons; the first preset condition comprises customer service personnel capable of processing the service to be distributed of the target user;
The obtaining unit is further configured to, after the processing unit selects a first customer service person meeting a first preset condition from the plurality of customer service persons, respectively obtain the number of services being processed by each of the first customer service persons if the number of the first customer service persons is greater than one;
The processing unit is further configured to determine a target customer service person from the first customer service persons after the obtaining unit obtains the number of services being processed by each of the first customer service persons respectively; the target customer service staff comprises the customer service staff with the minimum service quantity in the first customer service staff.
9. Traffic distribution device according to any of the claims 6-8,
the acquisition unit is used for acquiring text information published on the social platform by a plurality of users;
The processing unit is further configured to train a preset bayesian classifier by using the text information published on the social platform by the plurality of users after the obtaining unit obtains the text information published on the social platform by the plurality of users; the preset Bayesian classifier is a binary classifier used for classifying the text information into complaint information and non-complaint information;
And the processing unit is further configured to, after the processing unit determines a service to be allocated corresponding to target text information issued by a target user through a social platform, preferentially process the service to be allocated if the target text information is determined to be complaint information by using the preset bayesian classifier.
10. Traffic distribution device according to any of the claims 6-8,
The processing unit is further used for determining the importance degree of the target user in the social platform according to preset information; the preset information comprises authentication information of the target user in the social platform, concerned times and an asset amount of a financial account corresponding to the target user;
The processing unit is further configured to generate user information of the target user on the social platform according to the importance degree of the target user on the social platform after the processing unit determines the importance degree of the target user on the social platform.
11. A traffic distribution apparatus, characterized in that the traffic distribution apparatus comprises: a processor, a communication interface, and a memory; wherein the memory is used for storing one or more programs, the one or more programs comprising computer executable instructions, and when the service distribution apparatus is running, the processor executes the computer executable instructions stored in the memory to make the service distribution apparatus execute the service distribution method according to any one of claims 1 to 5.
12. A computer-readable storage medium having instructions stored thereon, which when run on a computer, cause the computer to perform the traffic distribution method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910754473.3A CN110544021A (en) | 2019-08-15 | 2019-08-15 | service distribution method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910754473.3A CN110544021A (en) | 2019-08-15 | 2019-08-15 | service distribution method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110544021A true CN110544021A (en) | 2019-12-06 |
Family
ID=68711433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910754473.3A Pending CN110544021A (en) | 2019-08-15 | 2019-08-15 | service distribution method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110544021A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539606A (en) * | 2020-04-14 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Service processing method, device and equipment |
| CN111861225A (en) * | 2020-07-23 | 2020-10-30 | 中国建设银行股份有限公司 | Task allocation method and device, electronic equipment and storage medium |
| CN116070879A (en) * | 2023-02-27 | 2023-05-05 | 北京时代凌宇数字技术有限公司 | City management event dispatching method and device, electronic equipment and storage medium |
| CN111861225B (en) * | 2020-07-23 | 2024-05-24 | 中国建设银行股份有限公司 | Task allocation method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102299903A (en) * | 2010-06-23 | 2011-12-28 | 深圳市腾讯计算机系统有限公司 | Method, device and system for processing user request |
| CN103309948A (en) * | 2013-05-20 | 2013-09-18 | 携程计算机技术（上海）有限公司 | System and method for public opinion monitoring analysis and intelligent distribution processing of coordination center |
| US20140350981A1 (en) * | 2013-05-27 | 2014-11-27 | Hitachi, Ltd. | Service provider allocation system and allocation management device |
| CN105740463A (en) * | 2016-03-03 | 2016-07-06 | 世纪禾光科技发展（北京）有限公司 | Website message allocation and management method, device and system |
| CN108416375A (en) * | 2018-02-13 | 2018-08-17 | 中国联合网络通信集团有限公司 | Work order sorting technique and device |
-
2019
- 2019-08-15 CN CN201910754473.3A patent/CN110544021A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102299903A (en) * | 2010-06-23 | 2011-12-28 | 深圳市腾讯计算机系统有限公司 | Method, device and system for processing user request |
| CN103309948A (en) * | 2013-05-20 | 2013-09-18 | 携程计算机技术（上海）有限公司 | System and method for public opinion monitoring analysis and intelligent distribution processing of coordination center |
| US20140350981A1 (en) * | 2013-05-27 | 2014-11-27 | Hitachi, Ltd. | Service provider allocation system and allocation management device |
| CN105740463A (en) * | 2016-03-03 | 2016-07-06 | 世纪禾光科技发展（北京）有限公司 | Website message allocation and management method, device and system |
| CN108416375A (en) * | 2018-02-13 | 2018-08-17 | 中国联合网络通信集团有限公司 | Work order sorting technique and device |
Non-Patent Citations (1)
| Title |
|---|
| 康琦，吴启迪: "《机器学习中的不平衡分类方法》", 同济大学出版社, pages: 40 - 42 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539606A (en) * | 2020-04-14 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Service processing method, device and equipment |
| CN111861225A (en) * | 2020-07-23 | 2020-10-30 | 中国建设银行股份有限公司 | Task allocation method and device, electronic equipment and storage medium |
| CN111861225B (en) * | 2020-07-23 | 2024-05-24 | 中国建设银行股份有限公司 | Task allocation method and device, electronic equipment and storage medium |
| CN116070879A (en) * | 2023-02-27 | 2023-05-05 | 北京时代凌宇数字技术有限公司 | City management event dispatching method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11323347B2 (en) | Systems and methods for social graph data analytics to determine connectivity within a community | |
| US10887177B2 (en) | Calculating trust scores based on social graph statistics | |
| Kvasnicova et al. | From an analysis of e-services definitions and classifications to the proposal of new e-service classification | |
| US9922134B2 (en) | Assessing and scoring people, businesses, places, things, and brands | |
| US10311106B2 (en) | Social graph visualization and user interface | |
| WO2019037202A1 (en) | Method and apparatus for recognising target customer, electronic device and medium | |
| CN107808314B (en) | User recommendation method and device | |
| US9246923B1 (en) | Developer risk classifier | |
| US20210256445A1 (en) | System and method for matching resource capacity with client resource needs | |
| WO2009130476A1 (en) | Method | |
| CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
| CN110544021A (en) | service distribution method and device | |
| CN110019774B (en) | Label distribution method, device, storage medium and electronic device | |
| WO2022257731A1 (en) | Method, device and system for performing algorithm negotiation on privacy computation | |
| CN110851482B (en) | Method and device for providing data model for multiple data parties | |
| CN110852809A (en) | Data processing method, device, equipment and medium | |
| CN109993417A (en) | A kind of service condition mark adding method, device and storage medium | |
| CN111476371B (en) | Method and device for evaluating specific risk faced by server | |
| CN111882113A (en) | Enterprise mobile banking user prediction method and device | |
| CN112132690B (en) | Method and device for pushing foreign exchange product information, computer equipment and storage medium | |
| CN107563599A (en) | Patent valve estimating system based on big data | |
| CN111144091B (en) | Customer service member determination method and device and group member identification determination method | |
| CN112163155A (en) | Information processing method, device, equipment and storage medium | |
| CN114254624B (en) | Method and system for determining website type | |
| CN112669154B (en) | Foreign currency exchange business development prediction implementation method and device and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191206 |
|
| RJ01 | Rejection of invention patent application after publication |