CN116523218A - Service personnel matching method and system - Google Patents
Service personnel matching method and system Download PDFInfo
- Publication number
- CN116523218A CN116523218A CN202310400742.2A CN202310400742A CN116523218A CN 116523218 A CN116523218 A CN 116523218A CN 202310400742 A CN202310400742 A CN 202310400742A CN 116523218 A CN116523218 A CN 116523218A
- Authority
- CN
- China
- Prior art keywords
- client
- matching
- service personnel
- information
- login
- 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 31
- 238000003066 decision tree Methods 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims description 18
- 230000006399 behavior Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 6
- 230000009191 jumping Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 description 25
- 108091006146 Channels Proteins 0.000 description 9
- 238000010586 diagram Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 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
- G06Q10/063118—Staff planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
Abstract
The invention provides a matching method and a matching system for service personnel, which relate to the technical field of data processing, and the method comprises the following steps: obtaining different matching strategies according to the client types, wherein each matching strategy comprises a multi-level matching rule; and constructing a decision tree model to predict the demands of the clients, so as to determine the priority order of the multi-level matching rules according to the demands of the clients, and matching service personnel for different types of clients by adopting the multi-level matching rules according to the priority order. The matching rule adjustment is realized according to the client demands, so that service personnel can be matched according to the client demands, the accuracy and the flexibility of the client matching service personnel are improved, and the technical problems of single matching rule and inaccurate matching result of the client and the service personnel in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a matching method and a matching system for service personnel.
Background
The current method for adding service personnel by the client is to judge through the geographic position and the distance, and display the nearest service personnel in the geographic position to the client for adding, so that the client is easily lost under the condition that the service personnel are unknowing, or the service personnel found by the client are out of compliance with the requirements, the service requirements and the like. The requirements of accurate establishment of the connected clients and addition of the clients in multiple scenes of operators are met, and the requirements of matching the clients with service staff in the activities are already met.
Therefore, the prior art has the technical problems that the matching of the client and the service personnel is inaccurate, the client requirements cannot be met, and the like.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a matching method for service personnel, so as to solve the technical problems of single matching rule and inaccurate matching result of clients and service personnel in the prior art. The method comprises the following steps: acquiring client information of a login client of a service interface;
matching the client information with prestored client type related information, determining the client type of the login client according to a matching result, and acquiring a matching strategy corresponding to the login client according to the client type of the login client, wherein the matching strategy comprises a preset multi-level matching rule, and the client type comprises a new client, an old client and a member client;
predicting the demand category of the login client through a decision tree model according to the client information;
determining the priority order of the multi-level matching rules according to the demand category;
and determining the account information of the service personnel of the login client by adopting the multilevel matching rule in sequence according to the priority order.
Further, predicting the demand category of the logged-in client through a decision tree model according to the client information includes:
extracting feature attributes from the client information, wherein the feature attributes comprise position features, business features and client-level features;
and inputting the characteristic attribute into the decision tree model to obtain the demand category, wherein the decision tree model is obtained by training by taking the characteristic attribute of the historical client information as a sample.
Further, in the process of training the decision tree model, each characteristic attribute of the historical client information corresponds to a weight value, and training of the decision tree model is performed according to each characteristic attribute of the historical client information and the corresponding weight value.
Further, training the decision tree model according to each characteristic attribute and the corresponding weight value of the historical client information, including:
extracting client behavior data according to historical client information in a database, wherein the client behavior data comprises the characteristic attributes and a selection result of a client on service personnel;
analyzing the client behavior data to obtain the correlation degree of each characteristic attribute of the historical client information and the selected result, and adjusting the weight value corresponding to each characteristic attribute according to the correlation degree;
and training the decision tree model according to the characteristic attributes of the historical client information and the adjusted weight values.
Further, determining account information of the service personnel of the login client by sequentially adopting the multi-level matching rule according to the priority order comprises the following steps:
according to the client type of the login client, obtaining a matching strategy corresponding to the login client comprises the following steps:
acquiring a plurality of basic matching rules;
when the client type is the old client or the member client, determining at least two historical matching rules for matching account information of service personnel for the login client according to the client information of the login client, selecting a basic matching rule corresponding to the historical matching rule from a plurality of basic matching rules, and combining the selected basic matching rules to form a multi-level matching rule in a matching strategy corresponding to the old client or the member client, wherein each level of matching rule comprises one or more basic matching rules;
when the client type is the new client, combining a plurality of basic matching rules to form a multi-level matching rule in a matching strategy corresponding to the new client, wherein each level of matching rule comprises one or a plurality of basic matching rules;
according to the priority order, determining the account information of the service personnel of the login client by adopting the multi-level matching rule in sequence comprises the following steps:
determining account information of service personnel of the login client by adopting a basic matching rule in the same-level matching rule in a logical sum mode; according to the priority order, if the account information of the service personnel of the login client is not determined in the current-stage matching rule, jumping to the next-stage matching rule to determine the account information of the service personnel of the login client; and if the account information of the service personnel logging in the client is determined in the current-stage matching rule, the matching flow of the service personnel is finished.
Further, if the account information of the service personnel of the login client is not determined by sequentially adopting the multi-stage matching rule, the account information of the preset service personnel is determined to be the account information of the service personnel of the login client.
Further, according to the friend information of the login client, a mark is added to the friend account information of the login client in the determined account information of the service personnel of the login client.
The invention also provides a matching system for the service personnel, which solves the technical problems of single matching rule and inaccurate matching result of the client and the service personnel in the prior art. The system comprises:
the client information acquisition module is used for acquiring client information of a login client of the service interface;
the matching strategy acquisition module is used for matching the client information with prestored client type related information, determining the client type of the login client according to a matching result, and acquiring a matching strategy corresponding to the login client according to the client type of the login client, wherein the matching strategy comprises a preset multi-level matching rule, and the client type comprises a new client, an old client and a member client;
the demand category prediction module is used for predicting the demand category of the login client through a decision tree model according to the client information;
the matching sequence generation module is used for determining the priority sequence of the multi-level matching rule according to the requirement category;
and the service personnel matching module is used for determining account information of service personnel logging in the client by sequentially adopting the multi-level matching rule according to the priority order.
Compared with the prior art, the beneficial effects that above-mentioned at least one technical scheme that this description embodiment adopted can reach include at least: obtaining different matching strategies according to the client types, wherein each matching strategy comprises a multi-level matching rule; and constructing a decision tree model to predict the demands of the clients, so as to determine the priority order of the multi-level matching rules according to the demands of the clients, and matching service personnel for different types of clients by adopting the multi-level matching rules according to the priority order. The matching rule priority adjustment is realized according to the client demands, so that service personnel can be matched according to the client demands, the accuracy and the flexibility of the client matching service personnel are improved, the accuracy and the precision of the matching result are improved, and the demands of users are further met.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a matching method for service personnel according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a matching system for service personnel according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a computer device according to an embodiment of the present invention.
Reference numerals in the drawings: 200. a system; 210. a customer information acquisition module; 220. a matching strategy acquisition module; 230. a demand category prediction module; 240. a matching sequence generating module; 250. a service personnel matching module; 301. a memory; 302. a processor.
Detailed Description
Embodiments of the present application are described in detail below with reference to the accompanying drawings.
Other advantages and effects of the present application will become apparent to those skilled in the art from the present disclosure, when the following description of the embodiments is taken in conjunction with the accompanying drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. The present application may be embodied or carried out in other specific embodiments, and the details of the present application may be modified or changed from various points of view and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In the embodiment of the invention, a matching method for service personnel is provided, different matching strategies are obtained according to the type of a client, and each matching strategy comprises a multi-level matching rule; and constructing a decision tree model to predict the demands of the clients, so as to determine the priority order of the multi-level matching rules according to the demands of the clients, and matching service personnel for different types of clients by adopting the multi-level matching rules according to the priority order. The matching rule priority adjustment is realized according to the client demands, so that service personnel can be matched according to the client demands, the accuracy and the flexibility of the client matching service personnel are improved, the accuracy and the precision of the matching result are improved, and the demands of users are further met.
As shown in fig. 1, the matching method of service personnel according to the embodiment of the invention includes the following steps:
step S100: acquiring client information of a login client of a service interface;
in specific implementation, the service interface can be a page of various activities and services, and in background configuration, different service activities can be configured in a self-defined manner according to operation requirements. The configuration includes three steps of activity policy configuration, activity rule configuration and activity release configuration. The activity name, activity validity period and activity pattern are preconfigured in the activity policy configuration. The active style may be selectable from different style templates and support uploading custom background pictures. After uploading the corresponding background map according to the UI specification, the client will look at the landing page of the custom background on the page. After the user logs in, the client information is firstly acquired, and may include client device information, location information, service history information, history matching information, grade information and the like. After the customer information is obtained, the login user information is updated to the customer database.
Step S200: matching the client information with prestored client type related information, determining the client type of the login client according to a matching result, and acquiring a matching strategy corresponding to the login client according to the client type of the login client, wherein the matching strategy comprises a preset multi-level matching rule, and the client type comprises a new client, an old client and a member client;
specifically, the pre-stored relevant information of the client type is a local client database, in the local database, the client is classified and stored according to different types, and the specific client type comprises: new clients, old clients, and member clients. Matching the client information of the login client with the client information in the local database, and if the client information does not exist in the client database, storing the login client into a new client type; if the client information exists in the client database, the client type of the login client is further acquired, and the login client is judged to be an old client or a member client. The clients are different in type, the corresponding matching strategies are different, and the matching modes of the clients are different. Such as: the new client corresponds to a new client matching policy; the old customer corresponds to an old customer matching strategy, and the matching is carried out according to the modes of preferential screening and the like of an associated service manager; the member clients correspond to the matching strategies, including the modes of matching according to client appointed client managers or directly matching high-level client managers. The different matching strategies respectively comprise multi-stage matching rules, the clients are classified according to the client types, and different matching strategies are applied, so that the client matching is more accurate, and the client experience is improved.
Further, according to the client type of the login client, obtaining a matching policy corresponding to the login client includes:
acquiring a plurality of basic matching rules;
when the client type is the old client or the member client, determining at least two historical matching rules for matching account information of service personnel for the login client according to the client information of the login client, selecting a basic matching rule corresponding to the historical matching rule from a plurality of basic matching rules, and combining the selected basic matching rules to form a multi-level matching rule in a matching strategy corresponding to the old client or the member client, wherein each level of matching rule comprises one or more basic matching rules;
when the client type is the new client, combining a plurality of basic matching rules to form a multi-level matching rule in a matching strategy corresponding to the new client, wherein each level of matching rule comprises one or a plurality of basic matching rules;
according to the priority order, determining the account information of the service personnel of the login client by adopting the multi-level matching rule in sequence comprises the following steps:
determining account information of service personnel of the login client by adopting a basic matching rule in the same-level matching rule in a logical sum mode; according to the priority order, if the account information of the service personnel of the login client is not determined in the current-stage matching rule, jumping to the next-stage matching rule to determine the account information of the service personnel of the login client; and if the account information of the service personnel logging in the client is determined in the current-stage matching rule, the matching flow of the service personnel is finished.
Specifically, after a client logs in, the client type is obtained, and the client type is divided into: new clients, old clients, and member clients. When the logged-in client type is an old client or a member client, the history matching information of the client is extracted, one or more basic matching rules related to the history matching rules of the client are selected from the basic matching rules, and the basic matching rules are combined in different combination modes to form a multi-level matching rule. When the login client is a new client, the multi-level matching rules corresponding to the new client are generated directly by combining various basic matching rules. The basic matching rule is a preset rule, and can be changed, added and deleted at any time.
In this embodiment, preferably, the plurality of basic matching rules specifically include: link matching: the method comprises the steps that sharer information is obtained through url (Uniform Resource Locator ) accessed by a client, and if the sharer information is carried in a link, a page displays channel activity codes of a shared client manager preferentially; position matching: when the client authorizes to agree to use the geographic position, the current position information of the client is acquired, the client manager of the reported geographic position is acquired through a longitude and latitude algorithm, and the client manager of which the service position is closest to the geographic position of the client is matched; branch office matching: and (5) docking with big data in an ftp mode, and dividing a client manager according to the branch office. After the customer logs in, the equipment number of the customer and the equipment number of the grid are obtained to find out the affiliated branch office, and the affiliated branch office is matched with a customer manager under the branch office of the customer; selecting and matching: and configuring a designated department, employee labels or client manager, and directly displaying a client manager list according to the configuration result of the selector component after the client enters the page. The background configuration is completed through a personnel selecting component, and an administrator can select departments or staff labels for configuration. When a plurality of departments are selected, taking a union of the departments; when a plurality of employee tags are selected, a union of the employee tags is taken; when there is both department and employee label, the employees in the department and label intersection range are fetched.
Further, after generating the multi-level matching rules corresponding to different login clients, each level of matching rule is displayed to the login clients according to the priority order determined in step S400; each level of matching rules respectively comprises one or more basic matching rules, and a plurality of basic matching rules in the same level of matching rules sequentially determine account information of service personnel of the login client in a logical sum mode; after each level of matching rules enter matching, a plurality of basic matching rules are sequentially displayed on the login clients respectively, and if the login clients finish matching of service personnel through the basic matching rules of the current level, the matching flow is ended; if the login client fails to match the service personnel through the current-stage matching rule, the login client automatically jumps to the next-stage matching rule to match. For example, if the first-level matching rule is position matching and person selection matching, after entering the matching rule, the user performs matching of service personnel according to the position matching and person selection matching respectively, and the results of the position matching and person selection matching are combined to obtain final service personnel account information, and then the matching is stopped. The end user achieves accurate matching under this level of matching rules.
Step S300: predicting the demand category of the login client through a decision tree model according to the client information;
further, step S300 further includes:
step S310: extracting feature attributes from the client information, wherein the feature attributes comprise position features, business features and client-level features;
step S320: and inputting the characteristic attribute into the decision tree model to obtain the demand category, wherein the decision tree model is obtained by training by taking the characteristic attribute of the historical client information as a sample.
In step S320, in the process of training the decision tree model, each feature attribute of the historical client information corresponds to a weight value, and training of the decision tree model is performed according to each feature attribute of the historical client information and the corresponding weight value.
In particular, the decision tree model is built from client information in a local client database. Firstly, carrying out data processing on information in a database, including clear processing, duplicate removal processing, missing value filling processing and the like on the data. And then extracting the equipment number, the position, the associated link, the browsing record, the business record, the client level and other characteristics of the client information in the local database, and finally matching the client manager information of the client. According to the extracted characteristic attributes, data segmentation is recursively carried out by taking information entropy as an index to generate a decision tree model, the built database model is evaluated and optimized, the output information of the decision tree model is the demand preference of a client, and the weight value occupied by each characteristic attribute of the user in the final matching of the user manager can be obtained through the decision tree model, so that the matching preference of the user is estimated. Extracting characteristic attributes (including equipment information, access sources, position information and the like) of acquired client information of a login client according to the estimated and optimized decision tree model, inputting the extracted characteristic attributes into a trained decision tree model, outputting the demand category of the user by the decision tree model, and obtaining a matching mode of client preference, wherein the method comprises the following steps: matching by location, matching by historic associated client manager, matching by associated client manager in the shared link, etc. After the client demand category is obtained, the multi-level matching rules are displayed for clients in sequence according to the sequence of the association degree with the demand category from large to small. For example, if the decision tree model predicts that the user demand category is link matching, the matching rule including link matching is preferentially presented, so that the client directly interfaces with a specific client manager in the shared link, and the service manager interface is preferentially presented.
Further, step S320 further includes:
step S321: extracting client behavior data according to historical client information in a database, wherein the client behavior data comprises the characteristic attributes and a selection result of a client on service personnel;
step S322: analyzing the client behavior data to obtain the correlation degree of each characteristic attribute of the historical client information and the selected result, and adjusting the weight value corresponding to each characteristic attribute according to the correlation degree;
step S323: and training the decision tree model according to the characteristic attributes of the historical client information and the adjusted weight values.
Specifically, each characteristic attribute in the decision tree model corresponds to a weight value. And analyzing the client behavior data in the local client database to obtain the association degree of each characteristic attribute and the client manager matching result, and determining the weight value of each characteristic attribute according to the association degree, thereby constructing the decision tree model. Through the continuous updating of the client data in the local client database, the weight value corresponding to each characteristic attribute is also continuously updated, and the corresponding decision tree model is also continuously updated and optimized, so that the demand category prediction of the user is more accurate.
Further, for modification of the feature attribute weight value, each time the client completes client manager matching, records client behaviors, incorporates the client behaviors into a local client database, performs data analysis by using machine learning to obtain matching preference and behavior trend of different types of users, and then corrects the weight of the feature attribute of the decision tree model according to the user matching preference so as to realize matching display more in line with the user preference.
Step S400: determining the priority order of the multi-level matching rules according to the demand category;
step S500: and determining the account information of the service personnel of the login client by adopting the multilevel matching rule in sequence according to the priority order.
In particular, the multi-level matching rules consist of one or more basic matching rules. And combining the multiple levels of matching rules.
After the clients log in, firstly determining a multi-level matching rule corresponding to the logged-in clients according to the client types, predicting the demand categories of the logged-in clients through a decision tree model, and displaying the first-level matching rule with the highest association degree according to the association degree of the demand categories and the matching rules of all levels. For example, if the predicted client demand category is link matching, a rule that is link matching in the multi-level matching rules is selected as a first-level rule, and the channel activity code of the link corresponding to the shared client manager is preferentially displayed. And the clients match the client managers according to the multi-level matching rules until the clients select the matched client managers. If the matching rules are matched with a plurality of client managers, a client manager list is displayed, whether friends are added or not is marked, and the client can click to check personal information of the client manager and channel activity codes for adding; if the personal information and the channel activity code of the client manager are matched, the personal information and the channel activity code of the client manager are directly displayed.
Further, after step S500, if the account information of the service personnel of the login client is not determined by sequentially adopting the multi-stage matching rule, determining the account information of the preset service personnel as the account information of the service personnel of the login client; and adding a mark to the friend account information of the login user in the determined account information of the service personnel of the login user according to the friend information of the login user.
Specifically, if service personnel cannot be determined after the matching is completed through the multi-level matching rule, preset service personnel are displayed on the login user, and customer loss caused by that customers cannot be matched with a customer manager is avoided; and when the list is empty, reminding a manager to adjust rule configuration, and avoiding the situation that service personnel cannot be determined. In addition, in the service personnel account information displayed after the matching is completed, the identification and the display are carried out on the client manager which is in friend relation with the login client.
Further, in the activity distribution configuration, a channel column of the activity distribution needs to be selected (the channel column and the corresponding code need to be configured by an operator in advance in channel management). In matching the buddy settings, the customer may be selected to be presented only with the customer manager that is not added as a buddy. And after the client adds friends through the activity, the system automatically sends welcome language and accessories through the client manager and automatically marks local tags for recording. After the background configuration activity is completed, the activity address can be obtained according to the channel column to carry out delivery. After the activity is put off or ended, if a client clicks to enter the landing page, the friendly prompt page which is ended by the activity is displayed, and the multi-user activity code of the preconfigured client manager is displayed, so that the loss of the client is avoided. According to the invention, the matching rules are configured in a plurality of modes, so that the matching accuracy of a client manager is improved, the client experience is improved, and the client loss is avoided.
In specific implementation, the service personnel may be various service personnel (for example, client managers of various services), and account information WeChat account numbers, enterprise WeChat account numbers, department information, names and the like of the service personnel.
Based on the same inventive concept, the embodiment of the invention also provides a matching system for service personnel, as described in the following embodiment. Because the principle of solving the problem of the matching system of the service personnel is similar to that of the matching method of the service personnel, the implementation of the matching system of the service personnel can refer to the implementation of the matching method of the service personnel, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 2 is a block diagram of a service person matching system 200 according to an embodiment of the present invention, as shown in fig. 2, including: a client information obtaining module 210, configured to obtain client information of a login client of the service interface; the matching policy obtaining module 220 is configured to match the client information with pre-stored client type related information, determine a client type of the login client according to a matching result, and obtain a matching policy corresponding to the login client according to the client type of the login client, where the matching policy includes a preset multi-level matching rule, and the client type includes a new client, an old client, and a member client; a demand category prediction module 230, configured to predict a demand category of the logged-in client through a decision tree model according to the client information; a matching sequence generating module 240, configured to determine a priority sequence of the multi-level matching rule according to the requirement category; and the service personnel matching module 250 is used for determining account information of service personnel of the login client by sequentially adopting the multi-level matching rule according to the priority order.
Further, the demand category prediction module 230 is further configured to: extracting feature attributes from the client information, wherein the feature attributes comprise position features, business features and client-level features;
and inputting the characteristic attribute into the decision tree model to obtain the demand category, wherein the decision tree model is obtained by training by taking the characteristic attribute of the historical client information as a sample.
Further, the demand category prediction module 230 is further configured to: in the process of training the decision tree model, each characteristic attribute of the historical client information is corresponding to a weight value, and training of the decision tree model is performed according to each characteristic attribute of the historical client information and the corresponding weight value.
Further, the demand category prediction module 230 is further configured to: extracting client behavior data according to historical client information in a database, wherein the client behavior data comprises the characteristic attributes and a selection result of a client on service personnel;
analyzing the client behavior data to obtain the correlation degree of each characteristic attribute of the historical client information and the selected result, and adjusting the weight value corresponding to each characteristic attribute according to the correlation degree;
and training the decision tree model according to the characteristic attributes of the historical client information and the adjusted weight values.
Further, the matching policy obtaining module 220 is configured to obtain a plurality of basic matching rules;
when the client type is the old client or the member client, determining at least two historical matching rules for matching account information of service personnel for the login client according to the client information of the login client, selecting a basic matching rule corresponding to the historical matching rule from a plurality of basic matching rules, and combining the selected basic matching rules to form a multi-level matching rule in a matching strategy corresponding to the old client or the member client, wherein each level of matching rule comprises one or more basic matching rules;
when the client type is the new client, combining a plurality of basic matching rules to form a multi-level matching rule in a matching strategy corresponding to the new client, wherein each level of matching rule comprises one or a plurality of basic matching rules;
the service person matching module 250 is configured to determine account information of the service person logging in the client according to a logical sum by adopting a basic matching rule in the matching rules of the same level; according to the priority order, if the account information of the service personnel of the login client is not determined in the current-stage matching rule, jumping to the next-stage matching rule to determine the account information of the service personnel of the login client; and if the account information of the service personnel logging in the client is determined in the current-stage matching rule, the matching flow of the service personnel is finished.
Further, the service person matching module 250 is further configured to determine the account information of the preset service person as the account information of the service person of the login client if the account information of the service person of the login client is not determined by sequentially adopting the multi-stage matching rule.
Further, the service person matching module 250 is further configured to add a tag to the friend account information of the login user in the determined account information of the service person of the login client according to the friend information of the login client.
In this embodiment, a computer device is provided, as shown in fig. 3, including a memory 301, a processor 302, and a computer program stored in the memory 301 and capable of running on the processor 302, where the processor 302 implements a matching method of any of the service personnel mentioned above when executing the computer program.
In particular, the computer device may be a computer terminal, a server or similar computing means.
In the present embodiment, there is provided a computer-readable storage medium storing a computer program for executing the matching method of any one of the service personnel described above.
In particular, computer-readable storage media, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable storage media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
The embodiment of the invention realizes the following technical effects:
according to the invention, different matching strategies are obtained according to the client type, and each matching strategy comprises a multi-stage matching rule; and constructing a decision tree model to predict the demands of the clients, so as to determine the priority order of the multi-level matching rules according to the demands of the clients, and matching service personnel for different types of clients by adopting the multi-level matching rules according to the priority order. The matching rule adjustment is realized according to the client demands, so that service personnel can be matched according to the client demands, the accuracy and the flexibility of the client matching service personnel are improved, the accuracy and the precision of the matching result are improved, and the demands of users are further met.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than what is shown or described, or they may be separately fabricated into individual integrated circuit modules, or a plurality of modules or steps in them may be fabricated into a single integrated circuit module. Thus, embodiments of the invention are not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, and various modifications and variations can be made to the embodiments of the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for matching service personnel, comprising:
acquiring client information of a login client of a service interface;
matching the client information with prestored client type related information, determining the client type of the login client according to a matching result, and acquiring a matching strategy corresponding to the login client according to the client type of the login client, wherein the matching strategy comprises a preset multi-level matching rule, and the client type comprises a new client, an old client and a member client;
predicting the demand category of the login client through a decision tree model according to the client information;
determining the priority order of the multi-level matching rules according to the demand category;
and determining the account information of the service personnel of the login client by adopting the multilevel matching rule in sequence according to the priority order.
2. The method of claim 1, wherein predicting the category of demand of the logged-in customer by a decision tree model based on the customer information, comprises:
extracting feature attributes from the client information, wherein the feature attributes comprise position features, business features and client-level features;
and inputting the characteristic attribute into the decision tree model to obtain the demand category, wherein the decision tree model is obtained by training by taking the characteristic attribute of the historical client information as a sample.
3. The method for matching service personnel according to claim 2, further comprising:
in the process of training the decision tree model, each characteristic attribute of the historical client information is corresponding to a weight value, and training of the decision tree model is performed according to each characteristic attribute of the historical client information and the corresponding weight value.
4. A method of matching service personnel according to claim 3, wherein training the decision tree model based on the characteristic attributes and corresponding weight values of the historical customer information comprises:
extracting client behavior data according to historical client information in a database, wherein the client behavior data comprises characteristic attributes and a selection result of a client on service personnel;
analyzing the client behavior data to obtain the correlation degree of each characteristic attribute of the historical client information and the selected result, and adjusting the weight value corresponding to each characteristic attribute according to the correlation degree;
and training the decision tree model according to the characteristic attributes of the historical client information and the adjusted weight values.
5. A method for matching service personnel according to any one of claims 1 to 4,
according to the client type of the login client, obtaining a matching strategy corresponding to the login client comprises the following steps:
acquiring a plurality of basic matching rules;
when the client type is the old client or the member client, determining at least two historical matching rules for matching account information of service personnel for the login client according to the client information of the login client, selecting a basic matching rule corresponding to the historical matching rule from a plurality of basic matching rules, and combining the selected basic matching rules to form a multi-level matching rule in a matching strategy corresponding to the old client or the member client, wherein each level of matching rule comprises one or more basic matching rules;
when the client type is the new client, combining a plurality of basic matching rules to form a multi-level matching rule in a matching strategy corresponding to the new client, wherein each level of matching rule comprises one or a plurality of basic matching rules;
according to the priority order, determining the account information of the service personnel of the login client by adopting the multi-level matching rule in sequence comprises the following steps:
determining account information of service personnel of the login client by adopting a basic matching rule in the same-level matching rule in a logical sum mode; according to the priority order, if the account information of the service personnel of the login client is not determined in the current-stage matching rule, jumping to the next-stage matching rule to determine the account information of the service personnel of the login client; and if the account information of the service personnel logging in the client is determined in the current-stage matching rule, the matching flow of the service personnel is finished.
6. The method for matching service personnel according to claim 1, further comprising:
if the account information of the service personnel of the login client is not determined by adopting the multi-stage matching rule in sequence, the account information of the preset service personnel is determined to be the account information of the service personnel of the login client.
7. The method for matching service personnel according to claim 6, further comprising:
and adding a mark to the friend account information of the login user in the determined account information of the service personnel of the login user according to the friend information of the login user.
8. A service personnel matching system, comprising:
the client information acquisition module is used for acquiring client information of a login client of the service interface;
the matching strategy acquisition module is used for matching the client information with prestored client type related information, determining the client type of the login client according to a matching result, and acquiring a matching strategy corresponding to the login client according to the client type of the login client, wherein the matching strategy comprises a preset multi-level matching rule, and the client type comprises a new client, an old client and a member client;
the demand category prediction module is used for predicting the demand category of the login client through a decision tree model according to the client information;
the matching sequence generation module is used for determining the priority sequence of the multi-level matching rule according to the requirement category;
and the service personnel matching module is used for determining account information of service personnel logging in the client by sequentially adopting the multi-level matching rule according to the priority order.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements a method for matching service personnel according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program that performs a matching method of one service person according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310400742.2A CN116523218A (en) | 2023-04-11 | 2023-04-11 | Service personnel matching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310400742.2A CN116523218A (en) | 2023-04-11 | 2023-04-11 | Service personnel matching method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116523218A true CN116523218A (en) | 2023-08-01 |
Family
ID=87395147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310400742.2A Pending CN116523218A (en) | 2023-04-11 | 2023-04-11 | Service personnel matching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116523218A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104539814A (en) * | 2014-11-26 | 2015-04-22 | 小米科技有限责任公司 | Customer service call forwarding method and device |
| CN107818344A (en) * | 2017-10-31 | 2018-03-20 | 上海壹账通金融科技有限公司 | The method and system that user behavior is classified and predicted |
| CN109886739A (en) * | 2019-01-31 | 2019-06-14 | 傲宝珠宝文化发展(深圳)有限公司 | Based on jewelry shops shopping guide's management method, system and its storage medium |
| CN110475032A (en) * | 2019-06-28 | 2019-11-19 | 平安科技（深圳）有限公司 | Multi-service interface switching method, device, computer installation and storage medium |
| CN110837587A (en) * | 2019-09-30 | 2020-02-25 | 北京健康之家科技有限公司 | Data matching method and system based on machine learning |
| CN110991903A (en) * | 2019-12-05 | 2020-04-10 | 苏州达家迎信息技术有限公司 | Service personnel allocation method, device, equipment and storage medium |
| CN112465276A (en) * | 2021-01-28 | 2021-03-09 | 湖南惠旅云网络科技有限公司 | Method for automatically generating scenic spot playing recommended route |
| CN113177694A (en) * | 2021-04-06 | 2021-07-27 | 北京健康之家科技有限公司 | Client distribution method, device, storage medium and computer equipment |
| CN114757430A (en) * | 2022-04-27 | 2022-07-15 | 杭州凡声优行科技有限公司 | Service resource allocation method and system |
-
2023
- 2023-04-11 CN CN202310400742.2A patent/CN116523218A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104539814A (en) * | 2014-11-26 | 2015-04-22 | 小米科技有限责任公司 | Customer service call forwarding method and device |
| CN107818344A (en) * | 2017-10-31 | 2018-03-20 | 上海壹账通金融科技有限公司 | The method and system that user behavior is classified and predicted |
| CN109886739A (en) * | 2019-01-31 | 2019-06-14 | 傲宝珠宝文化发展(深圳)有限公司 | Based on jewelry shops shopping guide's management method, system and its storage medium |
| CN110475032A (en) * | 2019-06-28 | 2019-11-19 | 平安科技（深圳）有限公司 | Multi-service interface switching method, device, computer installation and storage medium |
| CN110837587A (en) * | 2019-09-30 | 2020-02-25 | 北京健康之家科技有限公司 | Data matching method and system based on machine learning |
| CN110991903A (en) * | 2019-12-05 | 2020-04-10 | 苏州达家迎信息技术有限公司 | Service personnel allocation method, device, equipment and storage medium |
| CN112465276A (en) * | 2021-01-28 | 2021-03-09 | 湖南惠旅云网络科技有限公司 | Method for automatically generating scenic spot playing recommended route |
| CN113177694A (en) * | 2021-04-06 | 2021-07-27 | 北京健康之家科技有限公司 | Client distribution method, device, storage medium and computer equipment |
| CN114757430A (en) * | 2022-04-27 | 2022-07-15 | 杭州凡声优行科技有限公司 | Service resource allocation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10832181B2 (en) | Management of business process key performance indicators | |
| US7739121B2 (en) | Method and apparatus for providing intelligent and controlled access to supply chain information | |
| US8392335B2 (en) | System and method for modeling and applying a people network representation | |
| US8690666B2 (en) | Systems and methods for data valuation | |
| CN106844372B (en) | Logistics information query method and device | |
| US8639555B1 (en) | Workflow discovery through user action monitoring | |
| US20240127136A1 (en) | Wait Time Prediction | |
| US20200327470A1 (en) | Cognitively-Derived Knowledge Base of Supply Chain Risk Management | |
| Soltanifar et al. | Developing a digital entrepreneurial mindset for data-driven, cloud-enabled, and platform-centric business activities: practical implications and the impact on society | |
| US20180293525A1 (en) | Store service workbench | |
| US20230022064A1 (en) | Contextual modeling using application metadata | |
| JP2022002025A (en) | Information processing device and information processing method | |
| US8019638B1 (en) | Dynamic construction of business analytics | |
| US10902023B2 (en) | Database-management system comprising virtual dynamic representations of taxonomic groups | |
| US20130304547A1 (en) | Investment valuation projections in an on-demand system | |
| US20130253992A1 (en) | Information system with service-oriented architecture using multiple criteria threshold algorithms | |
| CN116523218A (en) | Service personnel matching method and system | |
| WO2009129865A1 (en) | Method and system for collecting and processing of inventory data of retail outlets | |
| CN114881695A (en) | Service data processing method, service system and computer storage medium | |
| US9009073B1 (en) | Product availability check using image processing | |
| US11093897B1 (en) | Enterprise risk management | |
| US7516175B1 (en) | Method of organizing and analyzing field warranty data | |
| CN112486461A (en) | Information processing system based on springboot frame | |
| CN111784091A (en) | Method and apparatus for processing information | |
| CN113378521B (en) | Automatic filling method, device and storage medium for visit record based on working daily report |
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 |