CN112163868A - Data processing method, device, equipment and storage medium - Google Patents
Data processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112163868A CN112163868A CN202011061878.8A CN202011061878A CN112163868A CN 112163868 A CN112163868 A CN 112163868A CN 202011061878 A CN202011061878 A CN 202011061878A CN 112163868 A CN112163868 A CN 112163868A
- Authority
- CN
- China
- Prior art keywords
- client
- customer
- seat
- bipartite graph
- matching
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 54
- 238000012549 training Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 23
- 230000015654 memory Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 abstract description 21
- 239000003795 chemical substances by application Substances 0.000 description 99
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Finance (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 invention discloses a data processing method, a device, equipment and a storage medium, wherein the method comprises the following steps: obtaining at least one client list sent by at least one terminal; and generating a bipartite graph according to at least one client and at least one free agent, and converting the matching problem between the client and the agent into a solving problem of the bipartite graph. And when the solved bipartite graph reaches the target matching condition, obtaining a target matching scheme of at least one client matched with the idle seat, and respectively sending the list of at least one client to the corresponding idle seat terminal according to the target matching scheme. The efficiency of obtaining the target distribution scheme is improved, the timeliness requirement of a scene of distributing the client to the seat is met, and the overall matching degree of the client and the seat is improved, so that after the idle seat contacts the client, the conversion rate of the client is high, the overall performance of the seat is improved, and the overall working efficiency of the seat is improved.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a data processing method, apparatus, device, and storage medium.
Background
In recent years, many enterprises have been using call center systems to communicate with customers to discover potential customers and maintain existing customers for their own needs, and these tasks are performed by call center agents. At present, after the contact information of the customer is acquired, the customer still knows the product in a short time, and the purchase willingness is high. Therefore, if the customer is contacted as soon as possible after the contact information of the customer is acquired, the conversion rate of the customer can be improved. Therefore, after the contact information of the user is obtained, in order to shorten the time, a client list is randomly or empirically allocated to the currently idle agents, and although the allocation formula shortens the time for contacting the client, whether the client list allocated to the agent is a good client group or not is not considered, for each agent, the performance of the agent is poor, namely the working efficiency of the agent is low, and therefore, the overall working efficiency of the agent is low.
Disclosure of Invention
The invention mainly aims to provide a data processing method, a data processing device, data processing equipment and a storage medium, and aims to improve the working efficiency of an agent.
To achieve the above object, the present invention provides a data processing method, including:
acquiring a list of at least one client sent by at least one terminal;
generating a bipartite graph, wherein the at least one customer respectively serves as a first vertex of the bipartite graph, and at least one free agent respectively serves as a second vertex of the bipartite graph;
when the bipartite graph is solved to reach a target matching condition, obtaining a target matching scheme for matching the at least one customer with the free seats, wherein the target matching scheme is used for indicating the free seats to be allocated to each customer in the at least one customer;
and respectively sending the list of the at least one client to the corresponding terminal of the idle seat according to the target matching scheme.
Optionally, when solving the bipartite graph to reach the target matching condition, obtaining a target matching scheme for matching the at least one client with an idle agent, including:
obtaining the matching degree between each client in the at least one client and each free seat in the at least one free seat in the bipartite graph;
and when solving that the bipartite graph reaches a target matching condition according to the matching degree between each client and each idle seat, obtaining a target matching scheme of the at least one client matched with the idle seat.
Optionally, the obtaining the matching degree between each client in at least one client in the bipartite graph and each idle agent in the at least one idle agent includes:
acquiring a first attribute characteristic of each client and a second attribute characteristic of each free seat;
and inputting the first attribute characteristic of each client and the second attribute characteristic of each idle seat into a preset matching model to obtain the matching degree of each client and each idle seat output by the preset matching model.
Optionally, before the inputting the first attribute feature of each customer and the second attribute feature of each idle agent into a preset matching model and obtaining the matching degree between each customer and each idle agent output by the preset matching model, the method further includes:
acquiring a training sample set, wherein the training sample set comprises a plurality of sample information, the sample information comprises a first attribute feature of a sample client, a second attribute feature of a sample agent contacting the sample client and a label, and the label is used for indicating whether the expected result is achieved after the sample agent contacts the sample client;
and training an initial matching model according to the training sample set to obtain the preset matching model.
Optionally, the solving the bipartite graph to reach the target matching condition includes:
and solving the bipartite graph by adopting a Hungarian algorithm to reach a target matching condition.
Optionally, the target matching condition is that the bipartite graph reaches maximum matching, and the solving of the bipartite graph by using the hungarian algorithm reaches the target matching condition includes:
selecting an ith customer from the at least one customer, the ith customer not being the same customer as the first i-1 customers;
according to the matching degree between the ith customer and each idle seat, determining the idle seat with the highest matching degree with the ith customer as the idle seat matched with the ith customer;
if the free seat matched with the ith customer is any one of the free seats matched with the first i-1 customers, adjusting the free seats matched with the first i customers to enable the sum of the matching degrees between the first i customers and the matched free seats to be maximum;
and if the free seat matched with the ith customer is not any free seat in the free seats matched with the first i-1 customers, updating i to be equal to i + 1.
Optionally, in the process of solving the bipartite graph by using the hungarian algorithm, process data of solving the bipartite graph by using the hungarian algorithm is obtained;
and sending the process data to the terminal of the idle seat.
The present invention also provides a data processing apparatus comprising:
the acquisition module is used for acquiring a list of at least one client sent by at least one terminal;
the processing module is used for generating a bipartite graph, wherein the at least one client is respectively used as a first vertex of the bipartite graph, and the at least one free agent is respectively used as a second vertex of the bipartite graph; the bipartite graph matching method is further used for obtaining a target matching scheme of the at least one customer and the free seats when solving that the bipartite graph reaches a target matching condition, wherein the target matching scheme is used for indicating the free seats to be allocated to each customer in the at least one customer;
and the distribution module is used for respectively sending the list of the at least one client to the corresponding terminal of the idle seat according to the target matching scheme.
The present invention also provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the data processing method according to any of the embodiments of the first aspect.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the data processing method as provided in any of the embodiments of the first aspect.
The present invention provides a program product comprising a computer program stored in a readable storage medium, from which the computer program can be read by at least one processor of an electronic device, the execution of the computer program by the at least one processor causing the electronic device to carry out the data processing method provided in any one of the first aspect.
In the invention, at least one client list sent by at least one terminal is obtained; and generating a bipartite graph according to at least one customer and at least one free agent, and formalizing a scene of the customer distributed to the agent into the bipartite graph, so that the matching problem between the customer and the agent is converted into a solving problem of the bipartite graph. Therefore, when the solved bipartite graph reaches the target matching condition, a target matching scheme of at least one client matched with the idle seat is obtained, and the list of at least one client is respectively sent to the corresponding idle seat terminal according to the target matching scheme. The efficiency of obtaining the target distribution scheme is improved, the timeliness requirement of a scene of distributing the client to the seat is met, the client is distributed to the idle seat in the overall view, the overall matching degree of the client and the seat can be improved, and therefore after the idle seat contacts the client, the conversion rate of the client is high, the overall performance of the seat is improved, and the overall working efficiency of the seat is improved.
Drawings
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a data processing method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a bipartite graph-based allocation scheme according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating a data processing method according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart illustrating a process for solving a bipartite graph by using the Hungarian algorithm according to an embodiment of the present invention;
FIG. 6 is a flowchart of a method for training a predetermined matching model according to an embodiment of the present invention;
FIG. 7 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present invention. As shown in fig. 1, after a client browses an advertisement delivered by a company and submits client information such as a contact address through a terminal device 101 such as a computer or a tablet, the terminal device 101 submits the client information to a backend server of the company, and the company backend server 102 acquires the client information. Or after the client fills the contact information through the promo sheet, the staff uploads the contact information of the client to the server 102 through the terminal device, so that the server 102 obtains the contact information of the client.
The client browses the advertisement put by the company or fills in the information on the leaflet, which shows that the client further knows the company business and achieves the willingness of trading. In addition, the client further knows the company business within a period of time after the client knows the product, and the willingness to reach the transaction is higher. Therefore, after the contact information of the customer is obtained, if the customer is contacted soon, the customer is contacted ideally when the customer still browses the advertisement on the webpage, and therefore the probability of achieving a transaction with the customer is high. Therefore, there is a high demand for time efficiency when customers touch by means of electrical pinning or the like.
However, in such a scenario with a high demand on the time efficiency, it is necessary to contact the customer as soon as possible after obtaining the contact address of the customer. Therefore, in order to shorten the time for contacting the customer, the server 102 randomly distributes the customer list to the terminal 103 of the currently idle seat after acquiring the contact way of the customer, or randomly distributes the customer list to the currently idle seat according to experience after acquiring the contact way of the customer on the announcement, without considering the matching degree between the customer and the seat, that is, whether the customer is a group of customers who are good at communication at the current seat. Further, the seat does not determine whether the customer who is distributed to the seat is a group of customers who are good at communication, nor does the seat fail to anticipate whether the customer who is distributed later is a group of customers who are good at communication. Therefore, the agent can only contact the client according to the distributed client list, the conversion efficiency of the client is low, the performance of the agent is affected, and the working efficiency of the agent is low.
In order to solve the above problems, the present invention proposes a solution: when distributing the customer list to the agents, it is desirable to distribute each customer to the agent most matched with the customer as much as possible, that is, for each agent, the customer who is distributed to the agent is the customer in the good-minded customer group, so that after the agent contacts the customer in an electric marketing mode, the probability that the customer achieves transaction to company business is high, and accordingly, the working efficiency of each agent is improved, and the working efficiency of the whole agent is also improved. Therefore, when distributing the customer list, the efficiency of the whole seat is considered, that is, the problem of matching the customer and the whole seat is considered, so that the matching degree of the customer and the whole seat is high.
According to the analysis of the matching scene between the client and the seat, the scene can be converted into the matching problem in mathematics, and the matching problem between the client and the seat is solved by adopting a mathematical method. Further, if the customers are used as a set and the seats are used as a set, the two sets are independent point sets, and each customer can only be distributed to one seat at the same time, so that the scene of the customer distributed to the seats can be formed into a bipartite graph, and the matching problem between the customer and the seats is converted into a solving problem of the bipartite graph. Namely, the matching problem of the client and the seat when the overall matching degree of the client and the seat is high is solved, namely the maximum matching of the bipartite graph is solved.
According to the invention, the scene of the customer to the seat is formalized into the bipartite graph, the matching between the customer and the seat when the overall matching degree of the customer and the seat is high is obtained by solving the maximum matching of the bipartite graph, the complexity of solving the matching problem between the customer and the seat is reduced, and the maximum matching or the optimal matching can be obtained by solving the bipartite graph. Therefore, the scene of distributing the customers to the seats is formalized into a bipartite graph, a matching scheme when the matching degree of the customers and the seats is high can be obtained, and the efficiency of the seats is improved on the basis of meeting the timeliness.
After the scene of the customer to the seat is formalized into a bipartite graph, in order to further improve the overall matching degree of the customer and the seat when the customer distributes to the seat, the invention adopts an artificial intelligence method to obtain a preset matching model, and the preset matching model is used for calculating the matching degree between the customer and the seat. Therefore, after the attribute characteristics of the customer and the attribute characteristics of the seat are obtained, the attribute characteristics of the customer and the attribute characteristics of the seat are analyzed through the preset matching model, the matching degree of the customer and the seat can be rapidly and accurately obtained, a distribution scheme which can enable the overall conversion efficiency of the customer to be high is determined, the overall conversion efficiency of the customer is improved, and the overall working efficiency of the seat is improved.
Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The features of the embodiments and examples described below may be combined with each other without conflict between the embodiments.
Fig. 2 is a flowchart illustrating a data processing method according to an embodiment of the present invention. The execution subject of the method in this embodiment may be an electronic device, such as a computer or a server. The method in this embodiment may be implemented by software, hardware, or a combination of software and hardware. As shown in fig. 2, the method may include:
s201, obtaining at least one client list sent by at least one terminal.
In this step, the list source channels of the customers may be, for example: a client browses advertisements put by a company and submits client information such as contact information through a terminal device 101 such as a computer or a tablet, the terminal device submits the client information to a background server of the company, or after the client fills the client information such as the contact information through a leaflet, a worker uploads the client information to the server through the terminal device, so that the server obtains the client information, and a client list is obtained.
In order to meet the requirement on timeliness, the client needs to be contacted as soon as possible after the list of the client is acquired. Therefore, optionally, the list of the clients within the preset time is obtained every preset time, for example, the preset time is 1 hour, the clients submit client information through a terminal or the clients enter the client information by a worker between 8 points and 9 points, and when 9 points are reached, the list of the clients between 8 points and 9 points is obtained; and a client submits client information through a terminal or a worker inputs the client information between the 9 points and the 10 points, and when the 10 points are reached, a list of the client between the 9 points and the 10 points is obtained, and the rest is done to obtain the list of the client.
It should be noted that, if only the list of 1 client is obtained when the list of clients is allocated, and only one agent is currently in an idle state, the data of the client may be directly processed to the agent in the idle state. For this case, the degree of matching between the customer and the agent may not be considered.
When 1 client list is obtained and a plurality of seats are in an idle state currently, the client data needs to be processed to the seat most suitable for contacting with the client; or when M customer lists are obtained and N seats are in an idle state, the total matching degree between the customer and the corresponding seat needs to be considered. Therefore, the number M of the list of clients and the number N of agents currently in an idle state cannot be 1 at the same time. In this embodiment, the number M of the client list and the number N of the agents currently in the idle state are both greater than 1, and M is less than or equal to N.
Optionally, when the number of the obtained clients is greater than the number of the current idle seats, the clients with the former time are selected according to the time when the clients submit the client information or the time when the staff enters the client information, so that the number of the clients is equal to the number of the current idle seats. At the next allocation, the clients that were not allocated last time are pre-considered.
And S202, generating a bipartite graph.
Wherein, at least one client is respectively used as a first vertex of the bipartite graph, and at least one free seat is respectively used as a second vertex of the bipartite graph.
In this step, after the list of the clients and the free seats are obtained, a bipartite graph is formed according to at least one client and at least one free seat. For example, as shown in fig. 3, a list of 4 clients is obtained, and if the number of currently idle agents is 5, each client is used as a first vertex of the bipartite graph, that is, the number of the first vertices of the bipartite graph is 4, and each idle agent is used as a second vertex of the bipartite graph, that is, the number of the second vertices of the bipartite graph is 5. Wherein the line between the customer and the agent is used to indicate that the customer is to be distributed to the agent on the other side of the line.
S203, when the bipartite graph is solved to reach the target matching condition, a target matching scheme of at least one client matched with the free seat is obtained.
The target matching scheme is used for indicating the free seats which are allocated to each client in at least one client.
In this step, the result obtained by solving the bipartite graph is a matching scheme, that is, the matching relationship between the vertex in one set and the vertex in the other set in the bipartite graph. Therefore, the scene of the customer to the seat is formalized into a bipartite graph, and the matching scheme obtained by solving the bipartite graph is the matching scheme between the customer and the seat.
Therefore, when the bipartite graph is solved, for example, by setting the iteration number, or setting a preset condition that the overall matching degree corresponding to the matching scheme obtained by solving the bipartite graph satisfies, when the iteration number during solving satisfies the iteration number requirement, or when the overall matching degree corresponding to the matching scheme satisfies the preset condition, stopping solving the bipartite graph, and obtaining a matching scheme, which is a target matching scheme in which at least one client matches with an idle seat and is used for indicating the idle seat allocated to each client in the at least one client.
The method for solving the bipartite graph can be a maximum flow algorithm, a Hungarian algorithm, a Kuhn-Munkres algorithm and the like. The invention exemplarily shows a specific solving step for solving a bipartite graph by using the Hungarian algorithm, and is specifically shown in FIG. 5.
And S204, respectively sending the list of at least one client to the corresponding terminal of the idle seat according to the target matching scheme.
In this step, the target allocation scheme indicates the free seat to which each of the at least one customer is allocated, and therefore, according to the target allocation scheme, an allocation relationship between each of the at least one customer and the corresponding free seat is established, for example, as shown in fig. 3, a schematic diagram of an allocation relationship obtained according to the target allocation scheme is exemplarily shown in a bipartite diagram.
After determining the free seat allocated to each client in at least one client, sending the list of the client to the corresponding terminal of the free seat, so that the free seat can obtain the clients needing to be contacted in an electric marketing mode according to the terminal equipment of the free seat.
In the data processing method provided by this embodiment, a list of at least one client sent by at least one terminal is obtained; and generating a bipartite graph according to at least one customer and at least one free agent, and formalizing a scene of the customer distributed to the agent into the bipartite graph, so that the matching problem between the customer and the agent is converted into a solving problem of the bipartite graph. Therefore, when the solved bipartite graph reaches the target matching condition, a target matching scheme of at least one client matched with the idle seat is obtained, and the list of at least one client is respectively sent to the corresponding idle seat terminal according to the target matching scheme. The efficiency of obtaining the target distribution scheme is improved, the timeliness requirement of a scene of distributing the client to the seat is met, the client is distributed to the idle seat in the overall view, the overall matching degree of the client and the seat can be improved, and therefore after the idle seat contacts the client, the conversion rate of the client is high, the overall performance of the seat is improved, and the overall working efficiency of the seat is improved.
The scenario of customer distribution to agents is formalized as a bipartite graph such that each customer is a first vertex of the bipartite graph and each agent is a second vertex of the bipartite graph, and for the scenario of customer distribution to agents, a line connecting the first vertex and the second vertex is an edge of the bipartite graph indicating the distribution of the customer to the agent at the other end of the edge. In order to improve the working efficiency of the seats, at least one customer can be distributed to the corresponding seat according to the matching degree between the customer and the seat. Therefore, when solving the bipartite graph matching problem, the influence of the weight of each edge on the obtained matching scheme can be considered, wherein the weight of each edge in the bipartite graph is the matching degree between the customer and the seat at the two ends of the edge. A target matching scheme is obtained according to the matching degree of the customer and the agent, and the embodiment shown in fig. 4 is specifically shown in detail.
Fig. 4 is a flowchart of a data processing method according to another embodiment of the present invention. On the basis of the embodiment shown in fig. 2, the method of the embodiment includes:
s401, obtaining at least one client list sent by at least one terminal.
In this step, S201 may be referred to for a specific implementation manner of S401, and details are not described here.
S402, generating a bipartite graph.
In this step, S202 may be referred to for a specific implementation manner of S402, and details are not described here.
S403, obtaining the matching degree between each client in at least one client in the bipartite graph and each free agent in at least one free agent.
In this step, the matching degree is used to indicate the matching degree between the customer and the agent, and from the perspective of the customer, the agent contacting the customer through an electronic marketing method needs to be familiar with the service that the customer needs to know, so that the customer improves the probability of the customer reaching a transaction through the introduction of the agent. From the perspective of an agent, a distributed client is required to be a client group which the agent is good at communicating with, so that when the agent contacts the client in an electric marketing mode, familiar services are introduced to the client, the probability of the client achieving a transaction is improved, and the performance of the client is improved.
For example, for the bipartite graph of the embodiment shown in fig. 3, for each first vertex, the weight of the edge between the first vertex and each second vertex is obtained, that is, the matching degree between each client in the at least one client and each free agent in the at least one free agent is obtained.
Optionally, a specific implementation manner of S403 is as follows:
s4031, the first attribute characteristics of each client and the second attribute characteristics of each free agent are obtained.
In this step, for each client, the attribute characteristics of the client are obtained according to the client information filled by the client and/or the client information stored in the database before (if the client has transacted the business of the company before). Wherein the attribute features include one or more of the following: age, gender, occupation, progress of the currently applied business.
Specifically, the attribute characteristics of the client include different contents for different scenes (different services). For example, for an insurance product, the customer's attribute characteristics may include at least one of: the age, sex, occupation, participation information of the client, physical examination information of the client, source channel of the client, and the like of the client are not listed in this embodiment, and the source channel may be, for example, client information acquired on the internet or client information acquired through a leaflet; for financial products, the customer's attribute characteristics may include at least one of: the age, sex, occupation, credit rating of the customer, financial information of the customer, source channel of the customer, etc.; for loan products, the customer's attribute characteristics may include at least one of: the age, sex, occupation, loan information, credit rating, property information, source channel, etc. of the customer.
For each agent, the agent's attribute characteristics include at least one of: age, sex of the seat, and working ability of the seat. The working capacity of the agent can be obtained according to the working data before each agent, and the working capacity of the agent comprises at least one of the following items: the conversion rate of the agent to the customers of different age groups, the conversion rate to the customers of different professions, the conversion rate to the customers of different sexes, the conversion rate to the customers of different regions, the conversion rate to the customers of different source channels and the like are not listed in the embodiment.
S4032, the first attribute characteristics of each client and the second attribute characteristics of each idle seat are input into a preset matching model, and the matching degree of each client and each idle seat output by the preset matching model is obtained.
In this step, the preset matching model is obtained by training in advance according to historical data, namely the attribute characteristics of the customer served before and the agent serving the customer, and whether the expected result is achieved after the agent contacts the customer, and is used for calculating the matching degree between the customer and the agent according to the attribute characteristics of the customer and the attribute characteristics of the idle agent. One way of obtaining the predetermined matching model can refer to fig. 6, which is not described herein again.
And inputting the attribute characteristics of the client and the attribute characteristics of the idle seat into a preset matching model, and calculating to obtain the matching degree between the client and the seat by the preset matching model according to the attribute characteristics of the client and the second attribute characteristics of the seat. For each customer, the matching degree of the customer and each agent is obtained, for example, for 4 customers and 5 agents shown in fig. 3, 20 matching degrees may be obtained.
S404, when the bipartite graph is solved according to the matching degree between each client and each idle seat to reach the target matching condition, a target matching scheme of at least one client matched with the idle seat is obtained.
In this step, after the matching degree between each customer and each idle seat is obtained in the above manner, that is, after the weight of each edge in the bipartite graph shown in fig. 3 is obtained, the bipartite graph is solved according to the weight of each edge, so as to obtain the target matching scheme.
Optionally, in the target matching scheme, an edge with a higher weight may be included as much as possible, that is, the client is distributed to an idle agent with a high matching degree with the client as much as possible.
S405, according to the target matching scheme, the list of at least one client is respectively sent to the corresponding terminal of the idle seat.
In this step, S204 may be referred to as S405, and details are not described herein.
The data processing scheme shown in this embodiment is based on the embodiment shown in fig. 2, and is a target matching scheme obtained on the basis of considering the matching degree between the client and the idle seat, so that when the list of at least one client is respectively sent to the corresponding idle seat according to the matching scheme, after the idle seat contacts the client in an electric marketing manner, the conversion rate of the client is increased for each client, thereby increasing the overall conversion rate of the client, and accordingly, the overall working efficiency of the seat is increased.
Fig. 5 is a flowchart for solving a bipartite graph by using the hungarian algorithm according to an embodiment of the present invention. As shown in fig. 5, the method of the present embodiment includes:
the present embodiment takes the step of solving the bipartite graph by the hungarian algorithm when the target matching condition is the bipartite graph and the maximum matching is achieved as an example. That is, the target allocation scheme corresponding to the maximum matching of the bipartite graph is the allocation scheme with the highest average total matching degree among all the allocation schemes, and the number of all the allocation schemes between the M clients and the N agentsComprises the following steps:
s501, selecting the ith client from at least one client.
Wherein the ith customer is not the same customer as the first i-1 customers.
S502, according to the matching degree between the ith client and each idle seat, determining the idle seat with the highest matching degree with the ith client as the idle seat matched with the ith client.
For S501 and S502, when the binary graph is solved by the Hungarian algorithm, the Hungarian algorithm is initialized, namely any client is selected from at least one client and is marked as a first client. Since each client of the at least one client can distribute to each free seat in the at least one free seat, for the first client, according to the matching degree of the first client and each free seat, the free seat with the highest matching degree with the first client is selected, and the distribution relation between the first client and the free seat is determined.
And selecting any client from at least one client except the first client, marking as a second client, and selecting the idle seat with the highest matching degree with the second client according to the matching degree of the second client and each idle seat.
Thus, each time a customer is selected, any customer is selected from the remaining at least one customer, such that each selected customer is not the same customer as the previously selected customer. And recording the client obtained for the ith time as the ith client. Wherein the ith customer is not the same customer as the first i-1 customers.
And after the ith customer is obtained, selecting the idle seat with the highest matching degree with the ith customer according to the matching degree of the ith customer and each idle seat.
S503, judging whether the free seat matched with the ith client is any one of the free seats matched with the first i-1 clients, and if so, executing S504; if not, go to S505.
In this step, since each client of the at least one client may distribute to each free seat of the at least one free seat, there may be an equal matching degree between one free seat and at least two clients, and for each client of the at least two clients, the matching degree with the free seat is the highest matching degree between the client and all the free seats, which results in an allocation relationship between one free seat and at least two clients, and thus may cause a situation of falling into a dead loop when solving a bipartite graph using the hungarian algorithm, and a target matching scheme may not be obtained.
Therefore, for the ith client, it needs to determine whether the free seat matched with the client is any one of the free seats matched with the first i-1 clients.
S504, adjusting the idle seats matched with the first i clients to enable the sum of the matching degrees between the first i clients and the matched idle seats to be maximum.
In this step, if the free seat matched with the ith customer is any one of the free seats matched with the first i-1 customers, the distributed free seats of the first i customers are adjusted, so that the sum of the matching degrees between the first i customers and the matched free seats is the maximum.
When the free seats matched with the first i clients are adjusted, only the matched free seats of some of the first i clients may be adjusted according to actual conditions, and the matched free seats of each of the first i clients may also be adjusted.
For example, taking i ═ 2 as an example, the free seat with the highest matching degree with the first customer and the free seat with the highest matching degree with the second customer are the same free seat, the matching degree is 0.9, the highest matching degree of the matching degree between the first customer and the free seat is 0.7, and the highest matching degree of the matching degree between the second customer and the free seat is 0.5. At this time, the spatial seat of the first customer is adjusted, the first customer is allocated to the free seat with the matching degree of 0.7 with the first customer, so that the total matching degree of the first customer and the second customer is 0.7+0.9 to 1.6, and if the second customer is allocated to the free seat with the matching degree of 0.5 with the second customer, the total matching degree of the first customer and the second customer is 0.9+0.5 to 1.4.
And S505, updating i to be equal to i +1, and returning to S501.
In this step, if the free seat matched with the ith customer is not any free seat in the free seats matched with the first i-1 customers, it is indicated that the free seat with the highest matching degree with the ith customer is not currently allocated with a customer, so that the ith customer is allocated to the free seat with the highest matching degree with the ith customer, and the sum of the matching degrees between the first i customers and the matched free seat is the largest.
Then, returning to S501, an i +1 th customer is selected from at least one customer.
Optionally, in the process of solving the bipartite graph by using the hungarian algorithm, process data of solving the bipartite graph by using the hungarian algorithm can be obtained; and sends the process data to the terminal of the idle seat. Thus, when the idle agent puts a question on the assignment scheme, the assignment scheme is determined according to the process data if the target assignment scheme is the maximum match.
It should be noted that fig. 5 merely illustrates an example of a possible implementation of solving the bipartite graph in the hungarian algorithm, and is not intended to limit the present invention.
Fig. 6 is a flowchart of a preset matching model training method according to an embodiment of the present invention. As shown in fig. 6, the preset matching model training method of the present embodiment includes:
s601, obtaining a training sample set.
The training sample set comprises a plurality of sample information, the sample information comprises a first attribute feature of a sample client, a second attribute feature of a sample agent contacting the sample client and a label, and the label is used for indicating whether the expected result is achieved after the sample agent contacts the sample client.
In this step, the sample client stored in the history data and the sample agent that contacted the sample client are obtained.
For each sample client, the first attribute characteristics of the sample client are obtained, wherein the attribute characteristics of the sample client correspond to the attribute characteristics of the client to be contacted in S4031. For example, for an insurance product, the sample customer's attribute characteristics may include at least one of: the age, sex, occupation, participation information, physical examination information, source channel and the like of the client.
And for each sample agent, acquiring the attribute characteristics of the sample agent, wherein the attribute characteristics of the sample agent correspond to the attribute characteristics of the agent shown in S4031. The attribute features of the sample agents include at least one of: age, gender, and working capacity of the sample agent. The working capacity of the sample seat can be obtained according to the working data before each sample seat, and the working capacity of the sample seat comprises at least one of the following items: the conversion rate of the sample seat to customers of different age groups, the conversion rate to customers of different professions, the conversion rate to customers of different sexes, the conversion rate to customers of different regions, the conversion rate to customers of different source channels and the like.
The expected result corresponds to the purpose of the sample agent contacting the sample customer, for example, when the sample agent sells insurance to the customer by way of e-pinning, the sample customer is expected to purchase insurance, if the sample customer purchases insurance, the sample agent contacts the sample customer to reach the expected result, and the value of the corresponding label may be 1, for example; otherwise, the expected result is not achieved after the sample agent contacts the sample client, and the value of the corresponding label may be 0, for example.
The determination of whether the expected result is achieved after the sample agent contacts the sample client may be, for example: after the sample seat contacts the sample client, whether the sample client achieves an expected result within a preset time length or not is judged; or after the sample agent contacts the sample client and the attribute characteristics of the sample client are obtained, whether the sample client achieves the expected result or not is judged.
The first attribute characteristic of each sample client, the second attribute characteristic of the sample seat contacting the sample client and the label correspond to sample information, and a plurality of groups of sample information and behavior training sample sets are obtained through historical data.
And S602, training the initial matching model according to the training sample set to obtain a preset matching model.
In this step, the matching model is represented as f (X, Y), where X represents the customer X, Y represents the attribute information of the seat Y, and the output value of f (X, Y) is the matching degree of the customer X and the seat Y. Wherein, one form of f (X, Y) is shown in formula one:
f(X，Y)＝W1·X+W2y ═ Z formula one
Wherein, X, Y, W1、W2Expressed in vectors, each element in X corresponds to each of the customer attribute features, each element in Y corresponds to each of the agent attribute features, W1Each element in (a) represents a weight of the impact of each of the customer attribute features on the expected result, W2Each element in (a) represents a weight of the impact of each of the agent attribute features on the expected result. Z represents a label, i.e., whether the agent achieves the desired result after contacting the sample customer.
At the beginning, W is initialized1、W2Inputting a training sample set into an initial matching model, and f (X, Y) according to initial W for the attribute characteristics of each sample client and the attribute characteristics of the corresponding sample seat1、W2And outputting the matching degree of the sample client and the corresponding sample seat, and when the matching degree is greater than the preset matching degree, considering that the expected result is achieved after the sample seat contacts the sample client, otherwise, not achieving the result.
Comparing the output result of f (X, Y) with the label Z in the sample information, and optimizing f (X, Y) according to the loss value, specifically, W of f (X, Y)1、W2And performing updating optimization. And then inputting the training sample set into the optimized matching model again, and repeating the optimization process until the training end condition is met to obtain the preset matching model.
The preset matching model training method provided by the embodiment is obtained through training of the first attribute feature of the sample client, the second attribute feature of the sample seat contacting the sample client and the label. Therefore, by presetting the matching model, each attribute feature of the client and the influence of each attribute feature of the idle agent on the matching degree between the client and the idle agent can be determined. Therefore, the matching degree between each client and each free seat can be accurately and efficiently obtained through the preset matching model according to the attribute characteristics of each client and the attribute characteristics of each free seat, so that the free seats corresponding to the lists of the clients are determined, the conversion rate of the clients is improved, and the working efficiency of the seats is improved.
It should be noted that the execution subject of the method in the embodiment of fig. 6 may be the same as the execution subject in the embodiment of fig. 2, or may be a different execution subject, and the present invention is not limited to this.
Fig. 7 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention. As shown in fig. 7, the data processing apparatus may include:
an obtaining module 71, configured to obtain a list of at least one client sent by at least one terminal;
a processing module 72, configured to generate a bipartite graph, where the at least one customer serves as a first vertex of the bipartite graph, and the at least one free agent serves as a second vertex of the bipartite graph; the bipartite graph matching method is further used for obtaining a target matching scheme of the at least one customer and the free seats when solving that the bipartite graph reaches a target matching condition, wherein the target matching scheme is used for indicating the free seats to be allocated to each customer in the at least one customer;
and the allocating module 73 is configured to send the list of at least one client to the corresponding terminal of the idle agent according to the target matching scheme.
The data processing apparatus provided in this embodiment may be configured to execute the technical solution provided in any of the foregoing method embodiments, and the implementation principle and technical effect of the data processing apparatus are similar, and the matching problem between the customer and the seat is converted into a solving problem of a bipartite graph, so that the efficiency of obtaining a target distribution scheme is improved, the timeliness requirement of a scene in which the customer is distributed to the seat is met, and the overall matching degree between the customer and the seat is improved, so that after the idle seat contacts the customer, the conversion rate of the customer is high, and the overall performance of the seat is improved, that is, the overall working efficiency of the seat is improved.
On the basis of the foregoing embodiment, in a possible implementation manner, the processing module 72 is specifically configured to:
obtaining the matching degree between each client in the at least one client and each free seat in the at least one free seat in the bipartite graph;
and when solving that the bipartite graph reaches a target matching condition according to the matching degree between each client and each idle seat, obtaining a target matching scheme of the at least one client matched with the idle seat.
In a possible implementation, the processing module 72 is specifically configured to:
acquiring a first attribute characteristic of each client and a second attribute characteristic of each free seat;
and inputting the first attribute characteristic of each client and the second attribute characteristic of each idle seat into a preset matching model to obtain the matching degree of each client and each idle seat output by the preset matching model.
In one possible implementation, the data processing apparatus further includes: a training module 74;
before the processing module 72 inputs the first attribute feature of each customer and the second attribute feature of each idle agent into a preset matching model and obtains the matching degree between each customer and each idle agent output by the preset matching model, the obtaining module 71 is further configured to:
acquiring a training sample set, wherein the training sample set comprises a plurality of sample information, the sample information comprises a first attribute feature of a sample client, a second attribute feature of a sample agent contacting the sample client and a label, and the label is used for indicating whether the expected result is achieved after the sample agent contacts the sample client;
and the training module 74 is configured to train the initial matching model according to the training sample set to obtain a preset matching model.
In a possible implementation, the processing module 72 is specifically configured to:
and solving the bipartite graph by adopting a Hungarian algorithm to reach a target matching condition.
In a possible implementation manner, the target matching condition is that the bipartite graph reaches the maximum matching, and the processing module 72 is specifically configured to:
selecting an ith customer from the at least one customer, the ith customer not being the same customer as the first i-1 customers;
according to the matching degree between the ith customer and each idle seat, determining the idle seat with the highest matching degree with the ith customer as the idle seat matched with the ith customer;
if the free seat matched with the ith customer is any one of the free seats matched with the first i-1 customers, adjusting the free seats matched with the first i customers to enable the sum of the matching degrees between the first i customers and the matched free seats to be maximum;
and if the free seat matched with the ith customer is not any free seat in the free seats matched with the first i-1 customers, updating i to be equal to i + 1.
In one possible implementation, the processing module 72 is further configured to:
in the process of solving the bipartite graph by adopting the Hungarian algorithm, acquiring process data of the Hungarian algorithm for solving the bipartite graph;
the allocating module 73 is further configured to send the process data to the terminal of the idle agent.
The data processing apparatus provided in any of the foregoing embodiments is configured to execute the technical solution of any of the foregoing method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 8, the electronic device includes: a memory 82, a processor 81 and a computer program stored on the memory 82 and executable on the processor 81, which computer program when executed by the processor 81 implements the steps of the data processing method provided by any of the method embodiments described above.
Optionally, the electronic device may further comprise a display 83.
The above devices of the electronic apparatus may be connected to each other by a bus.
The memory 82 may be a separate storage unit or a storage unit integrated into the processor 81. The number of the processors 81 is one or more.
In the above-mentioned implementation in the electronic device, the memory and the processor are directly or indirectly electrically connected to each other to realize data transmission or interaction, that is, the memory and the processor may be connected through an interface or may be integrated together. For example, the components may be electrically connected to each other via one or more communication buses or signal lines, such as a bus. The Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory is used for storing programs, and the processor executes the programs after receiving the execution instructions. Further, the software programs and modules within the aforementioned memories may also include an operating system, which may include various software components and/or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components.
The processor may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, and may include a Central Processing Unit (CPU), an image processor, and the like, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention.
The invention further provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the data processing method as provided in any one of the method embodiments described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A data processing method, comprising:
acquiring a list of at least one client sent by at least one terminal;
generating a bipartite graph, wherein the at least one customer respectively serves as a first vertex of the bipartite graph, and at least one free agent respectively serves as a second vertex of the bipartite graph;
when the bipartite graph is solved to reach a target matching condition, obtaining a target matching scheme for matching the at least one customer with the free seats, wherein the target matching scheme is used for indicating the free seats to be allocated to each customer in the at least one customer;
and respectively sending the list of the at least one client to the corresponding terminal of the idle seat according to the target matching scheme.
2. The method of claim 1, wherein obtaining the target matching scheme for the at least one customer to match with an available agent when solving the bipartite graph to reach a target matching condition comprises:
obtaining the matching degree between each client in the at least one client and each free seat in the at least one free seat in the bipartite graph;
and when solving that the bipartite graph reaches a target matching condition according to the matching degree between each client and each idle seat, obtaining a target matching scheme of the at least one client matched with the idle seat.
3. The method of claim 2, wherein the obtaining the matching degree between each client in the at least one client in the bipartite graph and each idle agent in the at least one idle agent comprises:
acquiring a first attribute characteristic of each client and a second attribute characteristic of each free seat;
and inputting the first attribute characteristic of each client and the second attribute characteristic of each idle seat into a preset matching model to obtain the matching degree of each client and each idle seat output by the preset matching model.
4. The method according to claim 3, wherein before inputting the first attribute feature of each customer and the second attribute feature of each idle agent into a preset matching model and obtaining the matching degree of each customer and each idle agent output by the preset matching model, the method further comprises:
acquiring a training sample set, wherein the training sample set comprises a plurality of sample information, the sample information comprises a first attribute feature of a sample client, a second attribute feature of a sample agent contacting the sample client and a label, and the label is used for indicating whether the expected result is achieved after the sample agent contacts the sample client;
and training an initial matching model according to the training sample set to obtain the preset matching model.
5. The method according to any one of claims 1-4, wherein said solving said bipartite graph to reach a target matching condition comprises:
and solving the bipartite graph by adopting a Hungarian algorithm to reach a target matching condition.
6. The method as recited in claim 5, wherein the target matching condition is that the bipartite graph reaches a maximum matching, and the solving the bipartite graph using the Hungarian algorithm reaches the target matching condition comprises:
selecting an ith customer from the at least one customer, the ith customer not being the same customer as the first i-1 customers;
according to the matching degree between the ith customer and each idle seat, determining the idle seat with the highest matching degree with the ith customer as the idle seat matched with the ith customer;
if the free seat matched with the ith customer is any one of the free seats matched with the first i-1 customers, adjusting the free seats matched with the first i customers to enable the sum of the matching degrees between the first i customers and the matched free seats to be maximum;
and if the free seat matched with the ith customer is not any free seat in the free seats matched with the first i-1 customers, updating i to be equal to i + 1.
7. The method of claim 6, further comprising:
in the process of solving the bipartite graph by adopting the Hungarian algorithm, acquiring process data of the Hungarian algorithm for solving the bipartite graph;
and sending the process data to the terminal of the idle seat.
8. A data processing apparatus, comprising:
the acquisition module is used for acquiring a list of at least one client sent by at least one terminal;
the processing module is used for generating a bipartite graph, wherein the at least one client is respectively used as a first vertex of the bipartite graph, and the at least one free agent is respectively used as a second vertex of the bipartite graph; the bipartite graph matching method is further used for obtaining a target matching scheme of the at least one customer and the free seats when solving that the bipartite graph reaches a target matching condition, wherein the target matching scheme is used for indicating the free seats to be allocated to each customer in the at least one customer;
and the distribution module is used for respectively sending the list of the at least one client to the corresponding terminal of the idle seat according to the target matching scheme.
9. An electronic device, characterized in that the electronic device comprises: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when being executed by the processor, carries out the steps of the data processing method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the data processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011061878.8A CN112163868A (en) | 2020-09-30 | 2020-09-30 | Data processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011061878.8A CN112163868A (en) | 2020-09-30 | 2020-09-30 | Data processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112163868A true CN112163868A (en) | 2021-01-01 |
Family
ID=73862349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011061878.8A Pending CN112163868A (en) | 2020-09-30 | 2020-09-30 | Data processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112163868A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113256070A (en) * | 2021-04-26 | 2021-08-13 | 北京淇瑀信息科技有限公司 | Supporting line distribution method and device based on electricity-pin conversion rate and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014060709A1 (en) * | 2012-10-18 | 2014-04-24 | Tellmeplus | Method and device for distributing information to a user provided with a communicating mobile terminal with information filtering and learning using bipartite graphs or neural networks |
| WO2017201905A1 (en) * | 2016-05-25 | 2017-11-30 | 百度在线网络技术（北京）有限公司 | Data distribution method and device, and storage medium |
| WO2018036154A1 (en) * | 2016-08-23 | 2018-03-01 | 平安科技（深圳）有限公司 | List allocation method, device, apparatus, and computer readable storage medium |
| CN109284881A (en) * | 2017-07-20 | 2019-01-29 | 北京嘀嘀无限科技发展有限公司 | Order allocation method, device, computer readable storage medium and electronic equipment |
| CN110447050A (en) * | 2017-12-04 | 2019-11-12 | 北京嘀嘀无限科技发展有限公司 | System and method for distributing order in online on-demand service |
| CN111062757A (en) * | 2019-12-17 | 2020-04-24 | 山大地纬软件股份有限公司 | Information recommendation method and system based on multi-path optimization matching |
| CN111680213A (en) * | 2019-03-11 | 2020-09-18 | 阿里巴巴集团控股有限公司 | Information recommendation method, data processing method and device |
-
2020
- 2020-09-30 CN CN202011061878.8A patent/CN112163868A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014060709A1 (en) * | 2012-10-18 | 2014-04-24 | Tellmeplus | Method and device for distributing information to a user provided with a communicating mobile terminal with information filtering and learning using bipartite graphs or neural networks |
| WO2017201905A1 (en) * | 2016-05-25 | 2017-11-30 | 百度在线网络技术（北京）有限公司 | Data distribution method and device, and storage medium |
| WO2018036154A1 (en) * | 2016-08-23 | 2018-03-01 | 平安科技（深圳）有限公司 | List allocation method, device, apparatus, and computer readable storage medium |
| CN109284881A (en) * | 2017-07-20 | 2019-01-29 | 北京嘀嘀无限科技发展有限公司 | Order allocation method, device, computer readable storage medium and electronic equipment |
| CN110447050A (en) * | 2017-12-04 | 2019-11-12 | 北京嘀嘀无限科技发展有限公司 | System and method for distributing order in online on-demand service |
| CN111680213A (en) * | 2019-03-11 | 2020-09-18 | 阿里巴巴集团控股有限公司 | Information recommendation method, data processing method and device |
| CN111062757A (en) * | 2019-12-17 | 2020-04-24 | 山大地纬软件股份有限公司 | Information recommendation method and system based on multi-path optimization matching |
Non-Patent Citations (1)
| Title |
|---|
| 丁雄;: "人力资源优化配置技术及其算法实现", 湖南工业大学学报, no. 03, pages 67 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113256070A (en) * | 2021-04-26 | 2021-08-13 | 北京淇瑀信息科技有限公司 | Supporting line distribution method and device based on electricity-pin conversion rate and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019242331A1 (en) | User behavior prediction method and apparatus, and behavior prediction model training method and apparatus | |
| CN108280670B (en) | Seed crowd diffusion method and device and information delivery system | |
| CN105376111B (en) | Resource allocation methods and device | |
| CN110765169B (en) | Information recommendation method, device, computer equipment and storage medium | |
| US20130117062A1 (en) | Online resource allocation algorithms | |
| CN112163887A (en) | Electric sales system, electric sales list management method, device, equipment and storage medium | |
| US11748452B2 (en) | Method for data processing by performing different non-linear combination processing | |
| US20210256445A1 (en) | System and method for matching resource capacity with client resource needs | |
| CN111210255B (en) | Advertisement pushing method and device and electronic equipment | |
| CN115470512A (en) | Method, device and system for carrying out multi-party algorithm negotiation aiming at privacy calculation | |
| CN112749323B (en) | Method and device for constructing user portrait | |
| CN108874805B (en) | Data processing method and device | |
| CN112163868A (en) | Data processing method, device, equipment and storage medium | |
| CN112529400B (en) | Data processing method, device, terminal and readable storage medium | |
| CN112163154A (en) | Data processing method, device, equipment and storage medium | |
| CN116797235A (en) | Method and device for processing consumption information, storage medium and computer equipment | |
| CN110751501A (en) | Commodity shopping guide method, device, equipment and storage medium in new retail mode | |
| CN110838019A (en) | Method and device for determining trial supply distribution crowd | |
| CN113112305A (en) | Information delivery method, device and equipment | |
| CN112132597A (en) | Data processing method, device, equipment and storage medium | |
| CN110738554A (en) | Task processing method and device, electronic equipment and computer readable storage medium | |
| CN111897910A (en) | Information pushing method and device | |
| CN111782926A (en) | Method and device for data interaction, storage medium and electronic equipment | |
| CN113762683B (en) | Store site selection method and device | |
| JP7337887B2 (en) | Information processing device, information processing method and information processing program |
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 |