Data processing method and device, equipment, storage medium and program product

Abstract

The invention discloses a data processing method and device, equipment, a storage medium and a program product, and the method comprises the steps: determining a first seat identifier corresponding to an intention based on the intention of a first object; determining a seat workload corresponding to the first seat identifier; according to the seat workload and the business data, determining the matching probability of the first seat identifier and the first object, and determining the seat identifier of which the matching probability meets a preset rule as a second seat identifier matched with the first object; and performing communication connection between the terminal corresponding to the second seat identifier and the terminal of the first object. The matching probability of different first seat identifiers and the first object is determined according to the seat workload, and then the second seat identifier meeting the preset rule is allocated to the first object, so that the load conditions of different seats are considered, the load balance of seat resources is realized, and the utilization rate of the seat resources is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method, apparatus, device, storage medium, and program product. Background Art

[0002] An online customer service system is an internet-based software system that provides real-time communication between businesses and users. Its purpose is to promptly respond to user inquiries, feedback, and other requests, interacting with users through human or intelligent customer service. In practice, when a user requests a call to a human agent, an agent is assigned before a communication connection is established. Successfully assigned users receive human service, while unsuccessful users are placed in a queue. Summary of the Invention

[0003] The embodiments of the present application provide a data processing method, apparatus, device, storage medium, and program product to achieve real-time adjustment of user-matched seats based on agent workload, thereby achieving agent load balancing and improving agent resource utilization.

[0004] In a first aspect, an embodiment of the present application provides a data processing method, the method comprising: Based on the intention of the first object and a preset seat information database, determining a first seat identifier corresponding to the intention in the seat information database; determining, based on the service data corresponding to the first agent identifier, an agent workload corresponding to the first agent identifier; determining, based on the agent workload and the business data, a matching probability between the first agent identifier and the first object, and determining the first agent identifier whose matching probability satisfies a preset rule as a second agent identifier matching the first object; Establish a communication connection between the terminal corresponding to the second agent identifier and the terminal of the first object.

[0005] In a second aspect, an embodiment of the present application provides a data processing device, including: a processing module, configured to determine, based on the intention of the first object and a preset seat information database, a first seat identifier corresponding to the intention in the seat information database; and for determining, based on the business data corresponding to the first agent identifier, an agent workload corresponding to the first agent identifier; and determining a matching probability between the first agent identifier and the first object based on the agent workload and the business data, and determining the first agent identifier whose matching probability satisfies a preset rule as a second agent identifier matching the first object; The communication module is configured to establish a communication connection between the terminal corresponding to the second agent identifier and the terminal of the first object.

[0006] In a third aspect, an embodiment of the present application provides a data processing device, the device comprising: A memory, a processor, and a data processing program stored in the memory and executable on the processor, wherein the data processing program is configured to implement part or all of the steps described in any method in the first aspect.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a data processing program is stored. When the data processing program is executed by a processor, some or all of the steps described in any method in the first aspect are implemented.

[0008] In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0009] By implementing the embodiments of the present application, first, based on the intention of the first object and the preset seat information database, the first seat identifier corresponding to the intention is determined in the seat information database; then, based on the business data corresponding to the first seat identifier, the seat workload corresponding to the first seat identifier is determined; then, based on the seat workload and business data, the matching probability between the first seat identifier and the first object is determined, and the first seat identifier whose matching probability meets the preset rules is determined as the second seat identifier that matches the first object; finally, the terminal corresponding to the second seat identifier is communicatively connected with the terminal of the first object.

[0010] By matching the agent ID based on the first object intent, calculating the agent workload and matching probability in combination with business data, and then screening out the second agent ID that meets the preset rules and establishing a communication connection, it is possible to accurately connect agent resources according to user needs, effectively avoid excessive concentration or idleness of resources, achieve load balancing of agent resources, and improve the utilization rate of agent resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0012] Figure 1 This is a schematic diagram of the architecture of a data processing system provided in an embodiment of the present application; Figure 2 This is a flow chart of a data processing method provided by an embodiment of the present application; Figure 3 is a flowchart of a process for determining a first agent identifier corresponding to an intent in an agent information library according to an embodiment of the present application; Figure 4 is a flowchart of a process for determining an agent workload corresponding to a first agent identifier according to an embodiment of the present application; Figure 5 is a flowchart of a process for determining a first agent workload corresponding to a first agent identifier according to an embodiment of the present application; Figure 6 is a flowchart of a process for determining a second agent workload corresponding to a first agent identifier according to an embodiment of the present application; Figure 7 is a structural schematic diagram of a data processing apparatus according to an embodiment of the present application; Figure 8 is a structural schematic diagram of a data processing apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. According to the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor should belong to the scope of protection of the present application.

[0014] The terms "first", "second", and "third" and the like in the specification and claims of the present application and drawings are used to distinguish different objects, rather than to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0015] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor does it necessarily refer to a particular embodiment in an exclusive sense. It is explicitly and implicitly understood by those skilled in the art that embodiments described herein can be combined with each other.

[0016] An online customer service system is an internet-based software system that provides real-time communication between businesses and users. Its purpose is to promptly respond to user inquiries, feedback, and other requests, interacting with users through manual or intelligent customer service.

[0017] In actual applications, when a user requests to be transferred to a human operator at the front end, an agent will be assigned before a connection is established with the agent. Successfully assigned users can access human service, while unsuccessful users enter a queue and wait. Traditional online customer service systems usually group customer service representatives first, then set a maximum number of users that the agents can receive, and randomly assign idle agents to serve users. This agent allocation method results in uneven agent workload and low agent resource utilization.

[0018] In response to the above problems, the embodiments of the present application provide a data processing method, apparatus, device, storage medium and program product. First, based on the intention of the first object and the preset agent information database, the first agent identifier corresponding to the intention in the agent information database is determined; then, based on the business data corresponding to the first agent identifier, the agent workload corresponding to the first agent identifier is determined; then, based on the agent workload and business data, the matching probability between the first agent identifier and the first object is determined, and the first agent identifier whose matching probability meets the preset rules is determined as the second agent identifier that matches the first object; finally, the terminal corresponding to the second agent identifier is communicatively connected with the terminal of the first object.

[0019] By matching the agent ID based on the first object intent, calculating the agent workload and matching probability in combination with business data, and then screening out the second agent ID that meets the preset rules and establishing a communication connection, it is possible to accurately connect agent resources according to user needs, effectively avoid excessive concentration or idleness of resources, achieve load balancing of agent resources, and improve the utilization rate of agent resources.

[0020] The data processing method, apparatus, device, storage medium and program product provided in the embodiments of the present application can be applied to Figure 1 In the data processing system shown, see Figure 1 , Figure 1 This is a schematic diagram of the architecture of a data processing system provided in an embodiment of the present application. Data processing system 100 includes a client 101 and a server 102. Client 101 can communicate with server 102 via a network. Client 101 refers to a device used by a first subject, such as a smartphone or computer. In this solution, the first subject can interact with the system through client 101 and set multiple parameters required to determine a second agent identifier that matches a user among multiple first agent identifiers.

[0021] Server 102 is a remote computer used to process large amounts of computing tasks and store data. In this solution, server 102 first determines a first agent identifier in the agent information database that corresponds to the first agent's intent based on the first subject's intent and a preset agent information database. It then determines the agent workload corresponding to the first agent identifier based on the business data corresponding to the first agent identifier. It then determines the matching probability between the first agent identifier and the first subject based on the agent workload and business data, and identifies the first agent identifier whose matching probability meets a preset rule as the second agent identifier that matches the first subject. Finally, it establishes a communication connection between the terminal corresponding to the second agent identifier and the terminal of the first subject.

[0022] Based on this, the present application provides a data processing method, apparatus, device, storage medium and program product, which are described in detail below with reference to the accompanying drawings.

[0023] See also Figure 2 , Figure 2 This is a flow chart of a data processing method provided in an embodiment of the present application. Figure 2 As shown, the method includes the following steps: S201: Based on an intention of a first object and a preset agent information database, determine a first agent identifier corresponding to the intention in the agent information database.

[0024] Among them, the execution subject of this method can be Figure 1 Data processing system 100 is shown with server 102 .

[0025] The first object refers to the subject that initiates the service request, that is, the user who has consulting needs, hereinafter referred to as the first object is the user.

[0026] Among them, the seat information database refers to a database or information collection that is pre-built and stores seat-related structured data. The seat information database includes but is not limited to the seat identification corresponding to each seat and the seat level label of each seat.

[0027] When determining user intent, if at least one intent is detected based on the user conversation, the user's primary intent must be determined from multiple intents. The content expressed by the user during the conversation may contain one or more different intents. For example, in a customer service conversation on an e-commerce platform, a user may want to inquire about how to use a product and also about after-sales service, resulting in two different intents.

[0028] When analyzing the user's conversation content reveals a lack of clear purpose or need, the user is deemed to have no intent. For example, in a customer service scenario, if a user says something unrelated to the business or service, such as "What a nice day today," or "I just saw a movie," and it's impossible to identify common intents such as "Inquiring about product information," "Requesting after-sales service," or "Conducting business transactions," the user is deemed to have no intent.

[0029] Among these detected intentions, the most important intention for the user will be further determined and determined to be the user's main intention.

[0030] In one possible implementation, if it is detected based on the user conversation that the user has at least one intention, then determining the user's main intention includes the following steps: obtaining at least one intention of the user based on the user conversation detection; detecting the number of times that sentences in the user conversation hit different intentions of the user, and sorting the different intentions of the user from large to small according to the number of hits; and determining the intention with the largest number of hits among the different intentions of the user as the user's main intention.

[0031] Natural language processing (NLP) technologies, such as word segmentation, part-of-speech tagging, named entity recognition, and semantic understanding, are typically used to analyze user input. These technologies identify the user's intended purpose or need, or intent, from the conversation text. A user conversation can include one or more intents. Alternatively, if analyzing the conversation content reveals a clear purpose or need, the user is deemed to have no intent. For example, in a customer service scenario, if a user says something unrelated to the business or service, such as "The weather is great today" or "I just watched a movie," and common intents such as "Inquire about product information," "Apply for after-sales service," or "Conduct business transactions" are unavailable, the user is deemed to have no intent.

[0032] Once the system has identified the user's intents, it further analyzes each statement in the conversation. For each statement, it determines whether it is related to a previously identified intent. If so, the statement is considered to have matched that intent, and the number of hits for that intent is accumulated. After counting all statements, the number of hits for each intent is calculated, and the intents are then sorted from highest to lowest by hit count.

[0033] After the hit counts and sorting of the intents are completed, the intent with the most hits is selected from these different intents and determined as the user's main intent.

[0034] For example, a user says, "My phone often crashes and charges very slowly. Can you help me fix this problem?" The "phone crashes" intent has the highest number of hits, so "phone crashes" is determined to be the user's main intent.

[0035] Among them, the method of determining the main intention from multiple intentions can also be based on the intention importance weight, based on the semantic vector space model, etc. Specifically, the step of determining the main intention based on the intention importance weight includes: assigning pre-set importance weights to different types of intentions. When multiple intentions are detected, the weights of each intention are added together, and the intention with the highest total weight is determined to be the main intention. For example, if the user expresses the intention to query product information and place an order to purchase at the same time, since the weight configured for the "place an order to purchase" intention is higher, then "place an order to purchase" is the main intention.

[0036] Specifically, the steps for determining the main intent based on the semantic vector space model include mapping the user conversation and each intent into the semantic vector space and calculating the similarity, such as cosine similarity, between the user conversation vector and each intent vector. The intent with the highest similarity is considered the main intent. For example, if a user says "I want a powerful and stylish phone," the semantic vector space model will find that this conversation has the highest similarity to the intent vector "buy a phone," thus determining it as the main intent.

[0037] It can be seen that in this example, by detecting the user's conversation intentions, counting the number of hits for different intentions and sorting them, the intention with the most hits is determined as the main intention, which can quickly determine the user's core needs and improve the response efficiency of user services.

[0038] In one possible implementation, see Figure 3 , Figure 3 This is a flow chart of determining the first seat identifier corresponding to the intention in the seat information database provided by the embodiment of the present application, such as Figure 3 As shown, the seat information database includes a seat identifier and a seat level label corresponding to the seat identifier. Based on the intention of the first object and the preset seat information database, determining the first seat identifier corresponding to the intention in the seat information database includes the following steps: S301, calculating the semantic similarity between the intention and the agent level label in the agent information database; Among them, the agent information database includes the agent ID and the agent level label corresponding to the agent ID. The agent ID is a symbol or code used to uniquely refer to a certain agent, which is similar to the agent's identity ID. The agent ID can be used to locate the specific agent or service unit; the agent level label is a classification mark of the agent's service capabilities, professional fields or skill levels. For example, the agent level label can be "XX consulting junior agent", "XX technical senior agent", etc., which is used to describe the type of business that the agent is good at handling or the level of ability he or she possesses.

[0039] Among them, the specific intention raised by the first object (i.e. the content of the user's needs or problems, for example, "consult XX processing procedures", "complaint issues", etc.) is compared and analyzed with the semantic content expressed by each agent level label in the agent information database, and the similarity between the two is calculated through natural language processing technology (such as word vector models, semantic matching algorithms, etc.).

[0040] Semantic similarity is a numerical indicator that measures the degree of closeness between two text fragments in terms of meaning. A higher value indicates a closer semantic connection between the two. Semantic similarity can be calculated by converting intent and agent level labels into word frequency vectors using cosine similarity and then calculating the angle. Alternatively, Jaccard similarity can be used to measure the matching degree by the ratio of word set intersection and union. Pre-trained language models such as BERT can also be used to generate semantic vectors and then calculate the cosine value. Similarly, similarity can be calculated using entity association and relationship reasoning in knowledge graphs. This method is particularly suitable for professional fields such as finance, and no restrictions are placed on the method of calculating semantic similarity.

[0041] S302: Determine the seat identifier corresponding to the seat level label whose semantic similarity is greater than a similarity threshold as the first seat identifier.

[0042] The similarity threshold can be set or modified by the user directly on the client 101 of the data processing system 100 . The similarity threshold can be 0.9, 0.8 or 0.75, and there is no restriction on the similarity threshold here.

[0043] After calculating the semantic similarity between the intent and all agent-level tags, each result is compared with a pre-set similarity threshold (the critical value for determining a match, for example, 0.7). Only when the semantic similarity value of an agent-level tag exceeds this threshold is the agent corresponding to that tag considered capable of handling the intent. At this point, the agent IDs associated with these qualifying tags are extracted as the first agent IDs capable of responding to the user's intent. The agents corresponding to these IDs are then initially screened as suitable service units.

[0044] It can be seen that in this example, by calculating the semantic similarity between the intention of the first object and the agent level label and screening out the agent identification corresponding to the label that meets the threshold, it is possible to accurately match agents with corresponding service capabilities and achieve efficient service allocation based on semantic understanding.

[0045] S202: Determine an agent workload corresponding to the first agent identifier based on business data corresponding to the first agent identifier.

[0046] Among them, business data refers to various types of quantitative information and business records directly related to the agent's work, which is used to reflect the entire process and status of the agent's business handling. Agent workload is a quantitative evaluation indicator of the agent's work pressure and task saturation based on business data, which is used to measure the amount of work tasks and stress level undertaken by the agent within a certain period of time.

[0047] For example, the business data corresponding to a certain seat ID is 5 calls currently being processed (with an average remaining time of 15 minutes per call), 10 calls on hold, and 40 calls handled today (with an average remaining time of 20 minutes per call), of which 30% are complex complaint-related calls. The agent's workload can be calculated by weighting the current processing time + the estimated waiting time + the historical processing time (the proportion of complex business) to reflect the agent's current work pressure and ability to undertake new tasks.

[0048] In one possible implementation, see Figure 4 , Figure 4 This is a flow chart of determining the agent workload corresponding to the first agent identifier provided by an embodiment of the present application, such as Figure 4 As shown, determining the agent workload corresponding to the first agent identifier based on the business data corresponding to the first agent identifier includes the following steps: S401: Determine a first agent workload corresponding to the first agent identifier according to the concurrent load data and the service efficiency data.

[0049] Business data includes concurrent load data, service efficiency data, customer service volume data, and service quality data. Specifically, concurrent load data refers to the volume of business handled by agents at the same time and resource usage, including the number of active transactions (e.g., number of calls answered simultaneously, number of tickets processed concurrently), system resource utilization (e.g., CPU / memory usage), and the number of concurrent requests during transaction processing. Service efficiency data measures the time efficiency of agent processing and includes information such as the processing time of individual transactions (total time from start to finish), response time (the interval between receiving a transaction request and starting processing), and timeout rate (the proportion of transactions that exceed the specified processing time). Customer service volume data refers to the total number of transactions handled by agents within a specific timeframe and related scale indicators, including the cumulative number of transactions handled (e.g., number of customers served daily, total number of tickets processed), queue length for pending transactions, and the time distribution of transaction processing (e.g., peak hour volume). Service quality data, used to assess the quality of agent processing, includes customer satisfaction scores, transaction accuracy rates, complaint rates (the proportion of transactions resulting from customer complaints), and repeat processing rates (the proportion of the same issue requiring repeated processing).

[0050] Concurrent load data reflects the amount of parallel tasks, while service efficiency data reflects the time spent on individual tasks. Combining these two data provides a preliminary assessment of an agent's baseline workload. This baseline workload is quantified by the volume of tasks an agent is currently handling (concurrent load data) and the time efficiency of these tasks (service efficiency data), resulting in the primary agent workload.

[0051] For example, if an agent is currently processing five tasks simultaneously (concurrent load data), and each task takes an average of 20 minutes to complete (the average processing time in the service efficiency data), then the first agent's workload can be expressed as the current number of concurrent tasks × average processing time, that is, 5 × 20 = 100 minutes, reflecting the time cost required for the agent to complete all tasks under the current concurrent state.

[0052] The first agent workload corresponding to the first agent identifier may be determined according to the concurrent load data and the service efficiency data by other calculation methods, and the specific calculation method is not limited here.

[0053] S402: Determine a second agent workload corresponding to the first agent identifier according to the service efficiency data and the reception scale data.

[0054] The second metric, Agent Workload, assesses the agent's overall workload based on historical reception volume and time efficiency. Reception volume data reflects the total volume of transactions, while service efficiency data reflects the time cost of handling each transaction. Multiplying the two quantifies the agent's overall workload over that period, used to assess their long-term workload pressure.

[0055] For example, if an agent receives a total of 100 transactions today (the cumulative number of transactions received in the reception scale data), and each transaction takes an average of 15 minutes (the average processing time in the service efficiency data), then the "second agent workload" can be calculated as "the cumulative number of transactions received × the average processing time", that is, 100 × 15 = 1500 minutes, which reflects the total time invested by the agent in handling transactions within a certain period of time (such as the current day).

[0056] The second agent workload corresponding to the first agent identifier may be determined based on the service efficiency data and the reception scale data in other calculation methods, and the specific calculation method is not limited here.

[0057] S403: Determine a service quality adjustment value corresponding to the first agent identifier according to the service quality data.

[0058] Among them, service quality data is a variety of quantitative indicators used to measure and evaluate the service level of agents or service entities during business processing. Service quality data can be used as user satisfaction scores and / or net recommendation values ​​for agents.

[0059] The agent's service quality index is used to adjust workload, reflecting the impact of service quality on work pressure. For example, if an agent's customer satisfaction score is below the standard, additional time may be required to handle customer complaints or repeat business (e.g., a high repeat handling rate). In this case, the service quality adjustment value is greater than 0, indicating an increase in workload. If satisfaction is high and the handling accuracy rate is high, the service quality adjustment value is less than 0, indicating a reduction in workload.

[0060] S404: Determine the agent workload corresponding to the first agent identifier according to the first agent workload, the second agent workload, and the quality of service adjustment value.

[0061] The first agent workload, the second agent workload, and the service quality adjustment value may be integrated by weighting or accumulation, and ultimately an agent workload that fully reflects the agent work saturation level may be obtained.

[0062] Specifically, based on the first agent workload, the second agent workload and the service quality adjustment value, the agent workload corresponding to the first agent identifier is determined, including: multiplying the first weight and the first agent workload to obtain a first result; multiplying the second weight and the second agent workload to obtain a second result; multiplying the third weight and the service quality adjustment item to obtain a third result; and adding the first result, the second result and the third result to obtain the agent workload.

[0063] Optionally, the calculation formula for determining the agent workload corresponding to the first agent identifier based on the first agent workload, the second agent workload, and the service quality adjustment value may be as follows: Load=W1xLoad1+W2xLoad2+W3xH; Among them, Load is the agent workload corresponding to the first agent identifier, Load1, Load2 and H are the first agent workload, the second agent workload and the service quality adjustment item respectively, and W1, W2 and W3 are the first weight, the second weight and the third weight respectively.

[0064] For example, please refer to Table 1: Table 1

[0065] Substitute the formulas to calculate the agent workload (W1 is 0.5, W1 is 0.2, and W1 is 0.3) as shown in Table 2 below: Table 2

[0066] Among them, when calculating the agent workload, in addition to considering the above-mentioned multiple business data, more information related to the agent's business data can be added and assigned corresponding weights, which is not limited here.

[0067] It can be seen that in this example, the first workload and the second workload are determined by combining concurrent load, service timeliness, and reception scale data, and adjusted according to the service quality data, so as to achieve quantification and dynamic correction of the agent workload, providing an accurate basis for subsequent resource allocation based on the agent workload.

[0068] In one possible implementation, see Figure 5 , Figure 5 This is a flow chart of determining the first agent workload corresponding to the first agent identifier provided by an embodiment of the present application, such as Figure 5 As shown, determining the first agent workload corresponding to the first agent identifier according to the concurrent load data and the service time efficiency data includes the following steps: S501: Perform a preset quotient operation on the number of concurrent reception objects and the standard number of concurrent reception objects to obtain a first value.

[0069] Among them, concurrent load data includes the number of concurrent reception objects and the standard number of concurrent reception objects. Specifically, the number of concurrent reception objects refers to the number of users or business objects that the agent is serving at the same time, and the standard number of concurrent reception objects refers to the reasonable number of users that an agent should receive based on business regulations or experience.

[0070] The formula for obtaining the first value by performing a preset quotient operation on the number of concurrent reception objects and the standard number of concurrent reception objects may be: L1=N1 / N2; Among them, L1 is the first value, N1 is the number of concurrent reception objects, and N2 is the standard number of concurrent reception objects.

[0071] S502: Perform a preset quotient operation on the duration of a single service to the received object and the standard duration of a single service to the object to obtain a second value.

[0072] Among them, service time efficiency data includes the single service duration of the received objects and the standard single service duration of the objects. Specifically, the single service duration of the received objects refers to the average time spent by the agent to handle each customer or business object (for example, if an agent takes a total of 120 minutes to receive 10 customers, the single duration is 12 minutes); the standard single service duration of the object is the ideal duration of a single service set by the enterprise based on the complexity of the business (for example, the standard service duration is 10 minutes).

[0073] The formula for obtaining the second value by performing a preset quotient operation on the single service duration of the received object and the standard single service duration of the object can be: L2=t1 / t2; Among them, L2 is the second value, t1 is the single service duration of the received object, and t2 is the standard single service duration of the object.

[0074] S503: Determine a first agent workload corresponding to the first agent identifier according to the first value and the second value.

[0075] The method for determining the first seat workload corresponding to the first seat identifier according to the first value and the second value may be weighted calculation or direct multiplication, and the method for determining the first seat workload is not limited here.

[0076] Specifically, determining the first agent workload corresponding to the first agent identifier according to the first value and the second value includes: performing a multiplication operation on the first value and the second value, and using the multiplication result as the first agent workload.

[0077] Optionally, the calculation formula for determining the first agent workload corresponding to the first agent identifier based on the first value and the second value may be as follows: Load1=L1xL2; Wherein, Load1 is the workload of the first seat, L1 is the first value, and L2 is the second value.

[0078] It can be seen that in this example, by comparing the concurrent reception volume and single service duration with the standard values ​​to calculate the coefficient, and then comprehensively determining the first agent workload, a quantitative assessment of the agent's concurrent pressure and time efficiency is achieved, providing accurate data support for the subsequent determination of the agent's workload.

[0079] In one possible implementation, see Figure 6 , Figure 6 This is a flow chart of determining the workload of a second agent corresponding to a first agent identifier provided by an embodiment of the present application, such as Figure 6 As shown, determining the second agent workload corresponding to the first agent identifier according to the service efficiency data and the reception scale data includes the following steps: S601: Perform a preset quotient operation on the service duration and the standard service duration to obtain a third value.

[0080] Among them, service time data also includes service time and standard service time. Specifically, service time refers to the total time that the agent actually puts into service during the statistical period. For example, if an agent has worked for a total of 4 hours today, the agent's service time is 4 hours; standard service time is the normal working time standard for agents set by the enterprise or industry (such as the standard daily working time is 8 hours).

[0081] The formula for obtaining the third value by performing a preset quotient operation on the service time and the standard service time is as follows: L3=t3 / t4; Among them, L3 is the third value, t3 is the service time, and t4 is the standard service time.

[0082] S602: Perform a preset quotient operation on the number of received objects and the standard number of received objects to obtain a fourth value.

[0083] Among them, the reception scale data includes the number of received objects and the standard number of received objects. Specifically, the number of received objects refers to the total number of customers or business objects actually served by the agent during the statistical period. For example, if an agent has processed 50 work orders today, the number of objects received by the agent is 50; the standard number of received objects is the ideal reception capacity of the agent set by the enterprise based on factors such as business complexity and service efficiency (such as the daily standard reception capacity is 60).

[0084] The formula for obtaining the fourth value by performing a preset quotient operation on the number of received objects and the standard number of received objects is as follows: L4=N3 / N4; Among them, L4 is the fourth value, N3 is the number of objects received, and N4 is the standard number of objects received.

[0085] S603: Determine a second agent workload corresponding to the first agent identifier according to the third value and the fourth value.

[0086] The method for determining the second agent workload corresponding to the first agent identifier according to the third value and the fourth value may be weighted calculation or direct multiplication, and the method for determining the first agent workload is not limited here.

[0087] Specifically, determining the second agent workload corresponding to the first agent identifier according to the third value and the fourth value includes: multiplying the third value and the fourth value, and using the multiplication result as the second agent workload.

[0088] Optionally, a calculation formula for determining the workload of the second agent corresponding to the first agent identifier according to the third value and the fourth value may be as follows: Load2=L3xL4; Among them, Load2 is the second seat workload, L3 is the third value, and L4 is the fourth value.

[0089] As can be seen, in this example, by comparing the service time and the number of received customers with the standard values, calculating the coefficients, and then comprehensively determining the second agent workload, a quantitative assessment of the agent time investment and business output is achieved, providing accurate data support for the subsequent determination of the agent workload.

[0090] In a possible implementation, determining the service quality adjustment value corresponding to the first agent identifier based on the service quality data includes calculating a difference between a first preset value and the object satisfaction to obtain the service quality adjustment value corresponding to the first agent identifier.

[0091] Among them, service quality data includes object satisfaction, which is the customer's satisfaction score with the agent service, usually on a 0-10 point scale, and can be converted through normalization.

[0092] Among them, the first preset value is the value set by the user of the business management department in the client 101 of the data processing system 100. The first preset value is the satisfaction benchmark value set by the enterprise. For example, the first preset value is 1, and the normalized object satisfaction is 0.8. At this time, the difference is 1-0.8=0.2, and 0.2 is used as the subsequent service quality adjustment item.

[0093] It can be seen that in this example, the service quality adjustment value is determined by calculating the difference between the first preset value and the object satisfaction, thereby achieving a quantitative assessment of the gap between the agent service quality and the standard, providing accurate data support for the subsequent determination of the agent workload.

[0094] S203: Determine a matching probability between the first agent identifier and the first object according to the agent workload and the service data, and determine the first agent identifier whose matching probability meets a preset rule as a second agent identifier matching the first object.

[0095] Among them, the agent workload is a quantitative indicator calculated through step S202, which reflects the agent's current work saturation and stress level; the business data covers the full amount of information on the agent's business processing, including dimensions such as concurrent reception volume, service time, reception scale and service quality.

[0096] Among them, the preset rules are pre-set judgment criteria or condition sets used to screen the matching probability, which can be set by users of the business management department in the client 101 of the data processing system 100. The preset rules can be taking the maximum value, taking the 75th percentile, etc., and there is no restriction on the preset rules here.

[0097] In a possible implementation, determining, according to the agent workload and the service data, a matching probability between the first agent identifier and the first object includes: Determine an agent workload adjustment value corresponding to the first agent identifier based on the agent workload corresponding to the first agent identifier; and determine a matching probability between the first agent identifier and the first object based on the business data corresponding to the first agent identifier and the agent workload adjustment value.

[0098] The original agent workload can be directly converted into an agent workload adjustment value using pre-set rules (e.g., calculation rules or mapping rules). The business data and the workload adjustment value are combined to calculate the matching probability between the first agent identifier and the first object using a model or algorithm (e.g., weighted summation or machine learning model).

[0099] As can be seen, in this example, by first converting the agent workload into an adjustment value and then comprehensively calculating the matching probability based on business data, a two-dimensional quantitative assessment of the agent's work saturation and service capability is achieved, providing a scientific decision-making basis for the accurate matching of users and agents.

[0100] In one possible implementation, determining the seat workload adjustment value corresponding to the first seat identifier based on the seat workload corresponding to the first seat identifier includes: obtaining an average seat workload based on the seat workload corresponding to the first seat identifier; determining an agent workload bias value corresponding to the first seat identifier based on the seat workload corresponding to the first seat identifier and the average seat workload; and determining the seat workload adjustment value corresponding to the first seat identifier based on the seat workload bias value, a preset first weight, and a second preset value.

[0101] wherein, after determining the agent work load corresponding to the first agent identifier, the agent work loads of all the related agents (i.e. the agent set of the first agent identifier) are aggregated, and the average agent work load is calculated by means of arithmetic average.

[0102] wherein, the agent work load bias value corresponding to the first agent identifier is determined according to the agent work load corresponding to the first agent identifier and the average agent work load, including: obtaining a fifth value by subtracting the average agent work load from the agent work load corresponding to the first agent identifier; taking the fifth value as the input of a sign function, and the output of the sign function is the agent work load bias value corresponding to the first agent identifier.

[0103] Optionally, the calculation formula for determining the agent work load bias value corresponding to the first agent identifier according to the agent work load corresponding to the first agent identifier and the average agent work load can be as follows: Lp=sign(Load-E); wherein, Lp is the agent work load bias value, sign(x) is a sign function, the output value is 1 when x>0, the output value is -1 when x<0, and the output value is 0 when x=0, Load is the agent work load, and E is the average agent work load.

[0104] wherein, the agent work load adjustment value corresponding to the first agent identifier is determined according to the agent work load bias value, the first preset weight, and the second preset value, including: obtaining a sixth value by multiplying the agent work load bias value and the first preset weight; obtaining the agent work load adjustment value by subtracting the sixth value from the second preset value.

[0105] Optionally, the calculation formula for determining the agent work load adjustment value corresponding to the first agent identifier according to the agent work load bias value, the first preset weight, and the second preset value can be as follows: B(t+1)=B(t)-W4xLp; wherein, B(t+1) is the agent work load adjustment value at time t+1, B(t) is the second preset value when t is 0, W4 is the first preset weight, and is used to control the amplitude of the bias term adjustment.

[0106] Specifically, the logic of the above formula is to determine whether the agent is overloaded or idle by comparing the current load of the agent and the average load in the field: overloading agent: reduce the bias value (the output of the sign function is 1, which leads to reduction), and reduce the probability of being selected; idle agent: increase the bias value (the output of the sign function is -1, which leads to increase), and increase the probability of being selected.

[0107] Wherein, by increasing or decreasing the bias term, a dynamic balance is formed, and the request quantity of the overloaded agent is reduced, which leads to a decrease in load, and the request quantity of the idle agent is increased, which leads to an increase in load, and the final goal is to make the load of all agents converge around the average value.

[0108] Exemplarily, assuming that there are A, B and C 3 agents, the agent workloads are [70%, 30%, 50%] respectively, the average load = 50%, the preset first weight = 0.1, and the second preset value = 0, at this time t = 0, the agent workload adjustment value (i.e. B(1)) is calculated as shown in the following table 3: Table 3

[0109] It can be seen that in this example, the adjustment value is generated by calculating the average load, the bias value and combining the preset weight, which quantifies the agent load from multiple dimensions and provides a scientific decision basis for subsequent resource allocation.

[0110] In a possible implementation, according to the business data corresponding to the first agent identifier and the agent workload adjustment value, the matching probability of the first agent identifier and the first object is determined, comprising: according to the standard reception object quantity in the business data and the agent workload adjustment value, the matching value of the first agent identifier and the first object is obtained; according to the matching value, the matching probability of the first agent identifier and the first object is determined.

[0111] Wherein, the standard reception object quantity and the agent workload adjustment value are operated by a specific algorithm (such as multiplication, weighted summation, etc.) to obtain the matching value of the first agent identifier and the first object.

[0112] Wherein, the matching value is a quantitative index of the agent standard reception capacity and the workload adjustment, which reflects the adaptation of the agent and the first object in the business bearing layer. After obtaining the matching value, the matching value is further converted into the matching probability of the first agent identifier and the first object by a specific conversion function (such as a normalization function, a probability mapping function, etc.).

[0113] For example, the matching value is normalized to map it to the interval of 0-1, and the obtained value is the matching probability.

[0114] Wherein, according to the standard reception object quantity in the business data and the agent workload adjustment value, the matching value of the first agent identifier and the first object is obtained, comprising: summing the standard reception object quantity and the agent workload adjustment value to obtain a seventh value; performing exponential calculation on the seventh value to obtain the matching value.

[0115] Optionally, the calculation formula of the matching value of the first agent identifier and the first object according to the standard number of objects to be received and the agent workload adjustment value in the service data can be as follows: p = exp(N4 + B); Wherein, p is the matching value, N4 is the standard number of objects to be received, and B is the agent workload adjustment value.

[0116] Wherein, according to the matching value, the matching probability of the first agent identifier and the first object is determined, including: summing up the matching values of all the first agent identifiers and the first object to obtain an eighth value; calculating the quotient of the matching value of each first agent identifier and the first object and the eighth value to obtain the matching probability of the first agent identifier and the first object.

[0117] Optionally, the calculation formula of the matching probability of the first agent identifier and the first object according to the matching value can be as follows: P = p / L8; Wherein, P is the matching probability of the first agent identifier and the first object, p is the matching value of the first agent identifier and the first object, and L8 is the eighth value, i.e. the sum of the matching values of all the first agent identifiers and the first object.

[0118] Wherein, in the above calculation formula, the use of the exponential function means to amplify the difference: the exponential function maps the linear score to the positive number space, and then amplifies the relative advantage of the high-score agent. At the same time, the probability is normalized: the sum of the exponential values of all agents in the selected field is used as the denominator to ensure that the sum of the output probabilities is 1.

[0119] Wherein, the influence of the dynamic bias term on the probability is: Overloaded agents are negative: reduce their exponential values and reduce the probability of being selected.

[0120] Space agents are positive: increase their exponential values and increase the probability of being selected.

[0121] Balancing goal: adjust the bias term value to achieve dynamic balance between agents.

[0122] Exemplarily, assuming that there are three agents A, B and C, the maximum receiving capacities of the agents are [20, 15, 18] (agent A has the strongest capacity), the initial bias term values are (0, 0, 0), and the dynamically calculated bias term values are [-4, 3, 1] (agent A is overloaded, agent B is idle, and agent C is idle) after several rounds of distribution. The probability without bias term and the probability after adding dynamic bias term are compared as shown in the following table 4 and table 5: Table 4 Probability without bias term

[0123] Table 5 Probability with dynamic bias term

[0124] Without the bias, Agent A, with the highest capability, dominates the selection process. However, with the bias, Agent A's probability of selection drops sharply due to its high load (overload penalty), while Agents B and C's probability of selection increases (idleness bonus).

[0125] It can be seen that in this example, the matching value is calculated by combining the standard number of reception objects and the agent workload adjustment value, and further converted into a matching probability, providing data support for accurately determining the matching relationship between agents and service objects.

[0126] S204: Establish a communication connection between the terminal corresponding to the second agent identifier and the terminal of the first object.

[0127] The second seat identifier is the unique identifier of the seat that is determined to be the most suitable for serving the first object after matching probability screening, and corresponds to a specific seat personnel or service unit.

[0128] The terminal corresponding to the second agent identifier refers to the device used by the agent to provide service (e.g., a customer service representative's phone, online chat console, etc.), which is used to receive and process service requests. The first terminal is the user device that initiates the service request (e.g., a customer's mobile phone, computer, app, etc.). A communication connection between these two terminals can be established through a technical interface or communication protocol, enabling real-time interaction between the agent and the user (e.g., voice calls, text chats, video calls, etc.).

[0129] It can be seen that in this example, by matching the agent ID based on the first object intention, calculating the agent workload and matching probability in combination with business data, and then screening out the second agent ID that meets the preset rules and establishing a communication connection, it is possible to accurately connect agent resources according to user needs, effectively avoid excessive concentration or idleness of resources, achieve load balancing of agent resources, and improve the utilization rate of agent resources.

[0130] In a possible implementation, the method further includes: determining, based on the historical conversation data, the number of first identifiers corresponding to domain expert seats and the number of second identifiers corresponding to shared seats in the first seat identifiers.

[0131] Among them, historical conversation data can be all or part of the conversation records (meeting specific conditions, such as call duration greater than the preset call duration) between customer service personnel and customers in the past period of time. Historical conversation data includes user questions, needs, conversation scenarios and other information. By analyzing historical conversation data, we can obtain the different technical fields involved in the historical conversation data and the frequency of occurrence of different technical fields, so as to set up domain expert seats in a targeted manner.

[0132] wherein the domain expert agent and the shared agent are both customer service personnel providing question and answer services, the domain expert agent has professional knowledge in a corresponding technical field, and the shared agent has multiple general skills and knowledge and can handle most types of questions.

[0133] wherein when determining whether the agent is a domain expert agent or a shared agent, the dialog data of each agent can be analyzed first, and then it is determined whether the agent has a service field in which the agent is good at and has certain professional knowledge in the field, and if so, the agent can be set as a domain expert agent.

[0134] wherein an adjustment period can be set, and in each adjustment period, the technical field corresponding to the agent is adjusted again according to the dialog data of the agent in the last adjustment period. Meanwhile, in order to prevent the agent from falling into an information cocoon and being mismatched from the beginning, the agent will be arranged as a shared agent to receive users with unclear intentions in rotation.

[0135] Specifically, determining the number of first identifiers corresponding to the domain expert agents in the first agent identifiers includes: multiplying the number of dialogs in each technical field in the historical dialog data and the single service duration of the received object to obtain an eighth value; multiplying the second weight and the single service standard duration of the object to obtain a ninth value; dividing the eighth value by the ninth value to obtain a tenth value; multiplying the third weight and the tenth value, and taking the multiplication result as the number of domain expert agents corresponding to each technical field.

[0136] wherein the second weight and the third weight can be configured or changed by a user of the business management department on the client 101 of the data processing system 100, which is not limited herein.

[0137] Optionally, the calculation formula for determining the number of first identifiers corresponding to the domain expert agents in the first agent identifiers can be as follows: NL=W6x((Ndxt1) / (W5xt2)); wherein NL is the number of domain expert agents in each technical field, W5 and W6 are the second weight and the third weight respectively, Nd is the number of dialogs in each technical field, t1 is the single service duration of the received object, and t2 is the single service standard duration of the object.

[0138] The content expressed by the user during the conversation may contain one or more different intentions. For example, in a customer service conversation on an e-commerce platform, a user may want to inquire about how to use a certain product and also want to inquire about the after-sales service of the product, which means there are two different intentions. When it is difficult to identify the user's clear purpose and needs by analyzing the user's conversation content, the user is considered to have no intention. For example, in a customer service scenario, the user says something unrelated to the business or service, such as "The weather is really nice today" or "I just watched a movie." At this time, it is impossible to find common intentions such as "inquire about product information", "apply for after-sales service", or "conduct business transactions", and the user is considered to have no intention.

[0139] Specifically, based on historical conversation data, shared seats are set up, including: By summarizing the technical fields to which each conversation in the historical conversation data belongs, the number of conversations in non-technical fields in the historical conversation data is determined; the number of shared seats is determined based on the number of conversations in non-technical fields, the total number of seats, the duration of a single service to the received objects, and the standard duration of a single service to the objects.

[0140] The specific implementation of this method may refer to the above implementation of determining the number of first identifications of domain expert seats in the first seat identifications, which will not be described in detail here.

[0141] It can be seen that in this example, the number of conversations in each technical field in the historical conversation data, the single service duration of the received objects and the standard single service duration of the objects are combined with weights to perform mathematical operations to determine the number of first identifiers of the corresponding field expert seats and the number of second identifiers of the corresponding shared seats. This takes into account the business volume and service complexity of different technical fields, and at the same time, adjusts the calculation results by weight to achieve accurate configuration of different numbers of seats.

[0142] See also Figure 7 , Figure 7 is a structural diagram of a data processing device provided in an embodiment of the present application, such as Figure 7 As shown, the data processing device 700 includes: The processing module 701 is configured to determine a first seat identifier corresponding to the intention in the seat information database based on the intention of the first object and a preset seat information database; and for determining, based on the business data corresponding to the first agent identifier, an agent workload corresponding to the first agent identifier; and determining a matching probability between the first agent identifier and the first object based on the agent workload and the business data, and determining the first agent identifier whose matching probability satisfies a preset rule as a second agent identifier matching the first object; The communication module 702 is configured to communicatively connect the terminal corresponding to the second agent identifier with the terminal of the first object.

[0143] In a possible implementation, the agent information base includes agent identifiers and agent level labels corresponding to the agent identifiers. In determining the first agent identifier corresponding to the intention in the agent information base based on the intention of the first object and the preset agent information base, the processing module 701 is specifically configured to: calculate semantic similarity between the intention and agent level labels in the agent information base; and determine the agent identifier corresponding to the agent level label with a semantic similarity greater than a similarity threshold as the first agent identifier.

[0144] In a possible implementation, the service data includes concurrent load data, service timeliness data, reception scale data, and service quality data. In determining the agent work load corresponding to the first agent identifier according to the service data corresponding to the first agent identifier, the processing module 701 is specifically configured to: determine a first agent work load corresponding to the first agent identifier according to the concurrent load data and the service timeliness data; determine a second agent work load corresponding to the first agent identifier according to the service timeliness data and the reception scale data; determine a service quality adjustment value corresponding to the first agent identifier according to the service quality data; and determine the agent work load corresponding to the first agent identifier according to the first agent work load, the second agent work load, and the service quality adjustment value.

[0145] In a possible implementation, the concurrent load data includes a number of concurrent reception objects and a standard number of concurrent reception objects, and the service timeliness data includes a single service time length of a received object and a standard single service time length of an object. In determining the first agent work load corresponding to the first agent identifier according to the concurrent load data and the service timeliness data, the processing module 701 is specifically configured to: perform a preset quotient operation on the number of concurrent reception objects and the standard number of concurrent reception objects to obtain a first value; perform a preset quotient operation on the single service time length of the received object and the standard single service time length of the object to obtain a second value; and determine the first agent work load corresponding to the first agent identifier according to the first value and the second value.

[0146] In one possible implementation, the service efficiency data also includes the service time and the standard service time, and the reception scale data includes the number of received objects and the standard number of received objects. In determining the second agent workload corresponding to the first agent identifier based on the service efficiency data and the reception scale data, the processing module 701 is specifically used to: perform a preset quotient operation on the service time and the standard service time to obtain a third value; perform a preset quotient operation on the number of received objects and the standard number of received objects to obtain a fourth value; and determine the second agent workload corresponding to the first agent identifier based on the third value and the fourth value.

[0147] In one possible implementation, the service quality data includes object satisfaction. In determining the service quality adjustment value corresponding to the first agent identifier based on the service quality data, the processing module 701 is specifically used to: calculate the difference between the first preset value and the object satisfaction, and obtain the service quality adjustment value corresponding to the first agent identifier.

[0148] In one possible implementation, in terms of determining the matching probability between the first agent identifier and the first object based on the agent workload and the business data, the processing module 701 is specifically used to: determine the agent workload adjustment value corresponding to the first agent identifier based on the agent workload corresponding to the first agent identifier; and determine the matching probability between the first agent identifier and the first object based on the business data corresponding to the first agent identifier and the agent workload adjustment value.

[0149] In one possible implementation, in terms of determining the seat workload adjustment value corresponding to the first seat identifier based on the seat workload corresponding to the first seat identifier, the processing module 701 is specifically used to: obtain an average seat workload based on the seat workload corresponding to the first seat identifier; determine an agent workload bias value corresponding to the first seat identifier based on the seat workload corresponding to the first seat identifier and the average seat workload; and determine the seat workload adjustment value corresponding to the first seat identifier based on the seat workload bias value, a preset first weight, and a second preset value.

[0150] In one possible implementation, in terms of determining the matching probability between the first agent identifier and the first object based on the business data corresponding to the first agent identifier and the agent workload adjustment value, the processing module 701 is specifically used to: obtain the matching value between the first agent identifier and the first object based on the standard number of reception objects in the business data and the agent workload adjustment value; and determine the matching probability between the first agent identifier and the first object based on the matching value.

[0151] It is worth noting that the specific functional implementation of the data processing device 700 is shown in the above Figure 2 The description of the data processing method shown in FIG. 1 is for example a processing module 701 for implementing the relevant contents of steps S201-S203, and a communication module 702 for implementing the relevant contents of step S204. The various units or modules in the data processing device 700 can be individually or completely combined into one or more other units or modules, or one (or more) of the units or modules can be further divided into multiple functionally smaller units or modules, which can achieve the same operation without affecting the technical effects of the embodiments of the present invention. The above-mentioned units or modules are divided according to logical functions. In actual applications, the functions of one unit (or module) are implemented by multiple units (or modules), or the functions of multiple units (or modules) are implemented by one unit (or module).

[0152] According to the description of the above method embodiment and related device embodiment, please refer to Figure 8 , Figure 8 is a structural diagram of a data processing device provided in an embodiment of the present application, Figure 8 The data processing device 800 shown includes a processor 801 , a memory 802 , a communication interface 803 , and a bus 804 . The processor 801 , the memory 802 , and the communication interface 803 are communicatively connected to each other via the bus 804 .

[0153] Optionally, the memory 802 is a ROM, a static storage device, a dynamic storage device or a RAM.

[0154] The memory 802 can store executable program codes. When the executable program codes stored in the memory 802 are executed by the processor 801, the processor 801 and the communication interface 803 are used to execute the program codes. Figure 2 The various steps of the data processing method of the embodiment are shown.

[0155] The processor 801 adopts a general-purpose CPU, a microprocessor, an application-specific integrated circuit ASIC, a GPU or one or more integrated circuits to execute relevant programs to perform the data processing method of the embodiment of the method of the present application.

[0156] Processor 801 can also be an integrated circuit chip with signal processing capabilities. During implementation, each step of the data processing method of the present application can be completed by hardware integrated logic circuits in processor 801 or by software instructions. Optionally, processor 801 is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. The processor can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor is a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The optional software module is located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other storage media well-known in the art. The storage medium is located in memory 802. Processor 801 reads information in memory 802 and, in conjunction with its hardware, completes the functions required to be performed by the modules included in a data processing device 700 of the embodiments of the present application, or executes the data processing method of the method embodiments of the present application.

[0157] The communication interface 803 uses, for example but not limited to, a transceiver or other transceiver-related device.

[0158] The bus 804 may include a path for transmitting information between various components of the data processing device 800 (eg, the memory 802 , the processor 801 , and the communication interface 803 ).

[0159] It should be noted that although Figure 8 The data processing device 800 shown only shows a memory, a processor, and a communication interface. However, in the specific implementation process, those skilled in the art should understand that the data processing device 800 also includes other devices necessary for normal operation. At the same time, according to specific needs, those skilled in the art should understand that the data processing device 800 may also include hardware devices that implement other additional functions. In addition, those skilled in the art should understand that the data processing device 800 may also include only the devices necessary to implement the embodiments of the present application, and does not necessarily include Figure 8 All devices shown in .

[0160] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program for electronic data exchange. The computer program includes execution instructions, and the execution instructions are used to execute part or all of the steps of any one of the data processing methods described in the above-mentioned data processing method embodiments. The above-mentioned computer includes an electronic client device.

[0161] The embodiment of the present application provides a computer program product, wherein the computer program product comprises a computer program, the computer program is operable to cause a computer to perform part or all of steps of any one of the data processing methods described in the foregoing method embodiment, and the computer program product can be a software installation package.

[0162] It should be noted that, for the foregoing embodiment of any one of the data processing methods, in order to simply describe, the foregoing embodiment is expressed as a combination of a series of actions, however, a person skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, a person skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions involved are not necessarily necessary for the present application.

[0163] The foregoing has introduced the embodiment of the present application in detail, and the principle and implementation manner of the data processing method, device, equipment, storage medium and program product of the present application are described by applying specific examples, the foregoing embodiment description is only for helping to understand the method of the present application and the core idea thereof; meanwhile, for a person skilled in the art, according to the idea of the data processing method, device, equipment, storage medium and program product of the present application, the specific implementation manner and application range will be changed, and according to the foregoing, the content of the specification should not be understood as the limitation of the present application.

[0164] The present application is described with reference to the flowcharts and / or block diagrams of the method, hardware product and computer program product of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device for realizing the functions specified in the flowcharts and / or block diagrams. Figure 1 The function of the device specified in one flow or multiple flows and / or blocks Figure 1 The function of the device specified in one flow or multiple flows and / or blocks

[0165] These computer program instructions can also be stored in a computer readable storage medium to cause the computer to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufactured product including instruction devices, the instruction devices realize the functions specified in the flowcharts and / or block diagrams. Figure 1 The function of the device specified in one flow or multiple flows and / or blocks Figure 1The memory can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0166] Although the present application is described herein in conjunction with various embodiments, it is understood that other variations of the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from an inspection of the drawings, the disclosure, and the appended claims. The word "comprising" does not exclude other components or steps not mentioned or comprising the essential characteristics of the application. The word "a" or "an" does not exclude a plurality. The mere fact that different claims depend on a common basis is not a indication that a combination of measures cannot be used to advantage.

[0167] It can be understood by those skilled in the art that all or part of the steps in the various methods of the method embodiments of any one of the above data processing methods can be completed by instructing the relevant hardware by a program, which can be stored in a computer readable memory, and the memory can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0168] It can be understood that any product controlled or configured to execute the processing method of the flowchart described in the data processing method embodiments of the present application, such as the device of the above flowchart and the computer program product, all belong to the scope of the related products described in the present application.

[0169] Obviously, those skilled in the art can make various modifications and variations to the data processing method, device, equipment, storage medium and program product provided by the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A data processing method, characterized in that: The method comprises: Based on the intention of the first object and a preset seat information database, determining a first seat identifier corresponding to the intention in the seat information database; determining, based on the service data corresponding to the first agent identifier, an agent workload corresponding to the first agent identifier; determining, based on the agent workload and the business data, a matching probability between the first agent identifier and the first object, and determining the first agent identifier whose matching probability satisfies a preset rule as a second agent identifier matching the first object; Establish a communication connection between the terminal corresponding to the second agent identifier and the terminal of the first object.

2. The method according to claim 1, wherein The business data includes concurrent load data, service timeliness data, reception scale data, and service quality data. Determining the agent workload corresponding to the first agent identifier based on the business data corresponding to the first agent identifier includes: Determining a first agent workload corresponding to the first agent identifier according to the concurrent load data and the service time efficiency data; determining a second agent workload corresponding to the first agent identifier according to the service efficiency data and the reception scale data; Determining a service quality adjustment value corresponding to the first agent identifier according to the service quality data; The agent workload corresponding to the first agent identifier is determined according to the first agent workload, the second agent workload, and the quality of service adjustment value.

3. The method according to claim 2, wherein The concurrent load data includes the number of concurrent reception objects and the standard number of concurrent reception objects, and the service time data includes the single service duration of the received objects and the standard single service duration of the objects; The determining, according to the concurrent load data and the service time efficiency data, the first agent workload corresponding to the first agent identifier includes: Performing a preset quotient operation on the number of concurrent reception objects and the standard number of concurrent reception objects to obtain a first value; Performing a preset quotient operation on the duration of the single service of the received object and the standard duration of the single service of the object to obtain a second value; A first agent workload corresponding to the first agent identifier is determined according to the first value and the second value.

4. The method according to claim 2, wherein The service efficiency data further includes a service duration and a standard service duration, and the reception scale data includes a number of received guests and a standard number of received guests. Determining the second agent workload corresponding to the first agent identifier based on the service efficiency data and the reception scale data includes: performing a preset quotient operation on the served time and the standard service time to obtain a third value; Performing a preset quotient operation on the number of received objects and the standard number of received objects to obtain a fourth value; Determine a second agent workload corresponding to the first agent identifier according to the third value and the fourth value.

5. The method according to claim 2, wherein The service quality data includes object satisfaction, and determining the service quality adjustment value corresponding to the first agent identifier according to the service quality data includes: The difference between the first preset value and the object satisfaction is calculated to obtain a service quality adjustment value corresponding to the first agent identifier.

6. The method according to any one of claims 1 to 5, wherein: The determining, based on the agent workload and the service data, a matching probability between the first agent identifier and the first object includes: determining, according to the agent workload corresponding to the first agent identifier, an agent workload adjustment value corresponding to the first agent identifier; A matching probability between the first agent identifier and the first object is determined according to the business data corresponding to the first agent identifier and the agent workload adjustment value.

7. The method according to claim 6, wherein The determining, according to the agent workload corresponding to the first agent identifier, an agent workload adjustment value corresponding to the first agent identifier, includes: Obtaining an average agent workload according to the agent workload corresponding to the first agent identifier; determining, according to the agent workload corresponding to the first agent identifier and the average agent workload, an agent workload offset value corresponding to the first agent identifier; An agent workload adjustment value corresponding to the first agent identifier is determined according to the agent workload offset value, a preset first weight, and a second preset value.

8. The method according to claim 6, wherein The determining, based on the business data corresponding to the first agent identifier and the agent workload adjustment value, a matching probability between the first agent identifier and the first object includes: Obtaining a matching value between the first agent identifier and the first object according to the standard reception object quantity in the business data and the agent workload adjustment value; A matching probability between the first agent identifier and the first object is determined according to the matching value.

9. A data processing device, characterized in that: The device comprises: A memory, a processor, and an executable program code stored in the memory and capable of running on the processor, wherein the processor executes the steps of the data processing method according to any one of claims 1 to 8 when executing the executable program code.

10. A computer program product, characterized in that The computer program product includes a computer program, and the computer program is used to enable a computer to execute the steps of the data processing method according to any one of claims 1 to 8.

Images