Digital service market simulation method and system

Abstract

The invention provides a digital service market simulation method and system, and the method comprises the steps: carrying out the modeling of an external demand environment in a digital service market, mapping the external demand environment into order states which represent the demands of a user and have different types and different difficulties, and setting an order arrival strategy and an order difficulty generation strategy; modeling a main body of the digital service system in the digital service market, wherein the main body comprises a platform, a mechanism and an execution agent; modeling order transfer rules among institutions in the digital service market and execution agent cooperation rules in the institutions; and based on modeling results of the three parts, configuring an external demand environment, a main body and rule parameters of the target digital service market, and performing simulation. Mapping from the digital service market to the computer simulation system is achieved through modeling from the three aspects of the external environment, the main body and the rule, and the problem that an existing digital service market lacks a visual and effective simulation method and an experiment system is solved.

Description

Technical Field

[0001] The present invention belongs to the field of digital service market, and in particular relates to a digital service market simulation method and system. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The digital service market is a new trade model based on digital technology and the Internet. It provides a wide range of services through digital platforms, such as government services, financial services, and communication services. In recent years, the digital service market has expanded rapidly around the world, becoming an important engine for promoting economic development, and is also becoming the key to achieving the development of my country's digital economy and comprehensively improving the level of digitalization.

[0004] The digital service market is composed of digital service systems and external demand environments. Among them, the digital service system is a new service system that uses digital technology to provide various services to service demanders, aiming to comprehensively improve service efficiency, quality and other service experiences, thereby promoting the development of my country's digital economy.

[0005] With the development of technologies such as cloud computing, big data, artificial intelligence, and mobile application development, digital service systems integrate resources, optimize business processes, and use advanced technologies to achieve automation, intelligence, and personalization of services. In the wave of informatization, digital service systems have become an important tool for modern enterprises and personal services with their high efficiency, convenience, and accuracy, providing service demanders with better quality, more efficient, and personalized services, and playing an important role in various fields. For example, the intelligent customer service system provides service demanders with a 24-hour, personalized service experience; the data service system helps enterprises discover problems in the service process and optimize the service process through data analysis.

[0006] The digital service system is an ecosystem in which participants achieve efficient collaboration by establishing a series of interactive relationships (such as social relationships, service relationships, supply relationships, etc.). Figure 1 As shown in the figure, the service operator adopts a variety of supply and demand matching strategies, integrates the business services of different service suppliers, and provides customers with candidate service solutions. According to customer feedback, the enterprise relationship network and the operating status of physical equipment are continuously adjusted, which in turn affects the performance of the service matching strategy, and finally forms a closed-loop digital service system.

[0007] Monitoring and analyzing the complex dynamics and operating status between participants can help guide the matching of services between supply and demand parties and improve the efficiency of multi-party collaboration. As the digital service market increasingly features the integration of society, physics, and information, it is crucial to achieve effective system governance and ensure the stability and efficiency of services. However, digital service systems often involve human and social factors. The complexity of the system and the variability of the external environment make it difficult to effectively evaluate the system and system anomalies occur frequently, seriously affecting service business continuity and demand-side experience. Summary of the invention

[0008] In order to solve the above problems, the present invention proposes a digital service market simulation method and system. The present invention realizes the mapping of the digital service market to the computer simulation system by modeling from three aspects: external environment, subject and rules, thereby solving the problem of lack of intuitive and effective simulation methods and experimental systems in the existing digital service market.

[0009] According to some embodiments, the present invention adopts the following technical solutions: A digital service market simulation method comprises the following steps: Model the external demand environment in the digital service market, map the external demand environment into order states of different types and difficulties representing user needs, and set order arrival strategies and order difficulty generation strategies; Modeling the main body of the digital service system in the digital service market, which includes the platform, the organization and the execution agent, and forming an entity class table of each main body; Modeling the order routing rules between institutions in the digital service market and the coordination rules of execution agents within institutions; Based on the modeling results of the three parts, the external demand environment, subjects and rule parameters of the target digital service market are configured, simulation is carried out, and simulation results are obtained.

[0010] As an optional implementation, the process of mapping the external demand environment into order states of different types and difficulties representing user needs includes constructing an order entity attribute table, wherein the order entity attribute table includes the order type, name, pending queue, ratio of order value to order difficulty, agent that accepts the order, order status, order arrival time, order delivery connection, and upper and lower limits of order difficulty thresholds.

[0011] As an optional implementation, the order type is provided with a plurality of basic orders, each basic order is matched with a corresponding mechanism in the digital service system, and each order has a corresponding difficulty value.

[0012] As an optional implementation, the process of setting the order arrival strategy includes: generating the order arrival time based on queuing theory, and setting an order arrival rate that can be adjusted by the user to control the average number of orders arriving per unit time.

[0013] As an optional implementation, the process of setting the order difficulty generation strategy includes: the distribution mode of the user-provided order includes normal distribution and uniform distribution, wherein, in the case of normal distribution, a plurality of optional difficulty generation levels are provided to the user according to the length and overall difficulty of the order, and the order probability of each level is controlled according to the normal distribution point value; In the case of uniform distribution, users cannot choose the difficulty of generating orders, and the type and difficulty value of generated orders are uniform.

[0014] As an optional implementation, the process of modeling the subject of the digital service system in the digital service market includes: The platform is used to coordinate and control the entire digital service system, receive orders from outside the digital service system, and assign the orders to different institutions for processing. At the same time, the platform calculates the total cost and total revenue and evaluates the overall performance; The organization is composed of internal salesmen and software robots, which are used to receive orders assigned by the platform and transfer orders between organizations; The execution agent includes a salesperson and a software robot. The salesperson is configured to handle orders of all difficulty levels, and the salesperson can create value by completing orders. The value created varies according to the difficulty, processing time and quantity of the completed orders. The software robot is configured to process orders with a difficulty level lower than a set level, but the order processing speed is higher than that of a salesperson, and the software robot does not consume additional costs when processing orders.

[0015] As an optional implementation, the process of modeling the order delivery rules between institutions in the digital service market and the cooperation rules of the execution agents within the institutions includes: the platform is responsible for receiving orders from the outside and allocating them to the institutions according to the set algorithm, and the overall effectiveness of the platform reflects the quality of the service; Different orders are processed in parallel, and the same order is processed in serial; After receiving an order from the platform or other institutions, the institution selects an execution agent to process the order based on the institution's internal order allocation strategy. The execution agent has the right to decide whether to establish a connection with other execution agents to jointly process the order; Each execution agent forms a collaborative network. Only the execution agents that are connected in the collaborative network establish connections to jointly process orders, and only agents with the attribute of salesperson can actively initiate connections to other execution agents.

[0016] As a further implementation method, the process of allocating it to an institution according to a set algorithm includes: the platform determines the institutions participating in the allocation according to the type of order, sorts the completion order of the institutions participating in the allocation according to the difficulty of the order, and then selects the institution's occupancy rate to give priority to allocating the order to the corresponding institution with the lowest occupancy rate; if all software robots of the currently allocated institution are occupied, the order will be passed on to the institution whose software robots are not fully occupied in the allocation order.

[0017] As a further implementation method, the process of selecting an execution agent to process the order according to the internal order allocation strategy of the organization includes: if the difficulty of the order is less than the difficulty threshold that the software robot can process, then the idle software robot is used first to process the order; if all the software robots are in an occupied state, then the execution agent with the least number of unprocessed tasks within the organization is queried to process the order; If the difficulty of the order exceeds the difficulty threshold that the software robot can handle, the salesperson with the least number of unprocessed tasks within the organization will be queried, and the order will be assigned to that salesperson for processing.

[0018] As a further implementation method, each time the organization allocates an order, the status of each execution agent within the organization is updated, including the occupancy rate and the total occupancy rate of the organization. When the execution agent within the organization completes processing the order, the execution agent returns the order to the organization level, which then judges and passes it to the next other organization to process the order.

[0019] As a further implementation method, after each execution agent forms a collaborative network, the rules for processing orders include: If the order difficulty value is less than the difficulty threshold that the software robot can handle, the salesperson selects other idle execution agents with whom he has a connection for collaborative processing; If the order difficulty is greater than the difficulty threshold that the software robot can handle, the salesperson will select other idle salespersons with whom he is connected to collaborate on the processing; If other execution agents connected to the execution agent are occupied, the execution agent can only process the order alone.

[0020] As a further implementation method, when the execution agent processes an order, it is necessary to calculate the order processing time according to the difficulty value of the order and the work efficiency of the corresponding execution agent. If the difficulty value of the order and the work efficiency of the corresponding execution agent cannot be divided evenly, the order processing time is calculated by rounding up; If multiple execution agents collaborate to process an order, the order processing time is calculated based on the difficulty value of the order and the sum of the work efficiency of each execution agent participating in the collaboration.

[0021] As a further implementation, after the execution agent processes the order, the efficiency of the digital service system is calculated, and the efficiency is the difference between revenue and cost.

[0022] A digital service market simulation system, comprising: An external demand environment module is configured to model the external demand environment in the digital service market, map the external demand environment into order states of different types and difficulties representing user demands, and set an order arrival strategy and an order difficulty generation strategy; A subject modeling module is configured to model the subject of the digital service system in the digital service market, wherein the subject includes a platform, an organization, and an execution agent, and form an entity class table of each subject; A rule modeling module configured to model order delivery rules between institutions in the digital service market and execution agent collaboration rules within the institutions; The simulation operation module is configured to configure the external demand environment, subject and rule parameters of the target digital service market based on the modeling results of the three parts, perform simulation and obtain simulation results.

[0023] Compared with the prior art, the present invention has the following beneficial effects: The present invention can simulate the digital service market scenario very well. From the perspective of modeling, the mapping of the digital service market to the computer simulation system is realized through modeling of the external environment, subject and rules; in terms of function, the environment design can personalize the order parameters; the subject design supports custom attributes and verification.

[0024] The present invention can intuitively display order delivery and Agent working status. By changing the system environment in multiple dimensions and adjusting the main parameters within the system, it helps system managers observe the parameters that affect system performance from multiple angles, in order to obtain the maximum benefits in actual situations.

[0025] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0027] Figure 1 This is a logic diagram of the operation of the digital service market in Example 1; Figure 2 This is a business flow chart of the digital service system in Example 1; Figure 3 It is the Agent operation association diagram in the first embodiment; Figure 4 This is an example of a collaborative network diagram of entities within an organization in Example 2; Figure 5 This is a network diagram of inter-institutional order delivery in Example 2; Figure 6 This is a diagram showing the Agent collaboration network and data display within the organization in Example 2. DETAILED DESCRIPTION

[0028] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0029] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0030] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0031] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0032] Embodiment 1 This embodiment discloses a modeling method for a digital service market, which specifically includes the following contents.

[0033] Step 1: Modeling the external environment In the digital service market, the external environment of the digital service system is the external demand of the system, which is represented by the orders that continuously arrive from different users. The time interval and quantity of the orders arriving, as well as the type and complexity of the arriving orders, need to be considered. The time it takes to complete an order reflects the ability of the system to complete the order, and the time and cost it takes for the system to complete all the incoming orders can measure the overall ability of the system.

[0034] Orders come from outside the system, and N basic types such as ABC... are set, as well as their random combinations. Among them, BA type orders are equivalent to AB type, and so on. At the same time, the same type of orders also have different levels of complexity (i.e., processing difficulty). The specific order entity attribute settings are shown in Table 1.

[0035] It should be noted that, the eg. in the following tables are all examples and can be modified in other embodiments.

[0036] Table 1 Order entity attribute table

[0037] The specific order environment operation mechanism is designed as follows: (1) Order type design Based on N basic types such as ABC... set in the order, N is a positive integer. A complex order can be composed of multiple basic types of orders, such as "Order ABH", "Order CEF", "Order ACDEFH", etc. N institutions of the same type are set up correspondingly in the digital service system, and institutions of the same type can only process orders of the same type. For example, institution A can only process orders of basic type A. Orders should also have different difficulty values, which represent the difficulty of the order. The value is a positive integer in the range [a, b]. Salesmen and software robots can process orders of different difficulties respectively. At the same time, the difficulty value of an order also indirectly indicates the value of the order. For example, if an institution processes an order with a difficulty of 100, then it can obtain of income, of which It is a ratio defined by the system, which represents the mapping ratio between the order difficulty and the value created by the Agent when processing the order. Therefore, an order can be represented as "Order A78B29E52". In addition, the system also stipulates that the maximum order difficulty that the robot can handle is .

[0038] (2) Order arrival strategy In order to simulate the arrival of user demand under actual circumstances, the time it takes for orders to arrive at the system will be generated based on queuing theory. At the same time, in order to regulate the amount of orders arriving at the system, the system sets an "order arrival rate" that can be adjusted by users to control the average number of orders arriving at the system per unit time.

[0039] (3) Order Difficulty Generation Strategy The difficulty of an order is a characteristic of the system's external environment and is one of the factors that need to be considered. The distribution of user-provided orders includes normal distribution and uniform distribution.

[0040] Normal distribution. Under normal distribution, the system provides users with three levels of difficulty generation: low difficulty, medium difficulty, and high difficulty. Low difficulty orders are short and have a low overall difficulty level, while high difficulty orders are long and have a high difficulty level. The system will control the probability of generating "low difficulty", "medium difficulty", and "high difficulty" orders at the following levels: , and .

[0041] Uniform distribution. In the case of uniform distribution, users cannot choose the difficulty of generating orders, and the system will evenly generate the type and difficulty of orders.

[0042] Step 2: Modeling the body The digital service system involves four types of entities: "platform", "organization", "salesman" and "software robot", which are modeled as follows.

[0043] (1) Platform The platform is responsible for coordinating and controlling the entire system, receiving orders from outside the system, and assigning orders to different institutions for processing. At the same time, the platform calculates the total cost and total revenue and evaluates the overall performance. The specific platform entity attributes are shown in Table 2.

[0044] Table 2 Platform entity class table

[0045] (2) Institutions The organization is composed of internal salesmen and software robots, responsible for receiving orders assigned by the platform, and can transfer orders between organizations. The organization class inherits threading.Thread and supports multi-threaded operation. The specific organization entity attributes are shown in Table 3.

[0046] Table 3 Organization entity class table

[0047] (3) Salesperson Salespersons are one of the entities that handle orders within an organization. Salespersons can create value by completing orders. The value created varies depending on the difficulty, processing time, and quantity of the orders. The salesperson's performance will increase accordingly based on the value they create. Unlike robots, salespersons can handle orders of all difficulty levels, but generally speaking, salespersons' processing efficiency is lower than that of robots. The specific salesperson entity attributes are shown in Table 4.

[0048] Table 4 Salesperson entity class table

[0049] (4) Software Robots Software robots (hereinafter referred to as robots) are another entity that processes orders within the organization. Compared with salesmen, robots can only process low-difficulty orders, but robots process orders faster and do not consume additional costs when processing orders. The specific software robot entity attributes are shown in Table 5.

[0050] Table 5 Software Robot Entity Class Table

[0051] Step 3: Rule Modeling like Figure 2 As shown in the figure, the supply side of the system is designed as a three-layer structure of "platform-institution-agent". The platform is responsible for receiving orders from outside the system and allocating them to institutions according to a certain algorithm. At the same time, the overall performance of the platform can reflect the quality of the system's services.

[0052] Different orders are processed in parallel, while the same order is processed in series. For example, for an ABCD type order, only after institution A has processed part A will institution BCD process the remaining part; of course, institution B can process part B first, and then institution ACD can process the remaining part.

[0053] Orders can be transferred between institutions. For example, the possible processing methods for "Order ABC" are: institution A processes it first, then passes it to institution C for processing, and finally institution B processes it. After an institution receives an order from the platform or other institutions, it selects an agent to process the order based on the institution's internal order allocation strategy. The agent has the right to decide whether to establish a connection with other agents to jointly process the order.

[0054] There are multiple agents in each organization, divided into salesmen and robots. A collaborative network will be formed between agents. Only agents that are connected in the network can establish connections to jointly process orders. During the operation of the system, only salesmen agents can actively initiate connections to other agents. The system defines that orders can be processed by more than two agents establishing connections and collaboration, and multiple agents establishing connections to process the same order are also allowed. At the same time, the collaborative relationships of the system operation are "human-machine collaboration" and "human-human collaboration".

[0055] (1) Inter-institutional order allocation strategy The platform chooses which institution to assign the order to first based on the institution's occupancy rate. For example, at a certain moment, an order of type ABCD arrives, and the difficulty value of each part is added to form a complete order A12B20C25D80. At this time, the occupancy rate of institution A is 30%, institution B is 50%, C is 40%, and D is 80%. The platform will assign the order to institution A. When institution A completes the order, the remaining BCD of the order are not completed. Institution A will then decide which institution to pass the order to based on the occupancy rates of institutions B, C, and D at this moment.

[0056] Assume that after institution A has processed the order, institution B has the lowest occupancy rate at this time, but it is possible that all robots in institution B are occupied. Although machines can only process orders with lower difficulty, machines do not consume additional costs like salesmen to process orders. At this moment, the unprocessed order is B20C25D80. Regardless of whether this order is assigned to institution B or institution C, it will be processed by its internal robots first. Although the overall occupancy rate of institution C is higher than that of institution B at this time, there may still be idle robots in institution C. The order allocation strategy needs to comprehensively consider the order difficulty, the occupancy rate of machines within the institution, and the occupancy rate of salesmen.

[0057] This embodiment takes the order "A12B40C20D87" as an example, and the specific process is as follows: When processing orders, priority is given to the part with difficulty 1, and the processing order is A12C20→B40D87; When the platform wants to process the A12C20 part, it will compare the occupancy ratios of the robots in the A and C organizations, and give priority to the organization with the lower occupancy ratio; If all robots in organizations A and C are occupied at this moment, then compare the occupancy ratio of salesmen in organizations A and C; In the extreme case, the occupancy rates of robots and salesmen in institutions A and C are both 100%. At this moment, we consider the B40D87 part to relieve the pressure of institutions A and C; In the more extreme case, if the occupancy rates of the four institutions ABCD are all 100%, the order will be assigned to the institution with the least "pressure" and wait for the assigned Agent to process it.

[0058] (2) Inter-institutional order allocation strategy After the order arrives at the agency, the agency will first obtain the part of the order that needs to be processed by itself, and then the specific processing process is as follows: If the difficulty is lower than the difficulty threshold that the robot can handle, the idle robots will be used first. If all robots are occupied, the most "idle" (with the least number of unprocessed tasks) agent in the organization will be queried to process the order.

[0059] If the difficulty of an order exceeds the difficulty threshold that the robot can handle, it will query the most "idle" salesperson within the organization and assign the order to that salesperson for processing.

[0060] Each time an organization allocates an order, it needs to update some of the status of the Agent within the organization (Agent occupancy rate, total organization occupancy rate, etc.). When the Agent within the organization completes processing the order, the Agent will return the order to the organization layer, which will then judge and pass it to the next organization to process the order.

[0061] (3) Human-machine collaboration / human-human collaboration strategy Initially, network connections are generated between agents within the organization based on the user's choice. For example, in the G (N, P) random network mode, assume that there is a 1 / 4 probability that any two agent nodes can be connected (dashed line connection). If 12 agents are preset at the beginning, then it is expected that there will be When a salesperson receives an order, the processing rules are as follows: If the order difficulty value is less than the difficulty threshold that the robot can handle, the salesperson can select other idle agents (including robots and salespersons) with whom he has a connection for collaborative processing.

[0062] If the order difficulty is greater than the difficulty threshold that the robot can handle, the salesperson can select other idle salespersons with whom he has a connection to collaborate on the processing.

[0063] When the order is processed to a remaining amount that is less than the difficulty threshold that the robot can handle, the salesperson can choose to collaborate with an idle robot to process the order.

[0064] If all other agents connected to the agent are occupied, the agent can only process the order alone. Of course, during the processing, the agent will constantly observe whether other agents connected to it are idle. If they are idle, it may establish a connection with them.

[0065] Agent collaboration can speed up processing, and two-person collaboration can even be faster than robots. However, robots do not consume additional costs to process orders. In addition, if the collaboration relationship is too complicated, it may even increase the waiting time for the next order.

[0066] After the agency has processed it, the order will be passed to the next agency for processing.

[0067] (4) Order processing time calculation rules When an order is generated, there will be a difficulty value. Orders with high difficulty can only be handled by sales staff, and the difficulty value corresponds to the amount of work required to complete the order.

[0068] All Agents have a work efficiency (eff) in their properties. eff is a positive integer. During the initial design, the system will calculate the average work efficiency of the robot selected by the user. robot_avg_efficacy and average work efficiency of salespersons people_avg_efficacy Normal distribution is used to generate the robot's work efficiency, and uniform distribution is used to generate the salesperson's work efficiency.

[0069] When the Agent processes an order, assuming that the difficulty value of the order is 35 and the Agent's work efficiency is 5, then the Agent needs 7 units of time to process the order; when the order difficulty is 32, the Agent also needs 7 units to process this problem. In order to facilitate the timing operation of the system, the Agent will no longer accept other orders for the remaining 0.6 units of time.

[0070] When it comes to Agent collaboration in processing orders, if Agent1 and Agent2 are collaborating to process an order with a difficulty of 90, where Agent1's work efficiency is 10 and Agent2's work efficiency is 6, then the time it takes for the two to collaborate in processing the order is Unit time.

[0071] System server architecture Figure 3 As shown, when processing orders, it is set that each organization occupies one thread, and the Agents within the organization are set to be performed serially. When each thread runs faster, the situation where all Agents run in parallel can be simulated.

[0072] (5) System performance calculation rules System performance reflects the working ability of the digital service system. In order to fit the actual scenario, in the digital service system, performance is defined as revenue minus cost. At the same time, in order to observe the system performance in detail, it cannot be limited to the organization and platform level. The value created by the Agent within the organization is the main source of system cost and revenue.

[0073] Each cycle of the robot consumes a certain amount of maintenance cost, and the robot can create value by processing orders. The calculation formula is: ; In the formula, The number of orders that the software robot participated in processing; Represents the total number of orders processed by all Agents involved in processing orders; Represents the total value that can be brought by processing orders of this difficulty.

[0074] For salesmen, there is a fixed basic salary in each cycle, and performance wages will be paid according to the salesmen's work performance. These two items are the main costs of the platform. Salesmen can also create value for the platform by processing orders. The calculation formula is: ; In the formula, The number of orders handled by the salesperson; Represents the total number of orders processed by all Agents involved in processing orders; Represents the total value that can be brought by processing orders of this difficulty.

[0075] Business staff salary The calculation formula is: ; In the formula, Represents the basic salary that the salesperson gets every cycle; It represents the mapping ratio of the value that orders of corresponding difficulty can bring into the salesperson's income.

[0076] For an organization, the cost is the maintenance fee of the robot per cycle and the salary of the salesperson. The income is the total value created by all the robots and salespeople within it multiplied by the ratio of the value created by the organization to its own income. This ratio is used to calculate the salary of the salesperson. value_ratio It should be high. Under normal circumstances, the organization will process all orders, so the total value created by all robots and salesmen in the organization = the sum of the difficulty of all orders received by the organization. The efficiency of the organization is the difference between its income and cost. It can be formally expressed as follows: Institutional costs The calculation formula is: ; In the formula, Represents the maintenance cost of the robot per cycle; Represents the salary of the salesperson per period.

[0077] Institutional income The calculation formula is: ; In the formula, The total value created by all robots and salespeople within the organization processing orders; Represents the mapping ratio of created value to the organization's own income, with a value greater than .

[0078] Institutional Effectiveness The calculation formula is: ; Calculating system performance from the perspective of the platform can help system operators regulate system parameters. After the salesperson has completed the business, the platform will update his or her performance and update some of the organization's data. Based on the system evaluation indicators (calculated by the difficulty of completing the task, the number of tasks, and customer satisfaction), the system hopes to eventually achieve self-regulation of the platform.

[0079] Platform costs The calculation formula is: ; Platform revenue The calculation formula is: ; In the formula, The total value created by processing orders for all institutions in the system; The mapping ratio of the representative value to the platform's own income, the value is greater than ; Customer satisfaction for completed orders.

[0080] Customer Satisfaction The calculation formula is: ; In the formula, The actual processing time of the order; The customer's expected processing time for their order; The average processing time for orders of the same difficulty in the past; It is the customer's psychological volatility, representing the different psychological states of different customers regarding the order completion time.

[0081] System performance The calculation formula is: .

[0082] Embodiment 2 The purpose of this embodiment is to provide a digital service market simulation system based on Python full-stack development. The goal of the digital service system simulation system is to realize a graphical system that is convenient for users to use. It requires simplicity, clarity, and beauty. At the same time, the system needs to achieve real-time transmission and display of data. Therefore, this system adopts the front-end and back-end separation framework of Python + Vue. The Python back-end runs on the cloud server and opens the program port to the outside world. The front-end runs locally, which is convenient for adjustment during development. Since the system involves a lot of data chart displays, the front-end integrates the Echarts framework. At the same time, Element-Plus is used to optimize the front-end page.

[0083] The above digital service market simulation system includes: A digital service market simulation system, comprising: An external demand environment module is configured to model the external demand environment in the digital service market, map the external demand environment into order states of different types and difficulties representing user demands, and set an order arrival strategy and an order difficulty generation strategy; A subject modeling module is configured to model the subject of the digital service system in the digital service market, wherein the subject includes a platform, an organization, and an execution agent, and form an entity class table of each subject; A rule modeling module configured to model order delivery rules between institutions in the digital service market and execution agent collaboration rules within the institutions; The simulation operation module is configured to configure the external demand environment, subject and rule parameters of the target digital service market based on the modeling results of the three parts, perform simulation and obtain simulation results.

[0084] Building and running a digital service market simulation system mainly involves the following steps: Step 1: Environment Setup In the environment configuration module, the data that needs to be displayed in real time, such as "order delivery" and "system performance", uses WebSocket technology for real-time interaction between front-end and back-end data. The user's one-way access request to the system uses the Flask framework for interaction between front-end and back-end data. The parameters that can be set in the system order environment are as follows: Order generation method: Use the selector to set the options to "Normal distribution" and "Uniform distribution".

[0085] Order Difficulty: Use the numeric input box to set the input (adjustment) to only positive integers, including the minimum and maximum values.

[0086] Order arrival rate: indicates the average number of orders arriving per unit time, set as an integer or decimal interval, such as [0.5,10].

[0087] Cycle duration: Use the numeric input box to set it to only positive integers, including the minimum and maximum values.

[0088] The environment design parameters are submitted to the backend " / envDesign" interface in the form of a form. The form needs to be verified by the frontend rules before submission.

[0089] Step 2: Main body setup The parameters that can be set by the subject in the system are as follows: Number of agents within the organization: including minimum, maximum and step size.

[0090] Human-machine ratio: includes minimum value, maximum value and step size.

[0091] Robot cycle maintenance cost: includes minimum value, maximum value and step length.

[0092] Salesperson basic salary: includes minimum value, maximum value and step size.

[0093] Salesperson performance: includes minimum value, maximum value and step size.

[0094] Average work efficiency of the robot: including minimum value, maximum value and step length.

[0095] Average work efficiency of salespersons: including minimum value, maximum value and step length.

[0096] Intranet Type: Use the selector for users to select.

[0097] Most of the system's main parameters are of numerical type, so they are displayed in the form of slider + data, which not only facilitates adjustment but also reduces input errors.

[0098] The main design parameters are submitted to the back-end " / agentDesign" interface in the form. The form needs to be verified by the front-end rules before submission.

[0099] After the user sets all the environment and subject parameters and submits them, the generated Agent can be previewed. By clicking the "Agent Preview" button on the "Subject Design" interface, the user can call the " / getAgent" interface on the backend and enter the Agent details page. This page uses a table to show the user all the Agents that have been designed and generated, including each Agent's name, type, affiliated organization, work efficiency, robot maintenance cost per cycle, salesperson's basic salary per cycle, and the connection relationship between Agents. This page allows users to use names to locate Agents through fuzzy queries. For example, if the query condition is "C", the results are "C_Robot_1, C_Robot_2, ..., C_People4", and users can filter Agent types (salesperson or robot).

[0100] Step 3: System Operation The backend logic of the system operation includes two modules: order delivery and human-machine collaboration, as follows: (1) Order delivery After the initial parameter settings are completed, the user can click to enter the operation interface. This interface is implemented using the relationship diagram in Echarts, which contains N institutional nodes. The operation interface includes the functions of system operation, pause, and continue. The system main interface also supports users to view the platform performance, institutional costs and institutional benefits, and the number of orders of different categories arriving at the system in real time.

[0101] (2) Human-machine collaboration In order to allow users to intuitively query the activities and data of the internal agents of the organization, the operation interface also supports users to click on the organization to enter the internal network diagram. In the network diagram, the dotted line between agents indicates that two agents can establish a collaborative relationship, and the actual line indicates that the agents are collaborating to process the same order. At the same time, the real-time cost, income, internal network type and agent occupancy rate of the organization will be displayed at the same time as the internal network diagram of the organization, and the description list in Element-Plus will be used for unified display. At the same time, when the user observes the network diagram, the real-time performance of the organization, the average performance of the agent, the performance of the robot and the performance of the salesperson are displayed. The first two are realized using line charts, and the latter two are displayed through bar charts.

[0102] The internal network of an organization can be set up in various types, such as Figure 4 As shown, the networks preset for human-computer collaboration include 5 regular networks, 2 random networks, 2 small-world networks, and 1 scale-free network. These networks are now introduced.

[0103] Isolated node network: Each agent in the network has no direct connection with other agents, cannot form a collaborative relationship with other agents, and can only process orders alone.

[0104] Globally coupled network: Each agent in the network has an association relationship with other agents and can form a collaborative relationship with any agent. The network type is a complete graph.

[0105] Star network: There is a key node in the star network. The Agent at this node has an association relationship with other Agents, but other Agents can only form a collaborative relationship with the Agent at the key node and cannot collaborate with other Agents.

[0106] One-dimensional ring: Agents form a ring network, and each agent can only form a cooperative relationship with two adjacent agents.

[0107] Two-dimensional lattice: In a two-dimensional lattice network, an agent can form an associated collaborative relationship with agents in the four directions of "up, down, left, and right". The two-dimensional lattice network requires that the number of agents is a perfect square number.

[0108] G(N,L) random network: N agent nodes are connected to each other through L randomly placed links. , initially L is set to ; G(N,P) random network: among N nodes, each pair of nodes is connected with probability P, where P is set to 0.25. .

[0109] WS small-world network: Consider a nearest neighbor coupled network with N nodes, which form a ring, where each node is connected to K / 2 nodes adjacent to it on the left and right, and K is an even number. The parameters satisfy N>>K>>ln(N)>>1. (K nearest neighbor rule network). Then reconnect each edge in the network randomly with probability p, that is, keep one end of the edge unchanged, and take the other end as a randomly selected node in the network. The small-world network stipulates that there will be no duplicate edges and self-loops in the network. Initially, K is set to 4 and p is set to 0.3.

[0110] NW small-world network: Similarly, in the K nearest neighbor rule network, an edge is added between a pair of randomly selected Agent nodes with probability p. The edge addition operation also ensures that there will be no duplicate edges or self-loops in the network. Initially, K is set to 4 and p is set to 0.3.

[0111] BA scale-free network: From a Each time a new node is introduced, existing nodes, that is, , a new node and an existing node Probability of connection With Node Degree is proportional, that is: After t steps, this algorithm produces a nodes, The network is initially set to have two nodes, and each time a new node is added, it is connected to the two existing nodes in the network according to the priority connection mechanism.

[0112] Step 4: System Output The system output part mainly includes three modules: main interface output, internal network diagram output and data visualization, as follows: (1) Main interface output During the operation of the system, orders will be continuously transferred between institutions. The system involves strong data interaction here. After the user clicks to run, the backend needs to continuously send data to the frontend, which is similar to a mechanism where the other party keeps talking on the phone. Therefore, the data interaction of the main interface uses WebSocket technology. When the user clicks to run, the system will first query whether the user's browser supports WebSocket. If it does, a WebSocket will be initialized. After the front-end WebSocket successfully establishes a connection with the back-end port 8765, a message with the content "begin" will be sent, indicating the start signal of the system operation. If the user's browser does not support WebSocket, a pop-up message will be used to inform the user.

[0113] In the Echarts relationship diagram, order delivery can be represented by links between nodes. In order to facilitate user observation and testing during development, the delivery of the same order will be marked with the same color, and animations will be added to indicate which institution is being delivered to which institution. The running effect is as follows: Figure 5 shown.

[0114] The system also supports users to view the platform performance, institutional costs and institutional benefits, and the number of order categories arriving at the system in real time during operation, using line charts, bar charts, and bar charts to display them respectively. These data will arrive when the backend uses WebSocket to send order delivery relationships. Users can click the data display button in the upper right corner to view these data. This function is implemented through the el-drawer drawer component of Element-Plus. In order to prevent the problem of different or delayed data display when opening the drawer multiple times, the data actively pushed by the backend each time will be saved in the front end.

[0115] (2) Output of internal network diagram of the organization The internal output results of the organization include network diagrams and some real-time operation data of the organization. During the operation of the system, the internal Agent of the organization continuously processes the orders that arrive at the organization. The data of the main interface is continuously pushed from the back end to the front end through the WebSocket connection. In order to save the cost of establishing connections between the front and back ends, the internal data of the organization is also transmitted through the WebSocket connection of the main interface and reaches the front end at the same time as the main interface data.

[0116] In order to intuitively represent the agent status, the network diagram can use different colors to indicate the idle / busy status of the agent, where blue / green indicates idle status, and the eye-catching red indicates that the agent is working. Figure 6 As shown, for the sake of system rigor and testing requirements, in some embodiments, the user can also point the mouse to the Agent icon, and the system will indicate the name of the Agent.

[0117] (3) Data analysis Set up the experimental analysis interface. After each round of operation, the system outputs the main data of this round of operation, so that users can compare the data results of different rounds more intuitively.

[0118] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of one or more computer-usable storage media (including but not limited to disk storage, CD - ROM , optical storage, etc.).

[0119] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0122] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.

Claims

1. A digital service market simulation method, characterized in that: The following steps are involved: Model the external demand environment in the digital service market, map the external demand environment into order states of different types and difficulties representing user needs, and set order arrival strategies and order difficulty generation strategies; Modeling the main body of the digital service system in the digital service market, which includes the platform, the organization and the execution agent, and forming an entity class table of each main body; Modeling the order routing rules between institutions in the digital service market and the coordination rules of execution agents within institutions; Based on the modeling results of the three parts, the external demand environment, subjects and rule parameters of the target digital service market are configured, simulation is carried out, and simulation results are obtained.

2. A digital service market simulation method as claimed in claim 1, characterized in that: The process of mapping the external demand environment into order states of different types and difficulties representing user needs includes constructing an order entity attribute table, which includes the type, name, pending queue, ratio of order value and order difficulty, agent that accepts the order, order status, order arrival time, order delivery connection, and upper and lower limits of order difficulty threshold.

3. A digital service market simulation method as claimed in claim 1, characterized in that: The process of setting the order difficulty generation strategy includes: the distribution mode of the user-provided order includes normal distribution and uniform distribution. In the case of normal distribution, multiple optional difficulty generation levels are provided to the user according to the length and overall difficulty of the order, and the order probability of each level is controlled according to the normal distribution point value; In the case of uniform distribution, users cannot choose the difficulty of generating orders, and the type and difficulty value of generated orders are uniform.

4. A digital service market simulation method as claimed in claim 1, characterized in that: The process of modeling the entities of the digital service system in the digital service market includes: The platform is used to coordinate and control the entire digital service system, receive orders from outside the digital service system, and assign the orders to different institutions for processing. At the same time, the platform calculates the total cost and total revenue and evaluates the overall performance; The organization is composed of internal salesmen and software robots, which are used to receive orders assigned by the platform and transfer orders between organizations; The execution agent includes a salesperson and a software robot. The salesperson is configured to handle orders of all difficulty levels, and the salesperson can create value by completing orders. The value created varies according to the difficulty, processing time and quantity of the completed orders. The software robot is configured to process orders with a difficulty level lower than a set level, but the order processing speed is higher than that of a salesperson, and the software robot does not consume additional costs when processing orders.

5. A digital service market simulation method as claimed in claim 1, characterized in that: The process of modeling the order delivery rules between institutions in the digital service market and the cooperation rules of the execution agents within the institutions includes: the platform is responsible for receiving orders from the outside and allocating them to institutions according to the set algorithm, while the overall performance of the platform reflects the quality of the service; Different orders are processed in parallel, and the same order is processed in serial; After receiving an order from the platform or other institutions, the institution selects an execution agent to process the order based on the institution's internal order allocation strategy. The execution agent has the right to decide whether to establish a connection with other execution agents to jointly process the order; Each execution agent forms a collaborative network. Only the execution agents that are connected in the collaborative network establish connections to jointly process orders, and only agents with the attribute of salesperson can actively initiate connections to other execution agents.

6. A digital service market simulation method as claimed in claim 5, characterized in that: The process of allocating it to institutions according to the set algorithm includes: the platform determines the institutions participating in the allocation according to the type of order, sorts the completion order of the institutions participating in the allocation according to the difficulty of the order, and then prioritizes the allocation of the order to the corresponding institution with the lowest occupancy rate based on the occupancy rate of the institution; if all software robots of the currently allocated institution are occupied, the order will be passed on to the institution whose software robots are not fully occupied according to the allocation order.

7. A digital service market simulation method as claimed in claim 5, characterized in that: The process of selecting an execution agent to process the order according to the internal order allocation strategy of the organization includes: if the difficulty of the order is less than the difficulty threshold that the software robot can process, the idle software robot is used first to process the order; if all the software robots are in the occupied state, the execution agent with the least number of unprocessed tasks in the organization is queried to process the order; If the difficulty of the order exceeds the difficulty threshold that the software robot can handle, the salesperson with the least number of unprocessed tasks within the organization will be queried, and the order will be assigned to that salesperson for processing.

8. A digital service market simulation method as claimed in claim 5, characterized in that: After the execution agents form a collaborative network, the rules for processing orders include: If the order difficulty value is less than the difficulty threshold that the software robot can handle, the salesperson selects other idle execution agents with whom he has a connection for collaborative processing; If the order difficulty is greater than the difficulty threshold that the software robot can handle, the salesperson will select other idle salespersons with whom he is connected to collaborate on the processing; If other execution agents connected to the execution agent are occupied, the execution agent can only process the order alone.

9. A digital service market simulation method as claimed in claim 5, characterized in that: When the execution agent processes an order, it is necessary to calculate the order processing time based on the difficulty value of the order and the work efficiency of the corresponding execution agent. If the difficulty value of the order and the work efficiency of the corresponding execution agent cannot be divided evenly, the order processing time is rounded up to calculate the order processing time. If multiple execution agents collaborate to process an order, the order processing time is calculated based on the difficulty value of the order and the sum of the work efficiency of each execution agent participating in the collaboration.

10. A digital service market simulation system, characterized in that: include: An external demand environment module is configured to model the external demand environment in the digital service market, map the external demand environment into order states of different types and difficulties representing user demands, and set an order arrival strategy and an order difficulty generation strategy; A subject modeling module is configured to model the subject of the digital service system in the digital service market, wherein the subject includes a platform, an organization, and an execution agent, and form an entity class table of each subject; A rule modeling module configured to model order delivery rules between institutions in the digital service market and execution agent collaboration rules within the institutions; The simulation operation module is configured to configure the external demand environment, subject and rule parameters of the target digital service market based on the modeling results of the three parts, perform simulation and obtain simulation results.

Images