Service request processing method and device, equipment and medium

Abstract

The invention discloses a service request processing method and device, equipment and a medium. The method comprises the following steps: acquiring a to-be-processed service request; inputting the to-be-processed service request into a first customer service robot, and processing the to-be-processed service request according to a workflow chart in the first customer service robot to obtain a corresponding target processing result; wherein the workflow chart comprises a first number of nodes; the first number of nodes are obtained by classification according to service functions. According to the technical scheme, classification is carried out according to the service functions to obtain the customer service robot formed by the corresponding nodes, unnecessary nodes are effectively prevented from being created, the complexity of the robot workflow chart is reduced, and therefore the time consumption of robot processing flow execution is reduced.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular, to a method, device, equipment and medium for processing service requests. Background Art

[0002] With the increasing development of artificial intelligence technology and the widespread application of artificial intelligence customer service robots, such as chatbots.

[0003] Currently, with the popularization of graphically constructing intelligent robot workflows, when multiple requirements and service data are constructed using general node classifications, only by finely classifying the nodes based on specific services and application scenarios can they be more accurately embedded in the service system. One of the key technologies to achieve these differential services is to summarize and organize the services and optimize the general node attributes for different scenarios.

[0004] For example, when identifying the user intention in a customer service robot that constructs a session workflow using general nodes, most current models require a model management node to control the process flow of other nodes. However, an increase in the number of steps in the flowchart made in this way means that the process is more complex and will also increase the response time. In an immediate response workflow, undoubtedly, the increase in response time cannot meet the requirement of fast response. Summary of the Invention

[0005] The present invention provides a method, device, equipment and medium for processing service requests. By classifying according to service functions to obtain a customer service robot composed of corresponding nodes, it effectively avoids creating unnecessary nodes, reduces the complexity of the robot workflow diagram, and thus reduces the execution time-consuming of the robot processing process.

[0006] According to one aspect of the present invention, there is provided a method for processing service requests, including:

[0007] Obtaining a service request to be processed;

[0008] Inputting the service request to be processed into a first customer service robot, and processing the service request to be processed according to the workflow diagram in the first customer service robot to obtain a corresponding target processing result; wherein, the workflow diagram includes a first number of nodes; the first number of nodes is obtained by classifying according to service functions.

[0009] According to another aspect of the present invention, there is provided a device for processing service requests, including:

[0010] A request acquisition module, configured to obtain a service request to be processed;

[0011] A request processing module, configured to input the to-be-processed service request into a first customer service robot, and process the to-be-processed service request according to a work flow chart in the first customer service robot to obtain a corresponding target processing result; wherein, the work flow chart includes a first number of nodes; the first number of nodes are classified according to service functions.

[0012] According to another aspect of the present invention, there is provided an electronic device, the electronic device includes:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the service request processing method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the service request processing method according to any embodiment of the present invention when executed.

[0017] The technical solution of the embodiment of the present invention is to obtain a to-be-processed service request; input the to-be-processed service request into a first customer service robot, and process the to-be-processed service request according to a work flow chart in the first customer service robot to obtain a corresponding target processing result; wherein, the work flow chart includes a first number of nodes; the first number of nodes are classified according to service functions. This technical solution effectively avoids creating unnecessary nodes by classifying the corresponding nodes according to service functions, reduces the complexity of the robot's work flow chart, and thus reduces the execution time of the robot's processing process.

[0018] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a flowchart of a service request processing method provided according to Embodiment 1 of the present invention;

[0021] Figure 2 It is a flowchart of a service request processing method provided according to Embodiment 2 of the present invention;

[0022] Figure 3 It is a schematic structural diagram of a service request processing device provided according to Embodiment 3 of the present invention;

[0023] Figure 4 It is a schematic structural diagram of an electronic device provided according to Embodiment 4 of the present invention. Detailed implementation manners

[0024] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0025] It should be noted that the terms "first", "second", and "target" in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0026] Embodiment 1

[0027] Figure 1 It is a flowchart of a service request processing method provided according to Embodiment 1 of the present invention. This embodiment is applicable to the situation where a customer service robot processes a service request. This method can be executed by a service request processing device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device with data processing capabilities. As Figure 1 shown, the method includes:

[0028] The technical solution in this embodiment can be applied to the business scenarios in the automotive finance field. A customer service robot can be pre-constructed according to the knowledge base in the automotive finance field to process corresponding business requests.

[0029] S110. Obtain the business request to be processed.

[0030] Among them, the business request to be processed can be considered as a business request that needs to be processed. The business request to be processed in this embodiment can be a business request in the automotive finance field. Exemplarily, the business request to be processed in this embodiment can be a business request related to the purchase, financing, insurance, maintenance, and related services of automobiles.

[0031] The system control platform in this embodiment can obtain the business request to be processed related to the purchase, financing, insurance, maintenance, and related services of automobiles input by the caller.

[0032] S120. Input the business request to be processed into the first customer service robot, and process the business request to be processed according to the workflow diagram in the first customer service robot to obtain the corresponding target processing result.

[0033] Among them, the workflow diagram includes a first number of nodes; the first number of nodes is obtained by classifying according to business functions. The first customer service robot can be considered as the main customer service robot. In this embodiment, the system control platform can include the main customer service robot, and other standby tool robots can be nested and called in the main customer service robot, so that the first customer service robot can call other customer service robots through the robot call nodes, thereby completing the processing of different business requests. The first number can be the number of nodes included in the workflow diagram of the first customer service robot. In this embodiment, the number of nodes for constructing the first customer service robot can be determined according to actual needs. Exemplarily, the number of nodes of the first customer service robot can be 20, can be 30, or the specific number of nodes can be set according to actual business needs. This embodiment does not limit this. The first customer service robot in this embodiment can be pre-constructed. In this embodiment, a first number of nodes can be obtained by classifying multiple nodes in terms of business function dimensions, and then the workflow diagram of the first customer service robot can be constructed graphically according to the first number of nodes. The target processing result can be understood as the processing result obtained by processing the business request to be processed in the first customer service robot. In this embodiment, the business request to be processed can be input into the first customer service robot, and then the business request to be processed can be processed sequentially according to each business node in the workflow diagram of the first customer service robot, so that the processed result, that is, the target processing result, can be obtained.

[0034] In this embodiment, optionally, the workflow diagram includes a preprocessing layer, a logic processing layer, and a data output layer; both the preprocessing layer and the data output layer include at least one node; the logic processing layer includes a second number of nodes.

[0035] Among them, the second number can be the number of nodes included in the logic processing layer. The second number in this embodiment is less than the first number. Exemplarily, if the first number is 20, the second number can be 15, or can be 12, and can also be set according to actual requirements.

[0036] The workflow diagram of the first customer service robot in this embodiment can be divided into three layers, namely a preprocessing layer, a logic processing layer, and a data output layer. Among them, both the preprocessing layer and the data output layer have at least one node, and the logic processing layer can include a second number of nodes. The preprocessing layer in this embodiment can also include a start node. The preprocessing layer in this embodiment can be composed of a start node and an opening statement node, and its function can be to be responsible for verifying external parameters and controlling the flowchart direction through branch conditions. The logic processing layer in this embodiment can include, but is not limited to, a direct reply node, a knowledge base query node, an intent recognition node, a rewrite node, a speech recognition node, a speech generation node, a robot call node, an LLM node, a code execution node, a data processing node, a network search node, and a service call node, etc. The function of its logic processing layer is completed by the combination of the included nodes to interact with the knowledge base, AI model, third-party API, and internal services. In this embodiment, due to the addition of a certain redundancy in the functions of each node, the number of nodes and the data flow overhead of the nodes are reduced; and because there are a wide variety of question types included in the customer's requests to be processed, in order to improve the answer accuracy rate, the LLM node and the knowledge base node can support multi-channel recall and call the re-ranking model. In the workflow of the existing robot, as the workflow increases, the flowchart will become more and more complex. Therefore, this application can reduce the complexity of the workflow diagram through the robot call node. The data output layer can include an LLM node for formatting and returning the answer given by the customer service robot to the caller.

[0037] In this embodiment, through such a setting, the function of the node can be adjusted, the number of nodes can be simplified, so that the workflow diagram of the obtained first customer service robot is clearer, thereby improving the response efficiency of the customer service robot.

[0038] It can be understood that in this embodiment, when graphically constructing the workflow diagram of the first customer service robot, based on the knowledge and business scenarios in the automotive finance field, the function range of the node is expanded, thereby reducing the complexity of the workload flowchart of the first customer service robot, that is, reducing the number of nodes of the first customer service robot, and professional data references can also be added to the attributes of each node, thereby improving the operation efficiency of the first customer service robot when processing business requests.

[0039] In the technical solution of the embodiment of the present invention, a to-be-processed service request is obtained; the to-be-processed service request is input into a first customer service robot, and the to-be-processed service request is processed according to the workflow diagram in the first customer service robot to obtain a corresponding target processing result; wherein, the workflow diagram includes a first number of nodes; the first number of nodes are obtained by classifying according to service functions. In this technical solution, a customer service robot composed of corresponding nodes obtained by classifying according to service functions effectively avoids creating unnecessary nodes, reduces the complexity of the robot's workflow diagram, and thus reduces the execution time of the robot's processing process.

[0040] Embodiment Two

[0041] Figure 2 It is a flowchart of a service request processing method provided according to Embodiment Two of the present invention, and this embodiment is optimized based on the above embodiment. The specific optimization is as follows: processing the to-be-processed service request according to the workflow diagram in the first customer service robot to obtain a corresponding target processing result, including: inputting the to-be-processed service request into the preprocessing layer of the workflow diagram in the first customer service robot to perform judgment and analysis on the to-be-processed service through the opening statement node in the preprocessing layer to obtain a corresponding target processing branch; sequentially processing the target processing branch through a second number of nodes in the logical processing layer to obtain at least one processing result; performing fusion processing on at least one processing result through the data output layer and outputting the target processing result. As Figure 2 shown, the method includes:

[0042] S210. Obtain a to-be-processed service request.

[0043] Wherein, the workflow diagram includes a first number of nodes; the first number of nodes are obtained by classifying according to service functions. In this embodiment, the workflow diagram of the first customer service robot includes a preprocessing layer, a logical processing layer, and a data output layer; both the preprocessing layer and the data output layer include at least one node; the logical processing layer includes a second number of nodes.

[0044] S220. Input the to-be-processed service request into the preprocessing layer of the workflow diagram in the first customer service robot to perform judgment and analysis on the to-be-processed service through the opening statement node in the preprocessing layer to obtain a corresponding target processing branch.

[0045] Among them, the opening statement node can be a node included in the preprocessing layer. In this embodiment, the opening statement node has built-in branch judgment, and there is no need to separately create a conditional judgment branch as a node. The function of the opening statement node in this embodiment is to be responsible for verifying the parameters included in the business request to be processed, and controlling the flow direction of the workflow diagram through branch conditions, so as to continue to perform corresponding analysis and processing through each node in the logic processing layer. The target processing branch can be understood as the processing branch obtained after the preprocessing layer makes a preliminary analysis and judgment on the business request to be processed.

[0046] Furthermore, in this embodiment, if there is only one node with an output result, there will be no built-in judgment branch in the node; if there are nodes with two output results, a judgment branch can be built in, thereby reducing the judgment nodes in the workflow diagram.

[0047] In this embodiment, the business request to be processed can be input into the preprocessing layer of the workflow diagram in the first customer service robot, so as to perform parameter verification on the business to be processed through the opening statement stage included in the preprocessing layer and determine the corresponding target processing branch through the judgment analysis of branch conditions, thereby controlling the flow direction of the workflow diagram.

[0048] In this embodiment, optionally, analyzing the business to be processed through the opening statement node in the preprocessing layer to obtain the corresponding target processing branch includes: determining the corresponding target processing branch by matching the business scenario in the business request to be processed through the opening statement node in the preprocessing layer in a regular matching manner.

[0049] Among them, regular matching is a fixed matching method using pre-configured for business scenarios. In this embodiment, the opening statement node in the preprocessing layer can pre-define a set of regular expressions according to different business scenarios in advance. Each regular expression corresponds to a specific business scenario or processing branch, and then the opening statement text is extracted from the business request to be processed; among them, the opening statement text is usually a descriptive text in the request that can indicate the business scenario; then the extracted opening statement text can be matched one by one with the pre-defined regular expression set, and according to the matching result, the processing branch corresponding to the regular expression that matches the opening statement text successfully is determined, that is, the target processing branch. In this embodiment, if multiple regular expressions match successfully, a priority rule can be designed or the most specific matching item can be selected to determine the final processing branch.

[0050] In this embodiment, a built-in branch judgment is provided in the opening statement node. Without passing through the large model processing, a regular matching method is used to preliminarily analyze the service request to be processed. Exemplarily, some fixed phrases can be configured through regular matching. When it is detected that the question contained in the service request to be processed issued by the user is "Who are you", a corresponding answer can be given through the pre-set fixed phrases. For example, the corresponding answer can be "I am your assistant, dedicated to answering your questions."

[0051] In this embodiment, through such a setting, by using the fixed phrases pre-set in the opening statement node, the response efficiency of the customer service robot is improved, and the cumbersome process of processing based on other large models is also avoided.

[0052] S230. Sequentially process the target processing branch through the second number of nodes in the logic processing layer to obtain at least one processing result.

[0053] Among them, the second number of nodes may include knowledge base query, intent recognition, and LLM nodes, etc. In this embodiment, for the knowledge base query, intent recognition, and LLM nodes in the logic processing layer, a single node is added with the function of calling multiple models and querying multiple data sources.

[0054] In the process of processing the service request to be processed in this embodiment, multiple tools with the same function may be called for different processing, so as to obtain multiple processing results. Exemplarily, if the service request to be processed is a query service request, then the knowledge base node in the logic processing layer can be used to query multiple data sources, such as network data source query, third-party search query, and document search query, etc., so as to obtain multiple data query results, and these multiple data query results are all used as processing results.

[0055] It can be understood that for each node in the second number of nodes in this embodiment, there is a corresponding processing method or processing flow. Specifically, in this embodiment, the target processing branch can be input into the starting node of the logic processing layer, and according to the preset processing flow, the processing results are sequentially passed to the next node for processing. Each node operates on the input data according to its own processing logic and outputs the processing result.

[0056] In this embodiment, optionally, at least one robot call node is included in the second number of nodes; correspondingly, sequentially processing the target processing branch through the second number of nodes in the logic processing layer to obtain at least one processing result includes: through the robot call node included in the logic processing layer, calling at least one second customer service robot according to the target processing branch for corresponding service processing, and outputting at least one processing result.

[0057] Among them, the robot call node can be used to call multiple tool robots. The second customer service robot can be regarded as a tool robot. In this embodiment, one tool robot can be called through the robot call node, and two or more tool robots can also be called simultaneously, which can be called according to the actual request.

[0058] In this embodiment, different tool robots can correspond to different functions. Exemplarily, tool robot A can be a robot with a local special search function, tool robot B can be a robot with a polishing function, and tool robot C can be a robot with a text writing function.

[0059] In this embodiment, the first customer service robot can call the second customer service robot through the robot call node for corresponding business processing. It can be understood that the first customer service robot is the main customer service robot, and the second customer service robot can be regarded as a tool robot for assisting the main customer service robot. Therefore, in this embodiment, the first customer service robot can call the corresponding second customer service robot through the robot call node.

[0060] In this embodiment, through the robot call node included in the logic processing layer of the first customer service robot, one or more second customer service robots are called according to the business functions required in the target processing branch for corresponding business processing, so as to output at least one corresponding processing result.

[0061] In this embodiment, through such a setting, with just one robot call node, the processing of different business functions can be achieved, simplifying the workflow nodes of the first customer service robot.

[0062] S240. Perform fusion processing on at least one processing result through the data output layer, and output the target processing result.

[0063] Among them, the fusion processing can be the processing of data fusion of multiple processing results. In this embodiment, at least one processing result can be processed through the data output layer for data fusion to form a complete and comprehensive result, and the finally formed result is used as the target processing result and output.

[0064] In this embodiment, optionally, at least one knowledge base query node is included in the second quantity of nodes; information about vehicle configurations, vehicle sales locations, and vehicle activities is pre-configured in the knowledge base query node.

[0065] In this embodiment, when constructing the workflow diagram of the first customer service robot, it is first necessary to create a knowledge base in the automotive finance field. By obtaining corresponding automotive data information from various official automotive websites and integrating the book data to form information such as vehicle configurations, sales stores, and recent activities, these information are pre-configured in the knowledge base nodes. In this embodiment, the knowledge base of the knowledge base query node can also be updated regularly. Specifically, in this embodiment, the integrated information can be formed into corresponding documents and stored in the knowledge base for easy query by the database. For example, when the user asks about the store information of a certain type of vehicle, the knowledge base query node will find the detailed information of the corresponding vehicle store from the document and reply to the user.

[0066] With such a setting in this embodiment, the accuracy of knowledge base query is improved, enabling users to receive satisfactory responses and enhancing the user experience.

[0067] In this embodiment, optionally, it further includes: obtaining the log records and user feedback information of the first customer service robot; optimizing the workflow diagram in the first customer service robot based on the log records and user feedback information.

[0068] Among them, the log records can record the actual running data of the workflow diagram of the first customer service robot. The user feedback information can be obtained through dedicated feedback channels. For example, the user feedback information includes but is not limited to feedback information obtained through channels such as the customer service chat window, online questionnaires, user satisfaction ratings, and social media comments.

[0069] The system control platform in this embodiment can also be configured with a log and marking feedback function to obtain the log records and user feedback information of the first customer service robot, thereby continuously optimizing and adjusting the workflow diagram of the first customer service robot based on the log records and user feedback information, and assisting in improving the robot process.

[0070] With such a setting in this embodiment, the workflow diagram of the first customer service robot can be optimized and adjusted by combining the actual running data of the first customer service robot and the user feedback information, comprehensively understanding the running situation of the customer service robot and the user needs, and improving the service quality and efficiency of the first customer service robot.

[0071] The technical solution of the embodiment of this application simplifies the workflow diagram of the main customer service robot. The nodes can be classified according to the dimension of business functions, thereby simplifying the nodes of the workflow diagram of the first customer service robot. For example, originally, the first customer service robot required a workflow diagram with 200 nodes to process corresponding business processes. Through the classification of nodes and the adjustment of the node function scope, the current first customer service robot only needs 20 nodes to achieve the business processes that were originally achieved by 200 nodes.

[0072] In the technical solution of the embodiment of the present invention, a to-be-processed service request is obtained; the to-be-processed service request is input into the preprocessing layer of the workflow in the first customer service robot, so as to judge and analyze the to-be-processed service through the opening statement node in the preprocessing layer, and obtain a corresponding target processing branch; the target processing branch is sequentially processed through the second number of nodes in the logic processing layer to obtain at least one processing result; at least one processing result is subjected to fusion processing through the data output layer to output a target processing result. Among them, the workflow includes a first number of nodes; the first number of nodes are obtained by classification according to service functions. In this technical solution, a customer service robot composed of corresponding nodes obtained by classification according to service functions effectively avoids creating unnecessary nodes, reduces the complexity of the robot's workflow, and thus reduces the execution time of the robot's processing process.

[0073] Embodiment III

[0074] Figure 3 It is a schematic structural diagram of a service request processing device provided according to Embodiment III of the present invention. As Figure 3 shown, the device includes:

[0075] A request acquisition module 310, configured to acquire a to-be-processed service request;

[0076] A request processing module 320, configured to input the to-be-processed service request into the first customer service robot, and process the to-be-processed service request according to the workflow in the first customer service robot to obtain a corresponding target processing result; among them, the workflow includes a first number of nodes; the first number of nodes are obtained by classification according to service functions.

[0077] Optionally, the workflow includes a preprocessing layer, a logic processing layer, and a data output layer; both the preprocessing layer and the data output layer include at least one node; the logic processing layer includes a second number of nodes.

[0078] Optionally, the request processing module 320 includes:

[0079] A target processing branch acquisition unit, configured to input the to-be-processed service request into the preprocessing layer of the workflow in the first customer service robot, so as to judge and analyze the to-be-processed service through the opening statement node in the preprocessing layer, and obtain a corresponding target processing branch;

[0080] A processing result acquisition unit, configured to sequentially process the target processing branch through the second number of nodes in the logic processing layer to obtain at least one processing result;

[0081] A target processing result output unit, configured to perform fusion processing on at least one processing result through the data output layer and output a target processing result.

[0082] Optionally, at least one of the second quantity of nodes includes a robot call node;

[0083] Correspondingly, the processing result obtaining unit is specifically configured to:

[0084] Through the robot call node included in the logic processing layer, at least one second customer service robot is called according to the target processing branch to perform corresponding service processing, and at least one processing result is output.

[0085] Optionally, at least one of the second quantity of nodes includes a knowledge base query node; information about vehicle configurations, vehicle sales locations, and vehicle activities is pre-configured in the knowledge base query node.

[0086] Optionally, the target processing branch obtaining unit is specifically configured to:

[0087] Through the opening statement node in the preprocessing layer, the business scenario in the to-be-processed service request is determined in a regular matching manner to obtain the corresponding target processing branch.

[0088] Optionally, it further includes an optimization module, which is configured to obtain the log records and user feedback information of the first customer service robot; optimize the workflow diagram in the first customer service robot according to the log records and user feedback information.

[0089] The service request processing device provided by an embodiment of the present invention can execute the service request processing method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0090] Embodiment 4

[0091] Figure 4 It is a schematic structural diagram of an electronic device provided according to Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0092] As Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0093] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0094] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the service request processing method.

[0095] In some embodiments, the service request processing method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the service request processing method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the service request processing method in any other appropriate manner (e.g., by means of firmware).

[0096] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0097] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0098] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0100] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0101] A computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0102] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0103] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for processing a business request, characterized in that: include: Get pending business requests; The pending business request is input into the first customer service robot, and the pending business request is processed according to the workflow diagram in the first customer service robot to obtain the corresponding target processing result; wherein the workflow diagram includes a first number of nodes; the first number of nodes are classified according to business functions.

2. The method according to claim 1, characterized in that The workflow diagram includes a preprocessing layer, a logic processing layer and a data output layer; the preprocessing layer and the data output layer each include at least one node; the logic processing layer includes a second number of nodes.

3. The method according to claim 2, characterized in that Processing the pending business request according to the workflow diagram in the first customer service robot to obtain a corresponding target processing result includes: Input the pending business request into the preprocessing layer of the workflow diagram in the first customer service robot, so as to judge and analyze the pending business through the opening speech node in the preprocessing layer to obtain the corresponding target processing branch; Processing the target processing branch in sequence through the second number of nodes in the logic processing layer to obtain at least one processing result; The at least one processing result is fused through the data output layer to output a target processing result.

4. The method according to claim 3, characterized in that The second number of nodes includes at least a robot calling node; Accordingly, the target processing branch is processed in sequence through the second number of nodes in the logic processing layer to obtain at least one processing result, including: Through the robot calling node included in the logic processing layer, at least one second customer service robot is called according to the target processing branch to perform corresponding business processing and output at least one processing result.

5. The method according to claim 3, characterized in that: The second number of nodes at least includes a knowledge base query node; the knowledge base query node is pre-configured with information about automobile configuration, automobile sales location and automobile activities.

6. The method according to claim 3, characterized in that The business to be processed is analyzed through the opening remark node in the preprocessing layer to obtain the corresponding target processing branch, including: The corresponding target processing branch is determined by the opening remark node in the preprocessing layer according to the regular matching method for the business scenario in the to-be-processed business request.

7. The method according to claim 1, characterized in that Also includes: Obtaining log records and user feedback information of the first customer service robot; The workflow diagram in the first customer service robot is optimized according to the log records and the user feedback information.

8. A service request processing device, characterized in that: include: A request acquisition module is used to obtain pending business requests; A request processing module is used to input the pending business request into the first customer service robot, and process the pending business request according to the workflow diagram in the first customer service robot to obtain the corresponding target processing result; wherein, the workflow diagram includes a first number of nodes; the first number of nodes are classified according to business functions.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the service request processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the service request processing method according to any one of claims 1 to 7 when executed.

Images