Request processing method and apparatus, device, and storage medium

Abstract

Embodiments of the present disclosure relate to a request processing method and apparatus, a device and a storage medium. The provided method comprises: receiving, by a target application, a target request to be processed, the target application being associated with a plurality of processing entities; in response to the target request being provided to a first processing entity among the plurality of processing entities, using a first model to generate evaluation information corresponding to the target request, the evaluation information indicating the degree of matching between a first group of processing entities associated with the first processing entity and the target request; and in response to the evaluation information satisfying a preset condition, using a second model to determine a first jump policy associated with the first processing entity. In this way, the embodiments of the present disclosure can use a hybrid model to determine a jump policy of a processing entity (e.g., a bot or an intelligent agent) in an application, thereby improving the request processing efficiency.

Description

Request processing methods, apparatus, devices and storage media

[0001] This application claims priority to Chinese Patent Application No. 202410789249.9, filed on June 18, 2024, entitled "Request Processing Method, Apparatus, Device and Storage Medium", the entire contents of which are incorporated herein by reference. Technical Field

[0002] The exemplary embodiments disclosed herein relate generally to the field of computers, and more particularly to request processing methods, apparatus, devices, and computer-readable storage media. Background Technology

[0003] With the development of computer technology, people can create and publish various types of applications through various platforms. For example, with the development of machine learning technology, people can quickly create applications by configuring application parameters, such as the models used by the application and available plugins. Summary of the Invention

[0004] In a first aspect of this disclosure, a request processing method is provided. The method includes: receiving a target request to be processed by a target application, the target application being associated with a plurality of processing entities; in response to the target request being provided to a first processing entity among the plurality of processing entities, generating evaluation information corresponding to the target request using a first model, the evaluation information indicating the degree of matching between a first group of processing entities associated with the first processing entity and the target request; and in response to the evaluation information satisfying preset conditions, determining a first redirection strategy associated with the first processing entity using a second model.

[0005] In a second aspect of this disclosure, a request processing apparatus is provided. The apparatus includes: a receiving module configured to receive a target request to be processed by a target application, the target application being associated with a plurality of processing entities; a generating module configured to, in response to the target request being provided to a first processing entity among the plurality of processing entities, generate evaluation information corresponding to the target request using a first model, the evaluation information indicating the degree of matching between a first group of processing entities associated with the first processing entity and the target request; and a determining module configured to, in response to the evaluation information satisfying preset conditions, determine a first redirection strategy associated with the first processing entity using a second model.

[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product includes computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method of the first aspect.

[0009] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0011] Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure may be implemented;

[0012] Figure 2 illustrates a flowchart of an example process for request processing according to some embodiments of the present disclosure;

[0013] Figure 3A illustrates an example framework of a request processing system according to some embodiments of the present disclosure;

[0014] Figure 3B illustrates an example framework of a strategy determination unit according to some embodiments of the present disclosure;

[0015] Figure 4 shows a schematic structural block diagram of an example request processing apparatus according to some embodiments of the present disclosure;

[0016] Figure 5 shows a block diagram of an electronic device capable of implementing several embodiments of the present disclosure. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0019] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0020] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0021] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0022] Traditionally, users can quickly create applications, such as bots, by configuring the models, plugins, and other elements used by the application. However, some applications may include multiple processing entities (e.g., sub-bots or agents). Therefore, managing the transitions between such processing entities has become a key concern.

[0023] Embodiments of this disclosure propose a request processing scheme. According to this scheme, a target application may receive a target request to be processed, and the target application is associated with multiple processing entities. Further, in response to the target request being provided to a first processing entity among the multiple processing entities, an evaluation information corresponding to the target request can be generated using a first model. The evaluation information indicates the degree of matching between a first group of processing entities associated with the first processing entity and the target request. If the matching is low, a first redirection strategy associated with the first processing entity can be determined using a second model in response to the evaluation information meeting preset conditions.

[0024] In this way, embodiments of the present disclosure can utilize hybrid models (e.g., models with different processing capabilities) to determine the jump strategy for in-application processing entities (e.g., bots or agents), thereby improving the efficiency of request processing.

[0025] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0026] Example Environment

[0027] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, the example environment 100 may include an electronic device 110.

[0028] In this example environment 100, electronic device 110 can run an application 120 that supports user interface interaction. Application 120 can be any suitable type of application for user interface interaction, and examples may include, but are not limited to, applications for development or other suitable applications that support application development. User 140 can interact with application 120 via electronic device 110 and / or its attached devices.

[0029] In environment 100 of Figure 1, if application 120 is active, electronic device 110 can present interface 150 through application 120.

[0030] In some embodiments, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0031] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 that support virtual scenarios in electronic devices 110.

[0032] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and electronic device 110 can achieve signaling interaction through the communication connection between them.

[0033] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0034] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.

[0035] Example application creation process

[0036] Figure 2 illustrates a flowchart of an example request processing procedure 200 according to some embodiments of the present disclosure. Procedure 200 may be implemented at electronic device 110 and / or server 130. Procedure 200 will now be described with reference to Figure 1.

[0037] In box 210, the target application receives the target request to be processed, and the target application is associated with multiple processing entities.

[0038] In some embodiments, developers may create applications based on multiple processing entities. Such processing entities may include existing applications (e.g., bots) or agents.

[0039] Figure 3A illustrates an example framework of a request processing system 300A according to some embodiments of the present disclosure. This processing system 300A describes the request processing process using an intelligent agent as the processing entity. It should be understood that the intelligent agent mentioned in the following embodiments can also be replaced by a processing entity such as a bot.

[0040] As an example, the application can receive a target request from user 302 in environment 310. As an example, user 302 can send the target request by interacting with the graphical interface provided by the target application. For example, user 302 can send a query message via a session window provided by the target application.

[0041] In box 220, in response to a target request being provided to a first processing entity among a plurality of processing entities, an evaluation information corresponding to the target request is generated using a first model. The evaluation information indicates the degree of matching between a first group of processing entities associated with the first processing entity and the target request.

[0042] The agent 320 shown in Figure 3A is used as an example of the first processing entity. As shown in Figure 3A, the agent 320 may be configured with an agent hook 312 to use the first model 324 to determine the routing strategy.

[0043] In some embodiments, agent hook 312 may be triggered before agent 320 processes the target request to determine whether agent 320 should continue to process the request or whether it is necessary to jump to another agent in the target application to process the request.

[0044] As shown in Figure 3A, agent 320 can initiate a request to first model 324. Specifically, the input information 322 of first model 324 can indicate the target request to be processed (e.g., a query message input by user 302), context information, and candidate agents.

[0045] Specifically, such contextual information may include, for example, the user 320's historical dialogue information with the target application. Such candidate agents may include a set of associated agents linked to agent 320, that is, one or more other agents to which agent 320 is allowed to jump. In some embodiments, candidate agents may also include agent 320 itself.

[0046] In some embodiments, the first model 324 can generate evaluation information 326 based on the input information 322. Such a first model 324 can be implemented using an appropriate machine learning model. As an example, the first model 324 can, for instance, have a relatively small model size and a fast processing speed. For example, the first model 324 can be implemented as an intent classification model.

[0047] As shown in Figure 3A, evaluation information 326 can indicate the degree of matching between one or more agents (i.e., the first set of processing entities) associated with agent 320 and the request to be processed. Such a degree of matching can be represented, for example, by a confidence score to indicate the confidence level of the intent corresponding to different agents.

[0048] Referring again to Figure 2, in box 230, in response to the evaluation information meeting the preset conditions, the second model is used to determine the first jump strategy associated with the first processing entity.

[0049] Referring again to Figure 3A, the evaluation information 326 may be further provided to the policy determination unit 328, for example. In some embodiments, if the policy determination unit 328 determines that the evaluation information 326 does not meet preset conditions, the policy determination unit 328 may determine a jump policy based on the evaluation information 326. For example, if the policy determination unit 328 determines based on the evaluation information 326 that the target request corresponds to a clear intent, the policy determination unit 328 may determine the jump policy of the agent 320 based on the evaluation information 326.

[0050] Specifically, when the number of agents whose matching degree is greater than a first threshold (e.g., a high threshold) as indicated by evaluation information 326 is less than a preset number, the policy determination unit 328 can determine that the target request corresponds to a relatively clear intent. Further, the policy determination unit 328 can select the agent with the highest matching degree based on the evaluation information 326 to determine the jumping strategy of agent 320.

[0051] For example, if the agent with the highest matching degree is agent 320 itself, the target application can determine that agent 320 should continue to handle the request. Conversely, if the agent with the highest matching degree is another agent, the target application can determine that it needs to switch to that other agent to handle the request.

[0052] Conversely, if the policy determination unit 328 determines that the evaluation information 326 meets the preset conditions, the target application can further utilize the second model to determine the jumping strategy of the agent 320. As shown in Figure 3A, if the policy determination unit 328 determines based on the evaluation information 326 that there is no matching agent or that intent disambiguation is required, the target application can utilize the planner 314 of the agent 320 to call the second model to determine the jumping strategy of the agent 320.

[0053] In some embodiments, the second model may be implemented, for example, based on an appropriate machine learning model. Compared to the first model 324, the second model may, for example, have a relatively large model size and can handle more complex scenarios. For example, the second model may be implemented as a language model.

[0054] The specific determination process of the policy determination unit 328 will be further described below with reference to Figure 3B. As shown in Figure 3B, in the processing stage 332, the policy determination unit 328 can divide each agent into multiple sets based on the matching degree of each agent indicated by the evaluation information 326. For example, the first set may include agents with a matching degree greater than a high threshold, the second set may include agents with a matching degree greater than a low threshold and less than or equal to the high threshold, and the third set may include agents with a matching degree less than or equal to the low threshold.

[0055] In some embodiments, the policy determination unit 328 can determine the number of agents in the first set. If the number is greater than a preset number, the policy determination unit 328 can determine that the evaluation information 326 meets the preset conditions and can trigger the second model to determine the jump policy. For example, if the number of agents in the first set is greater than one, the policy determination unit 328 can determine that further elimination of intent ambiguity is needed.

[0056] As another example, if the first set does not contain any agents, the policy determination unit 328 can determine that the evaluation information 326 meets the preset conditions and can trigger the second model to determine the jump policy.

[0057] In some embodiments, the target application may initiate a request to the second model and provide corresponding input information. Such input information may, for example, indicate the target request to be processed, the associated context, and one or more candidate agents (i.e., the second set of processing entities) associated with agent 320.

[0058] In some embodiments, the candidate agents to be processed by the second model may be the same as those processed by the first model, and may also include all agents that agent 320 can jump to.

[0059] However, in some scenarios, the target application may involve a large number of agents. The input of the second model may be constrained to accept information from all candidate agents, or the second model may take a long time to process a large number of candidate agents.

[0060] In some embodiments, the candidate agents processed by the second model may be one or more associated agents determined based on the evaluation information 326. For example, the candidate agents indicated by the input information provided to the second model may include agents from a first set and a second set determined based on the evaluation information 326, that is, one or more agents with a matching degree greater than a low threshold.

[0061] In this way, the embodiments of this disclosure can further reduce the complexity of the processing of the second model, thereby improving the efficiency of determining the jump strategy.

[0062] In some embodiments, to further improve the processing efficiency of the second model, if the number of agents in the first set and the second set is greater than a preset number, the target application may further select a preset number of agents from the first set and the second set based on the matching degree. For example, the target application may select the K agents with the highest matching degree based on the matching degree for the second model to process.

[0063] Conversely, if the number of agents in the first set and the second set is less than or equal to a preset number, the target application provides all agents in the first set and the second set.

[0064] In some embodiments, to improve the processing efficiency of the second model, the target application may also generate descriptive information about the candidate agents provided to the second model based on the evaluation information 326. As an example, such descriptive information may include the matching degree (e.g., score) of each candidate agent. Alternatively, such descriptive information may also include classification labels determined based on the matching degree. For example, the label for candidate agents with a matching degree greater than a high threshold may be "high confidence," and the label for candidate agents with a matching degree greater than a low threshold and less than or equal to the high threshold may be "low confidence."

[0065] By providing such descriptive information, the second model can reuse the output of the first model, thereby improving the quality of the generated jump strategy.

[0066] In some embodiments, the policy determination unit 328 can further determine the target scene label corresponding to the target request from a set of preset scene labels based on the matching degree indicated by the evaluation information 326, also known as a semantic label. As shown in Figure 3B, in the processing stage 334, the policy determination unit 328 can generate the corresponding semantic label. Such a semantic label can be used as part of the input information of the second model to assist the second model in generating a jump strategy.

[0067] Specifically, as shown in Figure 3B, the policy determination unit 328 can determine the corresponding semantic label based on the number of agents in the first set (i.e., the "high confidence" set) and the second set (i.e., the "low confidence" set) corresponding to different matching degree ranges.

[0068] For example, if size (high confidence) = 1 and size (low confidence) = 0, then the policy decision unit 328 can generate the semantic label "direct output" to indicate that the target request corresponds to a clear intent. size (high confidence) represents the number of agents in the first set (i.e., the "high confidence" set), and size (low confidence) represents the number of agents in the second set (i.e., the "low confidence" set).

[0069] For example, if size (high confidence) = 0 and size (low confidence) = 1, the policy decision unit 328 can generate the semantic label "low confidence clarification" to indicate that the second model needs to further determine whether the specific intent corresponding to the "low confidence" set is accurate.

[0070] For example, if size (high confidence) > 1, the policy decision unit 328 can generate the semantic label "multi-task planning" or "high confidence clarification" to indicate that the second model needs to execute the "multi-task planning" jump strategy, or to further determine the most matching intent in the "high confidence" set in a single-task scenario.

[0071] For example, if size(high confidence) = 0 and size(low confidence) > 1, the policy decision unit 328 can generate the semantic label “low confidence clarification” to indicate that the second model needs to further determine whether there is a matching intent in the “low confidence” set.

[0072] For example, if size (high confidence) = 0 and size (low confidence) = 0, the policy determination unit 328 can generate a semantic label "rejection" to indicate that there is no intention to identify or no matching agent was found. Accordingly, the second model needs to determine whether the semantic label "rejection" is accurate in order to determine whether the target application needs to execute the corresponding preset policy (e.g., a fallback policy).

[0073] For example, if the target request matches the denial intent configured by agent 320 or the target application, the policy determination unit can also generate a semantic label "deny response" to indicate that the target application or agent 320 is not suitable to process the request. Accordingly, the second model needs to determine whether the semantic label "deny response" is accurate in order to determine whether the target application needs to execute the corresponding preset policy (e.g., a fallback policy).

[0074] In some embodiments, the denial intent may be determined based on the developer's configuration information regarding the target application or agent 320. For example, the developer may use natural language to express the type of request that the target application or agent will not respond to.

[0075] Accordingly, developers can also configure preset strategies (i.e., fallback strategies) corresponding to rejection scenarios. Such preset strategies may include, for example, jumping to a preset agent, jumping to human intervention, stopping at the current agent and replying with a preset text, etc.

[0076] Referring again to Figure 3A, the target application can determine the appropriate transition strategy for agent 320 based on the output generated by the second model from the input information. As an example, such output can instruct the specific agent 330 to handle the request.

[0077] Specifically, if the specific agent 330 is agent 320 itself, the target application can determine not to perform a jump and remain with agent 320 to handle the request. Conversely, the target application can determine to jump to the specific agent 330 to handle the request.

[0078] In this way, embodiments of the present disclosure can utilize hybrid models (e.g., models with different processing capabilities) to determine the jump strategy for in-application processing entities (e.g., bots or agents), thereby improving the efficiency of request processing.

[0079] Example devices and equipment

[0080] Embodiments of this disclosure also provide corresponding apparatus for implementing the methods or processes described above. Figure 4 shows a schematic structural block diagram of an example request processing apparatus 400 according to certain embodiments of this disclosure. Apparatus 400 may be implemented as or included in electronic device 110 and / or server 130. The various modules / components in apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0081] As shown in Figure 4, the device 400 includes a receiving module 410 configured to receive a target request to be processed by a target application, the target application being associated with multiple processing entities; a generating module 420 configured to generate evaluation information corresponding to the target request using a first model in response to the target request being provided to a first processing entity among the multiple processing entities, the evaluation information indicating the degree of matching between a first group of processing entities associated with the first processing entity and the target request; and a determining module 430 configured to determine a first jump strategy associated with the first processing entity using a second model in response to the evaluation information meeting preset conditions.

[0082] In some embodiments, the determining module 430 is further configured to: determine whether the first group of processing entities includes a target processing entity with a matching degree greater than a first threshold; and determine that the evaluation information meets a preset condition in response to the first group of processing entities not including a target processing entity or the number of target processing entities being greater than a first preset number.

[0083] In some embodiments, the determining module 430 is further configured to: provide first input information to the second model, the first input information indicating a target request and a second set of processing entities associated with the first processing entity, the second set of processing entities being at least a portion of the processing entities in the first set of processing entities; and determine a first jump strategy associated with the first processing entity based on the output information of the second model.

[0084] In some embodiments, the determining module 430 is further configured to: determine a third group of processing entities from the first group of processing entities, wherein the matching degree of the third group of processing entities is greater than a second threshold; and determine a second group of processing entities based on the third group of processing entities.

[0085] In some embodiments, the determining module 430 is further configured to: determine the third group of processing entities as the second group of processing entities in response to the number of the third group of processing entities being less than or equal to a second preset number; or determine the second group of processing entities from the third group of processing entities based on the degree of matching in response to the number of the third group of processing entities being greater than the second preset number, wherein the second group of processing entities has a second predetermined number of processing entities.

[0086] In some embodiments, the first input information further includes descriptive information associated with the second set of processing entities, the descriptive information being generated based on the evaluation information.

[0087] In some embodiments, the description information indicates: the degree of matching with the corresponding processing entity in the second group of processing entities; or the classification label corresponding to the corresponding processing entity in the second group of processing entities, wherein the classification label is determined based on the degree of matching.

[0088] In some embodiments, the first input information further includes a target scene label, which is determined from a set of preset scene labels based on evaluation information.

[0089] In some embodiments, the apparatus 400 further includes a partitioning module configured to: partition the first group of processing entities into multiple sets corresponding to different matching degree ranges based on the matching degree indicated by the evaluation information; and determine a target scene label from a set of preset scene labels based on the number of processing entities in the multiple sets.

[0090] In some embodiments, the determining module 430 is further configured to: output a first message generated by the second model to the user; and determine a first redirection strategy based on the second message replied by the user using the second model.

[0091] In some embodiments, the generation module 420 is further configured to: provide second input information to the first model, the second input information indicating a target request and a plurality of associated processing entities associated with the first processing entity; and obtain evaluation information generated by the first model based on the second input information.

[0092] In some embodiments, the first redirection strategy indicates that either the first processing entity responds to the target request, or the request is redirected to the second processing entity to respond to the target request.

[0093] In some embodiments, the determining module 430 is further configured to: in response to the evaluation information not meeting preset conditions, determine a second jump strategy associated with the first processing entity based on the degree of matching.

[0094] In some embodiments, the determining module 430 is further configured to: determine the third processing entity with the highest matching degree from the first group of processing entities; and determine to jump to the third processing entity to process the target request in response to the third processing entity being different from the first processing entity.

[0095] In some embodiments, the first model includes a classification model and the second model includes a language model.

[0096] Figure 5 shows a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 500 shown in Figure 5 is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. The electronic device 500 shown in Figure 5 can be used to implement the electronic device 110 or server 130 of Figure 1.

[0097] As shown in Figure 5, the electronic device 500 is in the form of a general-purpose electronic device. Components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage devices 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in the memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0098] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0099] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 5, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0100] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0101] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0102] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0103] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0104] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0105] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0107] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for request processing, comprising: receiving, by a target application, a target request to be processed, the target application being associated with a plurality of processing entities; in response to the target request being provided to a first processing entity of the plurality of processing entities, generating, by a first model, evaluation information corresponding to the target request, the evaluation information indicating a matching degree of a first set of processing entities associated with the first processing entity to the target request; and in response to the evaluation information satisfying a preset condition, determining, by a second model, a first jump strategy associated with the first processing entity. 2.The method of claim 1, further comprising: determining whether the first set of processing entities comprises a target processing entity having a matching degree greater than a first threshold; and in response to the first set of processing entities not comprising the target processing entity or a number of the target processing entities being greater than a first preset number, determining that the evaluation information satisfies the preset condition. 3.The method of claim 1, wherein in response to the evaluation information satisfying a preset condition, determining, by a second model, a first jump strategy associated with the first processing entity comprises: providing, to the second model, first input information, the first input information indicating the target request and a second set of processing entities associated with the first processing entity, the second set of processing entities being at least part of the first set of processing entities; and based on output information of the second model, determining the first jump strategy associated with the first processing entity. 4.The method of claim 3, further comprising: determining, from the first set of processing entities, a third set of processing entities having a matching degree greater than a second threshold; and based on the third set of processing entities, determining the second set of processing entities. 5.The method of claim 4, wherein based on the third set of processing entities, determining the second set of processing entities comprises: in response to a number of the third set of processing entities being less than or equal to a second preset number, determining the third set of processing entities as the second set of processing entities; or in response to a number of the third set of processing entities being greater than a second preset number, determining, from the third set of processing entities, the second set of processing entities based on the matching degree, the second set of processing entities having the second predetermined number of processing entities. 6.The method of claim 3, wherein the first input information further comprises description information associated with the second set of processing entities, the description information being generated based on the evaluation information. 7.The method of claim 6, wherein the description information indicates: the matching degree corresponding to a respective processing entity of the second set of processing entities; or a classification label corresponding to a respective processing entity of the second set of processing entities, the classification label being determined based on the matching degree. 8.The method of claim 3, wherein the first input information further comprises a target scene label, the target scene label being determined from a set of preset scene labels based on the evaluation information. 9.The method of claim 8, further comprising: ​ ​ ​ ​ ​ based on the matching degree indicated by the evaluation information, dividing the first set of processing entities into a plurality of sets corresponding to different matching degree ranges; and based on the number of processing entities in the plurality of sets, determining the target scenario label from the set of preset scenario labels.

10. The method of claim 1, wherein determining, in response to the evaluation information satisfying a preset condition, a first jump strategy associated with the first processing entity using a second model comprises: outputting, to a user, a first message generated by the second model; and determining, using the second model, the first jump strategy based on a second message replied by the user.

11. The method of claim 1, wherein generating, using a first model, evaluation information corresponding to the target request comprises: providing, to the first model, second input information indicating the target request and a plurality of associated processing entities associated with the first processing entity; and obtaining the evaluation information generated by the first model based on the second input information.

12. The method of claim 1, wherein the first jump strategy indicates: responding, by the first processing entity, to the target request, or jumping to a second processing entity to respond to the target request.

13. The method of claim 1, further comprising: in response to the evaluation information not satisfying the preset condition, determining, based on the matching degree, a second jump strategy associated with the first processing entity.

14. The method of claim 13, wherein determining, based on the matching degree, a second jump strategy associated with the first processing entity comprises: determining, from the first set of processing entities, a third processing entity with the highest matching degree; and in response to the third processing entity being different from the first processing entity, determining to jump to the third processing entity to process the target request.

15. The method of claim 1, wherein the first model comprises a classification model, and the second model comprises a language model.

16. A request processing apparatus, comprising: a receiving module configured to receive, by a target application, a target request to be processed, the target application being associated with a plurality of processing entities; a generating module configured to, in response to the target request being provided to a first processing entity in the plurality of processing entities, generate, using a first model, evaluation information corresponding to the target request, the evaluation information indicating a matching degree of a first set of processing entities associated with the first processing entity to the target request; and a determining module configured to, in response to the evaluation information satisfying a preset condition, determine, using a second model, a first jump strategy associated with the first processing entity.

17. An electronic device, comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, cause the electronic device to perform the method of any one of claims 1-15. ​ 18. A computer-readable storage medium having stored thereon a computer program, the computer program being executable by a processor to implement the method of any one of claims 1 to 15.

19. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method of any one of claims 1 to 15.

Images