CN116016780A

CN116016780A - Session service configuration method, device, equipment and medium based on multiple NLPs

Info

Publication number: CN116016780A
Application number: CN202211575165.2A
Authority: CN
Inventors: 陈诗洋; 彭俊琦; 许阳; 林无声
Original assignee: Zhongan Online P&c Insurance Co ltd
Current assignee: Zhongan Online P&c Insurance Co ltd
Priority date: 2022-12-08
Filing date: 2022-12-08
Publication date: 2023-04-25

Abstract

The application discloses a session service configuration method, device, equipment and medium based on multiple NLPs, and relates to the technical field of man-machine interaction. The method comprises the following steps: acquiring user information and session data of a current user; according to the user information and the session data, calculating to obtain a target session service strategy through a preset decision route based on a plurality of NLP models; a flow engine is called, a session instance of the current user is built through the flow engine according to the user information, the session data and the target session service policy, and the session instance is bound with the current session of the current user; and configuring session service corresponding to the target session service strategy for the current session. The method and the system can simultaneously support multiple channels and multiple NLP models, and have flexibility and high expansibility when the method and the system relate to the fields of multiple-round session and multiple-scene interaction.

Description

Session service configuration method, device, equipment and medium based on multiple NLPs

Technical Field

The present application relates to the field of man-machine interaction technologies, and in particular, to a session service configuration method, device, equipment, and medium based on multiple NLPs.

Background

With the development of AI (Art i f i c i a l I nte l l i gence) technology, intelligent robots are increasingly used in the fields of customer service, telemarketing and the like. The intelligent robot service client is applied, the service standardization can be improved, the service efficiency can be effectively improved, and the enterprise cost is reduced.

Most of the intelligent voice robots and intelligent online customer service robots applied at present are realized by using a conventional customized design method, but the voice robots and the online customer service robots often face the same service scene, and the service flows of some scenes basically keep consistent, such as policy consultation in the insurance industry. In the traditional scheme, one part is needed to be realized in each of the two sets of platforms, and the scene online can be ensured only by continuously disconnecting the transmission support when new service scenes are continuously added. And when facing to multiple call centers and multiple NLP model suppliers, a mechanism is lacking to realize that one set of robot platform supports multiple channels and multiple NLP models.

Therefore, how to support a multi-channel and multi-NLP model through a mechanism or a platform is a current problem to be solved urgently, so as to have flexibility and high expansibility in the fields of multi-round session and multi-scene interaction.

Disclosure of Invention

In order to solve at least one problem mentioned in the background art, the application provides a session service configuration method, device, equipment and medium based on multiple NLPs, which can simultaneously support multiple channels and multiple NLP models, and has flexibility and high expansibility when the session service configuration method relates to multiple rounds of session and multiple scene interaction fields.

The specific technical scheme provided by the embodiment of the application is as follows:

in a first aspect, a session service configuration method based on multiple NLPs is provided, including:

acquiring user information and session data of a current user;

according to the user information and the session data, calculating to obtain a target session service strategy through a preset decision route based on a plurality of NLP models;

a flow engine is called, a session instance of the current user is built through the flow engine according to the user information, the session data and the target session service policy, and the session instance is bound with the current session of the current user;

and configuring session service corresponding to the target session service strategy for the current session.

Further, the session data includes a session state, and the calculating, according to the user information and the session data, a target session service policy through a preset decision route based on multiple NLP models includes:

identifying a session state of the current user;

creating a new open session for the current user in response to detecting the session state as a new session;

in response to detecting that the session state has a history session, configuring the history session for the current user.

Further, the user information includes a user identifier, and the target session service policy is obtained by calculating a preset decision route based on multiple NLP models according to the user information and the session data, and the method further includes:

loading the user portrait attribute of the current user through the user identifier;

calculating to obtain a guest cluster to which the current user belongs through the user portrait attribute;

and calculating to obtain a target session service strategy through a preset decision route based on a plurality of NLP models according to at least one of the user portrait attributes, the guest clusters and the session data.

Further, the calculating, according to at least one of the user portrayal attribute, the guest cluster and the session data, a target session service policy through a preset decision route based on multiple NLP models includes:

identifying a idea of the current user based on at least one of the user profile attribute, the guest cluster, and the session data;

loading a corresponding offloading policy according to the idea, wherein the offloading policy comprises at least one session service scheme and at least one NLP model;

forming each session service strategy group according to all the current session service schemes and all the current NLP model permutation and combination;

and grouping any session service policy as a target session service policy of the current session.

Further, the method further comprises:

each session service policy group is respectively configured into a test service flow to perform session service for the current user;

recording service test data corresponding to the session service policy group in each test service flow;

and calculating according to the service test data to obtain the service completion rate of each session service policy group.

Further, the grouping any one of the session service policies as the target session service policy of the current session includes:

and grouping the corresponding session service policies with the highest service completion rate as target session service policies of the current session.

Further, the calling the flow engine, according to the user information, the session data and the target session service policy, constructs a session instance of the current user through the flow engine, including:

identifying a node where the current user is located through the flow engine;

advancing a flow through the flow engine, executing flow processing according to the node where the current user is located, and receiving a returned interaction instruction;

the nodes comprise at least one of system nodes, robot nodes, service calling nodes and question-answering nodes.

In a second aspect, there is provided a session service configuration apparatus based on multiple NLPs, the apparatus comprising:

the communication module is used for acquiring the user information and session data of the current user;

the calculation module is used for calculating a target session service strategy through a preset decision route based on a plurality of NLP models according to the user information and the session data;

the flow module is used for calling a flow engine, constructing a session instance of the current user through the flow engine according to the user information, the session data and the target session service policy, and binding the session instance with the current session of the current user;

and the session service providing module is used for configuring the session service corresponding to the target session service policy for the current session.

In a third aspect, an electronic device is provided that includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the multiple NLP based session service configuration method when executing the computer program.

In a fourth aspect, a computer-readable storage medium is provided, storing computer-executable instructions for performing the multiple NLP-based session service configuration method.

The embodiment of the application has the following beneficial effects:

according to the session service configuration method, device, equipment and medium based on multiple NLPs, a set of session platforms can be configured to simultaneously support multiple channels and multiple NLP models, a target session service strategy can be obtained through calculation based on preset decision routes of the multiple NLP models, and finally session services corresponding to the target session service strategy are configured for the current session, so that flexibility and high expansibility can be maintained in the fields related to multiple-round session and multiple-scene interaction.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 shows a general flowchart of a session service configuration method based on multiple NLPs provided in an embodiment of the present application;

fig. 2 shows a specific flowchart of a session service configuration method based on multiple NLPs according to one embodiment of the present application;

fig. 3 is a schematic structural diagram of a session service configuration device based on multiple NLPs according to an embodiment of the present application;

FIG. 4 illustrates an exemplary system that may be used to implement various embodiments described herein.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

It should be understood that throughout the description of this application, unless the context clearly requires otherwise, the words "comprise," "comprising," and the like in the description and the claims are to be construed in an inclusive sense rather than an exclusive or exhaustive sense; that is, it is the meaning of "including but not limited to".

Example 1

The application provides a session service configuration method based on multiple NLPs, referring to FIG. 1, the method comprises the following steps:

s1, acquiring user information and session data of a current user;

s2, calculating to obtain a target session service strategy through a preset decision route based on a plurality of NLP models according to user information and session data;

s3, invoking a flow engine, constructing a session instance of the current user through the flow engine according to the user information, the session data and the target session service policy, and binding the session instance with the current session of the current user;

s4, configuring session service corresponding to the target session service strategy for the current session.

Specifically, the embodiment of the method can be applied to intelligent robot session control scenes, can also be applied to other man-machine interaction session scenes, can support single-round session interaction, can also support multi-round session interaction scenes, can simultaneously adapt to multiple channel sources, access multiple NLP models, performs policy matching according to regular routing, and can rapidly support configuration of multiple service scenes. Firstly, user information and session data of a current access user are required to be acquired, wherein the session data are mainly used for judging whether the current access user belongs to a new session or an old session and determining whether the new session needs to be started; the user information is mainly used for carrying out user portrait to obtain user attributes and corresponding guest group information, so that the idea of the user can be calculated and obtained, and the decision routing can be carried out later. The method can be used for matching the idea of the current user based on preset decision routes of multiple NLP models, identifying corresponding NLP service identifiers, then calling a flow engine, constructing a session instance of the current user by taking user information, session data and the idea identification NLP service identifiers of the user as context information, and binding the appointed flow instance with the current session. And finally, the process engine advances the process, sends the request to the corresponding NLP capability channel to complete the processing, and finally receives the response from the channel side to answer the current user, thereby realizing the configuration of the session service corresponding to the target session service strategy for the current user.

The following is further described by taking a conversation robot scenario as an example:

in some implementations, the session data includes a session state, based on which S2 includes:

s21, identifying the session state of the current user;

s22, creating a new open session for the current user in response to detecting that the session state is a new session;

s23, in response to detecting that the session state has a history session, configuring the history session for the current user. Specifically, the session robot mainly completes the control of the session process from the user to the robot. Firstly, receiving session data of a user, wherein the session data comprises voice data and text data, if the voice data is sent by the user, the session data is processed and converted into text through an ASR (Automat i c Speech Recogn it i on, automatic speech recognition technology) system, and the text is transmitted to a front robot through a specific protocol by a call center; if the text is online text, the text is directly transmitted to the front end of the robot through a specific protocol. The front end of the robot converts the session data into a universal robot dialogue protocol through protocol conversion and then transmits the universal robot dialogue protocol to the session robot. The robot may then identify the session state of the current user by the session management module, i.e. determine whether the current user has a session before, and decide whether to newly open the session or continue the previous session, which will also decide the flow node where the current user is located next.

In some embodiments, the user information includes a user identification, based on which S2 further includes:

s24, loading user portrait attributes of the current user through the user identifier;

s25, calculating to obtain a guest cluster to which the current user belongs through the user portrait attribute;

s26, calculating to obtain a target session service strategy through a preset decision route based on a plurality of NLP models according to at least one of user portrait attributes, guest clusters and session data.

Specifically, taking a new session as an example, the session robot can load the user portrait attribute of the current user through a user identifier in user information, wherein the user identifier can be a mobile phone number of the user or an identity identifier of the user or other identification information for identifying the user identity in the system; for old session, the user identification information stored before can be directly loaded, or the user portrait attribute of the current user can be loaded and updated according to the session data and other user characteristics. After the user portrait attributes are loaded, the user portrait attributes can be used to calculate the guest clusters, and the guest clusters can describe guest cluster information of different dimensions of the current user, such as age, health condition, occupation and other guest cluster information. The idea of the current user can be identified based on the user portrait attribute of the current user, the guest cluster information, session data and the like, and according to preset decision routes based on various service schemes, various channels and various NLP models, a target session service strategy can be obtained through calculation and matching in the whole deployed decision pool, so that the corresponding target session service strategy can be configured for the current user later.

In some embodiments, S26 comprises:

s261, identifying a idea of the current user according to at least one of user portrait attributes, guest clusters and session data;

s262, loading a corresponding distribution strategy according to the idea, wherein the distribution strategy comprises at least one session service scheme and at least one NLP model;

s263, forming each session service strategy group according to the current all session service schemes and the current all NLP model permutation and combination;

s264, any session service policy group is used as the target session service policy of the current session.

Specifically, the idea of the current user can be identified based on the user portrait attribute of the current user, the guest cluster information, session data and other information, and then a corresponding distribution strategy is loaded according to the idea, wherein the distribution strategy comprises at least one session service scheme and at least one NLP model. By way of example, taking a consultation policy scenario (idea) as an example, there may be two session service schemes, such as scheme one below:

1. firstly, inquiring a policy of which dangerous seed the user needs to claim through a robot;

2. the user answers and identifies by calling the NLP model corresponding to the current customer;

3. the play back policy list is selected by the user to further complete the session service.

For example, scheme two:

1. firstly, identifying the latest policy information of a user through user information, and then directly asking the user if the latest policy is required to be paid out;

3. if the answer is negative, the user is provided with the corresponding policy number so as to further complete the service.

At this time, two NLP models are included for the scene, and can be identified, and the permutation and combination can form 4 session service policy groups, namely group 1: scheme one+nlp1; group 2: scheme one+nlp2; group 3: scheme two+nlp1; group 4: scheme two+nlp2. At this time, a certain (any one of the groups 1-4) session service policy group can be randomly used as a target session service policy of the current session to provide session service; one of the target session service policies, which is the current session, may also be designated to provide session services.

In some embodiments, the method further comprises:

101. each session service strategy group is respectively configured into a test service flow to perform session service for the current user;

102. recording service test data of the corresponding session service policy group in each test service flow;

103. and calculating according to the service test data to obtain the service completion rate of each session service policy group.

Specifically, the above-mentioned group 1, group 2, group 3 and group 4 may also be used as test groups, and session service may be performed on the user by using the service schemes and the NLP models of the group 1, group 2, group 3 and group 4, respectively, and in the session service process, the corresponding NLP model may be invoked by the corresponding NLP capability identifier. In each test service flow, service process data and service result data of a user can be used as service test data and marked with test packet identifiers to be recorded respectively; and after the service is completed, obtaining the service completion rate of each test packet through data analysis and calculation.

In some embodiments, S264 comprises:

and grouping the corresponding session service policies with highest service completion rate as target session service policies of the current session.

Specifically, the best service scheme/optimal service scheme with the highest service completion rate can be used as the target session service policy to perform session service for the current user, so as to improve the session experience of the user. It should be noted that, according to a specific service scenario, the service completion rate is not necessarily used as a service evaluation index of each packet, and the packet with the optimal/optimal evaluation index can be selected as a target session service policy of the current session by using user satisfaction, service priority, and other dimensions as service evaluation indexes of each session service policy packet.

In some embodiments, S3 comprises:

s31, identifying the node where the current user is located through a flow engine;

s32, pushing a flow through a flow engine, executing flow processing according to the node where the current user is located, and receiving a returned interaction instruction;

the nodes comprise at least one of system nodes, robot nodes, service calling nodes and question answering nodes.

Specifically, the session robot subscribes to the return instruction event of the corresponding instance of the flow engine, and then advances the flow by calling the flow engine, and the flow engine performs corresponding processing according to the node where the current user is located. In the process of one interaction, the flow engine may return a plurality of interaction instructions through a plurality of nodes. If the NLP model is used in the interaction process, the NLP model is identified as a parameter call corresponding to the NLP model through the NLP model channel appointed by the user context at the flow engine side, and the NLP model sends a request to the corresponding NLP capability channel. After the interaction is completed, instructions are combined by the session robot, and standard robot response data are returned to the front end of the robot. The front end of the robot carries out corresponding protocol conversion on the data returned by the session robot and the request channel, and then returns to the corresponding access channel so as to provide session service for the user in the access channel.

In particular, the process engine is capable of abstracting a session into process instances, each process instance being an instantiation of a process, the engine describing the entire process of a process by a set of metadata. Each flow contains N nodes, each pointing to one or more next nodes. The flow instance records node information of the current flow and context data corresponding to the current flow. The nodes have various types and extensibility and can be divided into system nodes and custom nodes. The system nodes are mainly a start node, an end node, a sub-flow node and a routing node. The starting node and the ending node are only used as marks, and marked as the beginning or ending of the flow; the routing node can dynamically point to the next node according to the condition judgment. The sub-process node will restart a new sub-process from the current process, and the sub-process and the main process have the same process context. The robot custom nodes may include robot nodes, service invocation nodes, question answering nodes, and the like. The behavior of a node (the function of the node) is accomplished by the node itself. The public attribute of the node for the flow instance is whether the node is automatically operated, when the flow identifies that the current node is automatically operated, the operation of the node is completed in the process of one interaction, and the node continues to be operated downwards until the next non-automatically operated node is encountered. When a node runs is determined by the node itself, a node may run multiple times. The node can directly return after running, or can set itself to finish and return, and the flow instance judges whether to continue running downwards to the next node according to judging whether the current node is finished.

In this embodiment, a set of session platforms can be configured to support multiple channels and multiple NLP models at the same time, a target session service policy can be obtained by calculation based on a preset decision route of multiple NLP models, and finally session services corresponding to the target session service policy are configured for a current session, so that flexibility and high expansibility can be maintained in the fields involving multiple sessions and multiple scene interactions.

It should be noted that the terms "S1", "S2", and the like are used for the purpose of describing steps only, and are not intended to be limited to the order or sequence of steps or to limit the present application, but are merely used for convenience in describing the method of the present application and are not to be construed as indicating the sequence of steps. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.

Example two

Corresponding to the above embodiment, the present application further provides a session service configuration device based on multiple NLPs, and referring to fig. 3, the device includes a communication module, a calculation module, a flow module, and a session service providing module.

The communication module is used for acquiring user information and session data of a current user; the calculation module is used for calculating a target session service strategy through a preset decision route based on a plurality of NLP models according to the user information and the session data; the flow module is used for calling a flow engine, constructing a session instance of the current user through the flow engine according to the user information, the session data and the target session service policy, and binding the session instance with the current session of the current user; and the session service providing module is used for configuring the session service corresponding to the target session service policy for the current session.

Further, the session data includes a session state, based on which the computing module is further configured to identify a session state of the current user; and means for creating a new open session for the current user in response to detecting the session state as a new session; and the method is also used for configuring a history session for the current user in response to detecting that the session state has the history session.

Further, the user information comprises a user identifier, and based on the user identifier, the computing module is further used for loading the user portrait attribute of the current user; and the guest cluster to which the current user belongs is obtained through calculation of the user portrait attribute; and the target session service strategy is obtained through calculation according to at least one of the user portrait attributes, the guest clusters and the session data through a preset decision route based on a plurality of NLP models.

Further, the computing module is further configured to identify a idea of the current user based on at least one of the user profile attribute, the guest cluster, and the session data; the method comprises the steps of loading a corresponding offloading policy according to the idea, wherein the offloading policy comprises at least one session service scheme and at least one NLP model; the method comprises the steps of forming a plurality of session service policy groups according to all the session service schemes and all the NLP model permutation and combination; and is further configured to group any of the session service policies as a target session service policy for the current session.

Further, the device also comprises a test module, which is used for respectively configuring each session service policy group into a test service flow to perform session service for the current user; and recording service test data corresponding to the session service policy group in each test service flow; and the service completion rate of each session service policy group is obtained by calculating according to the service test data.

Further, the computing module is further configured to group the corresponding session service policy with the highest service completion rate as the target session service policy of the current session.

Further, the flow module is further configured to identify, by using the flow engine, a node where the current user is located; the flow engine is used for pushing a flow, executing flow processing according to the node where the current user is located, and receiving a returned interaction instruction; the nodes comprise at least one of system nodes, robot nodes, service calling nodes and question-answering nodes.

For specific limitations regarding the session service configuration apparatus based on multiple NLPs, reference may be made to the above-mentioned related limitations in the embodiment of the session service configuration method based on multiple NLPs, and thus a detailed description is omitted herein. The respective modules in the session service configuration apparatus based on a plurality of NLPs described above may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

Example III

Corresponding to the above embodiment, the present application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor can implement the session service configuration method based on multiple NLPs when executing the program.

As shown in fig. 4, in some embodiments, the system can be used as the above-described electronic device of any of the embodiments for a session service configuration method based on multiple NLPs. In some embodiments, a system may include one or more computer-readable media (e.g., system memory or NVM/storage) having instructions and one or more processors (e.g., processor (s)) coupled with the one or more computer-readable media and configured to execute the instructions to implement the modules to perform the actions described herein.

For one embodiment, the system control module may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) and/or any suitable device or component in communication with the system control module.

The system control module may include a memory controller module to provide an interface to the system memory. The memory controller modules may be hardware modules, software modules, and/or firmware modules.

The system memory may be used, for example, to load and store data and/or instructions for the system. For one embodiment, the system memory may include any suitable volatile memory, such as, for example, a suitable DRAM. In some embodiments, the system memory may comprise double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).

For one embodiment, the system control module may include one or more input/output (I/O) controllers to provide an interface to the NVM/storage device and the communication interface(s).

For example, NVM/storage may be used to store data and/or instructions. The NVM/storage may include any suitable nonvolatile memory (e.g., flash memory) and/or may include any suitable nonvolatile storage device(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).

The NVM/storage may include a storage resource that is physically part of the device on which the system is installed or it may be accessed by the device without being part of the device. For example, the NVM/storage may be accessed over a network via the communication interface(s).

The communication interface(s) may provide an interface for the system to communicate over one or more networks and/or with any other suitable device. The system may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and/or protocols.

For one embodiment, at least one of the processor(s) may be packaged together with logic of one or more controllers (e.g., memory controller modules) of the system control module. For one embodiment, at least one of the processor (S) may be packaged together with logic of one or more controllers of the system control module to form a system in package (S ip). For one embodiment, at least one of the processor(s) may be integrated on the same die as logic of one or more controllers of the system control module. For one embodiment, at least one of the processor(s) may be integrated on the same die with logic of one or more controllers of the system control module to form a system on chip (SoC).

In various embodiments, the system may be, but is not limited to being: a server, workstation, desktop computing device, or mobile computing device (e.g., laptop computing device, handheld computing device, tablet, netbook, etc.). In various embodiments, the system may have more or fewer components and/or different architectures. For example, in some embodiments, a system includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (AS ic), and a speaker.

It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, using application specific integrated circuits (AS I C), a general purpose computer or any other similar hardware device. In one embodiment, the software programs of the present application may be executed by a processor to implement the steps or functions as described above. Likewise, the software programs of the present application (including associated data structures) may be stored on a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. In addition, some steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.

Furthermore, portions of the present application may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present application by way of operation of the computer. Those skilled in the art will appreciate that the form of computer program instructions present in a computer readable medium includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the manner in which the computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Herein, a computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by a computer.

Communication media includes media whereby a communication signal containing, for example, computer readable instructions, data structures, program modules, or other data, is transferred from one system to another. Communication media may include conductive transmission media such as electrical cables and wires (e.g., optical fibers, coaxial, etc.) and wireless (non-conductive transmission) media capable of transmitting energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied as a modulated data signal, for example, in a wireless medium, such as a carrier wave or similar mechanism, such as that embodied as part of spread spectrum technology. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. The modulation may be analog, digital or hybrid modulation techniques.

An embodiment according to the present application comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to operate a method and/or a solution according to the embodiments of the present application as described above.

Example IV

Corresponding to the above embodiment, the present application further provides a computer readable storage medium storing computer executable instructions for executing the session service configuration method based on multiple NLPs.

In this embodiment, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory, such as random access memory (RAM, DRAM, SRAM); and nonvolatile memory such as flash memory, various read only memory (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic/ferroelectric memory (MRAM, feRAM); and magnetic and optical storage devices (hard disk, tape, CD, DVD); or other now known media or later developed computer-readable information/data that can be stored for use by a computer system.

While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted to embrace the preferred embodiments and all such variations and modifications as fall within the scope of the embodiments herein.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.

Claims

1. A session service configuration method based on multiple NLPs, comprising:

acquiring user information and session data of a current user;

2. The session service configuration method based on multiple NLPs according to claim 1, wherein the session data includes a session state, and the calculating, according to the user information and the session data, a target session service policy through a preset decision route based on multiple NLP models includes:

identifying a session state of the current user;

3. The session service configuration method based on multiple NLPs according to claim 1, wherein the user information includes a user identifier, and the target session service policy is obtained by calculating a preset decision route based on multiple NLP models according to the user information and the session data, and further comprising:

4. The session service configuration method based on multiple NLPs according to claim 3, wherein the calculating, according to at least one of the user profile attribute, the guest cluster and the session data, a target session service policy through a preset decision route based on multiple NLP models comprises:

5. The multiple NLP-based session service configuration method of claim 4, wherein the method further comprises:

6. The multiple NLP-based session service configuration method of claim 5, wherein grouping any one of the session service policies as a target session service policy for the current session, comprises:

7. The multiple NLP-based session service configuration method of claim 1, wherein the invoking the flow engine to construct the session instance of the current user through the flow engine according to the user information, the session data, and the target session service policy comprises:

identifying a node where the current user is located through the flow engine;

8. A session service configuration apparatus based on multiple NLPs, the apparatus comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the multiple NLP-based session service configuration method of any of claims 1 to 7 when the computer program is executed by the processor.

10. A computer-readable storage medium storing computer-executable instructions for performing the multiple NLP-based session service configuration method of any one of claims 1 to 7.