CN111368059B

CN111368059B - Method and system for autonomous response of group chat robot

Info

Publication number: CN111368059B
Application number: CN202010461146.1A
Authority: CN
Inventors: 杨明晖; 林川杰; 刘威; 崔恒斌; 刘洋
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2020-05-27
Filing date: 2020-05-27
Publication date: 2020-09-15
Anticipated expiration: 2040-05-27
Also published as: CN111368059A; CN112052323A; WO2021239002A1

Abstract

According to the method and the system for autonomous response of the group chat robot, after an input statement sent by a target user in a target communication group is received, a candidate list related to the input statement is generated based on the input statement and a preset knowledge base, and the candidate list is sent to a target client or a first group of clients including the target client, so that the influence on other users is reduced; and after the management client of the first group of clients selects the candidate list, sending the target answer matched with the selection to the second group of clients. The method can actively answer the questions posed by the user, meanwhile, interference to other users in group chat is avoided, and the user experience can be improved while the working efficiency is improved.

Description

Method and system for autonomous response of group chat robot

Technical Field

The specification relates to the technical field of internet, in particular to a method and a system for autonomous response of group chat robots.

Background

With the rapid development of information technology and internet technology, people's work, life, study, etc. are closely connected to a network, and Instant Messaging (IM) technology supports two or more people to communicate via the network, so that the IM technology is widely applied to the work and life of people, such as daily work and life communication, and brings various convenience to the work and life of people. Common IM software is constantly evolving towards more user-friendly instant messaging technology from the early MSN, ICQ, OICQ, to today's QQ, wechat, nailing, hundredth Hi, etc. Many instant messaging applications support group chat techniques, such as WeChat, nailing and Baidu Hi. Group chat techniques may allow multiple users in real life to aggregate together for interaction and sharing of information. In some service groups, there are both users of the service group and service personnel, such as service robots. In the use of the service group, the user can perform dialogue communication or business consultation in the service group. When a user makes business consultation in a service group, the user usually wants the customer service robot to actively respond to the consultation problem, but does not want the customer service robot to disturb other users. Therefore, how to ensure that the customer service robot can actively respond to the affairs consulted by the user without disturbing the dialogue communication between the users is a problem to be solved urgently.

Therefore, in order to ensure that the robot actively responds to the affairs consulted by the user without disturbing the dialogue communication of the user, a more efficient method and a more efficient system for autonomously responding to the group chat robot are needed.

Disclosure of Invention

In order to ensure that the robot actively responds to the affairs consulted by the user without disturbing the dialogue communication of the user, the specification provides a more efficient method and a more efficient system for autonomously responding to the group chat robot.

According to the method and the system for autonomous response of the group chat robot, after an input sentence sent by a user in group chat is received, a candidate list related to the input sentence is generated based on the input sentence and a preset knowledge base, the candidate list is sent to the user sending the input sentence, and after the user selects the candidate list, an answer matched with a selection result is sent to other users in the group chat. The method and the system can actively answer the questions posed by the user, cannot interfere with other users in group chat, and can improve the user experience while improving the working efficiency.

In a first aspect, the present specification provides a method for autonomous response of a group chat robot, comprising: receiving an input statement, wherein the input statement is input by a target client on an instant messaging group interface; generating a candidate list based on the input sentence and a preset knowledge base, wherein the candidate list comprises at least one recommended knowledge point related to the input sentence; sending the candidate list to the instant messaging group, wherein the candidate list is marked to be only visible to a first group of clients in the instant messaging group, and the first group of clients are part of clients including the target client; receiving a selection of the candidate list by a management client in the first set of clients; and sending a target answer matched with the selection to the instant messaging group, wherein the target answer is marked to be visible to a second group of clients in the instant messaging group, and the second group of clients comprises at least part of clients in the instant messaging group.

In some embodiments, said sending said candidate list to said instant messaging group comprises: sending first icon data to the instant messaging group, the first icon data being marked as visible only to the first group of clients, the first icon data comprising a list display request; receiving a signal that the first group of clients triggers the list display request; sending the candidate list to the instant messaging group, the candidate list marked as visible to a client that triggered the list display request.

In some embodiments, said sending said candidate list to said instant messaging group comprises: and sending the candidate list and first icon data to the instant messaging group, wherein the first icon data are marked to be only visible for the first group of clients, the first icon data comprise a list display request, and when the first icon data are triggered by the clients, the candidate list is displayed at the client triggering the first icon data.

In some embodiments, the sending the target answer matching the selection to the instant messaging group comprises: and sending the target answer and second icon data to the instant messaging group, wherein the second icon data are marked to be visible to the second group of clients, the second icon data comprise answer display requests, and when the second icon data are triggered by the clients, the target answer is displayed on the client triggering the second icon data.

In some embodiments, the generating a candidate list based on the input sentence and a preset knowledge base includes: identifying whether the input statement comprises a target question related to a preset transaction, wherein the preset transaction is customized for the instant messaging group; determining that the input sentence includes the target question; and generating the candidate list based on the input sentence and the preset knowledge base.

In some embodiments, the identifying whether the input statement includes a target question related to a preset transaction includes: matching the input sentence with a plurality of preset question templates to identify whether the input sentence is a question sentence; and when the input statement is a question statement, classifying the input statement, and identifying whether the input statement comprises a target question related to the preset transaction.

In some embodiments, the method for the group chat robot to autonomously answer further comprises: sending an answer evaluation request to the instant messaging group, wherein the answer evaluation request is marked to be visible only to the target client; and receiving the answer evaluation of the target client.

In some embodiments, the management client comprises the target client.

In some embodiments, the second set of clients comprises: and the management client selects the client from the instant communication group or all the clients in the instant communication group.

In a second aspect, the present specification provides a system for group chat robotic autonomous response, comprising at least one storage medium comprising at least one instruction set for group chat robotic autonomous response, and at least one processor; the at least one processor is communicatively connected to the at least one storage medium, wherein when the system is running, the at least one processor reads the at least one instruction set and performs the method for group chat robot autonomous answer according to the instruction of the at least one instruction set.

In a third aspect, the present specification provides a method for autonomous response of group chat robots, comprising: receiving an input statement and sending the input statement to a server, wherein the input statement is input by a target user on an instant messaging group interface; receiving a candidate list sent by the server and displaying the candidate list on the instant messaging group interface, wherein the candidate list is generated based on the input statement and the preset knowledge base and comprises at least one recommended knowledge point related to the input statement; receiving the selection of the target user to the candidate list, and sending the selection to the server; sending the selection to the instant messaging group; and receiving the target answer which is sent by the server and matched with the selection.

In some embodiments, the receiving the candidate list sent by the server includes: receiving the candidate list and first icon data sent by the server, wherein the first icon data comprise a list display request, and when the first icon data are triggered by a client, the candidate list is displayed at the client triggering the first icon data; receiving a trigger operation of the target user on the first icon data; and displaying the candidate list in the instant messaging group.

In a fourth aspect, the present specification provides a system for group chat robotic autonomous response, comprising at least one storage medium comprising at least one instruction set for group chat robotic autonomous response, and at least one processor; the at least one processor is communicatively coupled to the at least one storage medium, wherein when the system is operating, the at least one processor reads the at least one instruction set and performs the method for group chat robot autonomous reply according to the instruction of the at least one instruction set.

Other functions of the method and system for group chat robot autonomous response provided by the present specification will be partially listed in the following description. The following numerical and exemplary descriptions will be readily apparent to those of ordinary skill in the art in view of the description. The inventive aspects of the method, system, and storage medium for group chat robot autonomous reply provided herein may be fully explained by the practice or use of the methods, apparatus, and combinations described in the detailed examples below.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed to be used 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 disclosure, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 illustrates a system diagram of autonomous response of a group chat robot provided according to an embodiment of the present description;

fig. 2 is a schematic diagram illustrating an apparatus structure for autonomous reply of a group chat robot provided in accordance with an embodiment of the present specification;

fig. 3 illustrates a flowchart of a method for autonomous response of group chat robots provided in accordance with an embodiment of the present description;

FIG. 4 illustrates a flow diagram for generating a candidate list provided in accordance with an embodiment of the present description;

fig. 5 illustrates a flowchart of a method for autonomous response of group chat robots provided in accordance with an embodiment of the present description; and

fig. 6 is a schematic diagram illustrating an instant messaging group interface according to an embodiment of the present disclosure.

Detailed Description

The following description is presented to enable any person skilled in the art to make and use the present description, and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present description. Thus, the present description is not limited to the embodiments shown, but is to be accorded the widest scope consistent with the claims.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. For example, as used herein, the singular forms "a", "an" and "the" may include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises," "comprising," or "including," when used in this specification, are intended to specify the presence of stated integers, steps, operations, elements, or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or groups thereof.

These and other features of the present specification, as well as the operation and function of the elements of the structure related thereto, and the combination of parts and economies of manufacture, may be particularly improved upon in view of the following description. Reference is made to the accompanying drawings, all of which form a part of this specification. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the specification. It should also be understood that the drawings are not drawn to scale.

The flow diagrams used in this specification illustrate the operation of system implementations according to some embodiments of the specification. It should be clearly understood that the operations of the flow diagrams may be performed out of order. Rather, the operations may be performed in reverse order or simultaneously. In addition, one or more other operations may be added to the flowchart. One or more operations may be removed from the flowchart.

Group chat technology is an important function of instant messaging application software, and can allow multiple users in real life to gather together for interaction and sharing of information. In order to improve the working efficiency, a service group is released on the basis of common group chat. The service group refers to a group chat established for the purpose of a service user. The service group not only has users, but also has customer service. The user may be a served person in the service group. The user can perform group chat communication in the service group, and also can perform business consultation, business help or business feedback in the service group. The customer service may be a server in the service group, and may answer a question of the user, respond to an appeal of the user, or send a notification or announcement to the user, etc. in the service group. The customer service can comprise manual customer service and can also comprise a customer service robot. The customer service robot can help the manual customer service to respond to the appeal of the user, the pressure of the manual customer service is reduced, and the working efficiency of a service group is improved. The customer service robot can provide a series of auxiliary functions including service reminding, answer recommendation, question and answer warehousing and the like for the artificial customer service. The customer service robot can also directly answer the questions of the user.

Fig. 1 shows a schematic diagram of a system 100 for autonomous response of a group chat robot. System 100 may include server 200, client 300, network 120, and database 150. In some embodiments, clients 300 may include target client 301, client 302, client 303, client 304, and so on.

The server 200 may store data or instructions to perform the method of group chat robot autonomous answer described herein and may execute or be used to execute the data or instructions. The server 200 may comprise the robot server. In some embodiments, the server 200 may further include a server providing the group chat service. In some embodiments, the group chat service may also be provided by the robot server.

As shown in FIG. 1, user 110 is a user of client 300. Users 110 may include target users 111, users 112, users,User 113, user 114, and so on. Target user 111 is the user of target client 301, user 112 is the user of client 302, user 113 is the user of client 303, user 114 is the user of client 304, and so on. The client 300 is a connection device for the general target user 110 to communicate with the server 200. The client 300 is communicatively connected to the server 200. The server 200 may be communicatively coupled to a plurality of clients 300 simultaneously. In some embodiments, the client 300 may have one or more Applications (APPs) installed. The APP can provide the user 110 with the ability to interact with the outside world and an interface over the network 120. The APP includes but is not limited to: chat-type APP program, shopping-type APP program, video-type APP program, financing-type APP program, etc., such as Payment treasure^TMTaobao medicine^TMJingdong^TMOr financial service institutions such as banks and APP such as financial products. In some embodiments, the client 300 may include a mobile device, a tablet, a laptop, a built-in device of a motor vehicle, or the like, or any combination thereof. In some embodiments, the mobile device may include a smart home device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some embodiments, the smart home device may include a smart television, a desktop computer, or the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a personal digital assistant, a gaming device, a navigation device, and the like, or any combination thereof. In some embodiments, the virtual reality device or augmented reality device may include a virtual reality helmet, virtual reality glasses, a virtual reality patch, an augmented reality helmet, augmented reality glasses, an augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device or the augmented reality device may include google glasses, head mounted displays, gear VR, and the like. In some embodiments, the built-in devices in the motor vehicle may include an on-board computer, an on-board television, and the like. In some embodiments, the client 300 may be a device with location technology for locating the location of the client 300.

The client 300 is loaded withInstant messaging application software corresponding to server 200, e.g. nailing^TM. And the instant messaging application software is provided with an instant messaging group. User 110 is a user in the instant messaging group. User 110 may enter chat information in the instant messaging group. The instant messaging group includes at least two users 110.

Network 120 may facilitate the exchange of information or data. As shown in fig. 1, the client 300, the server 200, and the database 150 may be connected to the network 120 and transmit information or data to each other through the network 120. For example, server 200 may obtain input information from client 300 via network 120. In some embodiments, the network 120 may be any type of wired or wireless network, as well as combinations thereof. For example, network 120 may include a cable network, a wireline network, a fiber optic network, a telecommunications network, an intranet, the Internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), the Public Switched Telephone Network (PSTN), a Bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, or the like. In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired or wireless network access points, such as base stations or Internet exchange points 120-1, 120-2, … …, through which one or more components of client 300, server 200, database 150 may connect to network 120 to exchange data or information.

Database 150 may store data or instructions. In some embodiments, database 150 may store data obtained from server 200 or client 300. In some embodiments, database 150 may store data or instructions that server 200 may perform or be used to perform the methods of group chat robot autonomous answer described in this specification. In some embodiments, the database 150 may store a knowledge base associated with the instant messaging group default transaction. Server 200 and client 300 may have access to database 150, and server 200 and client 300 may access data or instructions stored in database 150 via network 120. In some embodiments, database 150 may be directly connected to server 200 and client 300. In some embodiments, database 150 may be part of server 200. In some embodiments, database 150 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), or the like, or any combination thereof. Exemplary mass storage may include magnetic disks, optical disks, solid state drives, and non-transitory storage media. Removable storage may include flash drives, floppy disks, optical disks, memory cards, zip disks, magnetic tape, and the like. Typical volatile read and write memory may include Random Access Memory (RAM). RAM may include Dynamic RAM (DRAM), double-date-rate synchronous dynamic RAM (DDR SDRAM), Static RAM (SRAM), thyristor RAM (T-RAM), zero-capacitance RAM (Z-RAM), and the like. ROM may include Masked ROM (MROM), Programmable ROM (PROM), virtually programmable ROM (PEROM), electrically programmable ROM (EEPROM), compact disk (CD-ROM), digital versatile disk ROM, and the like. In some embodiments, database 150 may be implemented on a cloud platform. By way of example only, the cloud platform may include forms such as a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, and the like, or forms similar to the above, or any combination thereof.

As shown in fig. 1, target user 111 inputs chat information through an instant messaging group of instant messaging application software on target client 301, which is transmitted to server 200 over network 120; the server 200 executes the instructions of the method for autonomous response of the group chat robots stored in the memory built in the server 200 and/or the database 150, generates a candidate list by responding to questions included in the input chat information, and transmits the candidate list to the target user 111 or a part of users in the instant messaging group; after the target user 111 selects the candidate list, the server 200 sends a target answer matching the selection to all users or a part of users in the instant messaging group.

Fig. 2 shows a schematic structural diagram of a device for autonomous reply of a group chat robot. The device may be a server 200 or a client 300. The following description will describe the apparatus by taking the server 200 as an example.

The server 200 may perform the method of group chat robot autonomous response described herein. The method is described elsewhere in this specification. For example, a method P200 for the server 200 to perform the group chat robot autonomous response is introduced in the descriptions of fig. 3 to 4.

As shown in fig. 2, server 200 includes at least one storage medium 230 and at least one processor 220. In some embodiments, server 200 may also include a communication port 250 and an internal communication bus 210. Meanwhile, the server 200 may also include an I/O component 260.

Internal communication bus 210 may connect various system components including storage medium 230 and processor 220.

I/O components 260 support input/output between server 200 and other components.

Storage medium 230 may include a data storage device. The data storage device may be a non-transitory storage medium or a transitory storage medium. For example, the data storage device may include one or more of a magnetic disk 232, a read only memory medium (ROM) 234, or a random access memory medium (RAM) 236. The storage medium 230 further includes at least one set of instructions stored in the data storage device. The instructions are computer program code that may include programs, routines, objects, components, data structures, procedures, modules, etc. that perform the methods of group chat robot autonomous responses provided herein.

The communication port 250 is used for data communication between the server 200 and the outside. For example, server 200 may connect to network 120 via communication port 250 and receive the universal instant messenger APP (e.g., nailing) from target user 111 via the universal instant messenger APP^TM) The input sentence, in turn, recommends an answer to target user 111 through communication port 250.

The at least one processor 220 is communicatively coupled to at least one storage medium 230 via an internal communication bus 210. The at least one processor 220 is configured to execute the at least one instruction set. When the system 100 is running, the at least one processor 220 reads the at least one instruction set and executes the method P200 of group chat robot autonomous answer provided herein according to the indication of the at least one instruction set. The processor 220 may perform all the steps involved in the method P200 of group chat robot autonomous reply. Processor 220 may be in the form of one or more processors, and in some embodiments, processor 220 may include one or more hardware processors, such as microcontrollers, microprocessors, Reduced Instruction Set Computers (RISC), Application Specific Integrated Circuits (ASICs), application specific instruction set processors (ASIPs), Central Processing Units (CPUs), Graphics Processing Units (GPUs), Physical Processing Units (PPUs), microcontroller units, Digital Signal Processors (DSPs), Field Programmable Gate Arrays (FPGAs), Advanced RISC Machines (ARM), Programmable Logic Devices (PLDs), any circuit or processor capable of executing one or more functions, or the like, or any combination thereof. For illustrative purposes only, only one processor 220 is depicted in server 200 in this description. However, it should be noted that the server 200 may also include multiple processors, and thus, the operations or method steps disclosed in this specification may be performed by one processor or by a combination of multiple processors as described in this specification. For example, if in this description processor 220 of server 200 performs steps a and B, it should be understood that steps a and B may also be performed jointly or separately by two different processors 220 (e.g., a first processor performing step a, a second processor performing step B, or both a first and second processor performing steps a and B).

Although the above structure describes the server 200, this structure is also applicable to the client 300. The target client 301 may perform the method of group chat robot autonomous answer described in this specification. The method is described elsewhere in this specification. For example, a method P300 for the target client 301 to perform the group chat robot autonomous answer is introduced in the description of fig. 5 and 6.

Fig. 3 shows a flow chart of a method P200 of autonomous reply of a group chat robot. As described above, the server 200 may perform the method P200 of group chat robot autonomous response provided in the present specification. Specifically, the processor 220 in the server 200 may read an instruction set stored in its local storage medium and/or the database 150, and then execute the method P200 of group chat robot autonomous response provided by the present specification according to the specification of the instruction set. The method P200 may include executing, by at least one processor 220 at the server 200 side:

s220: receiving an input sentence, which is input by the target client 301 on the instant messaging group interface.

As described above, the method P200 for autonomous response of group chat robots is mainly used for group chat services. The target client 301 may have a generic instant messaging application installed thereon, e.g., a nail^TMAPP. Nail for nailing^TMThe APP can be provided with a service group, namely the instant messaging group. The service of the instant messaging group may be provided by the server 200, a group chat service server in the server 200, or the robot server. The instant messaging group provides a shared instant public messaging service on the interface for at least two users 110. For example, when a user (e.g., target user 111) enters a message in the instant messaging group, the message may be immediately visible to all other users (e.g., user 112, user 113, user 114, etc.). Any user 110 may answer the input message. All users 110 in the instant messaging group and the bot may be online at the same time. Target user 111 is a user in the instant messaging group.

The instant messaging group may be a transaction service group. Further, the instant messaging group may be a business service group customized to a particular group of people. The customer service robot in the instant messaging group can provide business consultation service for the users in the instant messaging group. The transaction is a transaction associated with the instant messaging group. Different users have different definitions of the transaction. For example, an automobile company-defined transaction may be a transaction related to an automobile, such as an engine of the automobile, tires of the automobile, and so forth. The financial company-defined transaction may be a transaction that is intended to be tied to a finance, such as a stock, fund, insurance, or the like. The definitions of transactions vary from department to department within the same automotive company. For example, the definition of a business by the engine department may be the model of the engine, the power of the engine, the displacement of the engine, and so on. For example, the definition of affairs in the automobile tyre sector can be the structure of the tyre, the bearing pressure of the tyre, the pattern of the tyre, etc. Since the transactions defined by different users are different, the transactions associated with different communication groups are also different. The instant messaging group often presets transactions according to the requirements of users, so the preset transactions are customized for the instant messaging group. The pre-set transactions may be supplemented, modified and altered. And the robots in the instant messaging group provide business consultation service according to the preset business.

Target user 111 may enter the input sentence through the instant messenger group interface on target client 301. The input sentence may be chat information input by target user 111 in real time in the instant messaging group. The input sentence can be voice data or text data. When the input sentence is voice data, the server 200 may convert the voice data into text data. The input sentence may be any sentence input by target user 111 in the instant messenger group, may be a communication sentence with user 110, or may be some puzzled or encountered difficulty, and so on. The input statement may be data related to the preset transaction or data unrelated to the preset transaction. The input sentence may be data of mutual conversation and communication among users in the instant messaging group, or may be a question asked by the target user 111 to the robot or the other user 110. The input sentence may not have any sign for asking a question to the robot, for example, in a situation where users have dialogue communication with each other, the input sentence is a natural dialogue between users, and thus there is no sign for asking a question to the robot. There may also be some questions in the input sentence, such as "what is flower".

The working mode of the instant messaging group can be as follows: the target user 111 inputs the input sentence on the instant messaging group interface of the target client 301, the input sentence is transmitted to the server 200 through the network 120, and the clients of other users in the instant messaging group, such as the client 302, the client 303, the client 304, and the like, actively monitor the server 200, and actively acquire the input sentence from the server 200 and display the input sentence on the instant messaging group interface once the input sentence is monitored.

S230: and generating a candidate list based on the input sentence and the preset knowledge base.

The server 200 may respond to the input sentence according to the content of the input sentence. Specifically, the server 200 may generate the candidate list related to the input sentence according to the content of the input sentence and the knowledge base preset by the instant messaging group. The preset knowledge base may be a set of knowledge points related to the preset transaction. The knowledge base may be used to specify the function or rule of the predetermined transaction. For example, the instant messaging group is a payment treasure transaction group, the preset transaction may be a transaction related to a payment treasure, and the preset knowledge base may include a plurality of knowledge points related to functions supported by the payment treasure. The knowledge base may include a plurality of preset knowledge points, and each knowledge point of the plurality of knowledge points includes a knowledge point title and a knowledge point answer. Generally, the knowledge point title may be a question asked for the preset transaction, and the knowledge point answer may be answer content to the question. For example, in a pay for treasures group, the knowledge points of the knowledge base may be "title: what flower is, answer: flower is a product to be borrowed. "," title: what the balance is, answer: the balance treasure is a money fund. "," title: forgetting what the password does, answer: and the password is retrieved by using the mobile phone number. "and the like. The knowledge base is preset based on preset affairs of the instant messaging group. The knowledge base may be supplemented, modified and altered. The knowledge base may be stored in the server 200 or in the database 150.

The candidate list may be a number of knowledge point headings associated with the input sentence generated by the server 200 from the input sentence and the knowledge base. The candidate list may include at least one recommended knowledge point associated with the input sentence. In particular, the candidate list may comprise at least one recommended knowledge point title related to the input sentence.

No matter what the input sentence is, in order to ensure that the robot can quickly respond to the questions related to the preset affairs of the instant messaging group and simultaneously not disturb the normal communication among the users 110 in the instant messaging group, the robot needs to perform affair question recognition on the input sentence and judge whether to provide answers by intervening in conversations. Fig. 4 shows a flowchart for implementing step S230, i.e., a flowchart for generating the candidate list, according to an embodiment of the present specification. Specifically, step S230 may include:

s232: identifying whether the input statement includes a target question associated with a preset transaction.

After the target user 111 inputs the input sentence through the instant messaging group on the target client 301, the server 200 needs to perform transaction question recognition on the input sentence to recognize whether the input sentence is a target question related to the preset transaction. When the input sentence is not a question related to the preset transaction, the server 200 does not respond to the input sentence; when the input sentence is a question related to the preset transaction, the server 200 autonomously responds to the input sentence. The target question related to the preset transaction may be a question related to a plurality of knowledge points in the knowledge base. The target question may also be at least one of a plurality of knowledge point titles in the knowledge base.

Server 200 may perform transaction question recognition on the input sentence through question recognition module 282 and transaction recognition module 284. Question recognition module 282 may receive the input sentence and be configured to recognize whether the input sentence is a question. The question recognition module 282 is trained based on a plurality of preset question templates. The preset question templates may be created based on question format information. The question recognition module 282 may match the input sentence with the preset question templates to determine whether any template matches the input sentence, so as to recognize whether the input sentence is a question sentence. In this specification, the question format information may include general question format information and statement-style question format information. The general question format may refer to a question format in a grammatical sense, for example, an explicit question format such as "how weather is", "what is nailed", "why the profit of the balance treasure is getting low", and the like. The statement format for the statement may refer to a statement format for describing a fact to seek a response (e.g., hope of others to help with processing), such as "attendance check fails", "help me approve", "no-go-to-do", and the like.

The transaction identification module 284 may receive the input statement and is configured to classify the input statement, i.e., transaction problem identification, and identify whether the input statement includes a target question related to the preset transaction. The transaction identification module 284 is obtained by training based on the preset knowledge base and preset non-transaction corpus information. The transaction identification module 284 may be a text classification model with a classification result of two classes. The transaction identification module 284 takes the preset knowledge base as a positive sample of training, and takes the preset non-transaction corpus information as a negative sample of training, so as to form a training sample set for model training. The ratio of the data amount of the positive sample to the data amount of the negative sample may be 1:1, or may be other ratios, such as 1.2:1, and so on. The server 200 inputs the input statement into the transaction identification module 284, and the output result of the transaction identification module 284 is that the input statement belongs to the knowledge base class or the input statement belongs to the non-transaction corpus class. The preset non-transaction corpus information may be general chatting information, such as "hello", "weather so today", and the like. When the output result of the transaction identification module 284 is that the input statement belongs to the knowledge base class, the server 200 determines that the input statement includes a target question related to the preset transaction, and the server 200 may autonomously respond to the target question; when the output result of the transaction identification module 284 is that the input sentence belongs to the non-transaction corpus class, the server 200 determines that the input sentence does not include the target question related to the preset transaction, and thus may choose not to answer. Through the arrangement, the users 110 can be disturbed as little as possible during normal chatting, and the use experience of the users is enhanced.

The transaction identification module 284 can include one of a FastText model, a CNN model, and an LSTM model. The type of text classification model employed by transaction identification module 284 may be determined based on the amount of data of the samples used in the training of the text classification model. For example, when the samples used in the text classification model training are large data volumes, a CNN model or LSTM model may be used. The FastText model can be used when the samples used in the training of the text classification model are small data volumes. The transaction recognition module 284 provided in this specification may determine the type of the text classification model used based on the data amount of the sample used in the text classification model training, and may select a suitable text classification model for classification based on different application scenarios, that is, transaction problem recognition, thereby improving the efficiency of transaction problem recognition.

The question recognition module 282 and the transaction recognition module 284 may perform question recognition on the input sentence first, perform transaction problem recognition on the input sentence only when the input sentence is a question, and perform no transaction problem recognition when the input sentence is not a question, which may effectively save the amount of computation and resources.

Specifically, step S232 may include:

s232-2: and matching the input sentence with the preset question templates to identify whether the input sentence is a question or not.

The server 200 performs question format matching on the input sentence through the question recognition module 282, and traverses all question formats in the preset question formats by using the input sentence. If there is a matching question format, the server 200 determines that the input sentence is a question sentence. Otherwise, the server 200 determines that the input sentence is not a question sentence. If the input sentence is judged as a question sentence by the server 200, the server 200 regards the input sentence as a potential transaction problem and performs transaction problem identification.

S232-4: and when the input statement is a question statement, classifying the input statement, and identifying whether the input statement comprises a target question related to the preset transaction.

When the input sentence is not a question sentence, the server 200 determines that the input sentence does not include a target question related to the preset transaction. The server 200 considers that the input sentence is not a question of the preset transaction, and does not respond to the input sentence.

When the input sentence is a question sentence, the server 200 needs to further classify the input sentence, that is, identify a transaction problem, and determine whether the input sentence includes a target question related to the preset transaction. Specifically, the server 200 classifies the input sentence through the transaction identification module 284, and identifies whether the input sentence includes a target question related to the preset transaction. When classifying the input statement, the transaction identification module 284 may perform word segmentation on the input statement first, for example, how to open the word segmentation of the input statement "flower over" identified as question sentence is "flower over", "how to open" and "open"; and then, carrying out text classification processing on the participles obtained after the participle processing. For example, in case the transaction identification module 284 is a FastText model, first, the transaction identification module 284 represents the participles "flower", "how" and "open" as three Word vectors, e.g., using Word2Vec to represent the participles "flower", "how" and "open" as 3 Word vectors; then, the transaction identification module 284 converts the resulting 3 word vectors into a semantic matrix using convolution processing; subsequently, transaction identification module 284 converts the semantic matrix into a semantic vector using pooling calculations; finally, the transaction identification module 284 performs classification by using a Softmax layer to obtain scores classified into the knowledge base class and the non-transaction corpus class, and outputs the class with the larger score as a text classification result of the transaction identification module 284. When the output result of the transaction identification module 284 is that the input statement belongs to the knowledge base class, the server 200 determines that the input statement includes a target question related to the preset transaction; when the output result of the transaction identification module 284 is that the input statement belongs to the non-transaction corpus class, the server 200 determines that the input statement does not include the target question related to the preset transaction.

In the method P200 and the system 100 for autonomous response of group chat robots provided in this specification, the question recognition module 282 and the transaction recognition module 284 are used to perform question recognition on the input sentences first, and only when the input sentences are question sentences, the input sentences are classified, that is, transaction problem recognition, is performed without performing transaction problem recognition on all the input sentences, so that the amount of calculation is reduced, and the work efficiency is improved.

In some embodiments, the server 200 may also identify, by the semantic recognition module, whether the input sentence includes a target question related to a preset transaction. The semantic recognition module may be trained based on historical input sentences. The history input statements may include questions related to the preset transaction, and may also include communication sessions between the users 110. The semantic recognition module can perform semantic analysis on the input statement and judge whether the semantics of the input statement comprise a target question related to the preset transaction or not according to the result of the semantic analysis. For example, the history input sentence related to the preset transaction may be "what the nail is", "why the profit of the balance treasures becomes low", "attendance checking fails, or" the treasure cannot be logged in ". For example, the historical input sentence that is not related to the preset transaction may be "what weather" or the like. For example, the input statement may be "i'm last month's balance treasure profit is 100, which is only 50 ' in this month". The server 200 may obtain a semantic analysis result that "the balance treasure yield becomes low" by performing semantic analysis on the input sentence, and thus, it is determined that the input sentence may include a target question related to the preset transaction. The server 200 may perform semantic recognition on the input sentence through the semantic recognition module, and analyze the semantic meaning desired to be expressed by the input sentence, thereby recognizing whether the input sentence includes the target question related to the preset transaction. The semantic recognition module can carry out semantic analysis on the input sentences of which the expression of the question sentences is not obvious and dig out the potential expression of the input sentences, thereby making more accurate judgment.

When the input sentence does not include the target question related to the preset transaction, the server 200 regards that the input sentence is not the question for the preset transaction, and does not respond to the input sentence. When the input sentence includes a target question related to the preset transaction, the server 200 may actively respond to the input sentence. Therefore, the server 200 (i.e. the robot) can actively respond to the transaction problem provided by the user 110 in the instant messaging group under the condition that the user 110 does not have the active @ robot, and the server 200 (i.e. the robot) can be ensured not to disturb the dialogue communication among the users 110 in the instant messaging group, so that the experience of the user is improved, meanwhile, the working pressure of artificial customer service can be relieved, the workload of the artificial customer service is reduced, the utilization rate of the robot is improved, and the working efficiency of the customer service (including the artificial customer service and the robot) is improved. Specifically, after recognizing that the input statement includes the target question related to the preset transaction, the server 200 may perform:

s234: determining that the input statement includes a target question related to the preset transaction.

S236: generating the candidate list based on the input sentence and the preset knowledge base.

As previously mentioned, the candidate list may include at least one recommended knowledge point title associated with the input sentence. In step S236, the server 200 may generate the candidate list to reply to the user by finding the knowledge point title most similar to the input sentence. In step S236, the generating a candidate list based on the input sentence and the preset knowledge base may include performing, by the at least one processor 220 of the server 200:

s236-2: and performing word segmentation processing on the input sentence, and extracting a keyword corresponding to the input sentence.

For example, the server 200 divides the input sentence 'how to open' into 'flower'; then, the keywords in the word segmentation obtained after the word segmentation processing are extracted, for example, the keywords are 'flower' and 'open'.

S236-4: and matching the keywords corresponding to the input sentence with the preset knowledge base to obtain at least one recall knowledge point, wherein the knowledge points comprise the at least one recall knowledge point.

After extracting the keywords of the input sentence, the server 200 matches the keywords of the input sentence with a plurality of knowledge points in the knowledge base, actually matches the keywords of the input sentence with a plurality of knowledge point titles in the knowledge base, and recalls at least one knowledge point matched with the keywords of the input sentence from the knowledge base as the recalled knowledge point. And the recalling selects the knowledge points matched with the keywords of the input sentence from the knowledge base. And the recalled knowledge points are selected candidate knowledge points. For example, the keywords of the input sentence are 'flower' and 'open'. The server 200 looks up in the knowledge base whether a knowledge point title consistent with the flower and the opening exists. For example, the title of the recall knowledge point may be "how to open flowers bei" and "how to adjust the amount after opening flowers |", etc.

S236-6: calculating an association value of the input sentence with the at least one recalled knowledge point.

After the server 200 recalls the at least one knowledge point, an associated value of the input sentence and each of the at least one recalled knowledge point may be calculated. The associated value may be a similarity value of the input sentence to the each recalled knowledge point. The server 200 calculates the semantic similarity value between the input sentence and the title of each recalled knowledge point by performing semantic analysis on the input sentence.

S236-8: and selecting at least one recommended knowledge point from the at least one recalled knowledge point based on the association value, and generating the candidate list based on the title of the recommended knowledge point.

After the server 200 calculates the association value between the input sentence and each recall knowledge point, the at least one recall knowledge point is sorted based on the association value. The ranking may be ranking the at least one recalled knowledge point from large to small based on the relevance value. The server 200 may select at least one recalled knowledge point with the largest association value from the at least one recalled knowledge point as a recommended knowledge point, and generate the candidate list according to a title of the recommended knowledge point. The candidate list may comprise at least one recommended knowledge point title.

The server 200 selects the recommended knowledge point with the highest similarity with the input sentence from the knowledge base as the candidate list to be sent to the instant messaging group, so that the self-response accuracy of the customer service group chat robot is improved, and the user experience is improved. After generating the candidate list, the server 200 continues to perform:

s240: and sending the candidate list to the instant messaging group.

After the server 200 generates the candidate list, the candidate list may be sent to the instant messaging group. In order not to disturb the users 110 in the instant messaging group, the candidate list is marked as visible only to a first group of clients 310 in the instant messaging group, the first group of clients 310 being part of the clients including the target client 301. The first group of clients 310 may be target clients 301 in the instant messaging group, may be clients of users having special rights, such as clients of a group owner, clients of an administrator, and the like, and may be clients selected by the target clients 301, such as clients selected by the target clients 301, which may select to display the candidate list to be visible to a specific user in the instant messaging group after receiving the candidate list. The first group of clients 310 may also be clients in the instant messaging group corresponding to historical input sentences related to the input sentence. For example, the input statement may be 'how the amount of flowers is adjusted', the history input statement related to the input statement may be 'my amount of flowers is not enough', and then the client corresponding to the history input statement may be part of the first group of clients 310.

The candidate list may be made visible to only a first set of clients 310 in the instant messaging group in a variety of ways. This can be achieved, for example, by defining attribute data of the candidate list. The attribute data may be tag data, data symbol, and any other data that can be marked. The attribute data of the candidate list is marked as visible only to the first group of clients 310 in the instant messaging group, specifically, the tag data of the candidate list is associated with the devices of the first group of clients 310, or the attribute data has the same mark as the first group of clients 310, so that only the first group of clients 310 can listen to the candidate list in the server 200, and thus, only the first group of clients 310 can receive the candidate list. In addition, it is also possible to reserve a specific display bit identification bit in the data structure of the candidate list, and then define which clients are visible in the instant messaging group by assigning a value to the display bit identification bit. When the client 300 listens to the information in the instant messaging group running on the server 200, the client 300 first detects whether the value of the display flag allows the client to display itself. For the first group of clients 310, the value of the display flag allows itself to display the contents of the candidate list, and for the other clients 300, the value of the display flag does not allow itself to display the contents of the candidate list. Thus, the display identification bits allow only the first group of clients 310 to listen to the candidate list in the server 200.

The candidate list may be sent directly to and displayed in the instant messaging group of the first group of clients 310, or may be expressed in a less intrusive manner. For example, the server 200 presents a list display request to the interface of the instant messaging group of the first set of clients 310. When the user chooses to agree to display the candidate list, server 200 may display the candidate list. When the user selects not to agree to display the candidate list, the server 200 does not display the candidate list. The list display request may be an actionable icon displayed on the instant messaging group interface of the first set of clients 310. For example, the server 200 displays a red dot icon next to the input sentence on the instant messenger group interface of the target client 301 to indicate the candidate list recommended by the robot. The candidate list is only displayed when the target user 111 touches or clicks on this red icon. Alternatively, some or all of the other users of first group of clients 310 may display the candidate list by touching or clicking on the red icon. In this way, the server 200 can do as little disturbance as possible on the target communication interface to the normal communication between the target user 111 and the other users 110.

To implement the above function, the server 200 may send the candidate list to the instant messaging group, including the following steps: the server 200 sends first icon data to the instant messaging group, wherein the attribute of the first icon data is marked to be only visible to the first group of clients 310, and the first icon data comprises the list display request, for example, the first icon data comprises a link pointing to the list; server 200 receives a signal that any one of the clients in first set of clients 310 triggers the list display request (e.g., the icon is triggered at any one of the clients in first set of clients 310), the link is activated; the server 200 sends the candidate list to the instant messaging group, marked as visible to the client that triggered the list display request.

The server 200 sending the candidate list to the instant messaging group may further be: the server 200 simultaneously transmits the candidate list and first icon data to the instant messaging group, wherein the first icon data comprises a list display request, an attribute of the first icon data is marked to be visible only to the first group of clients 310, and the candidate list and the first icon data are defined as: the first icon data is first displayed on the first group of clients 310, and when the first icon data is triggered by any client in the first group of clients 310, the candidate list is displayed on the client that triggered the first icon data. When any one of the clients in the first group of clients 310 receives the candidate list and the first icon data, the client only displays the first icon data, which may be an operable icon, and only displays the candidate list on the interface when the user triggers the operable icon.

S250: a selection of the candidate list by an administrative client in the first set of clients 310 is received.

As previously mentioned, the candidate list may include at least one recommended knowledge point title associated with the input sentence. After receiving the candidate list, the target user 111 may select one or more recommended knowledge point titles that are most relevant to the question or most concerned or most wanted to view from the candidate list, so as to view answer content corresponding to the selected titles. At this time, the target client 301 is the management client. Server 200 may receive a selection of target user 111 on target client 301. Of course, the managing client may also be another client in the first set of clients 310. For example, the management client may be some clients (such as an administrator) with special rights in the first group of clients 310, and the management client may also be any client in the first group of clients 310. At this time, the users in the first group of clients 310 may all make selections on the candidate list, and the server 200 may receive the selections of the users in the first group of clients 310 on the corresponding clients.

S270: and sending the target answer matched with the selection to the instant messaging group.

The target answer may be a target knowledge point answer corresponding to the knowledge point title selected by the target client 301. After receiving the selection of the target user 111 on the target client 301, the server 200 may send the target answer to the instant messaging group. Wherein the target answer is marked as visible to a second set of clients 320 in the instant messaging group. The second group of clients 320 may comprise at least a portion of the clients in the instant messaging group and may also comprise the target client 301. The second group of clients 320 may be clients corresponding to the user selected by the target user 111 from the instant messaging group, may be clients in the first group of clients 310, may be clients selecting the candidate list from the first group of clients 310, or may be all the clients 300. Of course, the second group of clients 320 may also be the clients corresponding to the users selected from the instant messaging group by the management client in the first group of clients 310.

There are various ways for the server 200 to send the target answer to the instant messenger group. The target answer may be directly sent to and displayed in the instant messaging group of the second group of clients 320, or the above-mentioned low-invasive expression may be adopted. For example, the server 200 may display the target answer when the user selects to approve the display of the target answer, and the server 200 may not display the target answer when the user selects to disapprove the display of the target answer. The answer display request may be an actionable icon displayed on the instant messaging group interface of the second group of clients 320. For example, server 200 displays a red dot icon next to the candidate list or the target user's 111 selection of the candidate list on the instant messenger group interface of target client 301 to indicate the target answer that the robot recommends here. The target answer is only displayed when the target user 111 touches or clicks this red dot icon. Alternatively, some or all of the other users of the second group of clients 320 may display the target answer by touching or clicking the red icon. In this way, the server 200 can do as little disturbance as possible on the target communication interface to the normal communication between the target user 111 and the other users 110.

The server 200 transmitting the target answer to the instant messaging group may include: the server 200 sends second icon data to the instant messaging group, wherein the attribute of the second icon data is marked to be visible only to the second group of clients 320, and the second icon data comprises the answer display request, for example, the first icon data comprises a link pointing to the list; the server 200 receives a signal that any one of the second group of clients 320 triggers the answer display request (e.g., the icon is triggered at any one of the second group of clients 320), the link is activated; the server 200 sends the target answer to the instant messaging group, and the target answer is marked to be visible to the client terminal triggering the answer display request.

The server 200 may send the target answer to the instant messaging group by: the server 200 simultaneously sends the candidate list and second icon data to the instant messaging group, wherein the second icon data comprises an answer display request, the attribute of the second icon data is marked to be visible only to the second group of clients 320, and the target answer and the second icon data are defined as: the second icon data is first displayed on the second group of clients 320, and when the second icon data is triggered by any client in the second group of clients 320, the target answer is displayed on the client that triggered the second icon data. When any one of the clients 320 in the second group receives the target answer and the second icon data, the client only displays the second icon data, which may be an operable icon, and only displays the target answer on the interface when the user triggers the operable icon.

When the server 200 sends the target answer to the client 300, semantic analysis may be performed according to the semantics of the input sentence or in combination with the semantics of the historical input sentence, and the target answer is given in a dialogue communication manner according to the result of the semantic analysis, so as to improve the user experience. For example, the input statement is "how to return, i'm the month the profit of the balance treasure is 100, but this month only has 50! ". The server 200 may answer "the guest does not worry about, balance treasury float is normal because … …", and then give the target answer. Compared with a mechanical response, the intelligent dialogue communication type response can be more easily accepted by the user 110, the user 110 is answered in a relaxed and pleasant atmosphere, the sensitivity and the rejection of the user 110 to artificial intelligence are reduced to a certain extent, meanwhile, the adhesion degree of the user 110 and the robot is improved, and the utilization rate of the robot is improved.

As shown in fig. 3, the method P200 may further include, by the at least one processor 220 of the server 200:

s280: an answer evaluation request is sent to the target client 301.

S290: an answer evaluation of the target client 301 is received.

After the server 200 transmits the target answer to the target client 301, the server 200 may further transmit an answer evaluation request to the target client 301, request the target user 111 to evaluate the displayed answer content, and receive the answer evaluation result of the target client 301, and store the answer evaluation result in the server 200 or the database 150, so as to facilitate upgrading and improvement of the server 200.

To sum up, in the method P200 for autonomous response of group chat robots provided in this specification, after receiving an input sentence sent by a target user 111 in an instant messaging group, a server 200 generates a candidate list related to the input sentence based on the input sentence and a preset knowledge base, and sends the candidate list to a target client 301 corresponding to the target user 111 or a first group of clients 310 including the target client 301, so as to reduce the influence on other users; after the target user 111 selects the candidate list, the target answer matched with the selection is sent to the target client 301 corresponding to the target user 111 or a second group of clients 320 including the target client 301. The method P200 can actively answer the questions posed by the user, meanwhile, interference to other users in group chat is avoided, and the user experience can be improved while the working efficiency is improved.

Fig. 5 shows a flowchart of a method P300 of autonomous reply of a group chat robot. As described above, the client 300 may execute the method P300 of group chat robot autonomous response provided in the present specification. In particular, at least one processor in the target client 301 may read a set of instructions stored in its local storage medium and/or the database 150, and then execute the method P300 of group chat robot autonomous answer provided by the present specification, as specified by the set of instructions. The method P300 may include performing, by at least one processor of the target client 301:

s310: and receiving the input statement and sending the input statement to the server 200.

The input sentence is input by the target user 111 on the instant messaging group interface.

S330: and receiving the candidate list sent by the server 200 end and displaying the candidate list on the instant messaging group interface.

After receiving the candidate list, the target client 301 may display the candidate list on the instant messaging group interface. The candidate list may be presented directly on the instant messaging group interface or in a less intrusive manner. For example, a list display request is presented on the instant messaging group interface, and the target user 111 may make a selection operation on the list display request. When target user 111 chooses to agree to display the candidate list, target client 301 displays the candidate list on the instant messaging group interface. When target user 111 selects not to agree to display the candidate list, target client 301 does not display the candidate list on the instant messaging group interface.

Step S330 may include: receiving the candidate list and the first icon data sent by the server 200, where the first icon data includes the list display request, and the first icon data can be displayed as an operable icon at the client 300, where the first icon data is defined as: when the first icon data is triggered by a user, displaying the candidate list at a client terminal which triggers the first icon data; receiving a trigger operation of the target user 111 on the first icon data; and displaying the candidate list in the instant messaging group.

Fig. 6 illustrates a schematic diagram 600 of the instant messaging group interface provided according to an embodiment of the present disclosure. As shown in fig. 6, the first icon data may be an icon 620, which is displayed on the instant messaging group interface of the target client 301, and checking or clicking the icon 620 represents that the display is approved, and not checking or clicking the icon represents that the display is not approved. For example, the server 200 displays a red dot next to the input sentence 640 on the instant messenger group interface of the target client 301 to indicate the candidate list recommended by the robot. The answer content is displayed only when the target user 111 touches or clicks on this red dot.

S350: the selection of the candidate list by target user 111 is received and sent to server 200.

As previously mentioned, the candidate list may include at least one recommended knowledge point. The selection of the candidate list by the target user 111 comprises selecting one or more recommended knowledge points from the at least one recommended knowledge point, which are most relevant to the own question or most concerned or most wanted to view by the own. Target client 301 may send the selection to server 200.

S370: sending the selection to the instant messaging group.

The target client 301 may also send the selection to the instant messaging group. The selection may be marked as visible to all users or to a portion of users in the instant messaging group. Target user 111 may make a selection of visible users from the instant messaging group.

S380: receiving the target answer matched with the selection sent by the server 200.

After receiving the target answer, the target client 301 may display the target answer on the instant messaging group interface. The target answer may be marked as visible to all users or a portion of users in the instant messaging group. Target user 111 may make a selection of visible users from the instant messaging group. The target answer may be displayed directly on the instant messaging group interface or may be displayed on the instant messaging group interface in a low-intrusion manner. For example, an answer display request is presented on the instant messaging group interface, and the target user 111 may make a selection operation on the answer display request. When the target user 111 selects to agree to display the target answer, the target client 301 displays the target answer on the instant messaging group interface. When the target user 111 selects not to agree to display the target answer, the target client 301 does not display the target answer on the instant messaging group interface.

Step S380 may include: receiving the target answer and the second icon data sent by the server 200, where the second icon data includes the answer display request, and the second icon data may be displayed as an operable icon at the client 300, where the second icon data is defined as: when the second icon data is triggered by a user, displaying the target answer at a client terminal which triggers the second icon data; receiving a trigger operation of the target user 111 on the second icon data; and displaying the target answer in the instant messaging group.

To sum up, according to the method P200, the method P300, and the system 100 for autonomous response of the group chat robot provided in the present specification, after receiving an input sentence sent by a target user 111 in the instant messaging group, the server 200 generates a candidate list related to the input sentence based on the input sentence and the preset knowledge base, and sends the candidate list to a target client 301 corresponding to the target user 111 or a first group of clients 310 including the target client 301, so as to reduce the influence on other users; after the target user 111 or the management client in the first group of clients 310 selects the candidate list, the target answer matching the selection is sent to the second group of clients 320. The method P200, the method P300 and the system 100 can actively answer the questions posed by the user, meanwhile, interference to other users in group chat is avoided, and the user experience can be improved while the working efficiency is improved.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

In conclusion, upon reading the present detailed disclosure, those skilled in the art will appreciate that the foregoing detailed disclosure can be presented by way of example only, and not limitation. Those skilled in the art will appreciate that the present specification contemplates various reasonable variations, enhancements and modifications to the embodiments, even though not explicitly described herein. Such alterations, improvements, and modifications are intended to be suggested by this specification, and are within the spirit and scope of the exemplary embodiments of this specification.

Furthermore, certain terminology has been used in this specification to describe embodiments of the specification. For example, "one embodiment," "an embodiment," or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined as suitable in one or more embodiments of the specification.

It should be appreciated that in the foregoing description of embodiments of the specification, various features are grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the specification, for the purpose of aiding in the understanding of one feature. This is not to be taken as an admission that any of the features are required in combination, and it is fully possible for one skilled in the art to extract some of the features as separate embodiments when reading this specification. That is, embodiments in this specification may also be understood as an integration of a plurality of sub-embodiments. And each sub-embodiment described herein is equally applicable to less than all features of a single foregoing disclosed embodiment.

Each patent, patent application, publication of a patent application, and other material, such as articles, books, descriptions, publications, documents, articles, and the like, cited herein is hereby incorporated by reference. All matters hithertofore set forth herein except as related to any prosecution history, may be inconsistent or conflicting with this document or any prosecution history which may have a limiting effect on the broadest scope of the claims. Now or later associated with this document. For example, if there is any inconsistency or conflict in the description, definition, or use of a term associated with any of the contained materials with respect to the terms, descriptions, definitions, or uses associated with this document, the terms in this document shall prevail.

Finally, it should be understood that the embodiments of the application disclosed herein are illustrative of the principles of the embodiments of the present specification. Other modified embodiments are also within the scope of this description. Accordingly, the disclosed embodiments are to be considered in all respects as illustrative and not restrictive. Those skilled in the art may implement the applications in this specification in alternative configurations according to the embodiments in this specification. Therefore, the embodiments of the present description are not limited to the embodiments described precisely in the application.

Claims

1. A method for autonomous response of group chat robots comprises the following steps:

receiving an input statement, wherein the input statement is input by a target client on an instant messaging group interface;

generating a candidate list based on the input sentence and a preset knowledge base, wherein the candidate list comprises at least one recommended knowledge point related to the input sentence;

sending the candidate list to the instant messaging group, wherein the candidate list is marked to be only visible to a first group of clients in the instant messaging group, and the first group of clients are part of clients including the target client;

receiving a selection of the candidate list by a management client in the first set of clients; and

and sending a target answer matched with the selection to the instant messaging group, wherein the target answer is marked to be visible to a second group of clients in the instant messaging group, and the second group of clients comprises at least part of clients in the instant messaging group.

2. The method of group chat robot autonomous answer of claim 1, wherein the sending the candidate list to the instant messaging group comprises:

sending first icon data to the instant messaging group, the first icon data being marked as visible only to the first group of clients, the first icon data comprising a list display request;

receiving a signal that the first group of clients triggers the list display request;

sending the candidate list to the instant messaging group, the candidate list marked as visible to a client that triggered the list display request.

3. The method of group chat robot autonomous answer of claim 1, wherein the sending the candidate list to the instant messaging group comprises:

sending the candidate list and the first icon data to the instant messaging group,

wherein the first icon data is marked as visible only to the first set of clients, the first icon data comprising a list display request, the candidate list being displayed at the client that triggered the first icon data when the first icon data is triggered by the client.

4. The method of group chat robot autonomous answer of claim 1, wherein the sending the target answer matching the selection to the instant messaging group comprises:

sending the target answer and second icon data to the instant messaging group,

wherein the second icon data is marked as visible to the second set of clients, the second icon data including an answer display request, the target answer being displayed at the client that triggered the second icon data when the second icon data is triggered by the client.

5. The method of group chat robot autonomous answer of claim 1, wherein the generating a candidate list based on the input sentence and a preset knowledge base comprises:

identifying whether the input statement comprises a target question related to a preset transaction, wherein the preset transaction is customized for the instant messaging group;

determining that the input sentence includes the target question; and

and generating the candidate list based on the input sentence and the preset knowledge base.

6. The method of group chat robot autonomous answer of claim 5, wherein the identifying whether the input sentence includes a target question related to a preset transaction comprises:

matching the input sentence with a plurality of preset question templates to identify whether the input sentence is a question sentence; and

and when the input statement is a question statement, classifying the input statement, and identifying whether the input statement comprises a target question related to the preset transaction.

7. The method of group chat robot autonomous reply of claim 1, further comprising:

sending an answer evaluation request to the instant messaging group, wherein the answer evaluation request is marked to be visible only to the target client; and

and receiving answer evaluation of the target client.

8. The method of group chat robot autonomous answer of claim 1, wherein the administrative client comprises the target client.

9. The method of group chat robot autonomous answer of claim 1, wherein the second set of clients comprises: and the management client selects the client from the instant communication group or all the clients in the instant communication group.

10. A system for autonomous response of group chat robots, comprising:

at least one storage medium comprising at least one instruction set for group chat robotic autonomous response; and

at least one processor communicatively coupled to the at least one storage medium,

wherein when the system is running, the at least one processor reads the at least one instruction set and performs the method of group chat robot autonomous answer of any of claims 1-9 according to the indication of the at least one instruction set.

11. A group chat robot autonomous response method is applied to a target client and comprises the following steps:

receiving an input statement and sending the input statement to a server, wherein the input statement is input by a target user on an instant messaging group interface;

receiving a candidate list sent by the server and displaying the candidate list on the instant messaging group interface, wherein the candidate list is generated based on the input statement and a preset knowledge base, the candidate list is marked to be visible only to a first group of clients in the instant messaging group, the first group of clients are partial clients including the target client, and the candidate list comprises at least one recommended knowledge point related to the input statement;

receiving the selection of the target user to the candidate list, and sending the selection to the server;

sending the selection to the instant messaging group; and

and receiving a target answer which is matched with the selection and is sent by the server, wherein the target answer is marked to be visible to a second group of clients in the instant messaging group, and the second group of clients comprise at least part of clients in the instant messaging group.

12. The method for autonomous reply of group chat robots as claimed in claim 11, wherein the receiving of the candidate list sent by the server comprises:

receiving the candidate list and first icon data sent by the server, wherein the first icon data comprise a list display request, and when the first icon data are triggered by a client, the candidate list is displayed at the client triggering the first icon data;

receiving a trigger operation of the target user on the first icon data; and

and displaying the candidate list in the instant messaging group.

13. A system for autonomous response of group chat robots, comprising:

wherein when the system is running, the at least one processor reads the at least one instruction set and performs the method of group chat robot autonomous answer of any of claims 11-12 according to the indication of the at least one instruction set.