CN119719261A

CN119719261A - Answering method, device, electronic device and storage medium

Info

Publication number: CN119719261A
Application number: CN202311249059.XA
Authority: CN
Inventors: 雷耀强; 甘釜宾
Original assignee: Mashang Consumer Finance Co Ltd
Current assignee: Mashang Consumer Finance Co Ltd
Priority date: 2023-09-25
Filing date: 2023-09-25
Publication date: 2025-03-28

Abstract

The embodiment of the disclosure provides a response method, a device, electronic equipment and a storage medium, wherein the response method comprises the steps of determining a target knowledge theme corresponding to a business consultation request, determining a target knowledge image corresponding to the target knowledge theme in a preset image set according to the target knowledge theme, wherein the target knowledge image comprises a plurality of nodes, each node corresponds to at least one knowledge message, acquiring additional consultation information which is supplementary information of the business consultation request, determining a target node in the target knowledge image according to the additional consultation information, and performing response processing according to the knowledge information corresponding to the target node. Thus, the response efficiency can be improved when responding to the business consultation request.

Description

Response method, response device, electronic equipment and storage medium

Technical Field

The present application relates to the field of communications, and in particular, to a response method, a device, an electronic apparatus, and a storage medium.

Background

In the scenario of consultation response, manual response is a very common response mode. The requirements of the consultant can be rapidly understood by manually carrying out consultation response, the stamina state of the consultant can be accurately perceived, and the response mode can be adaptively adjusted.

Disclosure of Invention

The embodiment of the application provides a response method, a response device, electronic equipment and a storage medium, so as to improve response efficiency.

In a first aspect, an embodiment of the present application provides a response method, including:

Determining a target knowledge theme corresponding to the business consultation request;

Determining a target knowledge image corresponding to the target knowledge topic in a preset image set according to the target knowledge topic, wherein the target knowledge image comprises a plurality of nodes, and each node corresponds to at least one knowledge message;

Acquiring additional consultation information, wherein the additional consultation information is supplementary information of the business consultation request;

and determining a target node in the target knowledge image according to the additional consultation information, and performing response processing according to knowledge information corresponding to the target node.

In a second aspect, an embodiment of the present application provides a response device, including:

the determining unit is used for determining a target knowledge theme corresponding to the business consultation request;

the determining unit is further used for determining a target knowledge image corresponding to the target knowledge theme in a preset image set according to the target knowledge theme, wherein the target knowledge image comprises a plurality of nodes, and each node corresponds to at least one piece of knowledge information;

The acquisition unit is used for acquiring additional consultation information which is the supplementary information of the business consultation request;

And the response unit is used for determining a target node in the target knowledge image according to the additional consultation information and carrying out response processing according to the knowledge information corresponding to the target node.

In a third aspect, an embodiment of the application provides an electronic device comprising a processor and a memory configured to store computer-executable instructions that, when executed, cause the processor to perform the answering method according to the first aspect.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing computer-executable instructions which, when executed by a processor, implement the answering method according to the first aspect.

It can be seen that in the embodiment of the application, firstly, a target knowledge topic corresponding to a service consultation request is determined, secondly, a target knowledge image corresponding to the target knowledge topic is determined in a preset image set according to the target knowledge topic, the target knowledge image comprises a plurality of nodes, each node corresponds to at least one knowledge message, then, additional consultation information is acquired, the additional consultation information is supplementary information of the service consultation request, then, a target node is determined in the target knowledge image according to the additional consultation information, and response processing is performed according to the knowledge information corresponding to the target node. Therefore, on one hand, the target knowledge image corresponding to the target knowledge theme comprises a plurality of nodes, each node corresponds to at least one knowledge information, so that one target knowledge image can cover a large amount of knowledge on which a service consultation request depends, knowledge information corresponding to each node in the target knowledge image is utilized for answering, knowledge required for answering is avoided to be checked by manually switching back and forth among a plurality of knowledge documents, answering efficiency is improved, error rate of manual answering is reduced, on the other hand, when the service consultation request is answered, a sender of the service consultation request needs to reply after supplementing some additional consultation information, the current corresponding target node is positioned in the target knowledge image and answered through the additional consultation information, each speaking of the sender can be answered in a targeted mode in the consultation process, and consultation experience is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are only some embodiments described in the present specification, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art;

FIG. 1 is a schematic diagram of an environment for implementing a response method according to an embodiment of the present application;

FIG. 2 is a process flow diagram of a response method according to an embodiment of the present application;

FIG. 3 is a configuration interface diagram of a knowledge image according to an embodiment of the application;

FIG. 4 is a diagram of a knowledge image display interface according to an embodiment of the present application;

fig. 5 is a node information configuration page of a judging node according to an embodiment of the present application;

Fig. 6 is a node information configuration page of an image node according to an embodiment of the present application;

FIG. 7 is a process flow diagram of another response method according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a response device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the embodiments of the present application, the technical solutions of 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 specification, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

The response method provided by one or more embodiments of the present disclosure may be applied to an implementation environment of the response method, and as shown in fig. 1, the implementation environment includes at least a server 101 for responding to a service consultation request, and a terminal device 102 for sending the service consultation request.

The server 101 may be a server, or a server cluster formed by a plurality of servers, or one or more cloud servers in a cloud computing platform, which are used for responding to a service consultation request.

The terminal device 102 may be a mobile phone, a personal computer, a tablet computer, an electronic book reader, a device for performing information interaction based on VR (Virtual Reality technology), a vehicle-mounted terminal, an IoT device, a wearable intelligent device, a laptop portable computer, a desktop computer, etc., the terminal device 102 may configure a client of an application program, where a specific form of the client may be an application program, a sub-program in the application program, a service module in the application program, or a web page program, and the client may send a service consultation request to the server 101.

In the implementation environment, a server 101 determines a target knowledge topic corresponding to a service consultation request in the process of responding to the service consultation request sent by a terminal device 102, determines a target knowledge image corresponding to the target knowledge topic in a preset image set according to the target knowledge topic, wherein the target knowledge image comprises a plurality of nodes, each node corresponds to at least one knowledge message, acquires additional consultation information which is supplementary information of the service consultation request, determines a target node in the target knowledge image according to the additional consultation information, and carries out response processing according to the knowledge information corresponding to the target node. Therefore, the target knowledge image corresponding to the target knowledge subject comprises a plurality of nodes, each node corresponds to at least one knowledge message, so that one target knowledge image can cover a large amount of knowledge on which the service consultation request depends, knowledge messages corresponding to each node in the target knowledge image are utilized for responding, knowledge required by the response can be prevented from being checked by manually switching back and forth among a plurality of knowledge documents, response efficiency is improved, and error rate of manual response is reduced.

The present specification provides an embodiment of a response method:

In the scenario of manually performing consultation response, a worker often needs to memorize a large amount of business information, so as to provide good consultation services for the consultant in time. In the case that the detailed data of the business information is more, the staff member may rely on the query of the knowledge document, for example, the staff member searches the one or more knowledge documents corresponding to the business consulted by the consultant for the answer information required by the consultant, and then provides the answer information to the consultant. However, the patience of the consultant may significantly decrease as the waiting time increases. In the case where the information of interest to the consultant involves a plurality of knowledge documents, the staff may need to switch back and forth between the plurality of knowledge documents, which is time consuming and may be erroneous, reducing the efficiency of the response and bringing bad experience to the consultant. In order to solve the above problems, an embodiment of the present application provides a response method.

Fig. 2 is a process flow diagram of a response method according to an embodiment of the present application. Referring to fig. 2, the response method provided in the present embodiment specifically includes steps S202 to S208.

Step S202, determining a target knowledge topic corresponding to the business consultation request.

The business consultation request may be a request issued when the consultant makes a consultation with respect to the target business. Consultants include, but are not limited to, persons interested in the target business but not yet transacting the target business, and persons who have transacted the target business.

The target service may be a service capable of providing a service or a product to the user. For example, in a resource lending scenario, the target business may be a repayment advance settlement business, in a transaction scenario, the target business may be a discount area sales business, and so on.

Before determining the target knowledge topic corresponding to the service execution request, the service consultation request can be acquired. The obtaining of the service consultation request may be receiving the service consultation text, and generating a corresponding service consultation request according to the service consultation text.

The business consultation text can be text input by a consultant when asking questions for the target business.

For example, business consultation text 1 is how do you get you, i want to pay in advance?

Business consultation text 2 is that i purchase product a with quality problems, what credentials are needed to return the goods?

Business consultation text 3 is when my order 1 is shipped?

The business consultation text can also be text input when the consultant applies to transact/stop the target business.

For example, business consultation text 4 is how do you get good, business a transacted?

Business consultation text 5 is you in good order, i want to transact business a.

Referring to the business consultation text 5 in the above example, in the case where the consultant expresses a desire to apply for handling or for suspending the target business, a question about how to handle the target business or how to suspend the target business is implied in the business consultation text.

The business consultation request in this embodiment may also be replaced by a business transaction request or a business suspension request. The business transaction request may be a request submitted by an applicant to apply for a transaction target business. The service suspension request may be a request submitted by an applicant to suspend a target service. The response flow to the business transaction request or the business suspension request may refer to the response flow to the business consultation request in this embodiment.

The service consultation request can be obtained, or the service consultation voice can be received, and the corresponding service consultation request can be generated according to the service consultation voice.

The business consultation voice may be a voice sent by the consultant when asking questions for the target business, or a voice sent by the consultant when applying for handling/stopping the target business.

In a specific implementation mode, the business consultation request carries a request text, and the determining of the target knowledge topics corresponding to the business consultation request comprises the steps of respectively performing text similarity calculation processing on each knowledge topic in a preset knowledge topic set according to the request text to obtain text similarity of each knowledge topic, and determining the target knowledge topic of the business consultation request according to the text similarity of each knowledge topic.

The request text carried in the service consultation request can be the service consultation text, or can be the text obtained after the voice-to-word processing of the service consultation voice.

In particular implementations, a preset knowledge topic set may be configured at the knowledge base, the preset knowledge topic set including a plurality of knowledge topics.

In information technology, knowledge (knowledges) refers to the possession of information, or the ability to quickly locate information, to an organization or individual.

The knowledge center can be a knowledge management platform at the level of an organization, all knowledge of the organization is recorded in the knowledge center, and related knowledge is required by business systems or platforms of various departments of the organization to be acquired through the knowledge center.

The knowledge entered in the knowledge center may be stored in the form of a document, i.e. the knowledge center stores a plurality of knowledge documents, each of which stores a different knowledge. Each knowledge document may correspond to a knowledge topic. The knowledge topics corresponding to each knowledge document can be obtained by refining the central ideas of the content of the knowledge document.

Illustratively, the knowledge document for storing business consultation procedure knowledge of the a business may correspond to a knowledge topic "business a consultation procedure".

And carrying out text similarity calculation processing according to the request text and each knowledge topic in the preset knowledge topic set to obtain the text similarity between the request text and each knowledge topic. And regarding each knowledge topic, taking the text similarity between the knowledge topic and the request text as the text similarity of the knowledge topic.

The target knowledge subject of the business consultation request and the target knowledge subject corresponding to the business consultation request are the same concept.

According to the text similarity of each knowledge topic, determining a target knowledge topic of the business consultation request, namely sorting according to the numerical value of the text similarity of each knowledge topic to obtain a sorting result, determining the text similarity with the largest numerical value according to the sorting result, and determining the knowledge topic corresponding to the text similarity with the largest numerical value as the target knowledge topic.

For example, how does the request text 1:A business transact?

Knowledge topic 1 is "A business process," knowledge topic 2 is "B business process," knowledge topic C is "C business suspension process," and so on.

Performing text similarity calculation processing according to the request text 1 and the knowledge topic 1 to obtain text similarity s1 of the knowledge topic 1;

performing text similarity calculation processing according to the request text 1 and the knowledge topics 2 to obtain text similarity s2 of the knowledge topics 2;

And carrying out text similarity calculation processing on the request text 1 and the knowledge topics 3 to obtain the text similarity s3 of the knowledge topics 3.

S1> s2> s3, and determining the knowledge topic 1 corresponding to s1 as the target knowledge topic.

In practical applications, a user may express the same question by a plurality of different question methods when asking a question.

For example, request text 1 how does business a transact?

Request text 2 i want to transact business a, what is needed?

Request text 3, hello, i wants to consult business a handling mode.

In consideration of the above situation, a plurality of corresponding consultation sentences can be preconfigured for each knowledge topic, text similarity calculation processing is respectively carried out according to the request text and each consultation sentence of each knowledge topic in a preset knowledge topic set to obtain the text similarity of each knowledge topic, and the target knowledge topic of the business consultation request is determined according to the text similarity of each knowledge topic.

According to the request text and each consultation sentence of each knowledge topic in the preset knowledge topic set, text similarity calculation processing is carried out, and the text similarity of each knowledge topic is obtained, which can be realized in the following manner:

And determining the one with the largest text similarity between each consultation sentence of the knowledge topic and the second semantic recognition result as the text similarity of the knowledge topic according to each consultation sentence of the knowledge topic in the request text and the preset knowledge topic set.

For example, knowledge topic A has three pre-configured advisory statements, statement X1, statement X2, and statement X3.

Performing text similarity calculation processing according to the request text 1 and the sentence X1 to obtain text similarity S1 between the request text 1 and the sentence X1;

performing text similarity calculation processing according to the request text 1 and the sentence X2 to obtain text similarity S2 between the request text 1 and the sentence X2;

And performing text similarity calculation processing according to the request text 1 and the sentence X1 to obtain the text similarity S3 between the request text 1 and the sentence X3.

S1> S2> S3, and S3 is determined as the text similarity of the knowledge topic A.

Step S204, determining a target knowledge image corresponding to the target knowledge topic in a preset image set according to the target knowledge topic, wherein the target knowledge image comprises a plurality of nodes, and each node corresponds to at least one piece of knowledge information.

The target knowledge image corresponding to the target knowledge topic may be a knowledge image for describing a business consultation process, which is determined by the target knowledge topic.

The target knowledge topic may determine a corresponding one or more business consulting processes among the candidate plurality of business consulting processes.

The business consultation process may be a pre-configured consultation process for the target business.

Business consultation processes include, but are not limited to, business transaction sub-processes, business suspension sub-processes, and business information consultation sub-processes.

The business handling sub-flow is used for representing each step needed to be executed for handling the target business for the user, the business suspension sub-flow is used for representing each step needed to be executed for suspending the target business for the user, and the business information consulting sub-flow is used for representing each step needed to be executed when responding to the query of the user on the related information of the target business.

The preset image set may include a plurality of knowledge images.

The knowledge image may be knowledge represented in an image form in a knowledge document.

Each knowledge image may be one of a flowchart, a brain graph, a swim lane graph, and images of other image types.

Each knowledge document has a knowledge topic, and one or more knowledge images that each knowledge document includes may correspond to the knowledge topic that the knowledge document has.

In addition, each knowledge topic may have multiple sub-topics, and each knowledge document may be divided into multiple sub-documents, where each sub-document corresponds to one sub-topic of the knowledge topic that the knowledge document has. The one or more knowledge images included by each sub-document may correspond to the sub-topic to which the sub-document corresponds.

According to the target knowledge topics, determining target knowledge images corresponding to the target knowledge topics in a preset image set can be determining business consultation processes corresponding to the target knowledge topics in a plurality of candidate business consultation processes according to the target knowledge topics, and further determining target knowledge images describing the business consultation processes in the preset image set.

The target knowledge image includes a plurality of nodes, each node corresponding to one or more knowledge information.

Each knowledge information includes a piece of knowledge text or a knowledge image. Knowledge text is knowledge in text form in a knowledge document. The knowledge image is knowledge in the form of an image in a knowledge document.

In a specific implementation mode, the target knowledge image comprises text nodes and image nodes, the preset knowledge topic set comprises a target knowledge topic and a first knowledge topic, knowledge information corresponding to the text nodes comprises a sub-topic text of the target knowledge topic and a sub-topic text of the first knowledge topic, and knowledge information corresponding to the image nodes comprises a sub-topic text of the target knowledge topic and associated knowledge images describing a sub-process of a business consultation process corresponding to the target knowledge topic.

The target knowledge image comprises a plurality of nodes, which can comprise text nodes, image nodes and other types of nodes, and knowledge information corresponding to the other types of nodes can comprise knowledge represented by text and other data forms outside the image.

The set of preset knowledge topics may include a target knowledge topic and a first knowledge topic, the first knowledge topic being other knowledge topics in the set of preset knowledge topics than the target knowledge topic.

In particular, in a portion of the text nodes, the text nodes may correspond to a plurality of knowledge information, at least one of the plurality of knowledge information including a sub-topic text of the target knowledge topic, and at least one of the knowledge information including a sub-topic text of the first knowledge topic.

The number of the first knowledge topics may be one or a plurality of first knowledge topics. The number of the sub-subject texts may be one or a plurality.

The subtopic text may be text information in a corresponding sub-document of the subtopic in the knowledge document.

In another portion of the text nodes, the text nodes may correspond to a plurality of knowledge information, each of the plurality of knowledge information including a sub-topic text of the target knowledge topic.

In particular implementations, the image node may correspond to a plurality of knowledge information, where at least one of the plurality of knowledge information includes a sub-topic text of the target knowledge topic and at least one of the plurality of knowledge information includes an associated knowledge image describing a sub-process of the business advisory process to which the target knowledge topic corresponds.

The associated knowledge image describing the sub-flow of the business consultation flow corresponding to the target knowledge topic refers to the associated knowledge image describing the sub-flow, and the sub-flow belongs to the business consultation flow corresponding to the target knowledge topic.

The business advisory process may have a plurality of sub-processes, and each image node may correspond to one of the plurality of sub-processes.

Step S206, obtaining additional consultation information, wherein the additional consultation information is supplementary information of the business consultation request.

The additional consultation information may be text input by the issuer of the business consultation request after the business consultation request has been triggered, or voice uttered by the issuer of the business consultation request after the business consultation request has been triggered.

The sender of the business consultation request is the consultant for the target business.

In the scenario of service consultation response through the agent, on one hand, the sender of the service consultation request carries out service consultation under the premise of lacking knowledge of the target service, and is likely to not know which information needs to be provided by himself in the consultation process, for example, the last four digits of the identification number, the communication number, the product type and the like, so that the sender usually needs to supplement user information, product information or service information to the service consultation request after triggering the service consultation request, on the other hand, in various cases that the sender applies for handling the target service or applies for stopping the target service and the like, there may be some situations that the user will need to be confirmed, for example, before the agent carries out handling confirmation operation for the sender, the sender needs to say "approving handling" voice, so that the sender needs to supplement the service consultation request with intention confirmation information under the guidance of the agent.

The agent refers to the work position of the organization providing the target service in the call center or customer service department. Illustratively, agents can be largely categorized into the following categories according to their work content:

and generally consult, providing related information for users, and recording or transmitting the user information.

Technical support class, providing technical support and arranging related services for users, and the like.

Marketing class, namely, telephone marketing by dialing.

And information collection, namely screening, filtering, collecting or verifying a large amount of data.

And (5) revisiting complaints, namely processing user complaint suggestions and revisiting part of users.

And other transaction types, namely completing various other work contents through telephones.

The seat can be a robot seat or a manual seat.

In particular, after step S204 is performed, before step S206 is performed, a response process may be performed according to the intermediate response information. The intermediate response information may be determined by a business consultation procedure corresponding to the target knowledge image.

The intermediate answer message may be a preset answer phone, for example, "do you please provide your cell phone number", "do you please ask what is your product type.

The intermediate answer message may also be an operation guide call, for example, "you good, you need to open XXX to perform XX operation".

The additional advisory information may include feedback information of the sender of the business advisory request on the intermediate response information.

Step S208, determining a target node in the target knowledge image according to the additional consultation information, and performing response processing according to knowledge information corresponding to the target node.

The target knowledge image is used for describing a business consultation flow, and according to the additional consultation information, the corresponding operation steps of the additional consultation information in the business consultation flow can be determined to determine the target node.

In the scenario of service consultation response by the agent, the service consultation flow may include a plurality of operation steps of the agent. For some of the multiple operations, the agent may need to wait for the additional advisory information from the issuer of the advisory service request before proceeding with other operations after the operation. Each operational step may correspond to a node in the target knowledge image.

The node corresponding to the additional consultation information in the service consultation flow may be a node corresponding to an operation step executed by the agent after receiving the additional consultation information.

In addition, among the plurality of nodes included in the target knowledge node, a judgment node may be included.

After the operation step corresponding to the judging node, in the case that the obtained additional consultation information is different, the next operation step to be executed by the agent is also different.

For example, in the target knowledge image, the node 1 is connected to the node 2 and the node 3, respectively, the node 1 is located before the node 2, the node 1 is located before the node 3, and the node 1 is the judgment node. Node 1 corresponds to operation step 1, node 2 corresponds to operation step 2, and node 3 corresponds to operation step 3.

After the seat performs the operation step 1, additional consultation information 1 of the consultant is obtained, and the seat performs the operation step 2. Or after the seat executes the operation step 1, the additional consultation information 2 of the consultant is obtained, and the seat executes the operation step 3.

The knowledge information corresponding to the target node may include a preset answering operation, and the response processing is performed according to the knowledge information corresponding to the target node, which may be that the preset answering operation is broadcasted.

The knowledge information corresponding to the target node may include a preset knowledge image, where the preset knowledge image is used to describe a sub-process of the business consultation process, and the response processing is performed according to the knowledge information corresponding to the target node, or may be performed according to the sub-process corresponding to the preset knowledge image.

In a specific implementation mode, response processing is performed according to knowledge information corresponding to a target node, wherein the response processing comprises the steps of generating first response information according to a subtopic text of a target knowledge topic and a subtopic text of a first knowledge topic under the condition that the target node is a text node, and performing response processing according to the first response information.

And performing text splicing processing according to the sub-topic text of the target knowledge topic and the sub-topic text of the first knowledge topic to generate a response text, and taking the response text as first response information. The response processing according to the first response information may be that response voice is generated and broadcast according to the response text, or that the response text is displayed, and so on.

The sub-topic text of the target knowledge topic and the sub-topic text of the first knowledge topic are spliced to obtain the response text, so that the aim of integrating knowledge of different knowledge documents can be fulfilled, the knowledge documents do not need to be manually switched back and forth, and the response efficiency is improved.

In a specific implementation mode, the target knowledge image further comprises node description information of each node, determining the target node in the target knowledge image according to the additional consultation information, wherein semantic recognition processing is carried out according to the additional consultation information to obtain a semantic recognition result of the additional consultation information, corresponding first nodes are determined in the target knowledge image according to the additional consultation information, the additional consultation information comprises feedback information of a preset answering operation of a sender of a business consultation request on the first nodes, additional text corresponding to the additional consultation information is determined according to the semantic recognition result and the node description information of the first nodes, text similarity calculation processing is carried out according to the additional text and the node description information of at least one sub-node of the first nodes to obtain text similarity of each sub-node, and the target node is determined in the target knowledge image according to the text similarity of each sub-node.

In practical application, in the case that the additional consultation information is feedback information of the intermediate response information of the sender of the business consultation request, on one hand, the possibility of short reply of the sender when sending the additional consultation information is far higher than that of speaking a complete sentence, on the other hand, the additional consultation information of the sender may not be in a fixed sentence form when expressing different choices, so before text similarity calculation processing is performed, the intention of the sender can be determined by integrating the feedback information of the sender and node description information, and the target node can be more accurately positioned.

For example, the robot agent provides a scheme "suggest you first xxx and then xxx" to the counselor, the counselor says "can" indicating that the counselor agrees to the scheme, the counselor says "there is another method" indicating that the counselor does not agree to the scheme.

And carrying out semantic recognition processing according to the additional consultation information to obtain a semantic recognition result of the additional consultation information.

In the target knowledge image, the corresponding first node may be determined based on the additional advisory information, and the node corresponding to the operation step before the additional advisory information is acquired may be determined as the first node. The additional consultation information comprises feedback information of a preset answering operation of the sender of the business consultation request to the first node.

The descriptive information for each node includes a preset answer ticket for that node.

Determining an additional text corresponding to the additional consultation information according to the semantic recognition result and the node description information of the first node, which may be determining a user intention corresponding to the semantic recognition result according to the semantic recognition result and a preset answering technique of the first node, and generating the additional text corresponding to the additional consultation information according to the user intention and the preset answering technique of the first node.

For example, the preset answering procedure of the first node is to suggest you can.

Is it inconvenient to add consultation information, ask for another method?

And the semantic recognition result of the additional consultation information is X.

According to the semantic recognition result X and the preset answering operation "suggest you can" and user intention corresponding to the semantic recognition result includes user rejection suggestion ", further, according to the user intention and the preset answering operation" suggest you can "and additional text" user rejection "corresponding to additional consultation information is generated.

The first node may be a judging node, and the first node may be connected with at least one child node, with the first node being preceding and the child node being following. That is, each of the at least one child nodes of the first node may be one of the nodes located after the first node in the target knowledge image.

The description information of the node may include a judgment problem, and may also include a branching condition of the judgment problem.

For example, if the node is determined to be node 1, and node 1 is connected to node 2 and node 3, respectively, and node 1 is located before node 2, and node 1 is located before node 3, then both node 2 and node 3 are child nodes of node 1.

The description information of the node 1 includes a judgment question of the node 1 as to whether to agree to the advice a.

The description information of the node 2 includes a branching condition 1 of the judgment problem of the node 1, consent advice a.

The description information of the node 3 includes a branching condition 2 of the judgment problem of the node 1, reject advice a.

And performing text similarity calculation processing according to the additional text and the node description information of at least one sub-node of the first node to obtain text similarity of each sub-node, wherein the text similarity calculation processing can be performed according to the additional text and the node description information of each sub-node in the at least one sub-node to obtain text similarity between the node description information of each sub-node and the additional text, and the text similarity is used as the text similarity of each sub-node.

For example, the at least one child node of the first node includes node 1, node 2, and node 3.

And performing text similarity calculation processing according to the additional text and the node description information of the node 1 to obtain text similarity between the additional text and the node description information of the node 1, and taking the text similarity between the additional text and the node description information of the node 1 as the text similarity of the node 1.

And performing text similarity calculation processing according to the additional text and the node description information of the node 2 to obtain text similarity between the additional text and the node description information of the node 2, and taking the text similarity between the additional text and the node description information of the node 2 as the text similarity of the node 2.

And performing text similarity calculation processing according to the additional text and the node description information of the node 3 to obtain text similarity between the additional text and the node description information of the node 3, and taking the text similarity between the additional text and the node description information of the node 3 as the text similarity of the node 3.

According to the text similarity of each sub-node, determining the target node in the target knowledge image, namely sorting the text similarity of each sub-node according to the value, obtaining a sorting result, determining the text similarity with the largest value according to the sorting result, and determining the sub-node corresponding to the text similarity with the largest value as the target node.

For example, the additional text is "user reject suggestion a".

The first node is node 1 and at least one child node of the first node includes node 2 and node 3.

The descriptive information of node 2 includes consent advice a.

The descriptive information of the node 3 includes reject advice a.

Calculating the text similarity of the additional text and the description information of the node 2 to obtain the text similarity S1 corresponding to the node 2;

and calculating the text similarity of the additional text and the description information of the node 3 to obtain the text similarity S2 corresponding to the node 3.

S2> S1, so node 3 corresponding to S2 can be determined as the target node.

In a specific implementation mode, the service consultation request carries a user identifier, after a target knowledge image corresponding to the target knowledge topic is determined in a preset image set according to the target knowledge topic, the response method further comprises the steps of inquiring corresponding user service data according to the user identifier, and carrying out response processing according to knowledge information corresponding to a target node, wherein the response processing comprises the step of carrying out response processing according to the user service data and the knowledge information corresponding to the target node.

In the specific implementation, the service consultation request can be acquired under the condition that the sender of the service consultation request logs in the response system, and the service consultation request carries the user identification of the sender.

And the user identifier is used for identifying the unique corresponding user in the user data set corresponding to the response system.

The response system may pre-configure a set of user data for the registered user, the set of user data including a user identification and user traffic data for each of the plurality of registered users. Each registered user requests triggered under the condition of logging in the response system carries the user identification of the registered user.

According to the user identification, the user service data corresponding to the user identification can be queried in the user data set.

The response processing is performed according to the user service data and the knowledge information corresponding to the target node, and whether the sender of the service consultation request meets the judgment condition corresponding to the target node or not can be judged according to the user service data, so that the response processing is performed according to the judgment result and the knowledge information corresponding to the target node.

By performing response processing according to the user service data determined by the user identifier and the knowledge information corresponding to the target node, on one hand, the authenticity of the user service data can be ensured, and illegal users can be prevented from handling and stopping the target service by impersonating the identities of other people, on the other hand, the sender of the service consultation request can not remember the own user service data to generate the consultation requirement, or the sender of the service consultation request can generate interference to a response system because the user service data provided by the memory can be inaccurate.

In a specific implementation mode, the response method further comprises the steps of receiving node selection input in the target knowledge image, determining corresponding nodes to be processed according to the node selection input, and carrying out association display according to knowledge information corresponding to the target knowledge image and the nodes to be processed.

In the scene of service consultation response through the agent, the node selection input of the artificial agent in the target knowledge image can be received, and the node to be processed selected by the artificial agent is determined according to the node selection input.

The node to be processed can be a text node or an image node.

And under the condition that the node to be processed is a text node, performing associated display according to the target knowledge image and the knowledge information corresponding to the node to be processed, wherein the target knowledge image can be displayed in a first preset area, and at least one knowledge text corresponding to the node to be processed can be displayed in a second preset area. And the target knowledge image and at least one knowledge text are displayed in a correlated manner, so that the human seat can look at the knowledge text.

And under the condition that the node to be processed is an image node, performing association display according to the target knowledge image and the knowledge information corresponding to the node to be processed, wherein the target knowledge image can be displayed in a first preset area, and the knowledge image corresponding to the node to be processed can be displayed in a second preset area. And the correlation display of the target knowledge image and the knowledge image corresponding to the node to be processed is beneficial to the simultaneous checking and comparison of a plurality of images by the artificial agent.

Compared with a scheme that a knowledge document is seen, when a node to be processed in the diagram relates to another knowledge document, the node jumps to the other knowledge document to view the knowledge text or the knowledge image, the data query efficiency is higher in the implementation mode, and errors possibly caused by switching the manual agent back and forth among a plurality of knowledge documents are reduced.

In the embodiment shown in fig. 2, a target knowledge topic corresponding to the service consultation request is determined, a target knowledge image corresponding to the target knowledge topic is determined in a preset image set according to the target knowledge topic, the target knowledge image comprises a plurality of nodes, each node corresponds to at least one piece of knowledge information, additional consultation information is acquired, the additional consultation information is supplementary information of the service consultation request, the target node is determined in the target knowledge image according to the additional consultation information, and response processing is performed according to the knowledge information corresponding to the target node. Therefore, the target knowledge image corresponding to the target knowledge subject comprises a plurality of nodes, each node corresponds to at least one knowledge message, so that one target knowledge image can cover a large amount of knowledge on which the service consultation request depends, knowledge messages corresponding to each node in the target knowledge image are utilized for responding, knowledge required by the response can be prevented from being checked by manually switching back and forth among a plurality of knowledge documents, response efficiency is improved, and error rate of manual response is reduced.

According to the response method described above, based on the same technical concept, the embodiment of the present application further provides a knowledge image generating method, and the knowledge image generated by the knowledge image generating method can be used for the response method provided by the foregoing method embodiment. The method for generating the knowledge image provided by the embodiment of the application can specifically refer to fig. 3-6.

Fig. 3 is a configuration interface diagram of a knowledge image according to an embodiment of the present application.

As shown in fig. 3, in the image information area of the configuration interface of the knowledge image, the right side of the image name is the image name input box 302, the right side of the image type is the image type selection box 304, the right side of the associated knowledge is the knowledge addition control 306, and the right side of the knowledge addition control 306 is the control "start drawing".

Wherein the maximum character length that can be input, which is preconfigured in the image name input box 302, is 50 characters.

The image type selection box 304 is preconfigured with selections of a plurality of image types, such as a base image, a flowchart, a brain map, a swim lane map, and the like.

Illustratively, the knowledge addition control 306 may be a button control that, upon clicking on it, may pop up a pop-up window of knowledge list that exposes a knowledge list of multiple knowledge topics. Knowledge topics may be referred to the corresponding description of the embodiment of fig. 2.

If a knowledge theme (recorded as knowledge A) needs to be added with a knowledge image, a new flow can be clicked on a drawing tool page of the knowledge platform, and the image workbench is opened.

The drawing tool page of the knowledge base may be a page of the open source image engine antv-X6 (X6 for short). In addition, the rendering of the image may be performed by Kmp-x 6. The Kmp-X6 is an editable and previewable package implemented based on the data of the X6 and knowledge base, and other items of the same organization want to review the rendered image and only need to introduce the package to call for viewing and previewing.

The knowledge base station may include an image workbench that may display a configuration interface for knowledge images as shown in fig. 3.

The image name is filled in an image name input box 302 in the image workbench, the type of the image is selected in an image type selection box 304 of the image workbench, a knowledge adding control 306 is clicked, knowledge A is selected in a knowledge list displayed by a popup window, and then a control is clicked to start drawing.

The "knowledge A" is selected as the associated knowledge, which means that the knowledge image to be drawn is serving the knowledge A, i.e. the knowledge A is associated with the entire knowledge image to be drawn.

As shown in fig. 3, a start icon, a normal node icon, a judgment node icon, a sub-image icon, and an end icon are included in a toolbar region of a configuration interface of the knowledge image.

As shown in fig. 3, in the image drawing area of the configuration interface of the knowledge image:

The start icon 308 represents the business advisory process start and the end icon 322 represents the business advisory process result. The brain graph of the business consultation flow includes a plurality of nodes, wherein the first node is a common node 1 corresponding to a common node icon 310, the common node 1 points to a judgment node corresponding to a judgment node icon 312, the output of the judgment node includes two branches, one branch points to a common node 2 corresponding to a common node icon 314, and the other branch points to a common node 3 corresponding to a common node icon 318. The normal node 2 points to the image node 1 corresponding to the sub-image icon 316. The normal node 3 points to the image node 2 corresponding to the sub-image icon 320.

The lower part of the image drawing area comprises a cancel control, a save as draft control, a preview control and a save and release control.

As shown in fig. 3, the associated presentation area 324 of the configuration interface of the knowledge image includes knowledge text 1, knowledge text 2, knowledge text 3, and knowledge text 4.

After the knowledge image configuration is completed, the image workbench may display a presentation interface of the knowledge image.

Fig. 4 is a diagram of a knowledge image display interface according to an embodiment of the present application.

As shown in fig. 4, a start icon 402 represents a business advisory process start and an end icon 416 represents a business advisory process result. The brain graph of the business consultation flow comprises a plurality of nodes, wherein the first node is a common node 1 corresponding to a common node icon 404, the common node 1 points to a judgment node corresponding to a judgment node icon 406, the output of the judgment node comprises two branches, one branch points to a common node 2 corresponding to a common node icon 408, and the other branch points to a common node 3 corresponding to a common node icon 412. The normal node 2 points to the image node 1 corresponding to the sub-image icon 410. The normal node 3 points to the image node 2 corresponding to the sub-image icon 414.

The presentation interface diagram also includes an associated presentation area 418, where the associated presentation area 418 includes knowledge text 1, knowledge text 2, knowledge text 3, and knowledge text 4.

The association presentation area 418 may present knowledge information corresponding to the selected node to be processed.

For example, in the case that the human agent selects the common node 1 corresponding to the common node icon 404 as the node to be processed, the associated display area 418 can see that the knowledge information corresponding to the common node 1 includes the knowledge text 1, the knowledge text 2, the knowledge text 3 and the knowledge text 4, so as to achieve the effect of associating and displaying the knowledge information corresponding to the node to be processed and the node to be processed.

For another example, in the case that the human agent selects the image node 2 corresponding to the sub-image icon 414 as the node to be processed, the associated display area 418 can see that the knowledge information corresponding to the image node 2 includes the knowledge text 5 and the associated knowledge image (not shown in fig. 3), so as to achieve the effect of associating and displaying the knowledge information corresponding to the node to be processed and the node to be processed.

Since the technical conception is the same, the description in this embodiment is relatively simple, and the relevant parts only need to refer to the corresponding descriptions of the method embodiments provided above.

In the image drawing process, taking an image of brain graph type as an example, the nodes which can be added in the graph comprise common nodes, judging nodes and image nodes. The node configuration may be illustrated below in conjunction with fig. 5 and 6. Fig. 5 is a node information configuration page of a judging node according to an embodiment of the present application. Fig. 6 is a node information configuration page of an image node according to an embodiment of the present application.

I. Common node:

1. Double clicking node, configuring node information:

a) Node name

B) Node description

C) Knowledge of associations

The node description may include node description information of the general node. The definition of the node description information may refer to the corresponding description of the embodiment of fig. 2.

It should be noted that in configuring node information of the ordinary node, the associated knowledge of the ordinary node is different from the associated knowledge "knowledge a" of the knowledge image to be drawn.

The associated knowledge of a common node is used to indicate that the node is related to knowledge text in other knowledge documents, for example, when a human agent queries knowledge a and is at the current node, the content of knowledge B needs to be viewed. Knowledge B is another knowledge topic that is different from knowledge a.

A common node may be configured with one or more associated knowledge, each of which may be a sub-topic text of a first knowledge topic, which is a knowledge topic other than the target knowledge topic (i.e., knowledge a).

2. Clicking on a section of "knowledge a" in the association presentation area 324 (denoted as section P1) may associate the common node with "section P1" of "knowledge a", i.e. the section P1 indicating that the common node relates to "knowledge a". During the image rendering stage, the associated presentation area 324 may present a plurality of chapters with "knowledge A".

The "section P1" may be a sub-topic text of the target knowledge topic (i.e., knowledge A).

In addition, the common node may be a text node, and the definition of the text node is shown in the corresponding description part of the embodiment of fig. 2.

Ii. judgment node

1. Double clicking node, configuring node information:

a) Node name

B) Node description

C) Knowledge of associations

The node description and the configuration of the associated knowledge of the judgment node can refer to the common node.

2. Clicking on a section of "knowledge a" in the association presentation area 324 (denoted as section P2) may associate the determination node with "section P2" of "knowledge a", i.e. the "section P2" indicating that the determination node relates to "knowledge a".

The "section P2" may be a sub-topic text of the target knowledge topic (i.e., knowledge a).

In addition, the judging node may be a text node, and the definition of the judging node is shown in the corresponding description part of the embodiment of fig. 2.

As shown in fig. 5, in the node information configuration interface 500 for judging a node, a node name input box 502 is on the right side of the node name, and a node description input box 504 is on the right side of the node description. To the right of the associated knowledge is a knowledge addition control 506. The associated knowledge currently being presented includes knowledge file 508, knowledge text 510, and knowledge text 512.

Wherein the knowledge text 508, i.e., knowledge text a1, is in a disabled state;

Knowledge text 510, knowledge text a2, is in a deleted state;

knowledge text 512, namely knowledge text a3, is neither disabled nor deleted, knowledge text 512 is normally associated with the judgment node.

Image node

1. Double clicking node, configuring node information:

a) Node name

B) Node description

C) Correlating images

D) Correlation knowledge (common node)

The associated image of the image node is used to represent that the image node is related to a knowledge image in other knowledge documents, for example, when the human agent queries knowledge a and is at the current node, another knowledge image needs to be viewed.

In the case that the knowledge image to be drawn is a flowchart, the associated image of the image node in the knowledge image to be drawn may be a flowchart of a sub-flow of the business consultation flow described in the flowchart.

2. Clicking on a section of "knowledge a" associated with presentation area 324 (denoted as section P3) may associate the image node with "section P3" of "knowledge a", i.e. the image node is related to "section P3" of "knowledge a".

As shown in fig. 6, in the node information configuration interface 600 of the image node, the node name input box 602 is on the right side of the node name, and the node description input box 604 is on the right side of the node description. To the right of the associated image is an image retrieval box 606. The currently presented associated images include knowledge image 608, knowledge image 610, and knowledge image 612.

Wherein knowledge image 608, knowledge image b1, is in a disabled state;

knowledge image 610, knowledge image b2, is in a deleted state;

knowledge image 612, knowledge image b3, is neither stale nor deleted, knowledge image 612 is normally associated with an image node.

In addition, in the image drawing process, the custom connection can be realized through the registration connection provided by the X6, and the X6 supports the deletion of the edge and the addition of the document.

Registration links provided by X6 include, but are not limited to, base image links, mind map links, swim map links, and annotation links.

In the image rendering process, custom nodes can be implemented through registration nodes provided by X6 and support data that can be associated on the nodes.

The custom nodes include, but are not limited to, common nodes, judgment nodes and image nodes.

During the image rendering process, the business process may be completed by the node event provided by X6.

Node events include, but are not limited to, node selection events, add node events, image change events, node deletion events, edge addition events, edge deletion events, node drag events, node size change events, and the like.

The editing and viewing engine of the image knowledge such as the Kmp-X6 common component package can be completed through the self-defined edges, nodes and data of the internal event and knowledge center station of the monitoring X6. The Kmp-x6 package can be used to view and edit different image types, such as base images, mind maps, swim maps, etc., by defining parameters. Kmp-x6 also supports external interception, when a service button or some action event is triggered, the user can do different services through the transmitted parameters and events.

After image drawing is completed in the image drawing area and node information configuration of each node is performed, the drawn knowledge image may be saved.

For example, by clicking on the control "save as draft," verification of the image name may be triggered.

The checking mode of the image name can comprise the steps of checking whether the image name is empty or not and checking whether the image name is renamed with the saved image name or not.

Illustratively, by clicking on the control "save and issue", a check may be triggered in a number of ways:

(1) And (3) performing the check-up and duplicate-name check-up of the image name in the specified service domain, and prompting that the image name cannot be empty or the image name cannot be repeated under the field when the check-up fails.

(2) If the image is of the basic image type, checking whether the image contains a start icon and an end icon, and generating a warning prompt according to a checking result, wherein the image has no start/end node and cannot be stored.

(3) And (3) carrying out image integrity verification, wherein all nodes are required to be connected and associated with other nodes, cannot be the orphan nodes, and otherwise, generating a warning prompt, namely, checking if the image has the orphan nodes.

(4) And checking whether the knowledge text associated with each node exists, and if not, automatically disconnecting the link relation between the node and the knowledge text.

(5) Checking whether the knowledge text associated with each node is abnormal, wherein the knowledge state comprises, but is not limited to, a spent state, a deleted state or other abnormal states, and if the abnormal state exists, generating a warning prompt, namely, the node associated knowledge text is abnormal, and checking is carried out.

(6) Checking whether the knowledge image associated with each node is abnormal, wherein the knowledge state comprises, but is not limited to, invalid, deleted or other abnormal states, if abnormal, generating a warning prompt, namely 'the knowledge image associated with the node is abnormal, please check', and automatically selecting the node.

(7) Checking whether the image state of the knowledge image associated with each node is abnormal, wherein the image state comprises released and not released, if the image state is not released, generating a warning prompt, namely 'the state of the sub-image associated with the node is abnormal, please check', and automatically selecting the node.

After the verification is completed, a page of a mask layer can be displayed, a page file prompt that the current page is successfully released can be generated after the release is completed, and the page file prompt that the current page is in the process of releasing the image is slightly waiting for |.

After the publication is successful, the knowledge image may be viewed, as shown in FIG. 4.

Fig. 7 is a process flow diagram of another response method according to an embodiment of the present application.

Before executing the response method shown in fig. 7, the knowledge image generation method may be executed by the knowledge base station, the knowledge image generation method including the steps of:

Step S702, drawing is newly added.

Step S704, associating knowledge for the image.

For image-related knowledge, a corresponding knowledge topic may be configured for the knowledge image.

Step S706, an image is drawn.

Step S708, associating knowledge for the image node.

The knowledge is associated with the image nodes, and corresponding knowledge information is configured for each node in the knowledge image, wherein the knowledge information can comprise knowledge texts or knowledge images.

Step S710, publishing the image knowledge.

And publishing the knowledge image which is drawn and the node information configuration is completed.

Steps S702 to S710 may refer to an embodiment of a knowledge image generation method as shown in fig. 3 to 6.

As shown in fig. 7, the response method performed by the customer service system may include the steps of:

step S712, query image knowledge.

The agent sends a request for acquiring the target knowledge image to the knowledge center station through the customer service system.

And the knowledge center station returns the target knowledge image to the customer service system.

Step S714, click on each image node.

It should be noted that clicking on each image node refers to clicking on each node in the target knowledge image, and the node may be a text node or an image node, instead of clicking only the image node.

Step S716, look at knowledge associated with each node.

The knowledge associated with each node may include knowledge text or may include knowledge images.

In the foregoing embodiments, a response method is provided, and correspondingly, based on the same technical concept, an embodiment of the present application further provides a response device, which is described below with reference to the accompanying drawings.

Fig. 8 is a schematic diagram of a response device according to an embodiment of the present application.

The present embodiment provides a response device 800, including:

a determining unit 802, configured to determine a target knowledge topic corresponding to the service consultation request;

the determining unit 802 is further configured to determine, according to the target knowledge topic, a target knowledge image corresponding to the target knowledge topic in a preset image set, where the target knowledge image includes a plurality of nodes, and each node corresponds to at least one piece of knowledge information;

An obtaining unit 804, configured to obtain additional consultation information, where the additional consultation information is supplementary information of the service consultation request;

And a response unit 806, configured to determine a target node in the target knowledge image according to the additional consultation information, and perform response processing according to knowledge information corresponding to the target node.

Optionally, the target knowledge image further comprises node description information of each node, and a response unit 806, specifically configured to:

carrying out semantic recognition processing according to the additional consultation information to obtain a semantic recognition result of the additional consultation information;

Determining a corresponding first node according to the additional consultation information in the target knowledge image, wherein the additional consultation information comprises feedback information of a preset answering operation of the first node by an issuer of the business consultation request;

determining an additional text corresponding to the additional consultation information according to the semantic recognition result and the node description information of the first node;

performing text similarity calculation processing according to the additional text and node description information of at least one child node of the first node to obtain text similarity of each child node;

And determining the target node in the target knowledge image according to the text similarity of each child node.

Optionally, the service consultation request carries a user identifier, and the answering device 800 further includes:

the inquiring unit is used for inquiring corresponding user service data according to the user identification;

The response unit 806 is specifically configured to:

And carrying out response processing according to the user service data and the knowledge information corresponding to the target node.

Optionally, the business consultation request carries a request text, and the determining unit 802 is specifically configured to:

performing text similarity calculation processing according to the request text and each knowledge topic in a preset knowledge topic set to obtain text similarity of each knowledge topic;

and determining the target knowledge topics of the business consultation request according to the text similarity of each knowledge topic.

Optionally, the answering apparatus 800 further includes:

A receiving unit, configured to receive a node selection input in the target knowledge image;

a determining unit 802, configured to determine a corresponding node to be processed according to the node selection input;

And the display unit is used for carrying out association display according to the target knowledge image and the knowledge information corresponding to the node to be processed.

Optionally, the target knowledge image includes text nodes and image nodes;

The preset knowledge topic set comprises a target knowledge topic and a first knowledge topic, and knowledge information corresponding to the text node comprises a sub-topic text of the target knowledge topic and a sub-topic text of the first knowledge topic;

The knowledge information corresponding to the image nodes comprises a sub-topic text of the target knowledge topic and an associated knowledge image describing a sub-process of a business consultation process corresponding to the target knowledge topic.

Optionally, the answer unit 806 is specifically configured to:

generating first response information according to the subtopic text of the target knowledge topic and the subtopic text of the first knowledge topic under the condition that the target node is the text node;

And carrying out response processing according to the first response information.

The answering device provided by the embodiment of the application comprises a determining unit, a determining unit and an answering unit, wherein the determining unit is used for determining a target knowledge theme corresponding to a service consultation request, the determining unit is also used for determining a target knowledge image corresponding to the target knowledge theme in a preset image set according to the target knowledge theme, the target knowledge image comprises a plurality of nodes, each node corresponds to at least one knowledge message, the obtaining unit is used for obtaining additional consultation information which is complementary information of the service consultation request, and the answering unit is used for determining the target node in the target knowledge image according to the additional consultation information and carrying out answering processing according to the knowledge message corresponding to the target node. Therefore, the target knowledge image corresponding to the target knowledge subject comprises a plurality of nodes, each node corresponds to at least one knowledge message, so that one target knowledge image can cover a large amount of knowledge on which the service consultation request depends, knowledge messages corresponding to each node in the target knowledge image are utilized for responding, knowledge required by the response can be prevented from being checked by manually switching back and forth among a plurality of knowledge documents, response efficiency is improved, and error rate of manual response is reduced.

Corresponding to the above-described response method, based on the same technical concept, the embodiment of the application further provides an electronic device, where the electronic device is configured to execute the above-provided response method, and fig. 9 is a schematic structural diagram of an electronic device provided by the embodiment of the application.

As shown in fig. 9, the electronic device may have a relatively large difference due to different configurations or performances, and may include one or more processors 901 and a memory 902, where the memory 902 may store one or more storage applications or data. Wherein the memory 902 may be transient storage or persistent storage. The application programs stored in the memory 902 may include one or more modules (not shown), each of which may include a series of computer-executable instructions in the electronic device. Still further, the processor 901 may be arranged to communicate with the memory 902 and execute a series of computer executable instructions in the memory 902 on an electronic device. The electronic device may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input/output interfaces 905, one or more keyboards 906, and the like.

In one particular embodiment, an electronic device includes a memory, and one or more programs, where the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the electronic device, and execution of the one or more programs by one or more processors includes instructions for:

determining a target knowledge image corresponding to the target knowledge theme in a preset image set according to the target knowledge theme, wherein the target knowledge image comprises a plurality of nodes, and each node corresponds to at least one piece of knowledge information;

An embodiment of a computer-readable storage medium provided in the present specification is as follows:

corresponding to the above-described response method, the embodiment of the application further provides a computer readable storage medium based on the same technical concept.

The computer readable storage medium provided in this embodiment is configured to store computer executable instructions, where the computer executable instructions when executed by a processor implement the following procedures:

It should be noted that, in the present specification, the embodiments related to the computer readable storage medium and the embodiments related to the response method in the present specification are based on the same inventive concept, so the specific implementation of this embodiment may refer to the implementation of the foregoing corresponding method, and the repetition is omitted.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can 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 are also possible or may be advantageous.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-readable storage media (including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

Embodiments of the application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing description is by way of example only and is not intended to limit the present disclosure. Various modifications and changes may occur to those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. that fall within the spirit and principles of the present document are intended to be included within the scope of the claims of the present document.

Claims

1. A response method, comprising:

Determine the target knowledge topic corresponding to the business consultation request;

According to the target knowledge subject, determining a target knowledge image corresponding to the target knowledge subject in a preset image set; the target knowledge image includes a plurality of nodes, each of which corresponds to at least one piece of knowledge information;

Acquire additional consulting information, where the additional consulting information is supplementary information of the business consulting request;

A target node is determined in the target knowledge image according to the additional inquiry information, and a response process is performed according to the knowledge information corresponding to the target node.

2. The method according to claim 1, characterized in that the target knowledge image further includes node description information of each of the nodes; and determining the target node in the target knowledge image according to the additional consulting information comprises:

Performing semantic recognition processing according to the additional consulting information to obtain a semantic recognition result of the additional consulting information;

In the target knowledge image, a corresponding first node is determined according to the additional consultation information; the additional consultation information includes feedback information of a preset response speech of the sender of the business consultation request to the first node;

Determining, according to the semantic recognition result and the node description information of the first node, the additional text corresponding to the additional consulting information;

Performing text similarity calculation processing based on the additional text and node description information of at least one child node of the first node to obtain text similarity of each child node;

The target node is determined in the target knowledge image according to the text similarity of each of the sub-nodes.

3. The method according to claim 1, characterized in that the business consultation request carries a user identifier; after determining the target knowledge image corresponding to the target knowledge topic in a preset image set according to the target knowledge topic, the method further comprises:

According to the user identifier, query the corresponding user service data;

The answering process according to the knowledge information corresponding to the target node includes:

Response processing is performed according to the user service data and the knowledge information corresponding to the target node.

4. The method according to claim 1, wherein the business consultation request carries a request text; and the step of determining a target knowledge topic corresponding to the business consultation request comprises:

Performing text similarity calculation processing on the request text and each knowledge topic in the preset knowledge topic set to obtain the text similarity of each knowledge topic;

According to the text similarity of each of the knowledge topics, a target knowledge topic of the business consulting request is determined.

5. The method according to claim 1, further comprising:

Receiving a node selection input in the target knowledge image;

Determine the corresponding node to be processed according to the node selection input;

The target knowledge image and the knowledge information corresponding to the node to be processed are displayed in association.

6. The method according to claim 1, characterized in that the target knowledge image includes text nodes and image nodes;

The preset knowledge topic set includes a target knowledge topic and a first knowledge topic, and the knowledge information corresponding to the text node includes a sub-topic text of the target knowledge topic and a sub-topic text of the first knowledge topic;

The knowledge information corresponding to the image node includes the sub-topic text of the target knowledge topic and an associated knowledge image describing the sub-process of the business consulting process corresponding to the target knowledge topic.

7. The method according to claim 6, characterized in that the response processing according to the knowledge information corresponding to the target node comprises:

In the case where the target node is the text node, generating first response information according to the sub-topic text of the target knowledge topic and the sub-topic text of the first knowledge topic;

Perform response processing according to the first response information.

8. A response device, comprising:

A determination unit, used to determine a target knowledge topic corresponding to a business consulting request;

The determination unit is further configured to determine, according to the target knowledge subject, a target knowledge image corresponding to the target knowledge subject in a preset image set; the target knowledge image includes a plurality of nodes, each of which corresponds to at least one piece of knowledge information;

An acquiring unit, configured to acquire additional consulting information, wherein the additional consulting information is supplementary information of the business consulting request;

A response unit is used to determine a target node in the target knowledge image according to the additional consultation information, and perform response processing according to the knowledge information corresponding to the target node.

9. An electronic device, characterized in that the device comprises:

A processor; and a memory configured to store computer executable instructions, which, when executed, cause the processor to execute the response method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium is used to store computer-executable instructions, and when the computer-executable instructions are executed by a processor, the response method according to any one of claims 1 to 7 is implemented.