CN114201597A - Information response method and device, electronic equipment and storage medium - Google Patents

Abstract

The disclosure provides an information response method, relates to the technical field of computers, and particularly relates to an intelligent customer service technology and a cloud service technology. The specific implementation scheme is as follows: acquiring target input information; acquiring emotion category information and intention information of target input information; and responding to the target input information according to the emotion category information and the intention information. The disclosure also provides an information response device, an electronic device and a storage medium.

Description

Information response method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to an intelligent customer service technology and a cloud service technology. More specifically, the present disclosure provides an information answering method, apparatus, electronic device and storage medium.

Background

The intelligent customer service can replace the artificial customer service to respond to the information from the target object. For example, the intelligent customer service may respond to the information based on a preset knowledge base.

Disclosure of Invention

The disclosure provides an information response method, an information response device, information response equipment and a storage medium.

According to a first aspect, there is provided an information answering method, comprising: acquiring target input information; acquiring emotion category information and intention information of target input information; and responding to the target input information according to the emotion category information and the intention information.

According to a second aspect, there is provided an information answering device, comprising: the first acquisition module is used for acquiring target input information; the second acquisition module is used for acquiring emotion category information and intention information of the target input information; and the response module is used for responding the target input information according to the emotion type information and the intention information.

According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method provided in accordance with the present disclosure.

According to a fourth aspect, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method provided in accordance with the present disclosure.

According to a fifth aspect, a computer program product is provided, comprising a computer program which, when executed by a processor, implements a method provided according to the present disclosure.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram of an exemplary system architecture to which information response methods and apparatus may be applied, according to one embodiment of the present disclosure;

FIG. 2 is a flow diagram of an information response method according to one embodiment of the present disclosure;

FIG. 3 is a flow chart diagram of an information response method according to another embodiment of the present disclosure;

FIG. 4 is a block diagram of an information answering device according to one embodiment of the present disclosure; and

fig. 5 is a block diagram of an electronic device to which an information response method may be applied according to one embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

A single-turn dialogue based information response method can perform response once according to one information from a target object, namely, response is performed by using a single-turn dialogue mode. The method cannot solve the problem of complicated personalization of the user. The method cannot sense the negative emotion of the object and timely relieve the negative emotion of the object by utilizing artificial customer service.

Fig. 1 is a schematic diagram of an exemplary system architecture to which an information response method and apparatus may be applied, according to one embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired and/or wireless communication links, and so forth.

The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the information response method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the information responding apparatus provided by the embodiment of the present disclosure may be generally disposed in the server 105. The information response method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the information response device provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.

Fig. 2 is a flow chart of an information answering method according to one embodiment of the present disclosure.

As shown in fig. 2, the method 200 may include operations S210 to S230.

In operation S210, target input information is acquired.

In the disclosed embodiment, the target input information may be a question from a target object.

For example, the target input information may be text information or voice information. In one example, voice recognition may be performed on the voice information to obtain text information corresponding to the voice information.

For example, the destination input information may be "did my order ship".

In operation S220, emotion category information and intention information of the target input information are acquired.

In the embodiment of the disclosure, emotion analysis can be performed on target input information to acquire emotion category information.

For example, emotion recognition operators may be used to perform emotion analysis on the target input information.

For example, the emotion recognition operator may be a trained natural language processing model. The trained natural language processing model may perform sentiment analysis on the target input information.

It should be noted that various emotion recognition operators can be used to perform emotion analysis on the target input information, which is not limited by this disclosure.

For example, the emotion estimation value may be determined from the emotion category information.

In one example, the destination input information may be "did my order ship". Emotion analysis is performed on the target input information, and emotion category information can be acquired.

In the embodiment of the present disclosure, the target input information may be input into the intention recognition model, and intention information of the target input information may be acquired.

It should be noted that the intention recognition model can be various machine learning models based on natural language processing technology, and the disclosure is not limited thereto.

For example, the target input information may be "did my order shipped", which is input into the intention recognition model, and the intention information may be acquired. For example, the intention information of the target input information may be "query order logistics information".

In operation S230, target input information is responded according to the emotion classification information and the intention information.

For example, the emotion category information may indicate a first target emotion category and a second target emotion category.

In one example, the first target emotion category may characterize a non-negative emotion.

In one example, the second target emotion category may characterize a negative emotion.

Through the embodiment of the disclosure, the emotion and the intention indicated by the input information can be comprehensively analyzed, and the corresponding personalized response operation is executed, so that the accuracy of response information is improved, and the user experience is further improved.

Fig. 3 is a flowchart of an information answering method according to another embodiment of the present disclosure.

As shown in fig. 3, the method 300 may include operations S301 to S317.

In operation S301, target input information is acquired.

It should be noted that operation S301 in the method 300 is the same as or similar to operation S210 in the method 200. For the sake of brevity, this disclosure is not repeated.

In operation S302, emotion category information of target input information is acquired.

For example, emotion analysis may be performed on the target input information to obtain emotion category information.

In operation S303, a mood evaluation value is determined according to the mood category information.

For example, a mood evaluation value may be included in the mood category information. The emotion estimation value may be determined based on the emotion classification information.

In operation S304, it is determined whether the emotion estimation value is less than a preset emotion threshold value.

In the present disclosed embodiment, operation S305 may be performed in response to the emotion assessment value being greater than or equal to the preset emotion threshold value.

In the present disclosed embodiment, operation S307 may be performed in response to the emotion assessment value being less than the preset emotion threshold value.

Next, taking the emotion assessment value greater than or equal to the preset emotion threshold value as an example, detailed description will be made in conjunction with operations S305 to S306

In the embodiment of the present disclosure, in response to the emotion assessment value being greater than or equal to the preset emotion threshold value, it is determined that the emotion classification information indicates the second target emotion classification.

For example, the second target emotion category characterizes a negative emotion.

For example, the target input information is the information Info _1 "how my orders have not been shipped". The information Info _1 comes from the target object Obj _ 1. Emotion analysis is performed on the information Info _1 by using an emotion analysis operator, and an emotion evaluation value of 0.7 corresponding to the information Info _1 can be obtained. Taking the preset emotion threshold as 0.6 as an example, the emotion assessment value is greater than the preset emotion threshold. The target object Obj _1 may be determined to be a negative emotion. Next, operation S305 may be performed.

In operation S305, first preset information is presented.

For example, the first preset information may be information preset for a subject exhibiting a negative emotion.

In operation S306, a manual answer mode is switched to.

For example, after determining that the target object Obj _1 is a negative emotion, the target object Obj _1 is manually served.

The response can be more accurately carried out, and the user experience is improved.

Next, taking the emotion assessment value smaller than the preset emotion threshold as an example, a detailed description will be given in conjunction with operations S307 to S308.

In the embodiment of the present disclosure, in response to the emotion assessment value being less than the preset emotion threshold, it is determined that the emotion classification information indicates the first target emotion classification.

For example, a first target emotion category may characterize a non-negative emotion.

For example, the target input information is the information Info _2 "did my order ship". The information Info _2 comes from the target object Obj _ 2. From the information Info _2, operations S302 to S303 may be performed, resulting in an emotion assessment value of 0.5 for the information Info _ 2. Taking the preset emotion threshold value of 0.6 as an example, and then performing operation S304, it may be obtained that the emotion assessment value is smaller than the preset emotion threshold value. The target object Obj _2 may be determined to be a non-negative emotion. Next, operation S307 may be performed according to the information Info _ 2.

In operation S307, intention information of the target input information is acquired.

For example, using the intention recognition model described above, intention information Inten _1 of the information Info _2 may be acquired as "query order logistics information".

In operation S308, it is determined whether the intention information indicates a target intention.

For example, a plurality of third similarities between the plurality of preset intentions and the intention information may be calculated. And determining the target intention indicated by the intention information from the plurality of preset intentions according to the plurality of third similarities.

In the disclosed embodiment, in response to the intention information indicating the target intention, operation S309 may be performed.

In the present disclosed embodiment, in response to the intention information not indicating the target intention, operation S311 may be performed.

Next, taking the intention information indicating the target intention as an example, a detailed description will be made in conjunction with operations S309 to S310.

For example, the third similarity between the preset intention "query order logistics state" and the intention information Inten _1 is the largest among the preset intents, and the third similarity (for example, 0.75) is greater than a preset third similarity threshold (for example, 0.6). Accordingly, the preset intention "query order logistics state" may be determined as the target intention indicated by the intention information Inten _ 1.

In operation S309, a business data set corresponding to the target intention is acquired.

For example, the preset intention "query order logistics state" corresponds to one business data set. The business data set can be considered as the business data set corresponding to the target intent.

In operation S310, first response information is generated according to the service data set.

It should be noted that the business data set described above includes the order numbers of a plurality of orders and the logistics status of the orders. For example, the physical distribution status of one order is "in transit", and the physical distribution status of another order is "in transit". With the identification information of the target object, the order number of the order corresponding to the object can be acquired. And then according to the order number of the order, inquiring the corresponding logistics state in the service data set to generate first response information.

For example, using the identification information of the target object Obj _2, the order number of the order corresponding to the target object Obj _2 may be acquired. And then inquiring in the service data set according to the order number of the order. For example, the inquired logistics state is "in transit". Further, the first response information may be "your order is in transit, please wait patiently".

The intention of the user can be automatically identified, and the cost of manual service is reduced.

Next, taking the example that the intention information does not indicate the target intention, a detailed description is made in conjunction with operation S311.

For example, an example is given in which the target input information is information Info _3 "how to perform service evaluation". The information Info _3 comes from the target object Obj _ 3. From the information Info _3, operations S302 to S303 may be performed, resulting in an emotion assessment value of 0.3 for the information Info _ 3. Taking the preset emotion threshold value as 0.6 as an example, and then performing operation S304, it may be obtained that the emotion assessment value is smaller than the preset emotion threshold value. The target object Obj _3 may be determined to be a non-negative emotion. Operation S307 may be performed according to the information Info _3 to acquire intention information Inten _2 of the information Info _ 3. In one example, the target intention indicated by the intention information Inten _2 cannot be determined from a plurality of preset intents. After performing operation S308, operation S311 may be performed.

In operation S311, it is determined whether the intention information indicates a first target issue.

For example, a plurality of first similarities between a plurality of first preset questions and the intention information may be calculated. The first target question indicated by the intention information may be determined from a plurality of first preset questions according to a plurality of first similarities.

In the disclosed embodiment, in response to the intention information indicating the first target issue, operation S312 is performed.

In the disclosed embodiment, in response to the intention information not indicating the first target issue, operation S314 is performed.

Next, taking the intention information indicating the first target issue as an example, a detailed description will be made in conjunction with operations S311 and S312.

For example, among the plurality of first preset questions, the first preset question "how to perform service evaluation" has the largest first similarity with the intention information Inten _2, and the first similarity is greater than a preset first similarity threshold. Therefore, the first preset question "how to perform service evaluation" is determined as the first target question indicated by the intention information Inten _ 2.

In operation S312, first knowledge information corresponding to the first target issue is acquired.

For example, each first preset question corresponds to one first knowledge information. The first knowledge information corresponding to the first preset question "how to perform service evaluation" may be determined as the first knowledge information corresponding to the intention information Inten _ 2.

In operation S313, second response information is generated according to the first knowledge information.

For example, the first knowledge information corresponding to the intention information Inten _2 may be a specific operation flow for performing service evaluation. The first knowledge information may be used as the second response information.

Next, taking the example that the intention information does not indicate the first target issue, a detailed description is made in conjunction with operation S314. .

For example, it is exemplified that the target input information is information Info _4 "x × holiday is months and days". The information Info _4 comes from the target object Obj _ 4. From the information Info4, operations S302 to S303 may be performed, resulting in the emotion assessment value of the information Info _4 being 0.3. Taking the preset emotion threshold value as 0.6 as an example, and then performing operation S304, it may be obtained that the emotion assessment value is smaller than the preset emotion threshold value. The target object Obj _4 may be determined to be a non-negative emotion. Operation S307 may be performed according to the information Info _4 to acquire intention information Inten _3 corresponding to the information Info _ 4. Then, according to the intention information Inten _3, operation S308 is performed.

In one example, intent information Inten _3 does not indicate a target intent. After performing operation S308, operation S311 may be performed according to intention information Inten _ 3. In this example, intent information Inten _3 does not indicate the first target issue. After performing operation S311, operation S314 may be performed according to intention information Inten _ 3.

In operation S314, it is determined whether the intention information indicates a second target issue.

For example, a plurality of second degrees of similarity between a plurality of second preset questions and the intention information may be calculated. The second target question indicated by the intention information may be determined from a plurality of second preset questions according to a plurality of second similarities.

In the disclosed embodiment, in response to the intention information indicating the second target issue, operation S314 is performed.

In the embodiment of the present disclosure, in response to the intention information not indicating the second target issue, operation S317 is performed.

Next, taking the intention information indicating the second target issue as an example, a detailed description will be made in conjunction with operation S315 and operation S316.

For example, among the plurality of second preset questions, the second preset question "× bar is several months and days" has the largest second similarity with the intention information Inten _3, and the second similarity is greater than a preset second similarity threshold. Therefore, the second preset question "xx knots are months and days" is determined as the second target question indicated by the intention information Inten _ 3.

In operation S315, second knowledge information corresponding to the second target issue is acquired.

For example, each second preset question corresponds to one second knowledge information. Second knowledge information corresponding to a second preset question "xx knots are months and days" is acquired, and is determined as second knowledge information corresponding to intention information Inten _ 3.

In operation S315, third response information is generated according to the second knowledge information.

For example, the third response information may be "xx festival is 1 month and 1 day".

The method provides stronger conversation capability for the intelligent customer service and enlarges the scope of the intelligent customer service for answering knowledge. The question and answer quality of the intelligent customer service is improved, and the user experience is further improved.

Next, taking the second target question not indicated by the intention information as an example, a detailed description is made in conjunction with operation S317.

For example, take the example that the target input information is the information Info _5 "do you know who i is". The information Info _5 comes from the target object Obj _ 5. From the information Info _5, operations S302 to S303 may be performed, resulting in an emotion assessment value of 0.1 for the information Info _ 5. Taking the preset emotion threshold value as 0.6 as an example, and then performing operation S304, it may be obtained that the emotion assessment value is smaller than the preset emotion threshold value. The target object Obj _5 may be determined as a non-negative emotion and operation S307 may be performed according to the information Info _5 to acquire intention information Inten _4 of the information Info _ 5. Then, according to the intention information Inten _4, operation S308 is performed. In one example, intent information Inten _4 does not indicate a target intent. Then, according to the intention information Inten _4, operation S311 is performed. In this example, the intention information Inten _4 does not indicate the first target problem, operation S314 may be performed according to the intention information Inten _ 4. And, in this example, the intention information Inten _4 does not indicate the second target problem, operation S317 may be performed.

In operation S317, second preset information is presented.

For example, the second preset information may be "good you, please wait.

In some embodiments, a plurality of similarities between a plurality of preset questions and the intention information may be calculated; and determining the target question indicated by the intention information from the plurality of preset questions according to the plurality of similarities.

For example, the preset questions may include the first preset question described above and the second preset question described above. The similarity may include the first similarity described above and the second similarity described above.

Fig. 4 is a block diagram of an information answering device according to one embodiment of the present disclosure.

As shown in fig. 4, the apparatus 400 may include a first obtaining module 410, a second obtaining module 420, and a first responding module 430.

The first obtaining module 410 is configured to obtain the target input information.

A second obtaining module 420, configured to obtain emotion category information and intention information of the target input information.

A response module 430, configured to respond to the target input information according to the emotion classification information and the intention information.

In some embodiments, the reply module comprises: a first determination unit configured to determine an emotion estimation value according to the emotion classification information; a second determining unit, configured to determine that the emotion classification information indicates a first target emotion classification in response to the emotion assessment value being smaller than a preset emotion threshold; a first obtaining unit, configured to obtain, in response to the intention information indicating an intention of a target, a service data set corresponding to the intention of the target; and the first generating unit is used for generating first response information according to the service data set so as to respond to the target input information.

In some embodiments, the reply module comprises: a second acquisition unit configured to acquire knowledge information corresponding to the target question in response to determining that the intention information indicates the target question; and a second generating unit configured to generate second response information based on the knowledge information.

In some embodiments, the response module further comprises: a calculating unit, configured to calculate a plurality of similarities between a plurality of preset questions and the intention information; and a third determining unit, configured to determine, according to the plurality of similarities, a target question indicated by the intention information from the plurality of preset questions.

In some embodiments, the response module further comprises: a fourth determining unit, configured to determine that the emotion classification information indicates a second target emotion classification in response to the emotion assessment value being greater than or equal to a preset emotion threshold; the display unit is used for displaying the first preset information; and a switching unit for switching to the manual response mode.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 5 illustrates a schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 5, the apparatus 500 comprises a computing unit 501 which may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The calculation unit 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 executes the respective methods and processes described above, such as the information response method. For example, in some embodiments, the message answering method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the information answering method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the information answering method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

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

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

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims (13)

1. An information response method, comprising:

acquiring target input information;

acquiring emotion category information and intention information of the target input information; and

and responding to the target input information according to the emotion category information and the intention information.

2. The method of claim 1, wherein said responding to the target input information according to the emotion classification information and the intention information comprises:

determining an emotion evaluation value according to the emotion category information;

determining that the emotion category information indicates a first target emotion category in response to the emotion assessment value being less than a preset emotion threshold;

in response to the intention information indicating a target intention, obtaining a business data set corresponding to the target intention; and

and generating first response information according to the service data set so as to respond to the target input information.

3. The method of claim 1, said responding to the target input information according to the emotion classification information and the intention information comprising:

in response to determining that the intent information indicates a target issue, obtaining knowledge information corresponding to the target issue; and

and generating second response information according to the knowledge information.

4. The method of claim 3, said responding to the target input information according to the emotion classification information and the intention information further comprising:

calculating a plurality of similarities between a plurality of preset questions and the intention information; and

and according to the plurality of similarities, determining a target problem indicated by the intention information from the plurality of preset problems.

5. The method of claim 2, said responding to the target input information according to the emotion classification information and the intention information further comprising:

determining that the emotion category information indicates a second target emotion category in response to the emotion assessment value being greater than or equal to a preset emotion threshold;

displaying first preset information; and

and switching to a manual response mode.

6. An information answering device, comprising:

the first acquisition module is used for acquiring target input information;

the second acquisition module is used for acquiring emotion category information and intention information of the target input information; and

and the response module is used for responding the target input information according to the emotion category information and the intention information.

7. The apparatus of claim 6, wherein the reply module comprises:

a first determination unit, configured to determine an emotion assessment value according to the emotion category information;

a second determination unit, configured to determine that the emotion classification information indicates a first target emotion classification in response to the emotion assessment value being smaller than a preset emotion threshold;

a first obtaining unit, configured to obtain, in response to the intention information indicating an intention of a target, a business data set corresponding to the intention of the target; and

and the first generating unit is used for generating first response information according to the service data set so as to respond to the target input information.

8. The apparatus of claim 6, the reply module comprising:

a second acquisition unit configured to acquire knowledge information corresponding to a target question in response to a determination that the intention information indicates the target question; and

and the second generating unit is used for generating second response information according to the knowledge information.

9. The apparatus of claim 8, the reply module further comprising:

a calculation unit configured to calculate a plurality of similarities between a plurality of preset questions and the intention information; and

and the third determining unit is used for determining the target question indicated by the intention information from the preset questions according to the similarity degrees.

10. The apparatus of claim 6, the reply module further comprising:

a fourth determination unit configured to determine that the emotion classification information indicates a second target emotion classification in response to the emotion assessment value being greater than or equal to a preset emotion threshold;

the display unit is used for displaying the first preset information; and

and the switching unit is used for switching to the manual response mode.

11. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.

12. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1 to 5.

13. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images