CN114579750A

CN114579750A - Information processing method and device, computer equipment and storage medium

Info

Publication number: CN114579750A
Application number: CN202210314713.XA
Authority: CN
Inventors: 胡立云
Original assignee: Weikun Shanghai Technology Service Co Ltd
Current assignee: Weikun Shanghai Technology Service Co Ltd
Priority date: 2022-03-22
Filing date: 2022-03-22
Publication date: 2022-06-03

Abstract

The embodiment of the application provides an information processing method, an information processing device, computer equipment and a storage medium, which are applied to the fields of smart cities and artificial intelligence technology, and the method comprises the following steps: performing word segmentation processing on the appeal text of the target object to obtain a word segmentation result; performing emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object, and performing intention recognition on the word segmentation result to obtain a target appeal intention of the target object; determining a target appeal scene according to the target appeal information and the target appeal intention, and matching a target appeal processing scheme from the first corpus according to the target appeal scene; and performing appeal processing according to the target appeal processing scheme. By adopting the complaint process, the complaint processing efficiency and the complaint processing quality can be improved. The application relates to blockchain techniques, such as appealing text can be read from blockchains.

Description

Information processing method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of data analysis technologies, and in particular, to an information processing method and apparatus, a computer device, and a storage medium.

Background

The traditional appeal processing flow is complex, for example, the work of customer service personnel of financial companies, banks and the like is heavy and complex, and one of the important reasons is as follows: the inventor finds that a large amount of manpower and time are needed in the process, and due to the fact that judgment capabilities of personnel are different, the problem is easy to be solved in one link, the processing progress of the whole appeal process is slowed, user experience is influenced, and even the overall image of a company is influenced. Therefore, an intelligent scheme for improving the demand processing efficiency and the demand quality is urgently needed.

Disclosure of Invention

The embodiment of the application provides an information processing method, an information processing device, computer equipment and a storage medium, and the demand processing efficiency and the demand processing quality can be improved.

In one aspect, an embodiment of the present application provides an information processing method, including:

acquiring an appeal text of a target object, and performing word segmentation processing on the appeal text to obtain a word segmentation result;

performing emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object, and performing intention recognition on the word segmentation result to obtain a target appeal intention of the target object;

determining a target appeal scene according to the target appeal information and the target appeal intention, and matching a target appeal processing scheme from a first corpus according to the target appeal scene, wherein the first corpus comprises a plurality of appeal processing schemes, and each appeal processing scheme corresponds to one or more appeal scenes;

and performing appeal processing according to the target appeal processing scheme.

In another aspect, an embodiment of the present application provides an information processing apparatus, including:

the acquisition module is used for acquiring an appeal text of the target object and performing word segmentation processing on the appeal text to obtain a word segmentation result;

the recognition module is used for carrying out emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object, and carrying out intention recognition on the word segmentation result to obtain a target appeal intention of the target object;

the processing module is used for determining a target appeal scene according to the target appeal information and the target appeal intention, and matching a target appeal processing scheme from a first corpus according to the target appeal scene, wherein the first corpus comprises a plurality of appeal processing schemes, and each appeal processing scheme corresponds to one or more appeal scenes;

and the processing module is also used for performing appeal processing according to the target appeal processing scheme.

In another aspect, an embodiment of the present application provides a computer device, including a processor and a memory, where the processor and the memory are connected to each other, where the memory is used to store computer program instructions, and the processor is configured to execute the program instructions to implement the information processing method.

In another aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer program instructions are stored, and when the computer program instructions are executed by a processor, the computer program instructions are used to execute the information processing method.

In summary, the computer device may perform word segmentation on the appeal text of the target object to obtain a word segmentation result, perform emotion recognition on the word segmentation result to obtain target appeal information of the target object, perform intent recognition on the word segmentation result to obtain a target appeal intent of the target object, determine a target appeal scene according to the target appeal information and the target appeal intent, match a target appeal processing scheme from the first corpus according to the target appeal scene, and perform appeal processing according to the target appeal processing scheme.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic diagram of an information processing process provided in an embodiment of the present application;

fig. 2 is a schematic flowchart of an information processing method provided in an embodiment of the present application;

FIG. 3 is a flow chart illustrating an information processing method according to yet another embodiment of the present application;

fig. 4 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

The embodiment of the application provides an information processing scheme, which mainly depends on an AI (artificial intelligence) technology, breaks through the traditional mode of processing the target appeal (such as the user appeal), really hands the judgment and processing of the problems to a computer for processing, and greatly improves the processing speed of the appeal while releasing manpower. The information processing scheme can be executed by computer equipment, and the computer equipment can be an intelligent terminal or a server. The intelligent terminal can be an intelligent terminal with information processing capability such as a desktop computer. The server may be an independent server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, but is not limited thereto.

The information processing scheme is briefly introduced below by taking an object as an example.

As shown in fig. 1, the information processing scheme mainly includes three modules: data identification, scene analysis and scheme landing. Specifically, the method comprises the following steps: the data identification module is used for providing the most original data for the scene analysis module; the scene analysis module is used for carrying out analysis calculation according to the original data to obtain a calculation result; the solution landing module is used for providing a solution corresponding to the calculation result, wherein the solution landing module stores various solutions, and the solutions are a set of problem processing modes.

The data identification module comprises functions of emotion analysis, intention identification and the like. In one embodiment. The data recognition module also includes voice recognition functionality. In the embodiment of the application, the collected appeal voices of the user can be obtained, and the appeal voices can be converted into appeal texts through the voice recognition function. The appeal text can be used for representing appeal of the user. Besides the acquisition of the appeal text by the scheme, the appeal text can also be acquired by other modes, and the method for acquiring the appeal text is not limited by the embodiment of the application. The data obtained by the data identification module, such as the emotion information, provides a data base for the subsequent module processing.

Wherein, the scene analysis module comprises the functions of corpus feeding, scene classification and the like. In order to more accurately process the user appeal, the appeal of different users needs to be classified first, and detailed scenes are obtained, for example, by analyzing the appeal of different users, the finally detailed scenes can include scenes of user consultation product details, scenes of user complaint fund delayed account arrival, and the like. The accuracy of scene analysis depends on two kinds of data, one is data obtained by processing of the data identification module, and the other is corpus feeding inside the system. The data processed by the data identification module can be used for determining specific appeal scenes. Corpus feeding may refer to translating all scenarios of operator, developer, tester, etc. interacting with a user during the operation of a company into a computer-understood language for addition to a knowledge base. As the feeding corpora increase, the knowledge base will be more and more complete, thereby more accurately serving scene analysis.

Wherein, the scheme landing module is used for providing a processing scheme for the appeal. The solution of each scene interacting with the user is not constant, for example, the initial solution of the consultation-type scene may only inform the user of the product information consulted by the user, and with the enrichment of the knowledge base, other product information of the same type may also be provided to the user, and so on. For each question asked by the user, the system can calculate at least three solutions for the operator to select, thereby matching the solutions suitable for different user groups.

By adopting the information processing scheme provided by the embodiment of the application, the processing speed of appeal can be greatly increased, and the accuracy of problem processing is improved. Compare in traditional pure manual processing, added the advantage of machine learning, along with the increase of the quantity of handling the appeal, the rate of accuracy can be higher and higher.

Based on the information processing scheme described above, an embodiment of the present application provides an information processing method. The information processing method can be applied to the aforementioned computer apparatus. Referring to fig. 2, the method may include the steps of:

s201, obtaining an appeal text of the target object, and performing word segmentation processing on the appeal text to obtain a word segmentation result.

Wherein the object may be a user. Accordingly, the target object may be a target user. The target user may refer to a user who submits appeal information, and the appeal information may be appeal text or appeal voice.

In one embodiment, the appealing text may be a specified type of text submitted by the target user through the first window. The first window may be a chat window, a message window or a short message window. The specified types include, but are not limited to, advisory, complaint, suggestive, and the like, appeal types. In one embodiment, the appealing text may also be a specified type of text obtained by speech recognition of the appealing speech of the target user.

S202, performing emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object, and performing intention recognition on the word segmentation result to obtain a target appeal intention of the target object.

The target appeal emotion information refers to appeal emotion information of the target object. The target appeal intent refers to an appeal intent of the target object.

In one embodiment, the method for obtaining the target appeal emotion information of the target object by performing emotion recognition on the word segmentation result by the computer device may be as follows: and the computer equipment matches each word in the word segmentation result with each word in the second corpus to obtain a keyword group which reflects the appeal emotion and is included in the word segmentation result, and then determines the emotion entropy value corresponding to each keyword in the keyword group according to the corresponding relation between the word and the emotion entropy value, so that the target appeal emotion information of the target object is determined according to the emotion entropy value corresponding to each keyword. The keyword set may include one or more keywords reflecting the appeal emotion. The emotion entropy value may be used to indicate the degree of emotional tendency. Illustratively, the entropy value of emotion can take a value between 0 and 1, with higher entropy values indicating more positive intentions or more positive attitudes and lower entropy values indicating more negative intentions or more negative attitudes. As such, the emotion entropy values can be used to identify the emotional state.

In one embodiment, when the keyword group includes one keyword, the mode of determining the target appeal emotion information of the target object according to the emotion entropy value corresponding to each keyword may be: and determining the emotion entropy value corresponding to the keyword as the target appeal emotion information of the target object. In one embodiment, when the keyword group includes a plurality of keywords, the mode of determining the target appeal emotion information of the target object according to the emotion entropy corresponding to each keyword may be: and the computer equipment calculates according to the emotion entropy values corresponding to the keywords to obtain an emotion entropy value mean value, and determines the emotion entropy value mean value as the target appeal emotion information of the target object. The emotion entropy value mean value obtained through mean calculation can reflect the overall emotion tendency degree. For example, if the user a submits an appeal text to the computer device, where the appeal text is "i do not like this product, this product has low profit", and the computer device may obtain the keyword group according to the appeal text: dislike and low profit. The "dislike" and "low profit" here belong to words of negative intention. And then, the computer equipment can determine the emotion entropy values respectively corresponding to the two keywords according to the corresponding relation between the keywords and the emotion entropy values, and perform mean calculation on the emotion entropy values respectively corresponding to the two keywords to obtain the emotion entropy mean value so as to determine the emotion information required by the user A.

In one embodiment, since the keywords recorded in the second corpus may be incomplete, missing keywords reflecting the appeal emotion may also be determined as follows, so as to determine the target appeal emotion information of the target object by combining the obtained keyword group. The specific mode is as follows: the computer device can judge whether a first word exists in all words except the key word group in the word segmentation result, and the first word has a related second word in the second corpus or the third corpus. After determining that the first word exists in each word except the keyword group in the word segmentation result, the computer device may determine an emotion entropy value corresponding to the second word according to the correspondence between the word and the emotion entropy value, and determine an emotion entropy value of the first word according to the emotion entropy value corresponding to the second word. After obtaining the emotion entropy value corresponding to the keyword group and the emotion entropy value corresponding to the first word, the computer device may determine target emotion information corresponding to the target object according to the emotion entropy value corresponding to the keyword group and the emotion entropy value corresponding to the first word.

In one embodiment, the computer device obtains the entropy corresponding to the first word based on the entropy corresponding to the second word by setting the entropy corresponding to the first word to a value similar to the entropy corresponding to the second word (e.g., by a difference between the values similar to the entropy corresponding to the second word and a predetermined value), which indicates that the difference between the entropy corresponding to the first word and the entropy corresponding to the second word is small. The second word may include a word in the first word, or a part of the second word is the same as a part of the first word. The second term has the same emotional tendency as the first term. For example, suppose that a user a submits a solicitation text to a computer device, the solicitation text is "i do not tolerate the product, the product has low profit", and the computer device may obtain a keyword group according to the solicitation text: "low profit". The computer device may determine that a first word "intolerant" exists among words other than "low profit" in the segmentation result, that the associated second words "intolerant", "intolerant" and "not" in the second corpus or the third corpus all have a negative tendency. The computer device may set the sentiment entropy value of "intolerance" to a value that is close to the sentiment entropy value corresponding to "no".

In one embodiment, the computer device performs intent recognition according to the word segmentation result, and the manner of obtaining the target appeal intent of the target object may be: and the computer equipment inputs the word segmentation result into the intention recognition model for intention recognition to obtain the target appeal intention of the target object. The intention recognition model can be obtained by training an initial classification model by using a word segmentation result corresponding to each appeal text sample in a plurality of appeal text samples. In one embodiment, the computer device performs intent recognition according to the word segmentation result, and the manner of obtaining the target appeal intent of the target object may further be: and the computer equipment inputs the word segmentation result and the target appeal emotion information into the intention recognition model for intention recognition to obtain the target appeal intention of the target object.

In one embodiment, if the target appeal intention of the target object cannot be identified through the intention identification model, the word segmentation result can be set as a target category, and then all word segmentation results in the target category are clustered to obtain a plurality of word segmentation result sets; the method comprises the steps that computer equipment sends processing indication information to a target intelligent terminal, wherein the processing indication information carries a plurality of word segmentation result sets, and the processing indication information is used for indicating related personnel, such as an appeal intention of an operator corresponding to each word segmentation result set mark; the computer equipment receives the appeal intention, marked by each participle result set, returned by the target intelligent terminal, and determines the target participle result set where the participle result obtained according to the appeal text of the target object is located, so that the appeal intention, marked by the target participle result set, is determined as the target appeal intention of the target object. It should be noted that, the participle results from different sources may be aggregated in all the participle results in the target category, in this way, even if the intention recognition model cannot recognize the intention of the object, the intention of the object can be obtained, and the clustered results are provided to relevant personnel, such as operators for tagging, so that the workload of the operators can be reduced.

S203, determining a target appeal scene according to the target appeal information and the target appeal intention, and matching a target appeal processing scheme from a first corpus according to the target appeal scene, wherein the first corpus comprises a plurality of appeal processing schemes, and each appeal processing scheme corresponds to one or more appeal scenes.

In one embodiment, the appeal processing scheme in the first corpus may include at least one of: firstly, obtaining an appeal processing scheme according to appeal contents recorded by operators in a telephone mode and the like and a corresponding processing scheme; acquiring a demand processing scheme according to the problem reasons and the processing scheme recorded by the company developers and/or the testers when the system problems are processed; and thirdly, obtaining an appeal scene through the web crawler and an appeal processing scheme obtained through the corresponding processing scheme.

And S204, performing appeal processing according to the target appeal processing scheme.

In the embodiment of the application, the computer device can determine at least one appeal scene associated with the target appeal intention, and determine the appeal scene corresponding to the target appeal information from the at least one appeal scene as the target appeal scene according to the appeal emotion information corresponding to each appeal scene in the at least one appeal scene. Then, the computer may query a target appeal processing scheme corresponding to the target appeal scene from the first corpus, and perform appeal processing according to the target appeal processing scheme. For example, assume that the target appeal scenario is a query. Through the process, the computer device can query the target appeal processing scheme corresponding to the target appeal scene from the first corpus, and the computer device can provide the product details to the target user if the target appeal processing scheme provides the product details to the user.

In one embodiment, the at least one appeal scenario may be determined by: determining at least one appeal scene corresponding to the target appeal intention according to the corresponding relation between the appeal intention and the appeal scene to serve as at least one appeal scene related to the target appeal intention; or determining a target appeal category corresponding to the target appeal intention, and determining at least one appeal scene in the target appeal category as at least one appeal scene associated with the target appeal intention. For example, when the target appeal intention is a query product, a complaint product, an endorsement product, or expresses a desire for a product, the computer device may determine that a target appeal category corresponding to the target appeal intention is the product, and may determine at least one appeal scene in the appeal category of the product. In one embodiment, in the process of determining the at least one appeal scene corresponding to the target appeal intention, in order to accurately determine the at least one appeal scene, an appeal scene set in a target appeal category may be determined according to a corresponding relationship between the appeal intention and the appeal scene or determined, and then the at least one appeal scene is determined from the appeal scene set according to a word segmentation result.

In one embodiment, in the process of performing appeal processing according to the target appeal scheme, the computer device may send the target appeal processing scheme to the target intelligent terminal before performing the appeal processing according to the target appeal scheme, and execute the operation of performing the appeal processing on the target object according to the target appeal processing scheme when receiving a confirmation instruction returned by the target intelligent terminal according to the target appeal processing scheme.

In an embodiment, the computer device may send the segmentation result to the target intelligent terminal, and the computer device may further receive a corpus that is not recognized in the segmentation result and is fed back by the target intelligent terminal, and update the corpus to the aforementioned second corpus.

As can be seen, in the embodiment shown in fig. 2, the computer device may perform word segmentation on the appeal text of the target object to obtain a word segmentation result, perform emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object, perform intention recognition on the word segmentation result to obtain a target appeal intention of the target object, determine a target appeal scene according to the target appeal emotion information and the target appeal intention, match a target appeal processing scheme from the first corpus according to the target appeal scene, and perform appeal processing according to the target appeal processing scheme, so that the appeal processing efficiency and the appeal processing quality can be improved.

Based on the information processing method provided above, an embodiment of the present application further provides an information processing method. The information processing method can be applied to the aforementioned computer apparatus. Referring to fig. 3, the method may include the steps of:

s301, obtaining an appeal text of the target object, and performing word segmentation processing on the appeal text to obtain a word segmentation result.

S302, performing emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object, and performing intention recognition on the word segmentation result to obtain a target appeal intention of the target object.

S303, determining a target appeal scene according to the target appeal emotion information and the target appeal intention.

Steps S301 to S303 may refer to steps S201 to S203 in the embodiment of fig. 2, which is not described herein again in this embodiment of the present application.

S304, acquiring the object data of the target object.

When the object is a user, the object data may be user data. It should be noted that the user data referred to in the present application are all information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant countries and regions.

The user data may be data such as gender, age, and behavior preference.

S305, extracting the object label according to the object data.

When the object is a user, the object tag may be a user tag.

In one embodiment, the user tags may include gender tags when the user data includes gender, age tags (e.g., 70 after, 80 after, 90 after, or old, middle aged, young) when the user data includes age, and behavior preference tags when the user data includes behavior preferences.

S306, screening out an appeal processing scheme matched with the object tag from the at least one appeal processing scheme;

and S307, determining the matched appeal processing scheme as a target appeal processing scheme.

In one embodiment, the appeal processing scheme is used for feeding back information to the user, and when the user tags include gender tags, the appeal processing schemes corresponding to different gender tags provide different content details and/or different content types. When the user tags include age tags, the appeal processing schemes corresponding to different age tags may provide different content details and/or different content types. When the user tags include behavior preference tags, the content detail degree and/or the content type of the appeal processing scheme correspondingly provided by different behavior preference tags are different.

For example, when the user tags include the elderly people, an appeal processing scheme matching the elderly people tags may be identified from the appeal processing schemes corresponding to the target appeal scenes, and if at least one appeal processing scheme is a plurality of appeal processing schemes, product details provided by each target appeal processing scheme to the user are different, and the appeal processing scheme matching the elderly people tags identified herein may be the most detailed appeal processing scheme of the product details in the plurality of appeal processing schemes.

In one embodiment, the appeal processing scheme is to provide electronic resources, such as electronic coupons and subsidies, to the user, and when the user tags include gender tags, the appeal processing schemes corresponding to different gender tags correspond to different values or types of the provided electronic resources. When the user tags include age tags, the electronic resource values or types of electronic resources corresponding to the provided appeal processing schemes are different for different age tags. When the user tags comprise behavior preference tags, the values of the electronic resources or the types of the electronic resources of the appeal processing scheme correspondingly provided by different behavior preference tags are different.

And S308, performing appeal processing according to the target appeal processing scheme.

Step S308 may refer to step S204 in fig. 2, which is not described herein again in this embodiment of the application.

In one embodiment, in addition to matching the appeal processing scheme by extracting the user tag, the computer device may extract a product tag from the word segmentation result, and determine a target processing scheme from the at least one processing scheme according to the product tag. In one embodiment, the computer device may determine a product type according to the product tag, then query the first corpus for at least one appeal processing scheme corresponding to the target appeal scene, and screen out an appeal processing scheme matching the product type from the at least one appeal processing scheme, thereby determining the matching appeal processing scheme as the target appeal processing scheme. For example, when the product tag is off-shelf, the computer device may identify an appeal processing scheme matching the off-shelf from the at least one appeal processing scheme, the matching appeal processing scheme may be to recommend a new product to the user, or may be to recommend a new product of the same type to the user.

In one embodiment, besides the text of the target object, an appeal image of the target object may be obtained, where the appeal image may be an image such as an expression picture. The computer equipment can also perform emotion recognition on the appeal image to obtain appeal emotion information of the appeal image. Correspondingly, the target appeal scene can be determined according to the target emotion information and the target appeal intention, and the target appeal scene can also be determined in the following manner: the computer device can determine a target appeal scene according to the appeal emotion information, the target appeal emotion information and the target appeal intention of the appeal image. In one embodiment, the computer device updates the target emotion information with the appeal emotion information of the appeal image to obtain updated appeal emotion information. And determining a target appeal scene according to the updated appeal emotion information and the target appeal intention. The method for determining the target appeal scene according to the updated appeal information and the target appeal intention can refer to the method for determining the target appeal scene according to the target appeal information and the target appeal intention, and details of the embodiment of the application are omitted here.

In one embodiment, the computer device may perform emotion recognition on the appeal image through the emotion information recognition model to obtain appeal emotion information of the appeal image. The emotion information identification model is obtained by training an initial regression model by using a plurality of appeal image samples. In one embodiment, the computer device may further perform emotion recognition on the appeal emotion image through the emotion information recognition model to obtain initial appeal emotion information of the appeal image. Considering that the appeal emotion information of the appeal image is identified by the appeal emotion model in an actual application scene may not be accurate enough, for example, for the smiling expression image, in some cases, the expression image represents positive emotion, and in other cases, the expression represents negative emotion, so the computer device may further input a word segmentation result or the emotion type identification model to obtain the appeal emotion type identified by the emotion type identification model, and then the computer device adjusts the initial appeal emotion information of the appeal image by using the identified appeal emotion type to obtain the adjusted appeal emotion information corresponding to the appeal image, so as to serve as the appeal emotion information corresponding to the appeal image. For example, if the positive emotion represented by the appeal image is determined according to the appeal type identified by the emotion category identification model, the initial appeal emotion information may be increased by a certain value, and conversely, the initial appeal emotion information may be decreased by a certain value.

In one embodiment, the aforementioned object may also be an item or product. The appeal text may also be text for expressing appeal to a target item or target product. The appeal text can be submitted by the target person through a second window (a window which can be used for editing the appeal text) or can be obtained after the appeal voice of the target person is subjected to voice recognition. The object data may be project data or product data. The appealing intention can be a specific development intention. The appeal scene can be a specific development scene. The appeal processing scheme may be a specific development scheme.

As can be seen, in the embodiment shown in fig. 3, the computer device may further determine a specific appeal processing scheme in combination with the user tag, so that more accurate appeal processing is performed according to the determined appeal processing scheme, and the appeal processing quality is further improved.

The application relates to blockchain technology, and the appeal text or appeal image can be read from a blockchain or acquired through a blockchain network.

Based on the information processing method described above, an embodiment of the present application further provides an information processing apparatus. The information processing apparatus can be applied to the aforementioned computer device. Specifically, referring to fig. 4, the apparatus may include:

the obtaining module 401 is configured to obtain an appeal text of the target object, and perform word segmentation processing on the appeal text to obtain a word segmentation result.

The identification module 402 is configured to perform emotion identification on the word segmentation result to obtain target appeal emotion information of the target object, and perform intent identification on the word segmentation result to obtain a target appeal intent of the target object.

The processing module 403 is configured to determine a target appeal scene according to the target appeal information and the target appeal intention, and match a target appeal processing scheme from a first corpus according to the target appeal scene, where the first corpus includes multiple appeal processing schemes, and each appeal processing scheme corresponds to one or multiple appeal scenes.

The processing module 403 is further configured to perform appeal processing according to the target appeal processing scheme.

In an optional implementation manner, the identification module 402 performs emotion identification on the word segmentation result to obtain target appeal emotion information of the target object, specifically, matches each word in the word segmentation result with each word in the second corpus to obtain a keyword group reflecting appeal emotion, included in the word segmentation result; determining an emotion entropy value corresponding to each keyword in the keyword group according to the corresponding relation between the words and the emotion entropy values, wherein the emotion entropy values are used for indicating the emotion tendency degree; and determining target appeal emotional information of the target object according to the emotion entropy values corresponding to the keywords.

In an optional implementation manner, the identifying module 402 determines target appeal emotion information of the target object according to the emotion entropy values corresponding to the keywords, specifically, calculates an emotion entropy mean value according to the emotion entropy values corresponding to the keywords; and determining the emotion entropy value mean value as target appeal emotion information of the target object.

In an optional implementation manner, the processing module 403 determines a target appeal scene according to the target appeal information and the target appeal intention, specifically, determines at least one appeal scene corresponding to the target appeal intention according to a corresponding relationship between the appeal intention and the appeal scene; screening out an appeal scene matched with the target emotion information from the at least one appeal scene; and determining the matched appeal scene as a target appeal scene.

In an optional implementation manner, the processing module 403 is further configured to obtain object data of the target object; extracting an object tag according to the object data; the processing module 403 matches a target appeal processing scheme from the first corpus according to the target appeal scene, specifically, queries at least one appeal processing scheme corresponding to the target appeal scene from the first corpus; screening out an appeal processing scheme matched with the object tag from the at least one appeal processing scheme; determining the matched appeal processing scheme as a target appeal processing scheme.

In an optional embodiment, the processing module 403 is further configured to extract a product label from the word segmentation result; determining a product type from the product label; the processing module 403 matches a target appeal processing scheme from the first corpus according to the target appeal scene, specifically, queries at least one appeal processing scheme corresponding to the target appeal scene from the first corpus; screening out an appeal processing scheme matched with the product type from the at least one appeal processing scheme; determining the matched appeal processing scheme as a target appeal processing scheme.

In an optional implementation manner, the processing module 403 is further configured to, after matching a target appeal processing scheme from the first corpus according to the target appeal scene, send the target appeal processing scheme to the target smart terminal; and when a confirmation instruction returned by the target intelligent terminal according to the target appeal processing scheme is received, executing the step of performing appeal processing on the target object according to the target appeal processing scheme.

In the embodiment shown in fig. 4, the information processing device may perform word segmentation on the appeal text of the target object to obtain a word segmentation result, perform emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object, perform intention recognition on the word segmentation result to obtain a target appeal intention of the target object, determine a target appeal scene according to the target appeal emotion information and the target appeal intention, match a target appeal processing scheme from the first corpus according to the target appeal scene, and perform appeal processing according to the target appeal processing scheme, so that the appeal processing efficiency and the appeal processing quality can be improved.

Please refer to fig. 5, which is a schematic structural diagram of a computer device according to an embodiment of the present application. The computer device described in this embodiment may include: one or more processors 1000 and memory 2000. The processor 1000 and the memory 2000 may be connected by a bus or the like.

The Processor 1000 may be a Central Processing Unit (CPU), and may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 2000 may be a high-speed RAM memory or a non-volatile memory (e.g., a disk memory). The memory 2000 is used for storing a set of program codes, and the processor 1000 may call the program codes stored in the memory 2000. Specifically, the method comprises the following steps:

the processor 1000 is configured to obtain an appeal text of a target object, and perform word segmentation processing on the appeal text to obtain a word segmentation result; performing emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object, and performing intention recognition on the word segmentation result to obtain a target appeal intention of the target object; determining a target appeal scene according to the target appeal information and the target appeal intention, and matching a target appeal processing scheme from a first corpus according to the target appeal scene, wherein the first corpus comprises a plurality of appeal processing schemes, and each appeal processing scheme corresponds to one or more appeal scenes; and performing appeal processing according to the target appeal processing scheme.

In one embodiment, the processor 1000 is specifically configured to:

matching each word in the word segmentation result with each word in a second corpus to obtain a key phrase which reflects appeal emotion and is included in the word segmentation result;

determining an emotion entropy value corresponding to each keyword in the keyword group according to the corresponding relation between the words and the emotion entropy values, wherein the emotion entropy values are used for indicating the emotion tendency degree;

and determining target appeal emotion information of the target object according to the emotion entropy values corresponding to the key words.

In an embodiment, when determining the target appeal emotion information of the target object according to the emotion entropy values corresponding to the keywords, the processor 1000 is specifically configured to:

calculating to obtain an emotion entropy value mean value according to the emotion entropy values corresponding to the keywords;

and determining the emotion entropy value mean value as target appeal emotion information of the target object.

In an embodiment, the processor 1000 is further specifically configured to:

determining at least one appeal scene corresponding to the target appeal intention according to the corresponding relation between the appeal intention and the appeal scene;

screening out an appeal scene matched with the target emotion information from the at least one appeal scene;

and determining the matched appeal scene as a target appeal scene.

In one embodiment, the processor 1000 is further configured to:

acquiring object data of the target object;

extracting an object tag according to the object data;

when the target appeal processing scheme is matched from the first corpus according to the target appeal scene, the processor 1000 is specifically configured to:

inquiring at least one appeal processing scheme corresponding to the target appeal scene from the first corpus;

screening out an appeal processing scheme matching the object tag from the at least one appeal processing scheme;

determining the matched appeal processing scheme as a target appeal processing scheme.

In one embodiment, the processor 1000 is further configured to:

extracting a product label from the word segmentation result;

determining a product type from the product label;

when the target appeal processing scheme is matched from the first corpus according to the target appeal scene, the processor 1000 is further specifically configured to:

screening out an appeal processing scheme matched with the product type from the at least one appeal processing scheme;

In one embodiment, after matching the target appeal processing scheme from the first corpus according to the target appeal scenario, the processor 1000 is further configured to:

sending the target appeal processing scheme to a target intelligent terminal;

and when a confirmation instruction returned by the target intelligent terminal according to the target appeal processing scheme is received, executing the step of performing appeal processing on the target object according to the target appeal processing scheme.

In a specific implementation, the processor 1000 described in this embodiment of the present application may execute the implementation described in the embodiment of fig. 2 and the embodiment of fig. 3, and may also execute the implementation described in this embodiment of the present application, which is not described herein again.

The functional modules in the embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a form of sampling hardware, and can also be realized in a form of sampling software functional modules.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The computer readable storage medium may be volatile or nonvolatile. For example, the computer storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like. The computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a string of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, which is used for verifying the validity (anti-counterfeiting) of the information and generating a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. An information processing method, characterized by comprising:

2. The method of claim 1, wherein the performing emotion recognition on the word segmentation result to obtain target appeal emotion information of the target object comprises:

determining an emotion entropy value corresponding to each keyword in the keyword group according to a corresponding relation between the words and the emotion entropy values, wherein the emotion entropy values are used for indicating emotion tendency degrees;

3. The method of claim 2, wherein the determining the target appeal emotion information of the target object according to the emotion entropy value corresponding to each keyword comprises:

4. The method of any one of claims 1-3, wherein the determining a target appeal scene from the target appeal sentiment information and the target appeal intent, comprises:

and determining the matched appeal scene as a target appeal scene.

5. The method of claim 1, further comprising:

acquiring object data of the target object;

extracting an object tag according to the object data;

the matching of the target appeal processing scheme from the first corpus according to the target appeal scenes comprises:

6. The method of claim 1, further comprising:

extracting a product label from the word segmentation result;

determining a product type from the product label;

the matching of the target appeal processing scheme from the first corpus according to the target appeal scene comprises:

7. The method of claim 1, wherein after matching a target appeal processing scheme from a first corpus according to the target appeal scenario, the method further comprises:

sending the target appeal processing scheme to a target intelligent terminal;

8. An information processing apparatus characterized by comprising:

9. A computer device comprising a processor and a memory, the processor and the memory being interconnected, wherein the memory is configured to store computer program instructions, and the processor is configured to execute the program instructions to implement the method of any one of claims 1-7.

10. A computer-readable storage medium, having stored thereon computer program instructions, which, when executed by a processor, are adapted to perform the method of any one of claims 1-7.