CN117251631A

CN117251631A - Information recommendation method, device, equipment and storage medium based on artificial intelligence

Info

Publication number: CN117251631A
Application number: CN202311209775.5A
Authority: CN
Inventors: 罗冬阳
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2023-09-19
Filing date: 2023-09-19
Publication date: 2023-12-19

Abstract

The application belongs to the field of artificial intelligence and the field of financial science and technology, and relates to an information recommendation method based on artificial intelligence, which comprises the following steps: acquiring a current appointed communication theme of a target seat and a target user in the process of business communication operation; acquiring an agent portrait of a target agent and a user portrait of a target user; acquiring historical communication time sequence characteristic information of a target user; acquiring initial theme feature information; calculating the appointed communication theme, the seat portrait, the user portrait and the initial theme feature information based on the double-tower model to determine target theme feature information; and acquiring a target conversation corresponding to the target theme characteristic information and pushing the target conversation to a target seat. The application also provides an information recommendation device, computer equipment and a storage medium based on the artificial intelligence. Furthermore, the target session of the present application may be stored in the blockchain. The method and the device can be applied to the communication theme recommendation scene in the financial field, and the recommendation accuracy of the conversation is effectively improved based on the use of the double-tower model.

Description

Information recommendation method, device, equipment and storage medium based on artificial intelligence

Technical Field

The application relates to the technical field of artificial intelligence development and the field of financial science and technology, in particular to an information recommendation method, an information recommendation device, computer equipment and a storage medium based on artificial intelligence.

Background

In the operation of financial insurance service, an agent is usually required to actively communicate with a customer, and the core flow of the whole communication operation is completed in the communication process, so as to improve the success rate of the operation task. Illustratively, in the process of car insurance agent telephone service, the agent needs to carry out multiple rounds of telephone communication with the user so as to gradually discover the requirements of the client and promote the client to apply, renew or obtain satisfaction and claim experience.

The conventional communication operation flow often provides a set of universal speaking operation for the seat, so that the seat can communicate with the client better by referring to the universal speaking operation, and the communication operation flow is completed smoothly. However, this way of providing the universal phone call requires the agent to determine the currently required communication topic in advance according to personal experience, and it takes much time to select the phone call required for the communication topic from the universal phones to communicate with the client. Because the accuracy of the currently required communication theme determined based on personal experience is low, the problem that the recommendation of the conversation selected from the universal conversations by the seat is inaccurate is easily caused, and the communication efficiency between the seat and the client is further affected.

Disclosure of Invention

An object of the embodiments of the present application is to provide an information recommendation method, apparatus, computer device and storage medium based on artificial intelligence, so as to solve the existing processing manner of providing a general conversation, and because the accuracy of the currently required communication theme determined based on personal experience is low, the problem of inaccurate recommendation of a conversation selected from the general conversation is easily caused by an agent, and further the problem of influencing the communication efficiency between the agent and a client is further solved, and further the technical problem of influencing the communication efficiency between the agent and the client is solved.

In order to solve the above technical problems, the embodiments of the present application provide an information recommendation method based on artificial intelligence, which adopts the following technical scheme:

acquiring a current appointed communication theme of a target agent and a target user in the process of carrying out business communication operation between the target agent and the target user;

acquiring an agent portrait of the target agent and a user portrait of the target user;

acquiring historical communication time sequence characteristic information corresponding to the target user; the historical communication time sequence characteristic information at least comprises a historical theme and a historical intention;

Acquiring initial theme characteristic information to be recommended from a preset theme information base; wherein the number of initial theme feature information includes a plurality;

calculating the appointed communication theme, the seat portrait, the user portrait and the initial theme feature information based on a preset double-tower model, and determining target theme feature information from all the initial theme feature information;

acquiring a target conversation corresponding to the target theme feature information;

pushing the target theme feature information and the target conversation to the target seat.

Further, the step of calculating the specified communication theme, the seat portrait, the user portrait and the initial theme feature information based on the preset double-tower model to determine target theme feature information from all the initial theme feature information specifically includes:

inputting the appointed communication theme, the agent portrait and the user portrait into a user side tower model in the double tower model, and extracting vectors of the appointed communication theme, the agent portrait and the user portrait through the user side tower model to obtain corresponding first feature vectors;

Inputting the initial theme feature information into an object side tower model in the double tower model, and extracting vectors of the initial theme feature information through the object side tower model to obtain a plurality of corresponding second feature vectors;

calculating the similarity between the first feature vector and each second feature vector through an interoperation layer in the double-tower model;

and determining target theme characteristic information from all the initial theme characteristic information based on the similarity.

Further, the step of calculating, by the interoperation layer in the dual-tower model, a similarity between the first feature vector and each of the second feature vectors specifically includes:

obtaining a preset similarity calculation strategy;

determining a target similarity calculation strategy from all the similarity calculation strategies;

and calculating the similarity between the first feature vector and each second feature vector through an interoperation layer in the double-tower model based on the target similarity calculation strategy.

Further, the step of determining the target theme feature information from all the initial theme feature information based on the similarity specifically includes:

Comparing the values of all the similarities, and screening out the designated similarity with the highest value from all the similarities;

acquiring a third feature vector corresponding to the specified similarity from all the second feature vectors;

acquiring appointed initial theme feature information corresponding to the third feature vector from all the initial theme feature information;

and taking the appointed initial theme feature information as the target theme feature information.

Further, the step of obtaining the target session corresponding to the target theme feature information specifically includes:

calling a preset speaking library;

extracting a first conversation corresponding to the target theme feature information from the conversation library;

acquiring the communication success rate of each first conversation;

screening out second dialects with communication success rate greater than a preset success rate threshold from all the first dialects;

and taking the second phone as the target phone.

Further, the step of obtaining the historical communication time sequence characteristic information corresponding to the target user specifically includes:

calling a preset communication information database;

acquiring target user information of the target user;

Acquiring associated call information corresponding to the business communication operation based on the target user information;

screening appointed communication information corresponding to the associated communication information from the communication information database;

and taking the appointed communication information as the historical communication time sequence characteristic information.

Further, the step of acquiring the initial theme feature information to be recommended from the preset theme information base specifically includes:

invoking the theme information base;

acquiring a designated job type of the service communication job;

screening out appointed theme characteristic information corresponding to the appointed job type from the theme information base;

and taking the appointed theme characteristic information as the initial theme characteristic information.

In order to solve the above technical problems, the embodiment of the present application further provides an information recommendation device based on artificial intelligence, which adopts the following technical scheme:

the first acquisition module is used for acquiring the current appointed communication theme of the target agent and the target user in the process of carrying out business communication operation between the target agent and the target user;

the second acquisition module is used for acquiring the seat portrait of the target seat and acquiring the user portrait of the target user;

The third acquisition module is used for acquiring historical communication time sequence characteristic information corresponding to the target user; the historical communication time sequence characteristic information at least comprises a historical theme and a historical intention;

the fourth acquisition module is used for acquiring initial theme characteristic information to be recommended from a preset theme information base; wherein the number of initial theme feature information includes a plurality;

the determining module is used for calculating the specified communication theme, the seat portrait, the user portrait and the initial theme feature information based on a preset double-tower model, and determining target theme feature information from all the initial theme feature information;

a fifth acquisition module, configured to acquire a target conversation corresponding to the target theme feature information;

and the pushing module is used for pushing the target theme characteristic information and the target conversation to the target seat.

In order to solve the above technical problems, the embodiments of the present application further provide a computer device, which adopts the following technical schemes:

In order to solve the above technical problems, embodiments of the present application further provide a computer readable storage medium, which adopts the following technical solutions:

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

in the embodiment of the application, in the process of carrying out business communication operation between a target agent and a target user, a current appointed communication theme between the target agent and the target user is firstly obtained; then, acquiring an agent portrait of the target agent and a user portrait of the target user; later, acquiring historical communication time sequence characteristic information corresponding to the target user; acquiring initial theme characteristic information to be recommended from a preset theme information base; wherein the number of initial theme feature information includes a plurality; calculating the appointed communication theme, the seat portrait, the user portrait and the initial theme feature information based on a preset double-tower model, and determining target theme feature information from all the initial theme feature information; further acquiring a target conversation corresponding to the target theme feature information; and finally, pushing the target theme characteristic information and the target conversation to the target seat. In the process of carrying out business communication operation between the target agent and the target user, after the current appointed communication theme of the target agent and the target user is obtained, the agent portrait of the target agent, the user portrait of the target user, the historical communication time sequence characteristic information corresponding to the target user and the initial theme characteristic information to be recommended are subjected to calculation processing through the use of a preset double-tower model, the appointed communication theme, the agent portrait, the user portrait and the initial theme characteristic information can be used for rapidly and accurately determining the target theme characteristic information from all the initial theme characteristic information, and the accuracy of the generated target theme characteristic information is ensured. And the target conversation corresponding to the target theme feature information is obtained, and the target theme feature information and the target conversation are pushed to the target seat, and the target conversation is the conversation which is determined according to the target theme feature information and is matched with the target theme feature information, so that the recommendation accuracy of the target conversation is effectively ensured, the follow-up target seat is facilitated to communicate with a target user through the use of the target conversation, and the communication efficiency of business communication is improved.

Drawings

For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow chart of one embodiment of an artificial intelligence based information recommendation method according to the present application;

FIG. 3 is a schematic diagram of one embodiment of an artificial intelligence based information recommendation device according to the present application;

FIG. 4 is a schematic structural diagram of one embodiment of a computer device according to the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.

It should be noted that, the information recommending method based on artificial intelligence provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, the information recommending apparatus based on artificial intelligence is generally disposed in the server/terminal device.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow chart of one embodiment of an artificial intelligence based information recommendation method according to the present application is shown. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs. The information recommendation method based on the artificial intelligence can be applied to any scene where communication topic recommendation and conversation recommendation are required, and can be applied to products of the scenes, for example, communication topic recommendation and conversation recommendation in the field of financial insurance. The information recommendation method based on artificial intelligence comprises the following steps:

Step S201, in the process of performing a business communication operation between a target agent and a target user, acquiring a current specified communication theme between the target agent and the target user.

In this embodiment, the electronic device (for example, the server/terminal device shown in fig. 1) on which the information recommendation method based on artificial intelligence operates may acquire the specified communication theme through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection. In the communication operation scene of the insurance claim service, the service communication operation may include vehicle insurance service communication operation, life insurance service communication operation, accident insurance service communication operation, and the like. The specified communication theme refers to the content of the communication between the agent and the client, for example, the user can enter a quotation link after confirming the purchase intention, and the quotation link becomes the current communication theme. Illustratively, the communication topics may also include topics for confirming claims service appeal, purchase intent, introduction of product highlights, product price ratios, and confirmation of customer information of the customer.

Step S202, acquiring the seat portrait of the target seat and acquiring the user portrait of the target user.

In this embodiment, an image database storing image data is constructed in advance. The agent image of the target agent corresponding to the agent information can be acquired from the image database by acquiring the agent information of the target agent. And obtaining user information of the target user to obtain a user portrait of the target user from the portrait database. Wherein, the portrait of the seat at least comprises the data of the grade, region, sex, etc. of the seat. The representation of the user may include at least data of the user's gender, age, communication focus, financial level, etc.

Step S203, obtaining historical communication time sequence characteristic information corresponding to the target user; the historical communication time sequence characteristic information at least comprises a historical theme and a historical intention.

In this embodiment, the above specific implementation process of obtaining the historical communication timing characteristic information corresponding to the target user will be described in further detail in the following specific embodiments, which will not be described herein.

Step S204, obtaining initial theme feature information to be recommended from a preset theme information base; wherein the number of initial theme feature information includes a plurality.

In this embodiment, the specific implementation process of acquiring the initial theme feature information to be recommended from the preset theme information base is described in further detail in the following specific embodiments, which will not be described herein.

Step S205, calculating the specified communication theme, the seat portrait, the user portrait and the initial theme feature information based on a preset double-tower model, and determining target theme feature information from all the initial theme feature information.

In this embodiment, the above-mentioned dual-tower model is a model constructed based on the structures of the user-side tower model, and the interoperation layer, and the information recommendation function is implemented by dividing the model into two parts, namely the user-side tower model and the object-side tower model, and then combining the two parts by using the interoperation layer to generate the final prediction score. The specific implementation process of the target topic feature information is determined from all the initial topic feature information by performing calculation processing on the specified communication topic, the seat portrait, the user portrait and the initial topic feature information based on the preset double-tower model, and further details of the specific implementation process will be described in the following specific embodiments, which are not described herein.

Step S206, obtaining the target speech corresponding to the target theme feature information.

In this embodiment, the above specific implementation process of obtaining the target session corresponding to the target theme feature information will be described in further detail in the following specific embodiments, which will not be described herein.

Step S207, pushing the target theme feature information and the target conversation to the target seat.

In this embodiment, the communication information of the working terminal of the target seat may be obtained, and then the target theme feature information and the target conversation may be pushed to the working interface in the working terminal of the target seat based on the communication information.

In the process of carrying out business communication operation between a target agent and a target user, firstly, acquiring a current appointed communication theme of the target agent and the target user; then, acquiring an agent portrait of the target agent and a user portrait of the target user; later, acquiring historical communication time sequence characteristic information corresponding to the target user; acquiring initial theme characteristic information to be recommended from a preset theme information base; wherein the number of initial theme feature information includes a plurality; calculating the appointed communication theme, the seat portrait, the user portrait and the initial theme feature information based on a preset double-tower model, and determining target theme feature information from all the initial theme feature information; further acquiring a target conversation corresponding to the target theme feature information; and finally, pushing the target theme characteristic information and the target conversation to the target seat. In the process of carrying out business communication operation between the target agent and the target user, after the current appointed communication theme of the target agent and the target user is obtained, the agent portrait of the target agent, the user portrait of the target user, the historical communication time sequence characteristic information corresponding to the target user and the initial theme characteristic information to be recommended are subjected to calculation processing through the use of a preset double-tower model, the appointed communication theme, the agent portrait, the user portrait and the initial theme characteristic information can be used for rapidly and accurately determining the target theme characteristic information from all the initial theme characteristic information, and the accuracy of the generated target theme characteristic information is ensured. And the target conversation corresponding to the target theme feature information is obtained, and the target theme feature information and the target conversation are pushed to the target seat, and the target conversation is the conversation which is determined according to the target theme feature information and is matched with the target theme feature information, so that the recommendation accuracy of the target conversation is effectively ensured, the follow-up target seat is facilitated to communicate with a target user through the use of the target conversation, and the communication efficiency of business communication is improved.

In some alternative implementations, step S205 includes the steps of:

inputting the appointed communication theme, the agent portrait and the user portrait into a user side tower model in the double tower model, and extracting vectors of the appointed communication theme, the agent portrait and the user portrait through the user side tower model to obtain corresponding first feature vectors.

In this embodiment, the User side tower model specifically refers to a left User tower in the double tower model, and the first feature vector is obtained by using the left User tower to perform vector extraction on the specified communication theme, the seat portrait and the User portrait to output User Embedding.

Inputting the initial theme feature information into an object side tower model in the double tower model, and extracting vectors of the initial theme feature information through the object side tower model to obtain a plurality of corresponding second feature vectors.

In this embodiment, the object side tower model specifically refers to a right side Item tower in the double tower model, and the plurality of second feature vectors are obtained by performing vector extraction on each piece of initial subject feature information by using the side Item tower to output Item enhancement.

And calculating the similarity between the first feature vector and each second feature vector through an interoperation layer in the double-tower model.

In this embodiment, the similarity between the first feature vector and the second feature vectors may be calculated by using them as inputs to the interoperability layer in the double-tower model. The foregoing specific implementation process of calculating the similarity between the first feature vector and each of the second feature vectors through the interoperation layer in the dual-tower model will be described in further detail in the following specific embodiments, which will not be described herein.

In this embodiment, the specific implementation process of determining the target theme feature information from all the initial theme feature information based on the similarity is described in further detail in the following specific embodiments, which will not be described herein.

The appointed communication theme, the agent portrait and the user portrait are input into a user side tower model in the double tower model, and vector extraction is carried out on the appointed communication theme, the agent portrait and the user portrait through the user side tower model, so that a corresponding first feature vector is obtained; inputting the initial theme feature information into an object side tower model in the double tower model, and extracting vectors of the initial theme feature information through the object side tower model to obtain a plurality of corresponding second feature vectors; then calculating the similarity between the first feature vector and each second feature vector through an interoperation layer in the double-tower model; and determining target theme characteristic information from all the initial theme characteristic information based on the similarity. According to the method and the device, the specified communication theme, the seat portrait, the user portrait and the initial theme feature information are calculated by using the double-tower model, so that the target theme feature information can be rapidly and accurately determined from all the initial theme feature information, the generation efficiency of the target theme feature information is improved, and the accuracy of the generated target theme feature information is ensured.

In some optional implementations of the present embodiment, the calculating, by the interoperability layer in the dual-tower model, a similarity between the first feature vector and each of the second feature vectors includes the steps of:

and obtaining a preset similarity calculation strategy.

In this embodiment, the similarity calculation strategies include dot product operation, similarity calculation of Cosine, MLP structure, and the like.

And determining a target similarity calculation strategy from all the similarity calculation strategies.

In this embodiment, the determination manner of the target similarity calculation policy is not specifically limited, and may be set according to actual use requirements. Specifically, the present invention relates to a method for manufacturing a semiconductor device. The similarity calculation strategy with highest processing efficiency can be selected from all similarity calculation strategies by acquiring the processing efficiency of various similarity calculation strategies, so as to be used as a target similarity calculation strategy.

In this embodiment, the target similarity calculation strategy may be used to calculate the similarity between the first feature vector and each of the second feature vectors through the interoperation layer in the dual-tower model, so as to improve the calculation efficiency of the similarity and improve the obtaining rate of the similarity.

The method comprises the steps of obtaining a preset similarity calculation strategy; then determining a target similarity calculation strategy from all the similarity calculation strategies; and calculating the similarity between the first feature vector and each second feature vector through an interoperation layer in the double-tower model based on the target similarity calculation strategy. According to the method and the device, the target similarity calculation strategy is determined from the obtained similarity calculation strategy, and then the target similarity calculation strategy is used, so that the similarity between the first feature vector and each second feature vector is calculated through the interoperation layer in the double-tower model, the calculation processing of the similarity between the first feature vector and each second feature vector is completed rapidly, the obtaining rate of the similarity is improved, and the calculation intelligence of the similarity is improved.

In some optional implementations, the determining, based on the similarity, target theme feature information from all the initial theme feature information includes the steps of:

and comparing the values of all the similarities, and screening the designated similarity with the highest value from all the similarities.

In the present embodiment, the number of the above specified similarities may include one or more.

And acquiring a third feature vector corresponding to the specified similarity from all the second feature vectors.

In the present embodiment, a third feature vector corresponding to the specified similarity may be acquired from all the second feature vectors based on the correspondence between feature vectors and similarities. The number of third feature vectors may include one or more.

And acquiring appointed initial theme characteristic information corresponding to the third characteristic vector from all the initial theme characteristic information.

In this embodiment, after the third feature vector is determined, the theme feature information corresponding to the third feature vector may be obtained from all the initial theme feature information, so as to obtain the above-specified initial theme feature information.

The method comprises the steps of comparing all the similarity values, and screening out the designated similarity with the highest value from all the similarity values; then, a third feature vector corresponding to the appointed similarity is obtained from all the second feature vectors; and acquiring appointed initial theme characteristic information corresponding to the third characteristic vector from all the initial theme characteristic information, and taking the appointed initial theme characteristic information as the target theme characteristic information. According to the method, the third feature vector corresponding to the appointed similarity with the highest value in all the similarities is obtained from all the second feature vectors, and then the appointed initial topic feature information corresponding to the third feature vector is obtained from all the initial topic feature information to serve as final target topic feature information. The topic feature information corresponding to the third feature vector with the highest numerical value and the designated similarity is used as the target topic feature information, so that the obtained target topic feature information is the topic most suitable for the current context, and the accuracy of the generated target topic feature information is ensured.

In some alternative implementations, step S206 includes the steps of:

and calling a preset conversation library.

In this embodiment, the conversation library is a database that is pre-built according to the actual seat service communication record and stores conversation technologies applicable to various conversation topics.

And extracting a first conversation corresponding to the target theme characteristic information from the conversation library.

In this embodiment, a target dialogue topic matched with the target topic feature information may be queried from a dialogue library, and then a dialogue corresponding to the target dialogue topic may be extracted from the dialogue library, so as to obtain a first dialogue corresponding to the target topic feature information.

And obtaining the communication success rate of each first conversation.

In this embodiment, the communication success rate of each first session may be extracted by obtaining the communication statistics of all the first sessions and extracting information from the communication statistics.

And screening out second dialects with communication success rate larger than a preset success rate threshold from all the first dialects.

In this embodiment, the value of the success rate threshold is not specifically limited, and may be set according to actual use requirements.

And taking the second phone as the target phone.

The method comprises the steps of calling a preset conversation library; then extracting a first conversation corresponding to the target theme feature information from the conversation library; then, the communication success rate of each first conversation is obtained; and screening second dialects with communication success rate larger than a preset success rate threshold from all the first dialects, and taking the second dialects as the target dialects. According to the method and the device, the first telephone corresponding to the target theme characteristic information is extracted through the use of the telephone library, and then the second telephone with the communication success rate larger than the preset success rate threshold is intelligently screened out of all the first telephone to be used as the target telephone. Because the generated target conversation is the conversation with a larger communication success rate, the recommendation accuracy of the conversation is improved, and the follow-up target seat can use the target conversation to carry out service communication with the target user, so that the success rate of service achievement is effectively improved.

In some alternative implementations of the present embodiment, step S203 includes the steps of:

calling a preset communication information database.

In this embodiment, the communication information database is a database that is built in advance and stores call information generated in the process of performing communication operation with the user by the agent, and communication information matched with the call information. Typically, a communication workflow will include multiple rounds of business communication. The communication information at least comprises a communication theme and a user intention. For example, in the context of a communication operation of a insurance claim service, the communication theme may include a theme of confirming claim service appeal, purchase intention, introduction of a product highlight, product price ratio, and confirmation of customer information of a customer. User intent refers to an objection point of interest to the user in communicating with the agent, e.g., user intent may include price issues, intent to compare to other companies, etc.

And acquiring target user information of the target user.

In this embodiment, the target user information is identity information of the target user, for example, a name of the target user.

And acquiring associated call information corresponding to the business communication operation based on the target user information.

In this embodiment, the related call information is call information of the target user related to the service communication operation. For example, a communication workflow may include multiple rounds of communication, and associated call information may refer to previous rounds of calls associated with the communication workflow, such as multiple call information that may occur a few days or 10 days ago, etc.

And screening the appointed communication information corresponding to the associated communication information from the communication information database.

In this embodiment, the related call information is used to query a communication information database, so as to screen the designated communication information corresponding to the related call information from the communication information database. The communication information is designated as a communication theme and a user intention corresponding to the associated communication information.

The method and the device call a preset communication information database; then obtaining target user information of the target user; then, based on the target user information, acquiring associated call information corresponding to the service communication operation; and then screening appointed communication information corresponding to the related communication information from the communication information database, and taking the appointed communication information as the historical communication time sequence characteristic information. According to the method and the device, the target user information of the target user is used for inquiring the communication information database to acquire the associated communication information corresponding to the business communication operation, and further the appointed communication information corresponding to the associated communication information is screened out from the communication information database to quickly and accurately acquire the historical communication time sequence characteristic information, so that the acquisition efficiency of the historical communication time sequence characteristic information is improved, and the accuracy of the acquired historical communication time sequence characteristic information is ensured.

In some alternative implementations of the present embodiment, step S204 includes the steps of:

and calling the theme information base.

In this embodiment, the topic information base is a database that is constructed according to the actual dialog topic collection requirement and stores a plurality of job types and topic feature information corresponding to each job type.

And acquiring the appointed operation type of the service communication operation.

In this embodiment, the specified operation type of the service communication operation may be obtained by performing keyword analysis on the service communication operation. In the business scenario of the insurance business communication operation, the operation type may include a car insurance claim operation, an life insurance claim operation, a personal insurance claim operation, and so on.

And screening out the specified topic feature information corresponding to the specified job type from the topic information base.

In this embodiment, the information query may be performed on the topic information base by using the specified job type, so as to query the topic information base for specified topic feature information corresponding to the specified job type.

The application calls the theme information base; then obtaining the appointed operation type of the business communication operation; and screening out the appointed theme characteristic information corresponding to the appointed job type from the theme information base, and taking the appointed theme characteristic information as the initial theme characteristic information. According to the method and the device, the appointed operation type of the service communication operation is obtained, and further the appointed theme characteristic information corresponding to the appointed operation type is screened out from the theme information base and used as the initial theme characteristic information based on the use of the theme information base, so that the initial theme characteristic information is obtained rapidly and accurately, the obtaining efficiency of the initial theme characteristic information is improved, and the accuracy of the obtained initial theme characteristic information is guaranteed.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.

It is emphasized that to further guarantee the privacy and security of the target session, the target session may also be stored in a blockchain node.

The blockchain referred to in the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 3, as an implementation of the method shown in fig. 2, the application provides an embodiment of an information recommendation device based on artificial intelligence, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device is specifically applicable to various electronic devices.

As shown in fig. 3, the information recommendation device 300 based on artificial intelligence according to the present embodiment includes: a first acquisition module 301, a second acquisition module 302, a third acquisition module 303, a fourth acquisition module 304, a determination module 305, a fifth acquisition module 306, and a push module 307. Wherein:

the first obtaining module 301 is configured to obtain a current specified communication theme of the target agent and the target user during a business communication operation between the target agent and the target user;

a second obtaining module 302, configured to obtain an agent portrait of the target agent, and obtain a user portrait of the target user;

a third obtaining module 303, configured to obtain historical communication timing characteristic information corresponding to the target user; the historical communication time sequence characteristic information at least comprises a historical theme and a historical intention;

a fourth obtaining module 304, configured to obtain initial topic feature information to be recommended from a preset topic information base; wherein the number of initial theme feature information includes a plurality;

The determining module 305 is configured to perform calculation processing on the specified communication topic, the agent portrait, the user portrait, and the initial topic feature information based on a preset double-tower model, and determine target topic feature information from all the initial topic feature information;

a fifth obtaining module 306, configured to obtain a target conversation corresponding to the target theme feature information;

and the pushing module 307 is configured to push the target theme feature information and the target conversation to the target agent.

In this embodiment, the operations performed by the modules or units respectively correspond to the steps of the information recommendation method based on artificial intelligence in the foregoing embodiment one by one, which is not described herein again.

In some alternative implementations of the present embodiment, the determining module 305 includes:

the first extraction submodule is used for inputting the appointed communication theme, the agent portrait and the user portrait into a user side tower model in the double tower model, and extracting vectors of the appointed communication theme, the agent portrait and the user portrait through the user side tower model to obtain corresponding first feature vectors;

The second extraction submodule is used for inputting the initial theme feature information into an article side tower model in the double tower model, and extracting vectors of the initial theme feature information through the article side tower model to obtain a plurality of corresponding second feature vectors;

a computing sub-module for computing a similarity between the first feature vector and each of the second feature vectors through an interoperability layer in the dual-tower model;

and the first determining submodule is used for determining target theme characteristic information from all the initial theme characteristic information based on the similarity.

In some optional implementations of the present embodiment, the computing submodule includes:

the first acquisition unit is used for acquiring a preset similarity calculation strategy;

the first determining unit is used for determining a target similarity calculation strategy from all the similarity calculation strategies;

and the calculating unit is used for calculating the similarity between the first feature vector and each second feature vector through an interoperation layer in the double-tower model based on the target similarity calculation strategy.

In some optional implementations of this embodiment, the first determining submodule includes:

the comparison unit is used for carrying out numerical comparison on all the similarities and screening out the designated similarity with the highest numerical value from all the similarities;

a second obtaining unit, configured to obtain a third feature vector corresponding to the specified similarity from all the second feature vectors;

a third obtaining unit, configured to obtain specified initial topic feature information corresponding to the third feature vector from all the initial topic feature information;

and the second determining unit is used for taking the appointed initial theme characteristic information as the target theme characteristic information.

In some optional implementations of this embodiment, the fifth acquisition module 306 includes:

The first calling sub-module is used for calling a preset speaking library;

the third extraction sub-module is used for extracting a first conversation corresponding to the target theme characteristic information from the conversation library;

the first acquisition sub-module is used for acquiring the communication success rate of each first conversation;

the first screening submodule is used for screening second dialects with communication success rate greater than a preset success rate threshold from all the first dialects;

and the second determining submodule is used for taking the second phone as the target phone.

In some optional implementations of this embodiment, the third obtaining module 303 includes:

the second calling sub-module is used for calling a preset communication information database;

the second acquisition sub-module is used for acquiring the target user information of the target user;

a third obtaining sub-module, configured to obtain, based on the target user information, associated call information corresponding to the service communication operation;

the second screening sub-module is used for screening appointed communication information corresponding to the associated communication information from the communication information database;

And the third determining submodule is used for taking the appointed communication information as the historical communication time sequence characteristic information.

In some optional implementations of this embodiment, the fourth acquisition module 304 includes:

the third calling sub-module is used for calling the theme information base;

a fourth obtaining sub-module, configured to obtain a specified job type of the service communication job;

the third screening sub-module is used for screening out the appointed theme characteristic information corresponding to the appointed operation type from the theme information base;

and a fourth determining sub-module, configured to take the specified theme feature information as the initial theme feature information.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It should be noted that only computer device 4 having components 41-43 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used to store an operating system and various application software installed on the computer device 4, such as computer readable instructions of an information recommendation method based on artificial intelligence. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.

The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as executing computer readable instructions of the information recommendation method based on artificial intelligence.

The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.

in the embodiment of the application, in the process of carrying out business communication operation between a target agent and a target user, after the current appointed communication theme of the target agent and the target user is obtained, the agent portrait of the target agent, the user portrait of the target user, the historical communication time sequence characteristic information corresponding to the target user and the initial theme characteristic information to be recommended are calculated and processed through the use of a preset double-tower model, the appointed communication theme, the agent portrait, the user portrait and the initial theme characteristic information can be quickly and accurately determined from all the initial theme characteristic information, and the accuracy of the generated target theme characteristic information is ensured. And the target conversation corresponding to the target theme feature information is obtained, and the target theme feature information and the target conversation are pushed to the target seat, and the target conversation is the conversation which is determined according to the target theme feature information and is matched with the target theme feature information, so that the recommendation accuracy of the target conversation is effectively ensured, the follow-up target seat is facilitated to communicate with a target user through the use of the target conversation, and the communication efficiency of business communication is improved.

The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the artificial intelligence based information recommendation method as described above.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present application.

It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the protection scope of the application.

Claims

1. An information recommendation method based on artificial intelligence is characterized by comprising the following steps:

2. The method for recommending information based on artificial intelligence according to claim 1, wherein the step of computing the specified communication topic, the agent portrait, the user portrait, and the initial topic feature information based on a preset double-tower model, and determining target topic feature information from all the initial topic feature information comprises the following steps:

3. The method for recommending information based on artificial intelligence according to claim 2, wherein the step of calculating the similarity between the first feature vector and each of the second feature vectors through an interoperability layer in the dual tower model specifically comprises:

obtaining a preset similarity calculation strategy;

4. The method for recommending information based on artificial intelligence according to claim 2, wherein the step of determining target topic feature information from all the initial topic feature information based on the similarity comprises the following steps:

5. The method for recommending information based on artificial intelligence according to claim 1, wherein the step of acquiring the target session corresponding to the target subject feature information comprises the following steps:

calling a preset speaking library;

Acquiring the communication success rate of each first conversation;

and taking the second phone as the target phone.

6. The method for recommending information based on artificial intelligence according to claim 1, wherein the step of acquiring the historical communication timing characteristic information corresponding to the target user comprises:

calling a preset communication information database;

acquiring target user information of the target user;

7. The method for recommending information based on artificial intelligence according to claim 1, wherein the step of acquiring the initial topic feature information to be recommended from a preset topic information base specifically comprises:

invoking the theme information base;

acquiring a designated job type of the service communication job;

8. An artificial intelligence based information recommendation device, comprising:

9. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the artificial intelligence based information recommendation method of any of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the artificial intelligence based information recommendation method according to any of claims 1 to 7.