CN114936870A

CN114936870A - Smart interaction method, device, equipment, storage medium and computer program product

Info

Publication number: CN114936870A
Application number: CN202210367613.3A
Authority: CN
Inventors: 崔庆文; 邓杨; 黄斌; 蒋炜
Original assignee: CCB Finetech Co Ltd
Current assignee: CCB Finetech Co Ltd
Priority date: 2022-04-08
Filing date: 2022-04-08
Publication date: 2022-08-23

Abstract

The invention discloses an intelligent interaction method, device, equipment, storage medium and computer program product, and relates to the technical field of cloud computing security service. The method comprises the following steps: acquiring first interactive information input by a user, matching consulted personnel according to the first interactive information, and starting video service with the consulted personnel; acquiring second interactive information input by a user in a video process with consulted personnel, and sending the second interactive information to a cloud computing service center; and receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information, and outputting the first product recommendation information. According to the technical scheme, the first product recommendation information can be fed back to the user according to the second interaction information input by the user in the user service process, so that the effects of improving the service efficiency and the service accuracy and improving the user experience are achieved.

Description

Smart interaction method, device, equipment, storage medium and computer program product

Technical Field

The embodiment of the invention relates to the technical field of cloud computing security services, in particular to an intelligent interaction method, device, equipment, storage medium and computer program product.

Background

With rapid development of new technologies represented by big data, cloud computing, artificial intelligence and the like, new financial modes are fortunately coming, and financial industry business modes are also changing deeply.

In the past operation process, the operation mode of taking the network point as the center and the core channel, and taking the network point as the core, is the core channel for the customers to obtain bank products and services.

The current overall trend is: the network point service migrates simple services such as accounting transaction and the like to the online, and most of the services reserved at the network point are complex services.

How to improve the handling efficiency of complex services and further improve the operation efficiency of a network point as a whole is a problem to be solved urgently at present.

Disclosure of Invention

The embodiment of the invention provides an intelligent interaction method, an intelligent interaction device, intelligent interaction equipment, a storage medium and a computer program product, so that the service efficiency and the service accuracy are improved, and the user experience is improved.

In a first aspect, an embodiment of the present invention provides an intelligent interaction method, including:

acquiring first interactive information input by a user, matching consulted personnel according to the first interactive information, and starting video service with the consulted personnel;

acquiring second interactive information input by the user in the video process of the consulted person, and sending the second interactive information to a cloud computing service center;

and receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information, and outputting the first product recommendation information.

In a second aspect, an embodiment of the present invention provides an intelligent interaction device, including:

the system comprises a first interactive information acquisition module, a second interactive information acquisition module and a video service starting module, wherein the first interactive information acquisition module is used for acquiring first interactive information input by a user, matching consulted personnel according to the first interactive information and starting video service with the consulted personnel;

the second interactive information acquisition module is used for acquiring second interactive information input by the user in the video process of the consulted person and sending the second interactive information to the cloud computing service center;

and the first product recommendation information output module is used for receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information and outputting the first product recommendation information.

In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the intelligent interaction method according to any one of the embodiments of the present invention.

In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the intelligent interaction method according to any one of the embodiments of the present invention.

In a fifth aspect, the present invention further provides a computer program product, including a computer program, which when executed by a processor implements the intelligent interaction method according to any one of the embodiments of the present invention.

In the intelligent interaction scheme provided by the embodiment of the invention, first interaction information input by a user is obtained, consulted personnel is matched according to the first interaction information, and video service with the consulted personnel is started; then second interactive information input by the user in the video process of the consulted person is obtained, and the second interactive information is sent to the cloud computing service center; and finally, receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information, and outputting the first product recommendation information. According to the technical scheme, the first product recommendation information can be fed back to the user according to the second interaction information input by the user in the user service process, so that the effects of improving the service efficiency and the service accuracy and improving the user experience are achieved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts;

fig. 1 is a flowchart of an intelligent interaction method according to an embodiment of the present invention;

fig. 2 is a flowchart of an intelligent interaction method according to a second embodiment of the present invention;

fig. 3 is a diagram of an intelligent interaction service architecture based on an internet of things visual federal learning model according to a second embodiment of the present invention;

fig. 4 is a diagram of an intelligent interactive learning framework according to a second embodiment of the present invention;

FIG. 5 is a flowchart illustrating another intelligent interaction method according to a second embodiment of the present invention;

fig. 6 is a schematic structural diagram of an intelligent interaction device according to a third embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It should be further noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings, not all of them.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance. According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.

Example one

Fig. 1 is a flowchart of an intelligent interaction method according to an embodiment of the present invention, where the embodiment is suitable for improving service efficiency and service accuracy and enhancing user experience.

As shown in fig. 1, the method specifically includes the following steps:

s110, acquiring first interactive information input by a user, matching the consulted person according to the first interactive information, and starting video service of the consulted person.

The first interactive information may be understood as information initially input by the user on the smart service device after entering the banking outlet. The current first interaction information can be input in the following ways:

1) the user manually inputs the related consultation questions on the intelligent service equipment. For example, deposit xxx yuan, which deposit method has the highest profitability; deposit xxx yuan, which deposit mode has the lowest risk; the deposit mode with the highest cost performance (low risk rate and high return rate) is recommended, and the like. When the user inputs a question on the smart service device manually or by voice, the user may handle questions for other businesses, such as a xxx handling process, materials needed for handling xxx businesses, and the like, without being limited to the above listed financial problems.

2) The user manually inputs the question keyword information on the intelligent service equipment. The keyword information may be: financing, investment, security or loan, etc.

3) The user manually selects the type of service on the intelligent service device, for example: financial, investment, warranty, or loan transactions, etc.

It should be noted that, when inputting question keyword information on the intelligent service device in the above manner 2), one keyword information may be input, or several keyword information may be simultaneously input in an "or" and "relationship, so as to generate the first interaction information.

Optionally, when inputting question keyword information or selecting a service type on the intelligent service device according to the above mode 2) or mode 3), regarding the current interface as a first display interface; generating a second display interface according to the keyword information of the user input problem or the selected service type, and further inputting detailed interaction information by the user on the second display interface; and then, generating the first interactive information according to the information input by the user on the first display interface and the information input by the user on the second display interface.

The manner of inputting the first interaction information on the smart service device is not limited herein.

The intelligent service equipment can be a self-service robot arranged in a bank outlet, a tablet computer of hall service personnel or other multimedia terminals and the like.

After first interactive information input by a user is received, according to the type of the first interactive information input by the user or the manner of extracting keyword information and the like, the consulted person is matched with the user, and the current consulted person can be a financial expert or a corresponding type of service customer service and the like.

Optionally, before starting the video service of the user and the consultant, the user may be informed on the intelligent service device that the video service (or the intelligent image and video service) needs to be started by using the following contents, where the informed contents may be that text display or voice output is performed on a current page of the intelligent service device "aiming at the input first interaction information, a professional is matched for the user to perform video surface-to-surface consultation, and whether the user agrees to start the video" if the user clicks "yes", the video service with the consultant is started; if the user clicks 'no', the current service is ended, or the user continues to manually input the rest consultation information on the page of the intelligent service equipment.

S120, second interactive information input by the user in the video process of the consulted person is obtained, and the second interactive information is sent to the cloud computing service center.

In the process of the video between the user and the consultant, the consultant can ask questions according to the first interactive information input by the user, such as the amount of investment, the acceptable investment risk level, the expected return rate, whether to manage money for the first time or whether to accept high-risk investment, and the like. The user can reply again according to the questions proposed by the consultant, and the currently replied content is second interactive information.

When the second interactive information is input, the mode that the user manually inputs or selects the second interactive information on the intelligent service equipment according to the related questions consulted by the consultant can be adopted, and the mode that the user carries out semantic recognition on the questions answered by the consultant in a voice mode and the second interactive information is automatically extracted can be adopted. The specific manner of inputting the second interactive information is not limited herein.

The second interaction information can enable consultants to make the requirements of the users more clear, and the follow-up cloud computing service center can conveniently recommend more accurate products to the users.

The cloud computing service center is a computer program product which has a data processing function and can perform a product recommendation function according to the second interaction information, and the current computer program product can be understood as a computer program and is realized by corresponding computer code programming.

S130, receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information, and outputting the first product recommendation information.

The cloud computing service center contains the trained personalized recommendation model, and after the cloud computing service center receives the second interaction information, the personalized recommendation model can combine with the user historical behavior data to accurately output the first product recommendation information for the user.

The current first product recommendation information is determined by the cloud computing service center based on the second interaction information, the attribute information of the user and a pre-trained personalized recommendation model, and the personalized recommendation model is pre-trained based on the historical behavior information of the user for the bank product and the user attribute information. The method has the advantages that the personalized recommendation is carried out for the user based on the trained personalized recommendation model, and the recommendation accuracy can be improved.

The attribute information comprises interest labels and user feature vectors; the way of outputting the first product recommendation information for the user using the personalized recommendation model may be: the cloud computing service center firstly analyzes historical behavior information of a user, and the current historical behavior information can be as follows: the times of purchasing the financial products, the yield of each financial product, the historical assets of the user and other information; then obtaining the attribute information of the user, wherein the obtaining mode of the attribute information can adopt a networking mode to obtain the characteristic information of the user under the condition of user agreement, and the characteristic information comprises: a user representation generated in the database for a user from a user tag stored in a multidimensional manner; and finally, outputting the first product recommendation information for the user according to the personalized recommendation model by combining the received second interaction information.

The first product recommendation information is not limited by recommending a specific product, the output result of the personalized recommendation model can also be a product label set which is interested by the user and a list associated with the product, and information such as the relevance, recommendation rate and the like estimated by the cloud computing service center can be output together in the current product label set or the list associated with the product for the user to refer to.

The interest label is determined based on a preference model trained in advance, and the preference model is trained in advance based on historical behavior information and/or investigation information of a user for bank products; the user feature vector is determined based on a pre-trained user portrait model; the user portrait model is trained in advance based on user characteristic information.

Specifically, the personalized recommendation model is a product which is recommended to the client according to the historical behavior data and the client attribute data of each client and is likely to be interested, so that the product click rate of the client is increased, the personalized experience of the client is improved, and the client viscosity is increased. When the personalized recommendation model is used, the following process can be used for realizing the following steps:

extracting the interaction behaviors of the customers and the products and a clustering model formed by the clustering relation formed by the association relation of the products to form a product clustering set in which each customer is interested, and marking an interest label for the current product clustering set; analyzing the interaction behavior of the user and the product to form a preference model; matching products as targets of recommendation models according to interest tags and recent behaviors of users (for example, feature models are derived from structured data (relevant information of customers) and unstructured data (natural language processing)).

In training a user profile model: the long-term customer portrait and the short-term customer portrait of the user can be simultaneously calculated through the user characteristic information, the attenuation attribute of the user interest needs to be considered in the calculation process, and the interest of the user can be explored and guided in the recommendation process. Therefore, the personalized recommendation model of the user is trained based on the user portrait model and the preference model.

Furthermore, after the first product recommendation information is output, satisfaction survey can be conducted on the user, and the purpose of the satisfaction survey is to enrich the user portrait, update a preference model of the user and base better service in the later period.

The cloud computing service center sends the generated return visit information of the user to a service terminal of a website or a community bank, and the service terminal sends the return visit response information input by the user to the cloud computing service center; the cloud computing service center forms a user satisfaction survey model according to the return visit response information, the relevant model is used as a supplement of the user portrait and a recommendation algorithm to analyze the user satisfaction survey information, and the user portrait is supplemented and perfected according to the user requirements in a targeted mode. And iteratively optimizing a user preference model and the like according to the return visit of the product and the service information. The method has the advantages that timely experiential service is provided for the user, and finally a new personalized recommendation algorithm model is formed.

The intelligent interaction method provided by the embodiment of the invention comprises the steps of firstly obtaining first interaction information input by a user, matching consulted personnel according to the first interaction information, and starting video service with the consulted personnel; then second interactive information input by the user in the video process of the consulted person is obtained, and the second interactive information is sent to the cloud computing service center; and finally, receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information, and outputting the first product recommendation information. According to the technical scheme, in the process of serving the user, the first product recommendation information can be fed back to the user according to the second interaction information input by the user, so that the effects of improving the service efficiency and the service accuracy and improving the user experience are achieved.

Example two

Referring to fig. 2 to 4, fig. 2 is a flowchart of a smart interaction method according to a second embodiment of the present invention, and fig. 3 is a smart interaction service architecture diagram based on a visual federal learning model of the internet of things according to the second embodiment of the present invention; fig. 4 is a diagram of an intelligent interactive learning framework according to a second embodiment of the present invention.

The present embodiment refines the steps before acquiring the first interactive information input by the user based on the above-mentioned embodiments. The intelligent interaction method provided by the embodiment further includes, before acquiring the first interaction information input by the user: and when the vehicle of the user arrives according to the image acquired by the visual equipment, triggering the cloud computing service center to carry out parking space scheduling on the user.

When the user is driving, the bank outlets handle the outlet services, the visual devices arranged around the bank outlets can determine whether the user arrives at the outlets or not by acquiring the image information of the vehicle, and when the user vehicle arrives, the cloud computing service center can be triggered to carry out parking space scheduling on the user, so that the user can be helped to find an empty parking space, and the user can conveniently park.

Optionally, the mode of determining that the vehicle of the user arrives according to the image acquired by the visual device may be that, before the user goes to a bank website to transact the website service, a service transaction reservation can be made on a bank webpage in advance, and vehicle information, such as a vehicle model, a vehicle identifier, a vehicle color, a license plate number and the like, can be input during the reservation, so that the visual acquisition device can conveniently identify the vehicle of the user.

Specifically, as shown in fig. 2, the method of this embodiment specifically includes the following steps:

s210, receiving reservation information of the user to the website service, which is sent by the cloud computing service center.

Before the user enters the bank network, the user can reserve the network business to be transacted or consulted on the terminal equipment in advance through the super channel to generate reservation information.

Optionally, the reservation information is acquired by the cloud computing service center through a super channel, and the super channel includes a community bank, a mobile phone bank, an internet bank, a telephone bank, or a wechat bank.

Wherein, the reservation information may include: the system comprises the reservation time, a user starting address, a reserved target network point address, a service type and a travel mode. If for the self-driving trip, can also include: vehicle model, license plate number and the like.

When the reservation information of the user for the website service, which is sent by the computing service center, is received, a travel route can be generated according to the reservation information, and the travel route is recommended to the terminal equipment of the user.

If the user selects the non-self-driving trip, the trip distance can be obtained according to the user starting address and the reserved target site address, if the trip distance is smaller than the preset distance, walking is recommended for the user, and the navigation information is sent to the terminal equipment of the user.

And if the travel distance is not less than the preset distance, recommending an optimal route for the user according to the travel distance, wherein the current route comprises a transit route of a bus line and/or a subway, and sending the current route to the terminal equipment of the user.

If the user selects the self-driving trip, recommending trip information for the user when the time period reserved by the user is less than the preset time (such as 3 hours), wherein the current trip information comprises: travel routes and travel road condition information. And the travel information and the reservation information of the user are sent to the visual equipment outside the business hall.

S220, vehicle feature recognition is carried out on the image collected by the vision device, and whether the vehicle of the user arrives is determined according to the vehicle feature recognition result and the reservation information.

The visual device can estimate the approximate time range of the user arriving at the bank website according to the travel information, and in the current time range, the visual device extracts the vehicle characteristics based on the images acquired by the visual device and the vehicle information in the reservation information so as to identify the vehicle according to the vehicle characteristic identification result and determine whether the user arrives at the website.

The vehicle feature may be: vehicle identification, vehicle shape, vehicle color, license plate number, and the like.

Alternatively, the vision device may classify the vehicle type of the user according to the vehicle characteristics, and when the vehicle type of the user is determined to be a preset type, the current vehicle type may be supplemented to the user portrait information.

In one embodiment, the method for identifying the vehicle characteristics of the image acquired by the visual device and determining whether the vehicle of the user arrives according to the vehicle characteristic identification result and the reservation information comprises the following steps:

A1) and based on a preset target recognition model, recognizing the license plate characteristics and/or vehicle type characteristics of the image acquired by the current visual equipment.

The preset target recognition model is a model which is trained in advance by adopting a visual federal learning mechanism and is used for target recognition.

The visual federal learning mentioned in the technical scheme provided by the embodiment of the invention is divided into two levels: firstly, a platform with intelligent camera shooting facilities (such as a camera) for recognizing images and videos is used for training a related deep learning algorithm (such as a convolutional neural network algorithm); and secondly, the related algorithm is implanted into the intelligent camera facility in an advancing way by the Internet of things embedded chip technology, and the federal learning technology is adopted to support related application.

The core idea is as follows: and (4) forming a distributed training network for camera data dispersed in various places through federal learning. And under the condition that the data of the camera is not uploaded, cooperatively training a target detection model. On the one hand, the private data of the user are ensured not to be leaked. On the other hand, the training data of all the participants are fully utilized, and the recognition effect of the machine vision model is improved.

When the vehicle characteristic recognition is carried out on the image acquired by the visual equipment, a combination of a networking technology, a deep learning algorithm and a federal learning algorithm is needed, and a license plate recognition algorithm-convolutional neural network algorithm embedded in an embedded chip is combined to generate a preset target recognition model.

The vision federal learning of the bank outlets utilizes the capability support of a vehicle recognition algorithm model which is integrated in the early stage, the vehicle type characteristics are recognized while the license plate is recognized, and the vehicle type recognition is completed according to the external characteristics of the vehicle and the LOGO mark of the vehicle. And identifying the type of the vehicle by using the vehicle characteristic information of the smart city, and preliminarily finishing the mapping relation between the license plate and the vehicle characteristic.

The method comprises the steps that after a preset target recognition model is trained for multiple times in a cloud computing service center, an embedded chip is implanted into a visual learning device, the visual learning device extracts relevant features of a vehicle through federal learning, the relevant features are used as a feature extractor for recognizing vehicle types and vehicle license plate recognition, the feature extractor and a cloud computing platform are integrated to interact with features on line, and therefore the recognition operation of vehicle license plate features and/or vehicle type features is carried out on images collected by the current visual device.

A2) And matching the recognized license plate characteristics and/or vehicle type characteristics with the user vehicle information in the reservation information, and determining that the vehicle of the user arrives if the license plate characteristics and/or the vehicle type characteristics are matched with the user vehicle information in the reservation information.

And when the license plate characteristics and/or the vehicle type characteristics identified by the preset target identification model are consistent with the user vehicle information in the reservation information, determining that the vehicle of the user arrives.

And if the images are inconsistent, executing the step A1), and continuing to recognize the license plate features and/or the vehicle type features of the images acquired by the visual equipment.

And S230, when the vehicle arrives, sending a parking space scheduling request to the cloud computing service center so that the cloud computing service center carries out parking space scheduling and sends a parking space scheduling result to the user.

The visual device outside the business hall identifies the vehicles based on the vehicle information in the received reservation information, when the vehicles of the users arrive, the parking space scheduling request is sent to the cloud computing service center, and the cloud computing service center transmits the parking space information to the terminal devices of the users in real time through the network according to the real-time situation of the parking lot, so that the parking space scheduling and parking services can be automatically completed for the users, and the user experience is improved.

After the user identity is recognized, step S240 is further executed to transact the relevant service for the user.

S240, first interactive information input by a user is obtained.

And S250, sending the first interaction information to a cloud computing service center.

The first interactive information input by a user on the intelligent service equipment is uploaded to the cloud computing service center, and the cloud computing service center identifies the key information of the received first interactive information through semantic identification, keyword extraction and the like.

And S260, receiving second product recommendation information fed back by the cloud computing service center according to the first interaction information, and outputting the second product recommendation information.

And outputting second product recommendation information for the user on the intelligent service equipment according to the key information of the first interaction information and the historical behavior information of the inquiry user.

And S270, acquiring an operation instruction of the user on the second product recommendation information.

The current operating instructions may be to display "satisfied second product recommendation information" on the smart service device; if the user clicks "yes", the current service is ended, and if the user clicks "no", step S280 is performed.

And S280, matching the consulted person according to the first interactive information and starting video service of the consulted person when the operation instruction is a preset instruction.

The current preset instruction can be an instruction of 'no', 'unsatisfied' or're-recommending', and the like clicked by a user on the intelligent service equipment, and when the user is unsatisfied with the second product recommendation information, the consulted person is further matched according to the first interaction information, and video service with the consulted person is started.

And S290, acquiring second interactive information input by the user in the video process of the consulted person, and sending the second interactive information to the cloud computing service center.

And S291, receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information, and outputting the first product recommendation information.

The above steps S280 to S291 are the same as the steps S110 to S130 of the first embodiment of the present invention, and are not described herein again.

After the user transacts the business, the cloud computing service center acquires the home address information of the user according to the reservation information of the user, and acquires the current road condition information by combining the interaction of the smart city center according to the position information of the current service network and the home address information of the user, so as to generate an optimal return route for the user, and sends the current return route to the terminal equipment of the user.

Further, referring to fig. 5, fig. 5 is a flowchart of another intelligent interaction method according to a second embodiment of the present invention, which is a parallel scheme of the first embodiment. As shown in fig. 5, the method of this embodiment specifically includes the following steps:

s310, acquiring third interactive information in a voice form input by a user; and converting the third interactive information into text information based on a preset natural language processing NLP model.

The current third interactive information may be service consultation information or service handling information input by the user in the intelligent service device in a voice input manner.

The user may interact with the intelligent service device (intelligent robot or visual federal device) in the business hall through voice, for example, the third interaction information may be: please recommend several products with higher profitability. The intelligent service device converts the third interactive information in the form of voice input by the user into text by adopting a preset Natural Language Processing (NLP) model, that is, when receiving the voice input by the user, the intelligent service device converts the voice content into text information.

The intelligent service equipment has a primary man-machine interaction function and can carry out targeted question-answering interaction according to a service list provided by a bank outlet. According to the voice interaction information, a preset natural language processing NLP model is introduced, the input is man-machine interaction voice and character content, and the output is a user demand distribution and preference analysis framework and the like. And the requirements of the user can be further mined according to the information communicated with the user, the interest points of the user are preliminarily judged, and a basic information list and range are provided for the subsequent introduction of expert service.

And S320, searching corresponding third product recommendation information in a local knowledge question-answering base according to the text content and the reservation information of the user to the website service.

Taking the third interactive information as the user voice input "please recommend several products with higher profitability" as an example, after the intelligent service device uses the NLP model to perform text recognition, it can be known that the current keywords are "recommended", "high profitability" and "products"; and then, in combination with the reservation information of the user for the website service, for example, if the service type in the reservation information belongs to a financial service, it can be known that the user needs to handle the financial service, and then the third product recommendation information related to the financial service is searched in a local knowledge question and answer library (or a question and answer intelligent device) pre-stored in the intelligent service device.

S330, judging whether the third product recommendation information is found in the local knowledge question-answering base.

If so, executing step S340; if not, go to step S350.

The reason why the third product recommendation information is not found may be that, by extracting keyword information input by the user voice and comparing the keyword information with the reservation information, if it is determined that the user voice is correctly identified, the service that the user consults or needs to deal with is not stored in the local knowledge question-answering library, and the third product recommendation information cannot be found in the local knowledge question-answering library.

And S340, outputting the searched third product recommendation information.

And when the third product recommendation information is found in the local knowledge question-answering base, the found third product recommendation information is displayed through a visual interface line of the intelligent service equipment or is sent to the user in a voice output mode.

And S350, sending a service recommendation request to the cloud computing service center.

When the third product recommendation information is not found in the local knowledge question-answering base, the intelligent service equipment sends the third interaction information serving as a service recommendation request to the cloud computing service center, so that the cloud computing service center carries out service recommendation for the user.

And S360, receiving fourth product recommendation information fed back by the cloud computing service center according to the text content and the reservation information, and outputting the fourth product recommendation information.

And the cloud computing service center feeds back fourth product recommendation information to the intelligent service equipment according to the content in the service recommendation request, namely the text information and the reservation information feedback of the third interactive information, and the intelligent service equipment displays the fourth product recommendation information through a visual interface line of the intelligent service equipment or sends the fourth product recommendation information to the user in a voice output mode.

It should be noted that the manner of determining the fourth product recommendation information by the cloud computing service center is the same as the manner of determining the third product recommendation information by the intelligent service device, and the difference is that the knowledge question-answer library data of the question-answer library of the cloud computing center is more comprehensive.

In an embodiment, the intelligent interaction method provided in the embodiment of the present invention may further include the following steps:

B1) the method comprises the steps of obtaining an extraction key generated for an article to be stored of a user and a recorded biological feature recorded for the user, providing the extraction key for the user, and storing the extraction key and the recorded biological feature.

In the bank outlet service, there may be a business for managing valuables for a user, and in order to ensure effective management of the articles to be kept by the user, an extraction key may be generated when the user stores the articles to be kept, and a biometric characteristic may be recorded for the user under the agreement of the user.

The extraction key can be composed of numbers, upper case letters and lower case letters and special symbols which are randomly generated by the system and contain preset digits so as to be sent to a user for storage, and the cloud computing service center stores the extraction key and the recorded biological characteristics.

Optionally, when the articles to be stored are stored for the user, the electronic tags may also be set for the articles to be stored, the cloud computing service center may synchronize article-related information in the electronic tags sent by the internet of things devices of the network points to the terminal device of the user, and the user may know the storage state of the articles through the electronic tags.

If the article to be stored needs to be transported, the cloud computing service center synchronizes the position information sent by the internet of things equipment on the transport path and the article related information in the electronic tag to the terminal equipment of the user, so that the user can know the transport track of the transported article.

B2) And in response to receiving the article extraction instruction, performing user identity authentication according to the input key of the user, the current biological characteristics of the user, the extraction key and the recorded biological characteristics, and determining whether the user is allowed to extract the article to be kept according to an authentication result.

The input key may be a combination of numbers with preset digits, upper and lower case letters and special symbols set by the user, or may be identity information of the user for verifying the identity of the user.

When a user needs to extract an article to be stored, firstly, an input key of the user is obtained to confirm the user who has transacted business at the current website in advance. And under the condition that the input key passes, carrying out user identity verification on the current biological characteristics, the extracted key and the recorded biological characteristics of the user, and under the condition that the re-verification passes, allowing the user to extract the article to be kept.

In an embodiment, the intelligent interaction method further includes: based on first visual information acquired by the current visual equipment, triggering a security monitoring center to determine whether an appointed arrival area is safe or not, and indicating a vehicle to travel to the appointed arrival area after determining safety.

The current visual equipment can be understood as equipment deployed outside a bank outlet and is mainly used for monitoring abnormal conditions around the bank outlet.

The first visual information can be understood as the visual information collected when the current visual equipment receives the vehicle and arrives, so that whether suspicious vehicles or available personnel exist around the bank outlets or not is judged through the first visual information, and whether the area where the vehicle is about to arrive is safe or not is determined.

Specifically, triggering the security monitoring center to determine whether the specified arrival area is safe or not based on the first visual information acquired by the current visual device, and indicating the vehicle to travel to the specified arrival area after determining safety may include the following steps:

C1) when a first information acquisition instruction sent by a security monitoring center is received, first visual information acquired by current visual equipment is sent to the security monitoring center, so that the security monitoring center determines whether an appointed arrival area is safe or not based on the first visual information and security information of security facilities, and sends a safe passing message to a vehicle after determining the safety, so that the vehicle runs to the appointed arrival area according to the safe passing message.

The security monitoring center can be understood as a management center used for acquiring and storing monitoring information in a bank. The current monitoring information can be real-time monitoring information of a transport vehicle besides the information inside and around the bank outlets, and the real-time monitoring information of the transport vehicle can comprise: vehicle interior information and vehicle periphery information for securing the transportation vehicle.

The current vehicle may be a transportation vehicle serving a bank or a vehicle in which a transportation user keeps articles.

The first information acquisition instruction is sent by the security monitoring center when an upcoming message sent by the vehicle is received.

When a vehicle is about to arrive at a target network point, a message about to arrive is sent to a cloud computing service center, and when the cloud computing service center receives a first information acquisition instruction sent by a security monitoring center, first visual information acquired by peripheral visual equipment installed at a bank network point is acquired, and the current first visual information is sent to the security monitoring center.

The first visual information may be current information shot by a peripheral visual device installed at a bank outlet, and the current information may be picture information or video information.

And the security monitoring center confirms whether the area where the vehicle is about to arrive is safe or not according to the current first visual information and the security information of the security facility, and after the safety is confirmed, the transport vehicle runs to the appointed arrival area according to the safe passing message.

The security information of the security facility may be standardized information for confirming security, for example, whether the number of surrounding people exceeds a preset value, whether suspicious people or suspicious vehicles are included, or the like.

C2) And when a second information acquisition instruction sent by the security monitoring center is received, sending the second visual information acquired by the current visual equipment to the security monitoring center, so that the security monitoring center informs the vehicle to start the delivery of the conveyed articles after confirming that no abnormal condition exists according to the second visual information.

The second information acquisition instruction can be that after the vehicle arrives at a specified place of a bank outlet, the visual equipment deployed at the bank outlet acquires information of surrounding vehicles, people, objects and the like, and sends the currently acquired information as second visual information to the security monitoring center, and the security monitoring center informs the vehicle to start the delivery of the transported articles after confirming that no abnormal condition exists according to the received second visual information; before handing over, the information stored in the electronic tag on the code case can be read through the Internet of things equipment, the read information is sent to the security monitoring center, the security monitoring center judges whether the conveyed article is matched with the local website according to the information, and the personnel of the vehicle are informed to start handing over when the conveyed article is matched with the local website.

The intelligent interaction method provided by the implementation of the invention is described in two specific application scenarios.

Scene one:

(1) the method comprises the following steps that a user makes an appointment for a website service through super-channel facilities such as a community bank, a cloud computing service center determines travel information (such as a travel route and a traffic road condition) recommended for the user according to the appointment information and traffic information obtained through interaction with a smart city center, and the travel information is sent to the user; and sending the travel information and the reservation information to a vision device deployed in a business hall;

(2) the visual device in the business hall identifies the vehicle based on the vehicle information in the received reservation information, when the arrival of the vehicle of the user is identified, the cloud computing service center is requested to schedule the parking space for the vehicle, the cloud computing service center sends the parking space scheduling result to the user, and the user parks according to the scheduled parking space.

(3) The method comprises the steps that a user can interact with intelligent service equipment (a service robot or visual federal equipment) in a business hall through voice, the intelligent service equipment converts voice-form interaction information input by the user into a text by adopting an NLP (non line language) model, corresponding service recommendation information is searched in a local question-answering library according to text content and reservation information, and the searched service recommendation information is output in the forms of voice, screen interfaces and the like. And if the corresponding service recommendation information is not found in the local question-answering library, sending a request message to the cloud computing service center, so that the cloud computing service center determines the service recommendation information according to the text content and the reservation information in the request message and then sends the service recommendation information to the intelligent service equipment, and the intelligent service equipment outputs the service recommendation information in the forms of voice, screen interface and the like.

(4) The user can use the intelligent interactive device (intelligent facility/intelligent service facility) in the business hall to make self-help consultation.

(5) The intelligent interaction equipment can send interaction information input through a touch screen and the like to the cloud computing service center, the cloud computing service center determines service recommendation information according to the interaction information, and the service recommendation information is sent to the intelligent interaction equipment to be output.

(6) The intelligent interaction equipment can also match a proper expert according to the input interaction information, start a video service with the expert, acquire the interaction information of the user in the video process, send the interaction information to the bank cloud computing service center, the bank cloud computing service center determines personalized service recommendation information according to the received interaction information, historical behavior information and the like, sends the personalized service recommendation information to the intelligent interaction equipment for output, and sends the personalized service recommendation information to related experts so that the user can communicate with the expert. And the user carries out requirement implementation after finally determining the adopted recommended service.

(7) After the user transacts the business, the cloud computing service center obtains traffic information through interaction with the smart city center, generates travel information (traffic characteristic information) according to the traffic information, and recommends the travel information to the user through a customer manager service.

(8) When a user needs to keep articles, the cloud computing service center synchronizes article related information in the electronic tags sent by the internet of things equipment of the network points to the terminal equipment of the user, wherein the electronic tags are tags arranged on the articles to be kept, so that the user can know the article keeping state.

(9) The cloud computing service center synchronizes the position information sent by the Internet of things equipment on the conveying path and the article related information in the electronic tag to the terminal equipment of the user, so that the user can know the conveying track of the conveyed article.

(10) The cloud computing service center generates an extraction key for the article to be stored, provides the extraction key for the user, and logs in the biological characteristics of the user; and when the user extracts the article, performing user identity authentication according to the key input by the user and the biological characteristics of the user.

(11) The cloud computing service center initiates customer satisfaction survey through super channels such as a community bank, users participate in the satisfaction survey through the super channels, the cloud computing center forms a satisfaction frame list of products according to survey results, supplements customer portrait information, and can iteratively optimize a customer preference model according to the survey results of the products and the services.

Scene two:

before going out, the cloud computing service center issues scheduling information to the vehicle monitoring and scheduling center;

(1) the vehicle monitoring and dispatching center adopts a vehicle dispatching algorithm, plans a running route of a transport vehicle according to the destination of the transport vehicle and urban traffic characteristic information obtained through interaction with the smart city center, and sends a route planning instruction to the transport vehicle; the transport vehicle goes out according to the received route planning instruction;

(2) in the running process, the vehicle monitoring and dispatching center sends a line adjusting instruction to the transport vehicle according to the visual information sent by the visual equipment installed on the transport vehicle and the urban traffic characteristic information obtained by interacting with the smart city center; the visual information comprises road condition information; the traffic characteristic information includes: road congestion information, traffic light status information, and the like;

(3) in the running process, if the transport vehicle stops abnormally, the transport vehicle is informed to a vehicle monitoring and dispatching center to cause the vehicle to be abnormal, the vehicle monitoring and dispatching center judges whether the transport vehicle continues to run according to an original planned route or is switched to a backup route for running according to visual information sent by visual equipment on the transport vehicle and urban traffic characteristic information obtained through interaction with a smart city center, and generates an adjusting scheme according to a judgment result and sends the adjusting scheme to the transport vehicle;

(4) when the user arrives at a bank outlet, the security monitoring center sends an instruction which can arrive at a designated place to the transport vehicle after prejudging and confirming the safety of a business area according to the visual information sent by the visual equipment on the transport vehicle, the visual information sent by the visual equipment deployed at the bank outlet and the security information of the security facility;

(5) after arriving at a designated place of a bank outlet, visual equipment deployed in the bank outlet sends visual information of vehicles, people, objects and the like to a security monitoring center, the security monitoring center informs a transport vehicle to start handover after confirming that no abnormal condition exists according to the received visual information, and the transport vehicle informs related personnel of the bank outlet to carry out handover of transported objects; if the abnormity occurs, starting a plan; before handover, information stored in an electronic tag on the article box can be read through the Internet of things equipment, the read information is sent to a security monitoring center, the security monitoring center judges whether the transported articles are matched with the local network points or not according to the information, and the transportation vehicle is informed to start handover when the transported articles are matched with the local network points;

(6) after the handover is finished, the visual equipment on the transport vehicle uploads the visual information to the cloud computing service center;

(7) when the business of the bank outlets is finished and the transport vehicle receives the articles, the visual equipment deployed at the bank outlets sends visual information of the vehicle, people, articles and the like to the security monitoring center, the security monitoring center informs the transport vehicle of starting to receive the articles after confirming that no abnormal condition exists according to the visual information, and the transport vehicle informs related personnel of the bank outlets of handing over the articles;

(8) and after the return trip is finished, the visual equipment on the transport vehicle uploads the visual information to the cloud computing service center.

(9) The cloud computing service center collects visual information uploaded by all transport vehicles every day, the transport characteristics are calculated according to the visual information, the transport cost is calculated according to the transport characteristics and a scheduling and business network cost model, iterative upgrading is carried out on a vehicle scheduling algorithm by using a visual federal learning algorithm according to the visual information, and the upgraded vehicle scheduling algorithm is sent to a vehicle monitoring and scheduling center and bank outlets.

In each embodiment of the invention, the cloud computing service center can perform real-time iterative optimization on the used models (such as the personalized recommendation model and the user portrait model) according to the acquired real-time interaction information with the user, so that the cloud computing service center can be applied to the intelligent interaction scene in real time.

EXAMPLE III

Fig. 6 is a schematic structural diagram of an intelligent interaction device according to a third embodiment of the present invention, which is applicable to improve service efficiency and service accuracy and enhance user experience, and the device can be implemented in software and/or hardware, and can be integrated into any device providing intelligent interaction function, as shown in fig. 6, the intelligent interaction device specifically includes:

a first interactive information obtaining module 410, configured to obtain first interactive information input by a user, match a consulted person according to the first interactive information, and start a video service with the consulted person;

a second interaction information obtaining module 420, configured to obtain second interaction information input by the user in a video process with the consulted person, and send the second interaction information to a cloud computing service center;

the first product recommendation information output module 430 is configured to receive first product recommendation information fed back by the cloud computing service center according to the second interaction information, and output the first product recommendation information.

The intelligent interaction device provided by the embodiment of the invention firstly acquires first interaction information input by a user, matches a consulted person according to the first interaction information, and starts video service with the consulted person; then second interactive information input by the user in the video process of the consulted person is obtained, and the second interactive information is sent to the cloud computing service center; and finally, receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information, and outputting the first product recommendation information. According to the technical scheme, the first product recommendation information is fed back to the user according to the second interaction information input by the user in the user service process, so that the effects of improving the service efficiency and the service accuracy and improving the user experience can be achieved.

In one embodiment, the apparatus further comprises: the system comprises a first interactive information sending module and a second product recommendation information output module, wherein:

the first interaction information sending module is used for sending the first interaction information to the cloud computing service center;

and the second product recommendation information output module is used for receiving second product recommendation information fed back by the cloud computing service center according to the first interaction information and outputting the second product recommendation information.

In one embodiment, the apparatus further comprises: the third interactive information acquisition module, the third product recommendation information search module and the fourth product recommendation information output module, wherein:

the third interactive information acquisition module is used for acquiring third interactive information in a voice form input by a user; converting the third interactive information into text information based on a preset natural language processing NLP model;

the third product recommendation information searching module is used for searching corresponding third product recommendation information in a local knowledge question-answering library according to the text content and the reservation information of the user for the website service;

the fourth product recommendation information output module is used for outputting the searched third product recommendation information; if not, sending a service recommendation request to the cloud computing service center; and receiving the fourth product recommendation information fed back by the cloud computing service center according to the text content and the reservation information, and outputting the fourth product recommendation information.

In one embodiment, the apparatus further comprises: biological characteristic admission module and article extract instruction response module, wherein:

the biological feature admission module is used for acquiring an extraction key generated for an article to be stored of a user and admission biological features admitted by the user, providing the extraction key for the user, and storing the extraction key and the admission biological features;

and the article extraction instruction response module is used for responding to the received article extraction instruction, carrying out user identity authentication according to the input secret key of the user, the current biological characteristics of the user, the extraction secret key and the recorded biological characteristics, and determining whether the user is allowed to extract the article to be kept according to an authentication result.

In one embodiment, the apparatus further comprises: security protection surveillance center trigger module, wherein:

the security monitoring center triggering module is used for triggering the security monitoring center to determine whether the appointed arrival area is safe or not based on the first visual information acquired by the current visual equipment, and indicating the vehicle to travel to the appointed arrival area after the safety is determined.

In an embodiment, the safety passing message sending module is specifically configured to send, when receiving a first information obtaining instruction sent by a security monitoring center, first visual information obtained by a current visual device to the security monitoring center, so that the security monitoring center determines whether an appointed arrival area is safe or not based on the first visual information and security information of a security facility, and sends a safety passing message to a vehicle after determining safety, so that the vehicle travels to the appointed arrival area according to the safety passing message;

In an embodiment, the secure passage message sending module is specifically configured to:

and when a second information acquisition instruction sent by the security monitoring center is received, sending second visual information acquired by the current visual equipment to the security monitoring center, so that the security monitoring center informs the vehicle to start handing over of conveyed articles after confirming no abnormal condition according to the second visual information.

In one embodiment, the apparatus further comprises: parking stall scheduling module, wherein:

and the parking space scheduling module is used for triggering the cloud computing service center to perform parking space scheduling on the user when the vehicle of the user arrives according to the image acquired by the visual equipment.

In one embodiment, the parking space scheduling module includes: reservation information receiving element and parking stall scheduling unit, wherein:

the reservation information receiving unit is used for receiving reservation information of the user to the website service, which is sent by the cloud computing service center;

the parking space scheduling unit is used for carrying out vehicle feature recognition on the image acquired by the visual equipment and determining whether the vehicle of the user arrives or not according to a vehicle feature recognition result and the reservation information; and if the vehicle of the user arrives, sending a parking space scheduling request to the cloud computing service center so that the cloud computing service center carries out parking space scheduling and sends a parking space scheduling result to the user.

In one embodiment, the parking space scheduling module further includes a feature recognition unit and a vehicle information matching unit, wherein:

the characteristic recognition unit is used for recognizing license plate characteristics and/or vehicle type characteristics of the image acquired by the current visual equipment based on a preset target recognition model;

and the vehicle information matching unit is used for matching the identified license plate characteristics and/or vehicle type characteristics with the user vehicle information in the reservation information, and if the license plate characteristics and/or the vehicle type characteristics are consistent with the user vehicle information in the reservation information, determining that the vehicle of the user arrives.

In an embodiment, the preset target recognition model is a model for target recognition, which is trained in advance by using a visual federal learning mechanism.

In one embodiment, the reservation information is acquired by the cloud computing service center through a super channel, and the super channel includes a community bank, a mobile phone bank, an internet bank, a telephone bank, or a wechat bank.

In an embodiment, the first product recommendation information is determined by the cloud computing service center based on the second interaction information, the attribute information of the user, and a personalized recommendation model trained in advance, where the personalized recommendation model is trained in advance based on historical behavior information of the user for the bank product and the user attribute information.

In one embodiment, the attribute information includes an interest tag and a user feature vector;

wherein the interest label is determined based on a pre-trained preference model, and the user feature vector is determined based on a pre-trained user portrait model;

the preference model is trained in advance based on historical behavior information and/or investigation information of a user for bank products, and the user portrait model is trained in advance based on user characteristic information.

The product can execute the method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

Example four

Fig. 7 is a schematic structural diagram of an electronic device according to a ninth embodiment of the present invention. Fig. 7 shows a block diagram of an exemplary electronic device 7 suitable for implementing an embodiment of the invention. The electronic device 12 shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.

As shown in FIG. 7, electronic device 12 is embodied in the form of a general purpose computing device. The components of the electronic device 7 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, and commonly referred to as a "hard drive"). Although not shown in FIG. 7, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.

The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and/or any device (e.g., network card, modem, etc.) that enables the electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. In the electronic device 12 of the present embodiment, the display 24 is not provided as a separate body but is embedded in the mirror surface, and when the display surface of the display 24 is not displayed, the display surface of the display 24 and the mirror surface are visually integrated. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, to implement an intelligent interactive method provided by the embodiment of the present invention: acquiring first interactive information input by a user, matching consulted personnel according to the first interactive information, and starting video service with the consulted personnel;

EXAMPLE five

An embodiment five of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements an intelligent interaction method as provided in all embodiments of the present invention: acquiring first interactive information input by a user, matching consulted personnel according to the first interactive information, and starting video service with the consulted personnel;

and receiving first product recommendation information fed back by the cloud computing service center according to the second interaction information, and outputting the first product recommendation information. Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Example six

Embodiments of the present invention further provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the intelligent interaction method provided in any embodiment of the present application is implemented.

Computer program product in implementing the computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments illustrated herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An intelligent interaction method, the method comprising:

2. The method of claim 1, wherein before matching consulted people according to the first interaction information, the method further comprises:

sending the first interaction information to the cloud computing service center;

and receiving second product recommendation information fed back by the cloud computing service center according to the first interaction information, and outputting the second product recommendation information.

3. The method of claim 1, further comprising:

acquiring third interactive information in a voice form input by a user; converting the third interactive information into text information based on a preset natural language processing NLP model;

searching corresponding third product recommendation information in a local knowledge question-answering base according to the text content and the reservation information of the user for the website service;

if the third product recommendation information is found, outputting the found third product recommendation information; if not, sending a service recommendation request to the cloud computing service center; and receiving the fourth product recommendation information fed back by the cloud computing service center according to the text content and the reservation information, and outputting the fourth product recommendation information.

4. The method of claim 1, further comprising:

acquiring an extraction key generated for an article to be kept by a user and an admission biological characteristic admitted by the user, providing the extraction key for the user, and storing the extraction key and the admission biological characteristic;

and in response to receiving an article extraction instruction, carrying out user identity authentication according to an input key of a user, the current biological characteristics of the user, the extraction key and the recorded biological characteristics, and determining whether the user is allowed to extract the article to be kept according to an authentication result.

5. The method of claim 1, further comprising:

based on first visual information acquired by the current visual equipment, triggering a security monitoring center to determine whether an appointed arrival area is safe or not, and indicating a vehicle to travel to the appointed arrival area after determining safety.

6. The method according to claim 5, wherein the triggering a security monitoring center to determine whether a designated arrival area is safe based on first visual information acquired by a current visual device, and instructing a vehicle to travel to the designated arrival area after determining that the designated arrival area is safe comprises:

when a first information acquisition instruction sent by a security monitoring center is received, first visual information acquired by current visual equipment is sent to the security monitoring center, so that the security monitoring center determines whether an appointed arrival area is safe or not based on the first visual information and security information of security facilities, and sends a safe passing message to a vehicle after determining the safety, so that the vehicle runs to the appointed arrival area according to the safe passing message;

the first information acquisition instruction is sent by the security monitoring center when receiving an upcoming message sent by the vehicle.

7. The method of claim 6, wherein after the vehicle reaches the designated arrival area, the method further comprises:

8. The method of claim 1, wherein before obtaining the first interaction information input by the user, the method further comprises:

and when the vehicle of the user arrives according to the image acquired by the visual equipment, triggering the cloud computing service center to carry out parking space scheduling on the user.

9. The method of claim 8, wherein the triggering the cloud computing service center to perform parking space scheduling for the user when the vehicle of the user arrives is determined according to the image acquired by the visual device comprises:

receiving reservation information of a user to a website service, which is sent by the cloud computing service center;

carrying out vehicle feature recognition on the image acquired by the visual equipment, and determining whether the vehicle of the user arrives according to a vehicle feature recognition result and the reservation information; and if the vehicle of the user arrives, sending a parking space scheduling request to the cloud computing service center so that the cloud computing service center performs parking space scheduling and sends a parking space scheduling result to the user.

10. The method of claim 9, wherein the performing vehicle feature recognition on the image captured by the vision device, and determining whether the user's vehicle arrives according to the vehicle feature recognition result and the reservation information comprises:

based on a preset target recognition model, recognizing license plate features and/or vehicle type features of an image acquired by current visual equipment;

and matching the identified license plate characteristics and/or vehicle type characteristics with the user vehicle information in the reservation information, and if the license plate characteristics and/or the vehicle type characteristics are consistent with the user vehicle information in the reservation information, determining that the vehicle of the user arrives.

11. The method according to claim 10, wherein the preset target recognition model is a model for target recognition that is trained in advance by using a visual federal learning mechanism.

12. The method of claim 9, wherein the subscription information is obtained by the cloud computing service center through a super channel, wherein the super channel comprises a community bank, a cell phone bank, an internet bank, a telephone bank, or a wechat bank.

13. The method according to any one of claims 1 to 12, wherein the first product recommendation information is determined by the cloud computing service center based on the second interaction information, the attribute information of the user, and a personalized recommendation model trained in advance based on historical behavior information and user attribute information of the user for the bank product.

14. The method of claim 13, wherein the attribute information includes interest tags and user feature vectors;

15. An intelligent interaction device, comprising:

the system comprises a first interactive information acquisition module, a second interactive information acquisition module and a video service starting module, wherein the first interactive information acquisition module is used for acquiring first interactive information input by a user, matching a consulted person according to the first interactive information and starting a video service of the consulted person;

16. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the intelligent interaction method as claimed in any one of claims 1 to 14 when executing the computer program.

17. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the intelligent interaction method according to any one of claims 1 to 14.

18. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the intelligent interaction method of any one of claims 1-14.