Information processing method, device and medium

Abstract

The present application relates to an information processing method, device and medium, wherein the method comprises: receiving a first request message from a client; determining user attribute information corresponding to the first request message; obtaining first reply information of the first request message according to the user attribute information; obtaining second request information associated with the first request message according to the user attribute information; and sending the first reply information and first response information corresponding to the second request message to the client. The present application improves interaction efficiency and user experience.

Description

Technical Field

[0001] The present application relates to the field of blockchain technology, and mainly to an information processing method, device and medium. Background Art

[0002] With the popularization of the Internet and e-commerce, there are more and more intelligent customer services. Intelligent customer service is an industry-oriented application developed on the basis of large-scale knowledge processing, involving large-scale knowledge processing technology, natural language understanding technology, knowledge management technology, automatic question-answering system, reasoning technology, etc. It is universal in the industry and not only provides enterprises with fine-grained knowledge management technology, but also establishes a fast and effective technical means based on natural language for communication between enterprises and massive users; at the same time, it can also provide enterprises with statistical analysis information required for refined management.

[0003] At present, most intelligent customer service is based on the application of big data knowledge processing technology, that is, the required data is stored in the knowledge base in advance. When the intelligent customer service is working, the knowledge stored in the knowledge base is read at any time. After reading the existing knowledge, it is fed back to the visitor, adopting a question-and-answer dialogue mode. At present, this dialogue mode is fixed and the user experience effect is average. When the visitor is not very clear about his logic or intention, the entire consultation process will become very inefficient and time-consuming. Summary of the invention

[0004] The embodiments of the present application provide an information processing method, device and medium, which can reply to request information uploaded by a user and recommend related information, thereby improving interaction efficiency and user experience.

[0005] In a first aspect, an embodiment of the present application provides an information processing method, wherein:

[0006] Receiving first request information from a client;

[0007] Determining user attribute information corresponding to the first request information;

[0008] Acquire first reply information of the first request information according to the user attribute information;

[0009] Acquire second request information associated with the first request information according to the user attribute information;

[0010] Sending the first reply information and first response information corresponding to the second request information to the client.

[0011] In a second aspect, an embodiment of the present application provides an information processing device, wherein:

[0012] A communication unit, configured to receive first request information from a client;

[0013] A processing unit, configured to determine user attribute information corresponding to the first request information; obtain first reply information to the first request information according to the user attribute information; and obtain second request information associated with the first request information according to the user attribute information;

[0014] The communication unit is further configured to send first response information corresponding to the first reply information and the second request information to the client.

[0015] In a third aspect, an embodiment of the present application provides another information processing device, comprising a processor, a memory, a communication interface, and one or at least one program, wherein the one or at least one program is stored in the memory and configured to be executed by the processor, and the program includes instructions for some or all of the steps described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute to implement some or all of the steps described in the first aspect.

[0017] Implementing the embodiments of the present application will have the following beneficial effects:

[0018] After adopting the above-mentioned information processing method, device and medium, after receiving the first request information from the client, the user attribute information corresponding to the first request information is determined, and then the first reply information of the first request information and the second request information associated with the first request information are obtained according to the user attribute information. Finally, the first reply information and the first response information corresponding to the second request information are sent to the client. In other words, it is possible to reply to the request information uploaded by the user and recommend related information, thereby improving the interaction efficiency and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] in:

[0021] Figure 1 A flowchart of an information processing method provided in an embodiment of the present application;

[0022] Figure 2A schematic diagram of a scenario of an information processing method provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of another information processing method provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of the logical structure of an information processing device provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of the physical structure of an information processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. According to the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0028] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0029] The network architecture used in the embodiment of the present application includes a server and a client corresponding to the server. Among them, the client can be a personal computer (PC), a laptop or a smart phone, and can also be an electronic device such as an all-in-one machine, a handheld computer, a tablet computer (pad), a smart TV playback terminal, a vehicle-mounted terminal or a portable device. The client of the mobile terminal, for example, a smart phone, etc., its operating system can include but is not limited to operating systems such as Android system, IOS (operating system of Apple mobile phone), Window system. The client of the PC terminal, such as an all-in-one machine, etc., its operating system can include but is not limited to operating systems such as Linux system, Unix system, Windows series system (for example, Windows xp, Windows 7, etc.), Mac OSX system (operating system of Apple computer).

[0030] The server is similar to a general computer architecture, including a processor, a hard disk, a memory, a system bus, etc., and is used to provide services to the client. The client in the embodiment of the present application can install and run an application, and the server can be a server corresponding to the application installed by the client, providing application services for the application. Among them, the application may include a customer service application. The application may be a separately integrated application, or a small program embedded in other applications, or a system on a web page, etc., which is not limited here. The embodiment of the present application does not limit the number of clients and servers, and the server can provide services to one or more clients. The server can be implemented with an independent server or a server cluster consisting of multiple servers.

[0031] In an embodiment of the present application, the intelligent customer service is not transferred to the manual customer service, and the manual customer service provides customer service. Instead, it automatically replies according to the previously stored data. The present application can pre-store the historical request records of each user, and the historical request records include request information, and the reply information of the manual customer service or the intelligent customer service in response to the request information. It can be understood that by analyzing and learning different request information through historical request records, the expected answers corresponding to each request information can be obtained, so as to reply to the request information input by the current user, and the accuracy of the reply can be improved. It is also possible to obtain the request information that the user may also enter, so as to prompt the associated request information on the basis of replying according to the expected answer, so as to improve the interaction efficiency. Furthermore, it is also possible to obtain the expected answers corresponding to different request information of each user, or determine the user attribute information of each user (for example, user preference type, user frequently asked questions, etc.), or determine the hot search problems encountered in the current server, etc.

[0032] For example, when the client runs the first application, the user reports a customer service request instruction on the first application, and the client receives the customer service request instruction and sends a customer service access request corresponding to the customer service request instruction to the server. The server responds to the customer service access request and connects with the client, and the client displays the communication interface between the user and the intelligent customer service corresponding to the server. If the user enters the first request information in the communication interface, the server responds to the first request information and obtains the first reply information of the first request information and the second request information associated with the first request information.

[0033] The above historical request information can be stored in units of users, or can be stored in units of types, or can be stored in units of keywords, etc., which are not limited here. The set corresponding to the historical request records stored in the server is called a historical request record set. The present application can store the historical request record set in a block created on the blockchain network. Blockchain is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database. It is a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. The blockchain may include the underlying blockchain platform, the platform product service layer, and the application service layer. It can be seen that by distributing data through the blockchain, while ensuring data security, information sharing between different platforms can be achieved.

[0034] An information processing method proposed in an embodiment of the present application can be executed by an information processing device, wherein the device can be implemented by software and / or hardware, and can generally be integrated in a server. It can reply to request information uploaded by users and recommend related information, thereby improving interaction efficiency and user experience.

[0035] Please refer to Figure 1 , Figure 1 This is a flowchart of an information processing method provided by the present application. Taking the method applied to a server as an example, the method includes the following steps S101 to S105, wherein:

[0036] S101: receiving first request information from a client.

[0037] In an embodiment of the present application, the first request information can be input by voice or text, which is not limited here. The first request information can be used to consult questions, or can be used for complaints or suggestions, which is not limited here. This application takes consulting questions as an example. It should be noted that the first request information can carry user identification information and request scenario information. Among them, the user identification information is used to identify the user, and can be the account corresponding to the user submitting the first request information. The account can be the account for logging into the application, or the account of the mini program logged in in the application, or the account of the client, etc. It can be understood that different users may request different matters. For example, the first user inquires about the bill, the second user inquires about the repayment date, and the third user inquires about the limit on the increase in the credit limit, etc.

[0038] The request scenario information may include application information, such as application identification, application type, and request purpose. It is understandable that different application types may have different request items. For example, the customer service of financial applications may be consulted about bills, repayment dates, increase limits, transfer procedures, etc., and the customer service of government and enterprise applications may be consulted about demolition matters, policies, and handling agency information. Different applications correspond to different application identifications, and different applications may have different request items based on the characteristics of the application itself. For example, if an application launches a new function, the customer service of the application may be consulted on how to use the new function. If the location of a function in different applications is different, the customer service of any of the applications may be consulted on the location and usage of the function.

[0039] The present application does not limit the method for obtaining the requested scene information. In a possible example, the following steps A1 to A3 may be included, wherein:

[0040] A1: Parse the front-end page corresponding to the first request information to obtain page information of the front-end page.

[0041] The front-end page is a page where the user inputs the first request information, and may carry the purpose for which the user inputs the first request information. For example, in a shopping application, the front-end page is a product browsing page, and the first request information may be used to obtain size recommendations, logistics information, promotional information, etc. for the product on the product browsing page. For another example, in a financial application, the front-end page is a billing page, and the first request information may be used to obtain the minimum repayment date, credit limit increase matters, etc.

[0042] The page information includes page identification, page type, page components, etc., which are not limited here. Among them, the page identification can be a page name or a network address, etc. The page type can be the application type corresponding to the page or the function type of the application function in the page, etc. The page component can be an application function in the page, such as an input box, a comment column, a selection button, etc. The above information is also not limited. It can be understood that the page information can reflect the page attributes of the front-end page, so as to facilitate the acquisition of the request parameters of the first request information.

[0043] The present application does not limit the method for parsing the front-end page. The page image of the front-end page can be obtained; the page image can be divided to obtain multiple sub-images; and the page information of each sub-image can be obtained. The page image can be divided according to the page components of the page image, and the page components with the same application function and in adjacent positions are divided into one sub-image. By dividing the page image of the front-end page and obtaining the page information of each sub-image, the accuracy of obtaining the page information can be improved.

[0044] A2: Obtain request parameters of the first request information according to the page information.

[0045] The request parameters include the purpose of the request, the time of the request, the source of the request, etc., which are not limited here. The present application can obtain the request parameters based on the correlation between the page information and the first request information, or can count the request parameters corresponding to the page information, and then obtain the request parameters based on the correlation between the request parameters and the first request information, etc., which are not limited here.

[0046] A3: Obtain request scenario information of the first request information according to the request parameters.

[0047] It can be understood that in steps A1 to A3, the front-end page is first parsed to obtain the page information of the front-end page, then the request parameters are obtained according to the page information, and finally the request scenario information is obtained according to the request parameters, which can improve the accuracy of obtaining the request scenario information.

[0048] S102: Determine user attribute information corresponding to the first request information.

[0049] In an embodiment of the present application, user attribute information is used to describe the attributes in the user's attribute information corresponding to the first request information, such as: user preference type, whether the user is a new or old user, the source of the user (for example, computer or mobile, the application itself or a third-party application, etc.). It can be understood that user attribute information can reflect the user's preferences and subsequent questioning directions, so as to improve the accuracy of recommendations. For example, in financial applications, the first request information is used to obtain bills. New users may inquire about the minimum repayment amount after querying the bill, and old users may inquire about how to apply for an increase in the amount after querying the bill. For another example, in enterprise applications, the first request information is used to obtain the process of starting a business. After obtaining the process of starting a business, the user on the computer may inquire about the address of the handling agency. After obtaining the process of starting a business, the user on the mobile phone may inquire about the phone number of the agency that starts the business.

[0050] The present application does not limit the method for determining whether a user is a new user or an old user. The registration time can be searched based on the user identification information. If the registration information is greater than the preset time, the user is determined to be an old user. Alternatively, the number of times the current application is used or the frequency of use can be obtained based on the user identification information. If the number of times or the frequency of use is greater than the first preset threshold, the user is determined to be an old user. Alternatively, the user's familiarity value can be determined based on the first request information. If the familiarity value is greater than the second preset threshold, the user is determined to be an old user, and so on. Otherwise, the user is a new user. The above preset time, the first preset threshold, and the second preset threshold are not limited. It can be understood that old users have the advantages of long registration time for the current application, many times of use, fast frequency of use, and large familiarity value. Determining whether the user is an old user based on at least one of the above information can improve the accuracy of recognition.

[0051] This application does not limit the method of determining whether the user's source is from the mobile phone or the computer. The physical identification of the client can be obtained for identification. Or the front-end page can be identified. It can be understood that since the display effects of the computer and mobile phone are different, in one possible example, the source of the user is determined by identifying the front-end page.

[0052] The present application does not limit the method for obtaining the user preference type in the user attribute information. The first request information includes the user identification information. In a possible example, the following steps B1 to B3 are included, wherein:

[0053] B1: Obtain request scenario information of the first request information.

[0054] The method of requesting scene information and obtaining the requested scene information may refer to the description of step S101 and will not be repeated here.

[0055] B2: Acquire a first historical request record corresponding to the user identification information and the request scenario information from a pre-stored historical request record set.

[0056] Among them, the first historical request record is a historical request record corresponding to the request scenario information in the first historical request record set. The first historical request record may include the user corresponding to the user identification information, all historical request records in the current application, or all historical request records in all applications with the same application type as the current application, or all historical request records in the client, etc., which are not limited here. It should be noted that the number of the first historical request records can be one or more.

[0057] It can be understood that by analyzing the historical request records of the same user, the types of requests that the user frequently calls customer service, or the areas that the user is concerned about, or the areas that the user is not familiar with, etc. can be obtained, which is convenient for improving the accuracy of determining the user's preference type. On the basis of analyzing the historical request records of the same user, it is helpful to improve the accuracy of obtaining the user's preference type analysis in the current scenario.

[0058] B3: Determine the user preference type according to the first historical request record.

[0059] The present application does not limit the method for determining the user preference type based on the first historical request record. In one possible example, the first historical request record is parsed to obtain multiple reference request information; the multiple reference request information are classified to obtain multiple sub-historical request record sets; and the user preference type is determined based on the multiple sub-historical request record sets.

[0060] The reference request information may be the request information included in the first historical request record. The reference request information may be classified by time or by the type of request information, and the classification is not limited here. When the classification is performed by time, the behavior habits of users sending requests may be analyzed. When the classification is performed by type, the request type of the user sending the request, as well as the user's familiarity or focus areas, may be analyzed.

[0061] It can be understood that in this example, the first historical request record is first parsed to obtain reference request information, then the reference request information is classified to obtain sub-historical request record sets, and then the user preference type is analyzed based on the sub-historical request record sets, which can improve the accuracy of obtaining user preference type analysis in the current scenario.

[0062] In steps B1 to B3, the request scenario information of the first request information is first obtained, and the first historical request record corresponding to the user identification information and the request scenario information is obtained from the pre-stored historical request record set. The user preference type is determined according to the first historical request record, which can improve the accuracy of determining the user preference type.

[0063] S103: Acquire first reply information to the first request information according to user attribute information.

[0064] In the embodiment of the present application, the first reply information may be the reply information obtained by the intelligent customer service in response to the first request information. The present application does not limit the method for how the intelligent customer service obtains the first reply information. The first reply information may be obtained by querying from a pre-stored historical request record set based on the first request information, or the historical request record set may be trained in advance to obtain an artificial intelligence training model, and then the first request information is input into the artificial intelligence training model to obtain the first reply information, etc.

[0065] In a possible example, step S103 includes the following steps C1 to C3, wherein:

[0066] C1: Searching for third request information corresponding to the first request information from a pre-stored historical request record set.

[0067] The third request information corresponds to the first request information, and may be a request information including a keyword in the first request information, or may be a request information with a meaning similar to or the same as the first request information. For example, if the first request information is: when to ship, the second request information may be: when to ship, how long to ship, how long to arrive, etc. It should be noted that the number of the third request information may be one or more.

[0068] C2: Obtaining a first evaluation value of the third reply information corresponding to the third request information according to the user attribute information.

[0069] The first evaluation value is used to describe the degree of completion of the third reply information in solving the third request information. The greater the degree of completion, the higher the first evaluation value. It can be understood that obtaining the first evaluation value of the third reply information based on user attribute information can improve the evaluation standard and facilitate improving the accuracy of the reply.

[0070] The present application does not limit the acquisition of the first evaluation value based on the user attribute information. In one possible example, the first sub-evaluation value of the third reply information is acquired based on the user attribute information; the second sub-evaluation value between the third request information and the third reply information is acquired; and the first evaluation value is acquired based on the first sub-evaluation value and the second sub-evaluation value.

[0071] Among them, the first sub-evaluation value is used to describe the preference of the third reply information. The third sub-evaluation value of the third reply information can be obtained by user type (for example, new or old customers, computer customers or mobile customers); the fourth sub-evaluation value of the third reply information can be obtained by user preference type; and the first sub-evaluation value can be obtained based on the third sub-evaluation value and the fourth sub-evaluation value. It can be understood that obtaining the first sub-evaluation value of the third reply information from the dimensions of user attribute information such as user type and user preference type can improve the accuracy of obtaining the first sub-evaluation value.

[0072] The second sub-evaluation value is used to describe the completion of the third reply information, which can be understood as whether the third request information has been resolved. It can be determined based on the similarity value between the request information after the third reply information and the third request information. That is, the larger the similarity value, the lower the completion of the third reply information.

[0073] It can be understood that, in this example, obtaining the first evaluation value of the third reply information through the first sub-evaluation value and the second sub-evaluation value can improve the accuracy of obtaining the first evaluation value.

[0074] C3: If the first evaluation value is greater than or equal to the first threshold, determining that the third reply information is the first reply information of the first request information.

[0075] The first threshold is not limited, and the first threshold may be preset, or may be set according to an application or a user, etc. In a possible example, the first threshold may be the maximum value among the first evaluation values ​​of each third reply information, that is, the third reply information corresponding to the largest first evaluation value is selected as the first reply information, which can improve the accuracy of the reply.

[0076] It can be understood that in steps C1 to C4, the third request information corresponding to the first request information is first searched from the historical request record set. Then, the first evaluation value of the third request information is obtained according to the user attribute information, and the third reply information with the first evaluation value greater than or equal to the first threshold is used as the expected answer to the first request information, that is, the first reply information, which can improve the accuracy of obtaining the first reply information.

[0077] S104: Acquire second request information associated with the first request information according to the user attribute information.

[0078] In the embodiment of the present application, the second request information is associated information of the first request information, and can be obtained by counting historical request records. It should be noted that the number of the second request information can be one or more.

[0079] The present application does not limit the method for obtaining the second request information. In a possible example, step S104 includes the following steps D1 to D4, wherein:

[0080] D1: Count the first number of fourth request information after the third request information.

[0081] The fourth request information is a request information sent after the third request information. The first number is the number of occurrences of the fourth request information, which may be the total number of occurrences in the historical request record set, or the total number of occurrences in the first historical request record set, or the total number of occurrences in the historical request record set corresponding to the third request information, etc.

[0082] D2: Acquire the second evaluation value of the fourth request information after the first request information according to the user attribute information.

[0083] The second evaluation value is used to describe the possibility of the user corresponding to the user attribute information asking the fourth request information after the first request information.

[0084] The present application does not limit the method for obtaining the second evaluation value based on user attribute information. In one possible example, the fifth sub-evaluation value of the fourth request information is obtained based on the user attribute information; the sixth sub-evaluation value between the fourth request information and the first request information is obtained; and the second evaluation value is obtained based on the fifth sub-evaluation value and the sixth sub-evaluation value.

[0085] Among them, the fifth sub-evaluation value is used to describe the preference of the fourth request information. The seventh sub-evaluation value of the fourth request information can be obtained by user type (for example, new or old customers, computer customers or mobile customers); the eighth sub-evaluation value of the fourth request information can be obtained by user preference type; and the fifth sub-evaluation value can be obtained according to the seventh sub-evaluation value and the eighth sub-evaluation value. It can be understood that obtaining the fifth sub-evaluation value of the fourth request information from the dimensions of user attribute information such as user type and user preference type can improve the accuracy of obtaining the fifth sub-evaluation value.

[0086] The sixth sub-evaluation value is used to describe the correlation between the fourth request information and the first request information, and can be obtained through similarity values ​​of the request types between the two, etc., and is not limited here.

[0087] It can be understood that, in this example, obtaining the second evaluation value of the fourth request information through the fifth sub-evaluation value and the sixth sub-evaluation value can improve the accuracy of obtaining the second evaluation value.

[0088] D3: According to the first score and the second evaluation value, obtain a third evaluation value of the fourth request information that is located after the first request information.

[0089] Among them, the third evaluation value is the evaluation value corresponding to the combination of the first number and the second evaluation value, which can improve the accuracy of obtaining the second request information. This application does not limit the method of obtaining the third evaluation value from the first number and the second rating value. It can be obtained in the form of a weighted average, or it can be obtained based on the ratio between the first number and the total number of times, and then multiplied by the second evaluation value.

[0090] D4: If the third evaluation value is greater than or equal to the second threshold, determining that the fourth request information is the second request information.

[0091] The second threshold is not limited, and the second threshold may be preset, or may be set according to an application or a user, or may be set according to the total number of fourth request information. For example, if the total number is 10, the second threshold may be set to 6. For example, if the second threshold is 5, when the third evaluation value corresponding to one fourth request information is 7 and the third evaluation value corresponding to another fourth request information is 4, the fourth request information corresponding to the third evaluation value of 7 is determined to be the second request information.

[0092] It can be understood that in steps D1 to D4, the third evaluation value of the fourth request information is obtained from two aspects: counting the first number of times the fourth request information is requested, and obtaining the second evaluation value of the fourth request information that is located after the first request information based on user attribute information. When the third evaluation value is greater than or equal to the second threshold, the fourth request information is determined to be the second request information, thereby improving the accuracy of determining the second request information.

[0093] In a possible example, the method further includes the following steps E1 to E3, wherein:

[0094] E1: If the search for the third request information fails, the fifth request information corresponding to the first time period is obtained from the historical request record set.

[0095] The present application does not limit the first period, and statistics can be made based on the number of visits in the current server. For example, when the number of visits is large, the duration of the first period is 15 days, and when the number of visits is small, the duration of the first period is 30 days. The first period can also be counted based on the number of visits of the business type, which is the business type of the first request information. It can be understood that by counting the number of fifth request information in the first period, the accuracy and real-time performance of the statistics can be improved.

[0096] The fifth request information may be all historical request records in the server corresponding to the current application in the first period. It is understandable that if there is no third request information corresponding to the first request information in the historical request record set, it means that it is difficult to directly refer to the historical record to obtain the second request information.

[0097] E2: Count the second number of times the fifth request information is received.

[0098] The second number is the number of times the fifth request information occurs, and the description of the first number may be referred to and will not be repeated here.

[0099] E3: If the second number is greater than or equal to the third threshold, send the fifth request information to the client.

[0100] When the second number is greater than or equal to the third threshold, it indicates that the fifth request information occurs more frequently, which can be understood as the current hot question.

[0101] It can be understood that in steps E1 to E3, if there is no third request information corresponding to the first request information in the historical request record set, the second number of the fifth request information in the historical request records within the first time period can be counted, and the fifth request information whose second number is greater than or equal to the third threshold can be recommended to the user as a hot search question, thereby improving the accuracy of the recommendation.

[0102] In addition, after step E1, the call can be transferred to manual customer service to improve customer service response efficiency.

[0103] S105: Send the first reply information and the first response information corresponding to the second request information to the client.

[0104] In the embodiment of the present application, the first response information includes the first reply information and the second request information, and the first reply information and the second request information can be displayed in two sub-information, respectively, without limitation. Figure 2 As shown, after the client establishes a connection with the intelligent customer service of the server, it first sends a first request message to the server, and then receives a first reply message and a second request message in response to the intelligent customer service.

[0105] If there are multiple second request information, they are arranged according to the third evaluation value. For example, if one of the second request information has a third evaluation value of 8 and another has a third evaluation value of 7, the second request information with the evaluation value of 8 is located before the second request information with the evaluation value of 7.

[0106] exist Figure 1 In the method shown, after receiving the first request information from the client, the user attribute information corresponding to the first request information is determined, and then the first reply information of the first request information and the second request information associated with the first request information are obtained according to the user attribute information. Finally, the first reply information and the first response information corresponding to the second request information are sent to the client. In other words, it is possible to reply to the request information uploaded by the user and recommend related information, thereby improving the interaction efficiency and user experience.

[0107] In a possible example, the method further includes: obtaining second reply information corresponding to the second request information based on user attribute information; sending the first reply information and the second request information, as well as second response information corresponding to the second reply information, to the client end.

[0108] The second reply information may be obtained according to the third reply information corresponding to the third request information obtained above. The second response information may be displayed in the form of a first reply information, a second request information and a corresponding second reply information as a sub-information.

[0109] Take the client communication interface as an example. Figure 3 As shown, after the client establishes a connection with the intelligent customer service of the server, it first sends a first request message to the server, and then receives a first reply message in response to the intelligent customer service, as well as a second request message and a second reply message corresponding to the second request message. The second request message is displayed in bold format, and the second reply message is displayed in underline format.

[0110] It can be understood that by displaying the first reply information, the second request information, and the second reply information of the second request information, it is possible to avoid repeated interaction and improve the interaction efficiency.

[0111] In a possible example, after step S105, the method further includes: receiving a selection instruction from a user for second request information; and acquiring sixth request information associated with the second request information according to user attribute information.

[0112] The sixth request information may refer to the description of the second request information, which will not be described here. The sixth request information may be obtained after receiving the selection instruction, or may be obtained in the process of obtaining the third request information, which is not limited here. It can be understood that by recommending related information, it is convenient for users to select interactive content and improve the interaction efficiency.

[0113] The method of the embodiment of the present application is described in detail above, and the device of the embodiment of the present application is provided below.

[0114] and Figure 1 The embodiment shown is consistent with that shown in FIG. Figure 4 , Figure 4 is a structural diagram of an information processing device proposed in this application, such as Figure 4 As shown, the information processing device 400 includes:

[0115] The communication unit 402 is used to receive first request information from the client;

[0116] The processing unit 401 is used to determine the user attribute information corresponding to the first request information; obtain the first reply information of the first request information according to the user attribute information; obtain the second request information associated with the first request information according to the user attribute information;

[0117] The communication unit 402 is further configured to send the first reply information and first response information corresponding to the second request information to the client.

[0118] In a possible example, the information processing device 400 also includes a storage unit 403 for storing a set of historical request records; the first request information includes user identification information, the user attribute information includes a user preference type, and the processing unit 401 is specifically used to obtain request scenario information of the first request information; select the first historical request record corresponding to the user identification information and the request scenario information from the set of historical request records; and determine the user preference type based on the first historical request record.

[0119] In a possible example, the processing unit 401 is specifically used to parse the front-end page corresponding to the first request information to obtain page information of the front-end page; obtain request parameters of the first request information according to the page information; and obtain request scenario information of the first request information according to the request parameters.

[0120] In a possible example, the processing unit 401 is specifically used to search for the third request information corresponding to the first request information from the historical request record set; obtain a first evaluation value of the third reply information corresponding to the third request information based on the user attribute information; if the first evaluation value is greater than or equal to the first threshold, determine that the third reply information is the first reply information of the first request information.

[0121] In a possible example, the processing unit 401 is specifically used to count the first number of times the fourth request information follows the third request information; based on the user attribute information, obtain a second evaluation value of the fourth request information following the first request information; based on the first number of times and the second evaluation value, obtain a third evaluation value of the fourth request information following the first request information; if the association value is greater than or equal to a second threshold, determine that the fourth request information is the second request information.

[0122] In a possible example, the processing unit 401 is specifically used to obtain the fifth request information corresponding to the first time period from the historical request record set if the search for the third request information fails; count the second number of the fifth request information; and send the fifth request information to the client if the second number is greater than or equal to a third threshold.

[0123] In a possible example, the processing unit 401 is also used to obtain second reply information corresponding to the second request information based on the user attribute information; the communication unit 402 is also used to send the first reply information and the second request information to the client, as well as second response information corresponding to the second reply information.

[0124] The detailed execution process of each unit in the information processing device 400 can refer to the execution steps in the aforementioned method embodiment, which will not be repeated here.

[0125] and Figure 1 For details, please refer to Figure 5 , Figure 5 is a schematic diagram of another information processing structure provided by an embodiment of the present application. Figure 5 As shown, the information processing device 500 includes a processor 510 , a memory 520 , a communication interface 530 , and one or at least one program 540 . Figure 4 The related functions implemented by the communication unit 402 shown can be implemented through the communication interface 530. Figure 4 The related functions implemented by the storage unit 403 shown can be implemented by the memory 520. Figure 4 The related functions implemented by the processing unit 401 shown can be implemented by the processor 510.

[0126] The one or at least one program 540 is stored in the memory 520 and is configured to be executed by the processor 510. The program 540 includes instructions for executing the following steps:

[0127] Receiving first request information from a client;

[0128] Determining user attribute information corresponding to the first request information;

[0129] Acquire first reply information of the first request information according to the user attribute information;

[0130] Acquire second request information associated with the first request information according to the user attribute information;

[0131] Sending the first reply information and first response information corresponding to the second request information to the client.

[0132] In a possible example, the first request information includes user identification information, and the user attribute information includes a user preference type. In determining the user attribute information corresponding to the first request information, the program 540 is specifically used to execute the following steps:

[0133] Acquire request scenario information of the first request information;

[0134] Selecting a first historical request record corresponding to the user identification information and the request scenario information from a pre-stored historical request record set;

[0135] The user preference type is determined according to the first historical request record.

[0136] In a possible example, in terms of obtaining the request scenario information of the first request information, the program 540 is specifically used to execute instructions of the following steps:

[0137] Parsing the front-end page corresponding to the first request information to obtain page information of the front-end page;

[0138] Acquire request parameters of the first request information according to the page information;

[0139] The request scenario information of the first request information is obtained according to the request parameter.

[0140] In a possible example, in the aspect of obtaining the first reply information of the first request information according to the user attribute information, the program 540 is specifically used to execute the following steps:

[0141] Searching for third request information corresponding to the first request information from a pre-stored historical request record set;

[0142] Acquire, according to the user attribute information, a first evaluation value of the third reply information corresponding to the third request information;

[0143] If the first evaluation value is greater than or equal to a first threshold, the third reply information is determined to be the first reply information of the first request information.

[0144] In a possible example, in the aspect of acquiring the second request information associated with the first request information according to the user attribute information, the program 540 is specifically used to execute instructions of the following steps:

[0145] Counting the first number of fourth request information after the third request information;

[0146] According to the user attribute information, obtaining a second evaluation value of the fourth request information that is located after the first request information;

[0147] According to the first number of times and the second evaluation value, obtaining a third evaluation value of the fourth request information that is located after the first request information;

[0148] If the correlation value is greater than or equal to the second threshold, it is determined that the fourth request information is the second request information.

[0149] In one possible example, the program 540 is also used to execute instructions for the following steps:

[0150] If searching for the third request information fails, obtaining the fifth request information corresponding to the first time period from the historical request record set;

[0151] Counting the second number of times of the fifth request information;

[0152] If the second number of times is greater than or equal to a third threshold, sending the fifth request information to the client.

[0153] In one possible example, the program 540 is also used to execute instructions for the following steps:

[0154] Acquire second reply information corresponding to the second request information according to the user attribute information;

[0155] The first reply information and the second request information are sent to the client, as well as second response information corresponding to the second reply information.

[0156] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program, which enables a computer to execute part or all of the steps of any method recorded in the method embodiment, and the computer includes a client and a server.

[0157] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program can be operated to cause a computer to execute to implement some or all steps of any method recorded in the method embodiment. The computer program product can be a software installation package, and the computer includes a client and a server.

[0158] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modes involved are not necessarily required by the present application.

[0159] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0160] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as at least one unit or component can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0161] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on at least one network unit. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software program mode.

[0163] If the integrated unit is implemented in the form of a software program model and sold or used as an independent product, it can be stored in a computer-readable memory. According to this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk, etc., and other media that can store program codes.

[0164] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0165] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An information processing method, It is characterized in that include: Receiving first request information from a client; Determining user attribute information corresponding to the first request information; Acquire first reply information of the first request information according to the user attribute information; The first reply information is determined based on a first evaluation value of the third reply information, the third reply information is reply information of the third request information corresponding to the first request information, and the first evaluation value is used to describe the degree of completion of the third reply information in solving the third request information, and the greater the degree of completion, the higher the first evaluation value; Acquire second request information associated with the first request information according to the user attribute information; Sending first response information corresponding to the first reply information and the second request information to the client; The first request information includes user identification information, the user attribute information includes a user preference type, and the determining the user attribute information corresponding to the first request information includes: Parsing the front-end page corresponding to the first request information to obtain page information of the front-end page, and obtaining request parameters of the first request information according to the page information; Acquire request scenario information of the first request information according to the request parameter; Selecting a first historical request record corresponding to the user identification information and the request scenario information from a pre-stored historical request record set; The user preference type is determined according to the first historical request record.

2. The method according to claim 1, It is characterized in that The acquiring, according to the user attribute information, first reply information of the first request information includes: Searching for third request information corresponding to the first request information from a pre-stored historical request record set; Acquire, according to the user attribute information, a first evaluation value of the third reply information corresponding to the third request information; If the first evaluation value is greater than or equal to a first threshold, the third reply information is determined to be the first reply information of the first request information.

3. The method according to claim 2, It is characterized in that The acquiring, according to the user attribute information, second request information associated with the first request information includes: Counting the first number of fourth request information after the third request information; According to the user attribute information, obtaining a second evaluation value of the fourth request information that is located after the first request information; According to the first number of times and the second evaluation value, obtaining a third evaluation value of the fourth request information that is located after the first request information; If the third evaluation value is greater than or equal to the second threshold, the fourth request information is determined to be the second request information.

4. The method according to claim 2, It is characterized in that The method further comprises: If searching for the third request information fails, obtaining the fifth request information corresponding to the first time period from the historical request record set; Counting the second number of times of the fifth request information; If the second number of times is greater than or equal to a third threshold, sending the fifth request information to the client.

5. The method according to claim 1, It is characterized in that The method further includes: Obtaining second reply information corresponding to the second request information according to the user attribute information; Sending the first reply information, the second request information, and second response information corresponding to the second reply information to the client.

6. An information processing device, characterized in that, it includes: A communication unit, configured to receive first request information from a client; A processing unit, configured to determine user attribute information corresponding to the first request information; Obtaining first reply information of the first request information according to the user attribute information; Obtaining second request information associated with the first request information according to the user attribute information; The first reply information is determined based on a first evaluation value of third reply information, where the third reply information is reply information of a third request information corresponding to the first request information, and the first evaluation value is used to describe the degree of completion of the third request information solved by the third reply information. The greater the degree of completion, the higher the first evaluation value; The communication unit is further configured to send the first reply information and first response information corresponding to the second request information to the client; Wherein, the first request information includes user identification information, the user attribute information includes user preference types, and the processing unit determines user attribute information corresponding to the first request information, specifically: Parsing a front-end page corresponding to the first request information to obtain page information of the front-end page, and obtaining request parameters of the first request information according to the page information; Obtaining request scenario information of the first request information according to the request parameters; Selecting a first historical request record corresponding to the user identification information and the request scenario information from a pre-stored set of historical request records; Determining the user preference type according to the first historical request record.

7. An information processing device, characterized in that, it includes a processor, a memory, a communication interface, and one or at least one program. Wherein, the one or at least one program is stored in the memory and is configured to be executed by the processor, and the program includes instructions for executing the steps in the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program enables a computer to execute to implement the method according to any one of claims 1-5.

Images