Commodity information global association method and system in multi-round dialogue process

Abstract

The invention provides a commodity information global association method and system in a multi-round dialogue process, belongs to the technical field of data processing under the Internet industry, and is applied to first terminal equipment of an intelligent customer service system of a merchant user of an e-commerce platform. The method comprises the steps that first dialogue information input by a first consumption user is displayed on a first customer service interface, aiming at the first consumption user, of a merchant user, and the first customer service interface is associated with multiple pieces of historical dialogue information of the first consumption user; first dialogue information is sent to a server, the first dialogue information is associated with second dialogue information, the second dialogue information comprises reply information for consultation items of a target commodity, and the target commodity is a first commodity in the first type of commodities or a second commodity in the second type of commodities; receiving second dialogue information from the server; and displaying the second dialogue information. The accuracy, comprehensiveness and fluency of processing the conversation information of the consumer by the customer service system can be improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of data processing in the Internet industry, and particularly relates to a method and system for globally associating commodity information in a multi-turn dialogue process. BACKGROUND

[0002] At present, the intelligent customer service system of the merchant user of the e-commerce platform, after the user enters the customer service chat interface, the machine customer service generally interacts with the user first, and can answer some standardized and structured questions. However, in practice, the interaction between the user and the platform is usually carried out through multi-turn dialogue. For example, when the user consults the commodity, the user may raise multiple questions and hope that the platform can remember the previous dialogue content, especially the previously recommended commodity, so as to continue to discuss or query the related commodity in the subsequent dialogue.

[0003] Although the current intelligent machine customer service can identify the intention of some user questions and predict the answers based on the previous historical chat information, the intelligent machine customer service cannot provide accurate answer information for the user when the historical chat information is relatively complex and the description information of the reference mode of the historical dialogue associated commodity is contained in the user question description. Even if the human customer service is transferred, the human customer service needs to spend a long time to backtrack the previous chat information and query in the background to give the answer information of the user's demand, and the accuracy and timeliness are difficult to meet the user's demand. SUMMARY

[0004] The application provides a method and system for globally associating commodity information in a multi-turn dialogue process to improve the intelligence and applicability of the dialogue function of the e-commerce machine customer service, and to accurately identify the intention of the dialogue question containing the fuzzy reference of the historical dialogue associated commodity and the consultation matter, and to improve the accuracy, comprehensiveness and fluency of the customer service system in processing the dialogue information of the consumer user.

[0005] In a first aspect, the embodiments of the application provide a method for globally associating commodity information in a multi-turn dialogue process, applied to a first terminal device of an intelligent customer service system of a merchant user of an e-commerce platform, and the method comprises the following steps. A first conversation message entered by a first consumer user is displayed on a first customer service interface of a merchant user for the first consumer user. The first customer service interface is associated with multiple historical conversation messages of the first consumer user. The multiple historical conversation messages include first historical conversation messages for first-category products and second historical conversation messages for second-category products. The first-category products represented by the first historical conversation messages have generated a transaction status, and the transaction status includes at least one of the following: purchase status, exchange status, and return status. The second-category products represented by the second historical conversation messages have not generated the transaction status. The first conversation message includes first description information and second description information. The first description information is expressed in a vague manner as a reference to the historical conversation products. The historical conversation products include the first and second categories of products associated with the multiple historical conversation messages. The second description information is description information of the consultation matter, and the consultation matter refers to a business matter associated with the sale of the product. Sending the first conversation message to a server, the first conversation message being associated with a second conversation message, the second conversation message including a reply to the inquiry regarding a target product, the target product being the first product in the first category of products or the second product in the second category of products; receiving the second conversation information from the server; The second conversation information is displayed.

[0006] In a second aspect, an embodiment of the present application provides an intelligent customer service system, including a first terminal device and a server, wherein: The first terminal device is configured to perform the steps performed by the first terminal device in the first aspect above; The server is used to execute the steps executed by the server in the first aspect above.

[0007] It can be seen that in the embodiment of the application, the first terminal device first displays the first conversation information input by the first consumer user in the first customer service interface of the merchant user for the first consumer user, then sends the first conversation information to the server, the first conversation information is associated with the second conversation information, the second conversation information contains the reply information of the consultation matter for the target commodity, then receives the second conversation information from the server, and finally displays the second conversation information. Compared with the existing shop customer service system which can only predict the intention of the current conversation information of the user based on the previous historical conversation information and output inquiry statements instead of answers, and compared with the existing shop customer service system which can only reply vaguely or jump to manual customer service and wait for a long time when detecting the vague reference and consultation matter containing the historical conversation associated commodity, the intelligent customer service system of the application provides a function of accurately processing the conversation question and answer of the consultation matter containing the historical conversation associated commodity without switching to manual service, thereby improving the intelligence and applicability of the conversation function of the e-commerce machine customer service.

[0008] In addition, the intelligent customer service system of the application can specifically statistically analyze the first type of commodity and the second type of commodity based on the plurality of historical conversation information of the customer service interface, thereby supporting accurate identification of the intention of the conversation question containing the historical conversation associated commodity and the consultation matter, and then outputting the reply information of the consultation matter for the target commodity, thereby improving the accuracy, comprehensiveness and fluency of the customer service system in processing the conversation information of the consumer user. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only constitute some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0010] Figure 1 is a composition schematic diagram of an intelligent customer service system provided by an embodiment of the application; Figure 2 is a structure schematic diagram of a first terminal device provided by an embodiment of the application; Figure 3 is a flowchart of a global commodity information association method in a multi-round conversation process provided by an embodiment of the application; Figure 4 is a first customer service interface schematic diagram provided by an embodiment of the application; Figure 5 is a second customer service interface schematic diagram provided by an embodiment of the application. DETAILED DESCRIPTION

[0011] In order to better understand the technical scheme of the present application, the technical scheme in the embodiments of the present application will be described accurately and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0012] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but can optionally include steps or modules not listed, or can optionally include other steps or modules inherent to the process, method, product or device.

[0013] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification is not necessarily all referring to the same embodiment, nor is it necessarily referring to a preferred or alternative embodiment. It is explicitly and implicitly understood that the embodiments described herein can be combined with other embodiments.

[0014] At present, for the complex historical chat information and the description information of the user problem description containing the reference mode of the historical dialogue associated commodity, the intelligent machine customer service cannot provide accurate answer information for the user. Even if the human customer service is transferred, the human customer service also needs to spend a long time to backtrack the previous chat information, and then query in the background to give the answer information of the user's demand, and the accuracy and timeliness are difficult to meet the user's demand.

[0015] In view of the above problems, the embodiments of the present application provide a method and system for globally associating commodity information in a multi-round dialogue process. The embodiments of the present application will be described in detail below in combination with the drawings.

[0016] Please refer to Figure 1 , Figure 1is a component schematic diagram of an intelligent customer service system provided by an embodiment of the present application. The intelligent customer service system 10 includes a first terminal device 101 of a first consumer user, a server 103, and a second terminal device 102 of a merchant user. The server 103 is in communication connection with the first terminal device 101 and the second terminal device 102 respectively. The first consumer user can input dialogue information through the first terminal device 101, the dialogue information can include relevant inquiry information for a target commodity or a merchant user, and is displayed on a first customer interface. The merchant user can input reply information and commodity recommendation information and the like through the second terminal device 102. The first terminal device 101 and the second terminal device 102 can simultaneously display the first customer interface, realizing communication between the consumer user and the merchant user based on the first customer interface. The server 103 can determine associated second dialogue information based on the first dialogue information of the first terminal device 101, and send the second dialogue information to the second terminal device 102 for display.

[0017] Referring to Figure 2 , Figure 2 is a structural schematic diagram of a first terminal device provided by an embodiment of the present application. The first terminal device 101 includes a processor 120, a memory 130, a communication interface 140, and one or more programs 131, wherein the one or more programs 131 are stored in the above-mentioned memory 130 and are configured to be executed by the above-mentioned processor 120, and the one or more programs 131 include instructions for executing any step in the following method embodiment. In a specific implementation, the processor 120 is configured to execute any step in the following method embodiment executed by the first terminal device, and when performing data transmission such as sending, the communication interface 140 can be selectively called to complete the corresponding operation.

[0018] It should be noted that the structure of the second terminal device 102 and the server 103 can be the same as that of the above-mentioned first terminal device 101, which will not be described here.

[0019] Referring to Figure 3 , Figure 3 is a flowchart of a commodity information global association method in a multi-round dialogue process provided by an embodiment of the present application. The commodity information global association method in the multi-round dialogue process is applied to the first terminal device 101 of the intelligent customer service system 10 of the merchant user of an e-commerce platform. The commodity information global association method in the multi-round dialogue process includes the following steps.

[0020] S201, displaying first dialogue information input by a first consumer user on a first customer interface of a merchant user for the first consumer user.

[0021] The first customer service interface is associated with a plurality of historical dialogue information of the first consumer user, and the plurality of historical dialogue information includes first historical dialogue information of a first type of commodity and second historical dialogue information of a second type of commodity. In a specific implementation, the dialogue information of the first consumer user in the second historical dialogue information can be empty. Alternatively, the dialogue information of the first consumer user in the second historical dialogue information is not empty. In a specific implementation, the first type of commodity can be a commodity for which the consumer user initiates consultation and generates a transaction state. For example, after the user directly jumps to the customer service interface through the commodity detail page of commodity A, the first historical dialogue generates a transaction state. The first type of commodity can also be a commodity for which the merchant user initiates message recommendation, the user clicks the recommendation message to view the commodity, and the dialogue generates a transaction state. In a specific implementation, before the first customer service interface of the merchant user for the first consumer user displays the first dialogue information input by the first consumer user, the method further comprises: detecting that the commodity recommendation function of the first customer service interface is not closed.

[0022] The first type of commodity represented by the first historical dialogue information has generated a transaction state, and the transaction state includes at least one of the following: a purchase state, a replacement state, and a return state. The second type of commodity represented by the second historical dialogue information has not generated the transaction state. When determining whether a commodity has generated a transaction state, it can be determined first whether the historical dialogue corresponding to the commodity includes a corresponding function card, for example, a "return and replacement application" function card. The consumer user can jump to the corresponding function interface by clicking the function card to realize return and replacement. If the corresponding function card is included, it is determined that the commodity is a first type of commodity. Alternatively, the historical dialogue corresponding to the commodity can be matched according to a keyword, for example, the keyword "return" appears in the historical dialogue, and the order state of the commodity is queried to determine whether the commodity is a first type of commodity. The second type of commodity can refer to a commodity for which the consumer user has consulted but has not generated a transaction state, or a commodity for which the merchant user has pushed but the user has not dialogued for the commodity or has not generated a transaction state after the dialogue. For example Figure 4 As shown, Figure 4 is a first customer service interface diagram provided by an embodiment of the present application. The interface diagram includes a plurality of historical dialogues, wherein the commodity for which the consumer user initiates consultation and purchase is a first type of commodity, and the related historical dialogue is first historical dialogue information. The commodity for which the merchant user initiates recommendation is a second type of commodity, and the recommendation message of the merchant user is second historical dialogue information.

[0023] The first dialogue information includes first description information and second description information, the expression mode of the first description information is a fuzzy reference to a historical dialogue commodity, the historical dialogue commodity includes the first type of commodity and the second type of commodity associated with the plurality of historical dialogue information, and the second description information is description information of a consultation matter, the consultation matter refers to a business matter associated with commodity sales. The fuzzy reference refers to that the first dialogue information does not include an explicit commodity name or identity information, etc. For example, the first description information is "this mobile phone", "the shoes bought before", etc. The second description information can be used to consult commodity specification attributes, inventory, preferential treatment, logistics and return and exchange information, etc.

[0024] S202, sending the first dialogue information to the server.

[0025] The first dialogue information is associated with second dialogue information, and the second dialogue information contains reply information of the consultation matter for a target commodity, the target commodity being a first commodity in the first type of commodity or a second commodity in the second type of commodity.

[0026] In a specific implementation, the method further includes: detecting that a commodity recommendation function of the first customer service interface is closed; and then the second dialogue information is created by the server through the following steps: Step a1. History record storage.

[0027] After each round of dialogue, the system stores the user question, the system answer and the involved commodity information (such as commodity ID, commodity name, attribute, etc.) into the history record. For example, the user asks "what is the price of this mobile phone?" in the first round of dialogue, the system answers "the price of this mobile phone is 3999 yuan", and stores the commodity ID (such as "12345") and the commodity name (such as "X mobile phone") into the history record.

[0028] Step a2. Multi-round dialogue rewriting.

[0029] In the latest round of dialogue, the system first analyzes the user input to determine whether it involves a commodity in the historical dialogue. If the user input contains a reference to a historical commodity (such as "this mobile phone"), the system will rewrite the user input to a complete expression according to the history record. For example, the user input "what is the battery capacity of this mobile phone?", the system will rewrite it to "what is the battery capacity of X mobile phone?".

[0030] Step a3. Intention recognition and extraction of commodity ID.

[0031] The system uses an intent recognition model (such as BERT, GPT, etc.) to analyze the rewritten user question and extract the involved product ID. For example, in the user question "What is the battery capacity of X phone?", the system extracts the product ID "12345".

[0032] Step a4. Obtain product information according to product ID.

[0033] The system obtains the detailed information of the product (such as battery capacity, price, color, etc.) from the product database according to the extracted product ID. For example, the system queries the product information corresponding to the product ID "12345" as "X phone, battery capacity 3200mAh".

[0034] Step a5. Generate system answer.

[0035] The system generates an answer based on the user question and the extracted product information. For example: User question: "What is the battery capacity of this phone?" System answer: "The battery capacity of X phone is 3200mAh." That is, for the case where the product proactive recommendation function of the client interface is closed, the plurality of historical dialogue information are all dialogue information between the first consumer user and the current shop user's machine customer service and / or manual customer service, which can be understood as dialogue information with strong association with the first consumer user. Therefore, compared with the foregoing server-side technical solution, the server can also use the above more efficient algorithm steps to create the first dialogue information.

[0036] S203, receiving the second dialogue information from the server.

[0037] In one possible embodiment, the target product is determined by the server by performing the following steps: creating a corresponding relationship set according to the plurality of historical dialogue information, the corresponding relationship set containing a first corresponding relationship between a first identity information sequence and a transaction association label, and a second corresponding relationship between a second identity information sequence and a non-transaction association label; performing transaction association analysis on the first description information and / or the second description information of the first dialogue information to obtain a transaction association analysis result; performing product category analysis on the first description information of the first dialogue information to obtain a product category analysis result; determining the target product according to the corresponding relationship set, the transaction association analysis result, the product category analysis result, and the consultation matter.

[0038] The identity information sequence is used to indicate a specific commodity, and the transaction correlation label is a transaction state of the specific commodity. The identity information of the first type of commodity belongs to the first identity information sequence, and the identity information of the second type of commodity belongs to the second identity information sequence. Since the first type of commodity has a transaction state, the first identity sequence corresponds to the transaction correlation label, and similarly, the second type of commodity has no transaction state, so the second identity sequence corresponds to the non-transaction correlation label. In a specific implementation, the first description information and / or the second description information of the first dialogue information are subjected to transaction correlation analysis to obtain a transaction correlation analysis result, including: performing semantic analysis on the first description information and / or the second description information to determine whether there is a transaction-related semantic in the first description information and / or the second description information. If there is, it is determined that the commodity corresponding to the first dialogue information has transaction correlation. For example, if the semantic analysis result includes "purchased", "returned", and the like, the commodity referred to by the first dialogue information is the first type of commodity, and there is transaction correlation.

[0039] In a specific implementation, when performing commodity category analysis, the first description information can be subjected to syntax analysis to determine a noun phrase corresponding to the first description information, and then the historical commodity categories of the commodities included in the historical dialogue information are obtained. The noun phrase is compared with the historical commodity categories to determine the most relevant historical commodity category as the commodity category corresponding to the first dialogue information. For example, the first description information is "the rock shoes bought before", and it can be known that the noun phrase in this short sentence is "rock shoes". "Rock shoes" appears in the historical dialogue and is most relevant to it, so the commodity category corresponding to the first dialogue information is "rock shoes". In particular, if the first description information does not include a noun phrase and only uses "this" and the like to refer, the commodity in the historical dialogue information that is closest to the first dialogue information is determined as the target commodity.

[0040] It can be seen that in the embodiment, after the transaction correlation analysis and the commodity type analysis of the first dialogue information are performed, the target commodity is determined comprehensively, which can improve the accuracy of the confirmation of the target commodity and improve the intelligence of the dialogue function of the e-commerce machine customer service.

[0041] In one possible embodiment, the creating of the correspondence set according to the plurality of historical dialogue information includes: performing first identity information analysis, coding, and sorting on the first historical dialogue information in chronological order to obtain the first identity information sequence; performing second identity information analysis, coding, and sorting on the second historical dialogue information in chronological order to obtain the second identity information sequence; creating the first correspondence between the first identity information sequence and the transaction correlation label, and the second correspondence between the second identity information sequence and the non-transaction correlation label; and merging the first correspondence and the second correspondence to obtain the correspondence set.

[0042] In the process of obtaining the identity information sequence based on the identity information, the to-be-encoded commodity can be determined based on the historical dialogue information, and then the ID of the to-be-encoded commodity is obtained. Then, it is determined whether the to-be-encoded commodity belongs to the first type of commodity or the second type of commodity based on the above transaction correlation analysis result. If the to-be-encoded commodity belongs to the first type of commodity, the commodity identification code corresponding to the first type of commodity is obtained. In addition, the order number of the to-be-encoded commodity in the commodity category to which it belongs can be determined. The order number can be determined based on the dialogue time of the historical dialogue information. The earlier the dialogue time, the smaller the order number. Then, the identity information of the to-be-encoded commodity is generated based on the ID of the to-be-encoded commodity, the commodity identification code, and the order number. In this way, the first identity information sequence corresponding to the first type of commodity and the second identity information sequence corresponding to the second type of commodity are obtained.

[0043] It can be seen that in the embodiments of the present application, the identity information sequence is determined based on the first historical dialogue information and the second historical dialogue information respectively, which can improve the efficiency of the identity information sequence and ensure the accuracy of the determined identity information sequence.

[0044] In one possible embodiment, the determining the target commodity according to the correspondence set, the transaction correlation analysis result, the commodity category analysis result, and the consultation matter includes: taking the transaction correlation analysis result as a query identifier, querying the correspondence set to obtain an identity information sequence adapted to the transaction correlation analysis result; performing non-relevant identity information elimination on the adapted identity information sequence according to the commodity category analysis result and the consultation matter to obtain a third identity information sequence after non-relevant identity information elimination; and marking the commodity identified by the identity information closest to the current system time in the third identity information sequence as the target commodity.

[0045] In the process of determining the target commodity, the server determines the reply information of the consultation matter for the target commodity, which specifically includes the following steps: rewriting the first dialogue information based on the target commodity, determining whether the logic of the first dialogue information is correct, if correct, obtaining the answer information based on the rewritten first dialogue information and the question and answer model, and then generating the second dialogue information according to the answer information and the target commodity. If the logic of the rewritten first dialogue information is incorrect, for example, the first dialogue information is "what is the memory of rock climbing shoes", the rewritten first dialogue information can be logically corrected. For example, the above first dialogue information with incorrect logic is corrected to "what is the lining of rock climbing shoes". Then, the second dialogue information is generated based on the corrected first dialogue information and the target commodity.

[0046] It can be seen that in the embodiments, the target commodity is determined by comprehensively considering various information, which can improve the accuracy of the determination of the target commodity and enhance the intelligence of the dialogue function of the e-commerce machine customer service.

[0047] S204, display the second dialogue information.

[0048] In one possible implementation, the displaying the second dialogue information comprises: displaying the second dialogue information in a first adjacent dialogue area of the first dialogue information displayed on the first customer service interface, and displaying third historical dialogue information or a dialogue information folding function control in a second adjacent dialogue area of the first dialogue information displayed on the first customer service interface, the third historical dialogue information being historical dialogue information of the target commodity, and the dialogue information hidden by the dialogue information folding function control being historical dialogue information different from the historical dialogue information of the target commodity.

[0049] The first adjacent dialogue area and the second adjacent dialogue area are respectively located on two sides of the first dialogue information, that is, the second dialogue information can be displayed after the first dialogue information, the historical dialogue information of the target commodity before the first dialogue information is displayed before the first dialogue information, and the historical dialogue information of a non-target commodity before the first dialogue information is folded. For example Figure 5 As shown in Figure 5 is a second customer service interface schematic diagram provided by an embodiment of the present application. In the customer service interface, "how to return this table" is first dialogue information, and the historical dialogue information of the table before the first dialogue information is displayed on the interface, and information irrelevant to the table, for example Figure 4 the active recommendation information of the merchant user in the table is folded and not displayed. Then, after the second dialogue information is determined, the second dialogue information is displayed on the other side of the first dialogue information.

[0050] It can be seen that, in the embodiment, when the second dialogue information is displayed, the historical dialogue information of the target commodity is appropriately displayed, which can make the information displayed on the user customer service interface more intuitive and accurate, facilitate the consumption user to trace the target commodity, and improve the communication efficiency.

[0051] In the embodiment of the present application, the first terminal device first displays the first conversation information input by the first consumer user on the first customer service interface of the merchant user for the first consumer user, then sends the first conversation information to the server, the first conversation information is associated with the second conversation information, the second conversation information contains the reply information of the consultation matter for the target commodity, then receives the second conversation information from the server, and finally displays the second conversation information. Compared with the existing store customer service system which can only predict the intention of the current conversation information of the user based on the previous historical conversation information and output inquiry statements instead of answers, and compared with the existing store customer service system which can only reply vaguely or jump to manual customer service and wait for a long time when detecting the fuzzy reference and consultation matter containing the historical conversation associated commodity, the intelligent customer service system of the present application provides a function of accurately processing the conversation problem of the consultation matter containing the historical conversation associated commodity without switching to manual service, thereby improving the intelligence and applicability of the conversation function of the e-commerce machine customer service.

[0052] In addition, the intelligent customer service system of the present application can specifically statistically analyze the first type of commodity and the second type of commodity based on the plurality of historical conversation information of the customer service interface, thereby supporting accurate identification of the intention of the conversation problem containing the fuzzy reference and consultation matter of the historical conversation associated commodity, and then outputting the reply information of the consultation matter for the target commodity, thereby improving the accuracy, comprehensiveness and fluency of the customer service system in processing the conversation information of the consumer user.

[0053] In one possible embodiment, the second conversation information has at least one of the following forms: text information; and picture information; and a preset function card configured with a hyperlink function.

[0054] The hyperlink can be specifically for the related consultation content that the machine customer service cannot accurately obtain, but the commodity page can be quickly clicked by the user to jump to query. For example, the inventory information is displayed on the shoe size page, and the inventory quantity of each shoe size is dynamically displayed, so the user can query the inventory information by clicking the preset function card.

[0055] As can be seen, in the embodiment, the second conversation information can be presented in multiple ways, which can improve the intelligence of the reply and enhance the intuitiveness of the reply information, thereby improving the user experience.

[0056] In one possible embodiment, the text information includes hyperlink information and auxiliary instructions, the hyperlink information is indirect answer information of the consultation matter of the target commodity; wherein the indirect answer information is data information that can be queried by the identity information of the target commodity in the first data set; wherein the first data set contains the target commodity, and the update period of the consultation matter of the target commodity is less than a preset time length.

[0057] In order to avoid the delay problem of real-time jumping to other system servers to obtain the query result (the user's patience is limited in the dialogue scene), the customer service system server generally needs to maintain a query data set. That is, the data information of the query data set is updated synchronously at a predetermined period, such as a server update period of 1 hour or real-time update. For the consultation matters with a shorter update period, a second answer information can be sent to the user in the form of a hyperlink, so that the user jumps to the corresponding interface through the hyperlink to directly obtain real-time information. For example, the consultation matter is the inventory of the target commodity. Since the inventory changes rapidly, the user can be guided to the inventory query page through the hyperlink to obtain more accurate real-time information. Or the user's consultation matter is related to logistics. Since the logistics situation is complex, guiding the user to the logistics interface through the hyperlink can obtain more information.

[0058] It can be seen that, in the embodiment, for the consultation matters with a shorter update period, the user can be guided to view through the hyperlink, which can improve the accuracy of the reply information and improve the user experience.

[0059] In one possible embodiment, the text information includes static text information, the static text information contains first direct answer information of the consultation matter of the target commodity, and the first direct answer information is data information obtained by querying at the latest data update period; wherein the first direct answer information is data information that can be queried in a second data set through the identity information of the target commodity; wherein the update period of the data information of the consultation matter of the target commodity contained in the second data set is greater than or equal to the predetermined period.

[0060] If the consultation matter is the specification problem of the color, capacity, etc. of the commodity, the default update period of such consultation matter can obviously be set to, for example, 1 month, etc. For the server, only the identity information of the target commodity is needed as a query identifier to perform a query operation.

[0061] It can be seen that, in the embodiment, for the consultation matters with a longer update period, the static text information can be used to directly reply to the user's consultation matter, which improves the intuitiveness of the reply information.

[0062] In one possible embodiment, the text information includes static text information, the static text information contains second direct answer information of the consultation matter of the target commodity, and the second direct answer information is data information obtained by automatically performing a query operation according to the predicted indirect answer information of the consultation matter at a first time node, the first time node is an earlier time node than a second time node, and the second time node is a time node at which the first dialogue information is displayed.

[0063] Wherein, after confirming that the dialogue target is the target commodity, the corresponding indirect answer information of the target commodity that the user is likely to inquire can be predicted in advance, and the direct answer information corresponding to the indirect answer information is queried in the background in advance, so as to solve the delay problem of the time-consuming query operation in the real-time dialogue node. Correspondingly, the customer service interface no longer displays the indirect answer information, but directly displays the direct answer information.

[0064] It can be seen that in the embodiment, the predicted inquiry item of the user can also be extracted, and the answer information of the predicted inquiry item is directly output, so that the user can obtain more related inquiries without asking again, and the intelligence of the dialogue function of the e-commerce machine customer service is improved.

[0065] The application provides an intelligent customer service system, which comprises a first terminal device and a server, wherein the first terminal device is configured to perform the steps performed by the first terminal device in any of the above embodiments; and the server is configured to perform the steps performed by the server in any of the above embodiments.

[0066] The above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When realized by software, the above embodiments can be realized in the form of a computer program product in whole or in part. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired or wireless means. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center and the like containing one or more available medium collections. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD) or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0067] The embodiments of the application also provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the computer comprises an electronic device.

[0068] The embodiment of the present application further provides a computer program product, the computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer program being operable to cause a computer to execute some or all of the steps of any of the methods described in the above method embodiments. The computer program product can be a software installation package, and the computer comprises an electronic device.

[0069] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0070] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0071] In several embodiments provided by the present application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic. The division of the above units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical or other forms.

[0072] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0073] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0074] If the above integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable memory. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the above-mentioned method of each embodiment of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0075] A person of ordinary skill in the art can understand that all or part of the steps in the above-mentioned embodiments can be completed by programs instructing relevant hardware, and the programs can be stored in a computer readable memory, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0076] The embodiments of the present application are described in detail above, and the specific examples are applied to the principles and implementation modes of the present application. The above embodiment description 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, the specific implementation mode and application range will be changed; in summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A global association method for product information during a multi-round conversation, characterized in that: A first terminal device of an intelligent customer service system applied to a merchant user of an e-commerce platform, the method comprising: A first conversation message entered by a first consumer user is displayed on a first customer service interface of a merchant user for the first consumer user. The first customer service interface is associated with multiple historical conversation messages of the first consumer user. The multiple historical conversation messages include first historical conversation messages for first-category products and second historical conversation messages for second-category products. The first-category products represented by the first historical conversation messages have generated a transaction status, and the transaction status includes at least one of the following: purchase status, exchange status, and return status. The second-category products represented by the second historical conversation messages have not generated the transaction status. The first conversation message includes first description information and second description information. The first description information is expressed in a vague manner as a reference to the historical conversation products. The historical conversation products include the first and second categories of products associated with the multiple historical conversation messages. The second description information is description information of the consultation matter, and the consultation matter refers to a business matter associated with the sale of the product. Sending the first conversation message to a server, the first conversation message being associated with a second conversation message, the second conversation message including a reply to the inquiry regarding a target product, the target product being the first product in the first category of products or the second product in the second category of products; receiving the second conversation information from the server; The second conversation information is displayed.

2. The method according to claim 1, characterized in that The second dialogue information may be expressed in at least one of the following forms: Text messages; and Image information; and Configure preset function cards with hyperlink function.

3. The method according to claim 2, characterized in that The text information includes hyperlink information and auxiliary instructions, wherein the hyperlink information is indirect answer information of the consultation matter of the target product; The indirect answer information is the data information that can be queried through the identity information of the target product in the first data set; The update cycle of the consultation items of the target product included in the first data set is less than a preset time period.

4. The method according to claim 3, characterized in that The text information includes static text information, and the static text information includes first direct answer information of the consultation item of the target product, and the first direct answer information is data information queried in the latest data update cycle; The first direct answer information is data information in the second data set that can be queried through the identity information of the target product; The update period of the data information of the consultation items of the target product included in the second data set is greater than or equal to the preset time period.

5. The method according to claim 3, characterized in that The text information includes static text information, and the static text information includes the second direct answer information of the consultation matter of the target product. The second direct answer information is data information obtained by automatically executing a query operation at a first time node based on the predicted indirect answer information of the consultation matter. The first time node is a time node earlier than the second time node, and the second time node is the time node for displaying the first dialogue information.

6. The method according to any one of claims 1 to 5, characterized in that The displaying of the second dialogue information includes: displaying the second conversation information in a first adjacent conversation area of ​​the first conversation information displayed on the first customer service interface, and, The third historical conversation information or the conversation information folding function control is displayed in the second adjacent conversation area of ​​the first conversation information displayed on the first customer service interface. The third historical conversation information is the historical conversation information of the target product, and the conversation information hidden by the conversation information folding function control is historical conversation information different from the historical conversation information of the target product.

7. The method according to any one of claims 1 to 5, characterized in that The target product is determined by the server by executing the following steps: Creating a correspondence relationship set based on the plurality of historical conversation information, the correspondence relationship set including a first correspondence relationship between a first identity information sequence and a transaction-related tag, and a second correspondence relationship between a second identity information sequence and a non-transaction-related tag; performing a transaction relevance analysis on the first description information and / or the second description information of the first conversation information to obtain a transaction relevance analysis result; performing a product category analysis on the first description information of the first conversation information to obtain a product category analysis result; The target product is determined according to the corresponding relationship set, the transaction relevance analysis result, the product category analysis result, and the consultation matter.

8. The method according to claim 7, characterized in that The creating a corresponding relationship set according to the plurality of historical conversation information includes: Performing first identity information analysis, encoding, and sorting on the first historical conversation information in conversation chronological order to obtain a first identity information sequence; performing second identity information analysis, encoding, and sorting on the second historical conversation information in conversation chronological order to obtain a second identity information sequence; Creating the first correspondence between the first identity information sequence and the transaction relevance tag, and the second correspondence between the second identity information sequence and the non-transaction relevance tag; The first correspondence relationship and the second correspondence relationship are combined to obtain the correspondence relationship set.

9. The method according to claim 8, characterized in that The determining the target product according to the corresponding relationship set, the transaction relevance analysis result, the product category analysis result, and the consultation matter includes: Using the transaction correlation analysis result as a query identifier, querying the corresponding relationship set to obtain an identity information sequence that matches the transaction correlation analysis result; According to the product category analysis results and the consultation matters, irrelevant identity information is eliminated from the adapted identity information sequence to obtain a third identity information sequence after eliminating irrelevant identity information; and the product identified by the identity information closest to the current system time in the third identity information sequence is marked as the target product.

10. An intelligent customer service system, characterized in that: It includes a first terminal device and a server, wherein: The first terminal device is configured to execute the steps executed by the first terminal device in any one of the methods according to claims 1 to 9; The server is configured to execute the steps executed by the server in any one of the methods according to claims 1-9.

Images