Purchase demand information management method and electronic equipment

Abstract

The embodiment of the invention discloses a purchase demand information management method and electronic equipment. The method comprises the following steps: determining a purchase demand created by a first user; after the first user initiates an inquiry message to a plurality of second users based on the purchase demand, obtaining response contents replied by the plurality of second users, and determining a corresponding purchase demand identifier; and in response to a request submitted by the first user for checking the reply condition of the purchase demand, aggregating and displaying response contents replied by the plurality of second users corresponding to the same purchase demand. Through the embodiment of the invention, the efficiency can be improved, and the labor cost and the time cost are reduced.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a procurement demand information management method and electronic equipment. Background Art

[0002] In e-commerce scenarios related to cross-border trade, buyers usually belong to Class B buyers. Different from Class C buyers (individual consumers or terminal buyers who purchase goods mainly for personal consumption), so-called Class B buyers usually refer to bulk buyers or corporate buyers. They purchase goods in large quantities and may use them for commercial purposes, such as wholesale, resale, etc. Therefore, their shopping patterns and interaction methods on e-commerce platforms will also be different from those of Class C buyers.

[0003] In the above scenario, when purchasing goods, Class B buyers are involved in bulk purchases, exchange rates, raw material costs, and cross-border transportation, and there are also some factory-type merchants among the merchants, etc. Therefore, the prices of goods are usually not fixed, and some merchants' goods may only be sold to certain countries / regions. Therefore, after Class B buyers have purchasing needs, they usually need to first initiate inquiries to merchants through e-commerce platforms. After receiving the inquiry information and understanding the buyer's purchasing needs, the merchant can give a quotation, etc., and reply to the buyer through in-site messages, etc., and then the two parties can discuss specific cooperation based on the quotation.

[0004] However, a Class B buyer may need to send inquiries to multiple merchants for a purchase demand, so that he can make a choice after comparing multiple merchants. In addition, the same Class B buyer may have multiple different purchase requirements, and each purchase requirement may be inquired to multiple merchants. This means that after the same Class B buyer sends an inquiry, he may receive reply information from multiple different merchants. This information may correspond to the same purchase requirement or different purchase requirements, but it will be in the same message list. Buyers need to click to view the details one by one before they can determine which purchase requirements they correspond to, and then sort out the reply content corresponding to the same purchase requirement, and then analyze and compare it. The whole process requires a lot of manpower and time costs. Summary of the invention

[0005] This application provides a procurement demand information management method and electronic equipment, which can improve efficiency and reduce labor costs and time costs.

[0006] This application provides the following solutions:

[0007] A procurement demand information management method, comprising:

[0008] Identify the purchase requirements created by the first user;

[0009] After the first user initiates an inquiry message to multiple second users based on the purchase demand, obtaining response contents replied by the multiple second users and determining corresponding purchase demand identifiers;

[0010] In response to the request submitted by the first user to view the response status of the procurement demand, the response contents of the multiple second users corresponding to the same procurement demand are aggregated and displayed.

[0011] Among them, the response content includes: response content generated by the second user with the assistance of the artificial intelligence AI big model based on the natural language understanding and analysis and summary of the procurement needs.

[0012] Among them, it also includes:

[0013] During the aggregate display, providing an operation option for initiating a conversational communication with the second user;

[0014] After the first user initiates a request for conversational communication with the second user, the AI ​​big model provides the first user with recommended conversational content.

[0015] Among them, it also includes:

[0016] After the first user has completed all or part of the communication with multiple second users corresponding to the same procurement demand, the AI ​​big model generates summary content for the communication contents of the multiple second users, and / or content for multi-dimensional comparison based on the communication contents of different second users.

[0017] The content of the multi-dimensional comparison based on the communication contents of different second users includes at least one of the following:

[0018] Comparison of quoted prices, cost-profit, logistics costs, merchant response enthusiasm, and service capabilities among different second users.

[0019] A method for assisting in generating demand response information, comprising:

[0020] Receiving inquiry information initiated by the first user regarding his / her purchasing needs;

[0021] During the process of the second user replying to the inquiry information, the AI ​​big model is used to perform natural language understanding and analysis and summary on the inquiry information to assist in generating suggestion information about the response content, and / or to generate modification suggestion content after judging the rationality of the response content input by the second user.

[0022] The auxiliary generation of suggestion information about the response content includes:

[0023] Identifying information dimensions related to the purchasing decision included in the inquiry information;

[0024] If the inquiry information lacks information on some information dimensions, when generating the suggestion information, suggestion information on the response content to complete the missing information dimensions is generated.

[0025] Among them, it also includes:

[0026] During the conversation and communication between the second user and the first user, the AI ​​big model provides the second user with recommended conversation content.

[0027] Wherein, the first user and the plurality of second users include users from different countries / regions;

[0028] The method further comprises:

[0029] When receiving a message for dialogue communication with the first user, if there is a time difference and / or language difference, the AI ​​big model is used as an agent to conduct a dialogue with the first user.

[0030] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the methods described above.

[0031] An electronic device, comprising:

[0032] one or more processors; and

[0033] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of any of the methods described above.

[0034] A computer program product comprises a computer program / computer executable instructions, wherein the computer program / computer executable instructions implement the steps of any of the aforementioned methods when executed by a processor in an electronic device.

[0035] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0036] Through the embodiments of the present application, a purchase demand management service can be provided for the first user in the commodity information service system. Through this management service, the first user can create a specific purchase demand in the system, and then can initiate an inquiry message to multiple second users based on the purchase demand. The system can then obtain the response content of the multiple second users' replies and determine the corresponding purchase demand identifier. After the first user submits a request to view the reply status of the purchase demand through the above-mentioned management service, the response content of the multiple second users' replies corresponding to the same purchase demand can be aggregated and displayed. In this way, the first user can aggregate multiple different response contents corresponding to the same purchase demand together for display, thereby facilitating the first user to compare and analyze multiple different response contents, which is conducive to improving efficiency and reducing labor costs and time costs.

[0037] In a preferred embodiment, during the process of the second user replying to the response content, the response content can also be replied with the assistance of the AI ​​big model, so as to improve the reply quality of the response content. During the conversational communication between the first user and the second user, the AI ​​big model can also provide recommended speech techniques to both parties. After the first user has completed the communication with multiple second users corresponding to the same procurement demand, the AI ​​big model can also summarize or compare the communication content of multiple different second users corresponding to the same procurement demand to facilitate the first user to view.

[0038] Of course, any product implementing the present application does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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 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.

[0040] Figure 1 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0041] Figure 2 is a flow chart of the first method provided in an embodiment of the present application;

[0042] Figure 3 is a flow chart of the second method provided in an embodiment of the present application;

[0043] Figure 4 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0045] First of all, it should be noted that in the prior art, after a Class B buyer (which can be referred to as a "first user" in the embodiment of this application) generates a purchasing demand, it is usually by searching for related goods in a cross-border commodity information service system (i.e., a cross-border e-commerce platform, etc.) to find a merchant (also referred to as a supplier, which can be referred to as a "second user" in the embodiment of this application) of the related goods and initiate an inquiry. In other words, the specific purchasing demand of the specific first user will not be instantiated in a specific cross-border e-commerce platform. In other words, only the first user knows what his purchasing demand is, and then roughly determines the goods that meet the demand through various methods (including collecting or understanding some commodity information from some e-commerce platforms for C-end consumers, or based on his own experience, "expert" evaluations in short video platforms, etc.), and then searches for the same product in the cross-border e-commerce platform. If found, an inquiry can be initiated to the corresponding second user, and so on. This also leads to the fact that the cross-border e-commerce platform does not actually know the corresponding relationship between the purchasing demand and the inquiry information, and it is even more impossible to know which second users the first user has initiated inquiries to for the same purchasing demand. This is also the main reason why in the prior art, the first user can only click one by one in the message list to view the second user's reply messages, and then manually sort and compare them. In addition, in the prior art, whether it is the first user initiating an inquiry, the second user responding, the conversation between the first user and the second user, and then the comparison after the first user receives the response content or communicates with the second user, etc., it usually relies on manual work.

[0046] In view of the above situation, in the embodiment of the present application, in order to help buyers and sellers improve efficiency and reduce costs in the inquiry and reply process, a corresponding solution is provided. In this solution, first, for the buyer (which can be referred to as the "first user" in the embodiment of the present application), a purchase demand management interface can be provided for the first user in the system such as the cross-border e-commerce platform. After the first user generates a purchase demand, the purchase demand can be created through the management interface, including inputting the category information of the goods to be purchased, the target market information (that is, after the Class B buyer purchases the specific goods through the current cross-border e-commerce platform, the target countries or regions to which these goods need to be sold), etc., after which the system can create a unique identifier for the specific purchase demand, so that the system side can mark the specific purchase demand of the user. In an optional manner, the system can also recommend information about related goods to the first user for the purchase demand of the first user, or can directly initiate a search based on the category information associated with the purchase demand, and display the search results to the first user. The first user can browse these recommended or searched goods, select some of the intended goods, and initiate an inquiry to the corresponding merchant (also referred to as a supplier, which can be referred to as the "second user" in the embodiment of the present application). After the second user receives the inquiry information, he can reply to the first user with a response message. Afterwards, if the first user needs to view the second user's reply, he can directly initiate a viewing request through the above-mentioned management interface. Correspondingly, the response contents replied by multiple different second users can be aggregated and displayed in the interface based on procurement needs. In other words, the response contents replied by multiple different second users corresponding to the same procurement demand will be aggregated together for display, so that the first user no longer needs to search for the response content one by one in the message list interface. Among them, since in a cross-border scenario, the first user and multiple second users may come from different countries, therefore, in the process of aggregating and displaying the response contents replied by multiple different second users, the response contents replied by multiple second users in different languages ​​can also be translated and then aggregated for display.

[0047] In addition, in the specific implementation process, an AI (Artificial Intelligence) big model can also be introduced to help the first user and the second user complete the above-mentioned inquiry and / or response process. Among them, the so-called AI big model refers to a deep learning model containing massive parameters. This AI big model is large in scale and can store and process a large amount of information, thereby achieving higher performance in various tasks. Therefore, relying on the powerful natural language text understanding and logical thinking ability of the pre-trained AI big model, it can help the second user to provide relevant suggestions in the process of replying to the response content, or make a reasonable judgment on the response content of the second user to improve the quality of the response content; in addition, after the first user receives the response content of the second user, he may also communicate with the second user. During this communication process, the AI ​​big model can also recommend dialogue words for both parties. Furthermore, after the communication with multiple second users corresponding to the same procurement demand has been completed or partially completed, the communication content of multiple different users corresponding to the same procurement demand can be summarized through the AI ​​big model, or the communication content of multiple different second users can be compared in multiple dimensions, such as quotation price comparison, cost profit comparison, logistics cost comparison, merchant response enthusiasm comparison, merchant salesperson service ability comparison, etc.

[0048] Among them, regarding the AI ​​big model, the AI ​​big language model can be used specifically. Of course, on the basis of the open source AI big model, the AI ​​big model can be fine-tuned using the data in the relevant scenarios of the embodiments of the present application, so that the AI ​​big model can not only have the original basic knowledge base, but also obtain some general knowledge bases in the cross-border e-commerce scenario. In addition, the AI ​​big model can be fine-tuned according to some relevant data of the specific second user, so that the AI ​​big model obtains the special knowledge base of the specific second user, etc. Of course, after introducing the special knowledge base of a specific second user, the AI ​​big model becomes a proprietary model of the second user and can be used exclusively for serving the second user.

[0049] Through the above method, the response content of the second user's reply can be aggregated according to the procurement requirements, and the AI ​​big model can be used to assist the first user to improve the communication effect and efficiency, assist the second user to understand the first user's needs, assist the second user to generate response content such as quotation sheets, assist the first user to summarize or compare the communication results, etc. Through the above method, the time and labor costs of the first user can be reduced, which is conducive to improving the quality of the response content of the second user's reply. In addition, by summarizing and comparing the responses or communication content of multiple different second users corresponding to the same procurement requirement, the decision-making confidence and speed of the first user can be improved.

[0050] From the perspective of system architecture, Figure 1 As shown, the embodiment of the present application can provide procurement demand management services for first users such as Class B buyers in a cross-border commodity information service system (usually referred to as a cross-border e-commerce platform, or an international site of an e-commerce platform, etc.). The first user can create a procurement demand in the system. After the system searches for or recommends commodities based on specific procurement demands, the first user can initiate an inquiry to the second user based on the specific commodity. In this process, the AI ​​big model can be used to help the second user generate relevant suggestions on the response content and make a reasonable judgment on the response content of the second user. On the first user side, the response content of multiple second users corresponding to the same procurement demand can also be aggregated and displayed. When the first user needs to communicate with a second user, the AI ​​big model can be used to help the first user and the second user provide suggestions for both parties during the dialogue and communication process. The AI ​​big model can be used to help the first user summarize or compare the dialogue and communication content of multiple second users, and so on.

[0051] The specific implementation scheme provided in the embodiments of the present application is described in detail below.

[0052] Embodiment 1

[0053] First, this embodiment 1 provides a method for managing procurement demand information from the perspective of a first user (ie, a Class B buyer who initiates a procurement demand, etc.), see Figure 2 , the method may specifically include:

[0054] S201: Determine the purchase demand created by the first user.

[0055] In an embodiment of the present application, when the first user is purchasing goods through a cross-border e-commerce platform, a purchase demand management interface can be provided for the first user, through which an entry for creating purchase demands can be provided. Therefore, the first user can first create a specific purchase demand in the system. Specifically, the specific category information of the goods to be purchased can be specified in the purchase demand details. In addition, other information can also be set in the purchase demand details, for example, including the target sales market of the purchased goods (usually represented by the target country or region, etc.), etc.

[0056] S202: After the first user initiates an inquiry message to multiple second users based on the purchase demand, the response contents of the multiple second users are obtained, and the corresponding purchase demand identifiers are determined.

[0057] After the first user creates a specific purchase demand, the first user can initiate product selection by clicking the "Go to Product Selection" button on the purchase demand details page, and the cross-border product information service system can recommend potentially suitable products to the user through a product list page, or provide search results based on product category information associated with the purchase demand. Afterwards, the first user can also select some products from this product list page to add to the comparison. After comparing multiple products on the product comparison page, the first user can choose to initiate an inquiry to the second user (ie, merchant or supplier) corresponding to one or some specific products. Alternatively, the first user can also directly initiate an inquiry to the second user associated with one or some specific products from the above-mentioned product list page, and so on.

[0058] Since the user's product selection and inquiry process starts with the creation of a purchase demand, when an inquiry message is initiated to a second user associated with a certain product, the specific inquiry message can carry an associated purchase demand identifier. In this way, the system can determine which inquiry messages are associated with the same purchase demand based on the purchase demand identifier associated with the specific inquiry message. Correspondingly, after the second user receives the inquiry message, when replying, the above purchase demand identifier can also be carried in the reply response message. Therefore, after receiving the response message of the specific second user, the system can determine the purchase demand identifier associated with the response content in the response message through the purchase demand identifier carried therein.

[0059] S203: In response to the request submitted by the first user to view responses to the procurement requirement, aggregate and display the response contents of the multiple second users' responses corresponding to the same procurement requirement.

[0060] After the first user sends an inquiry message, if he needs to view the reply of the second user, he can also initiate a request through the relevant entrance provided in the aforementioned procurement demand management interface. Accordingly, the response contents of multiple second users' replies corresponding to the same procurement demand can be aggregated and displayed. For example, in specific implementation, after the first user initiates a specific viewing request, a list of procurement demands associated with the first user can be displayed. The user can first select a procurement demand from it, and then an interface for aggregating and displaying multiple response contents associated with the procurement demand can be displayed. In this way, since multiple different response contents corresponding to the same procurement demand can be aggregated into the same interface for display together, the first user no longer needs to search in the message interface, which facilitates the first user to compare and view multiple different response contents.

[0061] It should be noted here that after the second user receives a specific inquiry request, in the process of inputting the response content, the AI ​​big model can also help the second user to generate the response content. For example, the AI ​​big model can generate suggestion information about the reply content, and / or, the modification suggestion content generated after the rationality judgment of the reply content input by the second user, etc., and the specific content generated depends on the prompt information (i.e., prompt) input to the AI ​​big model. Among them, the suggestion information about the reply content can specifically include the suggested quotation, etc. In addition, in the specific implementation, since the first user usually needs to refer to information on multiple different dimensions in the process of making a purchasing decision, including price, the production capacity of the second user, delivery time, transportation method, etc., but the first user may only inquire about some of the dimensions when initiating an inquiry. At this time, the AI ​​big model can understand the inquiry information of the first user, determine which dimensions are included, and also determine which dimensions are missing. In the process of the second user's response, the AI ​​big model can prompt the second user to respond to these missing dimensions together, so that the response content can contain more key information on more dimensions. The quality of such response content will be higher, which is conducive to reducing subsequent communication costs.

[0062] In addition, when the AI ​​big model assists the second user in generating the response content, it can also generate the modification suggestion content after judging the rationality of the response content input by the second user. That is to say, after the second user enters certain response content, the AI ​​big model can be used to judge the rationality of such response content. For example, it can be combined with the current market conditions to judge whether the second user's quotation is too high, etc. If so, a more reasonable suggested quotation range can be given, etc. In short, with the assistance of the AI ​​big model, the efficiency and quality of the response content replied by the second user can be effectively improved. Afterwards, the specific response content will be replied to the first user.

[0063] After viewing the response content of the second user, the first user may need to have a conversational communication with the second user. Therefore, in the process of aggregate display, an operation option for initiating a conversational communication with the second user may be provided to facilitate the first user to initiate a conversational communication with the second user. In specific implementation, assuming that the response content of multiple second users is displayed in the same interface in the form of different information cards, etc., an operation option mentioned above may be provided in each information card, so that the first user can initiate conversations with different second users respectively, and so on.

[0064] After the first user initiates a request for a conversational communication with the second user, during the conversation between the two parties, the AI ​​big model can also provide the first user with recommended conversational content. For example, the AI ​​big model can recommend specific questions to be asked and specific question description methods based on a specific knowledge base. Of course, the AI ​​big model can also provide recommended conversational content for the second user.

[0065] In addition, since the first user and the second user may come from different countries / regions in a cross-border scenario, there may be some obstacles between the two parties in terms of time difference or language. For example, when the first user initiates a request for dialogue and communication to a second user, it may be the night rest time in the country / region where the second user is located. At this time, the second user will not be able to reply in time. Therefore, in view of the above situation, the embodiment of the present application can also provide an AI proxy service for the second user, that is, when the first user initiates a dialogue and communication request and the second user cannot reply in time, the AI ​​big model can be used as an agent to have a dialogue with the first user. Of course, in the specific implementation, it can be that when the second user has opened the proxy service, the AI ​​big model acts as the agent of the second user to have a dialogue with the first user. Among them, when the second user opens the above-mentioned proxy service, the conditions for using the AI ​​agent can also be configured. For example, if the time when the first user initiates the dialogue request is within a certain time period, the AI ​​agent is used to reply, and so on.

[0066] After the first user has completed all or part of the communication with multiple second users corresponding to the same purchasing demand, the AI ​​big model can also generate summary content for the communication content of multiple second users, and / or content based on multi-dimensional comparison of the communication content of different second users. For example, the communication content of each second user can be summarized separately, and the content of multiple rounds of dialogue can be summarized in summary form, so that the first user can quickly understand the content of the dialogue between the two parties. In addition, the communication content of different second users can also be compared, and this comparison can include comparisons in multiple dimensions, such as quotation price comparison, cost-profit comparison, logistics cost comparison, merchant response enthusiasm comparison, merchant salesman service ability comparison, etc. Among them, the merchant response enthusiasm, merchant salesman service ability, etc. can also be analyzed and understood by the AI ​​big model after reasoning to draw conclusions.

[0067] It should be noted that in the above content, when the second user needs to generate a quotation or other reply content after receiving the inquiry demand, or when the second user receives the first user's dialogue communication request and has a dialogue with the first user, the AI ​​big model mainly acts as the "assistant" of the second user to help the second user complete the generation of the reply content or the rationality judgment, or to help the second user recommend the words in the dialogue communication, etc. In the specific implementation, especially when the AI ​​big model is trained to be "intelligent" enough, the AI ​​big model may directly replace the second user to generate specific reply content such as a quotation, or directly have a dialogue with the first user, which is not limited here.

[0068] In summary, through the embodiments of the present application, a procurement demand management service can be provided for the first user in the commodity information service system. Through this management service, the first user can create a specific procurement demand in the system, and then can initiate an inquiry message to multiple second users based on the procurement demand. The system can then obtain the response content of the multiple second users' replies and determine the corresponding procurement demand identifier. After the first user submits a request to view the response status of the procurement demand through the above-mentioned management service, the response content of the multiple second users' replies corresponding to the same procurement demand can be aggregated and displayed. In this way, the first user can aggregate multiple different response contents corresponding to the same procurement demand together for display, thereby facilitating the first user to compare and analyze multiple different response contents, which is conducive to improving efficiency and reducing labor costs and time costs.

[0069] In a preferred embodiment, during the process of the second user replying to the response content, the response content can also be replied with the assistance of the AI ​​big model, so as to improve the reply efficiency and quality of the response content. During the conversational communication between the first user and the second user, the AI ​​big model can also provide recommended speech techniques to both parties. After the first user has completed the communication with multiple second users corresponding to the same procurement demand, the AI ​​big model can also summarize or compare the communication content of multiple different second users corresponding to the same procurement demand for the convenience of the first user to view.

[0070] Embodiment 2

[0071] This second embodiment provides a method for assisting in generating demand response information for the second user, that is, the merchant or supplier. Figure 3 , the method may specifically include:

[0072] S301: receiving inquiry information initiated by a first user regarding his / her purchasing needs;

[0073] S302: When the second user is replying to the inquiry information, the inquiry information is understood and analyzed and summarized by the AI ​​big model in natural language to generate suggestion information about the response content, and / or the modification suggestion content is generated after the rationality of the response content input by the second user is judged.

[0074] Specifically, when generating suggestion information about the response content, the information dimensions related to the procurement decision included in the inquiry information can be identified; if the inquiry information lacks information on some information dimensions, then when generating the suggestion information, suggestion information on the reply content that completes the missing information dimensions can be generated.

[0075] In addition, during the process of dialogue and communication with the first user, the AI ​​big model can also provide the second user with recommended dialogue content.

[0076] For the parts not described in detail in the second embodiment, please refer to the description of the first embodiment and other parts of this specification, which will not be repeated here.

[0077] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0078] Corresponding to the first embodiment, the embodiment of the present application further provides a procurement demand information management device, which may include:

[0079] A purchase demand determination unit, used to determine the purchase demand created by the first user;

[0080] a response content acquisition unit, configured to acquire the response contents replied by the plurality of second users after the first user initiates an inquiry message to the plurality of second users based on the procurement demand, and determine the corresponding procurement demand identifier;

[0081] The response content aggregation and display unit is used to respond to the request submitted by the first user to view the response status of the procurement demand, and aggregate and display the response content of the multiple second users' replies corresponding to the same procurement demand.

[0082] Among them, the response content includes: response content generated by the second user with the assistance of the artificial intelligence AI big model based on the natural language understanding and analysis and summary of the procurement needs.

[0083] In addition, the device may also include:

[0084] a dialogue option providing unit, configured to provide an operation option for initiating a dialogue communication with the second user during the aggregate display process;

[0085] The speech content recommendation unit is used to provide the first user with recommended dialogue speech content through the AI ​​big model after the first user initiates a request for conversational communication with the second user.

[0086] Furthermore, the device may further include:

[0087] The communication content summary unit is used to generate summary content for the communication contents of multiple second users through the AI ​​big model after the first user has completed all or part of the communication with multiple second users corresponding to the same procurement demand, and / or generate content based on multi-dimensional comparison of the communication contents of different second users.

[0088] The content of the multi-dimensional comparison based on the communication contents of different second users includes at least one of the following:

[0089] Comparison of quoted prices, cost-profit, logistics costs, merchant response enthusiasm, and service capabilities among different second users.

[0090] Corresponding to the second embodiment, the embodiment of the present application further provides a device for assisting in generating demand response information, which may include:

[0091] An inquiry information receiving unit, configured to receive inquiry information initiated by a first user in response to his / her purchasing needs;

[0092] The reply content auxiliary generation unit is used to perform natural language understanding and analysis and summary of the inquiry information through the AI ​​big model during the process of the second user replying to the inquiry information, to assist in generating suggestion information about the response content, and / or to generate modification suggestion content after judging the rationality of the response content input by the second user.

[0093] The reply content auxiliary generation unit may be specifically used for:

[0094] Identifying information dimensions related to the purchasing decision included in the inquiry information;

[0095] If the inquiry information lacks information on some information dimensions, when generating the suggestion information, suggestion information on the response content to complete the missing information dimensions is generated.

[0096] In addition, the device may also include:

[0097] The speech content recommendation unit is used to provide recommended dialogue speech content to the second user through the AI ​​big model during the process of the second user communicating with the first user.

[0098] Wherein, the first user and the plurality of second users include users from different countries / regions;

[0099] The device may also include:

[0100] The agent reply unit is used to, when receiving a message from the first user for dialogue communication, conduct a dialogue with the first user through the AI ​​big model as an agent if there is a time difference and / or language difference.

[0101] In addition, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0102] And an electronic device, comprising:

[0103] one or more processors; and

[0104] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of the aforementioned method embodiments.

[0105] A computer program product includes a computer program / computer executable instructions, which, when executed by a processor in an electronic device, implement the steps of the method described in the aforementioned method embodiment.

[0106] in, Figure 4 The architecture of the electronic device is shown as an example, which may include a processor 410, a video display adapter 411, a disk drive 412, an input / output interface 413, a network interface 414, and a memory 420. The processor 410, the video display adapter 411, the disk drive 412, the input / output interface 413, the network interface 414, and the memory 420 may be communicatively connected via a communication bus 430.

[0107] Among them, the processor 410 can be implemented by a general-purpose CPU (Central Processing Unit, processor), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., to execute relevant programs to implement the technical solution provided in this application.

[0108] The memory 420 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 420 can store an operating system 421 for controlling the operation of the electronic device 400, and a basic input and output system (BIOS) for controlling the low-level operation of the electronic device 400. In addition, a web browser 423, a data storage management system 424, and a procurement demand information management processing system 425, etc. can also be stored. The above-mentioned procurement demand information management processing system 425 can be an application program that specifically implements the operations of the aforementioned steps in the embodiment of the present application. In short, when the technical solution provided by the present application is implemented by software or firmware, the relevant program code is stored in the memory 420 and is called and executed by the processor 410.

[0109] The input / output interface 413 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0110] The network interface 414 is used to connect to a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0111] The bus 430 comprises a pathway for transmitting information between the various components of the device (eg, the processor 410, the video display adapter 411, the disk drive 412, the input / output interface 413, the network interface 414, and the memory 420).

[0112] It should be noted that, although the above device only shows a processor 410, a video display adapter 411, a disk drive 412, an input / output interface 413, a network interface 414, a memory 420, a bus 430, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include components necessary for implementing the solution of the present application, and does not necessarily include all the components shown in the figure.

[0113] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0114] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0115] The above is a detailed introduction to the procurement demand information management method and electronic device provided by this application. This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this 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 limiting this application.

Claims

1. A method for managing procurement demand information, characterized in that: include: Identify the purchase requirements created by the first user; After the first user initiates an inquiry message to multiple second users based on the purchase demand, obtaining response contents replied by the multiple second users and determining corresponding purchase demand identifiers; In response to the request submitted by the first user to view the replies to the procurement demand, the response contents of the multiple second users corresponding to the same procurement demand are aggregated and displayed.

2. The method according to claim 1, characterized in that The response content includes: response content generated by the second user with assistance based on the natural language understanding and analysis and summary of the procurement needs by the artificial intelligence AI big model.

3. The method according to claim 1, characterized in that Also includes: During the aggregate display, providing an operation option for initiating a conversational communication with the second user; After the first user initiates a request for conversational communication with the second user, the AI ​​big model provides the first user with recommended conversational content.

4. The method according to claim 1, characterized in that: Also includes: After the first user has completed all or part of the communication with multiple second users corresponding to the same procurement demand, the AI ​​big model generates summary content for the communication contents of the multiple second users, and / or content for multi-dimensional comparison based on the communication contents of different second users.

5. The method according to claim 4, characterized in that The content of the multi-dimensional comparison based on the communication contents of different second users includes at least one of the following: Compare the quoted prices, cost-profit, logistics costs, merchant response enthusiasm, and service capabilities of different second users.

6. A method for assisting in generating demand response information, characterized in that: include: Receiving inquiry information initiated by the first user regarding his / her purchasing needs; During the process of the second user replying to the inquiry information, the AI ​​big model is used to perform natural language understanding and analysis and summary on the inquiry information to assist in generating suggestion information about the response content, and / or to generate modification suggestion content after judging the rationality of the response content input by the second user.

7. The method according to claim 6, characterized in that The auxiliary generation of suggestion information about the response content includes: Identifying information dimensions related to the purchasing decision included in the inquiry information; If the inquiry information lacks information on some information dimensions, when generating the suggestion information, suggestion information on the response content to complete the missing information dimensions is generated.

8. The method according to claim 6, characterized in that Also includes: During the conversation and communication between the second user and the first user, the AI ​​big model provides the second user with recommended conversation content.

9. The method according to claim 6, characterized in that The first user and the plurality of second users include users from different countries / regions; The method further comprises: When receiving a message for dialogue communication with the first user, if there is a time difference and / or language difference, the AI ​​big model is used as an agent to conduct a dialogue with the first user.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 9 are implemented.

11. An electronic device, characterized in that: include: one or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of claims 1 to 9.

12. A computer program product comprising a computer program / computer executable instructions, characterized in that: When the computer program / computer executable instructions are executed by a processor in an electronic device, the steps of the method according to any one of claims 1 to 9 are implemented.

Images