Information generation method, device, equipment, storage medium and program product

Abstract

The present disclosure provides an information generation method, apparatus, electronic device, storage medium, and program product, relating to the field of artificial intelligence technology, and more specifically, to the field of intelligent recommendation technology. The method comprises: determining the demand type of demand information; in response to the demand type being a business demand, determining the business attributes of the demand information; in response to the business attributes of the demand information being a target service type business, extracting keywords from the demand information; matching the keywords with the collected service information of the service provider; and generating a business recommendation result. This method can achieve accurate information matching.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the field of intelligent recommendation technology, and more particularly to an information generation method, device, electronic device, and computer-readable storage medium. Background Art

[0002] With the advent of the information age, information technology is gradually penetrating every aspect of society and changing people's lifestyles. The Internet provides a vast amount of information resources and has become an important channel for people to obtain information. It allows people to access and obtain various types of information anytime and anywhere, greatly enriching the ways and methods people obtain information. Summary of the Invention

[0003] The embodiments of the present disclosure provide an information generation method, device, electronic device, computer-readable storage medium, and computer program product, which can achieve accurate information matching.

[0004] In a first aspect, an embodiment of the present disclosure proposes an information generation method, including: determining the demand type of demand information; in response to the demand type being a business demand, determining the business attributes of the demand information; in response to the business attributes of the demand information being a target service type business, extracting keywords of the demand information, matching the keywords with the collected service information of the service provider, and generating a business recommendation result.

[0005] In a second aspect, embodiments of the present disclosure provide an information generation device, comprising: a first determination module configured to determine a demand type of demand information; a second determination module configured to, in response to the demand type being a business demand, determine a business attribute of the demand information; and a first generation module configured to, in response to the business attribute of the demand information being a target service type business, extract keywords from the demand information, perform business matching on the keywords with collected service information of service providers, and generate business recommendation results.

[0006] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the information generation method described in any implementation method in the first aspect when executing the instructions.

[0007] In a fourth aspect, an embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, which are used to enable a computer to implement the information generation method described in any implementation manner in the first aspect when executed.

[0008] In a fifth aspect, an embodiment of the present disclosure provides a computer program product comprising a computer program, which, when executed by a processor, can implement the information generation method described in any implementation manner in the first aspect.

[0009] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Other features, objects and advantages of the present disclosure will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following drawings:

[0011] Figure 1 is an exemplary system architecture in which the present disclosure may be applied;

[0012] Figure 2 A flowchart of an information generation method provided in an embodiment of the present disclosure;

[0013] Figure 3 A flowchart of another information generation method provided by an embodiment of the present disclosure;

[0014] Figure 4 A flowchart of another information generation method provided in an embodiment of the present disclosure;

[0015] Figure 5 A flowchart of another information generation method provided in an embodiment of the present disclosure;

[0016] Figure 6 A structural block diagram of an information generating device provided in an embodiment of the present disclosure;

[0017] Figure 7 A schematic structural diagram of an electronic device suitable for executing an information generation method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other unless there is a conflict.

[0019] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0020] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the information generation method, apparatus, electronic device, and computer-readable storage medium disclosed herein can be applied.

[0021] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0022] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications for enabling information communication between the terminal devices 101, 102, and 103 and server 105 can be installed, such as information matching applications, information generation applications or platforms, and instant messaging applications. Various client applications and intelligent interactive applications, such as information generation applications and information matching applications, can be installed on terminal devices 101, 102, and 103.

[0023] Terminal devices 101, 102, 103 and server 105 can be either hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, laptop computers, and desktop computers. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules, or as a single software or software module, and are not specifically limited here. When server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software or software modules, or as a single software or software module, and are not specifically limited here.

[0024] The server 105 can provide various services through various built-in applications. Taking the information matching application that can generate information as an example, the server 105 can implement at least the following steps when running the information matching application: determining the demand type of the demand information; in response to the demand type being a business demand, determining the business attributes of the demand information; in response to the business attributes of the demand information being a target service type business, extracting keywords from the demand information; matching the keywords with the collected service information of the service provider to generate a business recommendation result. This method can achieve accurate information matching.

[0025] It should be noted that the demand information and / or service information can be obtained from the terminal devices 101, 102, and 103 via the network 104. In addition to obtaining the service information from the terminal devices 101, 102, and 103 via the network 104, the service information can also be pre-stored locally on the server 105 in various ways. Therefore, when the server 105 detects that such data is already stored locally, it can choose to directly obtain such data from the local storage.

[0026] Because generating business recommendation results, screening results, and query results requires a significant amount of computing resources and significant computational power, the information generation methods provided in the subsequent embodiments of this disclosure are generally executed by a server 105 possessing significant computing power and resources. Accordingly, the information generation device is generally also located within the server 105. However, it should also be noted that, if terminal devices 101, 102, and 103 also possess sufficient computing power and resources, the terminal devices 101, 102, and 103 may also utilize information generation applications or information matching applications installed thereon to perform the various computations previously assigned to the server 105, thereby outputting the same results as the server 105. In particular, in the presence of multiple terminal devices with varying computing power, if the information generation application or information matching application determines that the terminal device it is in possesses significant computing power and significant remaining computing resources, it may allow the terminal device to perform the aforementioned computations, thereby appropriately alleviating the computational pressure on the server 105. Accordingly, the information generation device may also be located within the terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also not include the server 105 and the network 104 .

[0027] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0028] Please refer to Figure 2 , Figure 2 This is a flowchart of an information generation method provided by an embodiment of the present disclosure, wherein process 200 includes the following steps:

[0029] Step 201: Determine the requirement type of the requirement information.

[0030] Illustratively, the demand information may include, but is not limited to, one or more of user demand, user information, and business cooperation requirements.

[0031] Optionally, user needs may refer to specific needs of a user (individual or enterprise, etc.). Business cooperation requirements may refer to specific business requirements within enterprise-oriented needs. User information may refer to basic user information, such as name, contact number, email address, mailing address, business scope, enterprise code, qualification information, and / or enterprise website.

[0032] In this embodiment, the execution subject of the information generation method (eg Figure 1 The server 105 shown determines the demand type of the demand information, classifies the demands, and provides matching results for different types of demands.

[0033] Step 202: In response to the requirement type being a business requirement, determine the business attribute of the requirement information.

[0034] Optionally, demand types may include, but are not limited to, business demands and query demands. Business demands may refer to scenario-based demands such as business cooperation, product purchases, service consultations, and franchises, while query demands may refer to information queries and searches.

[0035] After the execution entity confirms that the demand type of the demand information is a business demand, it further determines the business attributes of the demand information to provide a specific recommendation result.

[0036] Step 203: In response to the business attribute of the demand information being a target service type business, extract keywords from the demand information, perform business matching on the keywords with the collected service information of the service provider, and generate a business recommendation result.

[0037] Optionally, the target service business may refer to business such as purchasing goods, service consultation, etc.

[0038] For the demand information of the target service type business, the above-mentioned execution entity performs word slot extraction, extracts the keywords of the preset slots of the demand information, and performs business matching analysis on the extracted keywords with the collected service information of one or more service providers based on the artificial intelligence algorithm to generate business recommendation results. The business recommendation results may include but are not limited to matching service providers and / or services that match the demand.

[0039] In some embodiments, service providers may include businesses, advertisers, verified individuals, and the like. Service information may include, but is not limited to, one or more of the following: service type, service scope, service price, advertising information, and service provider attribute information. Service types may include, but are not limited to, product sales, technical services, consulting services, franchise services, and / or logistics services. Service provider attribute information may include, but is not limited to, qualifications, experience, and / or previous customer reviews. Rich service information can provide more accurate service recommendations.

[0040] The information generation method provided by the embodiments of the present disclosure not only connects the demand with the service information of the service provider and optimizes resource allocation, but also makes specific judgments on the demand type and business attributes of the demand information, and specifically matches the keywords extracted based on the demand information with the service information of the service provider to generate business recommendation results. This can achieve more accurate information matching, improve the efficiency and quality of service matching, promote the effective connection between market supply and demand, and enable both parties to reach cooperation or transactions accurately and efficiently.

[0041] Please refer to Figure 3 , Figure 3 This is a flowchart of an information generation method provided by an embodiment of the present disclosure, wherein process 300 includes the following steps:

[0042] Step 301: Determine the requirement type of the requirement information.

[0043] Step 302: In response to the requirement type being a business requirement, determine the business attribute of the requirement information.

[0044] Step 303: In response to the business attribute of the demand information being a target service type business, keywords of the demand information are extracted, and the keywords are matched with the collected service information of the service provider to generate a business recommendation result.

[0045] The above steps 301 to 303 are consistent with the above steps 201 to 203. For the same content, please refer to the corresponding parts above and will not be repeated here.

[0046] Step 304: In response to the service attribute of the demand information being a non-target service type service, extract keywords of the demand information.

[0047] Optionally, the business attributes of the demand information include target service type business and non-target service type business, wherein the non-target service type business may refer to business cooperation, franchising and the like.

[0048] Step 305: Based on the keywords, output prompt information for supplementing the required information.

[0049] In this embodiment, the execution entity may output prompt information for supplementing the demand information based on keywords and preset rules, allowing the user to supplement the demand information based on the prompt information, thereby making the supplemented demand information more detailed and comprehensive. If the demand information provided by the user meets the preset rules, the execution entity may skip step 305 and directly determine the screening results based on the demand information and the enterprise information database.

[0050] Step 306: Determine the screening result based on the supplemented demand information and the enterprise information database.

[0051] Exemplarily, the enterprise information database may include various types of information of one or more enterprises, such as service type, service scope, service price, advertising information, attribute information of the service provider, name, contact number, email address, mailing address, business scope, enterprise code, qualification information and / or enterprise website, etc.

[0052] For example, assuming that the business attribute of the demand information is franchise demand, the screening results may include the brand that the user wants to franchise, franchise rule information and / or franchise data information, etc.

[0053] The information generation method provided by the embodiment of the present disclosure responds to the business attribute of the demand information being a non-target service business, and outputs prompt information for supplementing the demand information, so that the supplemented demand information is more detailed and comprehensive, thereby more accurately and efficiently obtaining screening results based on the supplemented demand information and the enterprise information database.

[0054] Please refer to Figure 4 , Figure 4 This is a flowchart of another information generation method provided by an embodiment of the present disclosure, wherein process 400 includes the following steps:

[0055] Step 401: Determine the requirement type of the requirement information.

[0056] The above step 401 is consistent with the above step 201. For the same content, please refer to the corresponding part above and will not be repeated here.

[0057] Step 402: In response to the requirement type being a query requirement, perform reference resolution on the requirement information, and perform information retrieval on the reference resolution result to generate a query result.

[0058] For example, the query demand may refer to information query, search, etc.

[0059] For example, coreference resolution can refer to the process of determining the specific object or entity referred to by a pronoun, noun phrase, etc. by analyzing the text context and semantic information in natural language processing. For example, coreference resolution of demand information can include completing a missing clause or subject.

[0060] In some embodiments, the above step 402 performs reference resolution on the demand information and performs information retrieval on the reference resolution results to generate query results, which may include: performing reference resolution on the demand information based on a large language model; performing information retrieval on the reference resolution results based on a retrieval enhancement generation model and a knowledge graph library; and inputting the retrieval results into the large language model to generate query results.

[0061] The aforementioned execution entity can perform coreference resolution on the demand information based on a large language model, combined with a vector example library and contextual prompts, to obtain a coreference resolution result. Based on a Retrieval-Augmented Generation (RAG) model and a knowledge graph library, information retrieval is performed on the coreference resolution result to obtain a retrieval result. The retrieval result is then input into the large language model and combined with the vector example library and contextual prompts to generate a query result. A knowledge graph library is a knowledge base that graphically represents knowledge such as entities, relationships, and attributes.

[0062] In this way, after the demand information is dereferenced, accurate search results can be obtained by searching based on the search enhancement generation model and the knowledge graph library. By inputting the search results into the large language model, more readable query results can be generated.

[0063] The information generation method provided by the embodiment of the present disclosure, in response to determining that the demand type is a query demand, performs reference resolution on the demand information, and performs information retrieval on the reference resolution result to generate a query result. In this way, the present disclosure connects the demand with the service information of the service provider, and can not only provide accurate business recommendation results for business needs, but also generate accurate and more readable query results for the query needs.

[0064] Optionally, the number of solutions in the business recommendation results, the solutions in the screening results, and the solutions in the query results can be one or more, and can be selected by the service demander. The service demander can refer to a user (individual or enterprise, etc.), such as a search user, a buyer, or a platform user.

[0065] Optionally, the service demander and the service provider execute the selected business recommendation results or solutions from the screening results. The above-mentioned execution entity can continuously interact with the service demander and the service provider to monitor the execution status of all links, and can also obtain feedback information from the service demander and / or service provider during the execution of the solution, and adjust or supplement the details of the implementation of the solution.

[0066] In some embodiments, the above step 201 of determining the demand type of the demand information may include: performing intent recognition on the demand information to obtain an intent recognition result; performing cluster analysis on the intent recognition result based on clustering rules to determine the demand type of the demand information.

[0067] Optionally, the clustering rules include query requirement rules and business requirement rules. The query requirement rules may refer to clustering rules preset for query requirements, and the business requirement rules may refer to clustering rules preset for business requirements.

[0068] In this embodiment, the above-mentioned execution entity performs intent recognition on the demand information to obtain an intent recognition result; the intent recognition result is clustered and analyzed based on clustering rules. Cluster analysis refers to the analysis process of grouping a collection of physical or abstract objects into multiple classes composed of similar objects to determine the specific demand type of the demand information, which can improve the accuracy of determining the demand type.

[0069] In some embodiments, the above-mentioned step 203 (or step 303) matches the keywords with the collected service information of the service provider to generate a business recommendation result, including: matching the keywords with the service information to generate a first intermediate result; in response to obtaining the supplementary information of the demand, extracting the supplementary keywords of the preset slots of the supplementary information of the demand, matching the supplementary keywords with the service information to generate a second intermediate result; adjusting the first intermediate result based on the second intermediate result to generate a business recommendation result.

[0070] In this embodiment, the execution entity matches the extracted keywords with the service information to generate a first intermediate result. In response to determining that the user is continuing to supplement their demand information, the execution entity obtains the supplementary demand information, extracts the supplementary keywords for the preset slots in the supplementary demand information, and matches the supplementary keywords with the service information to generate a second intermediate result. Based on the second intermediate result, the execution entity adjusts the first intermediate result to generate a service recommendation result. In this way, through a more in-depth analysis of comprehensive and complete demand information, more accurate service recommendation results can be obtained.

[0071] Optionally, the service demander may also make modification suggestions based on these results, and the above-mentioned execution entity may adjust the business recommendation results, screening results, and query results based on the modification suggestions.

[0072] In some embodiments, the above step 203 (or step 303) matches the keywords with the collected service information of the service providers to generate business recommendation results, including: matching the keywords with the collected service information of the service providers to obtain matched service providers; sending demand information to the matched service providers, and prompting the matched service providers to confirm whether they have the ability to meet the demand information; generating business recommendation results based on the service information of the service providers that have the ability to meet the demand information.

[0073] In this embodiment, the above-mentioned execution entity matches the extracted keywords with the collected service information of the service providers, obtains the matched service providers, sends the demand information to the matched service providers, and prompts the matched service providers to confirm whether they have the ability to meet the demand information; matches the service information of the service providers that have the ability to meet the demand information with the keywords, and generates business recommendation results. In this way, by confirming whether the matched service providers have the ability to meet the demand information, service providers that currently do not meet the demand information can be screened out, avoiding recommending unsatisfactory service providers, and further improving the accuracy of the business recommendation results.

[0074] Optionally, the service provider may modify its own service information, and the execution entity obtains the modified service information, updates the service information of the service provider, and stores it for subsequent use.

[0075] In some embodiments, the method provided by the embodiments of the present disclosure may also include: determining recommendation statements to be prompted to the user based on historical behavior data, enterprise information database and / or dialogue database, and conducting multiple rounds of dialogues with the user based on the recommendation statements; integrating one or more of the user needs, user information and business cooperation requirements in the content of multiple rounds of dialogues to obtain demand information.

[0076] For example, the historical behavior data may include historical behaviors of one or more users regarding the sentences they last selected based on multiple recommended sentences.

[0077] Exemplarily, the enterprise information database may include various types of information of one or more enterprises, such as service type, service scope, service price, advertising information, attribute information of the service provider, name, contact number, email address, mailing address, business scope, enterprise code, qualification information and / or enterprise website, etc.

[0078] For example, the conversation database may include historical conversation data between one or more users and the subject of the present disclosure, and / or conversation data between one or more users and devices other than the subject of the present disclosure.

[0079] In this embodiment, the above-mentioned execution entity prompts the user with recommendation statements, interacts with the user, obtains and organizes user needs, user information and / or business cooperation requirements in multiple rounds of dialogue content, and can realize dynamic demand expression and obtain more comprehensive demand information.

[0080] Optionally, the execution entity may perform risk management on the content of the user-provided sentence, such as restricting the use of sensitive words and prompting the user to re-enter the sentence. The execution entity may also perform risk management on the content of the results (such as business recommendation results, screening results, and query results).

[0081] In some embodiments, the method provided by the embodiments of the present disclosure may further include: in response to determining that a conversation is ongoing, saving the ongoing conversation content in memory; in response to determining that the conversation is interrupted, saving the interrupted conversation content in cache; and in response to determining that the conversation has ended, saving the ended conversation content in a conversation database. In this way, conversation content in different states can be stored.

[0082] In some embodiments, the method provided by the embodiments of the present disclosure may further include: extracting clues from the conversation content in the conversation database to obtain demand clue information; in response to obtaining evaluation information of the business recommendation results, updating the business recommendation results based on the evaluation information and demand clue information.

[0083] In this embodiment, in response to determining that the conversation has ended, the execution entity extracts clues from the interactive conversation content between the execution entity and the current user in the conversation database, such as extracting and storing basic user information such as name, contact number, email address, mailing address, and quantity of purchased items. The user selects and implements a solution from the service recommendation results, screening results, or query results, and can provide an evaluation of the selected solution, such as satisfaction or detailed evaluation. The execution entity obtains evaluation information for the service recommendation results and updates the service recommendation results based on the evaluation information and stored demand clue information, such as proposing subsequent improvement measures or additional services, thereby improving the user experience.

[0084] Optionally, the above-mentioned execution entity can also obtain the implementation process information of the plan recorded by the user for the selected business recommendation results, screening results or query results. After the implementation of the plan is completed, the execution entity can provide the final implementation information to the user. The user can confirm the implementation process information. The execution entity can also generate an evaluation report based on the implementation process information and display it to the user.

[0085] For ease of understanding, the following Figure 5 The process 500 shown provides an application scenario in which the information generation method of the embodiment of the present disclosure can be implemented.

[0086] Step 501: Determine a recommendation statement to be prompted to the user based on historical behavior data, an enterprise information database, and / or a dialogue database in the recommendation system, and conduct multiple rounds of dialogue with the user based on the recommendation statement.

[0087] Step 502: Obtain user demand information based on multiple rounds of conversation content.

[0088] Step 503: Perform risk management on the conversation content and user account.

[0089] Step 504: perform intent recognition on the demand information to obtain an intent recognition result, perform cluster analysis on the intent recognition result based on clustering rules, and determine the demand type of the demand information.

[0090] Step 505: In response to the requirement type being a query requirement, reference resolution is performed on the requirement information based on the large language model.

[0091] Step 506: Based on the retrieval enhancement generation model and the knowledge graph library, information retrieval is performed on the coreference resolution results, and the retrieval results are input into the large language model to generate query results.

[0092] Step 507: In response to the requirement type being a business requirement, determine whether the business attribute of the requirement information is a target service type business.

[0093] Step 508: In response to the business attribute of the demand information being a target service type business, extract keywords from the demand information, perform business matching on the keywords with the collected service information of the service provider, and generate a business recommendation result.

[0094] Step 509: In response to the business attribute of the demand information being a non-target service business, a screening result is determined based on the keywords of the demand information and the enterprise information database.

[0095] Step 510: Perform state transfer and / or link transfer on the interactive dialogue, and manage the word slots of the dialogue content.

[0096] The status of an interactive conversation can be interrupted or ongoing. A link refers to a conversation between a user and the aforementioned execution entity. Managing the word slots of conversation content can refer to storing the key words in the conversation content and iteratively updating the preset slot information.

[0097] Step 511: Risk management can be performed on the content of the results.

[0098] Step 512: In response to determining that the conversation is ongoing, the content of the ongoing conversation is saved in the memory; in response to determining that the conversation is interrupted, the content of the interrupted conversation is saved in the cache; in response to determining that the conversation has ended, the content of the ended conversation is saved in the conversation database.

[0099] Step 513: extract clues from the conversation content in the conversation database to obtain demand clue information; in response to the evaluation information of the obtained result, update the result based on the evaluation information and the demand clue information.

[0100] Figure 5 The specific implementation of each step can refer to the corresponding explanation in the above method embodiment, which will not be repeated here.

[0101] Further references Figure 6 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an information generating device. The device embodiment corresponds to the above method embodiment, and the device can be specifically applied to various electronic devices.

[0102] like Figure 6 As shown, the information generation device 600 of this embodiment may include: a first determination module 601, a second determination module 602, and a first generation module 603. The first determination module 601 is configured to determine the demand type of the demand information. The second determination module 602 is configured to, in response to the demand type being a business demand, determine the business attributes of the demand information. The first generation module 603 is configured to, in response to the business attributes of the demand information being a target service type business, extract keywords from the demand information, perform business matching on the keywords with the collected service information of the service provider, and generate business recommendation results.

[0103] In this embodiment, the specific processing of the first determination module 601, the second determination module 602 and the first generation module 603 in the information generating device 600 and the technical effects brought about by them can refer to the relevant descriptions of the steps in the above embodiments respectively, and will not be repeated here.

[0104] In some optional implementations of this embodiment, the information generating device 600 further includes: an extraction module configured to extract keywords from the demand information in response to the business attribute of the demand information being a non-target service type business; an output module configured to output prompt information for supplementing the demand information based on the keywords; and a third determination module configured to determine a screening result based on the supplemented demand information and the enterprise information database.

[0105] In some optional implementations of this embodiment, the information generating device 600 further includes: a second generating module configured to perform reference resolution on the demand information in response to the demand type being a query demand, and perform information retrieval on the reference resolution result to generate a query result.

[0106] In some optional implementations of this embodiment, the first determination module 601 is further configured to: perform intent recognition on the demand information to obtain an intent recognition result, and perform cluster analysis on the intent recognition result based on clustering rules to determine the demand type of the demand information, where the clustering rules include query requirement rules and business requirement rules.

[0107] In some optional implementations of this embodiment, the information generation device 600 further includes a second generation module configured to: perform coreference resolution on the demand information based on the large language model; perform information retrieval on the coreference resolution results based on the retrieval-enhanced generation model and the knowledge graph library; and input the retrieval results into the large language model to generate a query result.

[0108] In some optional implementations of this embodiment, the first generating module 603 is further configured to: perform business matching between the keywords and the service information to generate a first intermediate result; in response to obtaining the supplementary demand information, extract the supplementary keywords for the preset slots in the supplementary demand information; perform business matching between the supplementary keywords and the service information to generate a second intermediate result; and adjust the first intermediate result based on the second intermediate result to generate a business recommendation result.

[0109] In some optional implementations of this embodiment, the first generating module 603 is further configured to: perform business matching between the keyword and the collected service information of service providers to obtain matching service providers; send the requirement information to the matching service providers; and prompt the matching service providers to confirm whether they have the ability to meet the requirement information; and generate business recommendation results based on the service information of the service providers that have the ability to meet the requirement information.

[0110] In some optional implementations of this embodiment, the information generating device 600 further includes: a conversation module configured to determine a recommendation statement to be presented to the user based on historical behavior data, the enterprise information database, and the conversation database, and to conduct multiple rounds of conversations with the user based on the recommendation statement; and an acquisition module configured to integrate one or more of user needs, user information, and business cooperation requirements from the multiple rounds of conversations to obtain demand information.

[0111] In some optional implementations of this embodiment, the information generating device 600 further includes: a first storage module configured to, in response to determining that a conversation is ongoing, store the content of the ongoing conversation in a memory; a second storage module configured to, in response to determining that a conversation is interrupted, store the content of the interrupted conversation in a cache; and a third storage module configured to, in response to determining that a conversation has ended, store the content of the ended conversation in a conversation database.

[0112] In some optional implementations of this embodiment, the information generating device 600 further includes: an extraction module configured to extract clues from the conversation content in the conversation database to obtain demand clue information; and an update module configured to, in response to obtaining evaluation information of the service recommendation result, update the service recommendation result based on the evaluation information and the demand clue information.

[0113] In some optional implementations of this embodiment, the service information includes one or more of the following: service type, service scope, service price, advertising information, and attribute information of the service provider.

[0114] This embodiment exists as an apparatus embodiment corresponding to the above-mentioned method embodiment. The technical effects brought about by the embodiments involving the information generating apparatus provided by this embodiment can be referred to the corresponding relevant descriptions in the above-mentioned method embodiments respectively, and will not be repeated here.

[0115] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the information generation method described in any of the above embodiments when executing.

[0116] According to an embodiment of the present disclosure, the present disclosure further provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the information generation method described in any of the above embodiments when executed.

[0117] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, which, when executed by a processor, can implement the information generating method described in any of the above embodiments.

[0118] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0119] like Figure 7As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0120] Various components in device 700 are connected to I / O interface 705, including an input unit 706, such as a keyboard, mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, optical disk, etc.; and a communication unit 709, such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0121] The computing unit 701 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the information generation method. For example, in some embodiments, the information generation method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the information generation method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the information generation method by any other appropriate means (e.g., by means of firmware).

[0122] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0124] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0126] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0127] A computer system may include a client and a server. The client and server are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and virtual private server (VPS) services. The server may also be a server in a distributed system or a server integrated with blockchain.

[0128] The information generation method provided by the embodiments of the present disclosure not only connects the demand with the service information of the service provider and optimizes resource allocation, but also makes specific judgments on the demand type and business attributes of the demand information, and specifically matches the keywords extracted based on the demand information with the service information of the service provider to generate business recommendation results. This can achieve more accurate information matching, improve the efficiency and quality of service matching, promote the effective connection between market supply and demand, and enable both parties to reach cooperation or transactions accurately and efficiently.

[0129] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0130] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for generating information, comprising: Determine a recommendation statement to be presented to the user based on historical behavior data, an enterprise information database, and a conversation database, and conduct multiple rounds of conversations with the user based on the recommendation statement; wherein the historical behavior data includes historical behavior-related data of one or more users selecting a recommendation statement based on multiple recommendation statements; Integrate one or more of user needs, user information, and business cooperation requirements in multiple rounds of conversations to obtain demand information; determining a demand type of the demand information; In response to the requirement type being a business requirement, determining a business attribute of the requirement information; In response to the business attribute of the demand information being a target service type business, keywords of the demand information are extracted, and business matching is performed between the keywords and the collected service information of the service providers to generate a business recommendation result.

2. The method according to claim 1, further comprising: In response to the service attribute of the demand information being a non-target service type service, extracting keywords of the demand information; Based on the keywords, output prompt information for supplementing the required information; Determine the screening results based on the supplemented demand information and enterprise information database.

3. The method according to claim 1 or 2, further comprising: In response to the requirement type being a query requirement, reference resolution is performed on the requirement information, and information retrieval is performed on the reference resolution result to generate a query result.

4. The method according to claim 1 or 2, wherein: The determining of the demand type of the demand information includes: Perform intent recognition on the demand information and obtain intent recognition results; The intention recognition result is clustered and analyzed based on clustering rules to determine the demand type of the demand information, wherein the clustering rules include query demand rules and business demand rules.

5. The method according to claim 3, wherein: The performing of reference resolution on the demand information and performing information retrieval on the reference resolution result to generate a query result includes: Based on the large language model, the demand information is dereferenced; Based on the retrieval enhancement generation model and knowledge graph library, information retrieval is performed on the coreference resolution results; The retrieval results are input into the large language model to generate the query results.

6. The method according to claim 1 or 2, wherein: The step of matching the keywords with the collected service information of the service providers to generate service recommendation results includes: Performing business matching between the keyword and the service information to generate a first intermediate result; In response to obtaining the supplementary demand information, extracting a supplementary keyword of a preset slot of the supplementary demand information, performing business matching between the supplementary keyword and the service information, and generating a second intermediate result; The first intermediate result is adjusted based on the second intermediate result to generate a business recommendation result.

7. The method according to claim 1, wherein The step of matching the keywords with the collected service information of the service providers to generate service recommendation results includes: Performing business matching between the keyword and the collected service information of the service provider to obtain a matching service provider; Sending the demand information to the matching service provider and prompting the matching service provider to confirm whether it has the ability to meet the demand information; The business recommendation result is generated based on the service information of the service provider having the ability to meet the demand information.

8. The method according to claim 1 or 2, further comprising: In response to determining that a conversation is ongoing, saving content of the ongoing conversation in memory; In response to determining that the conversation is interrupted, storing the interrupted conversation content in a cache; In response to determining that the conversation has ended, the ended conversation content is saved in a conversation database.

9. The method according to claim 8, further comprising: Extracting clues from the conversation content in the conversation database to obtain demand clue information; In response to obtaining evaluation information of the service recommendation result, the service recommendation result is updated based on the evaluation information and the demand clue information.

10. The method according to claim 1 or 2, wherein: The service information includes one or more of the following: service type, service scope, service price, advertising information and attribute information of the service provider.

11. An information generating device, comprising: a dialogue module configured to determine a recommendation statement to be presented to a user based on historical behavior data, an enterprise information database, and a dialogue database, and to conduct multiple rounds of dialogue with the user based on the recommendation statement; wherein the historical behavior data includes historical behavior data related to the recommendation statement selected by one or more users based on multiple recommendation statements; An acquisition module configured to integrate one or more of user needs, user information, and business cooperation requirements in multiple rounds of conversation content to obtain demand information; A first determining module is configured to determine a requirement type of the requirement information; a second determining module configured to determine a business attribute of the demand information in response to the demand type being a business demand; The first generating module is configured to extract keywords from the demand information in response to the business attribute of the demand information being a target service type business, perform business matching between the keywords and the collected service information of the service provider, and generate a business recommendation result.

12. The apparatus according to claim 11, further comprising: An extraction module is configured to extract keywords of the demand information in response to the business attribute of the demand information being a non-target service type business; an output module configured to output prompt information for supplementing the required information based on the keyword; The third determining module is configured to determine the screening result based on the supplemented demand information and the enterprise information database.

13. The apparatus according to claim 11 or 12, further comprising: The second generating module is configured to perform reference resolution on the requirement information in response to the requirement type being a query requirement, and perform information retrieval on the reference resolution result to generate a query result.

14. The device according to claim 11 or 12, wherein The first determination module is further configured to: perform intent recognition on the demand information to obtain intent recognition results; perform cluster analysis on the intent recognition results based on clustering rules to determine the demand type of the demand information, and the clustering rules include query demand rules and business demand rules.

15. The device according to claim 13, wherein The second generating module is further configured to: perform reference resolution on the demand information based on a large language model; Based on the retrieval enhancement generation model and the knowledge graph library, information retrieval is performed on the reference resolution results; the retrieval results are input into the large language model to generate the query results.

16. The device according to claim 11 or 12, wherein The first generating module is further configured to: perform business matching between the keyword and the service information to generate a first intermediate result; in response to obtaining the supplementary demand information, extract the supplementary keyword of the preset slot of the supplementary demand information, perform business matching between the supplementary keyword and the service information to generate a second intermediate result; The first intermediate result is adjusted based on the second intermediate result to generate a business recommendation result.

17. The device according to claim 11, wherein The first generating module is further configured to: perform business matching between the keyword and the collected service information of the service provider to obtain a matching service provider; The demand information is sent to the matched service provider, and the matched service provider is prompted to confirm whether it has the ability to meet the demand information; and the business recommendation result is generated based on the service information of the service provider that has the ability to meet the demand information.

18. The apparatus according to claim 11 or 12, further comprising: a first saving module configured to save the content of the ongoing conversation in a memory in response to determining that the conversation is ongoing; a second saving module configured to save the interrupted conversation content in a cache in response to determining that the conversation is interrupted; The third saving module is configured to save the ended conversation content in the conversation database in response to determining that the conversation has ended.

19. The apparatus according to claim 18, further comprising: an extraction module configured to extract clues from the conversation content in the conversation database to obtain demand clue information; The updating module is configured to update the business recommendation result based on the evaluation information and the demand clue information in response to obtaining the evaluation information of the business recommendation result.

20. The device according to claim 11 or 12, wherein The service information includes one or more of the following: service type, service scope, service price, advertising information and attribute information of the service provider.

21. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the information generating method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the information generation method according to any one of claims 1 to 10.

23. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the information generation method according to any one of claims 1 to 10.

Images