Method, device and equipment for optimizing reply content of user search request

Abstract

The invention provides a reply content optimization method, device and equipment for a user search request, and relates to the technical field of e-commerce platforms. The invention discloses a reply content optimization method for a user search request. The method comprises the following steps: acquiring search request information of a user; preprocessing the search request information; based on the preprocessed search request information, obtaining an optimization reply result corresponding to the search request information through a reply optimization model; and generating user reply information based on the optimized reply result. According to the embodiment of the invention, personalized and dynamic contents can be automatically generated according to the search request of the user.

Description

Technical Field

[0001] The present application relates to the technical field of e-commerce platforms, and in particular to a method, device and apparatus for optimizing reply content of user search requests. Background Art

[0002] At present, online shopping has become an indispensable part of people's daily life, and more and more people choose online platforms to meet their shopping needs. However, when users purchase products with personalized functions or personalized styles, the search and discovery methods of traditional online platforms lack understanding of user intentions and contexts, and cannot provide personalized and dynamic content and suggestions, which often cannot bring users a good shopping experience. Summary of the invention

[0003] According to one aspect of the present application, a method for optimizing reply content for user search requests is provided, including: obtaining user search request information; preprocessing the search request information; based on the preprocessed search request information, obtaining an optimized reply result corresponding to the search request information through a reply optimization model; and generating user reply information based on the optimized reply result.

[0004] According to some embodiments, the search request information is preprocessed, including: determining whether the search request information matches a preset operation configuration rule; if the search request information does not match the preset operation configuration rule, rewriting the search request information through a front-end engine; and performing retrieval enhancement processing based on the rewritten search request information to obtain a recall text of the search request information.

[0005] According to some embodiments, when the search request information does not match the preset operation configuration rules, the search request information is rewritten through the front-end engine, including: rewriting the search request information to generate multiple rounds of rewritten words corresponding to the search request information; performing structured parsing on the multiple rounds of rewritten words and obtaining parsing results; searching and classifying the multiple rounds of rewritten words according to the parsing results; performing a first security check on the classified multiple rounds of rewritten words; and outputting the classified multiple rounds of rewritten words through the front-end engine.

[0006] According to some embodiments, retrieval enhancement processing is performed based on the rewritten search request information to obtain the recall text of the search request information, including: performing a second security check on the multiple rounds of rewritten words output by the front engine; and performing retrieval enhancement processing based on the multiple rounds of rewritten words that pass the second security check to generate the recall text.

[0007] According to some embodiments, based on the preprocessed search request information, an optimized reply result corresponding to the search request information is obtained through a reply optimization model, including: generating input data for the reply optimization model based on the search request information, multiple rounds of rewritten words corresponding to the search request information, and recalled text according to preset prompt word rules; generating optimized reply results through the reply optimization model based on the input data; performing keyword analysis on the optimized reply results; and performing a third security check on the optimized reply results.

[0008] According to some embodiments, user reply information is generated based on the optimized reply result, including: when the optimized reply result passes the third security check, determining whether the optimized reply result needs to be completed with materials to generate the user reply information; when the optimized reply result does not pass the third security check, directly generating the user reply information based on the optimized reply result.

[0009] According to some embodiments, when the optimized reply result passes the third security check, it is determined whether the optimized reply result needs to be supplemented with materials to generate user reply information, including: when the materials need to be supplemented, calling a preset service to supplement the materials of the optimized reply result, and generating user reply information based on the optimized reply result with the materials supplemented; when the materials do not need to be supplemented, directly generating user reply information based on the optimized reply result.

[0010] According to some embodiments, when the search request information matches the preset operation configuration rules, user reply information is generated according to the preset operation configuration rules; and when the multiple rounds of rewritten words output by the front engine fail to pass the second security check, user reply information is generated according to the preset reply text.

[0011] According to one aspect of the present application, a device for optimizing reply content of a user search request is provided, including: an information acquisition module for acquiring the user's search request information; a preprocessing module for preprocessing the search request information; an optimization processing module for acquiring an optimized reply result corresponding to the search request information through a reply optimization model based on the preprocessed search request information; and an information output module for generating user reply information based on the optimized reply result.

[0012] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the aforementioned method.

[0013] According to one aspect of the present application, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the aforementioned method is implemented.

[0014] According to the embodiments of the present application, the user's search request can be processed through an intelligent language model, the user's needs and intentions can be understood quickly and accurately, and personalized and dynamic content and suggestions can be automatically generated to enhance the user's shopping experience.

[0015] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application.

[0017] Figure 1 A flow chart of a method for optimizing reply content to a user search request according to an exemplary embodiment of the present application is shown.

[0018] Figure 2 , Figure 3 A diagram showing a session effect of a service page according to an exemplary embodiment of the present application is shown.

[0019] Figure 4 A block diagram of a device for optimizing reply content to a user search request according to an exemplary embodiment of the present application is shown.

[0020] Figure 5 A block diagram of an electronic device according to an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0021] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0022] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0023] The described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application may be put into practice without one or more of these specific details, or other modes, components, materials, devices or operations may be adopted. In these cases, known structures, methods, devices, realizations, materials or operations will not be shown or described in detail.

[0024] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] The present application provides a method, device and equipment for optimizing reply content for user search requests, which can quickly and accurately understand the user's search needs and automatically generate personalized reply content.

[0027] A method, apparatus and device for optimizing reply content of a user search request according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0028] Figure 1 A flow chart of a method for optimizing reply content to a user search request according to an exemplary embodiment of the present application is shown.

[0029] like Figure 1 As shown, in step S100, the optimization device obtains the user's search request information.

[0030] For example, in step S100, the optimization device obtains the user's search request information through the service page.

[0031] The optimization device obtains the search keywords and other parameters entered by the user through the session of the service page to form the user's search request information.

[0032] According to some embodiments, the service page can receive information and parameters entered by the user through the front end, client or server of the platform. Among them, the front end, client or server of the platform, and the service page are all equipped with data embedding points to obtain real-time behavior data, and store it in the feature database and distributed database of the platform through Data Hub (data bus) and stream data processing.

[0033] In step S200, the optimization device pre-processes the search request information.

[0034] For example, in step S200, the optimization device rewrites the search request information through the front engine and performs retrieval enhancement processing to obtain the recall text of the search request information.

[0035] The optimization device first obtains a preset operation configuration rule and determines whether the search request information matches the preset operation configuration rule.

[0036] According to some embodiments, when the search request information matches the preset operation configuration rule, the optimization device directly generates user reply information corresponding to the search request information according to the preset operation configuration rule.

[0037] According to some embodiments, when the search request information does not match the preset operation configuration rule, the optimization device rewrites the search request information multiple times through the front-end engine and generates multiple rounds of rewritten words based on the search request information.

[0038] Furthermore, the optimization device performs structural analysis on the multi-round rewritten words, and searches and classifies the multi-round rewritten words through a preset classification model according to the obtained analysis results. The optimization device sets a classified fixed reply according to the classified multi-round rewritten words to generate user reply information.

[0039] The optimization device performs a first pre-stage security check on the classified multi-round rewritten words through a pre-stage engine, and the pre-stage engine outputs the words after the check passes.

[0040] The optimization device performs a second security check on the multiple rounds of rewritten words corresponding to the search request information output by the front engine to determine whether the search request information and its corresponding multiple rounds of rewritten words can be provided to the reply optimization model.

[0041] According to some embodiments, when multiple rounds of rewriting words fail to pass the second security check, the optimization device directly generates user reply information corresponding to the search request information based on the preset reply text.

[0042] When the multi-round rewritten words pass the second security check, the optimization device performs retrieval enhancement processing on the multi-round rewritten words and obtains the recalled text of the search request information.

[0043] According to some embodiments, the optimization device may perform retrieval enhancement processing on multiple rounds of rewritten words through multiple channels such as a retrieval enhancement engine and a main search title engine, and perform text enhancement and re-arrangement on the obtained recalled texts.

[0044] In step S300, based on the pre-processed search request information, the optimization device obtains the optimized reply result corresponding to the search request information through the reply optimization model.

[0045] For example, in step S300, the optimization device generates input data of a reply optimization model based on the pre-processed search request information, and obtains a corresponding optimized reply result through the reply optimization model.

[0046] Based on the search request information and its corresponding multiple rounds of rewritten words and recalled text, the optimization device generates input data of the reply optimization model according to preset prompt word rules to input into the reply optimization model.

[0047] According to some embodiments, the reply optimization model may adopt an LLM (Large Language Model) model, and use data stored in a feature database and a distributed database of the platform to pre-train the reply optimization model.

[0048] Based on the input data, the optimization device generates an optimized response result through a trained response optimization model.

[0049] According to some embodiments, the type of the reply optimization model can be dynamically adjusted according to the input data. For example, if the input data contains the user's shopping intention, the type of the reply optimization model can be adjusted to the shopping type. If the input data contains the user's chat content, the type of the reply optimization model can be adjusted to the chat type.

[0050] Furthermore, the optimization device performs keyword analysis on the optimized reply results obtained through the reply optimization model, and performs a post-third security check on the optimized reply results.

[0051] In step S400, based on the optimization reply result, the optimization device generates user reply information.

[0052] For example, in step S400, the optimization device determines whether the optimization reply result needs to be supplemented with materials, and generates user reply information.

[0053] According to some embodiments, when the optimization reply result fails to pass the third security check, the optimization device directly generates user reply information based on the optimization reply result.

[0054] When the optimization reply result passes the third security check, the optimization device determines whether the optimization reply result needs to be supplemented with materials.

[0055] According to some embodiments, the optimization device determines whether the product fields in the optimization reply result are complete. If some product fields are missing in the optimization reply result, the optimization device determines that the optimization reply result needs to be re-completed, otherwise it does not need to be re-completed.

[0056] When the material needs to be completed, the optimization device calls the preset service to complete the material of the optimization reply result, and generates user reply information based on the optimization reply result with the completed material.

[0057] According to some embodiments, the services invoked by the optimization device include product classification recall, product recall, category list recall, etc.

[0058] In the absence of need to complete the material, the optimization device directly generates user response information based on the optimization response result.

[0059] The optimization device returns the finally generated user reply information to the session of the service page to respond to the user's search request.

[0060] According to the embodiments of the present application, the user's search request can be quickly processed through the model, and the user's needs and intentions can be understood, and personalized and dynamic content and suggestions can be automatically generated to improve search efficiency and user experience.

[0061] Figure 2 , Figure 3 A diagram showing a session effect of a service page according to an exemplary embodiment of the present application is shown.

[0062] like Figure 2 As shown, a user can initiate a session by clicking the "Consult" icon on a service page (including a product details page).

[0063] After the user enters the session, he / she will communicate with the intelligent customer service. The intelligent customer service will first return "User Welcome" and "Frequently Asked Questions" for the user to choose. If the user clicks "Frequently Asked Questions", the intelligent customer service will answer the preset questions based on the preset knowledge base.

[0064] Furthermore, if the user asks a personalized question based on a common question, such as "What is the price of the product after the discount?", the intelligent customer service will first Figure 1 The process of the reply content optimization method determines whether the corresponding user reply information can be generated. After determining that it is impossible to directly reply to the user, the intelligent customer service evokes the merchant customer service to communicate with the user, such as Figure 3 shown.

[0065] After the user completes the communication with the merchant customer service, the user can close the conversation page with the merchant customer service and return to the conversation page with the intelligent customer service. The last communication message on the conversation page between the user and the intelligent customer service is set to the "Continue Invite" state, so that the user can communicate with the merchant customer service again.

[0066] Figure 4 A block diagram of a device for optimizing reply content to a user search request according to an exemplary embodiment of the present application is shown.

[0067] like Figure 4 As shown, the optimization device 500 includes an information acquisition module 510, a preprocessing module 520, an optimization processing module 530 and an information output module 540.

[0068] The information acquisition module 510 acquires the search keywords and other parameters entered by the user through the session of the service page to form the user's search request information.

[0069] The pre-processing module 520 obtains a preset operation configuration rule and determines whether the search request information matches the preset operation configuration rule.

[0070] In the case that the search request information does not match the preset operation configuration rule, the pre-processing module 520 performs multiple rounds of rewriting on the search request information through the front-end engine, and generates multiple rounds of rewritten words based on the search request information.

[0071] The pre-processing module 520 performs structural analysis on the multi-round rewritten words, and searches and classifies the multi-round rewritten words through a preset classification model according to the obtained analysis results.

[0072] The pre-processing module 520 performs a first pre-safety check on the classified multi-round rewritten words through a pre-engine, and outputs the words after the check passes.

[0073] The pre-processing module 520 performs a second security check on the multi-round rewritten words corresponding to the search request information output by the front engine to determine whether the search request information and the multi-round rewritten words corresponding to it can be provided to the reply optimization model.

[0074] In the case that the multi-round rewritten words pass the second security check, the pre-processing module 520 performs retrieval enhancement processing on the multi-round rewritten words and obtains the recalled text of the search request information.

[0075] Based on the search request information and its corresponding multiple rounds of rewritten words and recalled text, the optimization processing module 530 generates input data of the reply optimization model according to the preset prompt word rules to input into the reply optimization model.

[0076] Based on the input data, the optimization processing module 530 generates an optimized reply result through the trained reply optimization model.

[0077] The optimization processing module 530 performs keyword analysis on the optimized reply result obtained through the reply optimization model, and performs a post-third security check on the optimized reply result.

[0078] When the optimization reply result passes the third security check, the information output module 540 determines whether the optimization reply result needs to be supplemented with materials.

[0079] In the case where the material needs to be supplemented, the information output module 540 calls the preset service to supplement the material of the optimized reply result, and generates user reply information based on the optimized reply result with the material supplemented.

[0080] In the case where there is no need to complete the material, the information output module 540 directly generates user reply information according to the optimized reply result.

[0081] The information output module 540 returns the finally generated user reply information to the session of the service page to respond to the user's search request.

[0082] Figure 5 A block diagram of an electronic device according to an exemplary embodiment of the present application is shown.

[0083] like Figure 5 As shown, the electronic device 600 is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0084] like Figure 5 As shown, the electronic device 600 is in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc. The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the methods described in this specification according to various exemplary embodiments of the present application. For example, the processing unit 610 may execute the following: Figure 1 The method shown in .

[0085] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0086] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0087] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0088] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0089] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by combining software with necessary hardware. The technical solution according to the embodiment of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal or a network device, etc.) to execute the method according to the embodiment of the present application.

[0090] The software product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 thereof.

[0091] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0092] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0093] The computer-readable medium carries one or more programs. When the one or more programs are executed by a device, the computer-readable medium implements the aforementioned functions.

[0094] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0095] The embodiments of the present application are described in detail above, and the description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, changes or deformations made by those skilled in the art based on the idea of ​​the present application, the specific implementation method and the scope of application of the present application, all belong to the scope of protection of the present application. In summary, the content of this specification should not be construed as limiting the present application.

Claims

1. A method for optimizing reply content of a user search request, characterized in that: include: Get the user's search request information; Preprocessing the search request information; Based on the preprocessed search request information, obtaining an optimized reply result corresponding to the search request information through a reply optimization model; Based on the optimized reply result, user reply information is generated.

2. The method according to claim 1, characterized in that Preprocessing the search request information includes: Determining whether the search request information matches a preset operation configuration rule; In the case where the search request information does not match the preset operation configuration rule, rewriting the search request information through the front-end engine; Retrieval enhancement processing is performed based on the rewritten search request information to obtain the recalled text of the search request information.

3. The method according to claim 2, characterized in that In the case that the search request information does not match the preset operation configuration rule, rewriting the search request information by the front-end engine includes: Rewriting the search request information to generate multiple rounds of rewritten words corresponding to the search request information; Performing structural analysis on the multiple rounds of rewritten words and obtaining analysis results; Searching and classifying the multiple rounds of rewritten words according to the parsing results; Performing a first security check on the classified multi-round rewritten words; and The classified multi-round rewritten words are outputted through the front engine.

4. The method according to claim 3, characterized in that Performing retrieval enhancement processing based on the rewritten search request information to obtain the recalled text of the search request information includes: Performing a second security check on the multiple rounds of rewritten words output by the front engine; Retrieval enhancement processing is performed based on multiple rounds of rewritten words that pass the second security check to generate the recalled text.

5. The method according to claim 3, characterized in that: Based on the pre-processed search request information, obtaining an optimized reply result corresponding to the search request information through a reply optimization model includes: According to a preset prompt word rule, generating input data of the reply optimization model based on the search request information, the multiple rounds of rewritten words corresponding to the search request information and the recalled text; Based on the input data, generating the optimized response result through the response optimization model; Performing keyword analysis on the optimization response results; and A third safety check is performed on the optimization response result.

6. The method according to claim 5, characterized in that Based on the optimized reply result, user reply information is generated, including: If the optimized reply result passes the third security check, determining whether the optimized reply result needs to be supplemented with materials to generate the user reply information; In the case where the optimized reply result fails to pass the third security check, the user reply information is directly generated according to the optimized reply result.

7. The method according to claim 6, characterized in that When the optimized reply result passes the third security check, determining whether the optimized reply result needs to be supplemented with materials to generate the user reply information includes: In the case where the material needs to be supplemented, calling the preset service to supplement the material of the optimized reply result, and generating the user reply information based on the optimized reply result with the material supplemented; In the case where there is no need to complete the material, the user reply information is directly generated according to the optimized reply result.

8. The method according to claim 4, characterized in that Also includes: In the case where the search request information matches the preset operation configuration rule, generating the user reply information according to the preset operation configuration rule; as well as In the case that the multi-round rewritten words output by the front engine fail to pass the second security check, the user reply information is generated according to a preset reply text.

9. A device for optimizing the content of a reply to a user search request, characterized in that: include: An information acquisition module is used to obtain the user's search request information; A preprocessing module, used for preprocessing the search request information; An optimization processing module, used to obtain an optimized reply result corresponding to the search request information through a reply optimization model based on the pre-processed search request information; The information output module is used to generate user reply information based on the optimized reply result.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images