Search processing method, electronic device, and storage medium

Abstract

The present application relates to the field of large model technology and the technical field of computers, and discloses a search processing method, an electronic device, and a storage medium. The method comprises: acquiring a search request; performing attribute feature analysis on the search request and generating auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute feature of preset industry knowledge corresponding to the search request; and on the basis of the search request and the auxiliary information, acquiring a search result corresponding to the search request. The present application solves the technical problem in the prior art of low search accuracy due to the industry knowledge being difficult to introduce into the search processing process.

Description

Search processing method, electronic device and storage medium Technical Field

[0001] The present application relates to the fields of large model technology and computer technology, and in particular to a search processing method, electronic device and storage medium. Background Art

[0002] In recent years, search engine technologies based on artificial intelligence models have been increasingly applied across various industries. However, traditional search engines are typically based on small models and simple statistical algorithms, making them difficult to apply to complex scenarios. While some search engines based on large models exist (such as the Differential Search Index (DSI)), these often rely entirely on the performance of these models, making it difficult to combine them with the industry-specific customization and manual intervention required by traditional search engines. This limits the accuracy of these existing large-model-based search engines.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far.

[0004] Summary of the Invention

[0005] The embodiments of the present application provide a search processing method, an electronic device, and a storage medium to at least solve the technical problem in related technologies that it is difficult to inject industry knowledge into the search processing process, resulting in low search accuracy.

[0006] According to one aspect of an embodiment of the present application, a search processing method is provided, including: obtaining a search request; performing attribute feature analysis on the search request to generate auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute feature of preset industry knowledge corresponding to the search request; based on the search request and the auxiliary information, obtaining search results corresponding to the search request.

[0007] According to another aspect of an embodiment of the present application, another search processing method is provided, including: obtaining a search request; using a differential search index model to perform attribute feature analysis on the search request to generate auxiliary information associated with the search request, and performing industry knowledge reasoning on the search request and the auxiliary information to output a target document identifier, wherein the auxiliary information is at least one target attribute feature of preset industry knowledge corresponding to the search request; and obtaining search results corresponding to the search request based on the target document identifier.

[0008] According to another aspect of an embodiment of the present application, another search processing method is provided, including: obtaining an e-commerce service search request; performing e-commerce attribute feature analysis on the e-commerce service search request, and generating e-commerce service auxiliary information associated with the e-commerce service search request, wherein the e-commerce service auxiliary information is a target e-commerce attribute feature combination of e-commerce service industry knowledge corresponding to the e-commerce service search request; based on the e-commerce service search request and the e-commerce service auxiliary information, obtaining the e-commerce service search results corresponding to the e-commerce service search request.

[0009] According to another aspect of an embodiment of the present application, an electronic device is further provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes any one of the above-mentioned search processing methods when running.

[0010] According to another aspect of an embodiment of the present application, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned search processing methods.

[0011] In an embodiment of the present application, a search request is first obtained, and auxiliary information associated with the search request is generated by analyzing the attribute characteristics of the search request. Further, based on the search request and the auxiliary information, the search results corresponding to the search request are obtained. In the above process, the auxiliary information is at least one target attribute characteristic of the preset industry knowledge corresponding to the search request. Therefore, the search processing method provided by the present application introduces the attribute characteristics corresponding to the preset industry knowledge into the search process by mining the attribute characteristics of the search request, thereby achieving the purpose of performing search processing on the preset industry knowledge, thereby achieving the technical effect of improving the accuracy of searching for specific industry knowledge, and thus solving the technical problem in the related art that it is difficult to inject industry knowledge into the search processing process, resulting in low search accuracy.

[0012] It is easy to notice that the above general description and the following detailed description are merely for the purpose of exemplifying and explaining the present application, and do not constitute a limitation of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0014] FIG1 is a schematic diagram of an application scenario of the search processing method in this application;

[0015] FIG2 is a flowchart of a search processing method according to Example 1 of the present application;

[0016] FIG3 is a schematic diagram of an optional search processing process according to an embodiment of the present application;

[0017] FIG4 is a flowchart of another search processing method according to Embodiment 2 of the present application;

[0018] FIG5 is a flowchart of another search processing method according to Example 3 of the present application;

[0019] FIG6 is a schematic structural diagram of a search processing device according to Embodiment 4 of the present application;

[0020] FIG7 is a schematic structural diagram of an optional search processing device according to Example 4 of the present application;

[0021] FIG8 is a schematic structural diagram of another search processing device according to Embodiment 4 of the present application;

[0022] FIG9 is a schematic structural diagram of another search processing device according to Embodiment 4 of the present application;

[0023] Figure 10 is a structural block diagram of a computer terminal according to Example 5 of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] The technical solution provided in this application is mainly implemented using large-scale model technology. The large model here refers to a deep learning model with large-scale model parameters, which can usually contain hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than ten trillion model parameters. The large model can also be called a cornerstone model / foundation model. It is pre-trained by using large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks and has good generalization capabilities, such as large-scale language models (LLMs) and multi-modal pre-training models.

[0027] It should be noted that when large models are actually applied, the pre-trained model can be fine-tuned with a small number of samples, so that the large model can be applied to different tasks. For example, large models can be widely used in fields such as natural language processing (NLP) and computer vision. Specifically, they can be applied to computer vision tasks such as visual question answering (VQA), image captioning (IC), and image generation. They can also be widely used in natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. Therefore, the main application scenarios of large models include but are not limited to digital assistants, intelligent robots, search, online education, office software, e-commerce, and intelligent design.

[0028] First, some nouns or terms that appear in the process of describing the embodiments of the present application are subject to the following explanations.

[0029] Reasoning process: The process by which the model produces corresponding outputs through data input in actual scenarios.

[0030] Large Language Model (LLM): refers to an artificial intelligence model with a certain degree of general capabilities.

[0031] Differential Search Index (DSI): refers to a search system that uses a large model to replace traditional search engines.

[0032] Named Entity Recognition (NER): refers to a technology used to extract named entities from text.

[0033] Text snippet (prompt): Serves as the initial input text for the large model, used to guide the large model to generate specific content.

[0034] Feature: refers to the attribute information obtained after attribute labeling of the query.

[0035] Example 1

[0036] According to an embodiment of the present application, a search processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] Taking into account the huge amount of model parameters of the large model and the limited computing resources of the mobile terminal, the above-mentioned search processing method provided in the embodiment of the present application can be applied to the application scenario shown in Figure 1, but is not limited thereto. In the application scenario shown in Figure 1, the large model is deployed in the server 10, and the server 10 can be connected to one or more client devices 20 through a local area network connection, a wide area network connection, an Internet connection, or other types of data networks. The client devices 20 here can include but are not limited to: smart phones, tablet computers, laptops, PDAs, personal computers, smart home devices, car-mounted devices, etc. The client device 20 can interact with the user through a graphical user interface to implement the call to the large model, thereby implementing the method provided in the embodiment of the present application.

[0038] In the above operating environment, the present application provides a search processing method as shown in Figure 2. Figure 2 is a flow chart of a search processing method according to embodiment 1 of the present application. As shown in Figure 2, the search processing method includes:

[0039] Step S21, obtaining a search request;

[0040] Step S22: Analyze the attribute characteristics of the search request to generate auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute characteristic of the preset industry knowledge corresponding to the search request;

[0041] Step S23: Based on the search request and the auxiliary information, obtain search results corresponding to the search request.

[0042] The search request may be a query request in a target application scenario. The target application scenario may include, but is not limited to, scenarios involving LLM-based search in fields such as e-commerce, education, healthcare, conferences, social networks, financial products, logistics, and navigation. Correspondingly, the preset industry knowledge is the industry knowledge corresponding to the target application scenario.

[0043] The above auxiliary information is obtained from preset industry knowledge and at least one target attribute feature, and the at least one target attribute feature includes attribute features on multiple dimensions obtained by performing attribute feature mining on the search request. The combination of the above search request and auxiliary information is used as the input of the search model (which can be LLM), and the above search results are obtained by the output of the search model. It can be seen that the preset industry knowledge and the multiple attribute features corresponding to the search request are taken into consideration in the search processing process for the search request. Therefore, the above search processing process can have good intelligent search performance within the application scenario of the preset industry, that is, it can obtain accurate search results to meet the personalized search needs of a specific industry.

[0044] In an embodiment of the present application, a search request is first obtained, and auxiliary information associated with the search request is generated by analyzing the attribute characteristics of the search request. Further, based on the search request and the auxiliary information, the search results corresponding to the search request are obtained. In the above process, the auxiliary information is at least one target attribute characteristic of the preset industry knowledge corresponding to the search request. Therefore, the search processing method provided by the present application introduces the attribute characteristics corresponding to the preset industry knowledge into the search process by mining the attribute characteristics of the search request, thereby achieving the purpose of performing search processing on the preset industry knowledge, thereby achieving the technical effect of improving the accuracy of searching for specific industry knowledge, and thus solving the technical problem in the related art that it is difficult to inject industry knowledge into the search processing process, resulting in low search accuracy.

[0045] In an embodiment of the present application, a system composed of a client device and a server can perform the following steps: the client device executes a search request to the server, the server executes the steps corresponding to the search processing method, performs attribute feature analysis on the search request, and generates auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request, and based on the search request and the auxiliary information, obtains the search results corresponding to the search request, and returns the search results to the client (or provides the client with an interface for using the search processing function).

[0046] It should be noted that, when the operating resources of the client device can meet the deployment and operating conditions of the large model, the embodiments of the present application can be carried out in the client device.

[0047] In a specific implementation of the above-mentioned target application scenario, according to the search processing method provided in the embodiment of the present application, the industry knowledge corresponding to the target application scenario is injected into the intermediate reasoning process of the DSI to improve the accuracy of the search results and the relevance of the search results to the corresponding industry. In the above-mentioned specific implementation, the search processing process can be shown in Figure 3, including five stages: industry knowledge attribute extraction stage, small model training stage, feature selection stage, thinking chain training stage and online reasoning stage. The search processing method provided in the embodiment of the present application is further explained below using this specific implementation as an example.

[0048] In an optional embodiment, in step S22, attribute feature analysis is performed on the search request to generate auxiliary information associated with the search request, including the following method steps:

[0049] Step S221, extracting industry knowledge attributes from the search request to obtain attribute extraction results;

[0050] Step S222: performing attribute labeling on the attribute extraction result to obtain an attribute labeling result, wherein the attribute labeling result is used to indicate the knowledge attributes of the preset industry knowledge in multiple dimensions;

[0051] Step S223: perform feature selection on the attribute labeling result to obtain auxiliary information.

[0052] The knowledge attributes corresponding to the above-mentioned attribute labeling results include at least: geographical attributes, brand attributes, product attributes, etc. of preset industry knowledge. In the above-mentioned optional embodiment, in the industry knowledge attribute extraction stage in the search process, industry knowledge attributes are extracted for the search request, and the multiple dimensions corresponding to the above-mentioned industry knowledge attributes are determined by the scenario requirements. In the small model training stage, attribute labeling is performed on the extracted multiple-dimensional industry knowledge attributes to obtain attribute labeling results. The attribute labeling results may include multiple groups of labeling data, and each group of labeling data includes industry knowledge attributes and their corresponding labels. In the feature selection stage, feature selection is performed on the attribute labeling results, and the auxiliary information obtained is the target labeling data that matches the search request in the multiple groups of labeling data. During the search processing, the target labeling data is considered to be industry knowledge suitable for helping to obtain search results.

[0053] In an optional embodiment, in step S221, extracting industry knowledge attributes from the search request to obtain the attribute extraction result includes at least one of the following steps:

[0054] Step S2211: Based on the preset industry knowledge, the search request is segmented to obtain a first attribute extraction result;

[0055] Step S2212: Based on the preset industry knowledge, perform named entity recognition on the search request to obtain a second attribute extraction result;

[0056] Step S2213: Based on the preset industry knowledge, synonym expansion is performed on the first attribute extraction result to obtain a third attribute extraction result;

[0057] Step S2214: extract keywords from the search request based on the preset industry knowledge to obtain a fourth attribute extraction result;

[0058] Step S2215: rewrite the expression form of the search request based on the preset industry knowledge to obtain the fifth attribute extraction result.

[0059] As an exemplary embodiment, the following multiple attributes are extracted from preset industry knowledge (such as e-commerce knowledge, computer technology knowledge, etc.) to help achieve the link between the search request (such as multiple queries) and the target answer text.

[0060] The first type is word segmentation information. This information is generated by semantically segmenting the search request into multiple terms. For example, for the query "on the Nanjing Yangtze River Bridge," the resulting word segmentation information is: ["in", "Nanjing", "city", "Yangtze River Bridge", "on"].

[0061] The second type is named entity recognition (NER) information. This information is generated by identifying industry knowledge entities contained in the search request. For example, for the query "Apple phone case," the NER information generated by performing industry knowledge entity recognition includes the following: ["Apple":"brand","phone case":"product"].

[0062] The third type is synonym information. Synonym expansion is performed on the segmentation information to obtain synonym information corresponding to the search request, thereby increasing the coverage and accuracy of the search.

[0063] The fourth type is keyword information, which identifies keywords in search requests (such as query statements) to facilitate subsequent use of keywords.

[0064] The fifth type is rewriting information: the search request is rewritten to obtain rewriting information, which includes multiple expression sentences corresponding to the same search request.

[0065] Through the above-mentioned steps S221 and S2211 to S2215, the embodiment of the present application realizes the extraction of industry knowledge attributes of search requests in multiple dimensions, improves the machine understanding of search requests during the search processing, and thus helps to improve the accuracy and relevance of search results.

[0066] In an optional embodiment, in step S222, attribute annotation is performed on the attribute extraction result to obtain an attribute annotation result, which includes the following method steps:

[0067] Step S2221 , using a labeling model corresponding to preset industry knowledge, performs attribute labeling on the attribute extraction result to obtain an attribute labeling result, wherein the attribute labeling result includes: a plurality of attribute feature combinations.

[0068] As an exemplary embodiment, the annotation model corresponding to the preset industry knowledge can be an industry-customized pre-trained small model, such as a word segmentation model, a NER model, etc. for a specified industry. In the training small model stage in the search process, the above-mentioned pre-trained small model is used to perform attribute tagging on the attribute extraction results to obtain multiple attribute feature combinations. For example, the word segmentation model of a specified industry is used to perform attribute tagging on the word segmentation results of the search request corresponding to the specified industry, and n groups of features {f1, f2, ..., fn} corresponding to n words in the word segmentation results are obtained, wherein each group of features can contain at least one feature, for example, a group fi corresponding to the i-th word contains multiple features.

[0069] In an optional embodiment, in step S223, feature selection is performed on the attribute labeling result to obtain auxiliary information, including the following method steps:

[0070] Step S2231, selecting multiple candidate feature combinations from the attribute annotation results;

[0071] Step S2232, calculating the information gain of multiple candidate feature combinations for the preset result;

[0072] Step S2233: Based on information gain, at least one target attribute feature is selected from multiple candidate feature combinations to obtain auxiliary information.

[0073] As an exemplary embodiment, during the feature selection phase of the search process, for a search request (e.g., multiple queries), multiple candidate feature combinations are selected from the corresponding attribute annotation results. For example, m feature combinations are randomly sampled. Based on the m feature combinations, the information gain of each feature combination with respect to a preset result is calculated, where the preset result is the expected answer corresponding to the search request. When the search request contains multiple queries, the auxiliary information includes at least one target attribute feature F corresponding to each query.

[0074] In an optional embodiment, in step S2232, calculating the information gain of multiple candidate feature combinations for a preset result includes the following method steps:

[0075] Step S321, obtaining a first probability of obtaining a preset result based on the search request and the auxiliary information prediction, and obtaining a second probability of obtaining the preset result based on the search request prediction;

[0076] Step S322: Calculate information gain using the first probability and the second probability.

[0077] As an exemplary embodiment, when calculating the information gain of m feature combinations for a predetermined result, the m feature combinations are denoted as F1 to Fm. For any feature combination Fi, a first probability P(doc|query, Fi) and a second probability P(doc|query) are calculated. The first probability is the probability of obtaining the predetermined result in response to the search request with auxiliary information, and the second probability is the probability of obtaining the predetermined result in response to the search request without auxiliary information. For any feature combination Fi, the difference between the first and second probabilities is calculated as the corresponding information gain Hi, that is, Hi = P(doc|query, Fi) - P(doc|query).

[0078] In an optional embodiment, in step S2233, at least one target attribute feature is selected from multiple candidate feature combinations based on information gain, including the following method steps:

[0079] Step S331 : Select a candidate feature combination with the largest information gain from multiple candidate feature combinations to obtain at least one target attribute feature.

[0080] As an exemplary embodiment, based on the information gains H1 to Hm corresponding to the m feature combinations, the feature combination corresponding to the maximum information gain is selected as at least one target attribute feature F. For example, using the maxarg() function, the feature combination corresponding to maxarg(Hi) is selected as F.

[0081] In an optional embodiment, in step S23, based on the search request and the auxiliary information, obtaining search results corresponding to the search request includes the following method steps:

[0082] Step S231: Using a differential search index model to perform industry knowledge inference on the search request and auxiliary information to obtain a target document identifier, wherein the differential search index model is trained through machine learning using multiple sets of data, the multiple sets of data being a mixture of first training data and second training data, the first training data including: sample prompts and sample document identifiers, and the second training data including: sample prompts, at least one target attribute feature corresponding to the sample prompts, and the sample document identifiers;

[0083] Step S232: Obtain search results corresponding to the search request based on the target document identifier.

[0084] As an exemplary embodiment, the training set for training the differential search index (DSI) model includes first training data (prompt, target) and second training data (query, F_target), wherein F_target is obtained by concatenating at least one target attribute feature F corresponding to the query and a sample document identifier target.

[0085] In the thought chain training stage of the search process, at least one target attribute feature F is used as a thought chain to train the DSI model. In this way, the DSI model will learn the intermediate reasoning process of industry knowledge, making the search results more industry-relevant.

[0086] During the online inference phase of the search process, when a user searches using the trained DSI model, the user's search request (query_user) is first used as a sample prompt. The DSI model analyzes query_user using a combination of industry knowledge features to obtain at least one target attribute feature F_user corresponding to query_user. The concatenation of query_user and at least one target attribute feature F_user is then used as a sample prompt. The DSI model then uses this concatenation to obtain the document number corresponding to query_user. The document content corresponding to this document number is then used as the search result for query_user. This completes a search query for query_user.

[0087] It is easy to notice that, through the above-mentioned search processing method provided in the embodiment of the present application, preset industry knowledge is injected into the intermediate reasoning process of the DSI model, thereby improving the accuracy of the DSI model search results and the relevance to the specified industry.

[0088] In an optional embodiment, a graphical user interface is provided by a terminal device, and the content displayed by the graphical user interface at least partially includes an e-commerce service search dialog box. The search processing method further includes the following method steps:

[0089] Step S241 , in response to an input operation performed on the e-commerce service search dialog box, determining an e-commerce service search request;

[0090] Step S242, in response to the sending operation performed on the e-commerce service search dialog box, performing an e-commerce service attribute feature analysis on the e-commerce service search request to generate e-commerce service auxiliary information, and obtaining e-commerce service search results based on the e-commerce service search request and the e-commerce service auxiliary information;

[0091] Step S243: Display the e-commerce service search results in the e-commerce service search dialog box.

[0092] In the above optional embodiment, the above e-commerce service search dialog box can be used to implement an exclusive e-commerce service search function corresponding to a preset industry, such as an intelligent question and answer function set under the application scenario of the preset industry. The intelligent question and answer function is not limited to text question and answer, and the above embodiment can also be combined with speech-to-text, text-to-speech, video-to-text, text-to-video and other technologies to implement voice question and answer function, video question and answer function or virtual reality / augmented reality question and answer function.

[0093] When an input operation on the e-commerce service search dialog box is detected, an e-commerce service search request is determined according to the input content in the e-commerce service search dialog box. The e-commerce service search request may include at least one query statement.

[0094] When a send operation is detected on the e-commerce service search dialog box, a search event is triggered, e-commerce service attribute feature analysis is performed on the e-commerce service search request to generate e-commerce service auxiliary information, e-commerce service search results are obtained based on the e-commerce service search request and the e-commerce service auxiliary information, and an event for automatically displaying the e-commerce service search results in the e-commerce service search dialog box is automatically triggered. The e-commerce service search results can be displayed to the user in the form of text or images in a graphical user interface, converted into audio and output through an audio output device, or converted into video and displayed in the graphical user interface.

[0095] It should be noted that both the above-mentioned input operation and the above-mentioned sending operation can be operations in which a user touches the display screen of the above-mentioned terminal device with a finger and touches the terminal device. The touch operation can include single-point touch and multi-point touch, wherein the touch operation of each touch point can include clicking, long pressing, pressing hard, swiping, etc. The above-mentioned input operation and the above-mentioned sending operation can also be touch operations implemented through input devices such as a mouse and keyboard.

[0096] Through the above steps S241 to S243, the search processing method provided in the embodiment of the present application can be run on the client, embodying a visual interactive method to realize the search processing function. This visual interactive method can more intuitively provide the preset industry question and answer scenario to the user through the client, so that the user can more conveniently make an e-commerce service search request and trigger the query of the e-commerce service search results. This method is user-friendly and convenient for operation, and the user experience is good.

[0097] It should be noted that 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.

[0098] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0100] Example 2

[0101] In the operating environment as in Example 1, the present application provides another search processing method as shown in Figure 4. Figure 4 is a flow chart of another search processing method according to Example 2 of the present application. As shown in Figure 4, the search processing method includes:

[0102] Step S41, obtaining a search request;

[0103] Step S42: Analyze the attribute characteristics of the search request using a differential search index model to generate auxiliary information associated with the search request, and perform industry knowledge reasoning on the search request and the auxiliary information to output a target document identifier, wherein the auxiliary information is at least one target attribute characteristic of the preset industry knowledge corresponding to the search request;

[0104] Step S43: Obtain search results corresponding to the search request based on the target document identifier.

[0105] The search request may be a query request in a target application scenario. The target application scenario may include, but is not limited to, scenarios involving LLM-based search in fields such as e-commerce, education, healthcare, conferences, social networks, financial products, logistics, and navigation. Correspondingly, the preset industry knowledge is the industry knowledge corresponding to the target application scenario.

[0106] The auxiliary information is derived from pre-set industry knowledge and at least one target attribute feature, which includes multiple attribute features obtained by mining the attribute features of the search request. The combination of the search request and auxiliary information serves as input to a differential search index (DSI) model. The DSI model performs industry knowledge inference on the search request and auxiliary information to output a target document identifier. This target document identifier and the corresponding document content are then used as the search results for the search request.

[0107] It can be seen that the preset industry knowledge and various attribute characteristics corresponding to the search request are taken into consideration in the above search processing process for the search request. Therefore, the above search processing process can have good intelligent search performance within the application scenario of the preset industry, that is, it can obtain accurate search results to meet the personalized search needs of specific industries.

[0108] In an embodiment of the present application, a search request is first obtained, and attribute feature analysis of the search request is performed by adopting a differential search index model to generate auxiliary information associated with the search request, and industry knowledge reasoning is performed on the search request and the auxiliary information to output a target document identifier, wherein the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request, and further based on the target document identifier, the search results corresponding to the search request are obtained. In the above process, the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request. Therefore, the search processing method provided by the present application introduces the attribute features corresponding to the preset industry knowledge into the search processing by mining the attribute features of the search request, thereby achieving the purpose of performing search processing on the preset industry knowledge, thereby achieving the technical effect of improving the accuracy of searching for specific industry knowledge, and thus solving the technical problem in the related art that it is difficult to inject industry knowledge into the search processing process, resulting in low search accuracy.

[0109] In an embodiment of the present application, a system consisting of a client device and a server can perform the following steps: the client device executes a search request to the server, the server executes the steps corresponding to the search processing method, uses a differential search index model to perform attribute feature analysis on the search request to generate auxiliary information associated with the search request, and performs industry knowledge reasoning on the search request and the auxiliary information to output a target document identifier, wherein the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request, obtains the search results corresponding to the search request based on the target document identifier, and returns the search results to the client (or provides the client with an interface for using the search processing function).

[0110] It should be noted that, when the operating resources of the client device can meet the deployment and operating conditions of the large model, the embodiments of the present application can be carried out in the client device.

[0111] In an optional embodiment, in step S42, a differential search index model is used to perform industry knowledge reasoning on the search request and the auxiliary information to output a target document identifier, including the following method steps:

[0112] Step S421: determining initial prompt content through the search request, wherein the initial prompt content is configured based on a preset prompt template;

[0113] Step S422: combining the initial prompt content with the auxiliary information to obtain the target prompt content;

[0114] Step S423: Use the differential search index model to perform industry knowledge reasoning on the target prompt template to obtain the target document identifier.

[0115] In the application scenario, the initial prompt content corresponding to the search request (query) is determined through the obtained search request (the initial prompt content can be a text fragment prompt), and the initial prompt content is spliced ​​with the above-mentioned auxiliary information to obtain the target prompt content. The auxiliary information is obtained by at least one target attribute feature (denoted as F) of the preset industry knowledge corresponding to the search request. Therefore, the target prompt content can be expressed as query_F. The trained DSI model is used to perform industry knowledge inference on the target prompt content query_F based on the preset industry knowledge to obtain the target document identifier, and then the search result corresponding to the search request (query) is obtained.

[0116] It is easy to notice that, through the above-mentioned search processing method provided in the embodiment of the present application, preset industry knowledge is injected into the intermediate reasoning process of the DSI model, thereby improving the accuracy of the DSI model search results and the relevance to the specified industry.

[0117] It should be noted that the preferred implementation of this embodiment can be found in the relevant description in Example 1 and will not be repeated here.

[0118] Example 3

[0119] In the operating environment as in Example 1, the present application provides another search processing method as shown in Figure 5. Figure 5 is a flow chart of another search processing method according to Example 3 of the present application. As shown in Figure 5, the search processing method includes:

[0120] Step S51: Obtain an e-commerce service search request;

[0121] Step S52: Analyze the e-commerce attribute characteristics of the e-commerce service search request to generate e-commerce service auxiliary information associated with the e-commerce service search request, wherein the e-commerce service auxiliary information is at least one target e-commerce attribute characteristic of the e-commerce service industry knowledge corresponding to the e-commerce service search request;

[0122] Step S53: obtaining e-commerce service search results corresponding to the e-commerce service search request based on the e-commerce service search request and the e-commerce service auxiliary information.

[0123] The e-commerce service search request may be a query request in an e-commerce service application scenario. Correspondingly, the e-commerce service industry knowledge is the industry knowledge corresponding to the e-commerce service application scenario, such as conversation question-and-answer knowledge, user review knowledge, etc.

[0124] The above-mentioned e-commerce service auxiliary information is obtained from the e-commerce service industry knowledge and at least one target e-commerce attribute feature, and the target attribute feature includes multiple attribute features obtained by performing attribute feature mining on the e-commerce service search request. The combination of the above-mentioned e-commerce service search request and the e-commerce service auxiliary information is used as the input of the search model (which can be LLM), and the above-mentioned e-commerce service search results are obtained by the output of the search model. It can be seen that the e-commerce service industry knowledge and the multiple attribute features corresponding to the e-commerce service search request are taken into consideration in the search processing process for the e-commerce service search request. Therefore, the above-mentioned search processing process can have good intelligent search performance within the application scenario of the preset industry, that is, it can obtain accurate e-commerce service search results to meet the personalized search needs of the e-commerce service industry.

[0125] In an embodiment of the present application, an e-commerce service search request is first obtained, and e-commerce service auxiliary information associated with the e-commerce service search request is generated by performing e-commerce attribute feature analysis on the e-commerce service search request. Further, based on the e-commerce service search request and the e-commerce service auxiliary information, the e-commerce service search result corresponding to the e-commerce service search request is obtained. In the above process, the e-commerce service auxiliary information is at least one target e-commerce attribute feature of the e-commerce service industry knowledge corresponding to the e-commerce service search request. Therefore, the search processing method provided by the present application introduces the attribute features corresponding to the e-commerce service industry knowledge into the search processing by mining the attribute features of the e-commerce service search request, thereby achieving the purpose of searching for the e-commerce service industry knowledge, thereby achieving the technical effect of improving the accuracy of searching for the e-commerce service industry knowledge, and further solving the technical problem in the related technology that it is difficult to inject industry knowledge into the search processing process, resulting in low search accuracy.

[0126] In an embodiment of the present application, a system composed of a client device and a server can perform the following steps: the client device executes an e-commerce service search request to the server, the server executes the steps corresponding to the search processing method, performs e-commerce attribute feature analysis on the e-commerce service search request, and generates e-commerce service auxiliary information associated with the e-commerce service search request, wherein the e-commerce service auxiliary information is at least one target e-commerce attribute feature of the e-commerce service industry knowledge corresponding to the e-commerce service search request, based on the e-commerce service search request and the e-commerce service auxiliary information, obtains the e-commerce service search result corresponding to the e-commerce service search request, and returns the e-commerce service search result to the client (or provides the client with an interface for using the search processing function).

[0127] It should be noted that, when the operating resources of the client device can meet the deployment and operating conditions of the large model, the embodiments of the present application can be carried out in the client device.

[0128] In addition, in addition to e-commerce service scenarios, the search processing method provided in Example 1 can also be extended to legal question-and-answer scenarios, medical service scenarios, educational question-and-answer scenarios, etc.

[0129] In the legal question and answer scenario, the search processing method includes: obtaining a legal question and answer search request; performing e-commerce attribute feature analysis on the legal question and answer search request, and generating legal question and answer auxiliary information associated with the legal question and answer search request, wherein the legal question and answer auxiliary information is at least one target e-commerce attribute feature of the legal question and answer industry knowledge corresponding to the legal question and answer search request; based on the legal question and answer search request and the legal question and answer auxiliary information, obtaining the legal question and answer search results corresponding to the legal question and answer search request.

[0130] In a medical service scenario, the search processing method includes: obtaining a medical service search request; performing e-commerce attribute feature analysis on the medical service search request to generate medical service auxiliary information associated with the medical service search request, wherein the medical service auxiliary information is at least one target e-commerce attribute feature of the medical service industry knowledge corresponding to the medical service search request; based on the medical service search request and the medical service auxiliary information, obtaining medical service search results corresponding to the medical service search request.

[0131] In the education question and answer scenario, the search processing method includes: obtaining an education question and answer search request; performing e-commerce attribute feature analysis on the education question and answer search request, and generating education question and answer auxiliary information associated with the education question and answer search request, wherein the education question and answer auxiliary information is at least one target e-commerce attribute feature of the education question and answer industry knowledge corresponding to the education question and answer search request; based on the education question and answer search request and the education question and answer auxiliary information, obtaining the education question and answer search results corresponding to the education question and answer search request.

[0132] It should be noted that the preferred implementation of this embodiment can be found in the relevant description in Example 1 and will not be repeated here.

[0133] Example 4

[0134] According to an embodiment of the present application, an embodiment of a device for implementing the above-mentioned search processing method is also provided. FIG6 is a structural diagram of a search processing device according to embodiment 4 of the present application. As shown in FIG6 , the device includes:

[0135] Acquisition module 601, used to obtain a search request;

[0136] A generating module 602 is configured to perform attribute feature analysis on the search request and generate auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request;

[0137] The processing module 603 is configured to obtain search results corresponding to the search request based on the search request and the auxiliary information.

[0138] Optionally, the above-mentioned generation module 602 is also used to: extract industry knowledge attributes from the search request to obtain attribute extraction results; perform attribute labeling on the attribute extraction results to obtain attribute labeling results, wherein the attribute labeling results are used to indicate the knowledge attributes of the preset industry knowledge in multiple dimensions; perform feature selection on the attribute labeling results to obtain auxiliary information.

[0139] Optionally, the above-mentioned generation module 602 is also used to: perform word segmentation on the search request based on preset industry knowledge to obtain a first attribute extraction result; perform named entity recognition on the search request based on the preset industry knowledge to obtain a second attribute extraction result; perform synonym expansion on the first attribute extraction result based on the preset industry knowledge to obtain a third attribute extraction result; perform keyword extraction on the search request based on the preset industry knowledge to obtain a fourth attribute extraction result; rewrite the expression form of the search request based on the preset industry knowledge to obtain a fifth attribute extraction result.

[0140] Optionally, the generation module 602 is further configured to: use a labeling model corresponding to preset industry knowledge to perform attribute labeling on the attribute extraction result to obtain an attribute labeling result, wherein the attribute labeling result includes: a plurality of attribute feature combinations.

[0141] Optionally, the above-mentioned generation module 602 is also used to: select multiple candidate feature combinations from the attribute labeling results; calculate the information gain of the multiple candidate feature combinations for the preset results; and select at least one target attribute feature from the multiple candidate feature combinations based on the information gain to obtain auxiliary information.

[0142] Optionally, the generation module 602 is further configured to: obtain a first probability of obtaining a preset result based on the search request and the auxiliary information prediction, and obtain a second probability of obtaining a preset result based on the search request prediction; and calculate information gain using the first probability and the second probability.

[0143] Optionally, the generating module 602 is further configured to select a candidate feature combination with the largest information gain from a plurality of candidate feature combinations to obtain at least one target attribute feature.

[0144] Optionally, the above-mentioned processing module 603 is also used to: use a differential search index model to perform industry knowledge inference on the search request and auxiliary information to obtain a target document identifier, wherein the differential search index model is obtained through machine learning training using multiple sets of data, and the multiple sets of data are mixed data of first training data and second training data, the first training data includes: sample prompts, sample document identifiers, and the second training data includes: sample prompts, at least one target attribute feature corresponding to the sample prompts, and a sample document identifier; obtain the search results corresponding to the search request based on the target document identifier.

[0145] Optionally, FIG7 is a schematic structural diagram of an optional search processing device according to Example 4 of the present application. As shown in FIG7 , in addition to all the modules shown in FIG6 , the device further includes a visualization module 604. A graphical user interface is provided via a terminal device, and the content displayed by the graphical user interface at least partially includes an e-commerce service search dialog box. The visualization module 604 is configured to: determine a search request in response to an input operation performed on the e-commerce service search dialog box; perform attribute feature analysis on the search request to generate auxiliary information in response to a send operation performed on the e-commerce service search dialog box, and obtain search results based on the search request and the auxiliary information; and display the search results in the e-commerce service search dialog box.

[0146] In an embodiment of the present application, a search request is first obtained through an acquisition module, and an attribute feature analysis of the search request is performed through a generation module to generate auxiliary information associated with the search request. A processing module is further used to obtain search results corresponding to the search request based on the search request and the auxiliary information. In the above process, the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request. Therefore, the search processing method provided by the present application introduces the attribute features corresponding to the preset industry knowledge into the search processing by mining the attribute features of the search request, thereby achieving the purpose of performing search processing on the preset industry knowledge, thereby achieving the technical effect of improving the accuracy of searching for specific industry knowledge, and further solving the technical problem in related technologies that it is difficult to inject industry knowledge into the search processing process, resulting in low search accuracy.

[0147] It should be noted that the acquisition module 601, generation module 602, and processing module 603 correspond to steps S21 to S23 in Example 1. The three modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in Example 1. It should be noted that the modules or units can be hardware components or software components stored in a memory and processed by one or more processors. The modules can also be part of the device and can run in the operating environment provided in Example 1.

[0148] According to an embodiment of the present application, another embodiment of a device for implementing the search processing method in the above embodiment 2 is also provided. FIG8 is a schematic structural diagram of another search processing device according to embodiment 4 of the present application. As shown in FIG8 , the device includes:

[0149] Acquisition module 801, used to obtain a search request;

[0150] A generation module 802 is configured to perform attribute feature analysis on a search request using a differential search index model to generate auxiliary information associated with the search request, and to perform industry knowledge reasoning on the search request and the auxiliary information to output a target document identifier, wherein the auxiliary information is at least one target attribute feature of preset industry knowledge corresponding to the search request;

[0151] The processing module 803 is configured to obtain search results corresponding to the search request based on the target document identifier.

[0152] Optionally, the above-mentioned generation module 802 is also used to: determine the initial prompt content through a search request, wherein the initial prompt content is configured based on a preset prompt template; splice the initial prompt content with auxiliary information to obtain a target prompt template; use a differential search index model to perform industry knowledge inference on the target prompt template to obtain a target document identifier.

[0153] It should be noted that the acquisition module 801, generation module 802, and processing module 803 described above correspond to steps S41 to S43 in Example 2. The examples and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 2. It should be noted that the modules or units described above may be hardware components or software components stored in a memory and processed by one or more processors. The modules may also be part of a device and may run in the operating environment provided in Example 1.

[0154] According to an embodiment of the present application, another embodiment of a device for implementing the search processing method in the above embodiment 3 is also provided. FIG9 is a structural diagram of another search processing device according to embodiment 4 of the present application. As shown in FIG9 , the device includes:

[0155] Acquisition module 901, used to obtain e-commerce service search request;

[0156] A generating module 902 is configured to analyze e-commerce attribute characteristics of an e-commerce service search request and generate e-commerce service auxiliary information associated with the e-commerce service search request, wherein the e-commerce service auxiliary information is at least one target e-commerce attribute characteristic of the e-commerce service industry knowledge corresponding to the e-commerce service search request;

[0157] The acquisition module 903 is configured to acquire e-commerce service search results corresponding to the e-commerce service search request based on the e-commerce service search request and the e-commerce service auxiliary information.

[0158] It should be noted that the acquisition module 901, generation module 902, and processing module 903 correspond to steps S51 to S53 in Example 3. The examples and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 3. It should be noted that the modules or units can be hardware components or software components stored in a memory and processed by one or more processors. The modules can also be part of the device and can run in the operating environment provided in Example 1.

[0159] It should be noted that the preferred implementation of this embodiment can be found in the relevant descriptions in Example 1, Example 2 or Example 3, and will not be repeated here.

[0160] Example 5

[0161] According to an embodiment of the present application, an electronic device is further provided. The electronic device may be a computer terminal. The computer terminal may be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may be replaced by a terminal device such as a mobile terminal.

[0162] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of a computer network.

[0163] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the search processing method: obtaining a search request; performing attribute feature analysis on the search request to generate auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request; based on the search request and the auxiliary information, obtaining the search results corresponding to the search request.

[0164] Optionally, Figure 10 is a structural block diagram of a computer terminal according to Example 5 of the present application. As shown in Figure 10, the computer terminal 100 may include: one or more (only one is shown in the figure) processors 1002, a memory 1004, a storage controller 1006, and a peripheral interface 1008, wherein the peripheral interface 1008 is connected to the radio frequency module, the audio module and the display.

[0165] Among them, the memory 1004 can be used to store software programs and modules, such as the program instructions / modules corresponding to the search processing method and device in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned search processing method. The memory 1004 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include a memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 100 via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0166] The processor 1002 can call the information and application stored in the memory through the transmission device to perform the following steps: obtain a search request; perform attribute feature analysis on the search request to generate auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request; based on the search request and the auxiliary information, obtain the search results corresponding to the search request.

[0167] Optionally, the processor 1002 may also execute the program code of the following steps: extracting industry knowledge attributes from the search request to obtain attribute extraction results; labeling the attribute extraction results to obtain attribute labeling results, wherein the attribute labeling results are used to indicate the knowledge attributes of the preset industry knowledge in multiple dimensions; and performing feature selection on the attribute labeling results to obtain auxiliary information.

[0168] Optionally, the processor 1002 may also execute the following program code steps: based on preset industry knowledge, perform word segmentation on the search request to obtain a first attribute extraction result; based on the preset industry knowledge, perform named entity recognition on the search request to obtain a second attribute extraction result; based on the preset industry knowledge, perform synonym expansion on the first attribute extraction result to obtain a third attribute extraction result; based on the preset industry knowledge, perform keyword extraction on the search request to obtain a fourth attribute extraction result; based on the preset industry knowledge, rewrite the expression form of the search request to obtain a fifth attribute extraction result.

[0169] Optionally, the processor 1002 may also execute the program code of the following steps: using a labeling model corresponding to preset industry knowledge to label the attribute extraction results, and obtain attribute labeling results, wherein the attribute labeling results include: multiple attribute feature combinations.

[0170] Optionally, the processor 1002 may also execute the program code of the following steps: selecting multiple candidate feature combinations from the attribute labeling results; calculating the information gain of the multiple candidate feature combinations for the preset results; and selecting at least one target attribute feature from the multiple candidate feature combinations based on the information gain to obtain auxiliary information.

[0171] Optionally, the processor 1002 may also execute the following program code: obtaining a first probability of obtaining a preset result based on the search request and the auxiliary information prediction, and obtaining a second probability of obtaining a preset result based on the search request prediction; and calculating information gain using the first probability and the second probability.

[0172] Optionally, the processor 1002 may further execute program code of the following steps: selecting a candidate feature combination with the largest information gain from a plurality of candidate feature combinations to obtain at least one target attribute feature.

[0173] Optionally, the processor 1002 may also execute the program code of the following steps: using a differential search index model to perform industry knowledge inference on the search request and auxiliary information to obtain a target document identifier, wherein the differential search index model is obtained through machine learning training using multiple sets of data, and the multiple sets of data are mixed data of first training data and second training data, the first training data includes: sample prompts, sample document identifiers, and the second training data includes: sample prompts, at least one target attribute feature corresponding to the sample prompts, and a sample document identifier; obtaining search results corresponding to the search request based on the target document identifier.

[0174] Optionally, the processor 1002 may also execute the program code for the following steps: determining a search request in response to an input operation performed on the e-commerce service search dialog box; performing attribute feature analysis on the search request to generate auxiliary information in response to a send operation performed on the e-commerce service search dialog box, and obtaining search results based on the search request and the auxiliary information; and displaying the search results in the e-commerce service search dialog box.

[0175] The processor 1002 can call the information and application stored in the memory through the transmission device to perform the following steps: obtain a search request; use a differential search index model to perform attribute feature analysis on the search request to generate auxiliary information associated with the search request, and perform industry knowledge reasoning on the search request and the auxiliary information to output a target document identifier, wherein the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request; and obtain the search results corresponding to the search request based on the target document identifier.

[0176] Optionally, the processor 1002 may also execute the program code of the following steps: determining the initial prompt content through a search request, wherein the initial prompt content is configured based on a preset prompt template; splicing the initial prompt content with auxiliary information to obtain a target prompt template; and using a differential search index model to perform industry knowledge inference on the target prompt template to obtain a target document identifier.

[0177] The processor 1002 can call the information and application stored in the memory through the transmission device to execute the following steps: obtain an e-commerce service search request; perform e-commerce attribute feature analysis on the e-commerce service search request, and generate e-commerce service auxiliary information associated with the e-commerce service search request, wherein the e-commerce service auxiliary information is at least one target e-commerce attribute feature of the e-commerce service industry knowledge corresponding to the e-commerce service search request; based on the e-commerce service search request and the e-commerce service auxiliary information, obtain the e-commerce service search result corresponding to the e-commerce service search request.

[0178] According to an embodiment of the present application, a solution for a computer terminal for implementing a search processing method is provided. First, a search request is obtained, and auxiliary information associated with the search request is generated by performing attribute feature analysis on the search request. Further, based on the search request and the auxiliary information, the search results corresponding to the search request are obtained. In the above process, the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request. Therefore, the search processing method provided by the present application introduces the attribute features corresponding to the preset industry knowledge into the search processing by mining the attribute features of the search request, thereby achieving the purpose of performing search processing on the preset industry knowledge, thereby achieving the technical effect of improving the accuracy of searching for specific industry knowledge, and further solving the technical problem in the related art that it is difficult to inject industry knowledge into the search processing process, resulting in low search accuracy.

[0179] Those skilled in the art will appreciate that the structure shown in FIG10 is merely illustrative, and the computer terminal may also be a terminal device such as a smartphone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, or a mobile internet device (MID). FIG10 does not limit the structure of the computer terminal. For example, the computer terminal 100 may include more or fewer components (such as a network interface, a display device, etc.) than those shown in FIG10 , or may have a configuration different from that shown in FIG10 .

[0180] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0181] Example 6

[0182] According to an embodiment of the present application, a computer-readable storage medium is further provided. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the search processing method provided in the above embodiment 1, embodiment 2 or embodiment 3.

[0183] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0184] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: obtaining a search request; performing attribute feature analysis on the search request to generate auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute feature of preset industry knowledge corresponding to the search request; and obtaining search results corresponding to the search request based on the search request and the auxiliary information.

[0185] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: extracting industry knowledge attributes from the search request to obtain attribute extraction results; performing attribute labeling on the attribute extraction results to obtain attribute labeling results, wherein the attribute labeling results are used to indicate knowledge attributes of preset industry knowledge in multiple dimensions; performing feature selection on the attribute labeling results to obtain auxiliary information.

[0186] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: based on preset industry knowledge, performing word segmentation processing on the search request to obtain a first attribute extraction result; based on the preset industry knowledge, performing named entity recognition on the search request to obtain a second attribute extraction result; based on the preset industry knowledge, performing synonym expansion on the first attribute extraction result to obtain a third attribute extraction result; based on the preset industry knowledge, performing keyword extraction on the search request to obtain a fourth attribute extraction result; based on the preset industry knowledge, rewriting the expression form of the search request to obtain a fifth attribute extraction result.

[0187] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: using a labeling model corresponding to preset industry knowledge to perform attribute labeling on the attribute extraction results to obtain attribute labeling results, wherein the attribute labeling results include: multiple attribute feature combinations.

[0188] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: selecting multiple candidate feature combinations from the attribute labeling results; calculating the information gain of the multiple candidate feature combinations for the preset results; and based on the information gain, selecting at least one target attribute feature from the multiple candidate feature combinations to obtain auxiliary information.

[0189] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining a first probability of obtaining a preset result based on the search request and the auxiliary information prediction, and obtaining a second probability of obtaining the preset result based on the search request prediction; and calculating the information gain using the first probability and the second probability.

[0190] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: selecting a candidate feature combination with the largest information gain from multiple candidate feature combinations to obtain at least one target attribute feature.

[0191] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: using a differential search index model to perform industry knowledge inference on the search request and auxiliary information to obtain a target document identification, wherein the differential search index model is obtained through machine learning training using multiple sets of data, and the multiple sets of data are mixed data of first training data and second training data, the first training data includes: sample prompts, sample document identification, and the second training data includes: sample prompts, at least one target attribute feature corresponding to the sample prompts, and a sample document identification; obtaining search results corresponding to the search request based on the target document identification.

[0192] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining a search request in response to an input operation performed on the e-commerce service search dialog box; performing attribute feature analysis on the search request to generate auxiliary information in response to a send operation performed on the e-commerce service search dialog box, and obtaining search results based on the search request and the auxiliary information; and displaying the search results in the e-commerce service search dialog box.

[0193] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: obtaining a search request; performing attribute feature analysis on the search request using a differential search index model to generate auxiliary information associated with the search request, and performing industry knowledge reasoning on the search request and the auxiliary information to output a target document identifier, wherein the auxiliary information is at least one target attribute feature of the preset industry knowledge corresponding to the search request; and obtaining search results corresponding to the search request based on the target document identifier.

[0194] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining the initial prompt content through a search request, wherein the initial prompt content is configured based on a preset prompt template; splicing the initial prompt content with auxiliary information to obtain a target prompt template; and using a differential search index model to perform industry knowledge inference on the target prompt template to obtain a target document identifier.

[0195] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: obtaining an e-commerce service search request; performing e-commerce attribute feature analysis on the e-commerce service search request to generate e-commerce service auxiliary information associated with the e-commerce service search request, wherein the e-commerce service auxiliary information is at least one target e-commerce attribute feature of the e-commerce service industry knowledge corresponding to the e-commerce service search request; and obtaining e-commerce service search results corresponding to the e-commerce service search request based on the e-commerce service search request and the e-commerce service auxiliary information.

[0196] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0197] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0198] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0199] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0200] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0201] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, ROM, RAM, mobile hard drives, magnetic disks or optical disks.

[0202] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A search processing method, comprising: Get the search request; Performing attribute feature analysis on the search request to generate auxiliary information associated with the search request, wherein the auxiliary information is at least one target attribute feature of preset industry knowledge corresponding to the search request; Based on the search request and the auxiliary information, a search result corresponding to the search request is obtained.

2. The search processing method according to claim 1, wherein: Performing attribute feature analysis on the search request to generate the auxiliary information associated with the search request includes: Extracting industry knowledge attributes from the search request to obtain attribute extraction results; Performing attribute labeling on the attribute extraction result to obtain an attribute labeling result, wherein the attribute labeling result is used to indicate knowledge attributes of the preset industry knowledge in multiple dimensions; Feature selection is performed on the attribute labeling result to obtain the auxiliary information.

3. The search processing method according to claim 2, wherein: The industry knowledge attributes are extracted from the search request, and the attribute extraction results obtained include one or more of the following: Based on the preset industry knowledge, the search request is segmented to obtain a first attribute extraction result; Based on the preset industry knowledge, performing named entity recognition on the search request to obtain a second attribute extraction result; Based on the preset industry knowledge, performing synonym expansion on the first attribute extraction result to obtain a third attribute extraction result; Based on the preset industry knowledge, keyword extraction is performed on the search request to obtain a fourth attribute extraction result; Based on the preset industry knowledge, the search request is rewritten in a form of expression to obtain a fifth attribute extraction result.

4. The search processing method according to claim 2, wherein: The attribute extraction result is attributed and the attribute annotation result is obtained, including: The attribute extraction result is annotated using the annotation model corresponding to the preset industry knowledge to obtain the attribute annotation result, wherein the attribute annotation result includes: a plurality of attribute feature combinations.

5. The search processing method according to claim 2, wherein: Feature selection is performed on the attribute labeling result to obtain the auxiliary information including: Selecting multiple candidate feature combinations from the attribute labeling results; Calculating the information gain of the plurality of candidate feature combinations for a preset result; Based on the information gain, the at least one target attribute is selected from the plurality of candidate feature combinations. Features, and obtain the auxiliary information.

6. The search processing method according to claim 5, wherein: Calculating the information gain of the plurality of candidate feature combinations for the preset result includes: Obtaining a first probability of obtaining the preset result based on the search request and the auxiliary information prediction, and obtaining a second probability of obtaining the preset result based on the search request prediction; The information gain is calculated using the first probability and the second probability.

7. The search processing method according to claim 5, wherein: Based on the information gain, selecting the at least one target attribute feature from the plurality of candidate feature combinations includes: The candidate feature combination with the largest information gain is selected from the multiple candidate feature combinations to obtain the at least one target attribute feature.

8. The search processing method according to claim 1, wherein: Based on the search request and the auxiliary information, obtaining search results corresponding to the search request includes: A differential search index model is used to perform industry knowledge reasoning on the search request and the auxiliary information to obtain a target document identifier, wherein the differential search index model is obtained by machine learning training using multiple sets of data, and the multiple sets of data are mixed data of first training data and second training data, the first training data includes: sample prompts, sample document identifiers, and the second training data includes: the sample prompts, at least one target attribute feature corresponding to the sample prompts, and the sample document identifier; The search result corresponding to the search request is obtained based on the target document identifier.

9. The search processing method according to claim 1, wherein: A graphical user interface is provided through a terminal device, and the content displayed by the graphical user interface at least partially includes an e-commerce service search dialog box, and the search processing method further includes: In response to an input operation performed on the e-commerce service search dialog box, determining an e-commerce service search request; In response to a sending operation performed on the e-commerce service search dialog box, performing an e-commerce service attribute feature analysis on the e-commerce service search request to generate the e-commerce service auxiliary information, and acquiring the e-commerce service search result based on the e-commerce service search request and the e-commerce service auxiliary information; The e-commerce service search results are displayed in the e-commerce service search dialog box.

10. A search processing method, comprising: Get the search request; Using a differential search index model to perform attribute feature analysis on the search request to generate auxiliary information associated with the search request, and performing industry knowledge reasoning on the search request and the auxiliary information to output a target document identifier, wherein the auxiliary information is at least one target attribute feature of preset industry knowledge corresponding to the search request; The search result corresponding to the search request is obtained based on the target document identifier.

11. The search processing method according to claim 10, wherein: Using the differential search index model to perform industry knowledge reasoning on the search request and the auxiliary information to output the target document identifier includes: Determining initial prompt content through the search request, wherein the initial prompt content is configured based on a preset prompt template; splicing the initial prompt content with the auxiliary information to obtain target prompt content; The differential search index model is used to perform industry knowledge reasoning on the target prompt template to obtain the target document identifier.

12. A search processing method, comprising: Get e-commerce service search request; Performing e-commerce attribute feature analysis on the e-commerce service search request to generate e-commerce service auxiliary information associated with the e-commerce service search request, wherein the e-commerce service auxiliary information is at least one target e-commerce attribute feature of the e-commerce service industry knowledge corresponding to the e-commerce service search request; Based on the e-commerce service search request and the e-commerce service auxiliary information, an e-commerce service search result corresponding to the e-commerce service search request is obtained.

13. An electronic device comprising: A memory storing an executable program; A processor is configured to run the program, wherein the program executes the search processing method described in any one of claims 1 to 12 when running.

14. A computer-readable storage medium comprising a stored executable program, wherein: When the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the search processing method described in any one of claims 1 to 12.

Images