Data retrieval processing method, apparatus, device, and storage medium

Abstract

The application discloses a data retrieval processing method, device and equipment and a storage medium. The method comprises the following steps: setting a knowledge graph for each tenant in advance, wherein the knowledge graph comprises labels and corresponding relationships between the labels; obtaining an input search term; determining a label corresponding to the search term according to the search term and the knowledge graph; and determining a digital asset corresponding to the label according to the label. According to the method, the knowledge graph is established for each tenant in advance, the search is performed according to the knowledge graph during the search, the target label is found according to the label corresponding relationship after the input of the search term, and the accuracy of the search performed by the search term is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more particularly, to a method, apparatus, device, and storage medium for processing retrieved data. Background Art

[0002] In the field of content marketing, for the retrieval of a large amount of marketing content, the user's search terms are highly relevant to the field, and there are also industry characteristics in different industries. Relying solely on the word segmentation of a simple search system is difficult to achieve good search results. For example, A.O. Smith has a product model called "Thinker's Home". Using a conventional search engine and entering the search term "Thinker", the relevant product cannot be found. Summary of the Invention

[0003] The main purpose of this application is to provide a method, apparatus, device, and storage medium for processing retrieved data to solve the above problems.

[0004] To achieve the above object, according to one aspect of this application, a method for processing retrieved data is provided, including:

[0005] Pre-set a knowledge graph for each tenant, where the knowledge graph includes: tags and the associated correspondence relationships between the tags;

[0006] Obtain the input search term;

[0007] Determine the tag corresponding to the search term according to the search term and the knowledge graph;

[0008] Determine the digital asset corresponding to the tag according to the tag.

[0009] In one implementation, the tag includes a brand tag; pre-setting a knowledge graph for each tenant includes:

[0010] Pre-set the mutual exclusion relationship between brand tags;

[0011] After receiving the brand search term input by the user;

[0012] Determine the brand mutually exclusive to the brand search term according to the mutual exclusion relationship between the brand search term and the brand tags;

[0013] In the search results, block the relevant content corresponding to the brand tag mutually exclusive to the brand tag.

[0014] In one implementation, the pre-setting of the mutual exclusion relationship between tags includes:

[0015] For any tenant, obtain the industry information and tags of the tenant;

[0016] Identify the companies in the same industry within the industry information, and the tags for each company in the same industry;

[0017] Set the labels of the companies in the same industry and the labels of the tenants to be mutually exclusive.

[0018] In one implementation, the association relationships of the associated tags are preset;

[0019] After receiving the input search terms;

[0020] The associated brands are determined based on the relationship between the search terms and the tags;

[0021] The associated tags are displayed in the search results.

[0022] In one implementation, after receiving the user's input search terms;

[0023] The search terms are segmented; the product names and product series within the search terms are determined.

[0024] Searching for the product series individually yields the corresponding search results.

[0025] In one implementation, if multiple product series are obtained after segmenting the brand search terms;

[0026] Then, perform an AND operation on the multiple product series to obtain the processing search terms;

[0027] Search results are obtained by performing a search using the described search terms.

[0028] In one implementation, a knowledge graph is pre-configured for each tenant, including:

[0029] Pre-set the focus relationships between tags;

[0030] After receiving the user's input search terms;

[0031] Based on the focus relationship between the search terms and the tags, identify the brands that are most relevant to the search terms;

[0032] The search results will display relevant content corresponding to tags that are closely related to the main tags.

[0033] To achieve the above objectives, according to a second aspect of this application, a data retrieval processing apparatus is provided, comprising:

[0034] The configuration module is used to pre-configure a knowledge graph for each tenant, the knowledge graph including: tags and the association relationships between tags;

[0035] The acquisition module is used to acquire the input search terms;

[0036] The tag lookup module is used to determine the tag corresponding to the search term based on the search term and the knowledge graph.

[0037] The product search module is used to determine the digital asset corresponding to the tag based on the tag.

[0038] In one implementation, the setting module is further configured to pre-set the mutual exclusion relationship between tags;

[0039] The receiving module is also used to, after receiving the search terms entered by the user;

[0040] The tag search module is also used to determine tags that are mutually exclusive with the brand search terms based on the mutual exclusion relationship between the search terms and the tags;

[0041] The product search module is also used to filter out related content corresponding to tags that are mutually exclusive with the aforementioned tag in the search results.

[0042] In one implementation, the setting module is further configured to, for any given tenant, obtain the tenant's industry information and tags;

[0043] Identify the companies in the same industry within the industry information, and the tags for each company in the same industry;

[0044] Set the labels of the companies in the same industry and the labels of the tenants to be mutually exclusive.

[0045] In one implementation, the setting module is further configured to pre-set the association relationship of the associated tags;

[0046] The tag lookup module is also used to, after receiving the input search term, determine the associated tags associated with the search term based on the relationship between the search term and the tags;

[0047] The product search module is also used to retrieve related products by searching for the associated tags.

[0048] In one embodiment, the tag search module is further configured to, after receiving the search terms input by the user, perform word segmentation on the search terms, and determine the product name and product series in the search terms;

[0049] The product search module is also used to search for the product series individually and obtain the search results corresponding to the product series.

[0050] In one implementation, the tag search module further includes: a word segmentation unit, used to segment the search terms;

[0051] The processing unit is used to perform AND operations on multiple product series obtained after word segmentation of the search terms to obtain processed search terms;

[0052] The product search module is also used to retrieve search results by searching according to the processing search terms.

[0053] In one implementation, the setting module is also used to pre-set the focus relationship between tags;

[0054] The tag search module is used to receive the search terms input by the user and determine the brand tags that are closely related to the search terms based on the focus relationship between the search terms and the tags.

[0055] The product search module is also used to retrieve relevant content by searching for tags that are closely related to the search terms.

[0056] In the embodiments of this application, the above-described method of this application improves the accuracy of retrieval by pre-establishing a knowledge graph for each tenant and performing retrieval based on the knowledge graph. After the search terms are entered, the target tags are found according to the tag correspondence. Attached Figure Description

[0057] The accompanying drawings, which form part of this application, are used to provide a further understanding of the application and to make other features, objects, and advantages of the application more apparent. The illustrative embodiments and descriptions of this application are used to explain the application and do not constitute an undue limitation of the application. In the drawings:

[0058] Figure 1 This is a flowchart of a data retrieval processing method according to an embodiment of this application;

[0059] Figure 2 This is a schematic diagram of the structure of a data retrieval processing device according to an embodiment of this application;

[0060] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0061] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0062] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0063] Furthermore, the terms "installation," "setup," "equipped with," "connection," "linking," and "socketing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral structure; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, components, or parts. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances.

[0064] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0065] This application proposes a data retrieval processing method, see appendix. Figure 1 The flowchart shown illustrates a data retrieval processing method; the method includes:

[0066] Step S102: Pre-set a knowledge graph for each tenant, the knowledge graph including: tags and the association correspondence between tags.

[0067] The tenants are enterprise customers. Each tenant corresponds to one enterprise customer. The server provides storage space for tenant data across multiple tenants. The users are marketers who search for necessary marketing materials on the server. Each tenant's data storage area is pre-configured on the server to ensure data isolation between different tenants, enhancing privacy. The data storage area contains a massive amount of marketing product data for each tenant.

[0068] For example, in the server, a mapping is established between the tags "Smith" and "Thinker". These two tags, and their mapping, can be stored in the storage area of ​​the tenant "Smith Water Purifier".

[0069] When marketers conduct searches, they can search across all possible storage areas after entering search terms; this process is not limited by any particular storage area.

[0070] Furthermore, marketers can include more search criteria when conducting searches, such as...

[0071] Selecting "White Background Image" allows you to search only for content within that tenant's storage area that meets both the search keywords and the search condition "white background image." This means you can search only for information relevant to that tenant within their storage area. If you're only searching within this combined range, you can further refine your search terms.

[0072] For example, if the company is in the machinery manufacturing industry, enter the specifications of one of its products.

[0073] If the tenant is in the service industry, such as the catering industry, you can also enter the restaurant's style, such as Mediterranean style, to search for relevant advertising images and other materials.

[0074] Step S104: Obtain the input search terms;

[0075] Step S106: Determine the tag corresponding to the search term based on the search term and the knowledge graph;

[0076] Step S108: Determine the digital asset corresponding to the tag based on the tag.

[0077] Digital assets include a company's brand assets, such as font files and logos; marketing materials, such as product promotional videos and flyer designs; and e-commerce product content, such as product images and product detail pages.

[0078] Tags include brand, category, series, sub-series, etc.

[0079] For example, after a user enters "thinker," the knowledge graph can find the target tag "Smith," thereby finding relevant content for the corresponding product.

[0080] The method described above in this application improves the accuracy of retrieval by pre-establishing a knowledge graph for each tenant and then searching based on the knowledge graph during the retrieval process. After the search terms are entered, the target tags are found based on the tag correspondence.

[0081] Pre-configure a knowledge graph for each tenant, including:

[0082] Pre-set the mutual exclusion relationship between tags;

[0083] After receiving the user's input search terms;

[0084] Based on the mutual exclusion relationship between the search terms and the tags, determine the tags that are mutually exclusive with the search terms;

[0085] In the search results, content related to tags that are mutually exclusive with the stated tag is hidden.

[0086] In one implementation, after receiving a brand search term input by a user, a tag mutually exclusive with the search term is determined based on the mutual exclusion relationship between the search term and the tag; in the search results, the relevant content corresponding to the tag mutually exclusive with the tag is blocked.

[0087] For example, searching for "Clear shampoo" will result in mutually exclusive brand and category information, and will not bring up other brands of shampoo or other Clear products.

[0088] When marketers conduct searches, they sometimes retrieve similar brands with high relevance to enrich their search ideas. In one implementation, the association relationships of related tags can be pre-set in the server.

[0089] After receiving the input tag search terms;

[0090] Based on the relationship between the tag search terms and the tag tags, determine the associated tags that are associated with the tag search terms;

[0091] The associated tags are displayed in the search results.

[0092] The label can be a brand or a model number, etc.

[0093] For example, taking car brands as an example, new energy vehicle brands include BYD, Zotye, BAIC, Chery, SAIC, JAC, Geely, and GAC Trumpchi. Therefore, BYD and Zotye can be set as a strong association. When a user searches for ads related to BYD, Zotye products associated with BYD will also be found in the search results.

[0094] For example, Starbucks and Maan Coffee are two very famous coffee shops. If a user designs an ad for Starbucks, when someone searches for Starbucks, they can set Starbucks and Maan Coffee to have a strong association, displaying relevant product information about Maan Coffee.

[0095] Alternatively, they could be differentiated based on nationality, with Starbucks and KFC being strongly associated, since they are both American brands and might have more to draw inspiration from in terms of design style.

[0096] The search results can include images and case studies related to Starbucks advertisements. Case studies can include images and text.

[0097] The method of this invention greatly improves the efficiency of marketing personnel, significantly enhancing their work productivity. By inputting search terms, marketing personnel can quickly retrieve the content they want.

[0098] When users enter search terms, they may sometimes input a long string of words, including lengthy modifiers. In such cases, word segmentation is required. In one implementation, after receiving the user's search terms, word segmentation is performed on the search terms; the product name and product series within the search terms are determined; and a search is performed separately on the product series to obtain the search results corresponding to that product series.

[0099] For example, when a user enters "odor-eliminating refrigerator," the search engine performs word segmentation to determine that "odor-eliminating" is a type of refrigerator product with an odor-eliminating function. Therefore, refrigerators with this function are displayed in the search results. Refrigerators without this function are not displayed, thus improving search efficiency and effectively filtering out non-essential products.

[0100] If multiple modifiers all serve to define the product, a logical AND operation is needed to improve the accuracy of the search. In one implementation, if the search terms are segmented to obtain multiple product series, then an AND operation is performed on these product series to obtain processed search terms; the search is then performed according to these processed search terms to obtain the search results.

[0101] For example, after a user inputs "odor-neutralizing atomizing refrigerator," the system performs word segmentation on "odor-neutralizing atomizing refrigerator," determining that "odor-neutralizing" is a type of refrigerator product with odor-neutralizing function, and "atomizing" is a type of refrigerator with atomizing function. Therefore, a logical AND operation is performed to obtain the processed search terms: "odor-neutralizing AND atomizing."

[0102] The search terms "odor removal AND atomization" are used. Refrigerators with both odor removal and atomization functions are displayed. Refrigerators without these functions are not displayed, thus improving search efficiency and effectively filtering out non-essential products.

[0103] When there are many brands, users can prioritize certain brands during their searches. In one implementation, when setting up a knowledge graph for each tenant in advance, the following steps are taken:

[0104] The association relationships of related tags are preset; after receiving the input search term, the association tags associated with the search term are determined according to the association relationship between the search term and the tags; the related products are obtained by searching the associated tags.

[0105] Specifically, taking brands as an example, when determining which brands to focus on, one approach is to statistically analyze historical search data and sort each brand in descending order of the number of searches in history; identify the brand with the most searches; or select the top N brands by search frequency and set them as the brands to focus on.

[0106] For example, the search terms "A.O. Smith water purifier" and "water purifier" are pre-set as the primary focus. When a user enters "water purifier," the search prioritizes results related to A.O. Smith water purifiers.

[0107] It should be noted that the steps shown in the flowchart in 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 may be executed in a different order than that shown here.

[0108] According to a second aspect of the present invention, a data retrieval processing apparatus is also provided, see appendix. Figure 2 The diagram shows a structural schematic of a data retrieval processing device; the device includes:

[0109] Setting module 21 is used to pre-set a knowledge graph for each tenant, the knowledge graph including: tags and the association correspondence between tags;

[0110] The acquisition module 22 is used to acquire the input search terms;

[0111] Tag lookup module 23 is used to determine the tag corresponding to the search term based on the search term and the knowledge graph;

[0112] Product search module 24 is used to determine the digital asset corresponding to the tag based on the tag.

[0113] In one implementation, the setting module 21 is further configured to pre-set the mutual exclusion relationship between tags;

[0114] The tag search module 23 is also used to, after receiving the search terms entered by the user;

[0115] The brands mutually exclusive with the search terms are determined based on the mutual exclusion relationship between the search terms and the tags;

[0116] The product search module 24 is also used to filter out related content corresponding to brand tags that are mutually exclusive with the tag in the search results.

[0117] In one implementation, the setting module 21 is further configured to, for any given tenant, obtain the tenant's industry information and brand label;

[0118] Identify the companies in the same industry as those companies in the industry information, and the brand tags of each company in the same industry;

[0119] Set the brand labels of the companies in the same industry and the brand labels of the tenant to be mutually exclusive.

[0120] In one implementation, the setting module 21 is further configured to pre-set the association relationship of the associated brands;

[0121] The tag lookup module 23 is also used to, after receiving the input search term, determine the associated tags associated with the search term based on the association relationship between the search term and the tags;

[0122] The product search module 24 is also used to retrieve related products by searching the associated tags.

[0123] In one embodiment, the tag search module 23 is further configured to, after receiving the search terms input by the user, perform word segmentation on the search terms and determine the product name and product series in the search terms;

[0124] The product search module is also used to search for the product series individually and obtain the search results corresponding to the product series.

[0125] In one embodiment, the tag lookup module 23 further includes:

[0126] Word segmentation unit 231 is used to segment the search terms;

[0127] Processing unit 232 is used to perform AND operations on multiple product series obtained after word segmentation of search terms to obtain processed search terms;

[0128] The product search module 24 is also used to retrieve search results by performing a search according to the processing search terms.

[0129] In one implementation, the setting module 21 is further configured to pre-set the focus relationship between tags;

[0130] The tag search module 23 is used to, after receiving the search terms input by the user, determine the tags that are closely related to the search terms based on the focus relationship between the search terms and the tags;

[0131] The product search module 24 is also used to retrieve relevant content by searching for tags that are closely related to the search terms.

[0132] According to a third aspect of this application, an electronic device is provided, see appendix. Figure 3The schematic diagram of the electronic device shown includes at least one processor 31 and at least one memory 32; the memory 32 is used to store one or more program instructions; the processor 31 is used to run one or more program instructions to perform any of the above methods.

[0133] Fourthly, this application also proposes a computer-readable storage medium containing one or more program instructions for performing the method described in any of the preceding claims.

[0134] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0135] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0136] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0137] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0138] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0139] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0140] Obviously, those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, the present invention is not limited to any particular hardware and software combination.

[0141] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method of retrieving data processing, characterized by, Comprise: Pre-set knowledge graph for each tenant, comprising: labels and corresponding relationship between labels; Pre-set knowledge graph for each tenant, comprising: Pre-set mutual exclusion relationship between labels; After receiving the user input search term; According to the search term and the mutual exclusion relationship between the labels, determine the labels that are mutually exclusive with the search term; In the search results, shield the relevant content corresponding to the labels that are mutually exclusive with the labels; Pre-set the association relationship of the associated labels; After receiving the input search term, determine the associated brand labels associated with the search term according to the association relationship between the search term and the labels; Search the associated labels to get related products; Pre-set the data storage area of each tenant in the server to ensure that the data of different tenants are separated from each other, and after obtaining the input search term, the search can be performed in all combined storage areas or in the data storage area of the tenant; Obtain the input search term; According to the search term and the knowledge graph, determine the label corresponding to the search term; According to the label, determine the digital asset corresponding to the label; After receiving the user input search term; Carry out word segmentation processing on the search term; determine the product name and product series in the search term; Search the product series alone to get the search results corresponding to the product series.

2. The data retrieval processing method of claim 1, wherein If multiple product series are obtained after the search term is subjected to word segmentation processing; Then, the multiple product series are subjected to AND operation to obtain a processed search term; According to the processed search term, search to obtain search results.

3. The search data processing method of claim 1, wherein, The labels include brand labels; Pre-set knowledge graph for each tenant, comprising: Pre-set the focus relationship between labels; After receiving the user input search term; According to the search term and the focus relationship between the labels, determine the labels that are closely related to the search term; Search the labels that are closely related to the search term to get the corresponding relevant content.

4. A data retrieval processing device, characterized by comprising: Comprise: The setting module is used for pre-setting a knowledge graph for each tenant, and the knowledge graph comprises labels and corresponding relationship between labels; The setting module is further used for: Pre-set mutual exclusion relationship between labels; After receiving the user input search term; According to the search term and the mutual exclusion relationship between the labels, determine the labels that are mutually exclusive with the search term; In the search results, shield the relevant content corresponding to the labels that are mutually exclusive with the labels; Pre-set the association relationship of the associated labels; After receiving the input search term, determine the associated brand labels associated with the search term according to the association relationship between the search term and the labels; Search the associated labels to get related products; Pre-set the data storage area of each tenant in the server to ensure that the data of different tenants are separated from each other, and after obtaining the input search term, the search can be performed in all combined storage areas or in the data storage area of the tenant; The acquisition module is used for acquiring the input search term; A label searching module is configured to determine a label corresponding to the search term according to the search term and the knowledge graph; A product searching module is configured to determine a digital asset corresponding to the label according to the label; The product searching module is further configured to: perform word segmentation on the search term, and determine a product name and a product series in the search term; search the product series alone to obtain a search result corresponding to the product series.

5. An electronic device, comprising: Comprise: at least one processor and at least one memory; The memory is configured to store one or more program instructions; The processor is configured to run one or more program instructions to execute the method of any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, A computer readable storage medium comprises one or more program instructions for executing the method of any one of claims 1-3.

Images