Object search method, device and computer equipment based on big data

Abstract

The disclosed embodiments relate to a method, apparatus, and computer device for object search based on big data. The method comprises: obtaining multiple objects that match a search term and the names of multiple dimensions of the objects; matching the first segmentation in the search term in the order in which the first segmentation appears from the second segmentation of the names of the multiple dimensions in sequence to obtain multiple segmentation paths; determining the total weight of each segmentation path in the multiple segmentation paths based on the dimensional weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation; taking the largest total weight as the correlation between the object and the search term, and determining the object with the largest correlation from the multiple objects as the target object. The use of this method can comprehensively consider the situation in which the segmentation of the search term appears in different positions and dimensions of the product, thereby improving the accuracy and quality of the search.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the technical field of big data data access, and in particular to a method, apparatus, and computer device for object search based on big data. Background Art

[0002] Compared to general web search engines, electronic product searches have the following characteristics: First, product titles are shorter than web page titles; second, products can be searched across a wider range of dimensions, including title, brand, category, and attributes; and third, the number of products is generally smaller than the number of web pages. Given these characteristics, the search methods of general web search engines are not suitable for electronic product searches.

[0003] Existing electronic product search methods primarily involve establishing a search engine index, segmenting user-entered keywords, searching the index for the segmented results, and then intersecting multiple product sets containing the segmented keywords to obtain the searched product set. However, in existing search processes, the relevance of search results is determined solely based on whether the segmented keyword is included in the index, which reduces search accuracy and results in poor search quality. Summary of the Invention

[0004] Based on this, it is necessary to provide a search method, device and computer equipment that can improve search accuracy and search quality in response to the above technical problems.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for searching objects based on big data. The method includes:

[0006] Obtaining names of multiple objects and multiple dimensions of the objects that match the search term;

[0007] According to the order in which the first participle in the search term appears, the first participle is sequentially matched with the second participles of the names of the multiple dimensions to obtain multiple participle paths;

[0008] Determining a total weight of each segmentation path in the multiple segmentation paths according to the dimension weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation;

[0009] The largest total weight is used as the relevance between the object and the search term, and the object with the largest relevance is determined from the multiple objects as the target object.

[0010] In one embodiment, obtaining the names of multiple objects and multiple dimensions of the objects that match the search term includes:

[0011] Get multiple first participles of the search term;

[0012] The names of multiple dimensions of the object are obtained. If multiple second participles in the name match the multiple first participles, the object is one of the multiple objects that match the search term.

[0013] In one embodiment, the names of the multiple dimensions include at least one of the following:

[0014] Title name, category name, logo name.

[0015] In one embodiment, determining the total weight of each word segmentation path in the multiple word segmentation paths according to the dimension weight of the second word segmentation in the word segmentation path and the relationship weight between the second word segmentation and the next second word segmentation includes:

[0016] Obtaining the dimension weight of the second participle in the word segmentation path and the relationship weight between the second participle and the next second participle, wherein the dimension weight is obtained according to the type of dimension;

[0017] The product of the dimension weight and the relationship weight of the second word in the same word segmentation path is determined as the total weight of the word segmentation path.

[0018] In one embodiment, a method for obtaining the relationship weight between the second participle and the next second participle includes:

[0019] If the next second participle of the second participle and the second participle are located in the same dimension, the relationship weight between the second participle and the next second participle is determined to be a preset connection weight.

[0020] In one embodiment, a method for obtaining the relationship weight between the second participle and the next second participle includes:

[0021] If the next second participle of the second participle and the second participle are located in different dimensions, the relationship weight between the second participle and the next second participle is determined as a preset transfer weight.

[0022] In one embodiment, taking the largest total weight as the relevance between the object and the search term, and determining the object with the largest relevance from the multiple objects as the target object, includes:

[0023] comparing the total weight of each of the multiple segmentation paths, and taking the largest total weight as the relevance between the object and the search term;

[0024] A plurality of correlations corresponding to the plurality of objects are determined, and an object with the greatest correlation among the plurality of objects is used as a target object.

[0025] In a second aspect, the present disclosure also provides a device for searching objects based on big data. The device includes:

[0026] An acquisition module, configured to acquire a plurality of objects matching a search term and names of a plurality of dimensions of the objects;

[0027] a matching module, configured to sequentially match the first segmented words in the second segmented words of the names of the multiple dimensions according to the order in which the first segmented words appear in the search term, to obtain multiple segmented word paths;

[0028] A first determining module is configured to determine a total weight of each word segmentation path in the plurality of word segmentation paths according to a dimension weight of a second word segmentation in the word segmentation path and a relationship weight between the second word segmentation and a next second word segmentation;

[0029] The second determining module is configured to take the largest total weight as the correlation between the object and the search term, and determine the object with the largest correlation from the multiple objects as the target object.

[0030] In one embodiment, the acquisition module includes:

[0031] A first acquisition submodule, configured to acquire a plurality of first participles of a search term;

[0032] The second acquisition submodule is used to acquire the names of multiple dimensions of the object. If there are multiple second participles in the name that match the multiple first participles, the object is one of the multiple objects that match the search term.

[0033] In one embodiment, the names of the multiple dimensions include at least one of the following:

[0034] Title name, category name, logo name.

[0035] In one embodiment, the first determining module includes:

[0036] An acquisition module, configured to acquire a dimension weight of a second word segmentation in a word segmentation path and a relationship weight between the second word segmentation and a next second word segmentation, wherein the dimension weight is obtained according to a dimension type setting;

[0037] The determination module is used to respectively determine the product of the dimension weight and the relationship weight of the second word in the same word segmentation path as the total weight of the word segmentation path.

[0038] In one embodiment, the module for obtaining the relationship weight between the second participle and the next second participle includes:

[0039] The determining module is configured to determine, if the next second participle of the second participle and the second participle are located in the same dimension, a relationship weight between the second participle and the next second participle as a preset connection weight.

[0040] In one embodiment, the module for obtaining the relationship weight between the second participle and the next second participle includes:

[0041] A determination module is configured to determine, if the next second participle of the second participle and the second participle are located in different dimensions, a relationship weight between the second participle and the next second participle as a preset transfer weight.

[0042] In one embodiment, the second determining module includes:

[0043] a comparison module, configured to compare the total weight of each segmentation path in the plurality of segmentation paths, and take the largest total weight as the relevance between the object and the search term;

[0044] The determination module is configured to determine a plurality of correlations corresponding to the plurality of objects, and select an object with the greatest correlation among the plurality of objects as a target object.

[0045] In a third aspect, embodiments of the present disclosure further provide a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the embodiments of the present disclosure when executing the computer program.

[0046] In a fourth aspect, embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods of the embodiments of the present disclosure.

[0047] In a fifth aspect, embodiments of the present disclosure further provide a computer program product, comprising a computer program that, when executed by a processor, implements the steps of any one of the methods of the embodiments of the present disclosure.

[0048] The above-described search method, apparatus, computer device, storage medium, and computer program product first obtain the names of multiple objects matching the search term and multiple dimensions of each object, determine the multiple paths contained in the names of the multiple dimensions according to the search term, calculate the total weight of each path according to preset dimension weights and relationship weights, use the largest total weight among the multiple paths contained in each object as the relevance of the object with the search term, and use the object with the largest relevance as the target object of the search term. When calculating relevance, the disclosed embodiments can comprehensively consider the fact that the search term's segmentation appears in different locations and dimensions of the product, thereby improving the accuracy and quality of the search. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 1 is a flow chart of a method for searching an object based on big data in one embodiment;

[0050] Figure 2 1 is a flow chart of a method for searching an object based on big data in one embodiment;

[0051] Figure 3 Schematic diagram of a weight calculation method in one embodiment;

[0052] Figure 4 is a structural block diagram of a search device in one embodiment;

[0053] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure more clear, the embodiments of the present disclosure are further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present disclosure and are not intended to limit the embodiments of the present disclosure.

[0055] In order to facilitate those skilled in the art to understand the technical solution provided by the embodiments of the present disclosure, the technical environment in which the technical solution is implemented is described below.

[0056] The basic process for electronic product search is as follows: First, the product title, category name, brand name, and attribute name are segmented to create an index. The user enters a keyword, and the search engine segments the keyword. Each segmented result is searched in the index, and the resulting product sets are intersected to form the final search product set.

[0057] The following are examples:

[0058] Suppose a product library contains two products, Product A and Product B. Product A's title is "Brand A Mobile Phone," and Product B's title is "Brand A Bracelet." Suppose the word segmentation library contains the following words: {Brand A, Mobile Phone, Bracelet}. The word segmentation for Product A's title is <"Brand A," "Mobile Phone">, and the word segmentation for Product B's title is <"Brand A," "Bracelet">. An index file is created based on the word segmentation results. The file format is an inverted zipper, meaning that a word corresponds to the set of products containing that word. For example: Brand A: {Product A, Product B, ...}; Mobile Phone: {Product A, ...}; Brand A: {Product B, ...}.

[0059] Suppose a user searches for the keyword "Brand A wristband." Segmentation of the keyword yields the following results: Brand A, wristband. The index database is searched for the inverted zipper lists corresponding to Brand A and wristband: Brand A: {Product A, Product B, ...} Mobile phone: {Product A, ...}. The inverted zipper list is intersected to obtain Product B, and the result is returned to the user.

[0060] From the above search process, we can see that if product B is titled "Brand A Bracelet" and another product C is titled "Brand A Bracelet", when the user searches for "Brand A Bracelet", both product B and product C can be found. However, due to the different order of word segments in the names, the text relevance of product B is actually higher than that of product C.

[0061] In addition, if product D is titled "bracelet" and branded "Brand A", and the title is more important than the brand, when searching for "Brand A bracelet", both product B and product D will be found, but in reality, the text relevance of product B is greater than that of product D.

[0062] Based on actual technical requirements similar to those described above, the embodiments of the present disclosure provide a method, apparatus, computer equipment, storage medium, and computer program product for object search based on big data. The technical solutions of the embodiments of the present disclosure comply with the relevant provisions of national laws and regulations regarding the acquisition, storage, use, and processing of data.

[0063] In one embodiment, Figure 1 As shown, a method for object search based on big data is provided. This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0064] Step S101, obtaining multiple objects matching the search term and the names of multiple dimensions of the objects;

[0065] In an embodiment of the present disclosure, a user inputs a search term through a terminal, and after receiving the search term sent by the user, the terminal sends the search term to a server. After receiving the search term sent by the terminal, the server usually searches for multiple objects that match the search term in the index library, and each object also has corresponding names of multiple different dimensions. After finding the matching object, it is also necessary to obtain the names of the multiple different dimensions of each object. In one example, when a user searches for an electronic product, the names of the multiple dimensions of the product may include, but are not limited to, the product title name, product attribute name, product brand name, and other multiple-dimensional names.

[0066] Step S102, matching the first participles in the second participles of the names of the multiple dimensions in order of appearance of the first participles in the search term to obtain multiple participle paths;

[0067] In an embodiment of the present disclosure, after the search term is segmented, the search term can be segmented into multiple first segmentations. The names of the multiple dimensions of each object include second segmentations corresponding to the multiple first segmentations. In one example, the second segmentations can correspond to the multiple first segmentations or to some of the first segmentations in the multiple first segmentations. Matches are performed sequentially from the second segmentations in the names of the multiple dimensions in the order in which the first segmentations appear in the search term. Since the names of the multiple dimensions may contain multiple second segmentations corresponding to the same first segmentation, multiple matching methods are included, and multiple segmentation paths can be obtained after matching.

[0068] Step S103, determining the total weight of each segmentation path in the multiple segmentation paths according to the dimension weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation;

[0069] In the embodiment of the present disclosure, after obtaining multiple word segmentation paths corresponding to each object, it is necessary to determine the total weight corresponding to each word segmentation path. When determining the total weight of each path, first obtain the dimension weight of each second word segmentation according to the dimension in which the second word segmentation is located in the word segmentation path, and then obtain the relationship weight between each second word segmentation and the next second word segmentation according to the relationship between each second word segmentation and the next second word segmentation in the word segmentation path. After obtaining all the dimension weights and relationship weights contained in each word segmentation path, determine the total weight of each word segmentation path according to the weight calculation method.

[0070] In one example, when determining the total weight of each segmentation path, the sum of the dimension weight and the relationship weight corresponding to each path can be used as the total weight of the path. In another example, when the multiple first segmentations all have corresponding second segmentations in the segmentation path, the product of the dimension weight and the relationship weight corresponding to each path can be used as the total weight of the path. In a complete search process from inputting a search term to obtaining a target object, only one method of calculating the total weight is used.

[0071] Step S104 : taking the largest total weight as the correlation between the object and the search term, and determining the object with the largest correlation from the multiple objects as the target object.

[0072] In the disclosed embodiment, after determining the total weights of the multiple paths corresponding to each object, the largest weight among the multiple total weights is determined as the correlation between the object and the search term. After determining the multiple correlations corresponding to the multiple objects corresponding to the search term, the object with the largest correlation is selected as the target object of the search term.

[0073] In one example, after obtaining multiple relevances corresponding to multiple objects, the multiple objects may be sorted from large to small according to the relevance, and the multiple objects may be sent to the user terminal in the sorted order for display.

[0074] In this disclosed embodiment, multiple objects matching a search term and the names of multiple dimensions of each object are first obtained. Multiple paths contained in the names of the multiple dimensions are determined according to the search term. The total weight of each path is calculated according to preset dimension weights and relationship weights. The largest total weight among the multiple paths contained in each object is used as the object's relevance to the search term, and the object with the greatest relevance is used as the target object for the search term. This disclosed embodiment comprehensively considers the fact that the search term's segmentation appears in different locations and dimensions of the product when calculating relevance, thereby improving search accuracy and quality.

[0075] In one embodiment, obtaining the names of multiple objects and multiple dimensions of the objects that match the search term includes:

[0076] Step S201, obtaining multiple first participles of the search term;

[0077] Step S202 : obtaining names of multiple dimensions of an object. If multiple second participles in the name match the multiple first participles, the object is one of the multiple objects that match the search term.

[0078] In an embodiment of the present disclosure, after receiving the search term sent by the user terminal, the search term will be segmented, wherein the segmentation refers to dividing the input keyword into several words. A plurality of first segmentations after the search term segmentation is obtained, and the segmentations in the names of the multiple dimensions of the object in the index library are judged. If the names of the multiple dimensions of the object contain a second segmentation that matches the multiple first segmentations, then the object is one of the objects that match the search term, wherein the method for judging whether the second segmentation matches the first segmentation is generally to judge whether the second segmentation and the first segmentation are the same segmentation. If they are the same segmentation, the second segmentation matches the first segmentation. In one example, the names of the multiple dimensions of the object that matches the search term may contain one or more second segmentations that match the multiple first segmentations. In another example, the names of the multiple dimensions of the object that matches the search term may contain multiple second segmentations that match the same first segmentation.

[0079] In the embodiment of the present disclosure, the first participle of the search term is obtained, and objects matching the search term are determined based on the first participle. The embodiment of the present disclosure can obtain multiple objects matching the search term, thereby performing subsequent weight calculation and correlation confirmation.

[0080] In one embodiment, the names of the multiple dimensions include at least one of the following:

[0081] Title name, category name, logo name.

[0082] In the disclosed embodiment, each object corresponds to a multi-dimensional name, where the multi-dimensional names include but are not limited to title name, category name, and logo name. In one example, the multi-dimensional names may also include names of other dimensions such as color name, style name, and material name.

[0083] In the embodiment of the present disclosure, the names of multiple dimensions are expanded in detail.

[0084] In one embodiment, determining the total weight of each word segmentation path in the multiple word segmentation paths according to the dimension weight of the second word segmentation in the word segmentation path and the relationship weight between the second word segmentation and the next second word segmentation includes:

[0085] Obtaining the dimension weight of the second participle in the word segmentation path and the relationship weight between the second participle and the next second participle, wherein the dimension weight is obtained according to the type of dimension;

[0086] The product of the dimension weight and the relationship weight of the second word in the same word segmentation path is determined as the total weight of the word segmentation path.

[0087] In the embodiment of the present disclosure, when determining the total weight of each word segmentation path based on the dimension weights and relationship weights in the word segmentation path, it is first necessary to obtain the dimension weight corresponding to each second word segmentation in the word segmentation path, wherein the dimension weight is pre-set according to the type of different dimensions, and different dimension weights will correspond to different dimensions depending on the dimensions in which the second word segmentation is located. In addition to the dimension weights, it is also necessary to obtain the relationship weight between the second word segmentation and the next second word segmentation. After obtaining all the dimension weights and relationship weights in the word segmentation path, when the multiple first word segmentations all have corresponding second word segmentations in the word segmentation path, the dimension weights and relationship weights in the same word segmentation path are multiplied, and the product determined is the total weight of the word segmentation path.

[0088] In the embodiment of the present disclosure, the dimension weight and relationship weight of each path are obtained, and the total weight of each path is obtained based on the dimension weight and relationship weight. The embodiment of the present disclosure can obtain the total weight of each path, thereby determining the subsequent target object.

[0089] In one embodiment, a method for obtaining the relationship weight between the second participle and the next second participle includes:

[0090] If the next second participle of the second participle and the second participle are located in the same dimension, the relationship weight between the second participle and the next second participle is determined to be a preset connection weight.

[0091] In the embodiment of the present disclosure, when obtaining the relationship weight between the second participle and the next second participle, it is first necessary to determine whether the second participle and the next second participle are located in the same dimension. If the second participle and the next second participle are located in the same dimension, then the relationship weight between the second participle and the next second participle is a connection weight, wherein the connection weight is a pre-set weight that is associated with the arrangement order of the participles in the name. When the number of participles between the second participle and the next second participle is different, different connection weights usually correspond to them.

[0092] The disclosed embodiments provide a method for determining the relationship weight between a second participle and a subsequent second participle when they are located in the same dimension. The disclosed embodiments can determine the relationship weight between a second participle and a subsequent second participle when they are located in the same dimension, taking into account the discontinuity of the participles in the dimension name, thereby improving the accuracy of the final total weight and thus the accuracy of the correlation calculation.

[0093] In one embodiment, a method for obtaining the relationship weight between the second participle and the next second participle includes:

[0094] If the next second participle of the second participle and the second participle are located in different dimensions, the relationship weight between the second participle and the next second participle is determined as a preset transfer weight.

[0095] In an embodiment of the present disclosure, when obtaining the relationship weight between a second participle and the next second participle, it is first necessary to determine whether the second participle and the next second participle are located in the same dimension. If the second participle and the next second participle are located in different dimensions, the relationship weight between the second participle and the next second participle is a transfer weight, wherein the transfer weight is a preset weight corresponding to when two adjacent second participles are located in different dimensions. When the second participle and the next second participle are located in different dimensions, the dimension between the two is transferred, and therefore the relationship weight between the two is a transfer weight.

[0096] The disclosed embodiments provide a method for determining the relationship weight between a second participle and a subsequent second participle when the second participle and the subsequent second participle are located in different dimensions. The disclosed embodiments can determine the relationship weight between the second participle and the subsequent second participle when the second participle and the subsequent second participle are located in different dimensions. This takes into account the different dimensions of the participles, improves the accuracy of the final total weight, and thus improves the accuracy of the correlation calculation.

[0097] In one embodiment, taking the largest total weight as the relevance between the object and the search term, and determining the object with the largest relevance from the multiple objects as the target object, includes:

[0098] comparing the total weight of each of the multiple segmentation paths, and taking the largest total weight as the relevance between the object and the search term;

[0099] A plurality of correlations corresponding to the plurality of objects are determined, and an object with the greatest correlation among the plurality of objects is used as a target object.

[0100] In the disclosed embodiment, after obtaining the multiple total weights corresponding to the multiple paths for each object, the multiple total weights for each object are compared to obtain the maximum total weight for each object. This maximum total weight is used as the correlation between the object and the search term. After determining the correlation for each object, the object with the greatest correlation is used as the target object for the search term.

[0101] After obtaining the weight of each path, the disclosed embodiment can determine the relevance of each object to the search term, and determine the object with the greatest relevance as the target object of the search term. The disclosed embodiment can determine the target object corresponding to the search term based on the obtained weight information, thereby improving search accuracy and the quality of search results.

[0102] Figure 3is a schematic diagram showing a correlation calculation method according to an exemplary embodiment, with reference to Figure 3 As shown, assuming the search keyword is ABC, the search keyword is segmented to obtain three terms A, B, and C. Search in the index library, and product A is one of the objects that matches the search keyword. The title of product A is ABFC, the category name of product A is ZBL, and the brand name of product A is PIYC. The dimension weights of title, category, and brand are preset to be 1, 0.9, and 0.8 respectively; when two segmentations are adjacent, the connection weight is 1, and when there is one keyword between two adjacent segmentations, the connection weight is 0.9; the transfer weight is 0.8. The keyword term ABC is found in each dimension of the product as follows Figure 3 The two paths shown in , where W1, W2, W3 are dimension weights, W X1 、W X2 is the connection weight, W Z is the transfer weight. Then the relevance of the first path is W1×W X1 ×W1×W X2 ×W1=0.9; the correlation of the second path is W1×W Z ×W2×W Z × W3 = 0.46. Therefore, the total weight of the first path is greater than the total weight of the second path. The total weight of the first path is taken as the relevance score between the search keyword and product A.

[0103] It should be understood that although the steps of the flowcharts in the accompanying drawings are shown sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the accompanying drawings may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times. The order of execution of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with other steps or at least a portion of steps or stages in other steps.

[0104] Based on the same inventive concept, the embodiments of the present disclosure also provide a search device for implementing the aforementioned search method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more search device embodiments provided below can be found in the above-mentioned limitations of the search method and will not be repeated here.

[0105] In one embodiment, Figure 4 As shown, a device for searching objects based on big data is provided, comprising:

[0106] An acquisition module, configured to acquire a plurality of objects matching a search term and names of a plurality of dimensions of the objects;

[0107] a matching module, configured to sequentially match the first segmented words in the second segmented words of the names of the multiple dimensions according to the order in which the first segmented words appear in the search term, to obtain multiple segmented word paths;

[0108] A first determining module is configured to determine a total weight of each word segmentation path in the plurality of word segmentation paths according to a dimension weight of a second word segmentation in the word segmentation path and a relationship weight between the second word segmentation and a next second word segmentation;

[0109] The second determining module is configured to take the largest total weight as the correlation between the object and the search term, and determine the object with the largest correlation from the multiple objects as the target object.

[0110] In one embodiment, the acquisition module includes:

[0111] A first acquisition submodule, configured to acquire a plurality of first participles of a search term;

[0112] The second acquisition submodule is used to acquire the names of multiple dimensions of the object. If there are multiple second participles in the name that match the multiple first participles, the object is one of the multiple objects that match the search term.

[0113] In one embodiment, the names of the multiple dimensions include at least one of the following:

[0114] Title name, category name, logo name.

[0115] In one embodiment, the first determining module includes:

[0116] An acquisition module, configured to acquire a dimension weight of a second word segmentation in a word segmentation path and a relationship weight between the second word segmentation and a next second word segmentation, wherein the dimension weight is obtained according to a dimension type setting;

[0117] The determination module is used to respectively determine the product of the dimension weight and the relationship weight of the second word in the same word segmentation path as the total weight of the word segmentation path.

[0118] In one embodiment, the module for obtaining the relationship weight between the second participle and the next second participle includes:

[0119] The determining module is configured to determine, if the next second participle of the second participle and the second participle are located in the same dimension, a relationship weight between the second participle and the next second participle as a preset connection weight.

[0120] In one embodiment, the module for obtaining the relationship weight between the second participle and the next second participle includes:

[0121] A determination module is configured to determine, if the next second participle of the second participle and the second participle are located in different dimensions, a relationship weight between the second participle and the next second participle as a preset transfer weight.

[0122] In one embodiment, the second determining module includes:

[0123] a comparison module, configured to compare the total weight of each segmentation path in the plurality of segmentation paths, and take the largest total weight as the relevance between the object and the search term;

[0124] The determination module is configured to determine a plurality of correlations corresponding to the plurality of objects, and select an object with the greatest correlation among the plurality of objects as a target object.

[0125] Each module in the above-mentioned search device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0126] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store index library data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for object search based on big data is implemented.

[0127] Those skilled in the art will understand that Figure 5 The structure shown in the figure is merely a block diagram of a portion of the structure related to the embodiment of the present disclosure, and does not constitute a limitation on the computer device to which the embodiment of the present disclosure is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0128] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0129] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0130] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0131] 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 the embodiments of the present disclosure are all information and data authorized by the user or fully authorized by all parties.

[0132] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in the embodiments of the present disclosure may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in the embodiments of the present disclosure may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in each embodiment provided in the embodiments of the present disclosure may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but are not limited to these.

[0133] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0134] The above-described embodiments merely represent several implementation methods of the embodiments of the present disclosure. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patents of the embodiments of the present disclosure. It should be noted that a person skilled in the art can make several modifications and improvements without departing from the concept of the embodiments of the present disclosure, and these modifications and improvements fall within the scope of protection of the embodiments of the present disclosure. Therefore, the scope of protection of the embodiments of the present disclosure shall be subject to the appended claims.

Claims

1. A method for object search based on big data, characterized in that: The method comprises: Obtaining names of multiple objects and multiple dimensions of the objects that match the search term; According to the order in which the first participle in the search term appears, the first participle is sequentially matched with the second participles of the names of the multiple dimensions to obtain multiple participle paths; Determining the total weight of each segmentation path in the multiple segmentation paths according to the dimension weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation; determining the total weight of each segmentation path in the multiple segmentation paths according to the dimension weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation, including: obtaining the dimension weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation, wherein the dimension weight is obtained according to the type of dimension setting; respectively determining the product of the dimension weight and the relationship weight of the second segmentation in the same segmentation path as the total weight of the segmentation path; The method for obtaining the relationship weight between the second participle and the next second participle includes: If the next second participle of the second participle and the second participle are located in the same dimension, the relationship weight between the second participle and the next second participle is determined to be a preset connection weight; If the next second participle of the second participle and the second participle are located in different dimensions, the relationship weight between the second participle and the next second participle is determined to be a preset transfer weight; The largest total weight is used as the relevance between the object and the search term, and the object with the largest relevance is determined from the multiple objects as the target object.

2. The method according to claim 1, characterized in that The obtaining of multiple objects matching the search term and the names of multiple dimensions of the objects includes: Get multiple first participles of the search term; The names of multiple dimensions of the object are obtained. If multiple second participles in the name match the multiple first participles, the object is one of the multiple objects that match the search term.

3. The method according to claim 1, characterized in that The names of the multiple dimensions include at least one of the following: Title name, category name, logo name.

4. The method according to claim 1, wherein The step of taking the largest total weight as the relevance between the object and the search term, and determining the object with the largest relevance from the multiple objects as the target object, includes: comparing the total weight of each of the multiple segmentation paths, and taking the largest total weight as the relevance between the object and the search term; A plurality of correlations corresponding to the plurality of objects is determined, and an object with the greatest correlation among the plurality of objects is used as a target object.

5. An object search device based on big data, characterized in that: The device comprises: An acquisition module, configured to acquire a plurality of objects matching a search term and names of a plurality of dimensions of the objects; a matching module, configured to sequentially match the first segmented words in the second segmented words of the names of the multiple dimensions according to the order in which the first segmented words appear in the search term, to obtain multiple segmented word paths; a first determining module, configured to determine the total weight of each segmentation path in the multiple segmentation paths based on the dimension weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation; the determining the total weight of each segmentation path in the multiple segmentation paths based on the dimension weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation comprises: obtaining the dimension weight of the second segmentation in the segmentation path and the relationship weight between the second segmentation and the next second segmentation, wherein the dimension weight is obtained according to the type of dimension; determining the product of the dimension weight and the relationship weight of the second segmentation in the same segmentation path as the total weight of the segmentation path; obtaining the relationship weight between the second segmentation and the next second segmentation comprises: if the next second segmentation of the second segmentation and the second segmentation are in the same dimension, then the relationship weight between the second segmentation and the next second segmentation is determined as a preset connection weight; if the next second segmentation of the second segmentation and the second segmentation are in different dimensions, then the relationship weight between the second segmentation and the next second segmentation is determined as a preset transfer weight; The second determining module is configured to take the largest total weight as the correlation between the object and the search term, and determine the object with the largest correlation from the multiple objects as the target object.

6. The device according to claim 5, characterized in that The acquisition module includes: A first acquisition submodule, configured to acquire a plurality of first participles of a search term; The second acquisition submodule is used to acquire the names of multiple dimensions of the object. If there are multiple second participles in the name that match the multiple first participles, the object is one of the multiple objects that match the search term.

7. The device according to claim 5, characterized in that The names of the multiple dimensions include at least one of the following: Title name, category name, logo name.

8. The device according to claim 5, characterized in that The second determining module includes: a comparison module, configured to compare the total weight of each segmentation path in the plurality of segmentation paths, and take the largest total weight as the relevance between the object and the search term; The determination module is configured to determine a plurality of correlations corresponding to the plurality of objects, and select an object with the greatest correlation among the plurality of objects as a target object.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the search method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the search method according to any one of claims 1 to 4 are implemented.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the search method according to any one of claims 1 to 4 are implemented.

Images